{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "dc6fbe16",
   "metadata": {
    "id": "dc6fbe16"
   },
   "source": [
    "**Projet UE8 : prédire le prix des terrains à bâtir dans les Alpes du Sud (04 et 05)**\n",
    "\n",
    "*Structure et code repris du notebook du cours `End_to_end_machine_learning_project_V2.ipynb` (A. Géron, *Hands-On Machine Learning with Scikit-Learn & TensorFlow*, O'Reilly, 2019), adaptés aux données DVF.*\n",
    "\n",
    "*Objectif : prédire le prix au m² d'un **terrain à bâtir** dans les Alpes-de-Haute-Provence (04) et les Hautes-Alpes (05), à partir de sa surface, de sa localisation et du relief, avec les ventes DVF de 2014 à 2025. Zoom sur les Hautes-Alpes. Le code reste paramétrable (autres départements alpins, maisons) mais seuls les terrains du 04 et du 05 sont étudiés ici.*\n",
    "\n",
    "*Usage visé : donner un ordre de grandeur du prix d'un terrain, par exemple pour un constructeur de maisons des Hautes-Alpes qui aide ses clients à cadrer leur budget.*\n",
    "\n",
    "| Cours (Californie) | Ce projet (Alpes) |\n",
    "|---|---|\n",
    "| 1 ligne = 1 quartier | 1 ligne = 1 vente (mutation DVF) |\n",
    "| Label : `median_house_value` | Label : `prix_m2` en euros constants 2025 |\n",
    "| `ocean_proximity` (texte) | `code_departement`, type de vente, intercommunalité (texte) |\n",
    "| Split stratifié sur `income_cat` | Split stratifié sur la surface (variable la plus liée au prix) |\n",
    "| Carte `california.png` | Contours des départements (GeoJSON) + carte interactive folium |\n",
    "\n",
    "Plan : données et nettoyage, exploration, préparation, modèles du cours (régression linéaire, arbre, Random Forest, SVM, Grid Search, test), puis une partie « Au-delà du cours » (prix en log, zoom 05, réseau neuronal, carte interactive, contrôle des sources, diagnostic des erreurs, test des stations de ski) et une conclusion."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4d1a02a3",
   "metadata": {
    "id": "4d1a02a3"
   },
   "source": [
    "# Paramètres du projet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "7260addf",
   "metadata": {
    "id": "7260addf",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537318501,
     "user_tz": -120,
     "elapsed": 4,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "# Type de bien étudié : \"terrain\" (terrains à bâtir) ou \"maison\"\n",
    "TYPE_BIEN = \"terrain\"\n",
    "\n",
    "# Départements alpins\n",
    "DEPARTEMENTS = [\"04\", \"05\"]\n",
    "\n",
    "# Source des ventes :\n",
    "#   \"koumoul\" = base complète 2014-2025 (copie cumulée du DVF géolocalisé Etalab, data.ademe.fr)\n",
    "#   \"etalab\"  = DVF géolocalisé officiel, 5 dernières années seulement (2021-2025)\n",
    "SOURCE = \"koumoul\"\n",
    "ANNEES = list(range(2014, 2026)) if SOURCE == \"koumoul\" else [2021, 2022, 2023, 2024, 2025]\n",
    "\n",
    "# Variables géographiques (appels réseau, plus longs au 1er lancement puis en cache)\n",
    "GET_ALTITUDE = True      # altitude (API IGN)\n",
    "GET_PENTE = True         # pente et exposition (API IGN, 4 points autour de chaque bien)\n",
    "GET_COURS_EAU = True     # distance au cours d'eau le plus proche (BD TOPO IGN)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e7915694",
   "metadata": {
    "id": "e7915694"
   },
   "source": [
    "# Google Drive Working Directory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a3343363",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "a3343363",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537333346,
     "user_tz": -120,
     "elapsed": 14843,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "6c6af8e5-72c7-4728-a72f-d8030dca6d53"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Mounted at /content/drive\n"
     ]
    }
   ],
   "source": [
    "from google.colab import drive\n",
    "drive.mount('/content/drive')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "3d72dce2",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 36
    },
    "id": "3d72dce2",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537333347,
     "user_tz": -120,
     "elapsed": 6,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "5764e66c-0c4a-4583-b581-9fce0aa1da3c"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "'/content'"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "string"
      }
     },
     "metadata": {},
     "execution_count": 3
    }
   ],
   "source": [
    "import os\n",
    "os.getcwd() # Current Working directory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "834fad5b",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 36
    },
    "id": "834fad5b",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537333944,
     "user_tz": -120,
     "elapsed": 599,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "3396d664-d2a0-49f3-89ee-ef4bcddfdc4a"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "'/content/drive/MyDrive/Colab Notebooks/Projet Habitat 05'"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "string"
      }
     },
     "metadata": {},
     "execution_count": 4
    }
   ],
   "source": [
    "# Create Working Directory if necessary\n",
    "\n",
    "PROJECT_ROOT_DIR = \"/content/drive/MyDrive/Colab Notebooks/Projet Habitat 05\"\n",
    "\n",
    "os.makedirs(PROJECT_ROOT_DIR, exist_ok=True)\n",
    "\n",
    "# Change the current working directory\n",
    "\n",
    "os.chdir(PROJECT_ROOT_DIR)\n",
    "\n",
    "# Sub directories (same as the course)\n",
    "for path in [\"./data/\", \"./images/\", \"./models/\", \"./library/\"]:\n",
    "    os.makedirs(path, exist_ok=True)\n",
    "\n",
    "os.getcwd() # Current Working directory"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "47201b88",
   "metadata": {
    "id": "47201b88"
   },
   "source": [
    "# Setup"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bc582c3f",
   "metadata": {
    "id": "bc582c3f"
   },
   "source": [
    "On importe les modules courants, on règle l'affichage des graphiques et on prépare une fonction pour sauvegarder les figures (identique au cours)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "32301355",
   "metadata": {
    "id": "32301355",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537334746,
     "user_tz": -120,
     "elapsed": 800,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "# Common imports\n",
    "import sys\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import requests\n",
    "import os\n",
    "\n",
    "# To plot pretty figures\n",
    "%matplotlib inline\n",
    "import matplotlib as mpl\n",
    "import matplotlib.pyplot as plt\n",
    "mpl.rc('axes', labelsize=14)\n",
    "mpl.rc('xtick', labelsize=12)\n",
    "mpl.rc('ytick', labelsize=12)\n",
    "\n",
    "# Where to save the figures\n",
    "PROJECT_ROOT_DIR = \".\"\n",
    "CHAPTER_ID = \"projet_alpes_\" + TYPE_BIEN\n",
    "IMAGES_PATH = os.path.join(PROJECT_ROOT_DIR, \"images\", CHAPTER_ID)\n",
    "os.makedirs(IMAGES_PATH, exist_ok=True)\n",
    "\n",
    "def save_fig(fig_id, tight_layout=True, fig_extension=\"png\", resolution=300):\n",
    "    path = os.path.join(IMAGES_PATH, fig_id + \".\" + fig_extension)\n",
    "    print(\"Saving figure\", fig_id)\n",
    "    if tight_layout:\n",
    "        plt.tight_layout()\n",
    "    plt.savefig(path, format=fig_extension, dpi=resolution)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5bc92a5c",
   "metadata": {
    "id": "5bc92a5c"
   },
   "source": [
    "We import Machine Learning Package Scikit-Learn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "dcbaf5eb",
   "metadata": {
    "id": "dcbaf5eb",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537335488,
     "user_tz": -120,
     "elapsed": 740,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "# Import Machine Learnning Package Scikit-Learn\n",
    "import sklearn"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9a14b4d2",
   "metadata": {
    "id": "9a14b4d2"
   },
   "source": [
    "# Get the Data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9c7f4b91",
   "metadata": {
    "id": "9c7f4b91"
   },
   "source": [
    "## Load the Data : DVF (ventes immobilières)\n",
    "\n",
    "Deux sources possibles (paramètre `SOURCE`) :\n",
    "- **koumoul** (par défaut) : base complète **2014-2025**, copie cumulée du DVF géolocalisé Etalab, via l'API data.ademe.fr / Koumoul (≈ 310 000 lignes pour le 04 et le 05, quelques minutes au premier lancement) ;\n",
    "- **etalab** : DVF géolocalisé officiel (data.gouv.fr), 2021-2025 uniquement.\n",
    "\n",
    "Les données sont téléchargées une seule fois puis gardées dans `./data/` (cache). Un contrôle Koumoul / Etalab est fait en fin de notebook."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ff3cb54b",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "ff3cb54b",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537343325,
     "user_tz": -120,
     "elapsed": 7835,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "4ca58c08-754e-4bcd-e2e9-7302d18a0684"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "code_departement\n",
      "04    140456\n",
      "05    169250\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "DVF_URL = \"https://files.data.gouv.fr/geo-dvf/latest/csv/{annee}/departements/{dep}.csv.gz\"\n",
    "KOUMOUL_LINES = \"https://koumoul.com/data-fair/api/v1/datasets/demandes-de-valeurs-foncieres-france/lines\"\n",
    "\n",
    "# Cache : un fichier par source, département et année, dans data/dvf/\n",
    "CACHE_DIR = os.path.join(\"data\", \"dvf\")\n",
    "os.makedirs(CACHE_DIR, exist_ok=True)\n",
    "\n",
    "COLONNES = [\"id_mutation\", \"date_mutation\", \"nature_mutation\", \"valeur_fonciere\",\n",
    "            \"code_commune\", \"nom_commune\", \"code_departement\", \"id_parcelle\",\n",
    "            \"type_local\", \"surface_reelle_bati\", \"nombre_pieces_principales\",\n",
    "            \"code_nature_culture\", \"surface_terrain\", \"longitude\", \"latitude\"]\n",
    "TYPES = {\"code_commune\": str, \"code_departement\": str, \"id_parcelle\": str,\n",
    "         \"code_nature_culture\": str, \"id_mutation\": str}\n",
    "\n",
    "def load_etalab(dep, annee):\n",
    "    url = DVF_URL.format(annee=annee, dep=dep)\n",
    "    print(\"Téléchargement Etalab\", dep, annee)\n",
    "    return pd.read_csv(url, usecols=COLONNES, dtype=TYPES, low_memory=False)\n",
    "\n",
    "def load_koumoul(dep, annee):\n",
    "    \"\"\"Toutes les lignes d'un département et d'une année, par pages de 10 000 (API data-fair).\"\"\"\n",
    "    params = {\"size\": 10000, \"select\": \",\".join(COLONNES),\n",
    "              \"qs\": f'code_departement:\"{dep}\" AND annee:{annee}'}\n",
    "    r = requests.get(KOUMOUL_LINES, params=params, timeout=120).json()\n",
    "    lignes = r[\"results\"]\n",
    "    while r.get(\"next\") and len(r[\"results\"]) > 0:\n",
    "        r = requests.get(r[\"next\"], timeout=120).json()\n",
    "        lignes += r[\"results\"]\n",
    "    print(\"Téléchargement Koumoul\", dep, annee, \":\", len(lignes), \"lignes\")\n",
    "    return pd.DataFrame(lignes).reindex(columns=COLONNES)\n",
    "\n",
    "def load_morceau(dep, annee, source=SOURCE):\n",
    "    \"\"\"Lit le morceau en cache s'il existe, sinon le télécharge et l'enregistre.\"\"\"\n",
    "    chemin = os.path.join(CACHE_DIR, f\"{source}_{dep}_{annee}.csv.gz\")\n",
    "    if os.path.exists(chemin):\n",
    "        return pd.read_csv(chemin, dtype=TYPES, low_memory=False)\n",
    "    loader = load_koumoul if source == \"koumoul\" else load_etalab\n",
    "    morceau = loader(dep, annee)\n",
    "    morceau.to_csv(chemin, index=False)\n",
    "    return morceau\n",
    "\n",
    "def load_dvf_data():\n",
    "    morceaux = [load_morceau(dep, annee) for dep in DEPARTEMENTS for annee in ANNEES]\n",
    "    return pd.concat(morceaux, ignore_index=True)\n",
    "\n",
    "dvf = load_dvf_data()\n",
    "\n",
    "# Colonnes numériques forcées en nombres (sécurité)\n",
    "for c in [\"valeur_fonciere\", \"surface_reelle_bati\", \"nombre_pieces_principales\", \"surface_terrain\", \"longitude\", \"latitude\"]:\n",
    "    dvf[c] = pd.to_numeric(dvf[c], errors=\"coerce\")\n",
    "\n",
    "print(dvf[\"code_departement\"].value_counts().sort_index())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "4c6da8fe",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "4c6da8fe",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537343368,
     "user_tz": -120,
     "elapsed": 40,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "61c3b606-9ded-4357-e259-4b55b0ce3f73"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "(309706, 15)"
      ]
     },
     "metadata": {},
     "execution_count": 8
    }
   ],
   "source": [
    "dvf.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3ac964d6",
   "metadata": {
    "id": "3ac964d6"
   },
   "source": [
    "## Build one row per sale (mutation)\n",
    "\n",
    "Dans DVF, une vente (`id_mutation`) peut occuper plusieurs lignes (plusieurs parcelles, plusieurs natures de culture, plusieurs locaux).\n",
    "On regroupe pour obtenir **1 ligne = 1 vente**, puis on ne garde que les ventes « simples » :\n",
    "- **terrain** : ventes qui contiennent au moins une parcelle « terrain à bâtir » (code `AB`). Chaque vente reçoit un type (`type_mixite`) : AB seul, AB + terrain non constructible, AB + dépendance, AB + maison, etc. Seuls les types où le prix ne porte que sur le terrain sont gardés à l'étape suivante ;\n",
    "- **maison** : une seule maison (dépendances acceptées), aucun appartement ni local commercial."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "c9ae60f3",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "c9ae60f3",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537344040,
     "user_tz": -120,
     "elapsed": 670,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "7e11e8aa-7ae1-4756-ef39-0394168feee9"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "(111749, 15)"
      ]
     },
     "metadata": {},
     "execution_count": 9
    }
   ],
   "source": [
    "NATURES = [\"Vente\", \"Vente terrain à bâtir\"]\n",
    "\n",
    "d = dvf[dvf[\"nature_mutation\"].isin(NATURES)].copy()\n",
    "d[\"is_AB\"] = d[\"code_nature_culture\"] == \"AB\"\n",
    "d[\"is_non_AB\"] = d[\"code_nature_culture\"].notna() & ~d[\"is_AB\"]\n",
    "d[\"is_maison\"] = d[\"type_local\"] == \"Maison\"\n",
    "d[\"is_autre_local\"] = d[\"type_local\"].isin([\"Appartement\", \"Local industriel. commercial ou assimilé\"])\n",
    "\n",
    "# Informations générales de chaque vente\n",
    "ventes = d.groupby(\"id_mutation\").agg(\n",
    "    date_mutation=(\"date_mutation\", \"first\"),\n",
    "    valeur_fonciere=(\"valeur_fonciere\", \"first\"),\n",
    "    code_commune=(\"code_commune\", \"first\"),\n",
    "    nom_commune=(\"nom_commune\", \"first\"),\n",
    "    code_departement=(\"code_departement\", \"first\"),\n",
    "    longitude=(\"longitude\", \"mean\"),\n",
    "    latitude=(\"latitude\", \"mean\"),\n",
    "    nb_lignes_AB=(\"is_AB\", \"sum\"),\n",
    "    nb_lignes_non_AB=(\"is_non_AB\", \"sum\"),\n",
    "    nb_locaux_autres=(\"is_autre_local\", \"sum\"),\n",
    "    nb_lignes_local=(\"type_local\", \"count\"),\n",
    ")\n",
    "\n",
    "# Surface de terrain : une seule fois par parcelle et par nature de culture\n",
    "parcelles = d.drop_duplicates([\"id_mutation\", \"id_parcelle\", \"code_nature_culture\"])\n",
    "ventes[\"surface_terrain\"] = parcelles.groupby(\"id_mutation\")[\"surface_terrain\"].sum()\n",
    "\n",
    "# Maisons : nombre de maisons distinctes, surface bâtie et pièces\n",
    "maisons = d[d[\"is_maison\"]].drop_duplicates([\"id_mutation\", \"id_parcelle\", \"surface_reelle_bati\"])\n",
    "ventes[\"nb_maisons\"] = maisons.groupby(\"id_mutation\").size()\n",
    "ventes[\"surface_bati\"] = maisons.groupby(\"id_mutation\")[\"surface_reelle_bati\"].first()\n",
    "ventes[\"nb_pieces\"] = maisons.groupby(\"id_mutation\")[\"nombre_pieces_principales\"].first()\n",
    "ventes[\"nb_maisons\"] = ventes[\"nb_maisons\"].fillna(0)\n",
    "\n",
    "ventes.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "8d54fb79",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "8d54fb79",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537345242,
     "user_tz": -120,
     "elapsed": 1177,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "20e31ebf-bb99-4f53-ed22-64326b866203"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "terrain : 5865 ventes\n",
      "type_mixite\n",
      "AB seul                           3560\n",
      "AB + terrain non constructible    1169\n",
      "AB + maison                        940\n",
      "AB + local pro                      97\n",
      "AB + appartement                    77\n",
      "AB + dépendance                     22\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "# Détail des locaux et de la surface constructible de chaque vente\n",
    "locaux = d[d[\"type_local\"].notna()].drop_duplicates([\"id_mutation\", \"id_parcelle\", \"type_local\", \"surface_reelle_bati\"])\n",
    "types_locaux = pd.crosstab(locaux[\"id_mutation\"], locaux[\"type_local\"])\n",
    "for t in [\"Maison\", \"Appartement\", \"Dépendance\", \"Local industriel. commercial ou assimilé\"]:\n",
    "    ventes[\"nb_\" + t] = types_locaux[t].reindex(ventes.index).fillna(0) if t in types_locaux else 0\n",
    "ventes[\"surface_AB\"] = parcelles[parcelles[\"is_AB\"]].groupby(\"id_mutation\")[\"surface_terrain\"].sum()\n",
    "ventes[\"surface_AB\"] = ventes[\"surface_AB\"].fillna(0)\n",
    "\n",
    "if TYPE_BIEN == \"terrain\":\n",
    "    # Toutes les ventes contenant un terrain à bâtir, ventes mixtes comprises (flaguées)\n",
    "    biens = ventes[ventes[\"nb_lignes_AB\"] > 0].copy()\n",
    "    conditions = [biens[\"nb_Maison\"] > 0,\n",
    "                  biens[\"nb_Appartement\"] > 0,\n",
    "                  biens[\"nb_Local industriel. commercial ou assimilé\"] > 0,\n",
    "                  biens[\"nb_Dépendance\"] > 0,\n",
    "                  biens[\"nb_lignes_non_AB\"] > 0]\n",
    "    choix = [\"AB + maison\", \"AB + appartement\", \"AB + local pro\", \"AB + dépendance\",\n",
    "             \"AB + terrain non constructible\"]\n",
    "    biens[\"type_mixite\"] = np.select(conditions, choix, default=\"AB seul\")\n",
    "    biens[\"surface\"] = biens[\"surface_terrain\"]                       # surface totale vendue\n",
    "    biens[\"part_AB\"] = biens[\"surface_AB\"] / biens[\"surface_terrain\"]  # part constructible\n",
    "else:\n",
    "    mask = (ventes[\"nb_maisons\"] == 1) & (ventes[\"nb_locaux_autres\"] == 0)\n",
    "    biens = ventes[mask].copy()\n",
    "    biens[\"surface\"] = biens[\"surface_bati\"]\n",
    "\n",
    "biens[\"date_mutation\"] = pd.to_datetime(biens[\"date_mutation\"])\n",
    "biens[\"annee\"] = biens[\"date_mutation\"].dt.year\n",
    "biens[\"prix_m2_courant\"] = biens[\"valeur_fonciere\"] / biens[\"surface\"]\n",
    "\n",
    "print(TYPE_BIEN, \":\", len(biens), \"ventes\")\n",
    "if TYPE_BIEN == \"terrain\":\n",
    "    print(biens[\"type_mixite\"].value_counts())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "50aac7c3",
   "metadata": {
    "id": "50aac7c3"
   },
   "source": [
    "## Inflation : prix en euros constants 2025\n",
    "\n",
    "Pour comparer 2014 et 2025, on corrige l'inflation avec l'indice des prix à la consommation (Insee, moyennes annuelles, vérifiées sur insee.fr le 09/10/2026 : +0,9 % en 2025).\n",
    "C'est l'inflation générale : elle ne suit pas forcément l'évolution propre des prix du foncier."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "c5337bc4",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 460
    },
    "id": "c5337bc4",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537345283,
     "user_tz": -120,
     "elapsed": 35,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "f644c8b5-89de-4559-c3bf-0223a5a4f71c"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "2014    1.207898\n",
       "2015    1.207898\n",
       "2016    1.205487\n",
       "2017    1.193552\n",
       "2018    1.172448\n",
       "2019    1.159691\n",
       "2020    1.153922\n",
       "2021    1.135750\n",
       "2022    1.079610\n",
       "2023    1.029180\n",
       "2024    1.009000\n",
       "2025    1.000000\n",
       "dtype: float64"
      ],
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>1.207898</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2015</th>\n",
       "      <td>1.207898</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016</th>\n",
       "      <td>1.205487</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017</th>\n",
       "      <td>1.193552</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018</th>\n",
       "      <td>1.172448</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019</th>\n",
       "      <td>1.159691</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020</th>\n",
       "      <td>1.153922</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2021</th>\n",
       "      <td>1.135750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022</th>\n",
       "      <td>1.079610</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2023</th>\n",
       "      <td>1.029180</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024</th>\n",
       "      <td>1.009000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2025</th>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><br><label><b>dtype:</b> float64</label>"
      ]
     },
     "metadata": {},
     "execution_count": 11
    }
   ],
   "source": [
    "# Inflation annuelle moyenne en France (IPC Insee, en %), vérifiée sur insee.fr le 09/10/2026\n",
    "INFLATION = {2014: 0.5, 2015: 0.0, 2016: 0.2, 2017: 1.0, 2018: 1.8, 2019: 1.1, 2020: 0.5,\n",
    "             2021: 1.6, 2022: 5.2, 2023: 4.9, 2024: 2.0, 2025: 0.9}\n",
    "\n",
    "# Indice base 2025 = 1 : un euro de l'année a vaut combien d'euros de 2025 ?\n",
    "coef = {2025: 1.0}\n",
    "for a in range(2024, min(INFLATION) - 1, -1):\n",
    "    coef[a] = coef[a + 1] * (1 + INFLATION[a + 1] / 100)\n",
    "\n",
    "biens[\"coef_inflation\"] = biens[\"annee\"].map(coef)\n",
    "biens[\"prix_m2\"] = biens[\"prix_m2_courant\"] * biens[\"coef_inflation\"]\n",
    "pd.Series(coef).sort_index()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4aef72a9",
   "metadata": {
    "id": "4aef72a9"
   },
   "source": [
    "## Remove outliers (prix aberrants)\n",
    "\n",
    "Ventes à 1 €, ventes en bloc, erreurs de saisie, bâti caché dans le prix : le nettoyage se fait en cinq étapes (les comptes s'affichent sous la cellule).\n",
    "1. On garde les types de vente où le prix ne porte que sur le terrain : AB seul, AB + terrain non constructible, AB + dépendance.\n",
    "2. Surface entre 150 m² et 2 ha.\n",
    "3. Prix plancher de 5 €/m² (en dessous : terre agricole ou vente symbolique).\n",
    "4. Prix incohérent avec la commune : plus de 3 fois le prix médian de la commune (communes d'au moins 5 ventes). Ce sont souvent des maisons neuves vendues avant leur inscription au cadastre : DVF les classe en « terrain » alors que le prix comprend la construction. Les ventes retirées sont gardées dans `data/ventes_retirees_prix_incoherent.csv` pour vérification.\n",
    "5. Enfin, 1 % des prix les plus bas et 1 % des plus hauts dans chaque type de vente."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "fcf65b7b",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 279
    },
    "id": "fcf65b7b",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537345559,
     "user_tz": -120,
     "elapsed": 275,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "fa63e7a5-9382-4f20-bffe-0d1ba7d91db6"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "5865 ventes au départ\n",
      "4751 ventes après sélection des types (prix = terrain seul)\n",
      "4607 ventes après filtre des surfaces\n",
      "4463 ventes après prix plancher\n",
      "4323 ventes après retrait des prix incohérents avec la commune (140 retirées, liste dans data/ventes_retirees_prix_incoherent.csv)\n",
      "4233 ventes après nettoyage\n"
     ]
    },
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "                                 count   mean    std   min   25%    50%  \\\n",
       "type_mixite                                                               \n",
       "AB + dépendance                   17.0  141.0   78.0  45.0  77.0  123.0   \n",
       "AB + terrain non constructible  1004.0  110.0  112.0   8.0  45.0   75.0   \n",
       "AB seul                         3212.0  130.0   71.0  16.0  76.0  121.0   \n",
       "\n",
       "                                  75%    max  \n",
       "type_mixite                                   \n",
       "AB + dépendance                 193.0  304.0  \n",
       "AB + terrain non constructible  128.0  785.0  \n",
       "AB seul                         171.0  412.0  "
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-1d65f16c-9857-41a7-a938-8f6c43ef0ad2\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>type_mixite</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>AB + dépendance</th>\n",
       "      <td>17.0</td>\n",
       "      <td>141.0</td>\n",
       "      <td>78.0</td>\n",
       "      <td>45.0</td>\n",
       "      <td>77.0</td>\n",
       "      <td>123.0</td>\n",
       "      <td>193.0</td>\n",
       "      <td>304.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AB + terrain non constructible</th>\n",
       "      <td>1004.0</td>\n",
       "      <td>110.0</td>\n",
       "      <td>112.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>45.0</td>\n",
       "      <td>75.0</td>\n",
       "      <td>128.0</td>\n",
       "      <td>785.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AB seul</th>\n",
       "      <td>3212.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>71.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>76.0</td>\n",
       "      <td>121.0</td>\n",
       "      <td>171.0</td>\n",
       "      <td>412.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-1d65f16c-9857-41a7-a938-8f6c43ef0ad2')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-1d65f16c-9857-41a7-a938-8f6c43ef0ad2 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-1d65f16c-9857-41a7-a938-8f6c43ef0ad2');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "summary": "{\n  \"name\": \"biens\",\n  \"rows\": 3,\n  \"fields\": [\n    {\n      \"column\": \"type_mixite\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"AB + d\\u00e9pendance\",\n          \"AB + terrain non constructible\",\n          \"AB seul\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"count\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1635.922675434264,\n        \"min\": 17.0,\n        \"max\": 3212.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          17.0,\n          1004.0,\n          3212.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"mean\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 15.716233645501712,\n        \"min\": 110.0,\n        \"max\": 141.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          141.0,\n          110.0,\n          130.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"std\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 21.93171219946131,\n        \"min\": 71.0,\n        \"max\": 112.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          78.0,\n          112.0,\n          71.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"min\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 19.467922333931785,\n        \"min\": 8.0,\n        \"max\": 45.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          45.0,\n          8.0,\n          16.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"25%\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 18.193405398660254,\n        \"min\": 45.0,\n        \"max\": 77.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          77.0,\n          45.0,\n          76.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"50%\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 27.15388247255507,\n        \"min\": 75.0,\n        \"max\": 123.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          123.0,\n          75.0,\n          121.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"75%\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 33.06055050963308,\n        \"min\": 128.0,\n        \"max\": 193.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          193.0,\n          128.0,\n          171.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"max\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 252.3734006057955,\n        \"min\": 304.0,\n        \"max\": 785.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          304.0,\n          785.0,\n          412.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {},
     "execution_count": 12
    }
   ],
   "source": [
    "# Paramètres de nettoyage (terrains) : à ajuster si besoin\n",
    "TYPES_GARDES = [\"AB seul\", \"AB + terrain non constructible\", \"AB + dépendance\"]  # prix = terrain seulement\n",
    "SURFACE_MIN, SURFACE_MAX = 150, 20000   # m² : surfaces plausibles pour un terrain à bâtir\n",
    "PRIX_MIN = 5                            # €/m² (euros 2025) : en dessous = terre agricole ou vente symbolique\n",
    "\n",
    "print(len(biens), \"ventes au départ\")\n",
    "biens = biens[biens[\"surface\"] > 0]\n",
    "\n",
    "if TYPE_BIEN == \"terrain\":\n",
    "    # 1) Types de vente : avec une maison, un appartement ou un local pro, le prix inclut le bâti\n",
    "    biens = biens[biens[\"type_mixite\"].isin(TYPES_GARDES)]\n",
    "    print(len(biens), \"ventes après sélection des types (prix = terrain seul)\")\n",
    "    # 2) Surfaces plausibles\n",
    "    biens = biens[biens[\"surface\"].between(SURFACE_MIN, SURFACE_MAX)]\n",
    "    print(len(biens), \"ventes après filtre des surfaces\")\n",
    "    # 3) Prix plancher\n",
    "    biens = biens[biens[\"prix_m2\"] >= PRIX_MIN]\n",
    "    print(len(biens), \"ventes après prix plancher\")\n",
    "   # 3b) Prix incohérent avec la commune : plus de RATIO_COMMUNE fois le prix médian de la commune\n",
    "    #     (souvent une maison neuve pas encore au cadastre : la vente est vue comme \"terrain\",\n",
    "    #      mais le prix inclut la construction)\n",
    "    RATIO_COMMUNE = 3\n",
    "    mediane_commune = biens.groupby(\"code_commune\")[\"prix_m2\"].transform(\"median\")\n",
    "    ventes_commune = biens.groupby(\"code_commune\")[\"prix_m2\"].transform(\"size\")\n",
    "    incoherents = (ventes_commune >= 5) & (biens[\"prix_m2\"] > RATIO_COMMUNE * mediane_commune)\n",
    "    biens[incoherents].assign(mediane_commune=mediane_commune[incoherents]).to_csv(\n",
    "        os.path.join(\"data\", \"ventes_retirees_prix_incoherent.csv\"))   # gardées pour vérification\n",
    "    biens = biens[~incoherents]\n",
    "    print(len(biens), \"ventes après retrait des prix incohérents avec la commune\",\n",
    "          f\"({incoherents.sum()} retirées, liste dans data/ventes_retirees_prix_incoherent.csv)\")\n",
    "\n",
    "# 4) Prix : on retire le 1 % le plus bas et le plus haut, par type de vente\n",
    "groupe = biens[\"type_mixite\"] if TYPE_BIEN == \"terrain\" else pd.Series(\"maison\", index=biens.index)\n",
    "bas = groupe.map(biens.groupby(groupe)[\"prix_m2\"].quantile(0.01))\n",
    "haut = groupe.map(biens.groupby(groupe)[\"prix_m2\"].quantile(0.99))\n",
    "biens = biens[(biens[\"prix_m2\"] >= bas) & (biens[\"prix_m2\"] <= haut)]\n",
    "\n",
    "print(len(biens), \"ventes après nettoyage\")\n",
    "biens.groupby(groupe.loc[biens.index])[\"prix_m2\"].describe().round()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8228f18a",
   "metadata": {
    "id": "8228f18a"
   },
   "source": [
    "## Add altitude (API IGN)\n",
    "\n",
    "Variable essentielle en montagne. Appel à l'API altimétrique de l'IGN (Géoplateforme) par paquets de points ; les altitudes manquantes seront traitées plus bas (données manquantes)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "b80c531c",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "b80c531c",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537345805,
     "user_tz": -120,
     "elapsed": 247,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "bc57abd9-eed6-4621-e475-c306fc365abc"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "0 points à interroger\n"
     ]
    }
   ],
   "source": [
    "import requests, time\n",
    "\n",
    "ALTI_URL = \"https://data.geopf.fr/altimetrie/1.0/calcul/alti/rest/elevation.json\"\n",
    "ALTI_PATH = os.path.join(\"data\", \"altitudes_cache.csv\")\n",
    "\n",
    "def get_altitudes(points, batch=100):\n",
    "    \"\"\"points : DataFrame avec lon_r, lat_r (coordonnées arrondies). Retourne une Series d'altitudes.\"\"\"\n",
    "    altitudes = []\n",
    "    for i in range(0, len(points), batch):\n",
    "        p = points.iloc[i:i + batch]\n",
    "        params = {\"lon\": \"|\".join(p[\"lon_r\"].astype(str)), \"lat\": \"|\".join(p[\"lat_r\"].astype(str)),\n",
    "                  \"resource\": \"ign_rge_alti_wld\", \"zonly\": \"true\"}\n",
    "        try:\n",
    "            r = requests.get(ALTI_URL, params=params, timeout=30)\n",
    "            z = r.json()[\"elevations\"]\n",
    "        except Exception as e:\n",
    "            print(\"Paquet\", i, \"en erreur :\", e)\n",
    "            z = [np.nan] * len(p)\n",
    "        altitudes.extend(z)\n",
    "        time.sleep(0.1)\n",
    "    return pd.Series(altitudes, index=points.index)\n",
    "\n",
    "if GET_ALTITUDE:\n",
    "    biens[\"lon_r\"] = biens[\"longitude\"].round(4)\n",
    "    biens[\"lat_r\"] = biens[\"latitude\"].round(4)\n",
    "    points = biens[[\"lon_r\", \"lat_r\"]].dropna().drop_duplicates()\n",
    "    if os.path.exists(ALTI_PATH):\n",
    "        cache = pd.read_csv(ALTI_PATH)\n",
    "        cache[[\"lon_r\", \"lat_r\"]] = cache[[\"lon_r\", \"lat_r\"]].round(4)\n",
    "        points = points.merge(cache, on=[\"lon_r\", \"lat_r\"], how=\"left\")\n",
    "        a_faire = points[points[\"altitude\"].isna()][[\"lon_r\", \"lat_r\"]]\n",
    "    else:\n",
    "        cache = pd.DataFrame({\"lon_r\": [], \"lat_r\": [], \"altitude\": []}, dtype=float)\n",
    "        a_faire = points\n",
    "    print(len(a_faire), \"points à interroger\")\n",
    "    if len(a_faire):\n",
    "        a_faire = a_faire.copy()\n",
    "        a_faire[\"altitude\"] = get_altitudes(a_faire).values\n",
    "        cache = pd.concat([cache, a_faire], ignore_index=True).drop_duplicates([\"lon_r\", \"lat_r\"])\n",
    "        cache.to_csv(ALTI_PATH, index=False)\n",
    "    biens = biens.merge(cache, on=[\"lon_r\", \"lat_r\"], how=\"left\").drop(columns=[\"lon_r\", \"lat_r\"])\n",
    "    biens[\"altitude\"] = pd.to_numeric(biens[\"altitude\"], errors=\"coerce\")\n",
    "    biens.loc[biens[\"altitude\"] < -100, \"altitude\"] = np.nan   # -99999 = pas de valeur"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7a89b0da",
   "metadata": {
    "id": "7a89b0da"
   },
   "source": [
    "## Add slope and exposure (pente et exposition)\n",
    "\n",
    "À partir de l'altitude de 4 points situés à 25 m autour du bien (est, ouest, nord, sud), on calcule :\n",
    "- `pente_pct` : la pente en % (terrain plat ou en pente, donc coût de construction) ;\n",
    "- `orientation_sud` : de -1 (plein nord, ubac) à +1 (plein sud, adret), très recherché en montagne."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "36b62e78",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "36b62e78",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537346038,
     "user_tz": -120,
     "elapsed": 233,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "41124769-9822-4449-ad94-3fcc7b8cef38"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "0 points à calculer\n"
     ]
    }
   ],
   "source": [
    "if GET_PENTE and GET_ALTITUDE:\n",
    "    D = 25  # mètres\n",
    "    PENTE_PATH = os.path.join(\"data\", \"pentes_cache.csv\")\n",
    "    biens[\"lon_r\"] = biens[\"longitude\"].round(4)\n",
    "    biens[\"lat_r\"] = biens[\"latitude\"].round(4)\n",
    "    pts = biens[[\"lon_r\", \"lat_r\"]].dropna().drop_duplicates()\n",
    "\n",
    "    # Cache : on ne calcule que les points pas encore connus (nouveaux départements, maisons...)\n",
    "    if os.path.exists(PENTE_PATH):\n",
    "        pentes = pd.read_csv(PENTE_PATH)\n",
    "        pentes[[\"lon_r\", \"lat_r\"]] = pentes[[\"lon_r\", \"lat_r\"]].round(4)\n",
    "    else:\n",
    "        pentes = pd.DataFrame({\"lon_r\": [], \"lat_r\": [], \"pente_pct\": [], \"orientation_sud\": []}, dtype=float)\n",
    "    a_faire = pts.merge(pentes[[\"lon_r\", \"lat_r\"]], on=[\"lon_r\", \"lat_r\"], how=\"left\", indicator=True)\n",
    "    a_faire = a_faire[a_faire[\"_merge\"] == \"left_only\"][[\"lon_r\", \"lat_r\"]].reset_index(drop=True)\n",
    "    print(len(a_faire), \"points à calculer\")\n",
    "\n",
    "    if len(a_faire):\n",
    "        dlon = D / (111320 * np.cos(np.radians(a_faire[\"lat_r\"])))\n",
    "        dlat = D / 110540\n",
    "        voisins = {\"e\": (dlon, 0), \"w\": (-dlon, 0), \"n\": (0, dlat), \"s\": (0, -dlat)}\n",
    "        for k, (dx, dy) in voisins.items():\n",
    "            p = pd.DataFrame({\"lon_r\": (a_faire[\"lon_r\"] + dx).round(6), \"lat_r\": (a_faire[\"lat_r\"] + dy).round(6)})\n",
    "            print(\"Altitudes voisines\", k, \":\", len(p), \"points\")\n",
    "            a_faire[\"z_\" + k] = pd.to_numeric(get_altitudes(p).values, errors=\"coerce\")\n",
    "        dzdx = (a_faire[\"z_e\"] - a_faire[\"z_w\"]) / (2 * D)\n",
    "        dzdy = (a_faire[\"z_n\"] - a_faire[\"z_s\"]) / (2 * D)\n",
    "        a_faire[\"pente_pct\"] = 100 * np.sqrt(dzdx ** 2 + dzdy ** 2)\n",
    "        exposition = np.degrees(np.arctan2(-dzdx, -dzdy)) % 360    # 0 = nord, 180 = sud\n",
    "        a_faire[\"orientation_sud\"] = -np.cos(np.radians(exposition))\n",
    "        pentes = pd.concat([pentes, a_faire[[\"lon_r\", \"lat_r\", \"pente_pct\", \"orientation_sud\"]]], ignore_index=True)\n",
    "        pentes.to_csv(PENTE_PATH, index=False)\n",
    "\n",
    "    biens = biens.drop(columns=[c for c in [\"pente_pct\", \"orientation_sud\"] if c in biens.columns])\n",
    "    biens = biens.merge(pentes, on=[\"lon_r\", \"lat_r\"], how=\"left\").drop(columns=[\"lon_r\", \"lat_r\"])\n",
    "    biens.loc[biens[\"pente_pct\"] > 300, \"pente_pct\"] = np.nan   # valeurs aberrantes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9d457fcd",
   "metadata": {
    "id": "9d457fcd"
   },
   "source": [
    "## Add distance to rivers (distance au cours d'eau)\n",
    "\n",
    "Cours d'eau issus de la **BD TOPO de l'IGN** (couche `cours_d_eau`), puis distance en mètres entre chaque bien et le cours d'eau le plus proche.\n",
    "Deux effets possibles, à laisser trancher par le modèle : **agrément** (vue, fraîcheur) ou **risque** (crue, zone inondable)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "28fd66e8",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "28fd66e8",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537355510,
     "user_tz": -120,
     "elapsed": 9462,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "0cb9584b-3ff1-4c68-9629-784874599fc7"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "5596 cours d'eau (BD TOPO IGN)\n",
      "count    4137.0\n",
      "mean      345.0\n",
      "std       299.0\n",
      "min         0.0\n",
      "25%       136.0\n",
      "50%       254.0\n",
      "75%       461.0\n",
      "max      2227.0\n",
      "Name: dist_cours_eau_m, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "import geopandas as gpd\n",
    "\n",
    "IGN_WFS = \"https://data.geopf.fr/wfs/ows\"\n",
    "\n",
    "# Emprise de chaque département (sud, ouest, nord, est)\n",
    "EMPRISES = {\"04\": (43.66, 5.49, 44.66, 6.97), \"05\": (44.18, 5.41, 45.13, 7.08),\n",
    "            \"06\": (43.47, 6.63, 44.37, 7.72), \"38\": (44.69, 4.74, 45.89, 6.36),\n",
    "            \"73\": (45.05, 5.62, 45.94, 7.19), \"74\": (45.68, 5.80, 46.41, 7.05)}\n",
    "\n",
    "def get_cours_eau(sud, ouest, nord, est, page=1000):\n",
    "    \"\"\"Cours d'eau de la BD TOPO (IGN) dans une emprise, par pages de 1000.\"\"\"\n",
    "    features, debut = [], 0\n",
    "    while True:\n",
    "        params = {\"service\": \"WFS\", \"version\": \"2.0.0\", \"request\": \"GetFeature\",\n",
    "                  \"typeNames\": \"BDTOPO_V3:cours_d_eau\", \"outputFormat\": \"application/json\",\n",
    "                  \"bbox\": f\"{sud},{ouest},{nord},{est},urn:ogc:def:crs:EPSG::4326\",\n",
    "                  \"count\": page, \"startIndex\": debut}\n",
    "        r = requests.get(IGN_WFS, params=params, timeout=120)\n",
    "        r.raise_for_status()\n",
    "        lot = r.json()[\"features\"]\n",
    "        features += lot\n",
    "        if len(lot) < page:\n",
    "            break\n",
    "        debut += page\n",
    "    riv = gpd.GeoDataFrame.from_features(features, crs=\"EPSG:4326\")\n",
    "    return riv[[\"cleabs\", \"toponyme\", \"importance\", \"geometry\"]]\n",
    "\n",
    "def load_cours_eau_dep(dep):\n",
    "    \"\"\"Cours d'eau d'un département, en cache dans data/cours_eau_XX.geojson.\"\"\"\n",
    "    chemin = os.path.join(\"data\", f\"cours_eau_{dep}.geojson\")\n",
    "    if os.path.exists(chemin):\n",
    "        return gpd.read_file(chemin)\n",
    "    print(\"Téléchargement des cours d'eau\", dep)\n",
    "    riv = get_cours_eau(*EMPRISES[dep])\n",
    "    riv.to_file(chemin, driver=\"GeoJSON\")\n",
    "    return riv\n",
    "\n",
    "def distance_cours_eau(df, rivieres):\n",
    "    \"\"\"Distance (m) de chaque bien au cours d'eau le plus proche, en Lambert 93.\"\"\"\n",
    "    pts = gpd.GeoDataFrame(df[[\"longitude\", \"latitude\"]].copy(),\n",
    "                           geometry=gpd.points_from_xy(df[\"longitude\"], df[\"latitude\"]), crs=\"EPSG:4326\")\n",
    "    pts = pts.dropna(subset=[\"longitude\", \"latitude\"]).to_crs(\"EPSG:2154\")\n",
    "    riv = rivieres.to_crs(\"EPSG:2154\")\n",
    "    proches = gpd.sjoin_nearest(pts, riv[[\"geometry\"]], how=\"left\", distance_col=\"dist_cours_eau_m\")\n",
    "    proches = proches[~proches.index.duplicated()]\n",
    "    return proches[\"dist_cours_eau_m\"].reindex(df.index)\n",
    "\n",
    "if GET_COURS_EAU:\n",
    "    rivieres = pd.concat([load_cours_eau_dep(dep) for dep in DEPARTEMENTS], ignore_index=True)\n",
    "    rivieres = gpd.GeoDataFrame(rivieres.drop_duplicates(\"cleabs\"), crs=\"EPSG:4326\")\n",
    "    print(len(rivieres), \"cours d'eau (BD TOPO IGN)\")\n",
    "    biens = biens.reset_index(drop=True)\n",
    "    biens[\"dist_cours_eau_m\"] = distance_cours_eau(biens, rivieres)\n",
    "    print(biens[\"dist_cours_eau_m\"].describe().round(0))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d421d412",
   "metadata": {
    "id": "d421d412"
   },
   "source": [
    "## Keep the useful columns"
   ]
  },
  {
   "cell_type": "markdown",
   "source": [
    "## Add administrative layer (intercommunalité / EPCI) and population\n",
    "\n",
    "Découpage issu du benchmark : le Briançonnais, le Queyras ou Serre-Ponçon n'ont pas la même attractivité.\n",
    "Source : API Découpage administratif (geo.api.gouv.fr), commune → intercommunalité (EPCI) + population."
   ],
   "metadata": {
    "id": "1fIsSKDC8e1g"
   },
   "id": "1fIsSKDC8e1g"
  },
  {
   "cell_type": "code",
   "source": [
    "GEO_API = \"https://geo.api.gouv.fr\"\n",
    "COMMUNES_PATH = os.path.join(\"data\", \"communes_epci.csv\")\n",
    "\n",
    "def load_communes():\n",
    "    if os.path.exists(COMMUNES_PATH):\n",
    "        return pd.read_csv(COMMUNES_PATH, dtype={\"code_commune\": str, \"code_epci\": str})\n",
    "    communes = pd.concat([pd.DataFrame(requests.get(f\"{GEO_API}/communes\", timeout=60,\n",
    "                              params={\"codeDepartement\": dep, \"fields\": \"code,nom,codeEpci,population\"}).json())\n",
    "                          for dep in [\"04\", \"05\", \"06\", \"38\", \"73\", \"74\"]], ignore_index=True)\n",
    "    epcis = pd.DataFrame(requests.get(f\"{GEO_API}/epcis\", params={\"fields\": \"code,nom\"}, timeout=60).json())\n",
    "    communes = communes.merge(epcis.rename(columns={\"code\": \"codeEpci\", \"nom\": \"nom_epci\"}), on=\"codeEpci\", how=\"left\")\n",
    "    communes = communes.rename(columns={\"code\": \"code_commune\", \"codeEpci\": \"code_epci\",\n",
    "                                        \"population\": \"population_commune\"})\n",
    "    communes = communes[[\"code_commune\", \"code_epci\", \"nom_epci\", \"population_commune\"]]\n",
    "    communes.to_csv(COMMUNES_PATH, index=False)\n",
    "    return communes\n",
    "\n",
    "communes = load_communes()\n",
    "biens = biens.drop(columns=[c for c in [\"code_epci\", \"nom_epci\", \"population_commune\"] if c in biens.columns])\n",
    "biens = biens.merge(communes, on=\"code_commune\", how=\"left\")\n",
    "biens[\"nom_epci\"] = biens[\"nom_epci\"].fillna(\"inconnu\")   # communes fusionnées depuis (codes anciens)\n",
    "\n",
    "print(\"Ventes sans intercommunalité :\", (biens[\"nom_epci\"] == \"inconnu\").sum())\n",
    "biens.groupby(\"nom_epci\")[\"prix_m2\"].agg([\"count\", \"median\"]).round().sort_values(\"median\", ascending=False)"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 631
    },
    "id": "mYezih818hxS",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537355928,
     "user_tz": -120,
     "elapsed": 416,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "dc2b38dc-4e36-4e2e-9e72-bea263b53152"
   },
   "id": "mYezih818hxS",
   "execution_count": 16,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Ventes sans intercommunalité : 0\n"
     ]
    },
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "                                               count  median\n",
       "nom_epci                                                    \n",
       "CC du Briançonnais                               185   200.0\n",
       "CA Durance-Lubéron-Verdon Agglomération          726   171.0\n",
       "CC du Guillestrois et du Queyras                 139   141.0\n",
       "CA Gap-Tallard-Durance                           530   138.0\n",
       "CC Serre-Ponçon                                  323   137.0\n",
       "CC du Pays des Ecrins                            100   119.0\n",
       "CC Serre-Ponçon Val d'Avance                     194   107.0\n",
       "CC Pays Forcalquier et Montagne de Lure          133   105.0\n",
       "CC Haute-Provence - Pays de Banon                100   102.0\n",
       "CC Champsaur-Valgaudemar                         319   101.0\n",
       "CC Buëch-Dévoluy                                 180    98.0\n",
       "CA Provence-Alpes-Agglomération                  551    94.0\n",
       "CC Vallée de l'Ubaye - Serre-Ponçon              196    93.0\n",
       "CC Jabron-Lure-Vançon-Durance                     80    79.0\n",
       "CC du Sisteronais-Buëch                          269    66.0\n",
       "CC Alpes-Provence-Verdon \"Sources de lumière\"    195    64.0\n",
       "CC Pays d'Apt-Luberon                             13    62.0"
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-0eb45ef6-8ab7-4b74-990c-4f29abca893e\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>median</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>nom_epci</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>CC du Briançonnais</th>\n",
       "      <td>185</td>\n",
       "      <td>200.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CA Durance-Lubéron-Verdon Agglomération</th>\n",
       "      <td>726</td>\n",
       "      <td>171.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC du Guillestrois et du Queyras</th>\n",
       "      <td>139</td>\n",
       "      <td>141.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CA Gap-Tallard-Durance</th>\n",
       "      <td>530</td>\n",
       "      <td>138.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Serre-Ponçon</th>\n",
       "      <td>323</td>\n",
       "      <td>137.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC du Pays des Ecrins</th>\n",
       "      <td>100</td>\n",
       "      <td>119.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Serre-Ponçon Val d'Avance</th>\n",
       "      <td>194</td>\n",
       "      <td>107.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Pays Forcalquier et Montagne de Lure</th>\n",
       "      <td>133</td>\n",
       "      <td>105.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Haute-Provence - Pays de Banon</th>\n",
       "      <td>100</td>\n",
       "      <td>102.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Champsaur-Valgaudemar</th>\n",
       "      <td>319</td>\n",
       "      <td>101.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Buëch-Dévoluy</th>\n",
       "      <td>180</td>\n",
       "      <td>98.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CA Provence-Alpes-Agglomération</th>\n",
       "      <td>551</td>\n",
       "      <td>94.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Vallée de l'Ubaye - Serre-Ponçon</th>\n",
       "      <td>196</td>\n",
       "      <td>93.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Jabron-Lure-Vançon-Durance</th>\n",
       "      <td>80</td>\n",
       "      <td>79.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC du Sisteronais-Buëch</th>\n",
       "      <td>269</td>\n",
       "      <td>66.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Alpes-Provence-Verdon \"Sources de lumière\"</th>\n",
       "      <td>195</td>\n",
       "      <td>64.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Pays d'Apt-Luberon</th>\n",
       "      <td>13</td>\n",
       "      <td>62.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-0eb45ef6-8ab7-4b74-990c-4f29abca893e')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-0eb45ef6-8ab7-4b74-990c-4f29abca893e button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-0eb45ef6-8ab7-4b74-990c-4f29abca893e');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "summary": "{\n  \"name\": \"biens\",\n  \"rows\": 17,\n  \"fields\": [\n    {\n      \"column\": \"nom_epci\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 17,\n        \"samples\": [\n          \"CC du Brian\\u00e7onnais\",\n          \"CA Durance-Lub\\u00e9ron-Verdon Agglom\\u00e9ration\",\n          \"CC du Pays des Ecrins\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"count\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 190,\n        \"min\": 13,\n        \"max\": 726,\n        \"num_unique_values\": 16,\n        \"samples\": [\n          185,\n          726,\n          100\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"median\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 37.54840013823727,\n        \"min\": 62.0,\n        \"max\": 200.0,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          200.0,\n          171.0,\n          119.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {},
     "execution_count": 16
    }
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "1f3522e5",
   "metadata": {
    "id": "1f3522e5",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537356088,
     "user_tz": -120,
     "elapsed": 158,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "colonnes = [\"code_departement\", \"nom_epci\", \"nom_commune\", \"code_commune\", \"annee\",\n",
    "            \"longitude\", \"latitude\", \"surface\", \"prix_m2\"]\n",
    "if TYPE_BIEN == \"terrain\":\n",
    "    colonnes += [\"type_mixite\", \"part_AB\"]\n",
    "else:\n",
    "    colonnes += [\"nb_pieces\", \"surface_terrain\"]\n",
    "for col in [\"population_commune\", \"altitude\", \"pente_pct\", \"orientation_sud\", \"dist_cours_eau_m\"]:\n",
    "    if col in biens.columns:\n",
    "        colonnes += [col]\n",
    "\n",
    "alpes = biens[colonnes].reset_index(drop=True)\n",
    "alpes.to_csv(os.path.join(\"data\", \"alpes_\" + TYPE_BIEN + \".csv\"), index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "60b31d05",
   "metadata": {
    "id": "60b31d05"
   },
   "source": [
    "## Take a Quick Look at the Data Structure"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "baa92dee",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 487
    },
    "id": "baa92dee",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537356143,
     "user_tz": -120,
     "elapsed": 28,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "2a9ddef3-b42e-4a8a-9bef-22de8d264684"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "[Sortie retirée de la version publique : elle affichait des ventes individuelles DVF.]\n"
     ]
    }
   ],
   "source": [
    "alpes.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "ff9be440",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "ff9be440",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537356175,
     "user_tz": -120,
     "elapsed": 31,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "0bbf11d4-8441-4479-8091-e8cd817756f0"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 4233 entries, 0 to 4232\n",
      "Data columns (total 16 columns):\n",
      " #   Column              Non-Null Count  Dtype  \n",
      "---  ------              --------------  -----  \n",
      " 0   code_departement    4233 non-null   object \n",
      " 1   nom_epci            4233 non-null   object \n",
      " 2   nom_commune         4233 non-null   object \n",
      " 3   code_commune        4233 non-null   object \n",
      " 4   annee               4233 non-null   int32  \n",
      " 5   longitude           4137 non-null   float64\n",
      " 6   latitude            4137 non-null   float64\n",
      " 7   surface             4233 non-null   float64\n",
      " 8   prix_m2             4233 non-null   float64\n",
      " 9   type_mixite         4233 non-null   object \n",
      " 10  part_AB             4233 non-null   float64\n",
      " 11  population_commune  4233 non-null   int64  \n",
      " 12  altitude            4137 non-null   float64\n",
      " 13  pente_pct           4137 non-null   float64\n",
      " 14  orientation_sud     4137 non-null   float64\n",
      " 15  dist_cours_eau_m    4137 non-null   float64\n",
      "dtypes: float64(9), int32(1), int64(1), object(5)\n",
      "memory usage: 512.7+ KB\n"
     ]
    }
   ],
   "source": [
    "alpes.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "525cf400",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 178
    },
    "id": "525cf400",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537356187,
     "user_tz": -120,
     "elapsed": 11,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "6e32ca34-8651-4be5-a046-5f8dcaa95272"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "code_departement\n",
       "04    2141\n",
       "05    2092\n",
       "Name: count, dtype: int64"
      ],
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>code_departement</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>04</th>\n",
       "      <td>2141</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>05</th>\n",
       "      <td>2092</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><br><label><b>dtype:</b> int64</label>"
      ]
     },
     "metadata": {},
     "execution_count": 20
    }
   ],
   "source": [
    "alpes[\"code_departement\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "a5bfdfea",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 300
    },
    "id": "a5bfdfea",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537356225,
     "user_tz": -120,
     "elapsed": 37,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "dcea4338-9378-4e94-e0cd-97c9d21cf431"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "             annee    longitude     latitude       surface      prix_m2  \\\n",
       "count  4233.000000  4137.000000  4137.000000   4233.000000  4233.000000   \n",
       "mean   2019.356721     6.135633    44.313767   1158.347271   125.145609   \n",
       "std       3.161805     0.299737     0.335426   1236.661883    82.861681   \n",
       "min    2014.000000     5.476431    43.697432    150.000000     8.035665   \n",
       "25%    2017.000000     5.903772    44.020542    565.000000    64.126733   \n",
       "50%    2020.000000     6.064236    44.389759    798.000000   113.188839   \n",
       "75%    2022.000000     6.345871    44.566127   1294.000000   165.836972   \n",
       "max    2025.000000     6.934463    45.051443  16704.000000   784.526755   \n",
       "\n",
       "           part_AB  population_commune     altitude    pente_pct  \\\n",
       "count  4233.000000         4233.000000  4137.000000  4137.000000   \n",
       "mean      0.903522         5763.104418   823.385683    12.929620   \n",
       "std       0.217633        10620.606145   370.017868    14.094996   \n",
       "min       0.001247           53.000000   273.540000     0.000000   \n",
       "25%       1.000000          664.000000   503.140000     2.560000   \n",
       "50%       1.000000         1410.000000   792.750000     8.900000   \n",
       "75%       1.000000         4099.000000  1080.870000    18.350902   \n",
       "max       1.000000        41293.000000  1937.200000   152.782106   \n",
       "\n",
       "       orientation_sud  dist_cours_eau_m  \n",
       "count     4.137000e+03       4137.000000  \n",
       "mean      3.159633e-01        345.015459  \n",
       "std       6.217098e-01        298.916697  \n",
       "min      -1.000000e+00          0.207369  \n",
       "25%      -6.123234e-17        136.459523  \n",
       "50%       2.849234e-01        254.007917  \n",
       "75%       9.624266e-01        461.414725  \n",
       "max       1.000000e+00       2226.933640  "
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-73a284d2-740b-44d4-89de-53395cd5be0d\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>annee</th>\n",
       "      <th>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>surface</th>\n",
       "      <th>prix_m2</th>\n",
       "      <th>part_AB</th>\n",
       "      <th>population_commune</th>\n",
       "      <th>altitude</th>\n",
       "      <th>pente_pct</th>\n",
       "      <th>orientation_sud</th>\n",
       "      <th>dist_cours_eau_m</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>4233.000000</td>\n",
       "      <td>4137.000000</td>\n",
       "      <td>4137.000000</td>\n",
       "      <td>4233.000000</td>\n",
       "      <td>4233.000000</td>\n",
       "      <td>4233.000000</td>\n",
       "      <td>4233.000000</td>\n",
       "      <td>4137.000000</td>\n",
       "      <td>4137.000000</td>\n",
       "      <td>4.137000e+03</td>\n",
       "      <td>4137.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>2019.356721</td>\n",
       "      <td>6.135633</td>\n",
       "      <td>44.313767</td>\n",
       "      <td>1158.347271</td>\n",
       "      <td>125.145609</td>\n",
       "      <td>0.903522</td>\n",
       "      <td>5763.104418</td>\n",
       "      <td>823.385683</td>\n",
       "      <td>12.929620</td>\n",
       "      <td>3.159633e-01</td>\n",
       "      <td>345.015459</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.161805</td>\n",
       "      <td>0.299737</td>\n",
       "      <td>0.335426</td>\n",
       "      <td>1236.661883</td>\n",
       "      <td>82.861681</td>\n",
       "      <td>0.217633</td>\n",
       "      <td>10620.606145</td>\n",
       "      <td>370.017868</td>\n",
       "      <td>14.094996</td>\n",
       "      <td>6.217098e-01</td>\n",
       "      <td>298.916697</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2014.000000</td>\n",
       "      <td>5.476431</td>\n",
       "      <td>43.697432</td>\n",
       "      <td>150.000000</td>\n",
       "      <td>8.035665</td>\n",
       "      <td>0.001247</td>\n",
       "      <td>53.000000</td>\n",
       "      <td>273.540000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-1.000000e+00</td>\n",
       "      <td>0.207369</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2017.000000</td>\n",
       "      <td>5.903772</td>\n",
       "      <td>44.020542</td>\n",
       "      <td>565.000000</td>\n",
       "      <td>64.126733</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>664.000000</td>\n",
       "      <td>503.140000</td>\n",
       "      <td>2.560000</td>\n",
       "      <td>-6.123234e-17</td>\n",
       "      <td>136.459523</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>2020.000000</td>\n",
       "      <td>6.064236</td>\n",
       "      <td>44.389759</td>\n",
       "      <td>798.000000</td>\n",
       "      <td>113.188839</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1410.000000</td>\n",
       "      <td>792.750000</td>\n",
       "      <td>8.900000</td>\n",
       "      <td>2.849234e-01</td>\n",
       "      <td>254.007917</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>2022.000000</td>\n",
       "      <td>6.345871</td>\n",
       "      <td>44.566127</td>\n",
       "      <td>1294.000000</td>\n",
       "      <td>165.836972</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>4099.000000</td>\n",
       "      <td>1080.870000</td>\n",
       "      <td>18.350902</td>\n",
       "      <td>9.624266e-01</td>\n",
       "      <td>461.414725</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>2025.000000</td>\n",
       "      <td>6.934463</td>\n",
       "      <td>45.051443</td>\n",
       "      <td>16704.000000</td>\n",
       "      <td>784.526755</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>41293.000000</td>\n",
       "      <td>1937.200000</td>\n",
       "      <td>152.782106</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>2226.933640</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-73a284d2-740b-44d4-89de-53395cd5be0d')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-73a284d2-740b-44d4-89de-53395cd5be0d button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-73a284d2-740b-44d4-89de-53395cd5be0d');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "summary": "{\n  \"name\": \"alpes\",\n  \"rows\": 8,\n  \"fields\": [\n    {\n      \"column\": \"annee\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1131.3960113143823,\n        \"min\": 3.1618050499352375,\n        \"max\": 4233.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          2019.3567210016536,\n          2020.0,\n          4233.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"longitude\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1460.774994996665,\n        \"min\": 0.2997374413715138,\n        \"max\": 4137.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          6.135632574222816,\n          6.064236,\n          4137.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"latitude\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1449.2782908048296,\n        \"min\": 0.3354258674048011,\n        \"max\": 4137.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          44.3137672802745,\n          44.3897595,\n          4137.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"surface\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 5568.533996191559,\n        \"min\": 150.0,\n        \"max\": 16704.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          1158.347271438696,\n          798.0,\n          4233.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"prix_m2\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1449.793593539224,\n        \"min\": 8.035665202856825,\n        \"max\": 4233.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          125.14560869958751,\n          113.18883910386965,\n          4233.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"part_AB\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1496.3328352941953,\n        \"min\": 0.0012468827930174563,\n        \"max\": 4233.0,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          0.903521526169889,\n          1.0,\n          0.2176327113594726\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"population_commune\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 13669.387120145175,\n        \"min\": 53.0,\n        \"max\": 41293.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          5763.104417670683,\n          1410.0,\n          4233.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"altitude\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1282.3803313625274,\n        \"min\": 273.54,\n        \"max\": 4137.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          823.3856828619773,\n          792.75,\n          4137.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"pente_pct\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1452.9410635566621,\n        \"min\": 0.0,\n        \"max\": 4137.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          12.929619567434491,\n          8.900000000000091,\n          4137.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"orientation_sud\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1462.5401538731915,\n        \"min\": -1.0,\n        \"max\": 4137.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          0.31596331247160125,\n          0.284923411587854,\n          4137.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"dist_cours_eau_m\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1456.8102086214838,\n        \"min\": 0.20736890043783143,\n        \"max\": 4137.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          345.0154590559677,\n          254.00791676892206,\n          4137.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {},
     "execution_count": 21
    }
   ],
   "source": [
    "alpes.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "fed8e40e",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "fed8e40e",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537360948,
     "user_tz": -120,
     "elapsed": 4722,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "df4e3b3d-a8a4-457a-ce08-0a9c265606a2"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Saving figure attribute_histogram_plots\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 2000x1500 with 12 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "alpes.hist(bins=50, figsize=(20,15))\n",
    "save_fig(\"attribute_histogram_plots\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f70bb614",
   "metadata": {
    "id": "f70bb614"
   },
   "source": [
    "# Discover and Visualize the Data to Gain Insights"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bac958ba",
   "metadata": {
    "id": "bac958ba"
   },
   "source": [
    "## Visualizing Geographical Data\n",
    "\n",
    "Comme pour la Californie, chaque vente est placée par sa **longitude / latitude**.\n",
    "Au lieu d'une image calée par ses coordonnées (`extent=`), on dessine en fond les **contours officiels des départements** (GeoJSON) : ils sont dans le même système de coordonnées, donc tout se cale automatiquement."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "16c5e600",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "16c5e600",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537361424,
     "user_tz": -120,
     "elapsed": 473,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "5580e88d-e70c-4fcd-9baa-7398107fda7c"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "17 intercommunalités\n"
     ]
    }
   ],
   "source": [
    "import geopandas as gpd\n",
    "\n",
    "# Contours des départements\n",
    "GEOJSON_URL = \"https://raw.githubusercontent.com/gregoiredavid/france-geojson/master/departements-version-simplifiee.geojson\"\n",
    "try:\n",
    "    deps_geo = gpd.read_file(GEOJSON_URL)\n",
    "    deps_geo = deps_geo[deps_geo[\"code\"].isin(DEPARTEMENTS)]\n",
    "except Exception as e:\n",
    "    print(\"Contours des départements non chargés :\", e)\n",
    "    deps_geo = None\n",
    "\n",
    "# Contours des intercommunalités (EPCI) = fusion des contours de leurs communes (geo.api.gouv.fr), mis en cache\n",
    "EPCI_PATH = os.path.join(\"data\", \"epci_contours_\" + \"_\".join(DEPARTEMENTS) + \".geojson\")\n",
    "\n",
    "def load_epci_contours():\n",
    "    if os.path.exists(EPCI_PATH):\n",
    "        return gpd.read_file(EPCI_PATH)\n",
    "    morceaux = []\n",
    "    for dep in DEPARTEMENTS:\n",
    "        r = requests.get(f\"{GEO_API}/communes\", timeout=120,\n",
    "                         params={\"codeDepartement\": dep, \"fields\": \"code,codeEpci\",\n",
    "                                 \"format\": \"geojson\", \"geometry\": \"contour\"}).json()\n",
    "        morceaux.append(gpd.GeoDataFrame.from_features(r[\"features\"], crs=\"EPSG:4326\"))\n",
    "    com_geo = pd.concat(morceaux, ignore_index=True).dropna(subset=[\"codeEpci\"])\n",
    "    epci_geo = com_geo.dissolve(by=\"codeEpci\").reset_index()[[\"codeEpci\", \"geometry\"]]\n",
    "    noms = communes.dropna(subset=[\"code_epci\"]).drop_duplicates(\"code_epci\").set_index(\"code_epci\")[\"nom_epci\"]\n",
    "    epci_geo[\"nom_epci\"] = epci_geo[\"codeEpci\"].map(noms)\n",
    "    epci_geo.to_file(EPCI_PATH, driver=\"GeoJSON\")\n",
    "    return epci_geo\n",
    "\n",
    "try:\n",
    "    epci_geo = load_epci_contours()\n",
    "    print(len(epci_geo), \"intercommunalités\")\n",
    "except Exception as e:\n",
    "    print(\"Contours des EPCI non chargés :\", e)\n",
    "    epci_geo = None"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# Ville principale de chaque intercommunalité (commune la plus peuplée) : repère sur la carte, mis en cache\n",
    "VILLES_PATH = os.path.join(\"data\", \"villes_epci_\" + \"_\".join(DEPARTEMENTS) + \".csv\")\n",
    "\n",
    "def load_villes_epci():\n",
    "    if os.path.exists(VILLES_PATH):\n",
    "        return pd.read_csv(VILLES_PATH, dtype={\"codeEpci\": str})\n",
    "    morceaux = []\n",
    "    for dep in DEPARTEMENTS:\n",
    "        r = requests.get(f\"{GEO_API}/communes\", timeout=120,\n",
    "                         params={\"codeDepartement\": dep, \"fields\": \"nom,codeEpci,population,centre\"}).json()\n",
    "        morceaux.append(pd.DataFrame(r))\n",
    "    com = pd.concat(morceaux, ignore_index=True).dropna(subset=[\"codeEpci\", \"centre\"])\n",
    "    com[\"lon\"] = com[\"centre\"].map(lambda c: c[\"coordinates\"][0])\n",
    "    com[\"lat\"] = com[\"centre\"].map(lambda c: c[\"coordinates\"][1])\n",
    "    villes = (com.sort_values(\"population\", ascending=False)\n",
    "                 .drop_duplicates(\"codeEpci\")[[\"codeEpci\", \"nom\", \"population\", \"lon\", \"lat\"]])\n",
    "    villes.to_csv(VILLES_PATH, index=False)\n",
    "    return villes\n",
    "\n",
    "try:\n",
    "    villes_epci = load_villes_epci()\n",
    "    print(villes_epci.sort_values(\"population\", ascending=False).head(10))\n",
    "except Exception as e:\n",
    "    print(\"Villes principales non chargées :\", e)\n",
    "    villes_epci = None"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "GN9DI2yKDeq7",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537361659,
     "user_tz": -120,
     "elapsed": 233,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "86f28057-66de-4076-c641-c20715030589"
   },
   "id": "GN9DI2yKDeq7",
   "execution_count": 24,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "    codeEpci              nom  population     lon      lat\n",
      "0  200067825              Gap       41293  6.0616  44.5797\n",
      "1  200034700         Manosque       22718  5.7896  43.8293\n",
      "2  200067437  Digne-les-Bains       17979  6.2495  44.0954\n",
      "3  240500439         Briançon       11411  6.6536  44.8995\n",
      "4  200068765         Sisteron        7850  5.9276  44.1993\n",
      "5  200067742           Embrun        6412  6.4750  44.5806\n",
      "6  240400440      Forcalquier        5222  5.7842  43.9582\n",
      "7  200067445           Veynes        3214  5.8227  44.5599\n",
      "8  200067320   La Bâtie-Neuve        2628  6.2151  44.5817\n",
      "9  200072304    Barcelonnette        2518  6.6463  44.3751\n"
     ]
    }
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# Cours d'eau pour la carte :\n",
    "#  - CHOIX : liste de rivières choisies (cherchées par leur nom dans la couche \"cours d'eau\" de la BD TOPO)\n",
    "#  - TRACÉ continu : couche \"tronçons hydrographiques\" (y compris dans les lits larges et les lacs)\n",
    "RIVIERES = [\"Durance\", \"Guil\", \"Ubaye\", \"Buëch\", \"Bléone\", \"Verdon\", \"Asse\", \"Jabron\", \"Drac\", \"Clarée\", \"Guisane\"]\n",
    "COUCHE = \"BDTOPO_V3:troncon_hydrographique\"\n",
    "import re\n",
    "\n",
    "# 1) Champs de la couche des tronçons (lien vers le cours d'eau et nom)\n",
    "desc = requests.get(IGN_WFS, timeout=60, params={\"service\": \"WFS\", \"version\": \"2.0.0\",\n",
    "                    \"request\": \"DescribeFeatureType\", \"typeNames\": COUCHE,\n",
    "                    \"outputFormat\": \"application/json\"}).json()\n",
    "CHAMPS = [p[\"name\"] for p in desc[\"featureTypes\"][0][\"properties\"]]\n",
    "CHAMP_LIEN = next((c for c in CHAMPS if c.startswith(\"liens_vers_cours_d_eau\")), None)\n",
    "CHAMP_NOM = next((c for c in CHAMPS if \"toponyme\" in c), None)\n",
    "print(\"Lien vers le cours d'eau :\", CHAMP_LIEN, \"| nom :\", CHAMP_NOM)\n",
    "\n",
    "# 2) Rivières de la liste trouvées dans la couche \"cours d'eau\" (déjà chargée pour la distance au cours d'eau)\n",
    "# Nom sans l'article (\"la Durance\" -> \"Durance\"), puis on garde seulement les noms EXACTEMENT dans la liste\n",
    "nom_seul = rivieres[\"toponyme\"].fillna(\"\").str.replace(r\"^(le |la |les |l'|l’)\", \"\", regex=True, case=False)\n",
    "choix = rivieres[nom_seul.str.lower().isin([n.lower() for n in RIVIERES])]\n",
    "if deps_geo is not None:   # seulement celles qui passent dans nos départements\n",
    "    choix = choix[choix.intersects(deps_geo.to_crs(rivieres.crs).union_all())]\n",
    "# Une seule rivière par nom (s'il y a des homonymes, on garde la plus importante)\n",
    "choix = choix.assign(imp=pd.to_numeric(choix[\"importance\"], errors=\"coerce\")).sort_values(\"imp\").drop_duplicates(\"toponyme\")\n",
    "choix = choix[[\"cleabs\", \"toponyme\", \"importance\"]]\n",
    "print(len(choix), \"rivières trouvées :\", \", \".join(sorted(choix[\"toponyme\"].unique())))\n",
    "manquantes = [n for n in RIVIERES if not choix[\"toponyme\"].str.contains(rf\"\\b{n}\\b\", case=False).any()]\n",
    "if manquantes:\n",
    "    print(\"Non trouvées :\", manquantes)\n",
    "\n",
    "def get_troncons_riviere(riv, page=5000):\n",
    "    \"\"\"Tous les tronçons d'une rivière : ceux qui portent son nom OU qui lui sont reliés.\"\"\"\n",
    "    nom_sql = riv[\"toponyme\"].replace(chr(39), chr(39) * 2)   # l'Ubaye -> l''Ubaye (apostrophe échappée)\n",
    "    filtre = f\"{CHAMP_NOM} = '{nom_sql}'\"                      # tronçons qui portent le nom de la rivière\n",
    "    if CHAMP_LIEN:                                             # + tronçons reliés à la rivière\n",
    "        filtre = f\"({filtre}) OR ({CHAMP_LIEN} LIKE '%{riv['cleabs']}%')\"\n",
    "    features, debut = [], 0\n",
    "    while True:\n",
    "        r = requests.get(IGN_WFS, timeout=180, params={\"service\": \"WFS\", \"version\": \"2.0.0\",\n",
    "                         \"request\": \"GetFeature\", \"typeNames\": COUCHE, \"outputFormat\": \"application/json\",\n",
    "                         \"CQL_FILTER\": filtre, \"count\": page, \"startIndex\": debut})\n",
    "        if r.status_code != 200:\n",
    "            print(\"Réponse du serveur IGN :\", r.text[:800])\n",
    "            r.raise_for_status()\n",
    "        lot = r.json()[\"features\"]\n",
    "        features += lot\n",
    "        if len(lot) < page:\n",
    "            break\n",
    "        debut += page\n",
    "    tr = gpd.GeoDataFrame.from_features(features, crs=\"EPSG:4326\")[[\"geometry\"]] if features else \\\n",
    "         gpd.GeoDataFrame(geometry=[], crs=\"EPSG:4326\")\n",
    "    tr[\"toponyme\"], tr[\"importance\"] = riv[\"toponyme\"], riv[\"importance\"]\n",
    "    return tr\n",
    "\n",
    "# 3) Téléchargement rivière par rivière, avec cache (data/troncons_v2/<identifiant>.geojson)\n",
    "os.makedirs(os.path.join(\"data\", \"troncons_v2\"), exist_ok=True)\n",
    "try:\n",
    "    morceaux = []\n",
    "    for _, riv in choix.iterrows():\n",
    "        chemin = os.path.join(\"data\", \"troncons_v2\", f\"{riv['cleabs']}.geojson\")\n",
    "        if os.path.exists(chemin):\n",
    "            tr = gpd.read_file(chemin)\n",
    "        else:\n",
    "            tr = get_troncons_riviere(riv)\n",
    "            tr.to_file(chemin, driver=\"GeoJSON\")\n",
    "            print(f\"  {riv['toponyme']} : {len(tr)} tronçons\")\n",
    "        morceaux.append(tr)\n",
    "    grands_cours_eau = gpd.GeoDataFrame(pd.concat(morceaux, ignore_index=True), crs=\"EPSG:4326\")\n",
    "    if deps_geo is not None:\n",
    "        grands_cours_eau = gpd.clip(grands_cours_eau, deps_geo.to_crs(grands_cours_eau.crs))\n",
    "    print(len(grands_cours_eau), \"tronçons au total\")\n",
    "except Exception as e:\n",
    "    print(\"Tronçons non chargés :\", e)\n",
    "    grands_cours_eau = None"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "wysyOnjmD-Qz",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537365794,
     "user_tz": -120,
     "elapsed": 4124,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "425047f0-8baa-465c-ef71-38f6140152f6"
   },
   "id": "wysyOnjmD-Qz",
   "execution_count": 25,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Lien vers le cours d'eau : liens_vers_cours_d_eau | nom : cpx_toponyme_de_cours_d_eau\n",
      "11 rivières trouvées : l'Asse, l'Ubaye, la Bléone, la Clarée, la Durance, la Guisane, le Buëch, le Drac, le Guil, le Jabron, le Verdon\n",
      "5990 tronçons au total\n"
     ]
    }
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "285313d8",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 814
    },
    "id": "285313d8",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537368406,
     "user_tz": -120,
     "elapsed": 2610,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "14271199-09eb-4142-ca43-ff15ab94ca9e"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "4137 ventes sur la carte\n"
     ]
    },
    {
     "output_type": "stream",
     "name": "stderr",
     "text": [
      "/tmp/ipykernel_1095/859185071.py:68: UserWarning: Geometry is in a geographic CRS. Results from 'length' are likely incorrect. Use 'GeoSeries.to_crs()' to re-project geometries to a projected CRS before this operation.\n",
      "\n",
      "  ligne = groupe.geometry.iloc[groupe.geometry.length.argmax()]   # plus long tronçon\n"
     ]
    },
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Saving figure alpes_prix_m2_plot_epci\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 1100x700 with 2 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": [
    "import textwrap, unicodedata\n",
    "import matplotlib.patheffects as pe\n",
    "\n",
    "def nom_court(nom):\n",
    "    \"\"\"'CC du Briançonnais' -> 'Briançonnais' (plus lisible sur la carte).\"\"\"\n",
    "    for prefixe in [\"CC du \", \"CC de la \", \"CC de l'\", \"CC des \", \"CC de \", \"CA du \", \"CA de \", \"CA \", \"CC \"]:\n",
    "        if nom.startswith(prefixe):\n",
    "            return nom[len(prefixe):]\n",
    "    return nom\n",
    "\n",
    "def normalise(texte):\n",
    "    \"\"\"Minuscules, sans accents, apostrophes unifiées : 'Écrins' = 'Ecrins'.\"\"\"\n",
    "    texte = str(texte).replace(\"’\", \"'\")\n",
    "    return unicodedata.normalize(\"NFKD\", texte).encode(\"ascii\", \"ignore\").decode().lower().strip()\n",
    "\n",
    "halo = [pe.withStroke(linewidth=2.5, foreground=\"white\")]\n",
    "\n",
    "def carte(epci_noms=None, titre=\"\", figsize=(11, 7), fichier=\"carte\"):\n",
    "    \"\"\"Carte des prix au m². epci_noms = None -> tout ; sinon liste de noms courts d'intercommunalités (zoom).\"\"\"\n",
    "    # 1) Zone étudiée\n",
    "    zone_epci = epci_geo\n",
    "    if epci_noms is not None:\n",
    "        cibles = [normalise(n) for n in epci_noms]\n",
    "        zone_epci = epci_geo[epci_geo[\"nom_epci\"].map(lambda n: normalise(nom_court(str(n)))).isin(cibles)]\n",
    "        print(\"Intercommunalités retenues :\", \", \".join(zone_epci[\"nom_epci\"]))\n",
    "        oubliees = [n for n in epci_noms if normalise(n) not in\n",
    "                    zone_epci[\"nom_epci\"].map(lambda x: normalise(nom_court(str(x)))).tolist()]\n",
    "        if oubliees:\n",
    "            print(\"Non trouvées (vérifier l'orthographe) :\", oubliees)\n",
    "    zone = zone_epci.union_all()\n",
    "\n",
    "    # 2) Ventes, villes et rivières de la zone\n",
    "    pts = alpes.dropna(subset=[\"longitude\", \"latitude\"])\n",
    "    rivs, villes = grands_cours_eau, villes_epci\n",
    "    if epci_noms is not None:\n",
    "        dedans = gpd.GeoSeries(gpd.points_from_xy(pts[\"longitude\"], pts[\"latitude\"]), index=pts.index).within(zone)\n",
    "        pts = pts[dedans]\n",
    "        if rivs is not None:\n",
    "            rivs = gpd.clip(rivs, zone)\n",
    "        if villes is not None:\n",
    "            villes = villes[villes[\"codeEpci\"].isin(zone_epci[\"codeEpci\"])]\n",
    "    print(len(pts), \"ventes sur la carte\")\n",
    "\n",
    "    # Échelles plafonnées pour la lisibilité (les valeurs elles-mêmes ne sont pas modifiées)\n",
    "    taille = pts[\"surface\"].clip(upper=pts[\"surface\"].quantile(0.95))\n",
    "    vmax_prix = pts[\"prix_m2\"].quantile(0.95)\n",
    "\n",
    "    fig, ax = plt.subplots(figsize=figsize)\n",
    "\n",
    "    # Fond : départements, intercommunalités, cours d'eau\n",
    "    if deps_geo is not None:\n",
    "        deps_geo.plot(ax=ax, color=\"whitesmoke\", edgecolor=\"black\", linewidth=1.5)\n",
    "    epci_geo.boundary.plot(ax=ax, color=\"grey\", linewidth=0.6)\n",
    "    if rivs is not None and len(rivs) > 0:\n",
    "        imp = pd.to_numeric(rivs[\"importance\"], errors=\"coerce\")\n",
    "        rivs.plot(ax=ax, color=\"royalblue\", linewidth=(4 - imp.clip(upper=3)) * 0.8 + 0.4)\n",
    "\n",
    "    # Ventes (jaune = bon marché, rouge = cher) + échelle de couleur fine, à mi-hauteur\n",
    "    nuage = ax.scatter(pts[\"longitude\"], pts[\"latitude\"], s=taille / taille.median() * 10,\n",
    "                       c=pts[\"prix_m2\"], cmap=\"YlOrRd\", vmax=vmax_prix, alpha=0.6, label=\"Surface\")\n",
    "    barre = fig.colorbar(nuage, ax=ax, shrink=0.5, fraction=0.025, pad=0.02)\n",
    "    barre.set_label(\"€/m²\", fontsize=10)\n",
    "    barre.ax.tick_params(labelsize=8)\n",
    "\n",
    "    # Noms des cours d'eau (bleu, italique), une seule fois par nom\n",
    "    if rivs is not None and len(rivs) > 0:\n",
    "        for nom, groupe in rivs.dropna(subset=[\"toponyme\"]).groupby(\"toponyme\"):\n",
    "            ligne = groupe.geometry.iloc[groupe.geometry.length.argmax()]   # plus long tronçon\n",
    "            p = ligne.representative_point()\n",
    "            ax.annotate(nom, (p.x, p.y), fontsize=7, color=\"royalblue\", style=\"italic\", path_effects=halo)\n",
    "\n",
    "    # Noms des intercommunalités de la zone (gris, italique)\n",
    "    for _, row in zone_epci.iterrows():\n",
    "        p = row.geometry.representative_point()\n",
    "        nom = textwrap.fill(nom_court(str(row[\"nom_epci\"])), 18)\n",
    "        ax.annotate(nom, (p.x, p.y), fontsize=7, ha=\"center\", va=\"center\", color=\"dimgrey\",\n",
    "                    style=\"italic\", path_effects=halo)\n",
    "\n",
    "    # Villes principales (carré noir + nom en gras)\n",
    "    if villes is not None:\n",
    "        ax.scatter(villes[\"lon\"], villes[\"lat\"], marker=\"s\", s=25, color=\"black\", zorder=5)\n",
    "        for _, v in villes.iterrows():\n",
    "            ax.annotate(v[\"nom\"], (v[\"lon\"], v[\"lat\"]), xytext=(4, 4), textcoords=\"offset points\",\n",
    "                        fontsize=8, fontweight=\"bold\", color=\"black\", path_effects=halo, zorder=6)\n",
    "\n",
    "    # Cadrage sur la zone (+ petite marge)\n",
    "    minx, miny, maxx, maxy = zone.bounds\n",
    "    marge = 0.03\n",
    "    ax.set_xlim(minx - marge, maxx + marge)\n",
    "    ax.set_ylim(miny - marge, maxy + marge)\n",
    "\n",
    "    ax.set_ylabel(\"Latitude\", fontsize=10)\n",
    "    ax.set_xlabel(\"Longitude\", fontsize=10)\n",
    "    ax.tick_params(labelsize=8)\n",
    "    ax.set_title(f\"Prix au m² (euros 2025), {TYPE_BIEN}s : {titre}\\n(couleur plafonnée au 95e centile : \"\n",
    "                 f\"{round(vmax_prix)} €/m²)\", fontsize=11)\n",
    "    ax.legend(fontsize=9, loc=\"lower right\")\n",
    "    save_fig(fichier)\n",
    "    plt.show()\n",
    "\n",
    "# Carte complète\n",
    "carte(titre=\"04 et 05\", fichier=\"alpes_prix_m2_plot_epci\")"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# Zoom : nord des Hautes-Alpes (noms courts des intercommunalités, accents facultatifs)\n",
    "ZOOM_EPCI = [\"Briançonnais\", \"Pays des Écrins\", \"Guillestrois et du Queyras\", \"Champsaur-Valgaudemar\",\n",
    "             \"Serre-Ponçon\", \"Serre-Ponçon Val d'Avance\", \"Gap-Tallard-Durance\"]\n",
    "\n",
    "carte(ZOOM_EPCI, titre=\"nord des Hautes-Alpes\", fichier=\"alpes_prix_m2_zoom_nord_05\")"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 831
    },
    "id": "z15tECBYIevy",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537371459,
     "user_tz": -120,
     "elapsed": 3051,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "197a6629-8b0d-4b2f-8722-3f31acc8e68c"
   },
   "id": "z15tECBYIevy",
   "execution_count": 27,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Intercommunalités retenues : CC Serre-Ponçon Val d'Avance, CC du Guillestrois et du Queyras, CC Serre-Ponçon, CA Gap-Tallard-Durance, CC Champsaur-Valgaudemar, CC du Briançonnais, CC du Pays des Ecrins\n",
      "1758 ventes sur la carte\n"
     ]
    },
    {
     "output_type": "stream",
     "name": "stderr",
     "text": [
      "/tmp/ipykernel_1095/859185071.py:68: UserWarning: Geometry is in a geographic CRS. Results from 'length' are likely incorrect. Use 'GeoSeries.to_crs()' to re-project geometries to a projected CRS before this operation.\n",
      "\n",
      "  ligne = groupe.geometry.iloc[groupe.geometry.length.argmax()]   # plus long tronçon\n"
     ]
    },
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Saving figure alpes_prix_m2_zoom_nord_05\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 1100x700 with 2 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ]
  },
  {
   "cell_type": "markdown",
   "id": "11d33ed7",
   "metadata": {
    "id": "11d33ed7"
   },
   "source": [
    "## Looking for Correlations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "25c126ac",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 206
    },
    "id": "25c126ac",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537373666,
     "user_tz": -120,
     "elapsed": 3,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "365e1c63-877e-48d7-ec62-82eae95aedce"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "[Sortie retirée de la version publique : elle affichait des ventes individuelles DVF.]\n"
     ]
    }
   ],
   "source": [
    "alpes_analysis = alpes.select_dtypes(include=\"number\")\n",
    "alpes_analysis.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "source": [
    "### Lien entre le prix et les variables texte (département, intercommunalité, commune, type de vente)\n",
    "\n",
    "La corrélation ne se calcule que sur des nombres. Pour les variables texte, on mesure la **part de la variation du prix expliquée par le groupe** (η², « êta carré ») : 0 = le groupe ne dit rien du prix, 1 = le groupe explique tout. C'est comparable au carré de la corrélation (r²) des variables numériques.\n",
    "⚠️ Plus une variable a de groupes (ex. des centaines de communes), plus son η² est gonflé artificiellement.\n",
    ""
   ],
   "metadata": {
    "id": "MpHI_PxU9fzX"
   },
   "id": "MpHI_PxU9fzX"
  },
  {
   "cell_type": "code",
   "source": [
    "def eta2(groupes, y):\n",
    "    moyennes = y.groupby(groupes).transform(\"mean\")\n",
    "    return ((moyennes - y.mean()) ** 2).sum() / ((y - y.mean()) ** 2).sum()\n",
    "\n",
    "def liens_avec_prix(df):\n",
    "    num = df.select_dtypes(include=\"number\").corr()[\"prix_m2\"].drop(\"prix_m2\") ** 2\n",
    "    cat = pd.Series({c: eta2(df[c], df[\"prix_m2\"]) for c in df.select_dtypes(exclude=\"number\").columns})\n",
    "    nb_groupes = pd.Series({c: df[c].nunique() for c in cat.index})\n",
    "    tableau = pd.DataFrame({\"lien_avec_prix (r² ou η²)\": pd.concat([num, cat]),\n",
    "                            \"type\": [\"numérique\"] * len(num) + [\"texte\"] * len(cat),\n",
    "                            \"nb_groupes\": pd.concat([pd.Series(np.nan, index=num.index), nb_groupes])})\n",
    "    return tableau.sort_values(\"lien_avec_prix (r² ou η²)\", ascending=False).round(3)\n",
    "\n",
    "liens_avec_prix(alpes.drop(columns=[\"code_commune\", \"strat_cat\"], errors=\"ignore\"))"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 488
    },
    "id": "ynx__ghP9ki_",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537373728,
     "user_tz": -120,
     "elapsed": 4,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "06bc7c4e-7163-4b26-9137-22c47860e2d1"
   },
   "id": "ynx__ghP9ki_",
   "execution_count": 30,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "                    lien_avec_prix (r² ou η²)       type  nb_groupes\n",
       "nom_commune                             0.456      texte       254.0\n",
       "nom_epci                                0.238      texte        17.0\n",
       "surface                                 0.125  numérique         NaN\n",
       "population_commune                      0.022  numérique         NaN\n",
       "part_AB                                 0.017  numérique         NaN\n",
       "code_departement                        0.012      texte         2.0\n",
       "type_mixite                             0.011      texte         3.0\n",
       "latitude                                0.004  numérique         NaN\n",
       "altitude                                0.003  numérique         NaN\n",
       "pente_pct                               0.002  numérique         NaN\n",
       "annee                                   0.001  numérique         NaN\n",
       "dist_cours_eau_m                        0.000  numérique         NaN\n",
       "longitude                               0.000  numérique         NaN\n",
       "orientation_sud                         0.000  numérique         NaN"
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-b41ab5db-93ae-4d7a-9697-97b94a7549ff\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>lien_avec_prix (r² ou η²)</th>\n",
       "      <th>type</th>\n",
       "      <th>nb_groupes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>nom_commune</th>\n",
       "      <td>0.456</td>\n",
       "      <td>texte</td>\n",
       "      <td>254.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>nom_epci</th>\n",
       "      <td>0.238</td>\n",
       "      <td>texte</td>\n",
       "      <td>17.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>surface</th>\n",
       "      <td>0.125</td>\n",
       "      <td>numérique</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>population_commune</th>\n",
       "      <td>0.022</td>\n",
       "      <td>numérique</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>part_AB</th>\n",
       "      <td>0.017</td>\n",
       "      <td>numérique</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>code_departement</th>\n",
       "      <td>0.012</td>\n",
       "      <td>texte</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>type_mixite</th>\n",
       "      <td>0.011</td>\n",
       "      <td>texte</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>latitude</th>\n",
       "      <td>0.004</td>\n",
       "      <td>numérique</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>altitude</th>\n",
       "      <td>0.003</td>\n",
       "      <td>numérique</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pente_pct</th>\n",
       "      <td>0.002</td>\n",
       "      <td>numérique</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>annee</th>\n",
       "      <td>0.001</td>\n",
       "      <td>numérique</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dist_cours_eau_m</th>\n",
       "      <td>0.000</td>\n",
       "      <td>numérique</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>longitude</th>\n",
       "      <td>0.000</td>\n",
       "      <td>numérique</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>orientation_sud</th>\n",
       "      <td>0.000</td>\n",
       "      <td>numérique</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b41ab5db-93ae-4d7a-9697-97b94a7549ff')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-b41ab5db-93ae-4d7a-9697-97b94a7549ff button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-b41ab5db-93ae-4d7a-9697-97b94a7549ff');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "summary": "{\n  \"name\": \"liens_avec_prix(alpes\",\n  \"rows\": 14,\n  \"fields\": [\n    {\n      \"column\": \"lien_avec_prix (r\\u00b2 ou \\u03b7\\u00b2)\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.13143211593404822,\n        \"min\": 0.0,\n        \"max\": 0.456,\n        \"num_unique_values\": 12,\n        \"samples\": [\n          0.001,\n          0.002,\n          0.456\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"type\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          \"num\\u00e9rique\",\n          \"texte\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"nb_groupes\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 123.52327715859873,\n        \"min\": 2.0,\n        \"max\": 254.0,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          17.0,\n          3.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {},
     "execution_count": 30
    }
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# Prix au m² par intercommunalité : tableau, boîtes à moustaches, carte\n",
    "par_epci = (alpes.groupby(\"nom_epci\")[\"prix_m2\"]\n",
    "                 .agg(ventes=\"count\", mediane=\"median\",\n",
    "                      q25=lambda s: s.quantile(0.25), q75=lambda s: s.quantile(0.75))\n",
    "                 .round().sort_values(\"mediane\", ascending=False))\n",
    "display(par_epci)\n",
    "\n",
    "ordre = par_epci.index.tolist()[::-1]   # la plus chère en haut du graphique\n",
    "fig, axes = plt.subplots(1, 2, figsize=(16, 7), gridspec_kw={\"width_ratios\": [1.1, 1]})\n",
    "\n",
    "# a) Boîtes à moustaches : la boîte = 50 % des ventes, le trait = la médiane\n",
    "axes[0].boxplot([alpes.loc[alpes[\"nom_epci\"] == e, \"prix_m2\"] for e in ordre], vert=False, showfliers=False)\n",
    "axes[0].set_yticks(range(1, len(ordre) + 1))\n",
    "axes[0].set_yticklabels([nom_court(e) for e in ordre], fontsize=8)\n",
    "axes[0].axvline(alpes[\"prix_m2\"].median(), color=\"red\", linestyle=\"--\", label=\"médiane 04 + 05\")\n",
    "axes[0].set_xlabel(\"Prix au m² (euros 2025)\")\n",
    "axes[0].set_title(\"Prix au m² par intercommunalité\")\n",
    "axes[0].legend(fontsize=8)\n",
    "\n",
    "# b) Carte : chaque intercommunalité colorée selon son prix médian\n",
    "carte_epci = epci_geo.merge(par_epci, left_on=\"nom_epci\", right_index=True, how=\"left\")\n",
    "carte_epci.plot(column=\"mediane\", cmap=\"YlOrRd\", edgecolor=\"grey\", ax=axes[1], legend=True,\n",
    "                legend_kwds={\"shrink\": 0.5, \"label\": \"€/m² (médiane)\"}, missing_kwds={\"color\": \"lightgrey\"})\n",
    "for _, row in carte_epci.dropna(subset=[\"mediane\"]).iterrows():\n",
    "    p = row.geometry.representative_point()\n",
    "    axes[1].annotate(f\"{nom_court(row['nom_epci'])}\\n{int(row['mediane'])} €\", (p.x, p.y), fontsize=6,\n",
    "                     ha=\"center\", va=\"center\", path_effects=halo)\n",
    "axes[1].set_title(\"Prix médian au m² par intercommunalité\")\n",
    "axes[1].set_axis_off()\n",
    "\n",
    "save_fig(\"prix_par_epci\")\n",
    "plt.show()"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "-T3-rDAmPwvx",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537375727,
     "user_tz": -120,
     "elapsed": 1998,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "33c2bdf2-a0ad-483c-d08c-5d31eb34ad3c"
   },
   "id": "-T3-rDAmPwvx",
   "execution_count": 31,
   "outputs": [
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "                                               ventes  mediane    q25    q75\n",
       "nom_epci                                                                    \n",
       "CC du Briançonnais                                185    200.0  122.0  348.0\n",
       "CA Durance-Lubéron-Verdon Agglomération           726    171.0   98.0  218.0\n",
       "CC du Guillestrois et du Queyras                  139    141.0   88.0  193.0\n",
       "CA Gap-Tallard-Durance                            530    138.0   89.0  176.0\n",
       "CC Serre-Ponçon                                   323    137.0   75.0  182.0\n",
       "CC du Pays des Ecrins                             100    119.0   81.0  147.0\n",
       "CC Serre-Ponçon Val d'Avance                      194    107.0   82.0  129.0\n",
       "CC Pays Forcalquier et Montagne de Lure           133    105.0   43.0  164.0\n",
       "CC Haute-Provence - Pays de Banon                 100    102.0   61.0  119.0\n",
       "CC Champsaur-Valgaudemar                          319    101.0   67.0  130.0\n",
       "CC Buëch-Dévoluy                                  180     98.0   55.0  176.0\n",
       "CA Provence-Alpes-Agglomération                   551     94.0   52.0  121.0\n",
       "CC Vallée de l'Ubaye - Serre-Ponçon               196     93.0   53.0  140.0\n",
       "CC Jabron-Lure-Vançon-Durance                      80     79.0   57.0  105.0\n",
       "CC du Sisteronais-Buëch                           269     66.0   38.0  103.0\n",
       "CC Alpes-Provence-Verdon \"Sources de lumière\"     195     64.0   40.0  102.0\n",
       "CC Pays d'Apt-Luberon                              13     62.0   34.0   88.0"
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-6ce991bc-72ae-4326-8874-6e6543c0e0d2\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ventes</th>\n",
       "      <th>mediane</th>\n",
       "      <th>q25</th>\n",
       "      <th>q75</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>nom_epci</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>CC du Briançonnais</th>\n",
       "      <td>185</td>\n",
       "      <td>200.0</td>\n",
       "      <td>122.0</td>\n",
       "      <td>348.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CA Durance-Lubéron-Verdon Agglomération</th>\n",
       "      <td>726</td>\n",
       "      <td>171.0</td>\n",
       "      <td>98.0</td>\n",
       "      <td>218.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC du Guillestrois et du Queyras</th>\n",
       "      <td>139</td>\n",
       "      <td>141.0</td>\n",
       "      <td>88.0</td>\n",
       "      <td>193.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CA Gap-Tallard-Durance</th>\n",
       "      <td>530</td>\n",
       "      <td>138.0</td>\n",
       "      <td>89.0</td>\n",
       "      <td>176.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Serre-Ponçon</th>\n",
       "      <td>323</td>\n",
       "      <td>137.0</td>\n",
       "      <td>75.0</td>\n",
       "      <td>182.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC du Pays des Ecrins</th>\n",
       "      <td>100</td>\n",
       "      <td>119.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>147.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Serre-Ponçon Val d'Avance</th>\n",
       "      <td>194</td>\n",
       "      <td>107.0</td>\n",
       "      <td>82.0</td>\n",
       "      <td>129.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Pays Forcalquier et Montagne de Lure</th>\n",
       "      <td>133</td>\n",
       "      <td>105.0</td>\n",
       "      <td>43.0</td>\n",
       "      <td>164.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Haute-Provence - Pays de Banon</th>\n",
       "      <td>100</td>\n",
       "      <td>102.0</td>\n",
       "      <td>61.0</td>\n",
       "      <td>119.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Champsaur-Valgaudemar</th>\n",
       "      <td>319</td>\n",
       "      <td>101.0</td>\n",
       "      <td>67.0</td>\n",
       "      <td>130.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Buëch-Dévoluy</th>\n",
       "      <td>180</td>\n",
       "      <td>98.0</td>\n",
       "      <td>55.0</td>\n",
       "      <td>176.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CA Provence-Alpes-Agglomération</th>\n",
       "      <td>551</td>\n",
       "      <td>94.0</td>\n",
       "      <td>52.0</td>\n",
       "      <td>121.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Vallée de l'Ubaye - Serre-Ponçon</th>\n",
       "      <td>196</td>\n",
       "      <td>93.0</td>\n",
       "      <td>53.0</td>\n",
       "      <td>140.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Jabron-Lure-Vançon-Durance</th>\n",
       "      <td>80</td>\n",
       "      <td>79.0</td>\n",
       "      <td>57.0</td>\n",
       "      <td>105.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC du Sisteronais-Buëch</th>\n",
       "      <td>269</td>\n",
       "      <td>66.0</td>\n",
       "      <td>38.0</td>\n",
       "      <td>103.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Alpes-Provence-Verdon \"Sources de lumière\"</th>\n",
       "      <td>195</td>\n",
       "      <td>64.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>102.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC Pays d'Apt-Luberon</th>\n",
       "      <td>13</td>\n",
       "      <td>62.0</td>\n",
       "      <td>34.0</td>\n",
       "      <td>88.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-6ce991bc-72ae-4326-8874-6e6543c0e0d2')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-6ce991bc-72ae-4326-8874-6e6543c0e0d2 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-6ce991bc-72ae-4326-8874-6e6543c0e0d2');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "variable_name": "par_epci",
       "summary": "{\n  \"name\": \"par_epci\",\n  \"rows\": 17,\n  \"fields\": [\n    {\n      \"column\": \"nom_epci\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 17,\n        \"samples\": [\n          \"CC du Brian\\u00e7onnais\",\n          \"CA Durance-Lub\\u00e9ron-Verdon Agglom\\u00e9ration\",\n          \"CC du Pays des Ecrins\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"ventes\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 190,\n        \"min\": 13,\n        \"max\": 726,\n        \"num_unique_values\": 16,\n        \"samples\": [\n          185,\n          726,\n          100\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"mediane\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 37.54840013823727,\n        \"min\": 62.0,\n        \"max\": 200.0,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          200.0,\n          171.0,\n          119.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"q25\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 24.14935147101446,\n        \"min\": 34.0,\n        \"max\": 122.0,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          122.0,\n          98.0,\n          81.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"q75\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 61.6927276675203,\n        \"min\": 88.0,\n        \"max\": 348.0,\n        \"num_unique_values\": 16,\n        \"samples\": [\n          348.0,\n          218.0,\n          147.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {}
    },
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Saving figure prix_par_epci\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 1600x700 with 3 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "648437b8f378"
   },
   "source": [
    "**Lecture.** La localisation pèse lourd. La commune explique à elle seule 46 % de la variation du prix (η²) et l'intercommunalité 24 %, mais le chiffre de la commune est gonflé par ses 254 groupes, dont beaucoup n'ont que quelques ventes.\n",
    "Le prix médian va de 62 à 64 €/m² (Pays d'Apt-Luberon, Alpes-Provence-Verdon) à 200 €/m² dans le Briançonnais : un rapport de 1 à 3. Les deux départements se distinguent à peine (η² de 1 %), la différence se joue entre vallées et bassins de vie."
   ],
   "id": "648437b8f378"
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "b4c7de98",
   "metadata": {
    "id": "b4c7de98",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537375730,
     "user_tz": -120,
     "elapsed": 1,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "corr_matrix = alpes_analysis.corr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "2f4b271d",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 429
    },
    "id": "2f4b271d",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537375734,
     "user_tz": -120,
     "elapsed": 3,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "61c74089-9d38-4935-92ba-fbbc73766d57"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "prix_m2               1.000000\n",
       "population_commune    0.149624\n",
       "part_AB               0.130188\n",
       "latitude              0.064801\n",
       "altitude              0.050285\n",
       "pente_pct             0.041338\n",
       "longitude             0.009979\n",
       "orientation_sud      -0.009796\n",
       "dist_cours_eau_m     -0.015710\n",
       "annee                -0.031589\n",
       "surface              -0.353374\n",
       "Name: prix_m2, dtype: float64"
      ],
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>prix_m2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>prix_m2</th>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>population_commune</th>\n",
       "      <td>0.149624</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>part_AB</th>\n",
       "      <td>0.130188</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>latitude</th>\n",
       "      <td>0.064801</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>altitude</th>\n",
       "      <td>0.050285</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pente_pct</th>\n",
       "      <td>0.041338</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>longitude</th>\n",
       "      <td>0.009979</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>orientation_sud</th>\n",
       "      <td>-0.009796</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dist_cours_eau_m</th>\n",
       "      <td>-0.015710</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>annee</th>\n",
       "      <td>-0.031589</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>surface</th>\n",
       "      <td>-0.353374</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><br><label><b>dtype:</b> float64</label>"
      ]
     },
     "metadata": {},
     "execution_count": 33
    }
   ],
   "source": [
    "corr_matrix[\"prix_m2\"].sort_values(ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "b545ae3b",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 924
    },
    "id": "b545ae3b",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537379092,
     "user_tz": -120,
     "elapsed": 3357,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "fa0e7413-0314-4713-d653-5d161ba3e545"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Saving figure scatter_matrix_plot\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 1200x900 with 25 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": [
    "from pandas.plotting import scatter_matrix\n",
    "\n",
    "# Nuages de points croisés des variables les plus liées au prix (prix et surface en log pour lisser les extrêmes)\n",
    "vue = pd.DataFrame({\"log_prix\": np.log(alpes[\"prix_m2\"]), \"log_surface\": np.log(alpes[\"surface\"])})\n",
    "for c in [\"nb_ventes_commune\", \"population_commune\", \"part_AB\", \"altitude\"]:\n",
    "    if c in alpes.columns:\n",
    "        vue[c] = alpes[c]\n",
    "scatter_matrix(vue, figsize=(12, 9), alpha=0.2)\n",
    "save_fig(\"scatter_matrix_plot\")"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# La cible vue de près : prix au m² (asymétrique) et son log (quasi symétrique)\n",
    "fig, axes = plt.subplots(1, 2, figsize=(12, 4))\n",
    "alpes[\"prix_m2\"].hist(bins=50, ax=axes[0])\n",
    "axes[0].set_title(\"Prix au m² (euros 2025)\")\n",
    "axes[0].set_xlabel(\"€/m²\")\n",
    "np.log(alpes[\"prix_m2\"]).hist(bins=50, ax=axes[1])\n",
    "axes[1].set_title(\"log(prix au m²)\")\n",
    "axes[1].set_xlabel(\"log(€/m²)\")\n",
    "print(\"Asymétrie du prix :\", round(alpes[\"prix_m2\"].skew(), 2), \"| du log(prix) :\", round(np.log(alpes[\"prix_m2\"]).skew(), 2))\n",
    "save_fig(\"prix_m2_histogram\")\n",
    "plt.show()"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 442
    },
    "id": "LBWKmiYZO-SV",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537379933,
     "user_tz": -120,
     "elapsed": 836,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "1d9eaa22-0169-41fb-dbfa-d075e3e2a7c0"
   },
   "id": "LBWKmiYZO-SV",
   "execution_count": 36,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Asymétrie du prix : 1.94 | du log(prix) : -0.47\n",
      "Saving figure prix_m2_histogram\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 1200x400 with 2 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "5c5dc2df3418"
   },
   "source": [
    "**Lecture.** Le prix au m² est très asymétrique (1,94) : beaucoup de ventes entre 50 et 150 €/m², quelques-unes bien au-dessus. Son log est presque symétrique (-0,47). Les modèles sont entraînés sur le prix brut, comme dans le cours, et une variante en log est testée dans « Au-delà du cours »."
   ],
   "id": "5c5dc2df3418"
  },
  {
   "cell_type": "markdown",
   "id": "307c01a2",
   "metadata": {
    "id": "307c01a2"
   },
   "source": [
    "## Experimenting with Attribute Combinations\n",
    "\n",
    "Équivalent de `rooms_per_household` : on crée des variables plus parlantes que les données brutes.\n",
    "- `dist_prefecture_km` : distance à la préfecture du département (accès aux services, à l'emploi) ;\n",
    "- `dist_pole_km` : distance à la ville de plus de 10 000 habitants la plus proche (Gap, Manosque, Digne-les-Bains, Briançon) ;\n",
    "- `nb_ventes_commune` : nombre de ventes dans la commune sur la période (dynamisme du marché) ;\n",
    "- `log_population`, `log_surface` : population et surface en log, pour lisser les très grandes valeurs ;\n",
    "- maison uniquement : `terrain_par_m2_bati` (grand jardin ou non)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "4b52e4fa",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "4b52e4fa",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537379959,
     "user_tz": -120,
     "elapsed": 23,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "bbcc04ad-12e0-4566-e337-65a005c164f6"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Villes pôles : Gap, Manosque, Digne-les-Bains, Briançon\n"
     ]
    }
   ],
   "source": [
    "PREFECTURES = {\"04\": (6.2357, 44.0925), \"05\": (6.0794, 44.5594), \"06\": (7.2620, 43.7102),\n",
    "               \"38\": (5.7245, 45.1885), \"73\": (5.9178, 45.5646), \"74\": (6.1294, 45.8992)}\n",
    "SEUIL_POLE = 10000   # habitants : une \"ville pôle\" (Gap, Manosque, Digne, Briançon pour le 04 + 05)\n",
    "\n",
    "def haversine_km(lon1, lat1, lon2, lat2):\n",
    "    lon1, lat1, lon2, lat2 = map(np.radians, [lon1, lat1, lon2, lat2])\n",
    "    a = np.sin((lat2 - lat1) / 2) ** 2 + np.cos(lat1) * np.cos(lat2) * np.sin((lon2 - lon1) / 2) ** 2\n",
    "    return 6371 * 2 * np.arcsin(np.sqrt(a))\n",
    "\n",
    "# 1) Distance à la préfecture du département (comme dans la première version)\n",
    "pref_lon = alpes[\"code_departement\"].map(lambda d: PREFECTURES[d][0])\n",
    "pref_lat = alpes[\"code_departement\"].map(lambda d: PREFECTURES[d][1])\n",
    "alpes[\"dist_prefecture_km\"] = haversine_km(alpes[\"longitude\"], alpes[\"latitude\"], pref_lon, pref_lat)\n",
    "\n",
    "# 2) Distance à la ville pôle la plus proche (plus parlant : Briançon et Manosque sont loin de leur préfecture)\n",
    "poles = villes_epci[villes_epci[\"population\"] >= SEUIL_POLE]\n",
    "print(\"Villes pôles :\", \", \".join(poles[\"nom\"]))\n",
    "distances = pd.concat([haversine_km(alpes[\"longitude\"], alpes[\"latitude\"], p[\"lon\"], p[\"lat\"]).rename(p[\"nom\"])\n",
    "                       for _, p in poles.iterrows()], axis=1)\n",
    "alpes[\"dist_pole_km\"] = distances.min(axis=1)\n",
    "\n",
    "# 3) Dynamisme du marché, taille de la commune (en log), surface (en log)\n",
    "alpes[\"nb_ventes_commune\"] = alpes.groupby(\"code_commune\")[\"prix_m2\"].transform(\"count\")\n",
    "alpes[\"log_population\"] = np.log(alpes[\"population_commune\"])\n",
    "alpes[\"log_surface\"] = np.log(alpes[\"surface\"])   # le prix au m² baisse vite puis s'aplatit avec la surface\n",
    "\n",
    "if TYPE_BIEN == \"maison\":\n",
    "    alpes[\"terrain_par_m2_bati\"] = alpes[\"surface_terrain\"] / alpes[\"surface\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "00e19bdb",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 520
    },
    "id": "00e19bdb",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537380025,
     "user_tz": -120,
     "elapsed": 65,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "ad28235c-0f6d-42f9-fdb4-b73df1860973"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "                    Pearson prix  Pearson log(prix)  Spearman prix\n",
       "surface                   -0.353             -0.497         -0.623\n",
       "log_surface               -0.498             -0.614         -0.623\n",
       "nb_ventes_commune          0.187              0.223          0.326\n",
       "dist_pole_km              -0.278             -0.285         -0.312\n",
       "log_population             0.223              0.249          0.276\n",
       "population_commune         0.150              0.157          0.276\n",
       "part_AB                    0.130              0.253          0.242\n",
       "dist_prefecture_km         0.209              0.122          0.140\n",
       "altitude                   0.050              0.004         -0.067\n",
       "longitude                  0.010             -0.016         -0.062\n",
       "annee                     -0.032             -0.044         -0.038\n",
       "orientation_sud           -0.010             -0.015         -0.030\n",
       "pente_pct                  0.041             -0.010          0.027\n",
       "latitude                   0.065              0.040          0.022\n",
       "dist_cours_eau_m          -0.016              0.008          0.008"
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-6668b9c6-5e3c-44dc-acf1-a86f343b5ba7\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Pearson prix</th>\n",
       "      <th>Pearson log(prix)</th>\n",
       "      <th>Spearman prix</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>surface</th>\n",
       "      <td>-0.353</td>\n",
       "      <td>-0.497</td>\n",
       "      <td>-0.623</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log_surface</th>\n",
       "      <td>-0.498</td>\n",
       "      <td>-0.614</td>\n",
       "      <td>-0.623</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>nb_ventes_commune</th>\n",
       "      <td>0.187</td>\n",
       "      <td>0.223</td>\n",
       "      <td>0.326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dist_pole_km</th>\n",
       "      <td>-0.278</td>\n",
       "      <td>-0.285</td>\n",
       "      <td>-0.312</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log_population</th>\n",
       "      <td>0.223</td>\n",
       "      <td>0.249</td>\n",
       "      <td>0.276</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>population_commune</th>\n",
       "      <td>0.150</td>\n",
       "      <td>0.157</td>\n",
       "      <td>0.276</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>part_AB</th>\n",
       "      <td>0.130</td>\n",
       "      <td>0.253</td>\n",
       "      <td>0.242</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dist_prefecture_km</th>\n",
       "      <td>0.209</td>\n",
       "      <td>0.122</td>\n",
       "      <td>0.140</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>altitude</th>\n",
       "      <td>0.050</td>\n",
       "      <td>0.004</td>\n",
       "      <td>-0.067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>longitude</th>\n",
       "      <td>0.010</td>\n",
       "      <td>-0.016</td>\n",
       "      <td>-0.062</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>annee</th>\n",
       "      <td>-0.032</td>\n",
       "      <td>-0.044</td>\n",
       "      <td>-0.038</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>orientation_sud</th>\n",
       "      <td>-0.010</td>\n",
       "      <td>-0.015</td>\n",
       "      <td>-0.030</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pente_pct</th>\n",
       "      <td>0.041</td>\n",
       "      <td>-0.010</td>\n",
       "      <td>0.027</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>latitude</th>\n",
       "      <td>0.065</td>\n",
       "      <td>0.040</td>\n",
       "      <td>0.022</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dist_cours_eau_m</th>\n",
       "      <td>-0.016</td>\n",
       "      <td>0.008</td>\n",
       "      <td>0.008</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-6668b9c6-5e3c-44dc-acf1-a86f343b5ba7')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-6668b9c6-5e3c-44dc-acf1-a86f343b5ba7 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-6668b9c6-5e3c-44dc-acf1-a86f343b5ba7');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "summary": "{\n  \"name\": \"tableau_corr\",\n  \"rows\": 15,\n  \"fields\": [\n    {\n      \"column\": \"Pearson prix\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.21155373065105934,\n        \"min\": -0.498,\n        \"max\": 0.223,\n        \"num_unique_values\": 15,\n        \"samples\": [\n          0.01,\n          -0.01,\n          -0.353\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Pearson log(prix)\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.2553229514238967,\n        \"min\": -0.614,\n        \"max\": 0.253,\n        \"num_unique_values\": 15,\n        \"samples\": [\n          -0.016,\n          -0.015,\n          -0.497\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Spearman prix\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.29393371458787876,\n        \"min\": -0.623,\n        \"max\": 0.326,\n        \"num_unique_values\": 13,\n        \"samples\": [\n          0.022,\n          -0.03,\n          -0.623\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {},
     "execution_count": 38
    }
   ],
   "source": [
    "# Trois mesures du lien avec le prix, côte à côte :\n",
    "#  - Pearson prix     : relation en ligne droite (celle du cours)\n",
    "#  - Pearson log(prix): idem, avec le prix en log (distribution plus symétrique)\n",
    "#  - Spearman prix    : relation \"plus A monte, plus B monte (ou baisse)\", même si ce n'est pas une ligne droite\n",
    "alpes_analysis = alpes.select_dtypes(include=\"number\").copy()\n",
    "alpes_analysis[\"log_prix\"] = np.log(alpes_analysis[\"prix_m2\"])   # pour l'analyse seulement : PAS ajouté à alpes (sinon fuite de la cible)\n",
    "\n",
    "corr_matrix = alpes_analysis.corr()\n",
    "tableau_corr = pd.DataFrame({\n",
    "    \"Pearson prix\": corr_matrix[\"prix_m2\"],\n",
    "    \"Pearson log(prix)\": corr_matrix[\"log_prix\"],\n",
    "    \"Spearman prix\": alpes_analysis.corr(method=\"spearman\")[\"prix_m2\"],\n",
    "}).drop([\"prix_m2\", \"log_prix\"])\n",
    "tableau_corr.round(3).sort_values(\"Spearman prix\", key=abs, ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "97864d30",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "97864d30",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537380734,
     "user_tz": -120,
     "elapsed": 704,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "19589c8a-7fad-4eea-ee0b-3ebc82ce7e1e"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Prix médian au m² selon la distance à la ville pôle la plus proche\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "            ventes  prix_median\n",
       "0 à 5 km       649        162.0\n",
       "5 à 10 km      560        141.0\n",
       "10 à 15 km     940        119.0\n",
       "15 à 20 km     458        100.0\n",
       "20 à 25 km     381         96.0\n",
       "25 à 30 km     444         83.0\n",
       "30 à 35 km     332         75.0\n",
       "35 à 40 km     162         87.0\n",
       "40 à 45 km      92        110.0\n",
       "45 à 50 km      82        112.0\n",
       "50 à 55 km      36         72.0"
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-b2a0f93c-3986-42dc-9720-72bd58aa032c\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ventes</th>\n",
       "      <th>prix_median</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0 à 5 km</th>\n",
       "      <td>649</td>\n",
       "      <td>162.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5 à 10 km</th>\n",
       "      <td>560</td>\n",
       "      <td>141.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10 à 15 km</th>\n",
       "      <td>940</td>\n",
       "      <td>119.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15 à 20 km</th>\n",
       "      <td>458</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20 à 25 km</th>\n",
       "      <td>381</td>\n",
       "      <td>96.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25 à 30 km</th>\n",
       "      <td>444</td>\n",
       "      <td>83.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30 à 35 km</th>\n",
       "      <td>332</td>\n",
       "      <td>75.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35 à 40 km</th>\n",
       "      <td>162</td>\n",
       "      <td>87.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40 à 45 km</th>\n",
       "      <td>92</td>\n",
       "      <td>110.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45 à 50 km</th>\n",
       "      <td>82</td>\n",
       "      <td>112.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50 à 55 km</th>\n",
       "      <td>36</td>\n",
       "      <td>72.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b2a0f93c-3986-42dc-9720-72bd58aa032c')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-b2a0f93c-3986-42dc-9720-72bd58aa032c button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-b2a0f93c-3986-42dc-9720-72bd58aa032c');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "summary": "{\n  \"name\": \"plt\",\n  \"rows\": 11,\n  \"fields\": [\n    {\n      \"column\": \"ventes\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 277,\n        \"min\": 36,\n        \"max\": 940,\n        \"num_unique_values\": 11,\n        \"samples\": [\n          444,\n          649,\n          82\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"prix_median\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 27.780634196570034,\n        \"min\": 72.0,\n        \"max\": 162.0,\n        \"num_unique_values\": 11,\n        \"samples\": [\n          83.0,\n          162.0,\n          112.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {}
    },
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Petits : 150 à 625 m² | moyens : jusqu'à 1057 m² | grands : jusqu'à 16704 m²\n",
      "Prix médian au m² selon la taille du terrain et la distance\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "dist_pole_km  0-5 km  5-15 km  15-25 km  plus de 25 km\n",
       "surface                                               \n",
       "petits         206.0    170.0     143.0          131.0\n",
       "moyens         157.0    123.0     102.0          101.0\n",
       "grands          84.0     66.0      55.0           52.0"
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-b4adcf89-a3ec-4f8b-9da6-b07187cccb1a\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>dist_pole_km</th>\n",
       "      <th>0-5 km</th>\n",
       "      <th>5-15 km</th>\n",
       "      <th>15-25 km</th>\n",
       "      <th>plus de 25 km</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>surface</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>petits</th>\n",
       "      <td>206.0</td>\n",
       "      <td>170.0</td>\n",
       "      <td>143.0</td>\n",
       "      <td>131.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>moyens</th>\n",
       "      <td>157.0</td>\n",
       "      <td>123.0</td>\n",
       "      <td>102.0</td>\n",
       "      <td>101.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>grands</th>\n",
       "      <td>84.0</td>\n",
       "      <td>66.0</td>\n",
       "      <td>55.0</td>\n",
       "      <td>52.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b4adcf89-a3ec-4f8b-9da6-b07187cccb1a')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-b4adcf89-a3ec-4f8b-9da6-b07187cccb1a button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-b4adcf89-a3ec-4f8b-9da6-b07187cccb1a');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "variable_name": "croise",
       "summary": "{\n  \"name\": \"croise\",\n  \"rows\": 3,\n  \"fields\": [\n    {\n      \"column\": \"surface\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"petits\",\n          \"moyens\",\n          \"grands\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"0-5 km\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 61.39218191268331,\n        \"min\": 84.0,\n        \"max\": 206.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          206.0,\n          157.0,\n          84.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"5-15 km\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 52.080066564217574,\n        \"min\": 66.0,\n        \"max\": 170.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          170.0,\n          123.0,\n          66.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"15-25 km\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 44.034077712607996,\n        \"min\": 55.0,\n        \"max\": 143.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          143.0,\n          102.0,\n          55.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"plus de 25 km\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 39.878983604567125,\n        \"min\": 52.0,\n        \"max\": 131.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          131.0,\n          101.0,\n          52.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {}
    },
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Saving figure prix_distance_par_taille\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 800x400 with 1 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": [
    "# Effet de la distance à la ville pôle, en tableaux (plus lisible que le nuage de points)\n",
    "\n",
    "# 1) Prix médian par tranche de 5 km\n",
    "tranche_5km = ((alpes[\"dist_pole_km\"] // 5) * 5).astype(\"Int64\")\n",
    "par_distance = (alpes.groupby(tranche_5km)[\"prix_m2\"].agg(ventes=\"count\", prix_median=\"median\").round())\n",
    "par_distance.index = [f\"{d} à {d + 5} km\" for d in par_distance.index]\n",
    "print(\"Prix médian au m² selon la distance à la ville pôle la plus proche\")\n",
    "display(par_distance[par_distance[\"ventes\"] >= 20])   # tranches avec au moins 20 ventes\n",
    "\n",
    "# 2) Même chose à surface égale : petits / moyens / grands terrains (un tiers des ventes chacun)\n",
    "taille_terrain = pd.qcut(alpes[\"surface\"], 3, labels=[\"petits\", \"moyens\", \"grands\"])\n",
    "bornes = pd.qcut(alpes[\"surface\"], 3, retbins=True)[1].round()\n",
    "print(f\"Petits : {bornes[0]:.0f} à {bornes[1]:.0f} m² | moyens : jusqu'à {bornes[2]:.0f} m² | grands : jusqu'à {bornes[3]:.0f} m²\")\n",
    "bandes = pd.cut(alpes[\"dist_pole_km\"], [0, 5, 15, 25, 100], labels=[\"0-5 km\", \"5-15 km\", \"15-25 km\", \"plus de 25 km\"])\n",
    "croise = alpes.groupby([taille_terrain, bandes], observed=True)[\"prix_m2\"].median().unstack().round()\n",
    "print(\"Prix médian au m² selon la taille du terrain et la distance\")\n",
    "display(croise)\n",
    "\n",
    "# 3) Le même tableau en graphique : une ligne par taille de terrain\n",
    "ax = croise.T.plot(marker=\"o\", figsize=(8, 4))\n",
    "ax.set_xlabel(\"Distance à la ville pôle la plus proche\")\n",
    "ax.set_ylabel(\"Prix médian au m² (euros 2025)\")\n",
    "ax.set_title(\"Le prix baisse avec la distance, quelle que soit la taille du terrain\")\n",
    "ax.legend(title=\"Terrains\")\n",
    "save_fig(\"prix_distance_par_taille\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "16a73c84122a"
   },
   "source": [
    "**Lecture.**\n",
    "- La surface est le premier facteur (Spearman -0,62) : plus le terrain est grand, plus le prix au m² baisse.\n",
    "- La distance à la ville pôle compte ensuite. Le prix médian passe de 162 €/m² à moins de 5 km à 75 €/m² vers 30-35 km, puis remonte à 110 €/m² vers 40-50 km : ce sont les stations et les vallées touristiques. L'effet tient à surface égale (petits terrains : 206 €/m² près du pôle, 131 au-delà de 25 km).\n",
    "- `dist_prefecture_km` a un signe trompeur (positif) : Briançon et Manosque, chers, sont loin de leur préfecture. Elle est gardée, mais à lire avec prudence.\n",
    "- Altitude, pente, orientation et distance aux cours d'eau ne sont presque pas corrélées au prix prises seules. Le Random Forest peut quand même s'en servir en les combinant aux autres variables."
   ],
   "id": "16a73c84122a"
  },
  {
   "cell_type": "markdown",
   "id": "4248595d",
   "metadata": {
    "id": "4248595d"
   },
   "source": [
    "# Prepare the Data for Machine Learning Algorithms"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ab6c0284",
   "metadata": {
    "id": "ab6c0284"
   },
   "source": [
    "## Missing Data Cleaning"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e3898ccc",
   "metadata": {
    "id": "e3898ccc"
   },
   "source": [
    "3 options are possible (comme dans le cours) :\n",
    "\n",
    "```python\n",
    "alpes.dropna(subset=[\"longitude\"])      # option 1 Get rid / corresponding sales\n",
    "alpes.drop(\"altitude\", axis=1)          # option 2 Get rid / whole attribute\n",
    "median = alpes[\"altitude\"].median()     # option 3 Set to some value e.g. median\n",
    "alpes[\"altitude\"].fillna(median, inplace=True)\n",
    "```\n",
    "\n",
    "Let's look at the rows that contain at least one null:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "b27c3f91",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 447
    },
    "id": "b27c3f91",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537380764,
     "user_tz": -120,
     "elapsed": 20,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "41e70ad2-359f-467a-a548-c140aceb12d1"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "[Sortie retirée de la version publique : elle affichait des ventes individuelles DVF.]\n"
     ]
    }
   ],
   "source": [
    "sample_incomplete_rows = alpes[alpes.isnull().any(axis=1)].head()\n",
    "sample_incomplete_rows"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "b9006b28",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 743
    },
    "id": "b9006b28",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537395885,
     "user_tz": -120,
     "elapsed": 4,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "cab8a546-8c1d-412b-f445-1f811c787040"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "code_departement       0\n",
       "nom_epci               0\n",
       "nom_commune            0\n",
       "code_commune           0\n",
       "annee                  0\n",
       "longitude             96\n",
       "latitude              96\n",
       "surface                0\n",
       "prix_m2                0\n",
       "type_mixite            0\n",
       "part_AB                0\n",
       "population_commune     0\n",
       "altitude              96\n",
       "pente_pct             96\n",
       "orientation_sud       96\n",
       "dist_cours_eau_m      96\n",
       "dist_prefecture_km    96\n",
       "dist_pole_km          96\n",
       "nb_ventes_commune      0\n",
       "log_population         0\n",
       "log_surface            0\n",
       "dtype: int64"
      ],
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>code_departement</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>nom_epci</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>nom_commune</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>code_commune</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>annee</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>longitude</th>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>latitude</th>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>surface</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>prix_m2</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>type_mixite</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>part_AB</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>population_commune</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>altitude</th>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pente_pct</th>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>orientation_sud</th>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dist_cours_eau_m</th>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dist_prefecture_km</th>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dist_pole_km</th>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>nb_ventes_commune</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log_population</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log_surface</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><br><label><b>dtype:</b> int64</label>"
      ]
     },
     "metadata": {},
     "execution_count": 43
    }
   ],
   "source": [
    "alpes.isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d1126af7",
   "metadata": {
    "id": "d1126af7"
   },
   "source": [
    "Retain **Option 1** for longitude / latitude (ventes non géocodées : impossible de les placer sur la carte),\n",
    "and **Option 3** (median) for the other numerical attributes (altitude, surface de terrain...)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "8712ac34",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "8712ac34",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537395917,
     "user_tz": -120,
     "elapsed": 31,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "fd4269bd-b6d3-4296-a250-a4512ac84e77"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Médianes utilisées : {}\n"
     ]
    },
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "np.int64(0)"
      ]
     },
     "metadata": {},
     "execution_count": 44
    }
   ],
   "source": [
    "# Option 1 : ventes sans coordonnées\n",
    "alpes = alpes.dropna(subset=[\"longitude\", \"latitude\"])\n",
    "\n",
    "# Option 3 : médiane pour les autres colonnes numériques\n",
    "medians = {}\n",
    "for col in alpes.select_dtypes(include=\"number\").columns:\n",
    "    if alpes[col].isnull().any():\n",
    "        medians[col] = alpes[col].median()\n",
    "        alpes[col] = alpes[col].fillna(medians[col])\n",
    "\n",
    "print(\"Médianes utilisées :\", medians)\n",
    "alpes.isnull().sum().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ed7d663b",
   "metadata": {
    "id": "ed7d663b"
   },
   "source": [
    "## Handling Text and Categorical Attributes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f84a632d",
   "metadata": {
    "id": "f84a632d"
   },
   "source": [
    "Now let's preprocess the categorical input feature, `code_departement` (équivalent de `ocean_proximity`) :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "a4ff09d7",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 178
    },
    "id": "a4ff09d7",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537395937,
     "user_tz": -120,
     "elapsed": 19,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "012f2ee4-c7e9-4bea-adf7-6efcc66646a2"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "code_departement\n",
       "04                  2079\n",
       "05                  2058\n",
       "Name: count, dtype: int64"
      ],
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>code_departement</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>04</th>\n",
       "      <td>2079</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>05</th>\n",
       "      <td>2058</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><br><label><b>dtype:</b> int64</label>"
      ]
     },
     "metadata": {},
     "execution_count": 45
    }
   ],
   "source": [
    "alpes_cat = alpes[[\"code_departement\"]]\n",
    "alpes_cat.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "e8c4abf0",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 811
    },
    "id": "e8c4abf0",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537395982,
     "user_tz": -120,
     "elapsed": 44,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "53ca9861-7533-4bd3-d7e9-0804e8453241"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "22 colonnes créées : dep_04, dep_05, mix_AB + dépendance, mix_AB + terrain non constructible, mix_AB seul, epci_CA Durance-Lubéron-Verdon Agglomération, epci_CA Gap-Tallard-Durance, epci_CA Provence-Alpes-Agglomération, epci_CC Alpes-Provence-Verdon \"Sources de lumière\", epci_CC Buëch-Dévoluy, epci_CC Champsaur-Valgaudemar, epci_CC Haute-Provence - Pays de Banon, epci_CC Jabron-Lure-Vançon-Durance, epci_CC Pays Forcalquier et Montagne de Lure, epci_CC Pays d'Apt-Luberon, epci_CC Serre-Ponçon, epci_CC Serre-Ponçon Val d'Avance, epci_CC Vallée de l'Ubaye - Serre-Ponçon, epci_CC du Briançonnais, epci_CC du Guillestrois et du Queyras, epci_CC du Pays des Ecrins, epci_CC du Sisteronais-Buëch\n"
     ]
    },
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "epci_CC Pays d'Apt-Luberon                              11\n",
       "mix_AB + dépendance                                     17\n",
       "epci_CC Jabron-Lure-Vançon-Durance                      79\n",
       "epci_CC Haute-Provence - Pays de Banon                  99\n",
       "epci_CC du Pays des Ecrins                              99\n",
       "epci_CC Pays Forcalquier et Montagne de Lure           129\n",
       "epci_CC du Guillestrois et du Queyras                  137\n",
       "epci_CC du Briançonnais                                175\n",
       "epci_CC Buëch-Dévoluy                                  180\n",
       "epci_CC Alpes-Provence-Verdon \"Sources de lumière\"     190\n",
       "epci_CC Serre-Ponçon Val d'Avance                      193\n",
       "epci_CC Vallée de l'Ubaye - Serre-Ponçon               195\n",
       "epci_CC du Sisteronais-Buëch                           265\n",
       "epci_CC Champsaur-Valgaudemar                          309\n",
       "epci_CC Serre-Ponçon                                   319\n",
       "epci_CA Gap-Tallard-Durance                            526\n",
       "epci_CA Provence-Alpes-Agglomération                   528\n",
       "epci_CA Durance-Lubéron-Verdon Agglomération           703\n",
       "mix_AB + terrain non constructible                     978\n",
       "dep_05                                                2058\n",
       "dep_04                                                2079\n",
       "mix_AB seul                                           3142\n",
       "dtype: int64"
      ],
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>epci_CC Pays d'Apt-Luberon</th>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mix_AB + dépendance</th>\n",
       "      <td>17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CC Jabron-Lure-Vançon-Durance</th>\n",
       "      <td>79</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CC Haute-Provence - Pays de Banon</th>\n",
       "      <td>99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CC du Pays des Ecrins</th>\n",
       "      <td>99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CC Pays Forcalquier et Montagne de Lure</th>\n",
       "      <td>129</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CC du Guillestrois et du Queyras</th>\n",
       "      <td>137</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CC du Briançonnais</th>\n",
       "      <td>175</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CC Buëch-Dévoluy</th>\n",
       "      <td>180</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CC Alpes-Provence-Verdon \"Sources de lumière\"</th>\n",
       "      <td>190</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CC Serre-Ponçon Val d'Avance</th>\n",
       "      <td>193</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CC Vallée de l'Ubaye - Serre-Ponçon</th>\n",
       "      <td>195</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CC du Sisteronais-Buëch</th>\n",
       "      <td>265</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CC Champsaur-Valgaudemar</th>\n",
       "      <td>309</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CC Serre-Ponçon</th>\n",
       "      <td>319</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CA Gap-Tallard-Durance</th>\n",
       "      <td>526</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CA Provence-Alpes-Agglomération</th>\n",
       "      <td>528</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>epci_CA Durance-Lubéron-Verdon Agglomération</th>\n",
       "      <td>703</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mix_AB + terrain non constructible</th>\n",
       "      <td>978</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dep_05</th>\n",
       "      <td>2058</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dep_04</th>\n",
       "      <td>2079</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mix_AB seul</th>\n",
       "      <td>3142</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><br><label><b>dtype:</b> int64</label>"
      ]
     },
     "metadata": {},
     "execution_count": 46
    }
   ],
   "source": [
    "# One-hot : une colonne 0/1 par département, par type de vente et par intercommunalité\n",
    "# (pd.get_dummies plutôt que LabelBinarizer, qui ne crée qu'une seule colonne quand il n'y a que 2 valeurs)\n",
    "prefixes = {\"code_departement\": \"dep\", \"type_mixite\": \"mix\", \"nom_epci\": \"epci\"}\n",
    "cat_cols = [c for c in prefixes if c in alpes.columns]\n",
    "df_cat_one_hot = pd.get_dummies(alpes[cat_cols], prefix=[prefixes[c] for c in cat_cols], dtype=int)\n",
    "print(df_cat_one_hot.shape[1], \"colonnes créées :\", \", \".join(df_cat_one_hot.columns))\n",
    "df_cat_one_hot.sum().sort_values()   # nombre de ventes par colonne (repérer les groupes presque vides)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "7733872e",
   "metadata": {
    "id": "7733872e",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537395983,
     "user_tz": -120,
     "elapsed": 3,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "# On garde les infos géographiques à part pour la carte finale, puis on retire les colonnes texte des features\n",
    "# (type_mixite est déjà dans df_cat_one_hot ; code_departement est retiré plus tard, après le split stratifié)\n",
    "infos_carte = alpes[[\"code_departement\", \"nom_epci\", \"nom_commune\", \"code_commune\"]].copy()\n",
    "a_retirer = [\"nom_epci\", \"nom_commune\", \"code_commune\"] + ([\"type_mixite\"] if \"type_mixite\" in alpes.columns else [])\n",
    "alpes = alpes.drop(a_retirer, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "7cba6851",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 226
    },
    "id": "7cba6851",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537395985,
     "user_tz": -120,
     "elapsed": 4,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "61190074-15c7-451b-f56b-d6d8e873836b"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "[Sortie retirée de la version publique : elle affichait des ventes individuelles DVF.]\n"
     ]
    }
   ],
   "source": [
    "alpes.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6f8824c3",
   "metadata": {
    "id": "6f8824c3"
   },
   "source": [
    "## Training and Test Data Split Simple Split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "bd0524c0",
   "metadata": {
    "id": "bd0524c0",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396311,
     "user_tz": -120,
     "elapsed": 326,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "# Simple Split\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "train_set, test_set = train_test_split(alpes, test_size=0.2, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "90cf66a2",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "90cf66a2",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396334,
     "user_tz": -120,
     "elapsed": 13,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "4c8e4549-2518-4f1a-9091-08aabb9d045a"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "(4137, 17)"
      ]
     },
     "metadata": {},
     "execution_count": 50
    }
   ],
   "source": [
    "alpes.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "60f09f82",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "60f09f82",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396335,
     "user_tz": -120,
     "elapsed": 9,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "97f39ed8-6c4a-4957-8595-6a5ea51b0bae"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "(3309, 17)"
      ]
     },
     "metadata": {},
     "execution_count": 51
    }
   ],
   "source": [
    "train_set.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "2bd3cd7c",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "2bd3cd7c",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396344,
     "user_tz": -120,
     "elapsed": 9,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "d2edd730-278a-4870-d876-0bad1bbfc507"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "(828, 17)"
      ]
     },
     "metadata": {},
     "execution_count": 52
    }
   ],
   "source": [
    "test_set.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "84e40863",
   "metadata": {
    "id": "84e40863"
   },
   "source": [
    "## Training and Test Data Split Stratified Split\n",
    "\n",
    "Même logique que le cours : on stratifie sur la variable **la plus corrélée au prix** (le revenu en Californie).\n",
    "On ne la connaît pas d'avance : on la lit dans la matrice de corrélation, puis on la découpe en 5 tranches de taille égale (`income_cat` devient `strat_cat`).\n",
    "Ici, c'est la **surface** qui ressort (Spearman 0,62). On peut aussi forcer un choix métier (ex. `dist_prefecture_km`, `altitude`)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "4f715176",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 492
    },
    "id": "4f715176",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396375,
     "user_tz": -120,
     "elapsed": 30,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "351b0a57-c487-450b-94a9-0d8e77a7726e"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "surface               0.619692\n",
       "nb_ventes_commune     0.334629\n",
       "dist_pole_km          0.312320\n",
       "population_commune    0.286483\n",
       "part_AB               0.246387\n",
       "dist_prefecture_km    0.140244\n",
       "altitude              0.067251\n",
       "longitude             0.061580\n",
       "annee                 0.039271\n",
       "orientation_sud       0.030100\n",
       "pente_pct             0.026946\n",
       "latitude              0.022461\n",
       "dist_cours_eau_m      0.007777\n",
       "dtype: float64"
      ],
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>surface</th>\n",
       "      <td>0.619692</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>nb_ventes_commune</th>\n",
       "      <td>0.334629</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dist_pole_km</th>\n",
       "      <td>0.312320</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>population_commune</th>\n",
       "      <td>0.286483</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>part_AB</th>\n",
       "      <td>0.246387</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dist_prefecture_km</th>\n",
       "      <td>0.140244</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>altitude</th>\n",
       "      <td>0.067251</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>longitude</th>\n",
       "      <td>0.061580</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>annee</th>\n",
       "      <td>0.039271</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>orientation_sud</th>\n",
       "      <td>0.030100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pente_pct</th>\n",
       "      <td>0.026946</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>latitude</th>\n",
       "      <td>0.022461</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dist_cours_eau_m</th>\n",
       "      <td>0.007777</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><br><label><b>dtype:</b> float64</label>"
      ]
     },
     "metadata": {},
     "execution_count": 53
    }
   ],
   "source": [
    "# Variable de stratification = la plus liée au prix (Spearman : capte aussi les relations non linéaires)\n",
    "# On exclut strat_cat (créée juste après) et les variables \"doublons\" en log (même classement que l'originale)\n",
    "a_exclure = [\"prix_m2\", \"strat_cat\", \"log_surface\", \"log_population\"]\n",
    "correlations = (alpes.select_dtypes(include=\"number\").drop(columns=a_exclure, errors=\"ignore\")\n",
    "                .corrwith(alpes[\"prix_m2\"], method=\"spearman\").abs().sort_values(ascending=False))\n",
    "correlations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "8da55d48",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 290
    },
    "id": "8da55d48",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396398,
     "user_tz": -120,
     "elapsed": 22,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "4eea690a-1747-40b7-c635-30c2daf24d86"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Variable de stratification : surface\n"
     ]
    },
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "strat_cat\n",
       "1    828\n",
       "5    828\n",
       "2    827\n",
       "3    827\n",
       "4    827\n",
       "Name: count, dtype: int64"
      ],
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>strat_cat</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>828</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>828</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>827</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>827</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>827</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><br><label><b>dtype:</b> int64</label>"
      ]
     },
     "metadata": {},
     "execution_count": 54
    }
   ],
   "source": [
    "STRAT_VAR = correlations.index[0]   # ou forcer, ex. STRAT_VAR = \"dist_prefecture_km\"\n",
    "print(\"Variable de stratification :\", STRAT_VAR)\n",
    "\n",
    "alpes[\"strat_cat\"] = pd.qcut(alpes[STRAT_VAR].rank(method=\"first\"), q=5, labels=[1, 2, 3, 4, 5])\n",
    "alpes[\"strat_cat\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "e5db27ae",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 457
    },
    "id": "e5db27ae",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396605,
     "user_tz": -120,
     "elapsed": 206,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "5e0e291a-b788-48db-cd70-1411fece0ccf"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "<Axes: >"
      ]
     },
     "metadata": {},
     "execution_count": 55
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": [
    "alpes[STRAT_VAR].hist(bins=50)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "ca74fd9c",
   "metadata": {
    "id": "ca74fd9c",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396658,
     "user_tz": -120,
     "elapsed": 52,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "strat_train_set, strat_test_set = train_test_split(alpes, test_size=0.2,\n",
    "                                                   stratify=alpes[\"strat_cat\"],\n",
    "                                                   random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "bbe7f515",
   "metadata": {
    "id": "bbe7f515",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396659,
     "user_tz": -120,
     "elapsed": 4,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "def dep_proportions(data):\n",
    "    return data[\"strat_cat\"].value_counts() / len(data)\n",
    "\n",
    "train_set, test_set = train_test_split(alpes, test_size=0.2, random_state=42)\n",
    "\n",
    "compare_props = pd.DataFrame({\n",
    "    \"Overall\": dep_proportions(alpes),\n",
    "    \"Stratified\": dep_proportions(strat_test_set),\n",
    "    \"Random\": dep_proportions(test_set),\n",
    "}).sort_index()\n",
    "compare_props[\"Rand. %error\"] = 100 * compare_props[\"Random\"] / compare_props[\"Overall\"] - 100\n",
    "compare_props[\"Strat. %error\"] = 100 * compare_props[\"Stratified\"] / compare_props[\"Overall\"] - 100"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "cd653025",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 238
    },
    "id": "cd653025",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396684,
     "user_tz": -120,
     "elapsed": 28,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "556e532a-2c4b-4c4d-bc4d-06b626018505"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "            Overall  Stratified    Random  Rand. %error  Strat. %error\n",
       "strat_cat                                                             \n",
       "1          0.200145    0.200483  0.181159     -9.485927       0.168907\n",
       "2          0.199903    0.199275  0.200483      0.290030      -0.314126\n",
       "3          0.199903    0.199275  0.213768      6.935755      -0.314126\n",
       "4          0.199903    0.200483  0.194444     -2.730754       0.290030\n",
       "5          0.200145    0.200483  0.210145      4.996324       0.168907"
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-f07723fc-e033-4d81-a0d5-c733d68c3361\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Overall</th>\n",
       "      <th>Stratified</th>\n",
       "      <th>Random</th>\n",
       "      <th>Rand. %error</th>\n",
       "      <th>Strat. %error</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>strat_cat</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.200145</td>\n",
       "      <td>0.200483</td>\n",
       "      <td>0.181159</td>\n",
       "      <td>-9.485927</td>\n",
       "      <td>0.168907</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.199903</td>\n",
       "      <td>0.199275</td>\n",
       "      <td>0.200483</td>\n",
       "      <td>0.290030</td>\n",
       "      <td>-0.314126</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.199903</td>\n",
       "      <td>0.199275</td>\n",
       "      <td>0.213768</td>\n",
       "      <td>6.935755</td>\n",
       "      <td>-0.314126</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.199903</td>\n",
       "      <td>0.200483</td>\n",
       "      <td>0.194444</td>\n",
       "      <td>-2.730754</td>\n",
       "      <td>0.290030</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.200145</td>\n",
       "      <td>0.200483</td>\n",
       "      <td>0.210145</td>\n",
       "      <td>4.996324</td>\n",
       "      <td>0.168907</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-f07723fc-e033-4d81-a0d5-c733d68c3361')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-f07723fc-e033-4d81-a0d5-c733d68c3361 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-f07723fc-e033-4d81-a0d5-c733d68c3361');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "variable_name": "compare_props",
       "summary": "{\n  \"name\": \"compare_props\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"strat_cat\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          2,\n          5,\n          3\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Overall\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.00013239607384703256,\n        \"min\": 0.1999033115784385,\n        \"max\": 0.2001450326323423,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0.1999033115784385,\n          0.2001450326323423\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Stratified\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.0006615006733154209,\n        \"min\": 0.19927536231884058,\n        \"max\": 0.20048309178743962,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0.19927536231884058,\n          0.20048309178743962\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Random\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.013024453830476243,\n        \"min\": 0.18115942028985507,\n        \"max\": 0.213768115942029,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          0.20048309178743962,\n          0.21014492753623187\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Rand. %error\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 6.5305417429005335,\n        \"min\": -9.485927326191984,\n        \"max\": 6.935755217917034,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          0.290030317368533,\n          4.9963243016172925\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Strat. %error\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.29091565314467377,\n        \"min\": -0.3141264917722566,\n        \"max\": 0.290030317368533,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          0.16890709234755263,\n          -0.3141264917722566\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {},
     "execution_count": 58
    }
   ],
   "source": [
    "compare_props"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "2db090ac",
   "metadata": {
    "id": "2db090ac",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396720,
     "user_tz": -120,
     "elapsed": 35,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "# One-hot du département, puis on retire la colonne texte (comme ocean_proximity) et strat_cat (comme income_cat)\n",
    "train_set = strat_train_set.join(df_cat_one_hot).drop([\"code_departement\", \"strat_cat\"], axis=1)\n",
    "test_set = strat_test_set.join(df_cat_one_hot).drop([\"code_departement\", \"strat_cat\"], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "207bee83",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 548
    },
    "id": "207bee83",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396745,
     "user_tz": -120,
     "elapsed": 24,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "d1703a66-1645-4487-83c1-9ea09d109b30"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "[Sortie retirée de la version publique : elle affichait des ventes individuelles DVF.]\n"
     ]
    }
   ],
   "source": [
    "train_set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "22f51afc",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 548
    },
    "id": "22f51afc",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396782,
     "user_tz": -120,
     "elapsed": 36,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "6090dd26-84c8-482d-c2d9-5db910c8667a"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "[Sortie retirée de la version publique : elle affichait des ventes individuelles DVF.]\n"
     ]
    }
   ],
   "source": [
    "test_set"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "50b19462",
   "metadata": {
    "id": "50b19462"
   },
   "source": [
    "## Features and Labels Split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "47af0061",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 360
    },
    "id": "47af0061",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396787,
     "user_tz": -120,
     "elapsed": 3,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "56e0db53-ae31-4a54-f10f-57379525211a"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "[Sortie retirée de la version publique : elle affichait des ventes individuelles DVF.]\n"
     ]
    }
   ],
   "source": [
    "alpes_features = train_set.drop(\"prix_m2\", axis=1) # drop labels for training set\n",
    "alpes_features.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "58a3636c",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 241
    },
    "id": "58a3636c",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396874,
     "user_tz": -120,
     "elapsed": 56,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "c2d4b442-4e1f-4afb-a5a3-d29a6613f94b"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "[Sortie retirée de la version publique : elle affichait des ventes individuelles DVF.]\n"
     ]
    }
   ],
   "source": [
    "alpes_labels = train_set[\"prix_m2\"]\n",
    "alpes_labels.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8bbb5f54",
   "metadata": {
    "id": "8bbb5f54"
   },
   "source": [
    "## Standardization of the Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "fc310ad4",
   "metadata": {
    "id": "fc310ad4",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396875,
     "user_tz": -120,
     "elapsed": 52,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "# Standardization: x_standardized = (x - mean) / standard_deviation\n",
    "\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "X_train = alpes_features.values\n",
    "\n",
    "scaler = StandardScaler()\n",
    "scaler.fit(X_train)\n",
    "alpes_prepared = scaler.transform(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "755f5fc4",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "755f5fc4",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396878,
     "user_tz": -120,
     "elapsed": 52,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "e89b3815-d4a9-42e2-a517-4ae794d2be5b"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "array([[ 1.15146684, -1.19912498, -1.06877659, ..., -0.18717063,\n",
       "        -0.1584075 , -0.2636083 ],\n",
       "       [ 0.83492586,  1.61137176,  1.03268551, ...,  5.34271868,\n",
       "        -0.1584075 , -0.2636083 ],\n",
       "       [-1.38086099,  1.17803635,  1.59528381, ..., -0.18717063,\n",
       "         6.31283232, -0.2636083 ],\n",
       "       ...,\n",
       "       [-1.38086099,  0.17359486, -0.99067971, ..., -0.18717063,\n",
       "        -0.1584075 , -0.2636083 ],\n",
       "       [-0.43123806, -1.15132809, -1.04357167, ..., -0.18717063,\n",
       "        -0.1584075 , -0.2636083 ],\n",
       "       [-1.06432002, -0.80023093,  1.11670441, ..., -0.18717063,\n",
       "        -0.1584075 , -0.2636083 ]])"
      ]
     },
     "metadata": {},
     "execution_count": 65
    }
   ],
   "source": [
    "alpes_prepared"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b6fa28c1",
   "metadata": {
    "id": "b6fa28c1"
   },
   "source": [
    "# Select and Train a Model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "56a1b064",
   "metadata": {
    "id": "56a1b064"
   },
   "source": [
    "## Training and Evaluating on the Training Set"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3c7737c1",
   "metadata": {
    "id": "3c7737c1"
   },
   "source": [
    "LinearRegression"
   ]
  },
  {
   "cell_type": "code",
   "source": [
    "# Point de référence : un modèle \"naïf\" qui prédit toujours le prix moyen de l'entraînement\n",
    "# Tout modèle utile doit faire nettement mieux que ces erreurs.\n",
    "from sklearn.metrics import mean_squared_error, mean_absolute_error\n",
    "\n",
    "prediction_naive = np.full(len(alpes_labels), alpes_labels.mean())\n",
    "naive_rmse = np.sqrt(mean_squared_error(alpes_labels, prediction_naive))\n",
    "naive_mae = mean_absolute_error(alpes_labels, prediction_naive)\n",
    "print(f\"Prix moyen : {alpes_labels.mean():.0f} €/m²\")\n",
    "print(f\"Modèle naïf : RMSE = {naive_rmse:.0f} €/m², MAE = {naive_mae:.0f} €/m²\")\n",
    "print(\"Nombre de variables données aux modèles :\", alpes_prepared.shape[1])"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "-xRX799sTqwb",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537396878,
     "user_tz": -120,
     "elapsed": 30,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "00d46066-f486-476e-e9e6-aafcaafb59ee"
   },
   "id": "-xRX799sTqwb",
   "execution_count": 66,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Prix moyen : 124 €/m²\n",
      "Modèle naïf : RMSE = 80 €/m², MAE = 60 €/m²\n",
      "Nombre de variables données aux modèles : 37\n"
     ]
    }
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "ea8f937c",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 81
    },
    "id": "ea8f937c",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537397195,
     "user_tz": -120,
     "elapsed": 326,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "b619a8a1-119b-4ed7-87db-992a3ef20dba"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "LinearRegression()"
      ],
      "text/html": [
       "<style>#sk-container-id-1 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: #000;\n",
       "  --sklearn-color-text-muted: #666;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-1 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-1 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: flex;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "  align-items: start;\n",
       "  justify-content: space-between;\n",
       "  gap: 0.5em;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label .caption {\n",
       "  font-size: 0.6rem;\n",
       "  font-weight: lighter;\n",
       "  color: var(--sklearn-color-text-muted);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-1 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-1 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 0.5em;\n",
       "  text-align: center;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LinearRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>LinearRegression</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.linear_model.LinearRegression.html\">?<span>Documentation for LinearRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>LinearRegression()</pre></div> </div></div></div></div>"
      ]
     },
     "metadata": {},
     "execution_count": 67
    }
   ],
   "source": [
    "from sklearn.linear_model import LinearRegression\n",
    "\n",
    "lin_reg = LinearRegression()\n",
    "lin_reg.fit(alpes_prepared, alpes_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "08a92109",
   "metadata": {
    "id": "08a92109",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537397196,
     "user_tz": -120,
     "elapsed": 2,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "# let's try the trained linear regression model on a few training instances\n",
    "some_data_prepared = alpes_prepared[:5]\n",
    "some_labels = alpes_labels[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "ad73e233",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "ad73e233",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537397214,
     "user_tz": -120,
     "elapsed": 17,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "1f88c961-6fd6-42dc-8031-9010be9ff861"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Predictions: [106.8651816  131.77725567 156.13586224  84.42349562  48.62435446]\n"
     ]
    }
   ],
   "source": [
    "some_predicted_result = lin_reg.predict(some_data_prepared)\n",
    "print(\"Predictions:\", some_predicted_result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "f7ff14e6",
   "metadata": {
    "id": "f7ff14e6",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537397216,
     "user_tz": -120,
     "elapsed": 1,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "def round_v(myList, n = 0):\n",
    "    List_rounded = [round(x, n) for x in myList]\n",
    "    return List_rounded"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "de0d1e5c",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "de0d1e5c",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537397229,
     "user_tz": -120,
     "elapsed": 12,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "cdfafffe-12e7-466b-cb01-0d43e8d4d82c"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Predictions: [np.float64(107.0), np.float64(132.0), np.float64(156.0), np.float64(84.0), np.float64(49.0)]\n"
     ]
    }
   ],
   "source": [
    "print(\"Predictions:\", round_v(some_predicted_result))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "28667869",
   "metadata": {
    "id": "28667869"
   },
   "source": [
    "Compare against the actual values:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "c3417558",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "c3417558",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537397241,
     "user_tz": -120,
     "elapsed": 11,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "e97c5129-3421-4774-de0e-6e2d50a7dd83"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Labels: [194.0, 46.0, 175.0, 56.0, 57.0]\n"
     ]
    }
   ],
   "source": [
    "print(\"Labels:\", round_v(list(some_labels)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "1a49ee6e",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "1a49ee6e",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537397253,
     "user_tz": -120,
     "elapsed": 10,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "dc34665c-83f5-49b3-f95e-464b0ffdfa54"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "56"
      ]
     },
     "metadata": {},
     "execution_count": 73
    }
   ],
   "source": [
    "from sklearn.metrics import mean_squared_error\n",
    "\n",
    "alpes_predictions = lin_reg.predict(alpes_prepared)\n",
    "lin_mse = mean_squared_error(alpes_labels, alpes_predictions)\n",
    "lin_rmse = np.sqrt(lin_mse)\n",
    "round(lin_rmse)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "c0d02828",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "c0d02828",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537397304,
     "user_tz": -120,
     "elapsed": 50,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "631423b6-ba20-4800-d8ca-5bd32aaff39a"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "37"
      ]
     },
     "metadata": {},
     "execution_count": 74
    }
   ],
   "source": [
    "from sklearn.metrics import mean_absolute_error\n",
    "\n",
    "lin_mae = mean_absolute_error(alpes_labels, alpes_predictions)\n",
    "round(lin_mae)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c4e71b78",
   "metadata": {
    "id": "c4e71b78"
   },
   "source": [
    "DecisionTreeRegressor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "76caf8ec",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 81
    },
    "id": "76caf8ec",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537397534,
     "user_tz": -120,
     "elapsed": 229,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "b846acd3-9eb2-4763-9b5b-f90973b42438"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "DecisionTreeRegressor(random_state=42)"
      ],
      "text/html": [
       "<style>#sk-container-id-2 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: #000;\n",
       "  --sklearn-color-text-muted: #666;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-2 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-2 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-2 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: flex;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "  align-items: start;\n",
       "  justify-content: space-between;\n",
       "  gap: 0.5em;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 label.sk-toggleable__label .caption {\n",
       "  font-size: 0.6rem;\n",
       "  font-weight: lighter;\n",
       "  color: var(--sklearn-color-text-muted);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-2 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-2 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-2 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-2 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 0.5em;\n",
       "  text-align: center;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-2 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-2 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>DecisionTreeRegressor(random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>DecisionTreeRegressor</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.tree.DecisionTreeRegressor.html\">?<span>Documentation for DecisionTreeRegressor</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>DecisionTreeRegressor(random_state=42)</pre></div> </div></div></div></div>"
      ]
     },
     "metadata": {},
     "execution_count": 75
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeRegressor\n",
    "\n",
    "tree_reg = DecisionTreeRegressor(random_state=42)\n",
    "tree_reg.fit(alpes_prepared, alpes_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "0b31935f",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "0b31935f",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537397548,
     "user_tz": -120,
     "elapsed": 13,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "d624a0ba-8734-4b56-db9f-15280bcb8549"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "np.float64(1.1508299264797461)"
      ]
     },
     "metadata": {},
     "execution_count": 76
    }
   ],
   "source": [
    "alpes_predictions = tree_reg.predict(alpes_prepared)\n",
    "tree_mse = mean_squared_error(alpes_labels, alpes_predictions)\n",
    "tree_rmse = np.sqrt(tree_mse)\n",
    "tree_rmse"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "97ed31fb",
   "metadata": {
    "id": "97ed31fb"
   },
   "source": [
    "## Better Evaluation Using Cross-Validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "7ed5cf61",
   "metadata": {
    "id": "7ed5cf61",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537398420,
     "user_tz": -120,
     "elapsed": 870,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import cross_val_score\n",
    "\n",
    "scores = cross_val_score(tree_reg, alpes_prepared, alpes_labels,\n",
    "                         scoring=\"neg_mean_squared_error\", cv=10)\n",
    "tree_rmse_scores = np.sqrt(-scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "id": "0c61cac9",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "0c61cac9",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537398442,
     "user_tz": -120,
     "elapsed": 17,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "4105ea02-5b1c-4bcf-8ee8-2ee7c4059dc2"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Scores: [np.float64(74.0), np.float64(60.0), np.float64(66.0), np.float64(65.0), np.float64(60.0), np.float64(64.0), np.float64(66.0), np.float64(51.0), np.float64(66.0), np.float64(69.0)]\n",
      "Mean: 64\n",
      "Standard deviation: 6\n"
     ]
    }
   ],
   "source": [
    "def display_scores(scores):\n",
    "    print(\"Scores:\", round_v(scores))\n",
    "    print(\"Mean:\", round(scores.mean()))\n",
    "    print(\"Standard deviation:\", round(scores.std()))\n",
    "\n",
    "display_scores(tree_rmse_scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "bd232003",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "bd232003",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537398454,
     "user_tz": -120,
     "elapsed": 15,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "49927153-b1db-4c1a-9f05-5a22f1b2b748"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Scores: [np.float64(62.0), np.float64(62.0), np.float64(60.0), np.float64(53.0), np.float64(64.0), np.float64(51.0), np.float64(56.0), np.float64(45.0), np.float64(55.0), np.float64(60.0)]\n",
      "Mean: 57\n",
      "Standard deviation: 6\n"
     ]
    }
   ],
   "source": [
    "lin_scores = cross_val_score(lin_reg, alpes_prepared, alpes_labels,\n",
    "                             scoring=\"neg_mean_squared_error\", cv=10)\n",
    "lin_rmse_scores = np.sqrt(-lin_scores)\n",
    "display_scores(lin_rmse_scores)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "05f3da47",
   "metadata": {
    "id": "05f3da47"
   },
   "source": [
    "RandomForestRegressor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "46feca69",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 81
    },
    "id": "46feca69",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537401132,
     "user_tz": -120,
     "elapsed": 2677,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "c9c5d716-b233-4b70-df7e-cbf55c7853d5"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "RandomForestRegressor(n_jobs=-1, random_state=42)"
      ],
      "text/html": [
       "<style>#sk-container-id-3 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: #000;\n",
       "  --sklearn-color-text-muted: #666;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-3 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-3 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-3 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: flex;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "  align-items: start;\n",
       "  justify-content: space-between;\n",
       "  gap: 0.5em;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 label.sk-toggleable__label .caption {\n",
       "  font-size: 0.6rem;\n",
       "  font-weight: lighter;\n",
       "  color: var(--sklearn-color-text-muted);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-3 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-3 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-3 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-3 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-3 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 0.5em;\n",
       "  text-align: center;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-3 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-3 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestRegressor(n_jobs=-1, random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>RandomForestRegressor</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.ensemble.RandomForestRegressor.html\">?<span>Documentation for RandomForestRegressor</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestRegressor(n_jobs=-1, random_state=42)</pre></div> </div></div></div></div>"
      ]
     },
     "metadata": {},
     "execution_count": 80
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor\n",
    "\n",
    "forest_reg = RandomForestRegressor(n_estimators=100, random_state=42, n_jobs=-1)\n",
    "forest_reg.fit(alpes_prepared, alpes_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "e7cecb22",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "e7cecb22",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537401197,
     "user_tz": -120,
     "elapsed": 64,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "be22e4ec-b25e-42b9-9e60-b15898b692b0"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "18"
      ]
     },
     "metadata": {},
     "execution_count": 81
    }
   ],
   "source": [
    "alpes_predictions = forest_reg.predict(alpes_prepared)\n",
    "forest_mse = mean_squared_error(alpes_labels, alpes_predictions)\n",
    "forest_rmse = round(np.sqrt(forest_mse))\n",
    "forest_rmse"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "e4c9fb30",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "e4c9fb30",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537429214,
     "user_tz": -120,
     "elapsed": 28016,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "4e5983a5-908e-4e35-9b0b-1e2acc1a14f7"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Scores: [np.float64(59.0), np.float64(49.0), np.float64(51.0), np.float64(43.0), np.float64(55.0), np.float64(43.0), np.float64(44.0), np.float64(37.0), np.float64(43.0), np.float64(49.0)]\n",
      "Mean: 47\n",
      "Standard deviation: 6\n"
     ]
    }
   ],
   "source": [
    "forest_scores = cross_val_score(forest_reg, alpes_prepared, alpes_labels,\n",
    "                                scoring=\"neg_mean_squared_error\", cv=10)\n",
    "forest_rmse_scores = np.sqrt(-forest_scores)\n",
    "display_scores(forest_rmse_scores)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "062ae3fa",
   "metadata": {
    "id": "062ae3fa"
   },
   "source": [
    "Support Vector Machine Regressor\n",
    "\n",
    "⚠️ Le SVM devient très lent au-delà de ~15 000 lignes : pour les maisons, on l'entraîne sur un échantillon."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "b4dd5d77",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "b4dd5d77",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537429783,
     "user_tz": -120,
     "elapsed": 571,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "88db867d-1956-4671-dc86-0c5568f62d20"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "58"
      ]
     },
     "metadata": {},
     "execution_count": 83
    }
   ],
   "source": [
    "from sklearn.svm import SVR\n",
    "\n",
    "N_SVM = min(15000, len(alpes_prepared))\n",
    "idx = np.random.RandomState(42).choice(len(alpes_prepared), N_SVM, replace=False)\n",
    "\n",
    "svm_reg = SVR(kernel=\"linear\")\n",
    "svm_reg.fit(alpes_prepared[idx], alpes_labels.iloc[idx])\n",
    "alpes_predictions = svm_reg.predict(alpes_prepared)\n",
    "svm_mse = mean_squared_error(alpes_labels, alpes_predictions)\n",
    "svm_rmse = np.sqrt(svm_mse)\n",
    "round(svm_rmse)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "93cf0115",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "93cf0115",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537432440,
     "user_tz": -120,
     "elapsed": 2657,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "a65b8034-d508-4194-b8db-88deae1a5e36"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Scores: [np.float64(60.0), np.float64(66.0), np.float64(52.0), np.float64(70.0), np.float64(62.0), np.float64(59.0), np.float64(52.0), np.float64(56.0), np.float64(54.0), np.float64(52.0)]\n",
      "Mean: 58\n",
      "Standard deviation: 6\n"
     ]
    }
   ],
   "source": [
    "svm_scores = cross_val_score(svm_reg, alpes_prepared[idx], alpes_labels.iloc[idx],\n",
    "                             scoring=\"neg_mean_squared_error\", cv=10)\n",
    "svm_rmse_scores = np.sqrt(-svm_scores)\n",
    "display_scores(svm_rmse_scores)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "5c54e5f9cda6"
   },
   "source": [
    "**Comparaison des modèles (RMSE en €/m², prix moyen 124 €/m²)**\n",
    "\n",
    "| Modèle | Erreur sur l'entraînement | Erreur en validation croisée (10 plis) |\n",
    "|---|---|---|\n",
    "| Naïf (prix moyen) | 80 | |\n",
    "| Régression linéaire | 56 | 57 (± 6) |\n",
    "| Arbre de décision | 1 | 64 (± 6) |\n",
    "| Random Forest | 18 | 47 (± 6) |\n",
    "| SVM (noyau linéaire) | 58 | 58 (± 6) |\n",
    "\n",
    "L'arbre apprend l'entraînement par cœur (erreur de 1) et généralise mal (64) : surapprentissage typique. La régression linéaire et le SVM linéaire plafonnent vers 57, car les effets de la surface et des distances ne sont pas linéaires. Le Random Forest est le meilleur (47) ; l'écart entre 18 et 47 montre qu'il surapprend lui aussi en partie, ce qui est courant pour une forêt. On le garde pour le réglage."
   ],
   "id": "5c54e5f9cda6"
  },
  {
   "cell_type": "markdown",
   "id": "ed95092a",
   "metadata": {
    "id": "ed95092a"
   },
   "source": [
    "# Fine-Tune Your Model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "28fcfba0",
   "metadata": {
    "id": "28fcfba0"
   },
   "source": [
    "## Grid Search"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "978ed30c",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 167
    },
    "id": "978ed30c",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537530810,
     "user_tz": -120,
     "elapsed": 98368,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "c458dbe7-34e9-437f-de28-895f9e94f607"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5, estimator=RandomForestRegressor(n_jobs=-1, random_state=42),\n",
       "             param_grid=[{'max_features': [4, 8, 12, 20, 30],\n",
       "                          'n_estimators': [30, 100, 200]}],\n",
       "             return_train_score=True, scoring='neg_mean_squared_error')"
      ],
      "text/html": [
       "<style>#sk-container-id-4 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: #000;\n",
       "  --sklearn-color-text-muted: #666;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-4 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-4 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-4 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: flex;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "  align-items: start;\n",
       "  justify-content: space-between;\n",
       "  gap: 0.5em;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 label.sk-toggleable__label .caption {\n",
       "  font-size: 0.6rem;\n",
       "  font-weight: lighter;\n",
       "  color: var(--sklearn-color-text-muted);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-4 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-4 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-4 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-4 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-4 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 0.5em;\n",
       "  text-align: center;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-4 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-4 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=5, estimator=RandomForestRegressor(n_jobs=-1, random_state=42),\n",
       "             param_grid=[{&#x27;max_features&#x27;: [4, 8, 12, 20, 30],\n",
       "                          &#x27;n_estimators&#x27;: [30, 100, 200]}],\n",
       "             return_train_score=True, scoring=&#x27;neg_mean_squared_error&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>GridSearchCV</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.model_selection.GridSearchCV.html\">?<span>Documentation for GridSearchCV</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>GridSearchCV(cv=5, estimator=RandomForestRegressor(n_jobs=-1, random_state=42),\n",
       "             param_grid=[{&#x27;max_features&#x27;: [4, 8, 12, 20, 30],\n",
       "                          &#x27;n_estimators&#x27;: [30, 100, 200]}],\n",
       "             return_train_score=True, scoring=&#x27;neg_mean_squared_error&#x27;)</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>best_estimator_: RandomForestRegressor</div></div></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestRegressor(max_features=4, n_estimators=200, n_jobs=-1,\n",
       "                      random_state=42)</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>RandomForestRegressor</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.ensemble.RandomForestRegressor.html\">?<span>Documentation for RandomForestRegressor</span></a></div></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestRegressor(max_features=4, n_estimators=200, n_jobs=-1,\n",
       "                      random_state=42)</pre></div> </div></div></div></div></div></div></div></div></div>"
      ]
     },
     "metadata": {},
     "execution_count": 85
    }
   ],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "# max_features = nombre de variables tirées au hasard à chaque embranchement d'un arbre\n",
    "# (le cours va de 2 à 8 pour 8 variables ; nous en avons ~37, donc on monte plus haut)\n",
    "param_grid = [\n",
    "    # 3 × 5 = 15 combinaisons\n",
    "    {'n_estimators': [30, 100, 200], 'max_features': [4, 8, 12, 20, 30]}]\n",
    "\n",
    "forest_reg = RandomForestRegressor(random_state=42, n_jobs=-1)\n",
    "\n",
    "# 5 découpages : 15 × 5 = 75 entraînements (environ 1 à 2 minutes)\n",
    "grid_search = GridSearchCV(forest_reg, param_grid, cv=5,\n",
    "                           scoring='neg_mean_squared_error',\n",
    "                           return_train_score=True)\n",
    "grid_search.fit(alpes_prepared, alpes_labels)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b0fb5744",
   "metadata": {
    "id": "b0fb5744"
   },
   "source": [
    "The best hyperparameter combination found:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "0a256eec",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "0a256eec",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537530812,
     "user_tz": -120,
     "elapsed": 28,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "d144a5a1-6bcd-460e-d9d1-c4d9f6436931"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "{'max_features': 4, 'n_estimators': 200}"
      ]
     },
     "metadata": {},
     "execution_count": 86
    }
   ],
   "source": [
    "grid_search.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "8a8dae14",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 98
    },
    "id": "8a8dae14",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537530812,
     "user_tz": -120,
     "elapsed": 16,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "9eb31d98-aa17-45cb-940b-115858ef9569"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "RandomForestRegressor(max_features=4, n_estimators=200, n_jobs=-1,\n",
       "                      random_state=42)"
      ],
      "text/html": [
       "<style>#sk-container-id-5 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: #000;\n",
       "  --sklearn-color-text-muted: #666;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-5 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-5 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-5 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-5 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-5 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: flex;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "  align-items: start;\n",
       "  justify-content: space-between;\n",
       "  gap: 0.5em;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 label.sk-toggleable__label .caption {\n",
       "  font-size: 0.6rem;\n",
       "  font-weight: lighter;\n",
       "  color: var(--sklearn-color-text-muted);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-5 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-5 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-5 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-5 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-5 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-5 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-5 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-5 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-5 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-5 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 0.5em;\n",
       "  text-align: center;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-5 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-5 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-5 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-5\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestRegressor(max_features=4, n_estimators=200, n_jobs=-1,\n",
       "                      random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" checked><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>RandomForestRegressor</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.ensemble.RandomForestRegressor.html\">?<span>Documentation for RandomForestRegressor</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestRegressor(max_features=4, n_estimators=200, n_jobs=-1,\n",
       "                      random_state=42)</pre></div> </div></div></div></div>"
      ]
     },
     "metadata": {},
     "execution_count": 87
    }
   ],
   "source": [
    "grid_search.best_estimator_"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7e198f3b",
   "metadata": {
    "id": "7e198f3b"
   },
   "source": [
    "Let's look at the score of each hyperparameter combination tested during the grid search:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "82455875",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "82455875",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537530812,
     "user_tz": -120,
     "elapsed": 12,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "80fd50ca-1475-4304-b7ce-ac883e49f8cb"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "46 {'max_features': 4, 'n_estimators': 30}\n",
      "46 {'max_features': 4, 'n_estimators': 100}\n",
      "46 {'max_features': 4, 'n_estimators': 200}\n",
      "47 {'max_features': 8, 'n_estimators': 30}\n",
      "46 {'max_features': 8, 'n_estimators': 100}\n",
      "46 {'max_features': 8, 'n_estimators': 200}\n",
      "48 {'max_features': 12, 'n_estimators': 30}\n",
      "47 {'max_features': 12, 'n_estimators': 100}\n",
      "47 {'max_features': 12, 'n_estimators': 200}\n",
      "48 {'max_features': 20, 'n_estimators': 30}\n",
      "48 {'max_features': 20, 'n_estimators': 100}\n",
      "47 {'max_features': 20, 'n_estimators': 200}\n",
      "49 {'max_features': 30, 'n_estimators': 30}\n",
      "48 {'max_features': 30, 'n_estimators': 100}\n",
      "48 {'max_features': 30, 'n_estimators': 200}\n"
     ]
    }
   ],
   "source": [
    "cvres = grid_search.cv_results_\n",
    "for mean_score, params in zip(cvres[\"mean_test_score\"], cvres[\"params\"]):\n",
    "    print(round(np.sqrt(-mean_score)), params)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a18c8244",
   "metadata": {
    "id": "a18c8244"
   },
   "source": [
    "## Randomized Search"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "c7937d73",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 167
    },
    "id": "c7937d73",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537585427,
     "user_tz": -120,
     "elapsed": 54618,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "c8e474c3-ce18-421b-af75-e1c9ce9fab1a"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "RandomizedSearchCV(cv=5,\n",
       "                   estimator=RandomForestRegressor(n_jobs=-1, random_state=42),\n",
       "                   param_distributions={'max_features': <scipy.stats._distn_infrastructure.rv_discrete_frozen object at 0x7c79c9b45450>,\n",
       "                                        'n_estimators': <scipy.stats._distn_infrastructure.rv_discrete_frozen object at 0x7c79d839b8c0>},\n",
       "                   random_state=42, scoring='neg_mean_squared_error')"
      ],
      "text/html": [
       "<style>#sk-container-id-6 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: #000;\n",
       "  --sklearn-color-text-muted: #666;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-6 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-6 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-6 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-6 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-6 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-6 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-6 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: flex;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "  align-items: start;\n",
       "  justify-content: space-between;\n",
       "  gap: 0.5em;\n",
       "}\n",
       "\n",
       "#sk-container-id-6 label.sk-toggleable__label .caption {\n",
       "  font-size: 0.6rem;\n",
       "  font-weight: lighter;\n",
       "  color: var(--sklearn-color-text-muted);\n",
       "}\n",
       "\n",
       "#sk-container-id-6 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-6 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-6 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-6 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-6 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-6 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-6 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-6 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-6 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-6 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-6 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-6 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-6 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-6 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 0.5em;\n",
       "  text-align: center;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-6 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-6 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-6 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-6 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-6\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomizedSearchCV(cv=5,\n",
       "                   estimator=RandomForestRegressor(n_jobs=-1, random_state=42),\n",
       "                   param_distributions={&#x27;max_features&#x27;: &lt;scipy.stats._distn_infrastructure.rv_discrete_frozen object at 0x7c79c9b45450&gt;,\n",
       "                                        &#x27;n_estimators&#x27;: &lt;scipy.stats._distn_infrastructure.rv_discrete_frozen object at 0x7c79d839b8c0&gt;},\n",
       "                   random_state=42, scoring=&#x27;neg_mean_squared_error&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>RandomizedSearchCV</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.model_selection.RandomizedSearchCV.html\">?<span>Documentation for RandomizedSearchCV</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>RandomizedSearchCV(cv=5,\n",
       "                   estimator=RandomForestRegressor(n_jobs=-1, random_state=42),\n",
       "                   param_distributions={&#x27;max_features&#x27;: &lt;scipy.stats._distn_infrastructure.rv_discrete_frozen object at 0x7c79c9b45450&gt;,\n",
       "                                        &#x27;n_estimators&#x27;: &lt;scipy.stats._distn_infrastructure.rv_discrete_frozen object at 0x7c79d839b8c0&gt;},\n",
       "                   random_state=42, scoring=&#x27;neg_mean_squared_error&#x27;)</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" ><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>best_estimator_: RandomForestRegressor</div></div></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestRegressor(max_features=3, n_estimators=192, n_jobs=-1,\n",
       "                      random_state=42)</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-10\" type=\"checkbox\" ><label for=\"sk-estimator-id-10\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>RandomForestRegressor</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.ensemble.RandomForestRegressor.html\">?<span>Documentation for RandomForestRegressor</span></a></div></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestRegressor(max_features=3, n_estimators=192, n_jobs=-1,\n",
       "                      random_state=42)</pre></div> </div></div></div></div></div></div></div></div></div>"
      ]
     },
     "metadata": {},
     "execution_count": 89
    }
   ],
   "source": [
    "from sklearn.model_selection import RandomizedSearchCV\n",
    "from scipy.stats import randint\n",
    "\n",
    "param_distribs = {\n",
    "        'n_estimators': randint(low=1, high=200),\n",
    "        'max_features': randint(low=2, high=35),\n",
    "        }\n",
    "\n",
    "forest_reg = RandomForestRegressor(random_state=42, n_jobs=-1)\n",
    "rnd_search = RandomizedSearchCV(forest_reg, param_distributions=param_distribs,\n",
    "                                n_iter=10, cv=5, scoring='neg_mean_squared_error', random_state=42)\n",
    "rnd_search.fit(alpes_prepared, alpes_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "eb381ad6",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 98
    },
    "id": "eb381ad6",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537585432,
     "user_tz": -120,
     "elapsed": 3,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "a385d273-490a-4a32-e3ef-3c32e6a2a245"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "RandomForestRegressor(max_features=3, n_estimators=192, n_jobs=-1,\n",
       "                      random_state=42)"
      ],
      "text/html": [
       "<style>#sk-container-id-7 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: #000;\n",
       "  --sklearn-color-text-muted: #666;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-7 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-7 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-7 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-7 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-7 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: flex;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "  align-items: start;\n",
       "  justify-content: space-between;\n",
       "  gap: 0.5em;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 label.sk-toggleable__label .caption {\n",
       "  font-size: 0.6rem;\n",
       "  font-weight: lighter;\n",
       "  color: var(--sklearn-color-text-muted);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-7 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-7 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-7 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-7 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-7 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-7 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-7 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-7 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-7 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-7 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 0.5em;\n",
       "  text-align: center;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-7 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-7 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-7 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-7\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestRegressor(max_features=3, n_estimators=192, n_jobs=-1,\n",
       "                      random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-11\" type=\"checkbox\" checked><label for=\"sk-estimator-id-11\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>RandomForestRegressor</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.ensemble.RandomForestRegressor.html\">?<span>Documentation for RandomForestRegressor</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestRegressor(max_features=3, n_estimators=192, n_jobs=-1,\n",
       "                      random_state=42)</pre></div> </div></div></div></div>"
      ]
     },
     "metadata": {},
     "execution_count": 90
    }
   ],
   "source": [
    "rnd_search.best_estimator_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "c75931d6",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "c75931d6",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537585443,
     "user_tz": -120,
     "elapsed": 10,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "eadecce2-9c2b-40aa-8f7f-3bb2e5c1831d"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "50 {'max_features': 30, 'n_estimators': 15}\n",
      "46 {'max_features': 9, 'n_estimators': 189}\n",
      "47 {'max_features': 22, 'n_estimators': 103}\n",
      "48 {'max_features': 20, 'n_estimators': 75}\n",
      "47 {'max_features': 12, 'n_estimators': 88}\n",
      "48 {'max_features': 25, 'n_estimators': 131}\n",
      "48 {'max_features': 23, 'n_estimators': 53}\n",
      "46 {'max_features': 3, 'n_estimators': 88}\n",
      "49 {'max_features': 31, 'n_estimators': 38}\n",
      "46 {'max_features': 3, 'n_estimators': 192}\n"
     ]
    }
   ],
   "source": [
    "cvres = rnd_search.cv_results_\n",
    "for mean_score, params in zip(cvres[\"mean_test_score\"], cvres[\"params\"]):\n",
    "    print(round(np.sqrt(-mean_score)), params)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "df3307ccbb21"
   },
   "source": [
    "**Lecture.** Les meilleurs réglages tournent autour de 46 €/m² en validation croisée (5 plis). Le Grid Search retient 4 variables tirées par embranchement et 200 arbres ; la Randomized Search trouve presque la même chose (3 variables, 192 arbres). Le nombre d'arbres change peu le résultat au-delà de 100. Peu de variables par embranchement donne de meilleurs scores, sans doute parce que beaucoup des 37 colonnes (intercommunalités en one-hot) apportent peu. On garde le modèle du Grid Search."
   ],
   "id": "df3307ccbb21"
  },
  {
   "cell_type": "markdown",
   "id": "d62fc971",
   "metadata": {
    "id": "d62fc971"
   },
   "source": [
    "## Analyze the Best Models and Their Errors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "124aa4e0",
   "metadata": {
    "id": "124aa4e0",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537585471,
     "user_tz": -120,
     "elapsed": 27,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "feature_importances = grid_search.best_estimator_.feature_importances_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "0f2dc064",
   "metadata": {
    "id": "0f2dc064",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537585492,
     "user_tz": -120,
     "elapsed": 2,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "feature_importances_list = [float(round(x, 2)) for x in feature_importances]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "e8c84af9",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "e8c84af9",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537585500,
     "user_tz": -120,
     "elapsed": 7,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "9cd84409-e8f6-4bef-9a79-e0840f2d5675"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "[0.03,\n",
       " 0.06,\n",
       " 0.09,\n",
       " 0.14,\n",
       " 0.03,\n",
       " 0.04,\n",
       " 0.08,\n",
       " 0.03,\n",
       " 0.02,\n",
       " 0.04,\n",
       " 0.08,\n",
       " 0.07,\n",
       " 0.04,\n",
       " 0.04,\n",
       " 0.13,\n",
       " 0.01,\n",
       " 0.01,\n",
       " 0.0,\n",
       " 0.01,\n",
       " 0.01,\n",
       " 0.01,\n",
       " 0.0,\n",
       " 0.0,\n",
       " 0.0,\n",
       " 0.0,\n",
       " 0.0,\n",
       " 0.0,\n",
       " 0.0,\n",
       " 0.0,\n",
       " 0.0,\n",
       " 0.01,\n",
       " 0.0,\n",
       " 0.0,\n",
       " 0.02,\n",
       " 0.0,\n",
       " 0.0,\n",
       " 0.0]"
      ]
     },
     "metadata": {},
     "execution_count": 94
    }
   ],
   "source": [
    "feature_importances_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "ff23f4e2",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "ff23f4e2",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537585513,
     "user_tz": -120,
     "elapsed": 12,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "31ab727e-5b91-4c0c-854a-d1964c79d230"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "[(0.14, 'surface'),\n",
       " (0.13, 'log_surface'),\n",
       " (0.09, 'latitude'),\n",
       " (0.08, 'dist_prefecture_km'),\n",
       " (0.08, 'altitude'),\n",
       " (0.07, 'dist_pole_km'),\n",
       " (0.06, 'longitude'),\n",
       " (0.04, 'population_commune'),\n",
       " (0.04, 'nb_ventes_commune'),\n",
       " (0.04, 'log_population'),\n",
       " (0.04, 'dist_cours_eau_m'),\n",
       " (0.03, 'pente_pct'),\n",
       " (0.03, 'part_AB'),\n",
       " (0.03, 'annee'),\n",
       " (0.02, 'orientation_sud'),\n",
       " (0.02, 'epci_CC du Briançonnais'),\n",
       " (0.01, 'mix_AB seul'),\n",
       " (0.01, 'mix_AB + terrain non constructible'),\n",
       " (0.01, 'epci_CC Serre-Ponçon'),\n",
       " (0.01, 'epci_CA Durance-Lubéron-Verdon Agglomération'),\n",
       " (0.01, 'dep_05'),\n",
       " (0.01, 'dep_04'),\n",
       " (0.0, 'mix_AB + dépendance'),\n",
       " (0.0, 'epci_CC du Sisteronais-Buëch'),\n",
       " (0.0, 'epci_CC du Pays des Ecrins'),\n",
       " (0.0, 'epci_CC du Guillestrois et du Queyras'),\n",
       " (0.0, \"epci_CC Vallée de l'Ubaye - Serre-Ponçon\"),\n",
       " (0.0, \"epci_CC Serre-Ponçon Val d'Avance\"),\n",
       " (0.0, \"epci_CC Pays d'Apt-Luberon\"),\n",
       " (0.0, 'epci_CC Pays Forcalquier et Montagne de Lure'),\n",
       " (0.0, 'epci_CC Jabron-Lure-Vançon-Durance'),\n",
       " (0.0, 'epci_CC Haute-Provence - Pays de Banon'),\n",
       " (0.0, 'epci_CC Champsaur-Valgaudemar'),\n",
       " (0.0, 'epci_CC Buëch-Dévoluy'),\n",
       " (0.0, 'epci_CC Alpes-Provence-Verdon \"Sources de lumière\"'),\n",
       " (0.0, 'epci_CA Provence-Alpes-Agglomération'),\n",
       " (0.0, 'epci_CA Gap-Tallard-Durance')]"
      ]
     },
     "metadata": {},
     "execution_count": 95
    }
   ],
   "source": [
    "attributes = list(alpes_features)\n",
    "sorted(zip(feature_importances_list, attributes), reverse=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "02eb4302f386"
   },
   "source": [
    "**Lecture.** La surface domine (surface et log_surface : 27 % à elles deux). Viennent ensuite la position (latitude et longitude : 15 %), les distances à la préfecture et au pôle (15 %) et l'altitude (8 %). Les colonnes d'intercommunalité pèsent presque zéro, sauf le Briançonnais (2 %) : le modèle retrouve la géographie avec les coordonnées. Pente et orientation comptent peu (2 à 3 %)."
   ],
   "id": "02eb4302f386"
  },
  {
   "cell_type": "markdown",
   "id": "e53e582f",
   "metadata": {
    "id": "e53e582f"
   },
   "source": [
    "## Evaluate Your System on the Test Set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "f7984bc2",
   "metadata": {
    "id": "f7984bc2",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537585563,
     "user_tz": -120,
     "elapsed": 49,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    }
   },
   "outputs": [],
   "source": [
    "final_model = grid_search.best_estimator_\n",
    "\n",
    "X_test = test_set.drop(\"prix_m2\", axis=1).values\n",
    "y_test = test_set[\"prix_m2\"].copy()\n",
    "\n",
    "X_test_prepared = scaler.transform(X_test)\n",
    "\n",
    "final_predictions = final_model.predict(X_test_prepared)\n",
    "\n",
    "final_mse = mean_squared_error(y_test, final_predictions)\n",
    "final_rmse = np.sqrt(final_mse)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "3cdc5f91",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "3cdc5f91",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537585573,
     "user_tz": -120,
     "elapsed": 9,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "d245f8fc-63e6-4a7d-f864-ce03e8e73102"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "45"
      ]
     },
     "metadata": {},
     "execution_count": 97
    }
   ],
   "source": [
    "round(final_rmse)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5b56f9f5",
   "metadata": {
    "id": "5b56f9f5"
   },
   "source": [
    "We can compute a 95% confidence interval for the test RMSE:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "11b6fe41",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "11b6fe41",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537585583,
     "user_tz": -120,
     "elapsed": 9,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "d930c8fe-4d88-468b-d88f-e2d7326dae9a"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "[39.0, 50.0]"
      ]
     },
     "metadata": {},
     "execution_count": 98
    }
   ],
   "source": [
    "from scipy import stats\n",
    "\n",
    "np.set_printoptions(legacy='1.25')\n",
    "\n",
    "confidence = 0.95\n",
    "squared_errors = (final_predictions - y_test) ** 2\n",
    "round_v(np.sqrt(stats.t.interval(confidence, len(squared_errors) - 1,\n",
    "                         loc=squared_errors.mean(),\n",
    "                         scale=stats.sem(squared_errors))))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "dab72b7e5946"
   },
   "source": [
    "**Lecture.** Sur les 828 ventes jamais vues, l'erreur est de 45 €/m² (intervalle de confiance à 95 % : 39 à 50), au même niveau qu'en validation croisée : le modèle ne s'est pas sur-ajusté au test. C'est 44 % de moins que le modèle naïf (80). La cellule suivante montre que l'erreur absolue moyenne est de 27 €/m² et l'erreur relative médiane de 13 %.\n",
    "Le modèle donne une bonne tendance, pas un prix au terrain près : il ne connaît ni la viabilisation, ni le zonage du PLU, ni la vue."
   ],
   "id": "dab72b7e5946"
  },
  {
   "cell_type": "code",
   "source": [
    "# Variante : le Random Forest apprend log(prix), on reconvertit en €/m² (np.exp) pour comparer au modèle \"prix brut\"\n",
    "from sklearn.model_selection import cross_val_predict\n",
    "\n",
    "def rf():   # même réglage que le meilleur modèle du Grid Search\n",
    "    return RandomForestRegressor(**grid_search.best_params_, random_state=42, n_jobs=-1)\n",
    "\n",
    "def scores(vrai, predit):\n",
    "    return {\"RMSE (€/m²)\": round(np.sqrt(mean_squared_error(vrai, predit))),\n",
    "            \"MAE (€/m²)\": round(mean_absolute_error(vrai, predit)),\n",
    "            \"Erreur relative médiane\": f\"{np.median(np.abs(predit - vrai) / vrai):.0%}\"}\n",
    "\n",
    "# 1) Validation croisée (5 découpages) sur l'entraînement\n",
    "cv_brut = cross_val_predict(rf(), alpes_prepared, alpes_labels, cv=5)\n",
    "cv_log = np.exp(cross_val_predict(rf(), alpes_prepared, np.log(alpes_labels), cv=5))\n",
    "\n",
    "# 2) Test final (ventes jamais vues)\n",
    "rf_log = rf().fit(alpes_prepared, np.log(alpes_labels))\n",
    "test_log = np.exp(rf_log.predict(X_test_prepared))\n",
    "\n",
    "comparaison = pd.DataFrame({\n",
    "    \"Validation croisée - prix brut\": scores(alpes_labels, cv_brut),\n",
    "    \"Validation croisée - log(prix)\": scores(alpes_labels, cv_log),\n",
    "    \"Test - prix brut\": scores(y_test, final_predictions),\n",
    "    \"Test - log(prix)\": scores(y_test, test_log),\n",
    "}).T\n",
    "comparaison"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 175
    },
    "id": "YNaaOb_wWN5s",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537595513,
     "user_tz": -120,
     "elapsed": 9930,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "fd5ae8d5-e46d-4949-dfa9-341a4f9a8a97"
   },
   "id": "YNaaOb_wWN5s",
   "execution_count": 99,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "                               RMSE (€/m²) MAE (€/m²) Erreur relative médiane\n",
       "Validation croisée - prix brut          46         27                     15%\n",
       "Validation croisée - log(prix)          48         27                     15%\n",
       "Test - prix brut                        45         27                     13%\n",
       "Test - log(prix)                        51         28                     14%"
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-bf54789b-463e-457e-a8be-f21e97252c32\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>RMSE (€/m²)</th>\n",
       "      <th>MAE (€/m²)</th>\n",
       "      <th>Erreur relative médiane</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Validation croisée - prix brut</th>\n",
       "      <td>46</td>\n",
       "      <td>27</td>\n",
       "      <td>15%</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Validation croisée - log(prix)</th>\n",
       "      <td>48</td>\n",
       "      <td>27</td>\n",
       "      <td>15%</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Test - prix brut</th>\n",
       "      <td>45</td>\n",
       "      <td>27</td>\n",
       "      <td>13%</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Test - log(prix)</th>\n",
       "      <td>51</td>\n",
       "      <td>28</td>\n",
       "      <td>14%</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-bf54789b-463e-457e-a8be-f21e97252c32')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-bf54789b-463e-457e-a8be-f21e97252c32 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-bf54789b-463e-457e-a8be-f21e97252c32');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "variable_name": "comparaison",
       "summary": "{\n  \"name\": \"comparaison\",\n  \"rows\": 4,\n  \"fields\": [\n    {\n      \"column\": \"RMSE (\\u20ac/m\\u00b2)\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": 45,\n        \"max\": 51,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          48,\n          51,\n          46\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"MAE (\\u20ac/m\\u00b2)\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": 27,\n        \"max\": 28,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          28,\n          27\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Erreur relative m\\u00e9diane\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"15%\",\n          \"13%\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {},
     "execution_count": 99
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ebcfa3460a3a"
   },
   "source": [
    "**Lecture.** Le log n'apporte rien : 51 €/m² au test contre 45 pour le prix brut. Il ne réduit pas l'erreur relative (15 % dans les deux cas en validation croisée) et se trompe davantage sur les terrains chers, qui pèsent lourd dans la RMSE. On garde le prix brut."
   ],
   "id": "ebcfa3460a3a"
  },
  {
   "cell_type": "markdown",
   "id": "8ec06eab",
   "metadata": {
    "id": "8ec06eab"
   },
   "source": [
    "# Au-delà du cours\n",
    "\n",
    "Parties ajoutées au déroulé du cours :\n",
    "- zoom sur les Hautes-Alpes (05) ;\n",
    "- réseau neuronal Keras (Activité 3), comparé au Random Forest ;\n",
    "- carte interactive des prédictions (folium) ;\n",
    "- contrôle des sources (Koumoul contre Etalab) ;\n",
    "- diagnostic : quelles ventes portent l'erreur ;\n",
    "- test d'une variable « distance aux stations de ski ».\n",
    "\n",
    "La variante en log(prix) est placée juste avant, avec l'évaluation sur le jeu de test."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e52c216e",
   "metadata": {
    "id": "e52c216e"
   },
   "source": [
    "## Zoom Hautes-Alpes (05)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "50a450ba",
   "metadata": {
    "id": "50a450ba",
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 586
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537595520,
     "user_tz": -120,
     "elapsed": 8,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "157b39b7-c438-4d92-cd3d-aa71cec90bac"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Ventes du 05 dans le test : 409\n",
      "RMSE 05 : 55 €/m²\n"
     ]
    },
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "                       prix_m2  prix_predit\n",
       "nom_commune                                \n",
       "Montgenèvre              555.0        453.0\n",
       "Saint-Chaffrey           493.0        304.0\n",
       "Le Monêtier-les-Bains    363.0        250.0\n",
       "Manteyer                 347.0        213.0\n",
       "La Salle-les-Alpes       292.0        214.0\n",
       "Dévoluy                  276.0        195.0\n",
       "Ceillac                  251.0        214.0\n",
       "Baratier                 249.0        199.0\n",
       "Briançon                 232.0        210.0\n",
       "Puy-Sanières             184.0        163.0\n",
       "Neffes                   180.0        165.0\n",
       "Orcières                 174.0        145.0\n",
       "Gap                      171.0        159.0\n",
       "Les Orres                161.0        166.0\n",
       "Vars                     161.0         91.0"
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-41027480-a531-4a8e-aa07-5bae9d031642\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>prix_m2</th>\n",
       "      <th>prix_predit</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>nom_commune</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Montgenèvre</th>\n",
       "      <td>555.0</td>\n",
       "      <td>453.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Saint-Chaffrey</th>\n",
       "      <td>493.0</td>\n",
       "      <td>304.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Le Monêtier-les-Bains</th>\n",
       "      <td>363.0</td>\n",
       "      <td>250.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Manteyer</th>\n",
       "      <td>347.0</td>\n",
       "      <td>213.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>La Salle-les-Alpes</th>\n",
       "      <td>292.0</td>\n",
       "      <td>214.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Dévoluy</th>\n",
       "      <td>276.0</td>\n",
       "      <td>195.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ceillac</th>\n",
       "      <td>251.0</td>\n",
       "      <td>214.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Baratier</th>\n",
       "      <td>249.0</td>\n",
       "      <td>199.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Briançon</th>\n",
       "      <td>232.0</td>\n",
       "      <td>210.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Puy-Sanières</th>\n",
       "      <td>184.0</td>\n",
       "      <td>163.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Neffes</th>\n",
       "      <td>180.0</td>\n",
       "      <td>165.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Orcières</th>\n",
       "      <td>174.0</td>\n",
       "      <td>145.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Gap</th>\n",
       "      <td>171.0</td>\n",
       "      <td>159.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Les Orres</th>\n",
       "      <td>161.0</td>\n",
       "      <td>166.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Vars</th>\n",
       "      <td>161.0</td>\n",
       "      <td>91.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-41027480-a531-4a8e-aa07-5bae9d031642')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-41027480-a531-4a8e-aa07-5bae9d031642 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-41027480-a531-4a8e-aa07-5bae9d031642');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "summary": "{\n  \"name\": \"r05\",\n  \"rows\": 15,\n  \"fields\": [\n    {\n      \"column\": \"nom_commune\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 15,\n        \"samples\": [\n          \"Puy-Sani\\u00e8res\",\n          \"Orci\\u00e8res\",\n          \"Montgen\\u00e8vre\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"prix_m2\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 121.44122623133967,\n        \"min\": 161.0,\n        \"max\": 555.0,\n        \"num_unique_values\": 14,\n        \"samples\": [\n          184.0,\n          174.0,\n          555.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"prix_predit\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 83.24816600296457,\n        \"min\": 91.0,\n        \"max\": 453.0,\n        \"num_unique_values\": 14,\n        \"samples\": [\n          165.0,\n          159.0,\n          453.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {},
     "execution_count": 100
    }
   ],
   "source": [
    "resultats = test_set[[\"longitude\", \"latitude\", \"annee\", \"surface\", \"prix_m2\"]].copy()\n",
    "resultats[\"prix_predit\"] = final_predictions\n",
    "resultats[\"ecart_pct\"] = 100 * (resultats[\"prix_m2\"] - resultats[\"prix_predit\"]) / resultats[\"prix_predit\"]\n",
    "resultats = resultats.join(infos_carte)\n",
    "\n",
    "r05 = resultats[resultats[\"code_departement\"] == \"05\"]\n",
    "print(\"Ventes du 05 dans le test :\", len(r05))\n",
    "print(\"RMSE 05 :\", round(np.sqrt(mean_squared_error(r05[\"prix_m2\"], r05[\"prix_predit\"]))), \"€/m²\")\n",
    "r05.groupby(\"nom_commune\")[[\"prix_m2\", \"prix_predit\"]].median().round().sort_values(\"prix_m2\", ascending=False).head(15)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "2d972fc116b6"
   },
   "source": [
    "**Lecture.** Dans les Hautes-Alpes, l'erreur monte à 55 €/m² (409 ventes de test), contre 45 sur l'ensemble : le marché y est plus hétérogène. Le modèle sous-estime nettement les communes de stations, par exemple Saint-Chaffrey (493 €/m² réels, 304 prédits), Le Monêtier-les-Bains (363 contre 250), Vars (161 contre 91) ou Manteyer (station de Céüze). Gap, Briançon et Les Orres sont bien estimés. D'où le test d'une variable « station de ski » plus bas."
   ],
   "id": "2d972fc116b6"
  },
  {
   "cell_type": "markdown",
   "id": "8ee70716",
   "metadata": {
    "id": "8ee70716"
   },
   "source": [
    "## Réseau neuronal (Activité 3)\n",
    "\n",
    "Même logique que le pricer d'options : `compile` (MSE + Adam + MAE), `fit` (epochs, batch_size), `evaluate`.\n",
    "Sortie **positive** (un prix l'est toujours) : activation `softplus` sur un label mis à l'échelle.\n",
    "Réseau plus petit que dans le cours (données réelles moins nombreuses) + dropout + early stopping."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "a38e61c1",
   "metadata": {
    "id": "a38e61c1",
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 293
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537599067,
     "user_tz": -120,
     "elapsed": 3546,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "95d91c16-8321-48e5-bb71-f9a944ceadef"
   },
   "outputs": [
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "\u001b[1mModel: \"sequential\"\u001b[0m\n"
      ],
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
       "</pre>\n"
      ]
     },
     "metadata": {}
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │         \u001b[38;5;34m2,432\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m)             │         \u001b[38;5;34m2,080\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m)             │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)              │            \u001b[38;5;34m33\u001b[0m │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
      ],
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,432</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)             │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,080</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)             │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>)              │            <span style=\"color: #00af00; text-decoration-color: #00af00\">33</span> │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
       "</pre>\n"
      ]
     },
     "metadata": {}
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m4,545\u001b[0m (17.75 KB)\n"
      ],
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">4,545</span> (17.75 KB)\n",
       "</pre>\n"
      ]
     },
     "metadata": {}
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m4,545\u001b[0m (17.75 KB)\n"
      ],
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">4,545</span> (17.75 KB)\n",
       "</pre>\n"
      ]
     },
     "metadata": {}
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ],
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
       "</pre>\n"
      ]
     },
     "metadata": {}
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "\n",
    "ECHELLE = alpes_labels.median()          # label mis à l'échelle (valeurs proches de 1)\n",
    "y_train_nn = alpes_labels.values / ECHELLE\n",
    "\n",
    "tf.random.set_seed(42)\n",
    "ann = keras.Sequential([\n",
    "    keras.layers.Input(shape=(alpes_prepared.shape[1],)),\n",
    "    keras.layers.Dense(64, activation=\"relu\"),\n",
    "    keras.layers.Dropout(0.2),\n",
    "    keras.layers.Dense(32, activation=\"relu\"),\n",
    "    keras.layers.Dropout(0.2),\n",
    "    keras.layers.Dense(1, activation=\"softplus\"),\n",
    "])\n",
    "ann.compile(loss=\"mean_squared_error\", optimizer=\"adam\", metrics=[\"mean_absolute_error\"])\n",
    "ann.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "id": "1b32e364",
   "metadata": {
    "id": "1b32e364",
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 542
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537611120,
     "user_tz": -120,
     "elapsed": 12052,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "d2e196ec-9758-4992-a3d0-f342ee432059"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Epochs réalisés : 70\n",
      "Saving figure ann_learning_curves\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "<Figure size 800x500 with 1 Axes>"
      ],
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": [
    "early_stopping = keras.callbacks.EarlyStopping(patience=10, restore_best_weights=True)\n",
    "\n",
    "history = ann.fit(alpes_prepared, y_train_nn, epochs=200, batch_size=64,\n",
    "                  validation_split=0.2, callbacks=[early_stopping], verbose=0)\n",
    "print(\"Epochs réalisés :\", len(history.history[\"loss\"]))\n",
    "\n",
    "pd.DataFrame(history.history)[[\"loss\", \"val_loss\"]].plot(figsize=(8, 5))\n",
    "plt.xlabel(\"Epoch\")\n",
    "save_fig(\"ann_learning_curves\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "feafc7a7",
   "metadata": {
    "id": "feafc7a7",
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537611279,
     "user_tz": -120,
     "elapsed": 158,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "f358f603-774b-4678-e149-2396e5f65986"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "RMSE test réseau neuronal : 53 €/m²\n",
      "RMSE test Random Forest   : 45 €/m²\n"
     ]
    }
   ],
   "source": [
    "ann_predictions = ann.predict(X_test_prepared, verbose=0).ravel() * ECHELLE\n",
    "ann_rmse = np.sqrt(mean_squared_error(y_test, ann_predictions))\n",
    "\n",
    "print(\"RMSE test réseau neuronal :\", round(ann_rmse), \"€/m²\")\n",
    "print(\"RMSE test Random Forest   :\", round(final_rmse), \"€/m²\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "aa1a1a8dcace"
   },
   "source": [
    "**Lecture.** Le réseau neuronal fait moins bien que le Random Forest : 53 €/m² au test contre 45. L'arrêt anticipé (early stopping) a stoppé l'entraînement après 70 epochs, en gardant les meilleurs poids. Avec environ 3 300 lignes de données tabulaires, la forêt aléatoire reste plus adaptée ; un réseau aurait besoin de beaucoup plus de ventes."
   ],
   "id": "aa1a1a8dcace"
  },
  {
   "cell_type": "markdown",
   "id": "60c9e210",
   "metadata": {
    "id": "60c9e210"
   },
   "source": [
    "## Carte interactive (folium)\n",
    "\n",
    "Ventes du jeu de test, c'est-à-dire les 828 ventes que le modèle n'a pas vues pendant l'entraînement. Chaque point est une vente réelle.\n",
    "Trois vues, une seule affichée à la fois : **prix réel**, **prix prédit** et **écart réel / prédit** en 5 classes : gris clair quand l'écart est inférieur à 15 %, bleu quand la vente s'est faite moins cher que prévu, rouge quand elle s'est faite plus cher (teinte foncée au-delà de 30 %).\n",
    "En validation croisée, environ la moitié des ventes sont à moins de 15 % de l'estimation, 69 % à moins de 25 % et 89 % à moins de 50 %.\n",
    "La carte s'ouvre sur la vue des écarts, sur le Plan IGN passé en gris ; les photos aériennes IGN sont disponibles en second fond. Contours des départements et des intercommunalités.\n",
    "Survol : commune et prix ; clic : année, surface, prix réel, prix prédit et écart.\n",
    "La carte est enregistrée dans `images/carte_interactive.html` (elle n'est pas conservée dans le notebook, trop lourde).\n",
    "⚠️ Règles DVF : carte à usage de travail, non publiée telle quelle (pas de ventes individuelles indexables)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "id": "296a4403",
   "metadata": {
    "id": "296a4403",
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 964,
     "output_embedded_package_id": "1y1VCqQ3W29Icag6AtQUISwzFKHKaT9hJ"
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537619347,
     "user_tz": -120,
     "elapsed": 8065,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "0275b59b-f0c4-4287-ae37-c599ee842d13"
   },
   "outputs": [
    {
     "output_type": "display_data",
     "data": {
      "text/plain": "Output hidden; open in https://colab.research.google.com to view."
     },
     "metadata": {}
    }
   ],
   "source": [
    "import folium\n",
    "import branca.colormap as cm\n",
    "\n",
    "# Fonds IGN (OpenStreetMap refuse Colab : 403). Le plan est passé en gris pour que les points ressortent.\n",
    "WMTS_IGN = (\"https://data.geopf.fr/wmts?SERVICE=WMTS&REQUEST=GetTile&VERSION=1.0.0\"\n",
    "            \"&STYLE=normal&TILEMATRIXSET=PM&TILEMATRIX={z}&TILEROW={y}&TILECOL={x}\")\n",
    "\n",
    "carte = folium.Map(location=[44.6, 6.3], zoom_start=9, tiles=None)\n",
    "folium.TileLayer(WMTS_IGN + \"&LAYER=GEOGRAPHICALGRIDSYSTEMS.PLANIGNV2&FORMAT=image/png\",\n",
    "                 attr=\"&copy; IGN, Plan IGN\", name=\"Plan IGN (gris)\",\n",
    "                 class_name=\"fond-gris\").add_to(carte)\n",
    "folium.TileLayer(WMTS_IGN + \"&LAYER=ORTHOIMAGERY.ORTHOPHOTOS&FORMAT=image/jpeg\",\n",
    "                 attr=\"&copy; IGN, photographies aériennes\", name=\"Photos aériennes\",\n",
    "                 show=False, overlay=False).add_to(carte)\n",
    "carte.get_root().header.add_child(folium.Element(\n",
    "    \"<style>.fond-gris { filter: grayscale(100%) contrast(0.8) brightness(1.08); }</style>\"))\n",
    "# Contours départements + intercommunalités (chargés plus haut : deps_geo, epci_geo)\n",
    "# Panneau dédié, sous les points et non cliquable : les clics passent aux ventes\n",
    "folium.map.CustomPane(\"contours\", z_index=350, pointer_events=False).add_to(carte)\n",
    "\n",
    "if epci_geo is not None:\n",
    "    couche_epci = folium.FeatureGroup(name=\"Intercommunalités\", overlay=True, show=True)\n",
    "    folium.GeoJson(epci_geo.to_json(), pane=\"contours\",\n",
    "                   style_function=lambda f: {\"color\": \"#555555\", \"weight\": 1,\n",
    "                                             \"dashArray\": \"4 3\", \"fill\": False}).add_to(couche_epci)\n",
    "    couche_epci.add_to(carte)\n",
    "else:\n",
    "    print(\"⚠️ Contours des intercommunalités absents : relancer la case des cartes (deps_geo / epci_geo)\")\n",
    "\n",
    "if deps_geo is not None:\n",
    "    couche_dep = folium.FeatureGroup(name=\"Départements\", overlay=True, show=True)\n",
    "    folium.GeoJson(deps_geo.to_json(), pane=\"contours\",\n",
    "                   style_function=lambda f: {\"color\": \"#222222\", \"weight\": 2.5, \"fill\": False}).add_to(couche_dep)\n",
    "    couche_dep.add_to(carte)\n",
    "else:\n",
    "    print(\"⚠️ Contours des départements absents : relancer la case des cartes (deps_geo / epci_geo)\")\n",
    "\n",
    "\n",
    "# Couleurs : prix du clair au foncé ; écarts bleu (moins cher que prévu) / rouge (plus cher que prévu)\n",
    "vmin, vmax = resultats[\"prix_m2\"].quantile(0.05), resultats[\"prix_m2\"].quantile(0.95)\n",
    "couleurs_prix = cm.LinearColormap([\"#ffffb2\", \"#fecc5c\", \"#fd8d3c\", \"#e31a1c\", \"#800026\"],\n",
    "                                  vmin=vmin, vmax=vmax, caption=\"Prix au m² (euros 2025)\")\n",
    "# Écarts en 5 classes : une zone neutre de ± 15 % (gris clair) pour ne colorer que les vraies erreurs\n",
    "couleurs_ecart = cm.StepColormap([\"#2166ac\", \"#92c5de\", \"#e0e0e0\", \"#f4a582\", \"#b2182b\"],\n",
    "                                 index=[-50, -30, -15, 15, 30, 50], vmin=-50, vmax=50,\n",
    "                                 caption=\"Écart réel / prédit (%) : gris = moins de 15 % d'écart, bleu = moins cher que prévu, rouge = plus cher\")\n",
    "\n",
    "def point(v, couleur):\n",
    "    return folium.CircleMarker(\n",
    "        location=[v[\"latitude\"], v[\"longitude\"]], radius=6,\n",
    "        color=\"#333333\", weight=0.6,                       # fin contour sombre : lisible sur tous les fonds\n",
    "        fill=True, fill_color=couleur, fill_opacity=0.9,\n",
    "        tooltip=f\"{v['nom_commune']} : {v['prix_m2']:.0f} €/m²\",\n",
    "        popup=folium.Popup(\n",
    "            f\"<b>{v['nom_commune']}</b> ({v['annee']:.0f})<br>\"\n",
    "            f\"Surface : {v['surface']:.0f} m²<br>\"\n",
    "            f\"Réel : {v['prix_m2']:.0f} €/m²<br>Prédit : {v['prix_predit']:.0f} €/m²<br>\"\n",
    "            f\"Écart : {v['ecart_pct']:+.0f} %\", max_width=220))\n",
    "\n",
    "# Les ventes les plus chères dessinées en dernier (au-dessus)\n",
    "ordre = resultats.sort_values(\"prix_m2\")\n",
    "couches = {\n",
    "    \"Prix réel\": lambda v: couleurs_prix(min(max(v[\"prix_m2\"], vmin), vmax)),\n",
    "    \"Prix prédit\": lambda v: couleurs_prix(min(max(v[\"prix_predit\"], vmin), vmax)),\n",
    "    \"Écart réel / prédit\": lambda v: couleurs_ecart(min(max(v[\"ecart_pct\"], -50), 50)),\n",
    "}\n",
    "for nom, couleur_de in couches.items():\n",
    "    couche = folium.FeatureGroup(name=nom, overlay=False, show=(nom == \"Écart réel / prédit\"))   # une seule couche à la fois\n",
    "    for _, v in ordre.iterrows():\n",
    "        point(v, couleur_de(v)).add_to(couche)\n",
    "    couche.add_to(carte)\n",
    "\n",
    "couleurs_prix.add_to(carte)\n",
    "couleurs_ecart.add_to(carte)\n",
    "folium.LayerControl(collapsed=False).add_to(carte)\n",
    "carte.fit_bounds([[resultats[\"latitude\"].min(), resultats[\"longitude\"].min()],\n",
    "                  [resultats[\"latitude\"].max(), resultats[\"longitude\"].max()]])\n",
    "carte.save(os.path.join(IMAGES_PATH, \"carte_interactive.html\"))\n",
    "carte"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6ff99a0a",
   "metadata": {
    "id": "6ff99a0a"
   },
   "source": [
    "## Contrôle des sources (pour le rapport)\n",
    "\n",
    "On vérifie que la base Koumoul (2014-2025) donne les mêmes ventes que le DVF géolocalisé officiel d'Etalab sur les années communes (2021-2025).\n",
    "Contrôle fait sur les Hautes-Alpes (05) : nombre de ventes et prix médian au m² par année, avant filtres.\n",
    "Si les chiffres concordent, l'historique Koumoul peut être utilisé pour la tendance longue."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "e5db3ddf",
   "metadata": {
    "id": "e5db3ddf",
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 324
    },
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537626163,
     "user_tz": -120,
     "elapsed": 6774,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "3c569a5f-4b88-4e45-80ea-85d957cb73d2"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Téléchargement Etalab 05 2021\n",
      "Téléchargement Etalab 05 2022\n",
      "Téléchargement Etalab 05 2023\n",
      "Téléchargement Etalab 05 2024\n",
      "Téléchargement Etalab 05 2025\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "       koumoul  etalab  ecart_%\n",
       "annee                          \n",
       "2021       364   364.0      0.0\n",
       "2022       306   306.0      0.0\n",
       "2023       171   171.0      0.0\n",
       "2024       144   144.0      0.0\n",
       "2025       184   184.0      0.0"
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-63f49414-a185-4b12-a401-5dfa758f034e\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>koumoul</th>\n",
       "      <th>etalab</th>\n",
       "      <th>ecart_%</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>annee</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2021</th>\n",
       "      <td>364</td>\n",
       "      <td>364.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022</th>\n",
       "      <td>306</td>\n",
       "      <td>306.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2023</th>\n",
       "      <td>171</td>\n",
       "      <td>171.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024</th>\n",
       "      <td>144</td>\n",
       "      <td>144.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2025</th>\n",
       "      <td>184</td>\n",
       "      <td>184.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-63f49414-a185-4b12-a401-5dfa758f034e')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-63f49414-a185-4b12-a401-5dfa758f034e button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-63f49414-a185-4b12-a401-5dfa758f034e');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "variable_name": "controle",
       "summary": "{\n  \"name\": \"controle\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"annee\",\n      \"properties\": {\n        \"dtype\": \"int32\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          2022,\n          2025,\n          2023\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"koumoul\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 95,\n        \"min\": 144,\n        \"max\": 364,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          306,\n          184,\n          171\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"etalab\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 95.72460498743257,\n        \"min\": 144.0,\n        \"max\": 364.0,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          306.0,\n          184.0,\n          171.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"ecart_%\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.0,\n        \"min\": 0.0,\n        \"max\": 0.0,\n        \"num_unique_values\": 1,\n        \"samples\": [\n          0.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {}
    }
   ],
   "source": [
    "def comptage(dvf_brut, type_bien=TYPE_BIEN):\n",
    "    x = dvf_brut[dvf_brut[\"nature_mutation\"].isin(NATURES)].copy()\n",
    "    x[\"annee\"] = pd.to_datetime(x[\"date_mutation\"]).dt.year\n",
    "    if type_bien == \"terrain\":\n",
    "        x = x[x[\"code_nature_culture\"] == \"AB\"]\n",
    "    else:\n",
    "        x = x[x[\"type_local\"] == \"Maison\"]\n",
    "    return x.groupby(\"annee\")[\"id_mutation\"].nunique()\n",
    "\n",
    "DEP_CONTROLE = \"05\"\n",
    "annees_communes = [a for a in [2021, 2022, 2023, 2024, 2025] if a in ANNEES]\n",
    "autre = \"etalab\" if SOURCE == \"koumoul\" else \"koumoul\"\n",
    "loader_autre = load_etalab if autre == \"etalab\" else load_koumoul\n",
    "\n",
    "try:\n",
    "    dvf_autre = pd.concat([loader_autre(DEP_CONTROLE, a) for a in annees_communes], ignore_index=True)\n",
    "    dvf_05 = dvf[dvf[\"code_departement\"] == DEP_CONTROLE]\n",
    "    controle = pd.DataFrame({SOURCE: comptage(dvf_05), autre: comptage(dvf_autre)}).loc[annees_communes]\n",
    "    controle[\"ecart_%\"] = (100 * (controle[autre] - controle[SOURCE]) / controle[SOURCE]).round(1)\n",
    "    display(controle)\n",
    "except Exception as err:\n",
    "    print(\"Contrôle indisponible :\", err)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "b4752b538213"
   },
   "source": [
    "**Lecture.** Sur le 05, de 2021 à 2025, les deux sources donnent exactement le même nombre de ventes chaque année. L'historique Koumoul (2014-2020) peut donc être utilisé sans risque de doublon ou de trou."
   ],
   "id": "b4752b538213"
  },
  {
   "cell_type": "code",
   "source": [
    "# Diagnostic : d'où vient l'erreur de la validation croisée ? Qui porte l'erreur ?\n",
    "from sklearn.model_selection import cross_val_predict\n",
    "\n",
    "pred_cv = cross_val_predict(rf(), alpes_prepared, alpes_labels, cv=10)   # rf() : défini dans la case log(prix)\n",
    "\n",
    "diag = train_set[[\"surface\", \"prix_m2\"]].copy()\n",
    "diag[\"prix_predit\"] = pred_cv\n",
    "diag[\"erreur2\"] = (diag[\"prix_m2\"] - diag[\"prix_predit\"]) ** 2\n",
    "diag[\"type\"] = train_set.filter(like=\"mix_\").idxmax(axis=1).str.replace(\"mix_\", \"\")\n",
    "diag = diag.join(infos_carte[[\"nom_commune\"]], how=\"left\")\n",
    "\n",
    "print(\"RMSE validation croisée :\", round(np.sqrt(diag[\"erreur2\"].mean())), \"€/m²\\n\")\n",
    "\n",
    "# 1) Par type de vente : qui porte l'erreur ?\n",
    "par_type = diag.groupby(\"type\").agg(ventes=(\"prix_m2\", \"size\"),\n",
    "                                     prix_moyen=(\"prix_m2\", \"mean\"),\n",
    "                                     ecart_type=(\"prix_m2\", \"std\"),\n",
    "                                     rmse=(\"erreur2\", lambda e: np.sqrt(e.mean())),\n",
    "                                     part_erreur_pct=(\"erreur2\", \"sum\"))\n",
    "par_type[\"part_erreur_pct\"] = 100 * par_type[\"part_erreur_pct\"] / diag[\"erreur2\"].sum()\n",
    "display(par_type.round())\n",
    "\n",
    "# 2) Poids des plus grosses erreurs dans le total\n",
    "e = diag[\"erreur2\"].sort_values(ascending=False)\n",
    "for p in [0.01, 0.05]:\n",
    "    n = int(len(e) * p)\n",
    "    print(f\"Les {p:.0%} pires ventes ({n}) = {100 * e.iloc[:n].sum() / e.sum():.0f} % de l'erreur ; \"\n",
    "          f\"RMSE sans elles : {np.sqrt(e.iloc[n:].mean()):.0f} €/m²\")\n",
    "\n",
    "# 3) Les 15 pires ventes, pour voir si ce sont des erreurs de données\n",
    "display(diag.sort_values(\"erreur2\", ascending=False)\n",
    "            .head(15)[[\"nom_commune\", \"type\", \"surface\", \"prix_m2\", \"prix_predit\"]].round())"
   ],
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 747
    },
    "id": "iDLNiMcDvTVU",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537637227,
     "user_tz": -120,
     "elapsed": 11042,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "6a692174-8ca2-4222-a7fe-696b70b1da57"
   },
   "id": "iDLNiMcDvTVU",
   "execution_count": 106,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "RMSE validation croisée : 45 €/m²\n",
      "\n"
     ]
    },
    {
     "output_type": "display_data",
     "data": {
      "text/plain": [
       "                                ventes  prix_moyen  ecart_type  rmse  \\\n",
       "type                                                                   \n",
       "AB + dépendance                     11       141.0        75.0  49.0   \n",
       "AB + terrain non constructible     778       105.0       102.0  64.0   \n",
       "AB seul                           2520       130.0        71.0  37.0   \n",
       "\n",
       "                                part_erreur_pct  \n",
       "type                                             \n",
       "AB + dépendance                             0.0  \n",
       "AB + terrain non constructible             47.0  \n",
       "AB seul                                    53.0  "
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-283d403a-65fc-4629-950a-85223a702c80\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ventes</th>\n",
       "      <th>prix_moyen</th>\n",
       "      <th>ecart_type</th>\n",
       "      <th>rmse</th>\n",
       "      <th>part_erreur_pct</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>type</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>AB + dépendance</th>\n",
       "      <td>11</td>\n",
       "      <td>141.0</td>\n",
       "      <td>75.0</td>\n",
       "      <td>49.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AB + terrain non constructible</th>\n",
       "      <td>778</td>\n",
       "      <td>105.0</td>\n",
       "      <td>102.0</td>\n",
       "      <td>64.0</td>\n",
       "      <td>47.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AB seul</th>\n",
       "      <td>2520</td>\n",
       "      <td>130.0</td>\n",
       "      <td>71.0</td>\n",
       "      <td>37.0</td>\n",
       "      <td>53.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-283d403a-65fc-4629-950a-85223a702c80')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-283d403a-65fc-4629-950a-85223a702c80 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-283d403a-65fc-4629-950a-85223a702c80');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "summary": "{\n  \"name\": \"            \",\n  \"rows\": 3,\n  \"fields\": [\n    {\n      \"column\": \"type\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"AB + d\\u00e9pendance\",\n          \"AB + terrain non constructible\",\n          \"AB seul\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"ventes\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1285,\n        \"min\": 11,\n        \"max\": 2520,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          11,\n          778,\n          2520\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"prix_moyen\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 18.44812546936228,\n        \"min\": 105.0,\n        \"max\": 141.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          141.0,\n          105.0,\n          130.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"ecart_type\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 16.862186493255653,\n        \"min\": 71.0,\n        \"max\": 102.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          75.0,\n          102.0,\n          71.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"rmse\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 13.527749258468683,\n        \"min\": 37.0,\n        \"max\": 64.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          49.0,\n          64.0,\n          37.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"part_erreur_pct\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 29.022979401386987,\n        \"min\": 0.0,\n        \"max\": 53.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          0.0,\n          47.0,\n          53.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {}
    },
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Les 1% pires ventes (33) = 34 % de l'erreur ; RMSE sans elles : 37 €/m²\n",
      "Les 5% pires ventes (165) = 65 % de l'erreur ; RMSE sans elles : 27 €/m²\n"
     ]
    },
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "[Sortie retirée de la version publique : elle affichait des ventes individuelles DVF.]\n"
     ]
    }
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "6fe347896af5"
   },
   "source": [
    "**Lecture.** L'erreur vient surtout de quelques ventes : les 1 % pires (33 ventes) font 34 % de l'erreur, les 5 % pires en font 65 %. Sans elles, la RMSE tombe à 27 €/m². Les ventes « AB + terrain non constructible » portent 47 % de l'erreur pour 24 % des ventes.\n",
    "Les pires cas sont des terrains à 500-770 €/m² dans les stations du Briançonnais (Le Monêtier-les-Bains, Montgenèvre, Saint-Chaffrey) : terrains en front de neige, ou maisons neuves encore classées en terrain que le filtre par commune n'a pas repérées, puisque toute la commune est chère."
   ],
   "id": "6fe347896af5"
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "8d5769ac73b6"
   },
   "source": [
    "## Test : distance aux stations de ski\n",
    "\n",
    "Hypothèse : le modèle sous-estime les communes de stations parce qu'il ne sait pas où sont les stations. On ajoute la distance à la station la plus proche (35 communes supports dans le 04 et le 05), puis la distance à la grande station la plus proche (Serre Chevalier, Montgenèvre, Vars-Risoul, Les Orres, Orcières, Dévoluy, Pra-Loup, Val d'Allos), et on compare en validation croisée.\n",
    "Le test porte sur toutes les ventes nettoyées (4 137), d'où un niveau d'erreur un peu différent des 48 €/m² de la partie modèles."
   ],
   "id": "8d5769ac73b6"
  },
  {
   "cell_type": "code",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 178
    },
    "id": "888bb81d1cce",
    "executionInfo": {
     "status": "ok",
     "timestamp": 1791537676482,
     "user_tz": -120,
     "elapsed": 39250,
     "user": {
      "displayName": "Nathalie Wirth",
      "userId": "04968417715143734623"
     }
    },
    "outputId": "3c2b90da-dfd1-408f-c3cb-3467b0d75d27"
   },
   "execution_count": 107,
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "30 stations placées sur 35 (les autres n'ont aucune vente de terrain)\n",
      "619 ventes dans des communes de stations sur 4137\n"
     ]
    },
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "                                               RMSE toutes ventes  \\\n",
       "Sans variable station                                        43.1   \n",
       "+ distance à la station la plus proche                       43.3   \n",
       "+ distance à la grande station la plus proche                43.2   \n",
       "\n",
       "                                               RMSE communes de stations  \n",
       "Sans variable station                                               74.0  \n",
       "+ distance à la station la plus proche                              74.8  \n",
       "+ distance à la grande station la plus proche                       75.0  "
      ],
      "text/html": [
       "\n",
       "  <div id=\"df-00ac3c4f-31d0-47e4-b610-060325765345\" class=\"colab-df-container\">\n",
       "    <div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>RMSE toutes ventes</th>\n",
       "      <th>RMSE communes de stations</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Sans variable station</th>\n",
       "      <td>43.1</td>\n",
       "      <td>74.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>+ distance à la station la plus proche</th>\n",
       "      <td>43.3</td>\n",
       "      <td>74.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>+ distance à la grande station la plus proche</th>\n",
       "      <td>43.2</td>\n",
       "      <td>75.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-00ac3c4f-31d0-47e4-b610-060325765345')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-00ac3c4f-31d0-47e4-b610-060325765345 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-00ac3c4f-31d0-47e4-b610-060325765345');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "dataframe",
       "summary": "{\n  \"name\": \"pd\",\n  \"rows\": 3,\n  \"fields\": [\n    {\n      \"column\": \"RMSE toutes ventes\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.09999999999999787,\n        \"min\": 43.1,\n        \"max\": 43.3,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          43.1,\n          43.3,\n          43.2\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"RMSE communes de stations\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.5291502622129176,\n        \"min\": 74.0,\n        \"max\": 75.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          74.0,\n          74.8,\n          75.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
      }
     },
     "metadata": {},
     "execution_count": 107
    }
   ],
   "source": [
    "# Test : la distance aux stations de ski améliore-t-elle le modèle ?\n",
    "# Cellule autonome : elle relit data/alpes_terrain.csv (ventes nettoyées) et recalcule les variables.\n",
    "# Position d'une station = centre des ventes de sa commune support (approximation : le village, pas le pied des pistes).\n",
    "from sklearn.model_selection import KFold, cross_val_predict\n",
    "from sklearn.ensemble import RandomForestRegressor\n",
    "\n",
    "st = pd.read_csv(os.path.join(\"data\", \"alpes_terrain.csv\"),\n",
    "                 dtype={\"code_departement\": str, \"code_commune\": str}).dropna(subset=[\"longitude\"])\n",
    "\n",
    "# Communes supports de stations (1 = grande station)\n",
    "STATIONS = {\"Montgenèvre\": 1, \"Briançon\": 1, \"Saint-Chaffrey\": 1, \"La Salle-les-Alpes\": 1, \"Le Monêtier-les-Bains\": 1,\n",
    "            \"Vars\": 1, \"Risoul\": 1, \"Les Orres\": 1, \"Orcières\": 1, \"Dévoluy\": 1, \"Uvernet-Fours\": 1, \"Allos\": 1,\n",
    "            \"Puy-Saint-Vincent\": 0, \"Pelvoux\": 0, \"La Grave\": 0, \"Ancelle\": 0, \"Saint-Léger-les-Mélèzes\": 0,\n",
    "            \"Saint-Michel-de-Chaillol\": 0, \"Laye\": 0, \"Réallon\": 0, \"Crévoux\": 0, \"Ceillac\": 0, \"Abriès-Ristolas\": 0,\n",
    "            \"Molines-en-Queyras\": 0, \"Saint-Véran\": 0, \"Arvieux\": 0, \"Manteyer\": 0, \"Névache\": 0,\n",
    "            \"Enchastrayes\": 0, \"La Condamine-Châtelard\": 0, \"Selonnet\": 0, \"Saint-Jean-Montclar\": 0,\n",
    "            \"Seyne\": 0, \"Larche\": 0, \"Saint-Étienne-les-Orgues\": 0}\n",
    "centres = st.groupby(\"nom_commune\")[[\"longitude\", \"latitude\"]].median()\n",
    "trouvees = {n: g for n, g in STATIONS.items() if n in centres.index}\n",
    "print(len(trouvees), \"stations placées sur\", len(STATIONS), \"(les autres n'ont aucune vente de terrain)\")\n",
    "\n",
    "def km(lon1, lat1, lon2, lat2):   # distance à vol d'oiseau (formule de haversine)\n",
    "    lon1, lat1, lon2, lat2 = map(np.radians, [lon1, lat1, lon2, lat2])\n",
    "    a = np.sin((lat2 - lat1) / 2) ** 2 + np.cos(lat1) * np.cos(lat2) * np.sin((lon2 - lon1) / 2) ** 2\n",
    "    return 6371 * 2 * np.arcsin(np.sqrt(a))\n",
    "\n",
    "def dist_min(noms):\n",
    "    return np.min([km(st[\"longitude\"], st[\"latitude\"], *centres.loc[n]) for n in noms], axis=0)\n",
    "\n",
    "st[\"dist_station_km\"] = dist_min(list(trouvees))\n",
    "st[\"dist_grande_station_km\"] = dist_min([n for n, g in trouvees.items() if g == 1])\n",
    "\n",
    "# Mêmes variables que le modèle principal\n",
    "POLES = [(6.0616, 44.5797), (5.7896, 43.8293), (6.2495, 44.0954), (6.6536, 44.8995)]   # Gap, Manosque, Digne, Briançon\n",
    "st[\"dist_prefecture_km\"] = [km(lo, la, *PREFECTURES[d]) for lo, la, d in zip(st[\"longitude\"], st[\"latitude\"], st[\"code_departement\"])]\n",
    "st[\"dist_pole_km\"] = np.min([km(st[\"longitude\"], st[\"latitude\"], *p) for p in POLES], axis=0)\n",
    "st[\"nb_ventes_commune\"] = st.groupby(\"code_commune\")[\"prix_m2\"].transform(\"size\")\n",
    "st[\"log_population\"] = np.log(st[\"population_commune\"])\n",
    "st[\"log_surface\"] = np.log(st[\"surface\"])\n",
    "base = [\"annee\", \"longitude\", \"latitude\", \"surface\", \"part_AB\", \"population_commune\", \"altitude\", \"pente_pct\",\n",
    "        \"orientation_sud\", \"dist_cours_eau_m\", \"dist_prefecture_km\", \"dist_pole_km\", \"nb_ventes_commune\",\n",
    "        \"log_population\", \"log_surface\"]\n",
    "X_st = pd.concat([st[base], pd.get_dummies(st[[\"code_departement\", \"type_mixite\", \"nom_epci\"]]).astype(int)], axis=1)\n",
    "y_st = st[\"prix_m2\"]\n",
    "en_station = st[\"nom_commune\"].isin(list(trouvees))\n",
    "\n",
    "# Validation croisée (10 plis) du Random Forest réglé, sans puis avec les variables stations\n",
    "plis = KFold(n_splits=10, shuffle=True, random_state=42)\n",
    "lignes = {}\n",
    "for nom, X in {\"Sans variable station\": X_st,\n",
    "               \"+ distance à la station la plus proche\": X_st.assign(dist_station_km=st[\"dist_station_km\"]),\n",
    "               \"+ distance à la grande station la plus proche\": X_st.assign(dist_station_km=st[\"dist_station_km\"],\n",
    "                                                                            dist_grande_station_km=st[\"dist_grande_station_km\"])}.items():\n",
    "    pred = cross_val_predict(RandomForestRegressor(n_estimators=200, max_features=4, random_state=42, n_jobs=-1),\n",
    "                             X, y_st, cv=plis)\n",
    "    err2 = (pred - y_st) ** 2\n",
    "    lignes[nom] = {\"RMSE toutes ventes\": round(np.sqrt(err2.mean()), 1),\n",
    "                   \"RMSE communes de stations\": round(np.sqrt(err2[en_station].mean()), 1)}\n",
    "print(en_station.sum(), \"ventes dans des communes de stations sur\", len(st))\n",
    "pd.DataFrame(lignes).T"
   ],
   "id": "888bb81d1cce"
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "708cba7aa322"
   },
   "source": [
    "**Lecture.** Aucun gain : environ 43 €/m² dans les trois cas, et l'erreur reste autour de 75 €/m² dans les communes de stations.\n",
    "Le modèle connaît déjà la latitude et la longitude, il « sait » donc où sont les stations. Ce qu'il rate, ce sont les écarts **à l'intérieur** d'une même commune : à Saint-Chaffrey, un terrain au pied des pistes et un terrain en bas du village sont tous deux « à 0 km de la station » mais n'ont pas le même prix. Il faudrait une mesure plus fine (distance aux remontées mécaniques à 100 m près, vue, zonage du PLU), à tester après ce projet.\n",
    "\n",
    "Le chiffre qui l'explique : dans les dix principales communes de stations, 71 % des écarts de prix existent entre ventes d'une même commune, et seulement 29 % entre communes. Au Monêtier-les-Bains, les terrains vont de 65 à 688 €/m² (10e et 90e centiles), à Montgenèvre de 136 à 720 €/m². La station explique pourquoi Saint-Chaffrey est plus chère que Gap, et le modèle le sait déjà grâce aux coordonnées ; elle n'explique pas pourquoi deux terrains de Saint-Chaffrey n'ont pas le même prix."
   ],
   "id": "708cba7aa322"
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "482e7bc876b0"
   },
   "source": [
    "# Conclusion\n",
    "\n",
    "**Résultats (RMSE en €/m², prix moyen 124 €/m²)**\n",
    "\n",
    "| Modèle | Validation croisée | Test |\n",
    "|---|---|---|\n",
    "| Naïf (prix moyen) | 80 | |\n",
    "| Régression linéaire | 57 | |\n",
    "| SVM linéaire | 58 | |\n",
    "| Arbre de décision | 64 | |\n",
    "| Random Forest | 47 | |\n",
    "| Random Forest réglé (Grid Search) | 46 | **45** (IC 95 % : 39 à 50) |\n",
    "| Random Forest sur log(prix) | 48 | 51 |\n",
    "| Réseau neuronal (Keras) | | 53 |\n",
    "\n",
    "Le Random Forest réglé est retenu : erreur absolue moyenne de 27 €/m², erreur relative médiane de 13 %. Il divise presque par deux l'erreur du modèle naïf. La surface, la position et la distance aux villes expliquent l'essentiel du prix ; le relief compte peu.\n",
    "\n",
    "**Ce qui fait le prix d'un terrain**\n",
    "- La surface d'abord : plus le terrain est grand, moins le m² est cher (27 % de l'importance dans le modèle).\n",
    "- L'emplacement ensuite : de 62 €/m² dans le Verdon à 200 €/m² dans le Briançonnais. La position et la distance aux villes pèsent 30 % à elles deux ; le prix médian passe de 162 €/m² près de Gap, Manosque, Digne ou Briançon à 75 €/m² vers 30 km.\n",
    "- Les stations de ski créent les prix les plus élevés (jusqu'à 500-700 €/m²) et les plus dispersés : c'est là que le modèle se trompe le plus.\n",
    "- L'altitude joue un peu (8 %). La pente, l'exposition au sud et la proximité d'un cours d'eau ne changent presque rien, contrairement à l'intuition.\n",
    "\n",
    "**Limites**\n",
    "- Données manquantes dans DVF : viabilisation, zonage du PLU, vue, permis. Deux terrains voisins peuvent avoir des prix très différents pour ces raisons.\n",
    "- Maisons neuves déclarées comme terrains : le filtre par commune en retire 140, mais il en reste sans doute dans les communes chères (stations).\n",
    "- Petite fuite de données : `nb_ventes_commune` est calculé sur toutes les ventes avant la séparation entraînement / test. Un test complémentaire, en le recalculant sur l'entraînement seulement, ne change l'erreur que de 0,2 €/m² : l'effet est négligeable.\n",
    "- Peu de ventes (environ 4 100) et un marché très inégal : l'erreur atteint 55 €/m² dans les Hautes-Alpes et bien plus dans les stations.\n",
    "- Correction par l'inflation générale (IPC), qui ne suit pas forcément les prix du foncier.\n",
    "\n",
    "**Pistes**\n",
    "- Ajouter le zonage du PLU (Géoportail de l'urbanisme), la part de résidences secondaires (Insee) et les risques naturels (Géorisques). Deux autres couches ont déjà été testées à part, sans gain notable (moins de 1 €/m²) : le prix des ventes voisines et la distance aux remontées mécaniques (OpenStreetMap). Comme pour les stations, le modèle connaît déjà l'emplacement ; il lui manque des informations sur le terrain lui-même.\n",
    "- Valider par zone géographique (entraîner sur certaines intercommunalités, tester sur d'autres) pour vérifier que le modèle se transpose.\n",
    "- Donner une fourchette de prix plutôt qu'une valeur unique.\n",
    "- Étendre aux autres départements alpins (06, 38, 73, 74) : le code est prévu pour.\n",
    "\n",
    "**Application**\n",
    "Le modèle peut servir d'outil d'estimation pour un constructeur de maisons des Hautes-Alpes : sur une carte, on clique sur un lieu, on choisit une surface et on obtient une fourchette de prix au m². L'outil aide à cadrer le budget terrain d'un client, à repérer une annonce trop chère ou une bonne affaire et à orienter la prospection. Pour le publier, il faudrait n'afficher que les zones constructibles (PLU) et des estimations, jamais les ventes individuelles (règles DVF)."
   ],
   "id": "482e7bc876b0"
  }
 ],
 "metadata": {
  "colab": {},
  "kernelspec": {
   "display_name": "Python 3",
   "name": "python3"
  },
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}