formations/python-avancé/exercises/BANO.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4200dd32",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import warnings\n",
    "import matplotlib.pyplot as plt\n",
    "from Levenshtein import distance\n",
    "warnings.simplefilter(\"ignore\")\n",
    "%matplotlib notebook"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fe6a15c4",
   "metadata": {},
   "outputs": [],
   "source": [
    "bano = pd.read_csv(\"https://bano.openstreetmap.fr/data/bano-78.csv\", names=[\"id\", \"numero\", \"voie\", \"code_post\", \"nom_comm\", \"source\", \"lat\", \"lon\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "18f66986",
   "metadata": {},
   "outputs": [],
   "source": [
    "bano"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "40f775d7",
   "metadata": {},
   "outputs": [],
   "source": [
    "bano.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "181f584b",
   "metadata": {},
   "outputs": [],
   "source": [
    "fig1, ax1 = plt.subplots()\n",
    "ax1.set_aspect('equal')\n",
    "plot = ax1.scatter(bano.lon, bano.lat, s=.1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "41b10d5d",
   "metadata": {},
   "outputs": [],
   "source": [
    "bano.source"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "67014ee9",
   "metadata": {},
   "outputs": [],
   "source": [
    "bano.source = pd.Categorical(bano.source)\n",
    "fig1, ax1 = plt.subplots()\n",
    "ax1.set_aspect('equal')\n",
    "plot = ax1.scatter(bano.lon, bano.lat, s=1, c=bano.source.cat.codes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "47d5416a",
   "metadata": {},
   "outputs": [],
   "source": [
    "bano.voie.str.split().str[0].value_counts().head(15).index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8814511d",
   "metadata": {},
   "outputs": [],
   "source": [
    "fig1, ax1 = plt.subplots()\n",
    "ax1.set_aspect('equal')\n",
    "for kind in bano.voie.str.split().str[0].value_counts().head(15).index:\n",
    "    to_plot = bano[bano.voie.str.startswith(kind)]\n",
    "    ax1.scatter(to_plot.lon, to_plot.lat, s=.1, label=kind)\n",
    "ax1.legend(markerscale=10, fontsize='small', bbox_to_anchor=(1.05, .95),  loc='upper left', )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4d442c4b",
   "metadata": {},
   "outputs": [],
   "source": [
    "bano.numero.max()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "da44b40f",
   "metadata": {},
   "outputs": [],
   "source": [
    "pd.to_numeric(bano.numero, errors='coerce').max()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2cb15832",
   "metadata": {},
   "outputs": [],
   "source": [
    "bano[\"numero_as_number\"] = pd.to_numeric(bano[\"numero\"], errors='coerce')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cd103772",
   "metadata": {},
   "outputs": [],
   "source": [
    "bano[bano.numero == \"78250\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b4da24e3",
   "metadata": {},
   "outputs": [],
   "source": [
    "bano[(bano.numero_as_number > 3000) & (bano.numero_as_number < 5000)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f81334da",
   "metadata": {},
   "outputs": [],
   "source": [
    "bano[~bano.code_post.astype(str).str.startswith(\"78\")]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c33bb852",
   "metadata": {},
   "outputs": [],
   "source": [
    "road_name_counts = bano.voie.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6c0eb639",
   "metadata": {},
   "outputs": [],
   "source": [
    "road_name_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2abc0c2d",
   "metadata": {},
   "outputs": [],
   "source": [
    "road_name_counts[road_name_counts == 1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "39170999",
   "metadata": {},
   "outputs": [],
   "source": [
    "epsilon = 0.01\n",
    "for suspicious_name in road_name_counts[road_name_counts == 1].index:\n",
    "    lat, lon = bano[bano.voie == suspicious_name].loc[:,('lat', 'lon')].to_numpy()[0]\n",
    "    neighbors = bano[(lat - epsilon < bano.lat) & (bano.lat < lat + epsilon) & (lon - epsilon < bano.lon) & (bano.lon < lon + epsilon)]\n",
    "    neighbors_names = set(neighbors.voie.values) - set([suspicious_name])\n",
    "    if not neighbors_names:\n",
    "        continue\n",
    "    proposed_name = min(neighbors_names, key=lambda n: distance(n, suspicious_name))\n",
    "    if distance(proposed_name, suspicious_name) < 3:\n",
    "        print(f\"Proposing to replace {suspicious_name!r} by {proposed_name!r}\")\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b7dc66c4",
   "metadata": {},
   "outputs": [],
   "source": [
    "nom_comm_counts = bano.nom_comm.value_counts()\n",
    "print(nom_comm_counts)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}