{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "1dc378ec",
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "from collections import Counter\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "7f2cc4f5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'Restaurant': 1799, 'Cafe': 486, 'Fast Food': 388, 'Convenience': 326, 'Supermarket': 190, 'Bar': 185, 'Pharmacy': 71, 'Hospital': 40, 'Bank': 525, 'School': 40, 'Cinema': 35, 'Police': 49, 'Clothes': 217, 'Post Office': 49, 'Hairdresser': 66, 'Bakery': 126}\n"
     ]
    }
   ],
   "source": [
    "with open('/home/ubuntu/codebase/yexijia/保研/colocation_mvp/data/beijing_poi.json', 'r', encoding='utf-8') as f:\n",
    "    geojson_data = json.load(f)\n",
    "    \n",
    "features = geojson_data\n",
    "a = []\n",
    "b = {}\n",
    "for i in features:\n",
    "    if not i['type'] in a:\n",
    "        a.append(i['type'])\n",
    "        b[i['type']] = 1\n",
    "    else:\n",
    "        b[i['type']]+=1\n",
    "print(b)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "b49d7424",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>type</th>\n",
       "      <th>num</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Restaurant</td>\n",
       "      <td>1799</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Bank</td>\n",
       "      <td>525</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Cafe</td>\n",
       "      <td>486</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Fast Food</td>\n",
       "      <td>388</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Convenience</td>\n",
       "      <td>326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Clothes</td>\n",
       "      <td>217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Supermarket</td>\n",
       "      <td>190</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Bar</td>\n",
       "      <td>185</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Bakery</td>\n",
       "      <td>126</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Pharmacy</td>\n",
       "      <td>71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Hairdresser</td>\n",
       "      <td>66</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Police</td>\n",
       "      <td>49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Post Office</td>\n",
       "      <td>49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Hospital</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>School</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Cinema</td>\n",
       "      <td>35</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           type   num\n",
       "0    Restaurant  1799\n",
       "8          Bank   525\n",
       "1          Cafe   486\n",
       "2     Fast Food   388\n",
       "3   Convenience   326\n",
       "12      Clothes   217\n",
       "4   Supermarket   190\n",
       "5           Bar   185\n",
       "15       Bakery   126\n",
       "6      Pharmacy    71\n",
       "14  Hairdresser    66\n",
       "11       Police    49\n",
       "13  Post Office    49\n",
       "7      Hospital    40\n",
       "9        School    40\n",
       "10       Cinema    35"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame(list(b.items()), columns=['type', 'num'])\n",
    "df = df.sort_values(by='num',ascending=False)\n",
    "df.head(2100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "df12020c",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.13.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}