{
 "metadata": {
  "name": "",
  "signature": "sha256:6325d03b4911b2fe2381e18c976fc024715dd50631e9257256b40b228669291e"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Part 1: \u9244\u9053\u8def\u7dda\u56f3\u30c7\u30fc\u30bf\u3092\u30b0\u30e9\u30d5\u3068\u3057\u3066\u89e3\u91c8\u3057\u3066\u53ef\u8996\u5316\u3059\u308b \n",
      "\n",
      "by [Keiichiro Ono](http://keiono.github.io/)\n",
      "\n",
      "----\n",
      "\n",
      "\u3053\u306e\u30ce\u30fc\u30c8\u30d6\u30c3\u30af\u306e\u57fa\u672c\u30c7\u30fc\u30bf\u306f\u3001\u5168\u3066[\u99c5\u30c7\u30fc\u30bf.jp](http://www.ekidata.jp/)\u306e\u7121\u6599\u7248\u30c7\u30fc\u30bf\u3092\u5229\u7528\u3055\u305b\u3066\u3044\u305f\u3060\u304d\u307e\u3057\u305f\u3002\n",
      "\n",
      "\n",
      "<a href=\"http://www.ekidata.jp/\" target=\"_blank\"><img src=\"http://www.ekidata.jp/img/220x70_b.gif\"\u3000alt=\"\u99c5\u30c7\u30fc\u30bf\" border=\"0\"></a>\n",
      " \n",
      "\n",
      "## \u306f\u3058\u3081\u306b\n",
      "\u7121\u511f\u3067\u5165\u624b\u3067\u304d\u308b\u9244\u9053\u95a2\u4fc2\u306e\u30c7\u30fc\u30bf\u3092\u30de\u30c3\u30d4\u30f3\u30b0\u3059\u308b\u305f\u3081\u306eCytoscape\u30bb\u30c3\u30b7\u30e7\u30f3\u30d5\u30a1\u30a4\u30eb\u3092\u4f5c\u6210\u3059\u308b\u305f\u3081\u306b\u884c\u3063\u305f\u3001\u30c7\u30fc\u30bf\u306e\u52a0\u5de5\u904e\u7a0b\u3067\u3059\u3002\uff08\u52b9\u7387\u6027\u306f\u7121\u8996\u3057\u3066\u3042\u308a\u307e\u3059\u306e\u3067\u3054\u4e86\u627f\u4e0b\u3055\u3044\u3002\uff09\n",
      "\n",
      "\u8a73\u7d30\u306f[\u3053\u3061\u3089\u306e\u8a18\u4e8b](http://qiita.com/keiono/items/29286f49b15a5b13c987)\u3092\u3054\u89a7\u304f\u3060\u3055\u3044\u3002\n",
      "\n",
      "\n",
      "### \u30b4\u30fc\u30eb\n",
      "Cytoscape\u4e0a\u5229\u7528\u3067\u304d\u308b\u30b0\u30e9\u30d5\u3068\u3057\u3066\u306e\u767d\u5730\u56f3\u3092\u4f5c\u6210\u3059\u308b\u3002\n",
      "\n",
      "### \u5fc5\u8981\u306a\u77e5\u8b58\n",
      "\u3053\u306e\u30b5\u30f3\u30d7\u30eb\u3092\u7406\u89e3\u3059\u308b\u306e\u306b\u5fc5\u8981\u306a\u6570\u5b66\u7684\u77e5\u8b58\u306f\u30bc\u30ed\u3067\u3059\u3002\u57fa\u790e\u7684\u306aPython\u3068Pandas\u306e\u77e5\u8b58\u3060\u3051\u3067\u3059\u3002\n",
      "\n",
      "### \u30a2\u30c3\u30d7\u30c7\u30fc\u30c8\u60c5\u5831\n",
      "* 8/15/2014: \u73fe\u5728\u3053\u306e\u30ce\u30fc\u30c8\u306f\u30a2\u30c3\u30d7\u30c7\u30fc\u30c8\u4e2d\u3067\u3059\u3002\u968f\u6642\u4fee\u6b63\u3092\u52a0\u3048\u3066\u3044\u304d\u307e\u3059\u3002\n",
      "\n",
      "----\n",
      "## \u5b9f\u969b\u306e\u30ef\u30fc\u30af\u30d5\u30ed\u30fc\n",
      "\n",
      "### 0. \u5fc5\u8981\u306a\u30e9\u30a4\u30d6\u30e9\u30ea\u306e\u8aad\u307f\u8fbc\u307f"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas as pd"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### 1. \u30c7\u30fc\u30bf\u306e\u8aad\u307f\u8fbc\u307f\n",
      "\u307e\u305a\u3001\u5168\u3066\u306e\u30c7\u30fc\u30bf\u3092Pandas\u306eDataFrame\u306b\u8aad\u307f\u8fbc\u307f\u307e\u3059\u3002\u3053\u308c\u306f\uff08\u73fe\u5728\u306e\u57fa\u6e96\u3067\u306f\uff09\u3068\u3066\u3082\u5c0f\u3055\u306a\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306a\u306e\u3067\u3001\u666e\u901a\u306e\u30e9\u30c3\u30d7\u30c8\u30c3\u30d7\u3067\u3082\u5168\u304f\u554f\u984c\u3042\u308a\u307e\u305b\u3093\u3002\u3059\u3079\u3066\u306e\u4f5c\u696d\u3092\u30e1\u30e2\u30ea\u4e0a\u3067\u884c\u3044\u307e\u3059\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# \u99c5\u306b\u95a2\u3059\u308b\u30c7\u30fc\u30bf\n",
      "station_df = pd.read_csv('station20140303free.csv')\n",
      "\n",
      "# \u8def\u7dda\u306b\u95a2\u3059\u308b\u30c7\u30fc\u30bf\n",
      "connection_df = pd.read_csv('line20140303free.csv')\n",
      "\n",
      "# \u99c5\u3068\u99c5\u306e\u63a5\u7d9a\u30c7\u30fc\u30bf\u3001\u3064\u307e\u308a\u30b0\u30e9\u30d5\n",
      "graph_df = pd.read_csv('join20140303.csv')\n",
      "\n",
      "# \u9244\u9053\u4f1a\u793e\u306e\u30c7\u30fc\u30bf\n",
      "company_df = pd.read_csv('company20130120.csv')\n",
      "\n",
      "# \u770c\u540d\u3068\u770cID\u306e\u30c6\u30fc\u30d6\u30eb\n",
      "pref_df = pd.read_csv('pref.csv')\n",
      "\n",
      "# \u8def\u7dda\u540d\u306e\u30ea\u30b9\u30c8\uff08\u5f8c\u307b\u3069\u4f7f\u7528\uff09\n",
      "line_names = connection_df[['line_cd', 'line_name']]\n",
      "line_names.head()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>line_cd</th>\n",
        "      <th>line_name</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 1001</td>\n",
        "      <td>  \u4e2d\u592e\u65b0\u5e79\u7dda</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1002</td>\n",
        "      <td> \u6771\u6d77\u9053\u65b0\u5e79\u7dda</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 1003</td>\n",
        "      <td>  \u5c71\u967d\u65b0\u5e79\u7dda</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 1004</td>\n",
        "      <td>  \u6771\u5317\u65b0\u5e79\u7dda</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 1005</td>\n",
        "      <td>  \u4e0a\u8d8a\u65b0\u5e79\u7dda</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>5 rows \u00d7 2 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 2,
       "text": [
        "   line_cd line_name\n",
        "0     1001     \u4e2d\u592e\u65b0\u5e79\u7dda\n",
        "1     1002    \u6771\u6d77\u9053\u65b0\u5e79\u7dda\n",
        "2     1003     \u5c71\u967d\u65b0\u5e79\u7dda\n",
        "3     1004     \u6771\u5317\u65b0\u5e79\u7dda\n",
        "4     1005     \u4e0a\u8d8a\u65b0\u5e79\u7dda\n",
        "\n",
        "[5 rows x 2 columns]"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### 2. \u30c7\u30fc\u30bf\u306e\u6383\u9664\n",
      "\u305d\u306e\u307e\u307e\u3067\u3082\u4f7f\u3048\u308b\u306e\u3067\u3059\u304c\u3001\u898b\u6804\u3048\u306e\u826f\u3044\u7d50\u679c\u3092\u5f97\u308b\u305f\u3081\u306b\u3001\u5fc5\u8981\u306e\u306a\u3044\u3082\u306e\u3092\u524a\u9664\u3084\u3001\u65b0\u305f\u306a\u30c7\u30fc\u30bf\u306e\u751f\u6210\u3092\u884c\u3044\u307e\u3059\u3002\n",
      "\n",
      "#### \u5fc5\u8981\u306e\u306a\u3044\u30ab\u30e9\u30e0\u306e\u524a\u9664\n",
      "\u6709\u6599\u7248\u306e\u307f\u306b\u63d0\u4f9b\u3055\u308c\u3066\u3044\u308b\u30ab\u30e9\u30e0\u306f\u524a\u9664\u3057\u307e\u3059\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "station_df.drop(['station_name_k', 'station_name_r', 'e_sort'], axis=1, inplace=True)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "#### \u7def\u5ea6\u3068\u7d4c\u5ea6\u304b\u3089Cytoscape\u306e\u5ea7\u6a19\u7cfb\u306b\u5909\u63db\u3059\u308b\n",
      "\u5ea7\u6a19\u7cfb\u306e\u5909\u63db\u3068\u8a00\u3063\u3066\u3082\u3001\u7279\u306b\u8907\u96d1\u306a\u8a08\u7b97\u306f\u5fc5\u8981\u3042\u308a\u307e\u305b\u3093\u3002y\u8ef8\u306e\u4e0b\u304c\u6b63\u306e\u65b9\u5411\u306b\u306a\u3063\u3066\u3044\u308b\u306e\u3067\u3001\u305d\u308c\u3092\u4fee\u6b63\u3057\u3001\u3042\u3068\u306f\u6b63\u3057\u304f\u8868\u793a\u3055\u308c\u308b\u3088\u3046\u306b\u30b9\u30b1\u30fc\u30ea\u30f3\u30b0\u3057\u307e\u3059\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "SCALE_FACTOR = 10000\n",
      "\n",
      "station_df['x'] = station_df['lon']  * SCALE_FACTOR\n",
      "station_df['y'] = station_df['lat'] * (-SCALE_FACTOR)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "#### \u770c\u540d\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u3068\u99c5\u60c5\u5831\u306e\u7d71\u5408\n",
      "\u30b7\u30f3\u30d7\u30eb\u306a\u30de\u30fc\u30b8\u3092\u884c\u3044\u3001\u770cID\u3092\u770c\u540d\u306b\u5909\u63db\u3057\u307e\u3059"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# \u4eba\u9593\u306b\u3068\u3063\u3066\u8aad\u307f\u3084\u3059\u3044\u3088\u3046\u306b\u3001\u770c\u306eID\u3092\u770c\u540d\u306b\u5909\u63db\u3059\u308b\n",
      "merged_stations = pd.merge(pref_df, station_df, on = 'pref_cd')\n",
      "\n",
      "# \u8def\u7dda\u540d\u3082\u4eba\u304c\u8aad\u3081\u308b\u3082\u306e\u306b\u3059\u308b\n",
      "merged_stations = pd.merge(merged_stations, line_names, on='line_cd')\n",
      "\n",
      "# \u5fc5\u8981\u306e\u7121\u304f\u306a\u3063\u305f\u30ab\u30e9\u30e0\u3092\u9664\u53bb\n",
      "merged_stations.drop(['pref_cd', 'line_cd'], axis=1, inplace=True)\n",
      "\n",
      "merged_stations.head()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>pref_name</th>\n",
        "      <th>station_cd</th>\n",
        "      <th>station_g_cd</th>\n",
        "      <th>station_name</th>\n",
        "      <th>post</th>\n",
        "      <th>add</th>\n",
        "      <th>lon</th>\n",
        "      <th>lat</th>\n",
        "      <th>open_ymd</th>\n",
        "      <th>close_ymd</th>\n",
        "      <th>e_status</th>\n",
        "      <th>x</th>\n",
        "      <th>y</th>\n",
        "      <th>line_name</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> \u5317\u6d77\u9053</td>\n",
        "      <td> 1110101</td>\n",
        "      <td> 1110101</td>\n",
        "      <td>  \u51fd\u9928</td>\n",
        "      <td> 040-0063</td>\n",
        "      <td>   \u5317\u6d77\u9053\u51fd\u9928\u5e02\u82e5\u677e\u753a\uff11\uff12-\uff11\uff13</td>\n",
        "      <td> 140.726413</td>\n",
        "      <td> 41.773709</td>\n",
        "      <td> 1902-12-10</td>\n",
        "      <td> NaN</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1407264.13</td>\n",
        "      <td>-417737.09</td>\n",
        "      <td> JR\u51fd\u9928\u672c\u7dda(\u51fd\u9928\uff5e\u9577\u4e07\u90e8)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> \u5317\u6d77\u9053</td>\n",
        "      <td> 1110102</td>\n",
        "      <td> 1110102</td>\n",
        "      <td> \u4e94\u7a1c\u90ed</td>\n",
        "      <td> 041-0813</td>\n",
        "      <td>          \u51fd\u9928\u5e02\u4e80\u7530\u672c\u753a</td>\n",
        "      <td> 140.733539</td>\n",
        "      <td> 41.803557</td>\n",
        "      <td>        NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1407335.39</td>\n",
        "      <td>-418035.57</td>\n",
        "      <td> JR\u51fd\u9928\u672c\u7dda(\u51fd\u9928\uff5e\u9577\u4e07\u90e8)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> \u5317\u6d77\u9053</td>\n",
        "      <td> 1110103</td>\n",
        "      <td> 1110103</td>\n",
        "      <td>  \u6854\u6897</td>\n",
        "      <td> 041-1210</td>\n",
        "      <td> \u5317\u6d77\u9053\u51fd\u9928\u5e02\u6854\u6897\uff13\u4e01\u76ee\uff14\uff11-\uff13\uff16</td>\n",
        "      <td> 140.722952</td>\n",
        "      <td> 41.846457</td>\n",
        "      <td> 1902-12-10</td>\n",
        "      <td> NaN</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1407229.52</td>\n",
        "      <td>-418464.57</td>\n",
        "      <td> JR\u51fd\u9928\u672c\u7dda(\u51fd\u9928\uff5e\u9577\u4e07\u90e8)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> \u5317\u6d77\u9053</td>\n",
        "      <td> 1110104</td>\n",
        "      <td> 1110104</td>\n",
        "      <td> \u5927\u4e2d\u5c71</td>\n",
        "      <td> 041-1121</td>\n",
        "      <td>      \u4e80\u7530\u90e1\u4e03\u98ef\u753a\u5927\u5b57\u5927\u4e2d\u5c71</td>\n",
        "      <td> 140.713580</td>\n",
        "      <td> 41.864641</td>\n",
        "      <td>        NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1407135.80</td>\n",
        "      <td>-418646.41</td>\n",
        "      <td> JR\u51fd\u9928\u672c\u7dda(\u51fd\u9928\uff5e\u9577\u4e07\u90e8)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> \u5317\u6d77\u9053</td>\n",
        "      <td> 1110105</td>\n",
        "      <td> 1110105</td>\n",
        "      <td>  \u4e03\u98ef</td>\n",
        "      <td> 041-1111</td>\n",
        "      <td>        \u4e80\u7530\u90e1\u4e03\u98ef\u753a\u5b57\u672c\u753a</td>\n",
        "      <td> 140.688556</td>\n",
        "      <td> 41.886971</td>\n",
        "      <td>        NaN</td>\n",
        "      <td> NaN</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1406885.56</td>\n",
        "      <td>-418869.71</td>\n",
        "      <td> JR\u51fd\u9928\u672c\u7dda(\u51fd\u9928\uff5e\u9577\u4e07\u90e8)</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>5 rows \u00d7 14 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 5,
       "text": [
        "  pref_name  station_cd  station_g_cd station_name      post  \\\n",
        "0       \u5317\u6d77\u9053     1110101       1110101           \u51fd\u9928  040-0063   \n",
        "1       \u5317\u6d77\u9053     1110102       1110102          \u4e94\u7a1c\u90ed  041-0813   \n",
        "2       \u5317\u6d77\u9053     1110103       1110103           \u6854\u6897  041-1210   \n",
        "3       \u5317\u6d77\u9053     1110104       1110104          \u5927\u4e2d\u5c71  041-1121   \n",
        "4       \u5317\u6d77\u9053     1110105       1110105           \u4e03\u98ef  041-1111   \n",
        "\n",
        "                add         lon        lat    open_ymd close_ymd  e_status  \\\n",
        "0    \u5317\u6d77\u9053\u51fd\u9928\u5e02\u82e5\u677e\u753a\uff11\uff12-\uff11\uff13  140.726413  41.773709  1902-12-10       NaN         0   \n",
        "1           \u51fd\u9928\u5e02\u4e80\u7530\u672c\u753a  140.733539  41.803557         NaN       NaN         0   \n",
        "2  \u5317\u6d77\u9053\u51fd\u9928\u5e02\u6854\u6897\uff13\u4e01\u76ee\uff14\uff11-\uff13\uff16  140.722952  41.846457  1902-12-10       NaN         0   \n",
        "3       \u4e80\u7530\u90e1\u4e03\u98ef\u753a\u5927\u5b57\u5927\u4e2d\u5c71  140.713580  41.864641         NaN       NaN         0   \n",
        "4         \u4e80\u7530\u90e1\u4e03\u98ef\u753a\u5b57\u672c\u753a  140.688556  41.886971         NaN       NaN         0   \n",
        "\n",
        "            x          y       line_name  \n",
        "0  1407264.13 -417737.09  JR\u51fd\u9928\u672c\u7dda(\u51fd\u9928\uff5e\u9577\u4e07\u90e8)  \n",
        "1  1407335.39 -418035.57  JR\u51fd\u9928\u672c\u7dda(\u51fd\u9928\uff5e\u9577\u4e07\u90e8)  \n",
        "2  1407229.52 -418464.57  JR\u51fd\u9928\u672c\u7dda(\u51fd\u9928\uff5e\u9577\u4e07\u90e8)  \n",
        "3  1407135.80 -418646.41  JR\u51fd\u9928\u672c\u7dda(\u51fd\u9928\uff5e\u9577\u4e07\u90e8)  \n",
        "4  1406885.56 -418869.71  JR\u51fd\u9928\u672c\u7dda(\u51fd\u9928\uff5e\u9577\u4e07\u90e8)  \n",
        "\n",
        "[5 rows x 14 columns]"
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "#### \u8def\u7dda\u30c7\u30fc\u30bf\u306e\u7c21\u5358\u306a\u52a0\u5de5\n",
      "\u8def\u7dda\u60c5\u5831\u306e\u30c6\u30fc\u30d6\u30eb\u306b\u3082\u7c21\u5358\u306a\u52a0\u5de5\u3092\u65bd\u3057\u307e\u3059\u3002\n",
      "\n",
      "* \u5fc5\u8981\u306e\u306a\u3044\u30ab\u30e9\u30e0\u306e\u9664\u53bb"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# \u5fc5\u8981\u306a\u3044\u30ab\u30e9\u30e0\u306e\u524a\u9664\n",
      "connection_df.drop(['line_color_c', 'line_color_t', 'line_type', 'e_sort'], axis=1, inplace=True)\n",
      "connection_df.head(5)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>line_cd</th>\n",
        "      <th>company_cd</th>\n",
        "      <th>line_name</th>\n",
        "      <th>line_name_k</th>\n",
        "      <th>line_name_h</th>\n",
        "      <th>lon</th>\n",
        "      <th>lat</th>\n",
        "      <th>zoom</th>\n",
        "      <th>e_status</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 1001</td>\n",
        "      <td> 3</td>\n",
        "      <td>  \u4e2d\u592e\u65b0\u5e79\u7dda</td>\n",
        "      <td>  \u30c1\u30e5\u30a6\u30aa\u30a6\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3</td>\n",
        "      <td>  \u4e2d\u592e\u65b0\u5e79\u7dda</td>\n",
        "      <td> 137.493896</td>\n",
        "      <td> 35.411438</td>\n",
        "      <td> 8</td>\n",
        "      <td> 1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 1002</td>\n",
        "      <td> 3</td>\n",
        "      <td> \u6771\u6d77\u9053\u65b0\u5e79\u7dda</td>\n",
        "      <td> \u30c8\u30a6\u30ab\u30a4\u30c9\u30a6\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3</td>\n",
        "      <td> \u6771\u6d77\u9053\u65b0\u5e79\u7dda</td>\n",
        "      <td> 137.721489</td>\n",
        "      <td> 35.144122</td>\n",
        "      <td> 7</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 1003</td>\n",
        "      <td> 4</td>\n",
        "      <td>  \u5c71\u967d\u65b0\u5e79\u7dda</td>\n",
        "      <td>   \u30b5\u30f3\u30e8\u30a6\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3</td>\n",
        "      <td>  \u5c71\u967d\u65b0\u5e79\u7dda</td>\n",
        "      <td> 133.147896</td>\n",
        "      <td> 34.419338</td>\n",
        "      <td> 7</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 1004</td>\n",
        "      <td> 2</td>\n",
        "      <td>  \u6771\u5317\u65b0\u5e79\u7dda</td>\n",
        "      <td>   \u30c8\u30a6\u30db\u30af\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3</td>\n",
        "      <td>  \u6771\u5317\u65b0\u5e79\u7dda</td>\n",
        "      <td> 140.763192</td>\n",
        "      <td> 38.274267</td>\n",
        "      <td> 7</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 1005</td>\n",
        "      <td> 2</td>\n",
        "      <td>  \u4e0a\u8d8a\u65b0\u5e79\u7dda</td>\n",
        "      <td>  \u30b8\u30e7\u30a6\u30a8\u30c4\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3</td>\n",
        "      <td>  \u4e0a\u8d8a\u65b0\u5e79\u7dda</td>\n",
        "      <td> 139.121488</td>\n",
        "      <td> 36.798565</td>\n",
        "      <td> 8</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>5 rows \u00d7 9 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 6,
       "text": [
        "   line_cd  company_cd line_name   line_name_k line_name_h         lon  \\\n",
        "0     1001           3     \u4e2d\u592e\u65b0\u5e79\u7dda   \u30c1\u30e5\u30a6\u30aa\u30a6\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3       \u4e2d\u592e\u65b0\u5e79\u7dda  137.493896   \n",
        "1     1002           3    \u6771\u6d77\u9053\u65b0\u5e79\u7dda  \u30c8\u30a6\u30ab\u30a4\u30c9\u30a6\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3      \u6771\u6d77\u9053\u65b0\u5e79\u7dda  137.721489   \n",
        "2     1003           4     \u5c71\u967d\u65b0\u5e79\u7dda    \u30b5\u30f3\u30e8\u30a6\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3       \u5c71\u967d\u65b0\u5e79\u7dda  133.147896   \n",
        "3     1004           2     \u6771\u5317\u65b0\u5e79\u7dda    \u30c8\u30a6\u30db\u30af\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3       \u6771\u5317\u65b0\u5e79\u7dda  140.763192   \n",
        "4     1005           2     \u4e0a\u8d8a\u65b0\u5e79\u7dda   \u30b8\u30e7\u30a6\u30a8\u30c4\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3       \u4e0a\u8d8a\u65b0\u5e79\u7dda  139.121488   \n",
        "\n",
        "         lat  zoom  e_status  \n",
        "0  35.411438     8         1  \n",
        "1  35.144122     7         0  \n",
        "2  34.419338     7         0  \n",
        "3  38.274267     7         0  \n",
        "4  36.798565     8         0  \n",
        "\n",
        "[5 rows x 9 columns]"
       ]
      }
     ],
     "prompt_number": 6
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### \u4e8b\u696d\u8005\u60c5\u5831\u3068\u8def\u7dda\u30c7\u30fc\u30bf\u306e\u30de\u30fc\u30b8\n",
      "\u3053\u306e\u30de\u30fc\u30b8\u306b\u3088\u308a\u30c6\u30fc\u30d6\u30eb\u304c\u5197\u9577\u306b\u306a\u308a\u307e\u3059\u304c\u3001Cytoscape\u4e0a\u3067\u4fbf\u5229\u306a\u306e\u3067\u5b9f\u884c\u3057\u3066\u65b0\u3057\u3044\u30c6\u30fc\u30d6\u30eb\u306b\u3057\u307e\u3059\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "connection_final_df= pd.merge(connection_df, company_df, on='company_cd')\n",
      "connection_final_df.drop(['e_sort'], axis=1, inplace=True)\n",
      "connection_final_df.head()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>line_cd</th>\n",
        "      <th>company_cd</th>\n",
        "      <th>line_name</th>\n",
        "      <th>line_name_k</th>\n",
        "      <th>line_name_h</th>\n",
        "      <th>lon</th>\n",
        "      <th>lat</th>\n",
        "      <th>zoom</th>\n",
        "      <th>e_status_x</th>\n",
        "      <th>rr_cd</th>\n",
        "      <th>company_name</th>\n",
        "      <th>company_name_k</th>\n",
        "      <th>company_name_h</th>\n",
        "      <th>company_name_r</th>\n",
        "      <th>company_url</th>\n",
        "      <th>company_type</th>\n",
        "      <th>e_status_y</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>  1001</td>\n",
        "      <td> 3</td>\n",
        "      <td>          \u4e2d\u592e\u65b0\u5e79\u7dda</td>\n",
        "      <td>  \u30c1\u30e5\u30a6\u30aa\u30a6\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3</td>\n",
        "      <td>          \u4e2d\u592e\u65b0\u5e79\u7dda</td>\n",
        "      <td> 137.493896</td>\n",
        "      <td> 35.411438</td>\n",
        "      <td>  8</td>\n",
        "      <td> 1</td>\n",
        "      <td> 11</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4</td>\n",
        "      <td> \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> http://jr-central.co.jp/</td>\n",
        "      <td> 1</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>  1002</td>\n",
        "      <td> 3</td>\n",
        "      <td>         \u6771\u6d77\u9053\u65b0\u5e79\u7dda</td>\n",
        "      <td> \u30c8\u30a6\u30ab\u30a4\u30c9\u30a6\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3</td>\n",
        "      <td>         \u6771\u6d77\u9053\u65b0\u5e79\u7dda</td>\n",
        "      <td> 137.721489</td>\n",
        "      <td> 35.144122</td>\n",
        "      <td>  7</td>\n",
        "      <td> 0</td>\n",
        "      <td> 11</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4</td>\n",
        "      <td> \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> http://jr-central.co.jp/</td>\n",
        "      <td> 1</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 11402</td>\n",
        "      <td> 3</td>\n",
        "      <td>          JR\u8eab\u5ef6\u7dda</td>\n",
        "      <td>        \u30df\u30ce\u30d6\u30bb\u30f3</td>\n",
        "      <td>          JR\u8eab\u5ef6\u7dda</td>\n",
        "      <td> 138.532397</td>\n",
        "      <td> 35.392163</td>\n",
        "      <td> 10</td>\n",
        "      <td> 0</td>\n",
        "      <td> 11</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4</td>\n",
        "      <td> \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> http://jr-central.co.jp/</td>\n",
        "      <td> 1</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 11411</td>\n",
        "      <td> 3</td>\n",
        "      <td> JR\u4e2d\u592e\u672c\u7dda(\u540d\u53e4\u5c4b\uff5e\u5869\u5c3b)</td>\n",
        "      <td>    \u30c1\u30e5\u30a6\u30aa\u30a6\u30db\u30f3\u30bb\u30f3</td>\n",
        "      <td> JR\u4e2d\u592e\u672c\u7dda(\u540d\u53e4\u5c4b\uff5e\u5869\u5c3b)</td>\n",
        "      <td> 137.468492</td>\n",
        "      <td> 35.662471</td>\n",
        "      <td>  9</td>\n",
        "      <td> 0</td>\n",
        "      <td> 11</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4</td>\n",
        "      <td> \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> http://jr-central.co.jp/</td>\n",
        "      <td> 1</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 11413</td>\n",
        "      <td> 3</td>\n",
        "      <td>  JR\u98ef\u7530\u7dda(\u8c4a\u6a4b\uff5e\u5929\u7adc\u5ce1)</td>\n",
        "      <td>        \u30a4\u30a4\u30c0\u30bb\u30f3</td>\n",
        "      <td>  JR\u98ef\u7530\u7dda(\u8c4a\u6a4b\uff5e\u5929\u7adc\u5ce1)</td>\n",
        "      <td> 137.668949</td>\n",
        "      <td> 35.125648</td>\n",
        "      <td> 10</td>\n",
        "      <td> 0</td>\n",
        "      <td> 11</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4</td>\n",
        "      <td> \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> http://jr-central.co.jp/</td>\n",
        "      <td> 1</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>5 rows \u00d7 17 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "   line_cd  company_cd       line_name   line_name_k     line_name_h  \\\n",
        "0     1001           3           \u4e2d\u592e\u65b0\u5e79\u7dda   \u30c1\u30e5\u30a6\u30aa\u30a6\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3           \u4e2d\u592e\u65b0\u5e79\u7dda   \n",
        "1     1002           3          \u6771\u6d77\u9053\u65b0\u5e79\u7dda  \u30c8\u30a6\u30ab\u30a4\u30c9\u30a6\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3          \u6771\u6d77\u9053\u65b0\u5e79\u7dda   \n",
        "2    11402           3           JR\u8eab\u5ef6\u7dda         \u30df\u30ce\u30d6\u30bb\u30f3           JR\u8eab\u5ef6\u7dda   \n",
        "3    11411           3  JR\u4e2d\u592e\u672c\u7dda(\u540d\u53e4\u5c4b\uff5e\u5869\u5c3b)     \u30c1\u30e5\u30a6\u30aa\u30a6\u30db\u30f3\u30bb\u30f3  JR\u4e2d\u592e\u672c\u7dda(\u540d\u53e4\u5c4b\uff5e\u5869\u5c3b)   \n",
        "4    11413           3   JR\u98ef\u7530\u7dda(\u8c4a\u6a4b\uff5e\u5929\u7adc\u5ce1)         \u30a4\u30a4\u30c0\u30bb\u30f3   JR\u98ef\u7530\u7dda(\u8c4a\u6a4b\uff5e\u5929\u7adc\u5ce1)   \n",
        "\n",
        "          lon        lat  zoom  e_status_x  rr_cd company_name company_name_k  \\\n",
        "0  137.493896  35.411438     8           1     11         JR\u6771\u6d77     \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4   \n",
        "1  137.721489  35.144122     7           0     11         JR\u6771\u6d77     \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4   \n",
        "2  138.532397  35.392163    10           0     11         JR\u6771\u6d77     \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4   \n",
        "3  137.468492  35.662471     9           0     11         JR\u6771\u6d77     \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4   \n",
        "4  137.668949  35.125648    10           0     11         JR\u6771\u6d77     \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4   \n",
        "\n",
        "  company_name_h company_name_r               company_url  company_type  \\\n",
        "0     \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e           JR\u6771\u6d77  http://jr-central.co.jp/             1   \n",
        "1     \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e           JR\u6771\u6d77  http://jr-central.co.jp/             1   \n",
        "2     \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e           JR\u6771\u6d77  http://jr-central.co.jp/             1   \n",
        "3     \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e           JR\u6771\u6d77  http://jr-central.co.jp/             1   \n",
        "4     \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e           JR\u6771\u6d77  http://jr-central.co.jp/             1   \n",
        "\n",
        "   e_status_y  \n",
        "0           0  \n",
        "1           0  \n",
        "2           0  \n",
        "3           0  \n",
        "4           0  \n",
        "\n",
        "[5 rows x 17 columns]"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "#### \u99c5\u306e\u63a5\u7d9a\u30c7\u30fc\u30bf\u3092\u8def\u7dda\u60c5\u5831\u3068\u7d71\u5408\u3059\u308b\n",
      "\u3053\u306e\u8def\u7dda\u63a5\u7d9a\u30c7\u30fc\u30bf\u306b\u306f\u3001\u99c5\u306b\u95a2\u3059\u308b\u60c5\u5831\u306e\u306a\u3044\u3082\u306e\u304c\u542b\u307e\u308c\u3066\u3044\u307e\u3059\u3002\u305d\u308c\u3089\u3092\u3072\u3068\u5de5\u592b\u3057\u3066\u9664\u53bb\u3057\u307e\u3059\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# \u30b0\u30e9\u30d5\u3068\u8def\u7dda\u30c7\u30fc\u30bf\u3092\u30de\u30fc\u30b8\n",
      "graph_new_df = pd.merge(connection_final_df, graph_df, on='line_cd')\n",
      "\n",
      "# \u5168\u3066\u306e\u30e6\u30cb\u30fc\u30af\u306a\u99c5ID\u3092\u99c5\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u304b\u3089\u53d6\u308a\u51fa\u3059\n",
      "all_stations = merged_stations['station_cd'].unique()\n",
      "\n",
      "# \u30b0\u30e9\u30d5\u30c7\u30fc\u30bf\u306b\u542b\u307e\u308c\u308b\u30e6\u30cb\u30fc\u30af\u306a\u99c5ID\u3092\u62bd\u51fa\n",
      "st1 = graph_new_df['station_cd1']\n",
      "st2 = graph_new_df['station_cd2']\n",
      "stations_in_graph = pd.concat([st1,st2]).unique()\n",
      "\n",
      "# \u30c7\u30fc\u30bf\u306e\u306a\u3044\u99c5\u3092\u30c1\u30a7\u30c3\u30af\u3059\u308b\u95a2\u6570\n",
      "def has_loc(station_id1, station_id2, all_stations):\n",
      "    if station_id1 in all_stations and station_id2 in all_stations:\n",
      "        return True\n",
      "    else:\n",
      "        return False\n",
      "\n",
      "# \u305d\u306e\u95a2\u6570\u3092\u6e21\u3057\u3066\u30e9\u30e0\u30c0\u5f0f\u3068\u3057\u3066\u9069\u7528\n",
      "graph_new_df['has_station_data'] = graph_new_df.apply(lambda row:  has_loc(row['station_cd1'], row['station_cd2'], all_stations), axis=1)\n",
      "\n",
      "# \u30c7\u30fc\u30bf\u306e\u306a\u3044\u30a8\u30c3\u30b8\u3092\u9664\u53bb\u3059\u308b\n",
      "graph_final_df = graph_new_df[graph_new_df['has_station_data'] == True]\n",
      "graph_final_df.head(3)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>line_cd</th>\n",
        "      <th>company_cd</th>\n",
        "      <th>line_name</th>\n",
        "      <th>line_name_k</th>\n",
        "      <th>line_name_h</th>\n",
        "      <th>lon</th>\n",
        "      <th>lat</th>\n",
        "      <th>zoom</th>\n",
        "      <th>e_status_x</th>\n",
        "      <th>rr_cd</th>\n",
        "      <th>company_name</th>\n",
        "      <th>company_name_k</th>\n",
        "      <th>company_name_h</th>\n",
        "      <th>company_name_r</th>\n",
        "      <th>company_url</th>\n",
        "      <th>company_type</th>\n",
        "      <th>e_status_y</th>\n",
        "      <th>station_cd1</th>\n",
        "      <th>station_cd2</th>\n",
        "      <th>has_station_data</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>16</th>\n",
        "      <td> 11402</td>\n",
        "      <td> 3</td>\n",
        "      <td> JR\u8eab\u5ef6\u7dda</td>\n",
        "      <td> \u30df\u30ce\u30d6\u30bb\u30f3</td>\n",
        "      <td> JR\u8eab\u5ef6\u7dda</td>\n",
        "      <td> 138.532397</td>\n",
        "      <td> 35.392163</td>\n",
        "      <td> 10</td>\n",
        "      <td> 0</td>\n",
        "      <td> 11</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4</td>\n",
        "      <td> \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> http://jr-central.co.jp/</td>\n",
        "      <td> 1</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1140201</td>\n",
        "      <td> 1140202</td>\n",
        "      <td> True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>17</th>\n",
        "      <td> 11402</td>\n",
        "      <td> 3</td>\n",
        "      <td> JR\u8eab\u5ef6\u7dda</td>\n",
        "      <td> \u30df\u30ce\u30d6\u30bb\u30f3</td>\n",
        "      <td> JR\u8eab\u5ef6\u7dda</td>\n",
        "      <td> 138.532397</td>\n",
        "      <td> 35.392163</td>\n",
        "      <td> 10</td>\n",
        "      <td> 0</td>\n",
        "      <td> 11</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4</td>\n",
        "      <td> \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> http://jr-central.co.jp/</td>\n",
        "      <td> 1</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1140202</td>\n",
        "      <td> 1140203</td>\n",
        "      <td> True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>18</th>\n",
        "      <td> 11402</td>\n",
        "      <td> 3</td>\n",
        "      <td> JR\u8eab\u5ef6\u7dda</td>\n",
        "      <td> \u30df\u30ce\u30d6\u30bb\u30f3</td>\n",
        "      <td> JR\u8eab\u5ef6\u7dda</td>\n",
        "      <td> 138.532397</td>\n",
        "      <td> 35.392163</td>\n",
        "      <td> 10</td>\n",
        "      <td> 0</td>\n",
        "      <td> 11</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4</td>\n",
        "      <td> \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e</td>\n",
        "      <td> JR\u6771\u6d77</td>\n",
        "      <td> http://jr-central.co.jp/</td>\n",
        "      <td> 1</td>\n",
        "      <td> 0</td>\n",
        "      <td> 1140203</td>\n",
        "      <td> 1140204</td>\n",
        "      <td> True</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>3 rows \u00d7 20 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "    line_cd  company_cd line_name line_name_k line_name_h         lon  \\\n",
        "16    11402           3     JR\u8eab\u5ef6\u7dda       \u30df\u30ce\u30d6\u30bb\u30f3       JR\u8eab\u5ef6\u7dda  138.532397   \n",
        "17    11402           3     JR\u8eab\u5ef6\u7dda       \u30df\u30ce\u30d6\u30bb\u30f3       JR\u8eab\u5ef6\u7dda  138.532397   \n",
        "18    11402           3     JR\u8eab\u5ef6\u7dda       \u30df\u30ce\u30d6\u30bb\u30f3       JR\u8eab\u5ef6\u7dda  138.532397   \n",
        "\n",
        "          lat  zoom  e_status_x  rr_cd company_name company_name_k  \\\n",
        "16  35.392163    10           0     11         JR\u6771\u6d77     \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4   \n",
        "17  35.392163    10           0     11         JR\u6771\u6d77     \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4   \n",
        "18  35.392163    10           0     11         JR\u6771\u6d77     \u30b8\u30a7\u30a4\u30a2\u30fc\u30eb\u30c8\u30a6\u30ab\u30a4   \n",
        "\n",
        "   company_name_h company_name_r               company_url  company_type  \\\n",
        "16     \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e           JR\u6771\u6d77  http://jr-central.co.jp/             1   \n",
        "17     \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e           JR\u6771\u6d77  http://jr-central.co.jp/             1   \n",
        "18     \u6771\u6d77\u65c5\u5ba2\u9244\u9053\u682a\u5f0f\u4f1a\u793e           JR\u6771\u6d77  http://jr-central.co.jp/             1   \n",
        "\n",
        "    e_status_y  station_cd1  station_cd2 has_station_data  \n",
        "16           0      1140201      1140202             True  \n",
        "17           0      1140202      1140203             True  \n",
        "18           0      1140203      1140204             True  \n",
        "\n",
        "[3 rows x 20 columns]"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### 3.\u30c7\u30fc\u30bf\u306e\u66f8\u304d\u51fa\u3057\n",
      "\u4eca\u56de\u306f\u57fa\u790e\u3092\u5b66\u3076\u305f\u3081\u306b\u3001\u30d5\u30a1\u30a4\u30eb\u30d9\u30fc\u30b9\u3067\u30c7\u30fc\u30bf\u3092\u3084\u308a\u3068\u308a\u3057\u307e\u3059\u3002\u4ee5\u4e0b\u306eCSV\u30d5\u30a1\u30a4\u30eb\u306fCytoscape\u306b\u5bb9\u6613\u306b\u8aad\u307f\u8fbc\u3081\u307e\u3059\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "graph_final_df.to_csv('graph_disconnected.csv')\n",
      "merged_stations.to_csv('stations.csv')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 9
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### 4. Cytoscape\u3067\u306e\u8aad\u307f\u8fbc\u307f\u3068\u53ef\u8996\u5316\n",
      "\u30c6\u30ad\u30b9\u30c8\u30c6\u30fc\u30d6\u30eb\u306b\u306a\u308c\u3070\u3001Cytoscape\u306b\u8aad\u307f\u8fbc\u3080\u3053\u3068\u306f\u7c21\u5358\u3067\u3059\u3002\u8a73\u7d30\u306f\u8a18\u4e8b\u306e\u65b9\u306b\u3002\n",
      "\n",
      "#### \u65e5\u672c\u306e\u9244\u9053\u30b7\u30b9\u30c6\u30e0\uff08\u5730\u7406\u60c5\u5831\u306b\u3088\u308b\u30ce\u30fc\u30c9\u306e\u914d\u7f6e\uff09\n",
      "\n",
      "![](http://cl.ly/Wy4M/japan_railways.png)\n",
      "\n",
      "#### \u6771\u4eac\u30a8\u30ea\u30a2\u306e\u30ba\u30fc\u30e0\n",
      "\n",
      "![](http://cl.ly/X0Dr/tokyo.png)\n",
      "\n",
      "\n",
      "* [Cytoscape 3.1.1\u3067\u4f5c\u6210\u3057\u305f\u30bb\u30c3\u30b7\u30e7\u30f3\u30d5\u30a1\u30a4\u30eb](http://cl.ly/X0D7/japan_railways_final.cys)"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "----\n",
      "\n",
      "# Part 2: \u30b0\u30e9\u30d5\u306e\u52a0\u5de5\u3068\u516c\u5171\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3068\u306e\u30de\u30fc\u30b8\n",
      "\n",
      "## 1. \u30af\u30ea\u30fc\u30af\u306e\u4f5c\u6210\n",
      "\u30b0\u30e9\u30d5\u5185\u306e\u30b0\u30eb\u30fc\u30d7\u3092\u30af\u30ea\u30fc\u30af\u5316\u3057\u3001\u5168\u56fd\u306e\u8def\u7dda\u3092\u63a5\u7d9a\u3057\u307e\u3059\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# \u30b0\u30eb\u30fc\u30d7\u3092\u62bd\u51fa\u3000\uff08\u975e\u52b9\u7387\u306a\u306e\u3067\u5f53\u7136\u306a\u304c\u3089\u9045\u3044\u3051\u3069\u30b7\u30f3\u30d7\u30eb\u306a\u306e\u3067\uff09\n",
      "groups = map(lambda x: merged_stations[merged_stations['station_g_cd'] == x],  merged_stations['station_g_cd'].unique())\n",
      "\n",
      "# \u62bd\u51fa\u306e\u305f\u3081\u306e\u30e6\u30fc\u30c6\u30a3\u30ea\u30c6\u30a3\u95a2\u6570\n",
      "def add_cl(df, edges):\n",
      "    group_members = df['station_cd']\n",
      "    processed = set([])\n",
      "    map(lambda station_id: add_edge(station_id, group_members, edges, processed), group_members)\n",
      "\n",
      "def add_edge(current_station, stations, edges, processed):\n",
      "    for station in stations:\n",
      "        if station != current_station and station not in processed:\n",
      "            edges.append([station, 0, current_station])\n",
      "    processed.add(current_station)\n",
      "\n",
      "# \u65b0\u3057\u3044\u30a8\u30c3\u30b8\u3092\u5165\u308c\u308b\u5165\u308c\u7269\n",
      "group_edges = []\n",
      "map(lambda df: add_cl(df, group_edges) if len(df) != 1 else None, groups)\n",
      "\n",
      "#  \u6700\u7d42\u7684\u306b\u306f\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u306b\n",
      "cliques_df = pd.DataFrame(group_edges, columns=['station_cd1', 'line_cd', 'station_cd2'])\n",
      "\n",
      "# \u30af\u30ea\u30fc\u30af\u306e\u307f\u3092SIF\u5f62\u5f0f\u306e\u30c6\u30fc\u30d6\u30eb\u3068\u3057\u3066\u66f8\u304d\u51fa\u3057\u3066\u307f\u307e\u3059\n",
      "cliques_df.to_csv('cliques.sif', sep=' ', index=False)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 10
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### \u3061\u3083\u3093\u3068\u3057\u305f\u7d50\u679c\u306b\u306a\u3063\u3066\u3044\u308b\u304b\u53ef\u8996\u5316\u3057\u3066\u78ba\u8a8d\u3059\u308b\n",
      "\u3053\u3053\u3067\u66f8\u304d\u3060\u3057\u305f\u30d5\u30a1\u30a4\u30eb\u306fCytoscape\u3067\u6a19\u6e96\u7684\u306b\u4f7f\u308f\u308c\u3066\u3044\u308b\u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u306a\u306e\u3067\u3001\u305d\u306e\u307e\u307e\u8aad\u307f\u8fbc\u3081\u307e\u3059\u3002\u53ef\u8996\u5316\u3059\u308b\u3068\u4ee5\u4e0b\u306e\u69d8\u306a\u611f\u3058\u306b\u3002\n",
      "\n",
      "![](http://cl.ly/X3m2/cliques.png)\n",
      "\n",
      "\n",
      "\u5927\u4e08\u592b\u306a\u3088\u3046\u3067\u3059\u306d\u3002\n",
      "\n",
      "\n",
      "### \u65e2\u5b58\u306e\u30b0\u30e9\u30d5\u306b\u30de\u30fc\u30b8\u3059\u308b\n",
      "\u3067\u306f\u3053\u308c\u3092\u4eca\u3042\u308b\u9244\u9053\u8def\u7dda\u56f3\u3068\u30de\u30fc\u30b8\u3057\u307e\u3057\u3087\u3046\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "merged_graph = pd.concat([graph_final_df, cliques_df])\n",
      "merged_graph.to_csv('graph_connected.csv')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 11
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### \u30b3\u30cd\u30af\u30b7\u30e7\u30f3\u306e\u78ba\u8a8d\n",
      "\u63a5\u7d9a\u306f\u3046\u307e\u304f\u884c\u3063\u305f\u3067\u3057\u3087\u3046\u304b\uff1f\u518d\u3073Cytoscape\u306b\u8aad\u307f\u8fbc\u307e\u305b\u3066\u8a66\u3057\u307e\u3059\u3002\n",
      "\n",
      "#### \u5143\u3005\u306e\u8def\u7dda\u56f3\u3000\uff08\u975e\u63a5\u7d9a\u72b6\u614b\uff09\n",
      "\n",
      "![](http://cl.ly/X3dp/disconnected.png)\n",
      "\n",
      "\n",
      "\u5730\u7406\u60c5\u5831\u306e\u30de\u30c3\u30d4\u30f3\u30b0\u3092\u9664\u53bb\u3057\u3066\u30ec\u30a4\u30a2\u30a6\u30c8\u3059\u308b\u3068\u3001\u5f53\u7136\u3001\u5206\u65ad\u3055\u308c\u305f\u5404\u8def\u7dda\u304c\u898b\u3048\u307e\u3059\u3002\u30ba\u30fc\u30e0\u30a4\u30f3\u3057\u3066\u307f\u307e\u3059:\n",
      "\n",
      "\n",
      "![](http://cl.ly/X3hR/disconnected_zoom.png)\n",
      "\n",
      "\n",
      "\n",
      "#### \u65b0\u3057\u3044\u30c7\u30fc\u30bf (\u30b0\u30eb\u30fc\u30d7\u60c5\u5831\u3092\u4f7f\u3063\u3066\u63a5\u7d9a\u6e08\u307f\uff09\n",
      "\n",
      "##### \u65e5\u672c\u5168\u56fd\u306e\u9244\u9053\u30b7\u30b9\u30c6\u30e0\u30b0\u30e9\u30d5\n",
      "\n",
      "\n",
      "![](http://cl.ly/X3gA/connected_view.png)\n",
      "\n",
      "\n",
      "##### \u518d\u3073\u6771\u4eac\u30e1\u30c8\u30ed\u306e\u30b5\u30d6\u30b0\u30e9\u30d5\n",
      "\n",
      "\n",
      "![](http://cl.ly/X3kp/metro2.png)\n",
      "\n",
      "\n",
      "\u4eca\u56de\u306f\u4f4d\u7f6e\u60c5\u5831\u3092\u5730\u7406\u7684\u306a\u4e8b\u5b9f\u306b\u95a2\u4fc2\u306a\u304f\u30b0\u30e9\u30d5\u3068\u3057\u3066\u30ec\u30a4\u30a2\u30a6\u30c8\u3067\u304d\u3066\u3044\u307e\u3059\u3002\u5b9f\u969b\u306e\u8def\u7dda\u3068\u3001\u99c5\u306e\u30b0\u30eb\u30fc\u30d7\u3092\u7e4b\u3050\u30a8\u30c3\u30b8\u306f\u5b9f\u7dda\u3068\u7834\u7dda\u3067\u63cf\u304d\u5206\u3051\u3066\u3042\u308a\u307e\u3059\u3002"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## \u516c\u5171\u30c7\u30fc\u30bf\u306e\u6383\u9664\u3068\u30de\u30c3\u30d4\u30f3\u30b0\n",
      "\n",
      "\u4e57\u964d\u5ba2\u30c7\u30fc\u30bf\u306f\u3069\u3053\u304b\u306b\u306a\u3044\u304b\u3068\u63a2\u3057\u3066\u3044\u305f\u3068\u3053\u308d\u3001\u305d\u308c\u3089\u3057\u304d\u3082\u306e\u3092\u767a\u898b\u3057\u305f\u306e\u3067\u4f7f\u3063\u3066\u307f\u307e\u3059\u3002\n",
      "\n",
      "\u30bd\u30fc\u30b9\u306f\u3053\u3061\u3089\u3067\u3059: http://nlftp.mlit.go.jp/ksj/gml/datalist/KsjTmplt-S12.html\n",
      "\n",
      "\n",
      "\u8a73\u3057\u3044\u30b9\u30da\u30c3\u30af\u306f\u3053\u3061\u3089\n",
      "\n",
      "* http://nlftp.mlit.go.jp/ksj/gml/product_spec/KS-PS-S12-v2_0.pdf\n",
      "\n",
      "### \u6ce8\u610f\uff01\n",
      "\u3053\u306e\u30c7\u30fc\u30bf\u3001\u5b9f\u306f\u58ca\u308c\u305f\u72b6\u614b\u3067\u914d\u5e03\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u3053\u3093\u306a\u611f\u3058\u3067\u7c21\u5358\u306b\u4fee\u5fa9\u3067\u304d\u307e\u3059\u304c\u3002\n",
      "\n",
      "\n",
      "```\n",
      "cat S12-13.xml | sed -e \"s/ksj:ailroad/ksj:railroad/\" > fixed.xml\n",
      "```\n",
      "\n",
      "## XML\u30d5\u30a1\u30a4\u30eb\u3092\u51e6\u7406\u3059\u308b\n",
      "\u5fc5\u8981\u306a\u90e8\u5206\u3092\u62fe\u3044\u3060\u3057\u3066DataFrame\u306b\u3057\u307e\u3059\u3002\n",
      "\n",
      "(\u66ab\u5b9a\u7248\u3067\u3059\u3002\u5f8c\u307b\u3069\u6383\u9664\u3057\u307e\u3059\uff09\n"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import xml.etree.ElementTree as ET\n",
      "\n",
      "tree = ET.parse('fixed.xml')\n",
      "root = tree.getroot()\n",
      "PREFIX = '{http://nlftp.mlit.go.jp/ksj/schemas/ksj-app}'\n",
      "\n",
      "passenger_array = []\n",
      "entries = root.findall('./' + PREFIX + 'TheNumberofTheStationPassengersGettingonandoff')\n",
      "\n",
      "# \u30d5\u30a3\u30fc\u30eb\u30c9\u540d\u306e\u62bd\u51fa\n",
      "column_names = []\n",
      "for col in entries[0]:\n",
      "    column_names.append(col.tag.split('}')[1])\n",
      "\n",
      "# \u30c7\u30fc\u30bf\u3092\u62bd\u51fa\u3059\u308b\n",
      "for data in entries:\n",
      "    row=[]\n",
      "    for entry in data:\n",
      "        if(type(entry.text) is unicode):\n",
      "            row.append((entry.text).encode('utf-8'))\n",
      "        else:\n",
      "            row.append(entry.text)\n",
      "    passenger_array.append(row)\n",
      "\n",
      "# \u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u3078\n",
      "passenger_df = pd.DataFrame(passenger_array, columns=column_names)\n",
      "\n",
      "# \u30b9\u30da\u30c3\u30af\u30b7\u30fc\u30c8\u304b\u3089\u4eba\u529b\u3067\u4eba\u306e\u8aad\u3081\u308b\u30c6\u30fc\u30d6\u30eb\u306b\u3059\u308b\uff08\u30c0\u30e1\u30c0\u30e1\u306a\u3084\u308a\u65b9\u3067\u3059\u306d...\uff09\n",
      "railroad_division = [\n",
      "    ['\u666e\u901a\u9244\u9053 JR', '11'], \n",
      "    ['\u666e\u901a\u9244\u9053', '12'],  \n",
      "    ['\u92fc\u7d22\u9244\u9053', '13'], \n",
      "    ['\u61f8\u5782\u5f0f\u9244\u9053', '14'],\n",
      "    ['\u8de8\u5ea7\u5f0f\u9244\u9053', '15'], \n",
      "    ['\u6848\u5185\u8ecc\u6761\u5f0f\u9244\u9053','16'], \n",
      "    ['\u7121\u8ecc\u6761\u9244\u9053', '17'], \n",
      "    ['\u8ecc\u9053', '21'], \n",
      "    ['\u61f8\u5782\u5f0f\u30e2\u30ce\u30ec\u30fc\u30eb', '22'], \n",
      "    ['\u8de8\u5ea7\u5f0f\u30e2\u30ce\u30ec\u30fc\u30eb', '23'], \n",
      "    ['\u6848\u5185\u8ecc\u6761\u5f0f', '24'], \n",
      "    ['\u6d6e\u4e0a\u5f0f', '25']\n",
      "]\n",
      "\n",
      "railroad_company_classification = [\n",
      "    ['JR\u65b0\u5e79\u7dda', '1'], \n",
      "    ['JR\u5728\u6765\u7dda', '2'], \n",
      "    ['\u516c\u55b6\u9244\u9053', '3'], \n",
      "    ['\u6c11\u55b6\u9244\u9053', '4'], \n",
      "    ['\u7b2c\u4e09\u30bb\u30af\u30bf\u30fc', '5'] \n",
      "]\n",
      "\n",
      "rd_df = pd.DataFrame(railroad_division, columns=['rail_type', 'railroadDivision'])\n",
      "company_type_df = pd.DataFrame(railroad_company_classification, columns=['company_type', 'railroadCompanyClassification'])\n",
      "\n",
      "passenger_df.to_csv('passenger_original.csv')\n",
      "passenger_df.head()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>station</th>\n",
        "      <th>stationName</th>\n",
        "      <th>administrationCompany</th>\n",
        "      <th>routeName</th>\n",
        "      <th>railroadDivision</th>\n",
        "      <th>railroadCompanyClassification</th>\n",
        "      <th>duplicate2011</th>\n",
        "      <th>dataEorN2011</th>\n",
        "      <th>remarks2011</th>\n",
        "      <th>passengers2011</th>\n",
        "      <th>duplicate2012</th>\n",
        "      <th>dataEorN2012</th>\n",
        "      <th>remarks2012</th>\n",
        "      <th>passengers2012</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> None</td>\n",
        "      <td>      \u4e8c\u6708\u7530</td>\n",
        "      <td>    \u4e5d\u5dde\u65c5\u5ba2\u9244\u9053</td>\n",
        "      <td>      \u6307\u5bbf\u6795\u5d0e\u7dda</td>\n",
        "      <td> 11</td>\n",
        "      <td> 2</td>\n",
        "      <td> 1</td>\n",
        "      <td> 3</td>\n",
        "      <td> None</td>\n",
        "      <td>     0</td>\n",
        "      <td> 1</td>\n",
        "      <td> 3</td>\n",
        "      <td> None</td>\n",
        "      <td>     0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> None</td>\n",
        "      <td>       \u53e4\u5cf6</td>\n",
        "      <td> \u6c96\u7e04\u90fd\u5e02\u30e2\u30ce\u30ec\u30fc\u30eb</td>\n",
        "      <td> \u6c96\u7e04\u90fd\u5e02\u30e2\u30ce\u30ec\u30fc\u30eb\u7dda</td>\n",
        "      <td> 23</td>\n",
        "      <td> 5</td>\n",
        "      <td> 1</td>\n",
        "      <td> 1</td>\n",
        "      <td> None</td>\n",
        "      <td>  3907</td>\n",
        "      <td> 1</td>\n",
        "      <td> 1</td>\n",
        "      <td> None</td>\n",
        "      <td>  3980</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> None</td>\n",
        "      <td>  \u304a\u53f0\u5834\u6d77\u6d5c\u516c\u5712</td>\n",
        "      <td>     \u3086\u308a\u304b\u3082\u3081</td>\n",
        "      <td> \u6771\u4eac\u81e8\u6d77\u65b0\u4ea4\u901a\u81e8\u6d77\u7dda</td>\n",
        "      <td> 24</td>\n",
        "      <td> 5</td>\n",
        "      <td> 1</td>\n",
        "      <td> 1</td>\n",
        "      <td> None</td>\n",
        "      <td> 14612</td>\n",
        "      <td> 1</td>\n",
        "      <td> 1</td>\n",
        "      <td> None</td>\n",
        "      <td> 16130</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> None</td>\n",
        "      <td>    \u8239\u306e\u79d1\u5b66\u9928</td>\n",
        "      <td>     \u3086\u308a\u304b\u3082\u3081</td>\n",
        "      <td> \u6771\u4eac\u81e8\u6d77\u65b0\u4ea4\u901a\u81e8\u6d77\u7dda</td>\n",
        "      <td> 24</td>\n",
        "      <td> 5</td>\n",
        "      <td> 1</td>\n",
        "      <td> 1</td>\n",
        "      <td> None</td>\n",
        "      <td>  3767</td>\n",
        "      <td> 1</td>\n",
        "      <td> 1</td>\n",
        "      <td> None</td>\n",
        "      <td>  3235</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> None</td>\n",
        "      <td> \u30c6\u30ec\u30b3\u30e0\u30bb\u30f3\u30bf\u30fc</td>\n",
        "      <td>     \u3086\u308a\u304b\u3082\u3081</td>\n",
        "      <td> \u6771\u4eac\u81e8\u6d77\u65b0\u4ea4\u901a\u81e8\u6d77\u7dda</td>\n",
        "      <td> 24</td>\n",
        "      <td> 5</td>\n",
        "      <td> 1</td>\n",
        "      <td> 1</td>\n",
        "      <td> None</td>\n",
        "      <td> 12112</td>\n",
        "      <td> 1</td>\n",
        "      <td> 1</td>\n",
        "      <td> None</td>\n",
        "      <td> 12775</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>5 rows \u00d7 14 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 12,
       "text": [
        "  station stationName administrationCompany   routeName railroadDivision  \\\n",
        "0    None         \u4e8c\u6708\u7530                \u4e5d\u5dde\u65c5\u5ba2\u9244\u9053       \u6307\u5bbf\u6795\u5d0e\u7dda               11   \n",
        "1    None          \u53e4\u5cf6             \u6c96\u7e04\u90fd\u5e02\u30e2\u30ce\u30ec\u30fc\u30eb  \u6c96\u7e04\u90fd\u5e02\u30e2\u30ce\u30ec\u30fc\u30eb\u7dda               23   \n",
        "2    None     \u304a\u53f0\u5834\u6d77\u6d5c\u516c\u5712                 \u3086\u308a\u304b\u3082\u3081  \u6771\u4eac\u81e8\u6d77\u65b0\u4ea4\u901a\u81e8\u6d77\u7dda               24   \n",
        "3    None       \u8239\u306e\u79d1\u5b66\u9928                 \u3086\u308a\u304b\u3082\u3081  \u6771\u4eac\u81e8\u6d77\u65b0\u4ea4\u901a\u81e8\u6d77\u7dda               24   \n",
        "4    None    \u30c6\u30ec\u30b3\u30e0\u30bb\u30f3\u30bf\u30fc                 \u3086\u308a\u304b\u3082\u3081  \u6771\u4eac\u81e8\u6d77\u65b0\u4ea4\u901a\u81e8\u6d77\u7dda               24   \n",
        "\n",
        "  railroadCompanyClassification duplicate2011 dataEorN2011 remarks2011  \\\n",
        "0                             2             1            3        None   \n",
        "1                             5             1            1        None   \n",
        "2                             5             1            1        None   \n",
        "3                             5             1            1        None   \n",
        "4                             5             1            1        None   \n",
        "\n",
        "  passengers2011 duplicate2012 dataEorN2012 remarks2012 passengers2012  \n",
        "0              0             1            3        None              0  \n",
        "1           3907             1            1        None           3980  \n",
        "2          14612             1            1        None          16130  \n",
        "3           3767             1            1        None           3235  \n",
        "4          12112             1            1        None          12775  \n",
        "\n",
        "[5 rows x 14 columns]"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "\u4e57\u964d\u5ba2\u6570\u306a\u3069\u304c\u3061\u3083\u3093\u3068\u30c6\u30fc\u30d6\u30eb\u5316\u3055\u308c\u3066\u3044\u308b\u306e\u304c\u308f\u304b\u308a\u307e\u3059\u3002\u3061\u306a\u307f\u306b\u3053\u306e\u4e57\u964d\u5ba2\u6570\u306f\u3001\u4e00\u65e5\u3042\u305f\u308a\u306e\u5e73\u5747\u5024\u3060\u305d\u3046\u3067\u3059\u3002\n",
      "\n",
      "## \u30c7\u30fc\u30bf\u5185\u5bb9\u306e\u691c\u8a0e\n",
      "\u3055\u3066\u3001\u3053\u308c\u3067\u3068\u308a\u3042\u3048\u305a\u6a5f\u68b0\u306b\u8aad\u307f\u8fbc\u307e\u305b\u3084\u3059\u3044\u5f62\u5f0f\u306b\u306f\u306a\u308a\u307e\u3057\u305f\u304c\u3001\u3055\u3089\u306a\u308b\u5229\u7528\u3092\u3059\u308b\u305f\u3081\u306b\u3001\u3069\u306e\u3088\u3046\u306b\u4f7f\u3046\u304b\u3092\u691c\u8a0e\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002\u30c7\u30fc\u30bf\u306e\u69cb\u9020\u3092\u898b\u3066\u307f\u307e\u3057\u3087\u3046\u3002\n",
      "\n",
      "\n",
      "![](http://cl.ly/X4LZ/passengers_schema.png)\n",
      "\n",
      "\uff08[\u56fd\u571f\u4ea4\u901a\u7701\u306e\u30b5\u30a4\u30c8\u3088\u308a](http://nlftp.mlit.go.jp/ksj/gml/product_spec/KS-PS-S12-v2_0.pdf)\uff09\n",
      "\n",
      "\u3053\u3053\u3067\u6ce8\u76ee\u3059\u3079\u304d\u306f__\u91cd\u8907\u30b3\u30fc\u30c9__\u3068\u8a00\u3046\u9805\u76ee\u3067\u3059\u3002\u3069\u3046\u3084\u3089\u3001\u5fc5\u305a\u3057\u3082\u99c5\u3054\u3068\u306e\u30c7\u30fc\u30bf\u304c\u3068\u308c\u3066\u3044\u308b\u308f\u3051\u3067\u306f\u306a\u304f\u3001\u30c7\u30fc\u30bf\u306b\u3088\u3063\u3066\u306f\u4ed6\u306e\u99c5\u306e\u7d71\u8a08\u306b\u5408\u7b97\u3055\u308c\u3066\u3044\u305f\u308a\u3001\u6b20\u640d\u5024\u3082\u5b58\u5728\u3059\u308b\u3088\u3046\u3067\u3059\u3002\u66f4\u306b\u8abf\u3079\u308b\u3068\u3001\u4ed6\u306e\u99c5\u306b\u5408\u7b97\u3055\u308c\u3066\u3044\u308b\u5834\u5408\u3001\u5408\u7b97\u5148\u306e\u99c5\u306f\u5099\u8003\u6b04\u306bID\u3067\u6307\u5b9a\u3057\u3066\u3042\u308b\u308f\u3051\u3067\u306f\u306a\u304f\u3001\u4eba\u9593\u7528\u306e\u6587\u7ae0\u3067\u8a18\u8ff0\u3057\u3066\u3042\u308a\u307e\u3059\u3002\u5177\u4f53\u7684\u306b\u306f\u3001\u3053\u3093\u306a\u611f\u3058\u3067\u3059:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "remarks = pd.Series(passenger_df['remarks2011'].unique())\n",
      "remarks[:10]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 13,
       "text": [
        "0                 None\n",
        "1       \u6771\u65e5\u672c\u65c5\u5ba2\u9244\u9053\u3001\u82b1\u8f2a\u7dda\u3092\u542b\u3080\n",
        "2          \u9577\u91ce\u96fb\u9244\u3001\u5c4b\u4ee3\u7dda\u3092\u542b\u3080\n",
        "3       \u6771\u65e5\u672c\u65c5\u5ba2\u9244\u9053\u3001\u5c0f\u6d77\u7dda\u3092\u542b\u3080\n",
        "4          \u6771\u6b66\u9244\u9053\u3001\u6850\u751f\u7dda\u3092\u542b\u3080\n",
        "5    \u5929\u7adc\u6d5c\u540d\u6e56\u9244\u9053\u3001\u5929\u7adc\u6d5c\u540d\u6e56\u7dda\u3092\u542b\u3080\n",
        "6        \u6771\u4eac\u90fd\u30011\u53f7\u7dda\u6d45\u8349\u7dda\u3092\u542b\u3080\n",
        "7        \u829d\u5c71\u9244\u9053\u3001\u829d\u5c71\u9244\u9053\u7dda\u3092\u542b\u3080\n",
        "8        \u65b0\u4eac\u6210\u96fb\u9244\u3001\u65b0\u4eac\u6210\u7dda\u3092\u542b\u3080\n",
        "9          \u5317\u7dcf\u9244\u9053\u3001\u5317\u7dcf\u7dda\u3092\u542b\u3080\n",
        "dtype: object"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "\u3053\u308c\u3060\u3068\u3001\u6a5f\u68b0\u7684\u306b\u5408\u7b97\u5185\u5bb9\u3092\u628a\u63e1\u3059\u308b\u306e\u306f\u3068\u3066\u3082\u9762\u5012\u3067\u3059\u3002\u304b\u3068\u8a00\u3063\u3066\u3001\u73fe\u5728\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u5168\u90e8\u3092\u5358\u7d14\u306b\u99c5\u540d\u3067\u30de\u30c3\u30d4\u30f3\u30b0\u3057\u3066\u3082\u3001\u5408\u7b97\u306e\u65b9\u6cd5\u306a\u3069\u306b\u3088\u3063\u3066\u53ef\u8996\u5316\u306e\u7d50\u679c\u304c\u5de6\u53f3\u3055\u308c\u3066\u3057\u307e\u3044\u307e\u3059\u3002\n",
      "\n",
      "#### \u629c\u7c8b\u7248\u306e\u30c7\u30fc\u30bf\u3092\u4f5c\u308b\n",
      "\u3053\u306e\u3088\u3046\u306b\u5358\u7d14\u306a\u30de\u30c3\u30d4\u30f3\u30b0\u3067\u306f\u3046\u307e\u304f\u3044\u304d\u305d\u3046\u306b\u306a\u3044\u306e\u3067\u3001\u629c\u7c8b\u7248\u3092\u4f5c\u308a\u3001\u305d\u308c\u3067\u3069\u306e\u3088\u3046\u306a\u611f\u3058\u306b\u306a\u308b\u304b\u78ba\u304b\u3081\u308b\u3001\u3068\u8a00\u3046\u65b9\u91dd\u3067\u884c\u304d\u307e\u3059\u3002\u3064\u307e\u308a\u3001\u7c21\u5358\u306b\u6b63\u78ba\u306a\u30c7\u30fc\u30bf\u304c\u624b\u306b\u5165\u308b\u3082\u306e\u3060\u3051\u3092\u5229\u7528\u3057\u307e\u3059\u3002\u4f5c\u696d\u3068\u3057\u3066\u306f\u3001__dataEorN\u30ab\u30e9\u30e0\u306e\u307f\u3092\u5229\u7528\u3057\u30c7\u30fc\u30bf\u304c\u5b58\u5728\u3059\u308b\u3082\u306e\u3092\u53d6\u308a\u51fa\u3059__\u3068\u8a00\u3046\u5358\u7d14\u306a\u30d5\u30a3\u30eb\u30bf\u30ea\u30f3\u30b0\u3067\u3059\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "passenger_df['is_complete'] = passenger_df.apply(\n",
      "    lambda row:  True if row['dataEorN2011'] == '1' and  row['dataEorN2012'] == '1' and row['duplicate2011'] == '1' and row['duplicate2012'] == '1' and row['remarks2011'] == None  and row['remarks2012'] == None else False, axis=1)\n",
      "passenger_filtered = passenger_df[passenger_df['is_complete']]\n",
      "\n",
      "# \u8981\u3089\u306a\u304f\u306a\u3063\u305f\u60c5\u5831\u3092\u9664\u53bb\n",
      "passenger_filtered.drop(['is_complete', 'station', 'duplicate2011', 'duplicate2012', 'remarks2011', 'remarks2012', 'dataEorN2011', 'dataEorN2012'], axis=1, inplace=True)\n",
      "passenger_filtered.head()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stderr",
       "text": [
        "-c:6: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame\n"
       ]
      },
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>stationName</th>\n",
        "      <th>administrationCompany</th>\n",
        "      <th>routeName</th>\n",
        "      <th>railroadDivision</th>\n",
        "      <th>railroadCompanyClassification</th>\n",
        "      <th>passengers2011</th>\n",
        "      <th>passengers2012</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>       \u53e4\u5cf6</td>\n",
        "      <td> \u6c96\u7e04\u90fd\u5e02\u30e2\u30ce\u30ec\u30fc\u30eb</td>\n",
        "      <td> \u6c96\u7e04\u90fd\u5e02\u30e2\u30ce\u30ec\u30fc\u30eb\u7dda</td>\n",
        "      <td> 23</td>\n",
        "      <td> 5</td>\n",
        "      <td>  3907</td>\n",
        "      <td>  3980</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>  \u304a\u53f0\u5834\u6d77\u6d5c\u516c\u5712</td>\n",
        "      <td>     \u3086\u308a\u304b\u3082\u3081</td>\n",
        "      <td> \u6771\u4eac\u81e8\u6d77\u65b0\u4ea4\u901a\u81e8\u6d77\u7dda</td>\n",
        "      <td> 24</td>\n",
        "      <td> 5</td>\n",
        "      <td> 14612</td>\n",
        "      <td> 16130</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>    \u8239\u306e\u79d1\u5b66\u9928</td>\n",
        "      <td>     \u3086\u308a\u304b\u3082\u3081</td>\n",
        "      <td> \u6771\u4eac\u81e8\u6d77\u65b0\u4ea4\u901a\u81e8\u6d77\u7dda</td>\n",
        "      <td> 24</td>\n",
        "      <td> 5</td>\n",
        "      <td>  3767</td>\n",
        "      <td>  3235</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> \u30c6\u30ec\u30b3\u30e0\u30bb\u30f3\u30bf\u30fc</td>\n",
        "      <td>     \u3086\u308a\u304b\u3082\u3081</td>\n",
        "      <td> \u6771\u4eac\u81e8\u6d77\u65b0\u4ea4\u901a\u81e8\u6d77\u7dda</td>\n",
        "      <td> 24</td>\n",
        "      <td> 5</td>\n",
        "      <td> 12112</td>\n",
        "      <td> 12775</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td>       \u6c50\u7559</td>\n",
        "      <td>     \u3086\u308a\u304b\u3082\u3081</td>\n",
        "      <td> \u6771\u4eac\u81e8\u6d77\u65b0\u4ea4\u901a\u81e8\u6d77\u7dda</td>\n",
        "      <td> 24</td>\n",
        "      <td> 5</td>\n",
        "      <td>  6841</td>\n",
        "      <td>  7617</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>5 rows \u00d7 7 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 14,
       "text": [
        "  stationName administrationCompany   routeName railroadDivision  \\\n",
        "1          \u53e4\u5cf6             \u6c96\u7e04\u90fd\u5e02\u30e2\u30ce\u30ec\u30fc\u30eb  \u6c96\u7e04\u90fd\u5e02\u30e2\u30ce\u30ec\u30fc\u30eb\u7dda               23   \n",
        "2     \u304a\u53f0\u5834\u6d77\u6d5c\u516c\u5712                 \u3086\u308a\u304b\u3082\u3081  \u6771\u4eac\u81e8\u6d77\u65b0\u4ea4\u901a\u81e8\u6d77\u7dda               24   \n",
        "3       \u8239\u306e\u79d1\u5b66\u9928                 \u3086\u308a\u304b\u3082\u3081  \u6771\u4eac\u81e8\u6d77\u65b0\u4ea4\u901a\u81e8\u6d77\u7dda               24   \n",
        "4    \u30c6\u30ec\u30b3\u30e0\u30bb\u30f3\u30bf\u30fc                 \u3086\u308a\u304b\u3082\u3081  \u6771\u4eac\u81e8\u6d77\u65b0\u4ea4\u901a\u81e8\u6d77\u7dda               24   \n",
        "5          \u6c50\u7559                 \u3086\u308a\u304b\u3082\u3081  \u6771\u4eac\u81e8\u6d77\u65b0\u4ea4\u901a\u81e8\u6d77\u7dda               24   \n",
        "\n",
        "  railroadCompanyClassification passengers2011 passengers2012  \n",
        "1                             5           3907           3980  \n",
        "2                             5          14612          16130  \n",
        "3                             5           3767           3235  \n",
        "4                             5          12112          12775  \n",
        "5                             5           6841           7617  \n",
        "\n",
        "[5 rows x 7 columns]"
       ]
      }
     ],
     "prompt_number": 14
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### \u3055\u3089\u306a\u308b\u7d30\u304b\u306a\u8abf\u6574\n",
      "\n",
      "#### \u5404\u7a2e\u30b3\u30fc\u30c9\u3092\u4eba\u9593\u306e\u8aad\u3081\u308b\u6587\u5b57\u5217\u306b\u5909\u63db\n",
      "\u8def\u7dda\u306e\u7a2e\u5225\u306a\u3069\u304c\u6570\u5024\u3068\u3057\u3066\u4fdd\u5b58\u3057\u3066\u3042\u308b\u306e\u3067\u3001\u4eba\u9593\u304c\u8aad\u3081\u308b\u3082\u306e\u306b\u5909\u63db\u3057\u307e\u3059\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "temp_df = pd.merge(passenger_filtered, rd_df, on='railroadDivision')\n",
      "passenger_final_df = pd.merge(temp_df, company_type_df, on='railroadCompanyClassification')\n",
      "\n",
      "# \u5fc5\u8981\u306a\u304f\u306a\u3063\u305f\u30ab\u30e9\u30e0\u3092\u6d88\u53bb\n",
      "passenger_final_df.drop(['railroadDivision', 'railroadCompanyClassification'], axis=1, inplace=True)\n",
      "\n",
      "passenger_final_df.to_csv('passenger_final.csv')\n",
      "passenger_final_df[4000:4010]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>stationName</th>\n",
        "      <th>administrationCompany</th>\n",
        "      <th>routeName</th>\n",
        "      <th>passengers2011</th>\n",
        "      <th>passengers2012</th>\n",
        "      <th>rail_type</th>\n",
        "      <th>company_type</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>4000</th>\n",
        "      <td>    \u5357\u6804</td>\n",
        "      <td> \u8c4a\u6a4b\u9244\u9053</td>\n",
        "      <td> \u6e25\u7f8e\u7dda</td>\n",
        "      <td>  3435</td>\n",
        "      <td>  3422</td>\n",
        "      <td> \u666e\u901a\u9244\u9053</td>\n",
        "      <td> \u6c11\u55b6\u9244\u9053</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4001</th>\n",
        "      <td>    \u8001\u6d25</td>\n",
        "      <td> \u8c4a\u6a4b\u9244\u9053</td>\n",
        "      <td> \u6e25\u7f8e\u7dda</td>\n",
        "      <td>   747</td>\n",
        "      <td>   729</td>\n",
        "      <td> \u666e\u901a\u9244\u9053</td>\n",
        "      <td> \u6c11\u55b6\u9244\u9053</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4002</th>\n",
        "      <td> \u611b\u77e5\u5927\u5b66\u524d</td>\n",
        "      <td> \u8c4a\u6a4b\u9244\u9053</td>\n",
        "      <td> \u6e25\u7f8e\u7dda</td>\n",
        "      <td>  6391</td>\n",
        "      <td>  4281</td>\n",
        "      <td> \u666e\u901a\u9244\u9053</td>\n",
        "      <td> \u6c11\u55b6\u9244\u9053</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4003</th>\n",
        "      <td>  \u4e09\u6cb3\u7530\u539f</td>\n",
        "      <td> \u8c4a\u6a4b\u9244\u9053</td>\n",
        "      <td> \u6e25\u7f8e\u7dda</td>\n",
        "      <td>  2921</td>\n",
        "      <td>  3003</td>\n",
        "      <td> \u666e\u901a\u9244\u9053</td>\n",
        "      <td> \u6c11\u55b6\u9244\u9053</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4004</th>\n",
        "      <td>   \u5927\u6e05\u6c34</td>\n",
        "      <td> \u8c4a\u6a4b\u9244\u9053</td>\n",
        "      <td> \u6e25\u7f8e\u7dda</td>\n",
        "      <td>  2940</td>\n",
        "      <td>  3004</td>\n",
        "      <td> \u666e\u901a\u9244\u9053</td>\n",
        "      <td> \u6c11\u55b6\u9244\u9053</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4005</th>\n",
        "      <td>    \u9ad8\u5e2b</td>\n",
        "      <td> \u8c4a\u6a4b\u9244\u9053</td>\n",
        "      <td> \u6e25\u7f8e\u7dda</td>\n",
        "      <td>  2607</td>\n",
        "      <td>  2687</td>\n",
        "      <td> \u666e\u901a\u9244\u9053</td>\n",
        "      <td> \u6c11\u55b6\u9244\u9053</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4006</th>\n",
        "      <td>    \u82a6\u539f</td>\n",
        "      <td> \u8c4a\u6a4b\u9244\u9053</td>\n",
        "      <td> \u6e25\u7f8e\u7dda</td>\n",
        "      <td>   580</td>\n",
        "      <td>   621</td>\n",
        "      <td> \u666e\u901a\u9244\u9053</td>\n",
        "      <td> \u6c11\u55b6\u9244\u9053</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4007</th>\n",
        "      <td>   \u65b0\u8c4a\u6a4b</td>\n",
        "      <td> \u8c4a\u6a4b\u9244\u9053</td>\n",
        "      <td> \u6e25\u7f8e\u7dda</td>\n",
        "      <td> 18298</td>\n",
        "      <td> 16482</td>\n",
        "      <td> \u666e\u901a\u9244\u9053</td>\n",
        "      <td> \u6c11\u55b6\u9244\u9053</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4008</th>\n",
        "      <td>    \u8c4a\u5cf6</td>\n",
        "      <td> \u8c4a\u6a4b\u9244\u9053</td>\n",
        "      <td> \u6e25\u7f8e\u7dda</td>\n",
        "      <td>   471</td>\n",
        "      <td>   453</td>\n",
        "      <td> \u666e\u901a\u9244\u9053</td>\n",
        "      <td> \u6c11\u55b6\u9244\u9053</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4009</th>\n",
        "      <td>   \u56db\u5341\u4e07</td>\n",
        "      <td> \u5317\u9678\u9244\u9053</td>\n",
        "      <td> \u77f3\u5ddd\u7dda</td>\n",
        "      <td>   222</td>\n",
        "      <td>   225</td>\n",
        "      <td> \u666e\u901a\u9244\u9053</td>\n",
        "      <td> \u6c11\u55b6\u9244\u9053</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>10 rows \u00d7 7 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 15,
       "text": [
        "     stationName administrationCompany routeName passengers2011  \\\n",
        "4000          \u5357\u6804                  \u8c4a\u6a4b\u9244\u9053       \u6e25\u7f8e\u7dda           3435   \n",
        "4001          \u8001\u6d25                  \u8c4a\u6a4b\u9244\u9053       \u6e25\u7f8e\u7dda            747   \n",
        "4002       \u611b\u77e5\u5927\u5b66\u524d                  \u8c4a\u6a4b\u9244\u9053       \u6e25\u7f8e\u7dda           6391   \n",
        "4003        \u4e09\u6cb3\u7530\u539f                  \u8c4a\u6a4b\u9244\u9053       \u6e25\u7f8e\u7dda           2921   \n",
        "4004         \u5927\u6e05\u6c34                  \u8c4a\u6a4b\u9244\u9053       \u6e25\u7f8e\u7dda           2940   \n",
        "4005          \u9ad8\u5e2b                  \u8c4a\u6a4b\u9244\u9053       \u6e25\u7f8e\u7dda           2607   \n",
        "4006          \u82a6\u539f                  \u8c4a\u6a4b\u9244\u9053       \u6e25\u7f8e\u7dda            580   \n",
        "4007         \u65b0\u8c4a\u6a4b                  \u8c4a\u6a4b\u9244\u9053       \u6e25\u7f8e\u7dda          18298   \n",
        "4008          \u8c4a\u5cf6                  \u8c4a\u6a4b\u9244\u9053       \u6e25\u7f8e\u7dda            471   \n",
        "4009         \u56db\u5341\u4e07                  \u5317\u9678\u9244\u9053       \u77f3\u5ddd\u7dda            222   \n",
        "\n",
        "     passengers2012 rail_type company_type  \n",
        "4000           3422      \u666e\u901a\u9244\u9053         \u6c11\u55b6\u9244\u9053  \n",
        "4001            729      \u666e\u901a\u9244\u9053         \u6c11\u55b6\u9244\u9053  \n",
        "4002           4281      \u666e\u901a\u9244\u9053         \u6c11\u55b6\u9244\u9053  \n",
        "4003           3003      \u666e\u901a\u9244\u9053         \u6c11\u55b6\u9244\u9053  \n",
        "4004           3004      \u666e\u901a\u9244\u9053         \u6c11\u55b6\u9244\u9053  \n",
        "4005           2687      \u666e\u901a\u9244\u9053         \u6c11\u55b6\u9244\u9053  \n",
        "4006            621      \u666e\u901a\u9244\u9053         \u6c11\u55b6\u9244\u9053  \n",
        "4007          16482      \u666e\u901a\u9244\u9053         \u6c11\u55b6\u9244\u9053  \n",
        "4008            453      \u666e\u901a\u9244\u9053         \u6c11\u55b6\u9244\u9053  \n",
        "4009            225      \u666e\u901a\u9244\u9053         \u6c11\u55b6\u9244\u9053  \n",
        "\n",
        "[10 rows x 7 columns]"
       ]
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### \u7d50\u679c\u306e\u691c\u8a0e\n",
      "\u304b\u306a\u308a\u4eba\u9593\u306b\u8aad\u3081\u308b\u3088\u3046\u306b\u306a\u3063\u3066\u304d\u307e\u3057\u305f\u3002\u3067\u3082\u5fae\u5999\u306b\u6c17\u6301\u3061\u60aa\u3044\u5024\u304c\u5165\u3063\u3066\u3044\u307e\u3059\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "passenger_final_df[passenger_final_df['stationName'] == '\u5357\u963f\u8607\u767d\u5ddd\u6c34\u6e90']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>stationName</th>\n",
        "      <th>administrationCompany</th>\n",
        "      <th>routeName</th>\n",
        "      <th>passengers2011</th>\n",
        "      <th>passengers2012</th>\n",
        "      <th>rail_type</th>\n",
        "      <th>company_type</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>942</th>\n",
        "      <td> \u5357\u963f\u8607\u767d\u5ddd\u6c34\u6e90</td>\n",
        "      <td> \u5357\u963f\u8607\u9244\u9053</td>\n",
        "      <td> \u9ad8\u68ee\u7dda</td>\n",
        "      <td> 1</td>\n",
        "      <td> 24</td>\n",
        "      <td> \u666e\u901a\u9244\u9053</td>\n",
        "      <td> \u7b2c\u4e09\u30bb\u30af\u30bf\u30fc</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>1 rows \u00d7 7 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 16,
       "text": [
        "    stationName administrationCompany routeName passengers2011 passengers2012  \\\n",
        "942     \u5357\u963f\u8607\u767d\u5ddd\u6c34\u6e90                 \u5357\u963f\u8607\u9244\u9053       \u9ad8\u68ee\u7dda              1             24   \n",
        "\n",
        "    rail_type company_type  \n",
        "942      \u666e\u901a\u9244\u9053       \u7b2c\u4e09\u30bb\u30af\u30bf\u30fc  \n",
        "\n",
        "[1 rows x 7 columns]"
       ]
      }
     ],
     "prompt_number": 16
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "\u4e00\u65e5\u306e\u4e57\u964d\u5ba2\u304c\u4e00\u4eba\u3063\u3066\u3042\u308a\u3048\u308b\u306e\u3067\u3057\u3087\u3046\u304b\uff1f[\u99c5\u306e\u60c5\u5831](http://ja.wikipedia.org/wiki/%E5%8D%97%E9%98%BF%E8%98%87%E7%99%BD%E5%B7%9D%E6%B0%B4%E6%BA%90%E9%A7%85)\u3092\u898b\u3066\u307f\u307e\u3059\n",
      "\n",
      "![](http://upload.wikimedia.org/wikipedia/commons/e/e4/Minamiaso_Shirakawasuigen_Station01.jpg)\n",
      "\n",
      "> \u5357\u963f\u8607\u767d\u5ddd\u6c34\u6e90\u99c5\n",
      "> * 2011\u5e74\uff08\u5e73\u621023\u5e74\uff096\u6708 \u963f\u8607\u767d\u5ddd - \u898b\u6674\u53f0\u9593\u306b\u767d\u5ddd\u6c34\u6e90\u306e\u6700\u5bc4\u3068\u306a\u308b\u65b0\u99c5\u8a2d\u7f6e\u3092\u767a\u8868\u3002\n",
      "> * 2012\u5e74\uff08\u5e73\u621024\u5e74\uff093\u670817\u65e5 - \u958b\u696d\u3002\n",
      "> * 2012\u5e74\uff08\u5e73\u621024\u5e74\uff097\u670822\u65e5 - \u99c5\u820e\u5b8c\u6210[3]\u3002\n",
      "> * \u5099\u8003:\t\u7121\u4eba\u99c5\n",
      "\n",
      "\n",
      "\u958b\u696d\u524d\u306e\u30c7\u30fc\u30bf\u304c\u3042\u308b\u306e\u306f\u8b0e\u3067\u3059\u304c\u3001\u6570\u5b57\u7684\u306b\u306f\u3042\u308a\u3048\u305d\u3046\u3067\u3059(\u8a66\u9a13\u8d70\u884c\u6642\u306e\u7d71\u8a08\uff1f\uff09\u3002\u4eca\u56de\u306f\u305f\u307e\u305f\u307e\u3053\u3046\u3044\u3063\u305f\u5024\u3092\u767a\u898b\u3057\u307e\u3057\u305f\u304c\u3001\u5b9f\u969b\u306b\u306f\u76ee\u8996\u3067\u3053\u3046\u3044\u3063\u305f\u3053\u3068\u3092\u3059\u308b\u306e\u306f\u56f0\u96e3\u3067\u3059\u3002\u3060\u304b\u3089\u3053\u305d\u53ef\u8996\u5316\u3068\u3044\u3046\u624b\u6cd5\u304c\u751f\u304d\u3066\u304f\u308b\u306e\u3067\u3059\u304c\u3002\n",
      "\n",
      "\n",
      "#### \u306a\u305c\u308f\u3056\u308f\u3056\u4eba\u9593\u306e\u8aad\u3081\u308b\u975e\u52b9\u7387\u7684\u306a\u30c7\u30fc\u30bf\u306b\u5909\u63db\u3059\u308b\u306e\u304b\uff1f\n",
      "\u3053\u308c\u306f\u6a5f\u68b0\u306b\u3068\u3063\u3066\u306f\u30e1\u30ea\u30c3\u30c8\u304c\u306a\u3044\u306e\u3067\u3059\u304c\u3001\u53ef\u8996\u5316\u3092\u8003\u3048\u305f\u6642\u3001\u6570\u5b57\u306a\u3069\u306b\u30a8\u30f3\u30b3\u30fc\u30c9\u3055\u308c\u305f\u60c5\u5831\u306f\u76f4\u63a5\u30e9\u30d9\u30eb\u7b49\u3068\u3057\u3066\u4f7f\u7528\u3059\u308b\u306e\u306f\u4f7f\u3044\u52dd\u624b\u304c\u60aa\u3044\u306e\u3067\u3001\u30c7\u30fc\u30bf\u306e\u30b5\u30a4\u30ba\u304c\u5c0f\u3055\u3044\u5834\u5408\u306f\u3001\u52b9\u7387\u6027\u3088\u308a\u3082\u5b9f\u7528\u6027\u3092\u91cd\u8996\u3057\u3066\u3001\u3053\u306e\u3088\u3046\u306a\u5909\u63db\u3092\u4e88\u3081\u884c\u3063\u3066\u304a\u304f\u3053\u3068\u3067\u53ef\u8996\u5316\u306e\u6bb5\u968e\u3067\u306e\u8907\u96d1\u306a\u64cd\u4f5c\u3092\u907f\u3051\u308b\u4e8b\u304c\u51fa\u6765\u307e\u3059\u3002\n",
      "\n",
      "\n",
      "## \u5b9f\u969b\u306b\u30de\u30c3\u30d4\u30f3\u30b0\n",
      "\u6b32\u3057\u304b\u3063\u305f\u306e\u306f\u3001\u99c5\u540d\u3068\u4e57\u964d\u5ba2\u306e\u30b7\u30f3\u30d7\u30eb\u306a\u30c6\u30fc\u30d6\u30eb\u3067\u3057\u305f\u304c\u3001\u304b\u306a\u308a\u306e\u56de\u308a\u9053\u306b\u306a\u3063\u3066\u3057\u307e\u3044\u307e\u3057\u305f\u3002\u3053\u3053\u304b\u3089\u306f\u5b9f\u969b\u306b[Cytoscape](http://www.cytoscape.org/)\u3067\u53ef\u8996\u5316\u3057\u3066\u307f\u307e\u3057\u3087\u3046\u3002\n",
      "\n",
      "\n",
      "### \u6771\u4eac\u30e1\u30c8\u30ed\u3092\u984c\u6750\u3068\u3057\u305f\u30de\u30c3\u30d4\u30f3\u30b0\n",
      "\u3053\u3053\u3067[\u6771\u4eac\u30e1\u30c8\u30ed](http://www.tokyometro.jp/index.html)\u306e\u4e57\u964d\u5ba2\u3092\u8def\u7dda\u30b0\u30e9\u30d5\u4e0a\u3067\u8996\u899a\u7684\u306b\u628a\u63e1\u3057\u3066\u307f\u3088\u3046\u3068\u601d\u3044\u307e\u3059\u3002\u3068\u3053\u308d\u304c\u3001\u73fe\u6642\u70b9\u3067\u8def\u7dda\u540d\u306e\u30de\u30c3\u30d7\u306f\u884c\u3048\u307e\u305b\u3093\u3001\u306a\u305c\u306a\u3089\u3001\u4e00\u65b9\u306f\u300c__\u6771\u4eac\u30e1\u30c8\u30ed__\u300d\u3001\u3082\u3046\u4e00\u65b9\u306f\u300c__\u6771\u4eac\u5730\u4e0b\u9244__\u300d\u3068\u7570\u306a\u308b\u540d\u79f0\u3092\u4f7f\u3063\u3066\u3044\u308b\u304b\u3089\u3067\u3059\u3002\u3068\u3044\u3046\u8a33\u3067\u5207\u308a\u51fa\u3057\u3001\u5909\u63db\u3001\u30de\u30fc\u30b8\u3067\u3059\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "tokyo_metro = passenger_final_df[passenger_final_df['administrationCompany'] == '\u6771\u4eac\u5730\u4e0b\u9244']\n",
      "def create_line_name(company, line):\n",
      "    prefix = company.replace('\u5730\u4e0b\u9244',  '\u30e1\u30c8\u30ed')\n",
      "    suffix = line.split('\u7dda')[1]\n",
      "    return prefix + suffix + '\u7dda'\n",
      "    \n",
      "tokyo_metro['line_name'] = tokyo_metro.apply(lambda row:  create_line_name(row['administrationCompany'], row['routeName']), axis=1)\n",
      "tokyo_metro['station_name'] = tokyo_metro['stationName']\n",
      "\n",
      "merged = pd.merge(merged_stations, tokyo_metro, on=['station_name', 'line_name'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 17
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "#### \u30c7\u30fc\u30bf\u30bf\u30a4\u30d7\u306e\u5909\u66f4\n",
      "\n",
      "\u6570\u5b57\u3068\u3057\u3066\u6271\u308f\u306a\u3051\u308c\u3070\u3044\u3051\u306a\u3044\u3082\u306e\u3092\u6587\u5b57\u5217\u3068\u3057\u3066\u8aad\u307f\u8fbc\u3093\u3067\u3044\u308b\u306e\u3092\u5fd8\u308c\u3066\u3044\u307e\u3057\u305f\u3002\u5909\u63db\u3057\u307e\u3057\u3087\u3046\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "merged['passengers2012'] = merged['passengers2012'].astype(int)\n",
      "merged['passengers2011'] = merged['passengers2011'].astype(int)\n",
      "\n",
      "# \u4e57\u964d\u5ba2\u30c8\u30c3\u30d710\u306e\u99c5\u3092\u8868\u793a\u3057\u3066\u3001\u59a5\u5f53\u6027\u3092\u691c\u8a0e\u3059\u308b\n",
      "sorted_df = merged.sort_index(by='passengers2012', ascending=False)\n",
      "sorted_df[['station_name', 'line_name', 'passengers2012']][:10]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>station_name</th>\n",
        "      <th>line_name</th>\n",
        "      <th>passengers2012</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>57</th>\n",
        "      <td>   \u6c60\u888b</td>\n",
        "      <td> \u6771\u4eac\u30e1\u30c8\u30ed\u4e38\u30ce\u5185\u7dda</td>\n",
        "      <td> 483952</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>64</th>\n",
        "      <td>  \u5927\u624b\u753a</td>\n",
        "      <td> \u6771\u4eac\u30e1\u30c8\u30ed\u4e38\u30ce\u5185\u7dda</td>\n",
        "      <td> 277336</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>27</th>\n",
        "      <td>  \u897f\u8239\u6a4b</td>\n",
        "      <td>  \u6771\u4eac\u30e1\u30c8\u30ed\u6771\u897f\u7dda</td>\n",
        "      <td> 274785</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>90</th>\n",
        "      <td>   \u9280\u5ea7</td>\n",
        "      <td> \u6771\u4eac\u30e1\u30c8\u30ed\u65e5\u6bd4\u8c37\u7dda</td>\n",
        "      <td> 245548</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>56</th>\n",
        "      <td>   \u6e0b\u8c37</td>\n",
        "      <td>  \u6771\u4eac\u30e1\u30c8\u30ed\u9280\u5ea7\u7dda</td>\n",
        "      <td> 226644</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>50</th>\n",
        "      <td>   \u65b0\u6a4b</td>\n",
        "      <td>  \u6771\u4eac\u30e1\u30c8\u30ed\u9280\u5ea7\u7dda</td>\n",
        "      <td> 223335</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>69</th>\n",
        "      <td>   \u65b0\u5bbf</td>\n",
        "      <td> \u6771\u4eac\u30e1\u30c8\u30ed\u4e38\u30ce\u5185\u7dda</td>\n",
        "      <td> 220154</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>82</th>\n",
        "      <td>   \u4e0a\u91ce</td>\n",
        "      <td> \u6771\u4eac\u30e1\u30c8\u30ed\u65e5\u6bd4\u8c37\u7dda</td>\n",
        "      <td> 212509</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>29</th>\n",
        "      <td> \u9ad8\u7530\u99ac\u5834</td>\n",
        "      <td>  \u6771\u4eac\u30e1\u30c8\u30ed\u6771\u897f\u7dda</td>\n",
        "      <td> 186629</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>32</th>\n",
        "      <td>  \u98ef\u7530\u6a4b</td>\n",
        "      <td>  \u6771\u4eac\u30e1\u30c8\u30ed\u6771\u897f\u7dda</td>\n",
        "      <td> 169830</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>10 rows \u00d7 3 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 18,
       "text": [
        "   station_name  line_name  passengers2012\n",
        "57           \u6c60\u888b  \u6771\u4eac\u30e1\u30c8\u30ed\u4e38\u30ce\u5185\u7dda          483952\n",
        "64          \u5927\u624b\u753a  \u6771\u4eac\u30e1\u30c8\u30ed\u4e38\u30ce\u5185\u7dda          277336\n",
        "27          \u897f\u8239\u6a4b   \u6771\u4eac\u30e1\u30c8\u30ed\u6771\u897f\u7dda          274785\n",
        "90           \u9280\u5ea7  \u6771\u4eac\u30e1\u30c8\u30ed\u65e5\u6bd4\u8c37\u7dda          245548\n",
        "56           \u6e0b\u8c37   \u6771\u4eac\u30e1\u30c8\u30ed\u9280\u5ea7\u7dda          226644\n",
        "50           \u65b0\u6a4b   \u6771\u4eac\u30e1\u30c8\u30ed\u9280\u5ea7\u7dda          223335\n",
        "69           \u65b0\u5bbf  \u6771\u4eac\u30e1\u30c8\u30ed\u4e38\u30ce\u5185\u7dda          220154\n",
        "82           \u4e0a\u91ce  \u6771\u4eac\u30e1\u30c8\u30ed\u65e5\u6bd4\u8c37\u7dda          212509\n",
        "29         \u9ad8\u7530\u99ac\u5834   \u6771\u4eac\u30e1\u30c8\u30ed\u6771\u897f\u7dda          186629\n",
        "32          \u98ef\u7530\u6a4b   \u6771\u4eac\u30e1\u30c8\u30ed\u6771\u897f\u7dda          169830\n",
        "\n",
        "[10 rows x 3 columns]"
       ]
      }
     ],
     "prompt_number": 18
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "\u3060\u3044\u305f\u3044\u60f3\u50cf\u3068\u4e00\u81f4\u3057\u307e\u3059\u306d\u3002\u7121\u8ad6\u3001\u3053\u308c\u306f\u99c5\u3054\u3068\u306e\u30c7\u30fc\u30bf\u306e\u307f\u3092\u62bd\u51fa\u3057\u305f\u3082\u306e\u3067\u3059\u304b\u3089\u3001\u5de8\u5927\u99c5\u3068\u3057\u3066\u8907\u6570\u306e\u8def\u7dda\u3092\u5408\u7b97\u3057\u305f\u5834\u5408\u306f\u3001\u5f53\u7136\u65b0\u5bbf\u3068\u304b\u304c\u30c8\u30c3\u30d7\u306b\u6765\u308b\u3068\u601d\u3044\u307e\u3059\u304c\u3001\u5730\u4e0b\u9244\u306e\u3072\u3068\u99c5\u5f53\u305f\u308a\u3060\u3068\u3053\u3093\u306a\u611f\u3058\u3067\u9593\u9055\u3044\u306a\u3055\u305d\u3046\u3067\u3059\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# \u7d50\u679c\u306e\u66f8\u304d\u51fa\u3057\n",
      "merged.to_csv('metro_data_table.csv')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 19
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### \u30b9\u30af\u30ec\u30a4\u30d4\u30f3\u30b0: Web\u30da\u30fc\u30b8\u306e\u52a0\u5de5\u306b\u3088\u308b\u8def\u7dda\u3054\u3068\u306e\u8272\u30c7\u30fc\u30bf\u62bd\u51fa\n",
      "\u305b\u3063\u304b\u304f\u306a\u306e\u3067\u3001\u3053\u306e\u30c7\u30fc\u30bf\u306b\u3082\u3046\u4e00\u4ed5\u4e8b\u3057\u3066\u307f\u307e\u3057\u3087\u3046\u3002\u8def\u7dda\u3054\u3068\u306e\u8272\u306f\u30e9\u30a4\u30f3\u30ab\u30e9\u30fc\u3068\u547c\u3070\u308c\u3066\u3001\u99c5\u306b\u63b2\u793a\u3057\u3066\u3042\u308b\u8def\u7dda\u56f3\u306a\u3069\u3067\u304a\u99b4\u67d3\u307f\u3067\u3059\u306d\u3002\u6b8b\u5ff5\u306a\u304c\u3089\u6a5f\u68b0\u304c\u8aad\u307f\u3084\u3059\u3044\u3088\u3046\u306a\u30c7\u30fc\u30bf\u306f\u898b\u3064\u304b\u3089\u306a\u304b\u3063\u305f\u306e\u3067\u3059\u304c\u3001Wikipedia\u306b\u306f\u3061\u3083\u3093\u3068\u3042\u308a\u307e\u3057\u305f\u3002\n",
      "\n",
      "* [\u65e5\u672c\u306e\u9244\u9053\u30e9\u30a4\u30f3\u30ab\u30e9\u30fc\u4e00\u89a7](http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E9%89%84%E9%81%93%E3%83%A9%E3%82%A4%E3%83%B3%E3%82%AB%E3%83%A9%E3%83%BC%E4%B8%80%E8%A6%A7)\n",
      "\n",
      "\u3053\u308c\u3092Cytoscape\u3067\u4f7f\u3048\u308b\u5f62\u306b\u52a0\u5de5\u3057\u307e\u3057\u3087\u3046\u3002\u3053\u306e\u4f5c\u696d\u306f_\u30b9\u30af\u30ec\u30a4\u30d4\u30f3\u30b0_\u3068\u547c\u3070\u308c\u3001\u3067\u304d\u308c\u3070\u907f\u3051\u305f\u3044\u30a4\u30e4\u306a\u4f5c\u696d\u306a\u306e\u3067\u3059\u304c\u3001[\u6a5f\u68b0\u304c\u7406\u89e3\u3067\u304d\u308bWeb](http://ja.wikipedia.org/wiki/%E3%82%BB%E3%83%9E%E3%83%B3%E3%83%86%E3%82%A3%E3%83%83%E3%82%AF%E3%83%BB%E3%82%A6%E3%82%A7%E3%83%96)\u304c\u3082\u3063\u3068\u5145\u5b9f\u3059\u308b\u307e\u3067\u3001\u4ed5\u65b9\u304c\u306a\u3044\u30aa\u30fc\u30d0\u30fc\u30d8\u30c3\u30c9\u3060\u3068\u601d\u3063\u3066\u8ae6\u3081\u307e\u3057\u3087\u3046\u3002\n",
      "\n",
      "\u4ee5\u4e0b\u3001\u6b63\u78ba\u3055\u306b\u3082\u6b20\u3051\u308b\u9069\u5f53\u306a\u51e6\u7406\u3067\u3059\u304c\u3001\u3068\u308a\u3042\u3048\u305a\u5927\u65b9\u306e\u60c5\u5831\u306f\u62fe\u3048\u307e\u3059\u3002\u8def\u7dda\u540d\u304b\u3089RGB\u306e\u6587\u5b57\u5217\u3078\u5909\u63db\u3057\u307e\u3059\u3002"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from lxml.html import parse\n",
      "from urllib2 import urlopen\n",
      "\n",
      "page = parse(urlopen('http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E9%89%84%E9%81%93%E3%83%A9%E3%82%A4%E3%83%B3%E3%82%AB%E3%83%A9%E3%83%BC%E4%B8%80%E8%A6%A7'))\n",
      "doc = page.getroot()\n",
      "table_rows = doc.findall('.//tr')\n",
      "\n",
      "color_list = []\n",
      "for row in table_rows:\n",
      "    line_name = None\n",
      "    line_color = None\n",
      "    \n",
      "    row_data = row.findall('.//%s' % 'td')\n",
      "    for val in row_data:\n",
      "        style = val.get('style')\n",
      "        for child in val:\n",
      "            if child.tag is 'a':\n",
      "                line_name = child.get('title')\n",
      "        if style is not None:\n",
      "            line_color = style\n",
      "    if line_name is not None and line_color is not None:\n",
      "        new_color = line_color.split(';')[0].replace('background:', '')\n",
      "        color_list.append([line_name.encode('utf-8'), new_color.encode('utf-8')])\n",
      "        \n",
      "# \u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u306b\u3002\u3000\n",
      "color_df = pd.DataFrame(color_list, columns=['line_name', 'line_color'])\n",
      "\n",
      "# CSV\u3068\u3057\u3066\u66f8\u304d\u51fa\u3057\n",
      "color_df.to_csv('line_colors.csv')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 20
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Cytoscape\u3067\u306e\u4f5c\u696d\n",
      "\u3067\u306f\u51fa\u6765\u4e0a\u304c\u3063\u305f\u30c7\u30fc\u30bf\u3092Cytoscape\u306b\u518d\u3073\u8aad\u307e\u305b\u307e\u3059\u3002\u8a73\u7d30\u306f\u8a18\u4e8b\u306e\u65b9\u306b\u3002\n",
      "\n",
      "![](http://cl.ly/X4Ih/tokyo_metro.png)\n",
      "\n",
      "![](http://cl.ly/X4Q9/tokyo_metro_geo.png)\n"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## \u307e\u3068\u3081\n",
      "\u3053\u306e\u3088\u3046\u306b\u3001\u5b9f\u969b\u306e\u30c7\u30fc\u30bf\u524d\u51e6\u7406\u306f\u3068\u3066\u3082\u5730\u9053\u3067\u3064\u307e\u3089\u306a\u3044\u4f5c\u696d\u304c\u591a\u3044\u306e\u3082\u4e8b\u5b9f\u3067\u3059\u3002\u914d\u5e03\u5143\u304c\u30b7\u30f3\u30d7\u30eb\u304b\u3064\u6b63\u78ba\u306b\u6a5f\u68b0\u53ef\u8aad\u306a\u30c7\u30fc\u30bf\u3092\u914d\u5e03\u3057\u3066\u304f\u308c\u308c\u3070\u307b\u3068\u3093\u3069\u306e\u554f\u984c\u306f\u89e3\u6c7a\u3059\u308b\u306e\u3067\u3059\u304c...\n",
      "\n",
      "\u611a\u75f4\u3092\u8a00\u3063\u3066\u3066\u3082\u59cb\u307e\u3089\u306a\u3044\u306e\u3067\u3001\u5728\u91ce\u306e\u500b\u4eba\u958b\u767a\u8005\u3084\u6c11\u9593\u4f01\u696d\u3067\u3082\u6c17\u8efd\u306b\u5229\u7528\u3067\u304d\u308b\u5f62\u3067\u306e\u30c7\u30fc\u30bf\u306e\u516c\u958b\u3078\u306e\u63d0\u8a00\u3092\u307e\u3068\u3081\u3066\u3001\u516c\u7684\u6a5f\u95a2\u306b\u50cd\u304d\u304b\u3051\u308b\u3068\u8a00\u3046\u6d3b\u52d5\u3082\u3042\u308a\u304b\u306a\u3001\u3068\u601d\u3044\u307e\u3059\u3002\u3053\u306e\u8a18\u4e8b\u3092\u304a\u8aad\u307f\u306e\u7686\u3055\u3093\u306e\u3088\u3046\u306b\u3001\u5b9f\u969b\u306b\u30c7\u30fc\u30bf\u3092\u4f7f\u3046\u4eba\u3005\u306e\u5177\u4f53\u7684\u6307\u6458\u304c\u3042\u3063\u305f\u307b\u3046\u304c\u3001\u516c\u958b\u3059\u308b\u5074\u3082\u3084\u308a\u3084\u3059\u3044\u3068\u601d\u3044\u307e\u3059\u306e\u3067\u3002\u3053\u3046\u3044\u3063\u305f\u8a71\u984c\u306b\u8208\u5473\u306e\u3042\u308b\u65b9\u306f\u3001\u305c\u3072\u4ee5\u4e0b\u306e\u30b0\u30eb\u30fc\u30d7\u306b\u53c2\u52a0\u3057\u3066\u307f\u3066\u304f\u3060\u3055\u3044\u3002\n",
      "\n",
      "* [Data Visualization Japan](https://www.facebook.com/groups/datavizjapan/) (Facebook\u30b0\u30eb\u30fc\u30d7\u3067\u3059)"
     ]
    }
   ],
   "metadata": {}
  }
 ]
}