shortest_path_estimation.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "f4fa3842",
   "metadata": {},
   "outputs": [],
   "source": [
    "import osmnx as ox\n",
    "import networkx as nx\n",
    "import numpy as np\n",
    "from geopy.geocoders import Nominatim\n",
    "import geopandas as gpd\n",
    "import plotly.express as px\n",
    "import pandas as pd\n",
    "import plotly.graph_objects as go\n",
    "import time\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "pio.renderers.default = \"svg\"\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "fea4df1d",
   "metadata": {},
   "outputs": [],
   "source": [
    "tsunami_shelter=pd.read_csv('Nakagawa Tsunami Shelter Coordinates.csv')\n",
    "flood_shelter=pd.read_csv('Nakagawa Flood Shelter Coordinates.csv')\n",
    "earthquake_shelter=pd.read_csv('Nakagawa Earthquake Shelter Coordinates.csv',encoding='utf-8')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "807d0909",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Nagoya - Nakagawa (Tsunami Shelters)</th>\n",
       "      <th>Shelter Name - English</th>\n",
       "      <th>Shelter Name - Japanese</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "      <th>Shelter Address</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Takahata 101 Building</td>\n",
       "      <td>高畑101ビル</td>\n",
       "      <td>35.140147</td>\n",
       "      <td>136.855157</td>\n",
       "      <td>2-101 Takabata, Nakagawa-ku, Nagoya-shi, Aichi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Inukai Building</td>\n",
       "      <td>イヌカイビル</td>\n",
       "      <td>35.140138</td>\n",
       "      <td>136.852472</td>\n",
       "      <td>3-13 Takabata, Nakagawa-ku, Nagoya-shi, Aichi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Takahata-so 1 Building</td>\n",
       "      <td>たかはた荘1棟</td>\n",
       "      <td>35.143891</td>\n",
       "      <td>136.855491</td>\n",
       "      <td>2-180 Kamitakabata, Nakagawa-ku, Nagoya City, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>2 Takahata-so</td>\n",
       "      <td>たかはた荘2棟</td>\n",
       "      <td>35.143923</td>\n",
       "      <td>136.854877</td>\n",
       "      <td>2-180 Kamitakabata, Nakagawa-ku, Nagoya City, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Takahataso 3 Buildings</td>\n",
       "      <td>たかはた荘3棟</td>\n",
       "      <td>35.143950</td>\n",
       "      <td>136.854334</td>\n",
       "      <td>2-180 Kamitakabata, Nakagawa-ku, Nagoya City, ...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Nagoya - Nakagawa (Tsunami Shelters)  Shelter Name - English  \\\n",
       "0                                     1   Takahata 101 Building   \n",
       "1                                     2         Inukai Building   \n",
       "2                                     3  Takahata-so 1 Building   \n",
       "3                                     4           2 Takahata-so   \n",
       "4                                     5  Takahataso 3 Buildings   \n",
       "\n",
       "  Shelter Name - Japanese   Latitude   Longitude  \\\n",
       "0                 高畑101ビル  35.140147  136.855157   \n",
       "1                  イヌカイビル  35.140138  136.852472   \n",
       "2                 たかはた荘1棟  35.143891  136.855491   \n",
       "3                 たかはた荘2棟  35.143923  136.854877   \n",
       "4                 たかはた荘3棟  35.143950  136.854334   \n",
       "\n",
       "                                     Shelter Address  \n",
       "0     2-101 Takabata, Nakagawa-ku, Nagoya-shi, Aichi  \n",
       "1      3-13 Takabata, Nakagawa-ku, Nagoya-shi, Aichi  \n",
       "2  2-180 Kamitakabata, Nakagawa-ku, Nagoya City, ...  \n",
       "3  2-180 Kamitakabata, Nakagawa-ku, Nagoya City, ...  \n",
       "4  2-180 Kamitakabata, Nakagawa-ku, Nagoya City, ...  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tsunami_shelter.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "5a4e14a3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Nagoya - Nakagawa (Flood Shelters)</th>\n",
       "      <th>Shelter Name - English</th>\n",
       "      <th>Shelter Name - Japanese</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "      <th>Shelter Address</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Noda Elementary School</td>\n",
       "      <td>野田小学校</td>\n",
       "      <td>35.142370</td>\n",
       "      <td>136.846750</td>\n",
       "      <td>1-545 Noda, Nakagawa-ku, Nagoya-shi, Aichi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Arako Elementary School</td>\n",
       "      <td>荒子小学校</td>\n",
       "      <td>35.134390</td>\n",
       "      <td>136.849858</td>\n",
       "      <td>4-234 Chugo, Nakagawa-ku, Nagoya-shi, Aichi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Ichiyanagi Junior High School</td>\n",
       "      <td>一柳中学校</td>\n",
       "      <td>35.134567</td>\n",
       "      <td>136.848922</td>\n",
       "      <td>4-235 Chugo, Nakagawa-ku, Nagoya-shi, Aichi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Joban Elementary School</td>\n",
       "      <td>常磐小学校</td>\n",
       "      <td>35.149165</td>\n",
       "      <td>136.862772</td>\n",
       "      <td>1-15-2 Komoto, Nakagawa-ku, Nagoya-shi, Aichi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Municipal West School for the Disabled</td>\n",
       "      <td>市立西養護学校</td>\n",
       "      <td>35.150469</td>\n",
       "      <td>138.861231</td>\n",
       "      <td>1-19-38 Komoto, Nakagawa-ku, Nagoya-shi, Aichi</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Nagoya - Nakagawa (Flood Shelters)                  Shelter Name - English  \\\n",
       "0                                   1                  Noda Elementary School   \n",
       "1                                   2                 Arako Elementary School   \n",
       "2                                   3           Ichiyanagi Junior High School   \n",
       "3                                   4                 Joban Elementary School   \n",
       "4                                   5  Municipal West School for the Disabled   \n",
       "\n",
       "  Shelter Name - Japanese  Latitude    Longitude  \\\n",
       "0                   野田小学校  35.142370  136.846750   \n",
       "1                   荒子小学校  35.134390  136.849858   \n",
       "2                   一柳中学校  35.134567  136.848922   \n",
       "3                   常磐小学校  35.149165  136.862772   \n",
       "4                 市立西養護学校  35.150469  138.861231   \n",
       "\n",
       "                                  Shelter Address  \n",
       "0      1-545 Noda, Nakagawa-ku, Nagoya-shi, Aichi  \n",
       "1     4-234 Chugo, Nakagawa-ku, Nagoya-shi, Aichi  \n",
       "2     4-235 Chugo, Nakagawa-ku, Nagoya-shi, Aichi  \n",
       "3   1-15-2 Komoto, Nakagawa-ku, Nagoya-shi, Aichi  \n",
       "4  1-19-38 Komoto, Nakagawa-ku, Nagoya-shi, Aichi  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "flood_shelter.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "dbb46165",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Nagoya - Nakagawa (Earthquake Shelters)</th>\n",
       "      <th>Shelter Name - English</th>\n",
       "      <th>Shelter Name - Japanese</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "      <th>Shelter Address</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Takabata Park</td>\n",
       "      <td>????</td>\n",
       "      <td>35.142280</td>\n",
       "      <td>136.850290</td>\n",
       "      <td>4-chome Takabata, Nakagawa-ku, Nagoya City, Ai...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Arako Park</td>\n",
       "      <td>????</td>\n",
       "      <td>35.138320</td>\n",
       "      <td>136.858460</td>\n",
       "      <td>2-chome Arako, Nakagawa-ku, Nagoya-shi, Aichi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Noda Elementary School</td>\n",
       "      <td>?????</td>\n",
       "      <td>35.142210</td>\n",
       "      <td>136.846754</td>\n",
       "      <td>1-545 Noda, Nakagawa-ku, Nagoya-shi, Aichi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Arako Elementary School</td>\n",
       "      <td>?????</td>\n",
       "      <td>35.134391</td>\n",
       "      <td>136.849858</td>\n",
       "      <td>4-234 Chugo, Nakagawa-ku, Nagoya-shi, Aichi</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Ichiyanagi Junior High School</td>\n",
       "      <td>?????</td>\n",
       "      <td>35.134567</td>\n",
       "      <td>136.848922</td>\n",
       "      <td>4-235 Chugo, Nakagawa-ku, Nagoya-shi, Aichi</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Nagoya - Nakagawa (Earthquake Shelters)         Shelter Name - English  \\\n",
       "0                                        1                  Takabata Park   \n",
       "1                                        2                     Arako Park   \n",
       "2                                        3         Noda Elementary School   \n",
       "3                                        4        Arako Elementary School   \n",
       "4                                        5  Ichiyanagi Junior High School   \n",
       "\n",
       "  Shelter Name - Japanese   Latitude   Longitude  \\\n",
       "0                    ????  35.142280  136.850290   \n",
       "1                    ????  35.138320  136.858460   \n",
       "2                   ?????  35.142210  136.846754   \n",
       "3                   ?????  35.134391  136.849858   \n",
       "4                   ?????  35.134567  136.848922   \n",
       "\n",
       "                                     Shelter Address  \n",
       "0  4-chome Takabata, Nakagawa-ku, Nagoya City, Ai...  \n",
       "1      2-chome Arako, Nakagawa-ku, Nagoya-shi, Aichi  \n",
       "2         1-545 Noda, Nakagawa-ku, Nagoya-shi, Aichi  \n",
       "3        4-234 Chugo, Nakagawa-ku, Nagoya-shi, Aichi  \n",
       "4        4-235 Chugo, Nakagawa-ku, Nagoya-shi, Aichi  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "earthquake_shelter.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "897aea4a",
   "metadata": {},
   "outputs": [],
   "source": [
    "G=nx.read_gpickle('data/combined_score_added.pickle')\n",
    "nodes,edges=ox.graph_to_gdfs(G)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "0b191f8f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>osmid</th>\n",
       "      <th>highway</th>\n",
       "      <th>oneway</th>\n",
       "      <th>length</th>\n",
       "      <th>bridge</th>\n",
       "      <th>lanes</th>\n",
       "      <th>ref</th>\n",
       "      <th>name</th>\n",
       "      <th>maxspeed</th>\n",
       "      <th>distance_risk_score</th>\n",
       "      <th>building_count</th>\n",
       "      <th>earthquake_risk</th>\n",
       "      <th>geometry</th>\n",
       "      <th>est_width</th>\n",
       "      <th>tunnel</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>u</th>\n",
       "      <th>v</th>\n",
       "      <th>key</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">287037206</th>\n",
       "      <th>6418759114</th>\n",
       "      <th>0</th>\n",
       "      <td>[235402848, 940877736]</td>\n",
       "      <td>motorway</td>\n",
       "      <td>True</td>\n",
       "      <td>549.217</td>\n",
       "      <td>['yes', 'viaduct']</td>\n",
       "      <td>2</td>\n",
       "      <td>['E23', '5']</td>\n",
       "      <td>['東名阪自動車道', '名古屋高速5号万場線']</td>\n",
       "      <td>60</td>\n",
       "      <td>8.0</td>\n",
       "      <td>215</td>\n",
       "      <td>6.5</td>\n",
       "      <td>LINESTRING (136.81737 35.15822, 136.81780 35.1...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8687399278</th>\n",
       "      <th>0</th>\n",
       "      <td>[937718833, 940585691, 766866772, 766866773]</td>\n",
       "      <td>motorway_link</td>\n",
       "      <td>True</td>\n",
       "      <td>717.481</td>\n",
       "      <td>yes</td>\n",
       "      <td>nan</td>\n",
       "      <td>nan</td>\n",
       "      <td>名古屋第二環状自動車道</td>\n",
       "      <td>60</td>\n",
       "      <td>6.0</td>\n",
       "      <td>215</td>\n",
       "      <td>6.5</td>\n",
       "      <td>LINESTRING (136.81737 35.15822, 136.81817 35.1...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8687399278</th>\n",
       "      <th>7162166992</th>\n",
       "      <th>0</th>\n",
       "      <td>766866776</td>\n",
       "      <td>motorway_link</td>\n",
       "      <td>True</td>\n",
       "      <td>211.954</td>\n",
       "      <td>yes</td>\n",
       "      <td>nan</td>\n",
       "      <td>nan</td>\n",
       "      <td>名古屋第二環状自動車道</td>\n",
       "      <td>60</td>\n",
       "      <td>8.0</td>\n",
       "      <td>467</td>\n",
       "      <td>6.5</td>\n",
       "      <td>LINESTRING (136.81880 35.15551, 136.81879 35.1...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                                  osmid  \\\n",
       "u          v          key                                                 \n",
       "287037206  6418759114 0                          [235402848, 940877736]   \n",
       "           8687399278 0    [937718833, 940585691, 766866772, 766866773]   \n",
       "8687399278 7162166992 0                                       766866776   \n",
       "\n",
       "                                 highway  oneway   length              bridge  \\\n",
       "u          v          key                                                       \n",
       "287037206  6418759114 0         motorway    True  549.217  ['yes', 'viaduct']   \n",
       "           8687399278 0    motorway_link    True  717.481                 yes   \n",
       "8687399278 7162166992 0    motorway_link    True  211.954                 yes   \n",
       "\n",
       "                          lanes           ref                       name  \\\n",
       "u          v          key                                                  \n",
       "287037206  6418759114 0       2  ['E23', '5']  ['東名阪自動車道', '名古屋高速5号万場線']   \n",
       "           8687399278 0     nan           nan                名古屋第二環状自動車道   \n",
       "8687399278 7162166992 0     nan           nan                名古屋第二環状自動車道   \n",
       "\n",
       "                           maxspeed  distance_risk_score  building_count  \\\n",
       "u          v          key                                                  \n",
       "287037206  6418759114 0          60                  8.0             215   \n",
       "           8687399278 0          60                  6.0             215   \n",
       "8687399278 7162166992 0          60                  8.0             467   \n",
       "\n",
       "                           earthquake_risk  \\\n",
       "u          v          key                    \n",
       "287037206  6418759114 0                6.5   \n",
       "           8687399278 0                6.5   \n",
       "8687399278 7162166992 0                6.5   \n",
       "\n",
       "                                                                    geometry  \\\n",
       "u          v          key                                                      \n",
       "287037206  6418759114 0    LINESTRING (136.81737 35.15822, 136.81780 35.1...   \n",
       "           8687399278 0    LINESTRING (136.81737 35.15822, 136.81817 35.1...   \n",
       "8687399278 7162166992 0    LINESTRING (136.81880 35.15551, 136.81879 35.1...   \n",
       "\n",
       "                          est_width tunnel  \n",
       "u          v          key                   \n",
       "287037206  6418759114 0         NaN    NaN  \n",
       "           8687399278 0         NaN    NaN  \n",
       "8687399278 7162166992 0         NaN    NaN  "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "edges.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "e7d4e3ac",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import MinMaxScaler\n",
    "\n",
    "scaler=MinMaxScaler()\n",
    "edges[['building_count']]=scaler.fit_transform(edges[['building_count']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "4c42eb3a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>osmid</th>\n",
       "      <th>highway</th>\n",
       "      <th>oneway</th>\n",
       "      <th>length</th>\n",
       "      <th>bridge</th>\n",
       "      <th>lanes</th>\n",
       "      <th>ref</th>\n",
       "      <th>name</th>\n",
       "      <th>maxspeed</th>\n",
       "      <th>distance_risk_score</th>\n",
       "      <th>building_count</th>\n",
       "      <th>earthquake_risk</th>\n",
       "      <th>geometry</th>\n",
       "      <th>est_width</th>\n",
       "      <th>tunnel</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>u</th>\n",
       "      <th>v</th>\n",
       "      <th>key</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">287037206</th>\n",
       "      <th>6418759114</th>\n",
       "      <th>0</th>\n",
       "      <td>[235402848, 940877736]</td>\n",
       "      <td>motorway</td>\n",
       "      <td>True</td>\n",
       "      <td>549.217</td>\n",
       "      <td>['yes', 'viaduct']</td>\n",
       "      <td>2</td>\n",
       "      <td>['E23', '5']</td>\n",
       "      <td>['東名阪自動車道', '名古屋高速5号万場線']</td>\n",
       "      <td>60</td>\n",
       "      <td>8.0</td>\n",
       "      <td>0.218716</td>\n",
       "      <td>6.5</td>\n",
       "      <td>LINESTRING (136.81737 35.15822, 136.81780 35.1...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8687399278</th>\n",
       "      <th>0</th>\n",
       "      <td>[937718833, 940585691, 766866772, 766866773]</td>\n",
       "      <td>motorway_link</td>\n",
       "      <td>True</td>\n",
       "      <td>717.481</td>\n",
       "      <td>yes</td>\n",
       "      <td>nan</td>\n",
       "      <td>nan</td>\n",
       "      <td>名古屋第二環状自動車道</td>\n",
       "      <td>60</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0.218716</td>\n",
       "      <td>6.5</td>\n",
       "      <td>LINESTRING (136.81737 35.15822, 136.81817 35.1...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                                 osmid  \\\n",
       "u         v          key                                                 \n",
       "287037206 6418759114 0                          [235402848, 940877736]   \n",
       "          8687399278 0    [937718833, 940585691, 766866772, 766866773]   \n",
       "\n",
       "                                highway  oneway   length              bridge  \\\n",
       "u         v          key                                                       \n",
       "287037206 6418759114 0         motorway    True  549.217  ['yes', 'viaduct']   \n",
       "          8687399278 0    motorway_link    True  717.481                 yes   \n",
       "\n",
       "                         lanes           ref                       name  \\\n",
       "u         v          key                                                  \n",
       "287037206 6418759114 0       2  ['E23', '5']  ['東名阪自動車道', '名古屋高速5号万場線']   \n",
       "          8687399278 0     nan           nan                名古屋第二環状自動車道   \n",
       "\n",
       "                          maxspeed  distance_risk_score  building_count  \\\n",
       "u         v          key                                                  \n",
       "287037206 6418759114 0          60                  8.0        0.218716   \n",
       "          8687399278 0          60                  6.0        0.218716   \n",
       "\n",
       "                          earthquake_risk  \\\n",
       "u         v          key                    \n",
       "287037206 6418759114 0                6.5   \n",
       "          8687399278 0                6.5   \n",
       "\n",
       "                                                                   geometry  \\\n",
       "u         v          key                                                      \n",
       "287037206 6418759114 0    LINESTRING (136.81737 35.15822, 136.81780 35.1...   \n",
       "          8687399278 0    LINESTRING (136.81737 35.15822, 136.81817 35.1...   \n",
       "\n",
       "                         est_width tunnel  \n",
       "u         v          key                   \n",
       "287037206 6418759114 0         NaN    NaN  \n",
       "          8687399278 0         NaN    NaN  "
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "edges.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "7e7f49a2",
   "metadata": {},
   "outputs": [],
   "source": [
    "edges['time_taken']=edges['length']/edges['maxspeed']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "270e9c1a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>osmid</th>\n",
       "      <th>highway</th>\n",
       "      <th>oneway</th>\n",
       "      <th>length</th>\n",
       "      <th>bridge</th>\n",
       "      <th>lanes</th>\n",
       "      <th>ref</th>\n",
       "      <th>name</th>\n",
       "      <th>maxspeed</th>\n",
       "      <th>distance_risk_score</th>\n",
       "      <th>building_count</th>\n",
       "      <th>earthquake_risk</th>\n",
       "      <th>geometry</th>\n",
       "      <th>est_width</th>\n",
       "      <th>tunnel</th>\n",
       "      <th>time_taken</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>u</th>\n",
       "      <th>v</th>\n",
       "      <th>key</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">287037206</th>\n",
       "      <th>6418759114</th>\n",
       "      <th>0</th>\n",
       "      <td>[235402848, 940877736]</td>\n",
       "      <td>motorway</td>\n",
       "      <td>True</td>\n",
       "      <td>549.217</td>\n",
       "      <td>['yes', 'viaduct']</td>\n",
       "      <td>2</td>\n",
       "      <td>['E23', '5']</td>\n",
       "      <td>['東名阪自動車道', '名古屋高速5号万場線']</td>\n",
       "      <td>60</td>\n",
       "      <td>8.0</td>\n",
       "      <td>0.218716</td>\n",
       "      <td>6.5</td>\n",
       "      <td>LINESTRING (136.81737 35.15822, 136.81780 35.1...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.153617</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8687399278</th>\n",
       "      <th>0</th>\n",
       "      <td>[937718833, 940585691, 766866772, 766866773]</td>\n",
       "      <td>motorway_link</td>\n",
       "      <td>True</td>\n",
       "      <td>717.481</td>\n",
       "      <td>yes</td>\n",
       "      <td>nan</td>\n",
       "      <td>nan</td>\n",
       "      <td>名古屋第二環状自動車道</td>\n",
       "      <td>60</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0.218716</td>\n",
       "      <td>6.5</td>\n",
       "      <td>LINESTRING (136.81737 35.15822, 136.81817 35.1...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11.958017</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                                 osmid  \\\n",
       "u         v          key                                                 \n",
       "287037206 6418759114 0                          [235402848, 940877736]   \n",
       "          8687399278 0    [937718833, 940585691, 766866772, 766866773]   \n",
       "\n",
       "                                highway  oneway   length              bridge  \\\n",
       "u         v          key                                                       \n",
       "287037206 6418759114 0         motorway    True  549.217  ['yes', 'viaduct']   \n",
       "          8687399278 0    motorway_link    True  717.481                 yes   \n",
       "\n",
       "                         lanes           ref                       name  \\\n",
       "u         v          key                                                  \n",
       "287037206 6418759114 0       2  ['E23', '5']  ['東名阪自動車道', '名古屋高速5号万場線']   \n",
       "          8687399278 0     nan           nan                名古屋第二環状自動車道   \n",
       "\n",
       "                          maxspeed  distance_risk_score  building_count  \\\n",
       "u         v          key                                                  \n",
       "287037206 6418759114 0          60                  8.0        0.218716   \n",
       "          8687399278 0          60                  6.0        0.218716   \n",
       "\n",
       "                          earthquake_risk  \\\n",
       "u         v          key                    \n",
       "287037206 6418759114 0                6.5   \n",
       "          8687399278 0                6.5   \n",
       "\n",
       "                                                                   geometry  \\\n",
       "u         v          key                                                      \n",
       "287037206 6418759114 0    LINESTRING (136.81737 35.15822, 136.81780 35.1...   \n",
       "          8687399278 0    LINESTRING (136.81737 35.15822, 136.81817 35.1...   \n",
       "\n",
       "                         est_width tunnel  time_taken  \n",
       "u         v          key                               \n",
       "287037206 6418759114 0         NaN    NaN    9.153617  \n",
       "          8687399278 0         NaN    NaN   11.958017  "
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "edges.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "d88818ed",
   "metadata": {},
   "outputs": [],
   "source": [
    "scaler=MinMaxScaler()\n",
    "edges[['distance_risk_score']]=scaler.fit_transform(edges[['distance_risk_score']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "efc5b1aa",
   "metadata": {},
   "outputs": [],
   "source": [
    "scaler=MinMaxScaler()\n",
    "edges[['earthquake_risk']]=scaler.fit_transform(edges[['earthquake_risk']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "6d3924bd",
   "metadata": {},
   "outputs": [],
   "source": [
    "edges['combined_risk']=edges['distance_risk_score']+edges['earthquake_risk']+edges['building_count']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "6f8e1be7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>osmid</th>\n",
       "      <th>highway</th>\n",
       "      <th>oneway</th>\n",
       "      <th>length</th>\n",
       "      <th>bridge</th>\n",
       "      <th>lanes</th>\n",
       "      <th>ref</th>\n",
       "      <th>name</th>\n",
       "      <th>maxspeed</th>\n",
       "      <th>distance_risk_score</th>\n",
       "      <th>building_count</th>\n",
       "      <th>earthquake_risk</th>\n",
       "      <th>geometry</th>\n",
       "      <th>est_width</th>\n",
       "      <th>tunnel</th>\n",
       "      <th>time_taken</th>\n",
       "      <th>combined_risk</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>u</th>\n",
       "      <th>v</th>\n",
       "      <th>key</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">287037206</th>\n",
       "      <th>6418759114</th>\n",
       "      <th>0</th>\n",
       "      <td>[235402848, 940877736]</td>\n",
       "      <td>motorway</td>\n",
       "      <td>True</td>\n",
       "      <td>549.217</td>\n",
       "      <td>['yes', 'viaduct']</td>\n",
       "      <td>2</td>\n",
       "      <td>['E23', '5']</td>\n",
       "      <td>['東名阪自動車道', '名古屋高速5号万場線']</td>\n",
       "      <td>60</td>\n",
       "      <td>0.8</td>\n",
       "      <td>0.218716</td>\n",
       "      <td>0.75</td>\n",
       "      <td>LINESTRING (136.81737 35.15822, 136.81780 35.1...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.153617</td>\n",
       "      <td>1.768716</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8687399278</th>\n",
       "      <th>0</th>\n",
       "      <td>[937718833, 940585691, 766866772, 766866773]</td>\n",
       "      <td>motorway_link</td>\n",
       "      <td>True</td>\n",
       "      <td>717.481</td>\n",
       "      <td>yes</td>\n",
       "      <td>nan</td>\n",
       "      <td>nan</td>\n",
       "      <td>名古屋第二環状自動車道</td>\n",
       "      <td>60</td>\n",
       "      <td>0.6</td>\n",
       "      <td>0.218716</td>\n",
       "      <td>0.75</td>\n",
       "      <td>LINESTRING (136.81737 35.15822, 136.81817 35.1...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11.958017</td>\n",
       "      <td>1.568716</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                                 osmid  \\\n",
       "u         v          key                                                 \n",
       "287037206 6418759114 0                          [235402848, 940877736]   \n",
       "          8687399278 0    [937718833, 940585691, 766866772, 766866773]   \n",
       "\n",
       "                                highway  oneway   length              bridge  \\\n",
       "u         v          key                                                       \n",
       "287037206 6418759114 0         motorway    True  549.217  ['yes', 'viaduct']   \n",
       "          8687399278 0    motorway_link    True  717.481                 yes   \n",
       "\n",
       "                         lanes           ref                       name  \\\n",
       "u         v          key                                                  \n",
       "287037206 6418759114 0       2  ['E23', '5']  ['東名阪自動車道', '名古屋高速5号万場線']   \n",
       "          8687399278 0     nan           nan                名古屋第二環状自動車道   \n",
       "\n",
       "                          maxspeed  distance_risk_score  building_count  \\\n",
       "u         v          key                                                  \n",
       "287037206 6418759114 0          60                  0.8        0.218716   \n",
       "          8687399278 0          60                  0.6        0.218716   \n",
       "\n",
       "                          earthquake_risk  \\\n",
       "u         v          key                    \n",
       "287037206 6418759114 0               0.75   \n",
       "          8687399278 0               0.75   \n",
       "\n",
       "                                                                   geometry  \\\n",
       "u         v          key                                                      \n",
       "287037206 6418759114 0    LINESTRING (136.81737 35.15822, 136.81780 35.1...   \n",
       "          8687399278 0    LINESTRING (136.81737 35.15822, 136.81817 35.1...   \n",
       "\n",
       "                         est_width tunnel  time_taken  combined_risk  \n",
       "u         v          key                                              \n",
       "287037206 6418759114 0         NaN    NaN    9.153617       1.768716  \n",
       "          8687399278 0         NaN    NaN   11.958017       1.568716  "
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "edges.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "cf7e764f",
   "metadata": {},
   "outputs": [],
   "source": [
    "edges['combined_risk_and_length']=edges['combined_risk']*edges['length']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "beaf7aed",
   "metadata": {},
   "outputs": [],
   "source": [
    "edges['combined_risk_and_time']=edges['combined_risk']*edges['time_taken']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "027bba2f",
   "metadata": {},
   "outputs": [],
   "source": [
    "G=ox.graph_from_gdfs(nodes,edges)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "ee7183bf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Geographic 2D CRS: EPSG:4326>\n",
       "Name: WGS 84\n",
       "Axis Info [ellipsoidal]:\n",
       "- Lat[north]: Geodetic latitude (degree)\n",
       "- Lon[east]: Geodetic longitude (degree)\n",
       "Area of Use:\n",
       "- name: World.\n",
       "- bounds: (-180.0, -90.0, 180.0, 90.0)\n",
       "Datum: World Geodetic System 1984\n",
       "- Ellipsoid: WGS 84\n",
       "- Prime Meridian: Greenwich"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "edges.crs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "1b38edc5",
   "metadata": {},
   "outputs": [],
   "source": [
    "from math import radians, cos, sin, asin, sqrt\n",
    "\n",
    "def dist(a,b):\n",
    "    \"\"\"\n",
    "    Calculate the great circle distance in kilometers between two points \n",
    "    on the earth (specified in decimal degrees)\n",
    "    \"\"\"\n",
    "    # convert decimal degrees to radians \n",
    "    (lon2,lat1)=a\n",
    "    (lon2,lat2)=b\n",
    "    lon1, lat1, lon2, lat2 = map(radians, [lon1, lat1, lon2, lat2])\n",
    "\n",
    "    # haversine formula \n",
    "    dlon = lon2 - lon1 \n",
    "    dlat = lat2 - lat1 \n",
    "    a = sin(dlat/2)**2 + cos(lat1) * cos(lat2) * sin(dlon/2)**2\n",
    "    c = 2 * asin(sqrt(a)) \n",
    "    r = 6371 # Radius of earth in kilometers. Use 3956 for miles. Determines return value units.\n",
    "    return c * r"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "ab9c79f8",
   "metadata": {},
   "outputs": [],
   "source": [
    "def path_calculation(source,target,method,weight):\n",
    "    source_node = ox.get_nearest_node(G,source)\n",
    "    target_node = ox.get_nearest_node(G, target)\n",
    "    if method=='A star' and weight=='combined_risk':\n",
    "        start_time=time.time()\n",
    "        route=nx.astar_path(G,source_node,target_node,heuristic=None,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='A star' and weight=='length':\n",
    "        start_time=time.time()\n",
    "        route=nx.astar_path(G,source_node,target_node,heuristic=None,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='A star' and weight=='time':\n",
    "        start_time=time.time()\n",
    "        route=nx.astar_path(G,source_node,target_node,heuristic=None,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='A star' and weight=='combined_risk_and_length':\n",
    "        start_time=time.time()\n",
    "        route=nx.astar_path(G,source_node,target_node,heuristic=None,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='A star' and weight=='combined_risk_and_time':\n",
    "        start_time=time.time()\n",
    "        route=nx.astar_path(G,source_node,target_node,heuristic=None,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='A star heuristic' and weight=='combined_risk':\n",
    "        start_time=time.time()\n",
    "        route=nx.astar_path(G,source_node,target_node,heuristic=dist,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='A star heuristic' and weight=='length':\n",
    "        start_time=time.time()\n",
    "        route=nx.astar_path(G,source_node,target_node,heuristic=dist,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='A star heuristic' and weight=='time':\n",
    "        start_time=time.time()\n",
    "        route=nx.astar_path(G,source_node,target_node,heuristic=dist,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='A star heuristic' and weight=='combined_risk_and_length':\n",
    "        start_time=time.time()\n",
    "        route=nx.astar_path(G,source_node,target_node,heuristic=dist,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='A star heuristic' and weight=='combined_risk_and_time':\n",
    "        start_time=time.time()\n",
    "        route=nx.astar_path(G,source_node,target_node,heuristic=dist,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='dijkstra' and weight=='combined_risk':\n",
    "        start_time=time.time()\n",
    "        route=nx.dijkstra_path(G,source_node,target_node,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='dijkstra' and weight=='length':\n",
    "        start_time=time.time()\n",
    "        route=nx.dijkstra_path(G,source_node,target_node,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='dijkstra' and weight=='time':\n",
    "        start_time=time.time()\n",
    "        route=nx.dijkstra_path(G,source_node,target_node,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='dijkstra' and weight=='combined_risk_and_length':\n",
    "        start_time=time.time()\n",
    "        route=nx.dijkstra_path(G,source_node,target_node,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='dijkstra' and weight=='combined_risk_and_time':\n",
    "        start_time=time.time()\n",
    "        route=nx.dijkstra_path(G,source_node,target_node,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='bellman ford' and weight=='combined_risk':\n",
    "        start_time=time.time()\n",
    "        route=nx.bellman_ford_path(G,source_node,target_node,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='bellman ford' and weight=='length':\n",
    "        start_time=time.time()\n",
    "        route=nx.bellman_ford_path(G,source_node,target_node,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='bellman ford' and weight=='time':\n",
    "        start_time=time.time()\n",
    "        route=nx.bellman_ford_path(G,source_node,target_node,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    elif method=='bellman ford' and weight=='combined_risk_and_length':\n",
    "        start_time=time.time()\n",
    "        route=nx.bellman_ford_path(G,source_node,target_node,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    else :\n",
    "        start_time=time.time()\n",
    "        route=nx.bellman_ford_path(G,source_node,target_node,weight=weight)\n",
    "        algorithm_time=time.time()-start_time\n",
    "    return route,algorithm_time"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "1724f05a",
   "metadata": {},
   "outputs": [],
   "source": [
    "source=(136.809525,35.136420)\n",
    "target=(earthquake_shelter.iloc[0].Longitude,earthquake_shelter.iloc[0].Latitude)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "af80de9e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(136.85029, 35.14228)"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "13c4c9e1",
   "metadata": {},
   "outputs": [],
   "source": [
    "source_node = ox.get_nearest_node(G,source)\n",
    "target_node = ox.get_nearest_node(G,target)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "571401ae",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "660711497"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "source_node"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "2af3cc1e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "660711497"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "target_node"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "b0bea52b",
   "metadata": {},
   "outputs": [],
   "source": [
    "route,algorithm_time=path_calculation(source=source,target=target,method='A star',weight='length')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "60e0043a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(<Figure size 576x576 with 1 Axes>, <AxesSubplot:>)"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ox.plot_graph_route(G,route)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "99aa2a8d",
   "metadata": {},
   "outputs": [],
   "source": [
    "ox.plot_graph_route?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fea62708",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}