{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Session 2: Vector Data Analysis and Map Projection\n",
    "*Written by Men Vuthy, 2021*"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Overview:\n",
    "\n",
    "In this session, we will learn about reading and exporting spatial data `Shapefile` and how to deal with map projections in Python by using `Geopandas` and `pyproj` modules and some useful data management functionalities.\n",
    "\n",
    "After this session, you will understand how to:\n",
    "\n",
    "* Read and write vector data\n",
    "* Create geometries into GeoDataFrame\n",
    "* Change the coordinate reference system of the data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Downloading data**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The data used in this session is *Provincial population census 2019 of Cambodia* which shows the total population, total population of males and females, total households, household size, density and areas by provinces in the Kingdom of Cambodia. This data is provided for free by [OpenDevelopementCambodia](https://opendevelopmentcambodia.net). Read more about this [dataset](https://data.opendevelopmentcambodia.net/dataset/population-census-2019-provisional-population-totals)\n",
    "\n",
    "Dataset: \n",
    "\n",
    "* [Shapefile](https://data.opendevelopmentmekong.net/dataset/2aaa4d7b-72b3-46d3-979e-8f30e4d801bd/resource/8d44398c-9d2c-4b8a-9194-b9d29774fc41/download/provisional_census2019.zip)\n",
    "* [GeoJSON](https://data.opendevelopmentmekong.net/dataset/2aaa4d7b-72b3-46d3-979e-8f30e4d801bd/resource/bba28f46-a5e8-498c-b465-de2163a8f5b9/download/provisional_census2019.geojson)\n",
    "           \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1. Introduction to Geopandas"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "`Geopandas` is a module to ease the work with geospatial data in Python easier. This module is extended from `pandas` module to allow spatial operations on geometric objects. In previous session, geometric operations are performed by `shapely`, but `Geopandas` further depends on `fiona` for file access and `matplotlib` for plotting. It actually combines the capabilities of `pandas` and `shapely`, providing geospatial operations in pandas and a high-level interface to multiple geometries to shapely. More details about `GeoPandas` is available [here](https://geopandas.org)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 1.a. Reading vector files"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The first step in analysis pipline is mostly reading the input data. The most common dataformats in GIS includes [Shapefile](https://en.wikipedia.org/wiki/Shapefile), [GeoJSON](https://en.wikipedia.org/wiki/GeoJSON), and [kml or kmz](https://en.wikipedia.org/wiki/Keyhole_Markup_Language). In this section, we will apply various functions from `Geopandas` to read these input files for analysis. The main fuction for reading input data is `gpd.read_file()`, let's see how to use it:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import necessary modules\n",
    "import geopandas as gpd"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Reading a shapefile**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Set filepath\n",
    "fp = \"data/provisional_census2019/provisional_census2019.shp\"\n",
    "\n",
    "# Read file using gpd.read_file()\n",
    "data = gpd.read_file(fp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>ogc_fid</th>\n",
       "      <th>pro_code</th>\n",
       "      <th>province_k</th>\n",
       "      <th>provinces</th>\n",
       "      <th>households</th>\n",
       "      <th>males</th>\n",
       "      <th>females</th>\n",
       "      <th>total</th>\n",
       "      <th>house_size</th>\n",
       "      <th>area_km2</th>\n",
       "      <th>pop_km2</th>\n",
       "      <th>reference</th>\n",
       "      <th>geometry</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>កំពង់ឆ្នាំង</td>\n",
       "      <td>Kampong Chhnang</td>\n",
       "      <td>122925.0</td>\n",
       "      <td>251895.0</td>\n",
       "      <td>274037.0</td>\n",
       "      <td>525932.0</td>\n",
       "      <td>4.3</td>\n",
       "      <td>5521</td>\n",
       "      <td>95</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>MULTIPOLYGON (((440280.561 1383585.909, 440090...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>កណ្តាល</td>\n",
       "      <td>Kandal</td>\n",
       "      <td>273111.0</td>\n",
       "      <td>580129.0</td>\n",
       "      <td>615418.0</td>\n",
       "      <td>1195547.0</td>\n",
       "      <td>4.4</td>\n",
       "      <td>3179</td>\n",
       "      <td>376</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>POLYGON ((481223.477 1313362.233, 481407.227 1...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>12</td>\n",
       "      <td>ភ្នំពេញ</td>\n",
       "      <td>Phnom Penh</td>\n",
       "      <td>399203.0</td>\n",
       "      <td>1039192.0</td>\n",
       "      <td>1090179.0</td>\n",
       "      <td>2129371.0</td>\n",
       "      <td>5.3</td>\n",
       "      <td>679</td>\n",
       "      <td>3136</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>POLYGON ((491536.140 1297379.094, 491748.953 1...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>14</td>\n",
       "      <td>ព្រៃវែង</td>\n",
       "      <td>Prey Veng</td>\n",
       "      <td>227008.0</td>\n",
       "      <td>501346.0</td>\n",
       "      <td>556082.0</td>\n",
       "      <td>1057428.0</td>\n",
       "      <td>4.7</td>\n",
       "      <td>4883</td>\n",
       "      <td>217</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>POLYGON ((536011.301 1311635.984, 536169.301 1...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>20</td>\n",
       "      <td>ស្វាយរៀង</td>\n",
       "      <td>Svay Rieng</td>\n",
       "      <td>131937.0</td>\n",
       "      <td>249446.0</td>\n",
       "      <td>275108.0</td>\n",
       "      <td>524554.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>2966</td>\n",
       "      <td>177</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>POLYGON ((587996.231 1282290.102, 588224.731 1...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ogc_fid  pro_code                         province_k        provinces  \\\n",
       "0        1         4  កំពង់ឆ្នាំង  Kampong Chhnang   \n",
       "1        2         8                 កណ្តាល           Kandal   \n",
       "2        3        12              ភ្នំពេញ       Phnom Penh   \n",
       "3        4        14              ព្រៃវែង        Prey Veng   \n",
       "4        5        20           ស្វាយរៀង       Svay Rieng   \n",
       "\n",
       "   households      males    females      total  house_size  area_km2  pop_km2  \\\n",
       "0    122925.0   251895.0   274037.0   525932.0         4.3      5521       95   \n",
       "1    273111.0   580129.0   615418.0  1195547.0         4.4      3179      376   \n",
       "2    399203.0  1039192.0  1090179.0  2129371.0         5.3       679     3136   \n",
       "3    227008.0   501346.0   556082.0  1057428.0         4.7      4883      217   \n",
       "4    131937.0   249446.0   275108.0   524554.0         4.0      2966      177   \n",
       "\n",
       "                                       reference  \\\n",
       "0  Provisional_Population_Census__00.06.2019.pdf   \n",
       "1  Provisional_Population_Census__00.06.2019.pdf   \n",
       "2  Provisional_Population_Census__00.06.2019.pdf   \n",
       "3  Provisional_Population_Census__00.06.2019.pdf   \n",
       "4  Provisional_Population_Census__00.06.2019.pdf   \n",
       "\n",
       "                                            geometry  \n",
       "0  MULTIPOLYGON (((440280.561 1383585.909, 440090...  \n",
       "1  POLYGON ((481223.477 1313362.233, 481407.227 1...  \n",
       "2  POLYGON ((491536.140 1297379.094, 491748.953 1...  \n",
       "3  POLYGON ((536011.301 1311635.984, 536169.301 1...  \n",
       "4  POLYGON ((587996.231 1282290.102, 588224.731 1...  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Reading a GeoJSON file**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Set filepath\n",
    "fp = \"data/provisional_census2019/provisional_census2019.geojson\"\n",
    "\n",
    "# Read file using gpd.read_file()\n",
    "data = gpd.read_file(fp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>ogc_fid</th>\n",
       "      <th>pro_code</th>\n",
       "      <th>province_k</th>\n",
       "      <th>provinces</th>\n",
       "      <th>households</th>\n",
       "      <th>males</th>\n",
       "      <th>females</th>\n",
       "      <th>total</th>\n",
       "      <th>house_size</th>\n",
       "      <th>area_km2</th>\n",
       "      <th>pop_km2</th>\n",
       "      <th>reference</th>\n",
       "      <th>geometry</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>កំពង់ឆ្នាំង</td>\n",
       "      <td>Kampong Chhnang</td>\n",
       "      <td>122925.0</td>\n",
       "      <td>251895.0</td>\n",
       "      <td>274037.0</td>\n",
       "      <td>525932.0</td>\n",
       "      <td>4.3</td>\n",
       "      <td>5521</td>\n",
       "      <td>95</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>MULTIPOLYGON (((440280.561 1383585.908, 440090...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>កណ្តាល</td>\n",
       "      <td>Kandal</td>\n",
       "      <td>273111.0</td>\n",
       "      <td>580129.0</td>\n",
       "      <td>615418.0</td>\n",
       "      <td>1195547.0</td>\n",
       "      <td>4.4</td>\n",
       "      <td>3179</td>\n",
       "      <td>376</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>MULTIPOLYGON (((481223.477 1313362.233, 481407...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>12</td>\n",
       "      <td>ភ្នំពេញ</td>\n",
       "      <td>Phnom Penh</td>\n",
       "      <td>399203.0</td>\n",
       "      <td>1039192.0</td>\n",
       "      <td>1090179.0</td>\n",
       "      <td>2129371.0</td>\n",
       "      <td>5.3</td>\n",
       "      <td>679</td>\n",
       "      <td>3136</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>MULTIPOLYGON (((491536.140 1297379.094, 491748...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ogc_fid  pro_code   province_k        provinces  households      males  \\\n",
       "0        1         4  កំពង់ឆ្នាំង  Kampong Chhnang    122925.0   251895.0   \n",
       "1        2         8       កណ្តាល           Kandal    273111.0   580129.0   \n",
       "2        3        12      ភ្នំពេញ       Phnom Penh    399203.0  1039192.0   \n",
       "\n",
       "     females      total  house_size  area_km2  pop_km2  \\\n",
       "0   274037.0   525932.0         4.3      5521       95   \n",
       "1   615418.0  1195547.0         4.4      3179      376   \n",
       "2  1090179.0  2129371.0         5.3       679     3136   \n",
       "\n",
       "                                       reference  \\\n",
       "0  Provisional_Population_Census__00.06.2019.pdf   \n",
       "1  Provisional_Population_Census__00.06.2019.pdf   \n",
       "2  Provisional_Population_Census__00.06.2019.pdf   \n",
       "\n",
       "                                            geometry  \n",
       "0  MULTIPOLYGON (((440280.561 1383585.908, 440090...  \n",
       "1  MULTIPOLYGON (((481223.477 1313362.233, 481407...  \n",
       "2  MULTIPOLYGON (((491536.140 1297379.094, 491748...  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We have read the input data with `Geopandas` fuction into variable `data`. Our data consists of multiple columns, but the most important is <span style=\"color:red\">'geometry'</span> column at the last. As we can see, the type of geometry in this <span style=\"color:green\">'geometry'</span> is MULTIPOLYGON."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "geopandas.geodataframe.GeoDataFrame"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check the type of data\n",
    "type(data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can see that the type of data is `geopandas.geodataframe`. As mentioned above, this type of data will allow us to handle spatial data easier by using similar approaches and datastructures in `Pandas`. Furthermore, we will be able to analyze features and operate functions in a way without the need of GIS application."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 1.b. Plotting vector files"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Besides reading in dataframe, you can also quickly plot the data based on its shapes or geometries by using `.plot()` fuction from geopandas because `Geopandas` provides a high-level interface to the `matplotlib` library for making maps. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "data.plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "***Plotting map of GeoPandas data (optional)***\n",
    "\n",
    "Read more about plotting [geopandas.GeoDataframe](https://geopandas.org/docs/user_guide/mapping.html)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# input data for plotting\n",
    "data.plot(column='total', legend=True, cmap='viridis')\n",
    "\n",
    "# set label x and y\n",
    "plt.xlabel('longitude')\n",
    "plt.ylabel('latitude')\n",
    "\n",
    "# Remove empty white space around the plot\n",
    "plt.tight_layout()\n",
    "\n",
    "# save figure (jpg, png, pdf, etc)\n",
    "plt.savefig('result/cambo_pop.png', dpi = 150)  # dpi is for setting image quality\n",
    "\n",
    "plt.show();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 1.c. Analyzing vector file"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "After importing input data, we can do some small analyses based on its attribute table. Now, let's see what we can do:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'init': 'epsg:32648'}"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check projection of data by using .crs\n",
    "data.crs "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['ogc_fid', 'pro_code', 'province_k', 'provinces', 'households',\n",
       "       'males', 'females', 'total', 'house_size', 'area_km2', 'pop_km2',\n",
       "       'reference', 'geometry'], dtype=object)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check all column names\n",
    "data.columns.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "25"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check the number of rows or length of data\n",
    "len(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>ogc_fid</th>\n",
       "      <th>pro_code</th>\n",
       "      <th>province_k</th>\n",
       "      <th>provinces</th>\n",
       "      <th>households</th>\n",
       "      <th>males</th>\n",
       "      <th>females</th>\n",
       "      <th>total</th>\n",
       "      <th>house_size</th>\n",
       "      <th>area_km2</th>\n",
       "      <th>pop_km2</th>\n",
       "      <th>reference</th>\n",
       "      <th>geometry</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>12</td>\n",
       "      <td>ភ្នំពេញ</td>\n",
       "      <td>Phnom Penh</td>\n",
       "      <td>399203.0</td>\n",
       "      <td>1039192.0</td>\n",
       "      <td>1090179.0</td>\n",
       "      <td>2129371.0</td>\n",
       "      <td>5.3</td>\n",
       "      <td>679</td>\n",
       "      <td>3136</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>MULTIPOLYGON (((491536.140 1297379.094, 491748...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ogc_fid  pro_code province_k   provinces  households      males    females  \\\n",
       "2        3        12    ភ្នំពេញ  Phnom Penh    399203.0  1039192.0  1090179.0   \n",
       "\n",
       "       total  house_size  area_km2  pop_km2  \\\n",
       "2  2129371.0         5.3       679     3136   \n",
       "\n",
       "                                       reference  \\\n",
       "2  Provisional_Population_Census__00.06.2019.pdf   \n",
       "\n",
       "                                            geometry  \n",
       "2  MULTIPOLYGON (((491536.140 1297379.094, 491748...  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Select Phnom Penh\n",
    "data.loc[data['province_k'] == 'ភ្នំពេញ'] # or data.loc[data['provinces'] == 'Phnom Penh']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "So let's check the shape of each multipolygon and the data type"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "shapely.geometry.multipolygon.MultiPolygon"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check the type of geometry\n",
    "type(data['geometry'][2])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/svg+xml": "<svg xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" width=\"300\" height=\"300\" viewBox=\"467199.72185599955 1261224.8215559996 39767.32648800011 37654.38648800063\" preserveAspectRatio=\"xMinYMin meet\"><g transform=\"matrix(1,0,0,-1,0,2560104.0296)\"><g><path fill-rule=\"evenodd\" fill=\"#66cc99\" stroke=\"#555555\" stroke-width=\"265.1155099200007\" opacity=\"0.6\" d=\"M 491536.14020000026,1297379.0938 L 491748.95270000026,1297372.3439 L 492136.3280999996,1297377.9689 L 492584.8284,1297360.5939 L 493076.6727999998,1297358.3438 L 493443.6107,1297338.5938 L 493797.7982999999,1297281.9684999995 L 494058.89219999965,1297192.4688 L 494238.3925999999,1297052.2185999993 L 494304.48610000033,1296913.4682999998 L 494389.48649999965,1296606.718 L 494466.7988,1296247.9677 L 494633.45529999956,1296018.7174999993 L 494784.8616000004,1295825.0922999997 L 495038.1118999999,1295560.0922999997 L 495217.51829999965,1295365.217 L 495370.23709999956,1295198.2168 L 495533.1747000003,1295046.5918 L 495599.08100000024,1294769.2162999995 L 495644.79980000015,1294634.3411999997 L 495775.5186999999,1294616.3412999995 L 496016.33139999956,1294608.2161999997 L 496322.1129,1294606.8412999995 L 496553.45689999964,1294596.0912999995 L 496525.2692999998,1294529.2160999998 L 496394.5504999999,1294218.466 L 496236.5504999999,1293758.4655 L 496110.30009999964,1293304.0900999997 L 495986.6436999999,1292847.2146 L 495876.1749,1292259.4640999995 L 495750.3936999999,1291863.4637 L 495623.1749999998,1291481.5885 L 495544.8622000003,1291152.4629999995 L 495507.2056999998,1291019.7131999992 L 495331.3398000002,1291005.6254999992 L 495242.4689999996,1290916.755 L 495040.04119999986,1290615.5823999997 L 494862.2993,1290190.9782999996 L 494738.8677000003,1289919.4291999992 L 494625.31070000026,1289608.3818999995 L 494250.0778999999,1288423.44 L 494107.7670999998,1288331.7106999997 L 493887.76680000033,1288032.4604 L 493652.3914999999,1287649.21 L 493452.4775,1287356.274 L 493193.65189999994,1287006.8598999996 L 493038.35610000044,1286644.5043 L 492870.119,1286075.0884 L 492794.44379999954,1285759.0396999996 L 492741.4600999998,1285369.2355 L 492725.89080000017,1284996.7074999996 L 492618.08050000016,1284795.7577999998 L 492675.64070000034,1284688.0823999997 L 492724.14070000034,1284463.8319 L 492765.60950000025,1284315.582 L 492872.07830000017,1283967.2065999992 L 492986.4846999999,1283597.8311 L 493031.7346999999,1283451.706 L 493184.4534,1282978.0806 L 493258.0162000004,1282761.9552999996 L 493379.23500000034,1282405.8299 L 493479.2973999996,1282156.7048 L 493501.92260000017,1282091.2047 L 493573.329,1281884.4546 L 493739.20409999974,1281472.0790999997 L 493832.0164999999,1281100.7037 L 493897.11039999966,1280708.5784 L 493971.5164999999,1280189.3278 L 494011.5480000004,1279655.2025 L 494097.9227999998,1278455.076199999 L 494104.20430000033,1278272.0759999994 L 494180.14190000016,1278118.5757999998 L 494213.92310000025,1278064.7007 L 494315.1107,1277969.8256 L 494397.0482999999,1277904.0755 L 494504.3607,1277848.7006 L 494600.23589999974,1277796.9505 L 494822.4360999996,1277647.5198 L 494889.2675,1277602.5753 L 495143.705,1277446.0749999993 L 495383.98670000024,1277313.7 L 495578.23699999973,1277209.2 L 495858.1590999998,1277091.401 L 496135.2686,1276958.1996999998 L 496443.89410000015,1276708.4493 L 496860.5192999998,1276526.3243 L 497385.26999999955,1276362.3241 L 497895.864,1276266.8237999994 L 498384.7708,1276196.823999999 L 498846.9276,1276127.9488999993 L 499175.4590999996,1276057.5735999998 L 499377.92819999997,1276021.1985999998 L 499530.6470999997,1276029.4487999994 L 499632.1470999997,1276051.5736999996 L 499848.14740000013,1276046.5737999994 L 500036.0850999998,1276064.1985999998 L 500227.7101999996,1276096.9486999996 L 500379.4913999997,1276099.9487999994 L 500519.9293,1276094.9488999993 L 500812.0856999997,1276104.1988999993 L 501040.77329999954,1276106.8237999994 L 501617.49289999995,1276119.0737999994 L 501882.1492999997,1276091.9487999994 L 502024.27440000046,1276085.9486999996 L 502128.4932000004,1276077.6986999996 L 502434.93120000046,1276038.9487999994 L 502928.3378999997,1275970.6986999996 L 503227.2131000003,1275919.1986999996 L 503563.0258999998,1275858.9485 L 504056.8075000001,1275729.9484 L 504555.80819999985,1275583.0733 L 504434.55790000036,1275473.1983 L 504264.9331,1275179.072899999 L 504059.55759999994,1274715.9474 L 503820.49509999994,1274355.4472 L 503373.36959999986,1273951.6966999993 L 503157.65050000045,1273713.1964999996 L 502955.52529999986,1273337.5709 L 502866.27529999986,1272998.195699999 L 502933.4940999998,1272624.1952 L 502998.9316999996,1272132.1947 L 503036.0256000003,1271893.819599999 L 503071.8691999996,1271659.3192999996 L 503079.2444000002,1271498.194 L 503096.1816999996,1271320.569 L 503085.7757000001,1271203.4437 L 503070.9628999997,1271001.1937 L 503070.1191999996,1270646.4431999996 L 503165.5569000002,1270296.318 L 503172.2757000001,1269947.9425 L 503196.7445,1269444.6919 L 505401.0904000001,1269390.6919999998 L 505494.1843999997,1269320.1920999996 L 505361.93400000036,1269222.4419999998 L 505172.4028000003,1269153.5667 L 504863.6524,1269097.5668 L 504610.9020999996,1269011.5665 L 504176.71410000045,1268798.0664 L 503751.9949000003,1268513.5660999995 L 503388.46329999994,1268185.0657 L 503142.7757000001,1267860.0655 L 503093.5569000002,1267529.0649999995 L 503143.71329999994,1267441.69 L 502920.7128999997,1267437.3147999998 L 502614.9625000004,1267475.4398999996 L 502305.61849999987,1267488.0650999993 L 501860.74289999995,1267494.5648999996 L 501491.7114000004,1267520.6898999996 L 501106.5235000001,1267509.9398999996 L 500761.83579999954,1267509.5649999995 L 500394.4601999996,1267491.19 L 500185.585,1267461.44 L 499937.6162999999,1267408.5648999996 L 499790.7410000004,1267394.5647999998 L 499685.6158999996,1267387.4397 L 499569.0219,1267386.4398999996 L 499361.7094999999,1267357.0648999996 L 499053.08380000014,1267289.4396 L 498639.0834999997,1267173.4396 L 498072.5515,1267134.8146 L 497630.4888000004,1267129.3147 L 497443.2112999996,1267114.7813 L 497342.41839999985,1267106.9594 L 497222.20139999967,1267144.4362 L 497117.9254999999,1267139.5647 L 496913.9254999999,1267173.1896 L 496724.6127000004,1267192.0647 L 496392.92480000015,1267295.8147 L 496090.36199999973,1267464.5649999995 L 495853.8618999999,1267625.5649999995 L 495705.01800000016,1267814.6901999991 L 495617.0804000003,1268040.6907 L 495352.36120000016,1268410.0658999998 L 495118.14240000024,1268799.6912999991 L 494899.17360000033,1269175.4418 L 494745.01690000016,1269522.0671999995 L 494626.6107999999,1269725.0672999993 L 494471.2357,1270043.6926 L 494355.36039999966,1270272.1928 L 494249.64159999974,1270489.3181 L 494194.89169999957,1270587.0681999996 L 492985.92140000034,1270130.8178 L 491425.66980000027,1269553.0672999993 L 491369.23220000044,1269191.4418 L 491352.41980000027,1269088.3167 L 491315.73220000044,1268949.8167 L 491285.41970000044,1268802.4415 L 491267.82579999976,1268660.1914 L 491262.10730000027,1268569.9411999993 L 491080.4820999997,1267571.4403 L 491187.91970000044,1267211.5648999996 L 491281.4820999997,1266879.6895 L 491376.66970000044,1266592.1890999991 L 491554.20749999955,1265994.2706 L 491575.29480000027,1265916.9385 L 491597.63879999984,1265416.5628999993 L 491566.95880000014,1265067.6053999998 L 491555.8713999996,1263393.5968999993 L 491494.37009999994,1263412.9256999996 L 491414.3816999998,1263423.8334 L 491243.4973,1263409.2901 L 491108.9715,1263416.562 L 491008.98599999957,1263403.8366 L 490913.4502999997,1263530.1859 L 490750.79389999993,1263556.686 L 490566.6063000001,1263555.1859 L 490462.2934999997,1263647.811 L 490519.29360000044,1263791.4364 L 490409.9500000002,1263870.0614 L 490160.7932000002,1264008.3114 L 489956.10560000036,1264118.5616999995 L 489712.13680000044,1264160.3115999997 L 489480.98000000045,1264141.0616999995 L 489249.82359999977,1264078.5616999995 L 489063.10479999986,1264079.6865999997 L 488886.4484000001,1264126.4366999995 L 488718.7604,1264133.9365999997 L 488518.16640000045,1264024.5616999995 L 488337.9475999996,1263894.8115999997 L 488120.9160000002,1263725.6864 L 487849.2906999998,1263550.1863 L 487700.6031999998,1263583.0612 L 487606.2906999998,1263819.1864999998 L 487473.9468,1263999.4364999998 L 487373.5092000002,1264073.0616999995 L 487212.04,1264179.5616999995 L 487083.6963999998,1264213.6868999992 L 486982.04,1264214.9368999992 L 486890.75850000046,1264075.0617999993 L 486817.2896999996,1263920.0614999998 L 486676.6332,1263629.0613 L 486532.1331000002,1263360.9361 L 486411.7580000004,1263118.3109 L 486314.1955000004,1262912.4355999995 L 486236.8515999997,1262781.5603999998 L 486193.7890999997,1262697.6854999997 L 486047.6014999999,1262769.9354999997 L 485872.1951000001,1262848.5604999997 L 485696.78839999996,1262906.8105999995 L 485560.78839999996,1262967.6856999993 L 485466.72589999996,1263013.3106999993 L 485365.03830000013,1263057.6859 L 485210.0067999996,1263114.6857999992 L 485154.1003,1263101.936 L 485071.6628,1263012.9357999992 L 484970.13150000013,1262921.4355999995 L 484864.7251000004,1262903.4356999993 L 484747.8499999996,1262883.0605999995 L 484660.25629999954,1262848.6856999993 L 484566.256,1262830.8105999995 L 484462.0684000002,1262845.9356999993 L 484317.1930999998,1262908.0607999992 L 484228.1308000004,1263013.4359 L 484178.38069999963,1263170.811 L 484131.19319999963,1263327.061 L 484060.0055999998,1263359.9363 L 483962.1616000002,1263381.4363 L 483923.94290000014,1263460.1864 L 483874.4116000002,1263568.1864999998 L 483495.6924,1263574.0614999998 L 482998.9731999999,1263572.3115999997 L 481645.97169999965,1263624.4367999993 L 481543.0653,1263631.9366999995 L 481451.44049999956,1263765.1868999992 L 481302.5028,1264006.4372 L 481181.5652,1264200.5622 L 481107.65890000015,1264375.8124 L 481106.19010000024,1264534.5627999995 L 480973.5959,1264605.2042999994 L 480881.2374,1264709.8774999995 L 480814.73929999955,1264824.4021 L 480764.25,1264943.8528 L 480690.36319999956,1264999.2682 L 480599.5334,1265087.0633 L 480408.36120000016,1265031.286 L 480320.9282999998,1264945.0845999997 L 480251.9671,1264846.5689 L 480149.7567999996,1264720.961 L 480061.09219999984,1264643.3798999991 L 479947.79899999965,1264586.7333 L 479866.5230999999,1264568.2617 L 479833.2740000002,1264507.9207 L 479877.6063000001,1264416.793299999 L 480048.7775999997,1264379.8497 L 480244.57799999975,1264349.0635 L 480283.9844000004,1264281.3336999994 L 480295.0673000002,1264180.354699999 L 480260.5865000002,1264062.1356 L 480192.85670000035,1263899.5844 L 480146.06149999984,1263797.3740999997 L 480006.90759999957,1263672.9979999997 L 479930.5580000002,1263621.2771 L 479795.0982999997,1263618.8143 L 479689.0321000004,1263612.187 L 479615.307,1263591.7226 L 479488.46740000043,1263562.168 L 479341.8443999998,1263532.6867999993 L 479243.4093000004,1263556.0109 L 479088.18769999966,1263616.4367999993 L 478946.0939999996,1263653.937 L 478800.18769999966,1263688.9371 L 478711.42349999957,1263708.711 L 478600.5931000002,1263804.7642 L 478484.8367999997,1263876.1882 L 478414.64439999964,1263930.3720999993 L 478343.2204,1263974.7041999996 L 478330.9057,1264083.0716999993 L 478291.4996999996,1264232.0770999994 L 478199.1409,1264355.2223 L 478126.4855000004,1264447.581 L 478067.3761,1264533.7824 L 477992.2578999996,1264612.5952 L 477920.7494,1264671.4383 L 477906.06180000026,1264749.8133 L 477931.9167999998,1264849.0335 L 478003.437,1264916.9383 L 478088.3113000002,1264975.8727 L 478114.8119,1265087.8136 L 478114.1716,1265172.9044 L 478030.43319999985,1265207.3850999996 L 477870.0931000002,1265181.6886999998 L 477791.5318999998,1265142.1184 L 477704.0990000004,1265062.0743 L 477628.9808,1265026.3624 L 477550.46750000026,1265020.8135 L 477438.6863000002,1265025.1885 L 477422.0974000003,1265115.0267999992 L 477461.50370000023,1265235.7089 L 477498.44739999995,1265340.3818999995 L 477446.7263000002,1265432.7408 L 477252.74870000035,1265437.4392 L 477206.59389999975,1265383.482999999 L 477143.7899000002,1265341.6138 L 477080.98599999957,1265281.2728 L 477005.8674999997,1265230.7835 L 476925.2171,1265228.3137999997 L 476864.2507999996,1265259.106899999 L 476790.36390000023,1265321.9109 L 476726.4042999996,1265351.1890999991 L 476631.5071,1265399.4923 L 476552.6942999996,1265416.7325999998 L 476480.0389,1265441.3616 L 476397.53199999966,1265478.3050999995 L 476355.0290999999,1265518.0644 L 476291.904,1265594.5645 L 476255.40390000027,1265663.3146 L 476250.8727000002,1265776.3146 L 476316.2564000003,1265879.7577 L 476434.47589999996,1265994.2825 L 476503.43680000026,1266074.3265 L 476565.0097000003,1266219.6373999994 L 476534.22339999955,1266303.376 L 476496.34169999976,1266347.8151999991 L 476390.1440000003,1266419.1323 L 476302.71109999996,1266409.2807999998 L 476239.90720000025,1266414.2064999994 L 476110.5081000002,1266408.945 L 475968.0911999997,1266387.1903 L 475861.5909000002,1266432.1904 L 475783.3409000002,1266531.5654 L 475765.7993,1266608.7761 L 475707.9212999996,1266616.1645999998 L 475606.9424,1266569.3698999994 L 475463.34049999993,1266558.5656 L 475377.1843999997,1266602.1905 L 475342.18099999987,1266734.3840999994 L 475354.4956,1266843.9832 L 475375.43039999995,1266983.1369 L 475424.6882999996,1267090.2729 L 475544.21580000035,1267237.4411999993 L 475711.6162,1267289.7674 L 475876.6305,1267351.3399 L 475895.1020999998,1267447.3927999996 L 475835.9927000003,1267552.0660999995 L 475714.07940000016,1267621.0274 L 475610.63769999985,1267596.3984999992 L 475512.1216000002,1267483.1051 L 475363.1161000002,1267368.5804999992 L 475263.1842,1267179.1910999995 L 475180.2778000003,1267109.8160999995 L 475064.4342,1267059.5661999993 L 474943.7153000003,1267052.5659999996 L 474824.9726,1267069.3387 L 474675.96750000026,1267183.8635 L 474572.52579999994,1267245.4362 L 474446.8711000001,1267278.4414 L 474298.08949999977,1267244.9414 L 474217.58939999994,1267155.0662999991 L 474285.59800000023,1267055.7931999993 L 474368.10479999986,1266943.7313 L 474423.5201000003,1266809.5033 L 474361.27699999977,1266668.0658999998 L 474269.5888,1266580.4539 L 474142.1205000002,1266537.0657 L 473856.37009999994,1266551.1908 L 473733.90830000024,1266659.2671 L 473640.3184000002,1266738.0799 L 473482.5262000002,1266733.3159999996 L 473347.30730000045,1266615.9408999998 L 473358.3164999997,1266468.3927999996 L 473554.1166000003,1266289.8323999997 L 473752.3799,1266166.6874 L 473848.43290000036,1266037.3852999993 L 473849.66420000046,1265901.9256999996 L 473754.84229999967,1265808.3355 L 473586.13379999995,1265798.4842 L 473294.0884999996,1265877.19 L 473209.98029999994,1265956.7476 L 473156.35830000043,1266054.626 L 473147.73819999956,1266230.7233 L 473177.29339999985,1266384.6544 L 473040.4006000003,1266461.3158999998 L 472910.0689000003,1266477.0132 L 472785.6924,1266404.3578999992 L 472690.87090000045,1266364.9516 L 472586.2438000003,1266327.5657 L 472510.9625000004,1266265.8155 L 472397.8373999996,1266249.8157 L 472326.7748999996,1266275.0657 L 472247.0560999997,1266289.9408 L 472186.3373999996,1266265.3155 L 472109.5246000001,1266256.8156 L 472128.9309,1266401.5658 L 472129.21219999995,1266517.3158 L 472158.46219999995,1266807.3162999991 L 472159.9934,1267075.4416 L 472149.24349999987,1267295.1918 L 472153.5247999998,1267539.3170999996 L 472169.3060999997,1267772.0673999991 L 472174.4935999997,1268056.6925 L 472174.8689000001,1268310.9429 L 472170.55649999995,1268520.568 L 472177.9001000002,1268848.5682999995 L 472326.7440999998,1268952.6933999993 L 472337.369,1269195.5687 L 472331.2441999996,1269480.6941 L 472556.5882000001,1269568.1941 L 472581.1195,1269648.0691999998 L 472575.33829999994,1269764.9442999996 L 472704.9633999998,1269777.0691999998 L 472728.6195,1269930.5693999995 L 472716.6195,1270077.9444999993 L 472787.7446999997,1270075.069599999 L 472910.90110000037,1270061.6947 L 473173.8699000003,1270060.4444999993 L 473483.7455000002,1270047.4444999993 L 473656.55790000036,1270059.3193999995 L 473677.2143000001,1270121.4443999995 L 473708.33939999994,1270252.0697 L 473704.9331,1270333.3197 L 473876.37069999985,1270324.9444999993 L 474119.1835000003,1270361.8198 L 474147.55869999994,1270445.444599999 L 474135.6211000001,1270597.9448 L 474134.9023000002,1270714.6951 L 474139.05869999994,1270782.0701 L 474162.2148000002,1270842.8202999998 L 474227.4650999997,1270933.9452999998 L 474313.21520000044,1271060.5703999996 L 474379.9650999997,1271203.6954999994 L 474477.1216000002,1271322.570699999 L 474559.99679999985,1271386.9455999993 L 474645.3716000002,1271437.320699999 L 474710.49679999985,1271509.3209 L 474721.93450000044,1271697.946 L 474749.27809999976,1271937.3211 L 474763.9656999996,1272170.3213999998 L 474766.0281999996,1272395.4466999993 L 474746.93450000044,1272678.6969 L 474751.8722,1272881.0721 L 474733.8722,1273084.3222 L 474720.1847,1273333.4475999996 L 474652.43460000027,1273366.8227999993 L 474489.40309999976,1273471.4475999996 L 474335.65309999976,1273548.322899999 L 474100.0279000001,1273751.1982 L 473949.4963999996,1273871.3231 L 473742.9024,1274091.1985999998 L 473581.08970000036,1274295.0737999994 L 473480.2149,1274508.6991 L 473392.46449999977,1274694.4493 L 473256.52699999977,1274676.0742 L 473051.8706,1274564.0741 L 472831.99540000036,1274446.698999999 L 472600.68259999994,1274329.1988999993 L 472434.4013,1274391.8241 L 472276.83860000037,1274444.4488999993 L 472194.1509999996,1274497.8241 L 472124.2134999996,1274574.1994 L 472100.05709999986,1274715.0743 L 472095.0258999998,1274836.9494 L 472061.9946999997,1275013.3247999996 L 472030.2134999996,1275117.4498999994 L 471976.2840999998,1275175.0705999993 L 471942.4634999996,1275291.45 L 472047.2758999998,1275507.5752 L 472025.4949000003,1275818.8255 L 471931.24480000045,1276026.4507999998 L 471771.21329999994,1276215.3259999994 L 471623.61930000037,1276339.2009999994 L 471492.18180000037,1276348.576199999 L 471346.5253999997,1276244.7010999992 L 471147.6501000002,1276107.8259999994 L 470974.4938000003,1276122.3257999998 L 470791.2125000004,1276125.4510999992 L 470611.8372999998,1276174.3260999992 L 470444.9305999996,1276163.4510999992 L 470331.1182000004,1276151.076199999 L 470334.1495000003,1276341.9513 L 470314.6807000004,1276625.7016 L 470272.3683000002,1276863.8267 L 470218.4620000003,1277039.5768999998 L 470154.6179999998,1277267.5770999994 L 470060.4304999998,1277508.4525 L 469967.3680999996,1277688.0776 L 469813.5866,1277845.0779 L 469673.49289999995,1277930.8279999997 L 469538.3990000002,1278004.9530999996 L 469401.0861999998,1278179.8281999994 L 469706.1805999996,1278341.7034 L 469797.5242999997,1278452.0784 L 469843.5554999998,1278646.7037 L 469803.3054999998,1278723.2038 L 469690.9303000001,1278775.7038 L 469614.0242999997,1278849.7038 L 469629.86789999995,1279106.7041999996 L 469626.4932000004,1279259.4542999994 L 469416.61760000046,1279253.7042999994 L 469187.7740000002,1279241.7041999996 L 468986.77359999996,1279247.4543999992 L 468833.8673,1279266.9543999992 L 468730.3985000001,1279341.0796 L 468672.58579999954,1279467.2047 L 468704.6173,1279623.7047 L 468847.6173999999,1279677.9547 L 469067.5861999998,1279678.5798 L 469236.9928000001,1279674.2048 L 469389.9304999998,1279663.5797 L 469533.8055999996,1279574.0795 L 469760.27440000046,1279527.8296 L 469824.3684,1279549.4545 L 469924.4308000002,1279570.3296 L 470023.30599999987,1279678.2045 L 470142.0247999998,1279605.9545 L 470271.8063000003,1279543.4545 L 470390.11870000046,1279515.3295 L 470441.4627,1279569.9542999994 L 470518.68149999995,1279662.3293999992 L 470572.1190999998,1279721.8296 L 470616.6815999998,1279768.7046 L 470689.21279999986,1279842.2045 L 470766.8691999996,1279951.2046 L 470813.9631000003,1280058.9549 L 470861.08800000045,1280175.5798 L 470889.1191999996,1280256.7049 L 470987.08829999994,1280269.2049 L 471073.61959999986,1280291.955 L 471036.7757000001,1280501.4551999997 L 470992.2757000001,1280615.7054999992 L 470928.68209999986,1280742.7054999992 L 470872.7445,1280837.9556 L 470826.96329999994,1280947.2057 L 470790.0882000001,1281056.4558 L 470751.9631000003,1281177.081 L 470734.1819000002,1281264.706 L 470738.057,1281441.0812999997 L 470824.6195,1281613.4562 L 470949.3382000001,1281759.2064999994 L 471032.08860000037,1281888.4565999992 L 471072.8387000002,1281940.4564999994 L 471140.3075000001,1282060.8318 L 471189.9638,1282155.9569 L 471220.5263,1282258.7069 L 471229.46389999986,1282428.7072 L 471186.24509999994,1282546.8321 L 471146.8388,1282619.2073 L 471056.55759999994,1282849.0825999994 L 471050.21360000037,1282974.7076999992 L 471048.99480000045,1283088.9576999992 L 471088.4637000002,1283241.083 L 471215.8076999998,1283511.2082 L 471377.49540000036,1283895.4583 L 471484.4642000003,1284127.4586999994 L 471577.4018000001,1284360.709 L 471621.9645999996,1284482.4591 L 471678.02699999977,1284677.834 L 471717.5270999996,1284936.5844999999 L 471751.96470000036,1285173.8345999997 L 471838.5899,1285490.9597999994 L 471858.4023000002,1285592.0851 L 471940.55879999977,1286108.7105999999 L 471976.21520000044,1286283.8355 L 472081.9653000003,1286685.961 L 472062.9653000003,1286966.4611 L 472026.1217,1287151.7113 L 471989.2778000003,1287345.9616999999 L 471956.2154000001,1287488.2118999995 L 471931.9654000001,1287644.5869999994 L 472334.0593999997,1288216.2124 L 472419.0281999996,1288228.4625 L 472510.18460000027,1288452.2125 L 472547.99710000027,1288614.5877 L 472524.09109999985,1288743.5877999999 L 472483.6848,1288882.9629999995 L 472460.0454000002,1288957.2 L 472531.40359999985,1289209.5884 L 472590.24760000035,1289405.3385 L 472739.46640000027,1289516.9635 L 472905.21640000027,1289589.0887 L 473092.56039999984,1289638.3385 L 473527.0920000002,1289645.2135 L 474075.0301999999,1289668.2135 L 474579.6553999996,1289695.3384 L 474885.6557,1289846.0884 L 475630.03160000034,1290012.4637 L 475993.2507999996,1290071.5887 L 476127.21949999966,1290225.2137 L 476533.7198999999,1290235.9637 L 476773.3139000004,1290271.0886 L 477001.43900000025,1290303.7137 L 477327.6582000004,1290325.9636 L 477574.8770000003,1290336.9636 L 477702.2522,1290292.2136 L 477880.56489999965,1290238.4635 L 478085.78369999956,1290272.3384 L 478260.44010000024,1290359.8385 L 478528.0656000003,1290380.9637 L 478891.25320000015,1290414.5884 L 479235.28479999956,1290413.8384 L 479509.2538,1290426.0885 L 479698.3507000003,1290506.7173999995 L 479603.7226,1290549.3386 L 479425.5038999999,1290693.3388 L 479309.7224000003,1290858.8389999997 L 479285.7224000003,1291015.3389999997 L 479423.72279999964,1291341.9642999992 L 479611.34800000023,1291598.4647 L 479863.9419,1291860.0898 L 480051.53589999955,1292093.7149999999 L 480065.6919999998,1292205.59 L 479940.9419999998,1292297.3400999997 L 479789.4731999999,1292435.0901999995 L 479804.9731999999,1292624.4656 L 479816.5981,1292749.0907 L 479852.5669,1292993.2159 L 479866.7857999997,1293161.0909 L 479934.5356999999,1293345.3410999998 L 479883.8169999998,1293559.2162999995 L 479870.0981999999,1293807.2163999993 L 479974.8485000003,1294013.0917 L 480129.1922000004,1294150.0917 L 480189.2862,1294320.4668 L 480306.5674,1294355.8421 L 480404.5990000004,1294291.9669 L 480613.6617,1294362.8419 L 480725.6616000002,1294269.842 L 480835.3492999999,1294352.2168 L 480813.88040000014,1294511.2171999998 L 480770.7241000002,1294638.5922999997 L 480712.2242,1294744.2173999995 L 480628.2241000002,1294832.0923999995 L 480516.16139999963,1294889.5924999993 L 480646.3491000002,1295055.9675999992 L 480702.8805,1295090.7177 L 480879.5993999997,1295108.8427 L 481130.6309000002,1295127.4678 L 481486.1311999997,1295126.8424999993 L 481814.88150000013,1295118.5925999992 L 482170.3819000004,1295115.3424999993 L 482374.2570000002,1295112.4674999993 L 482569.2571,1295111.2173999995 L 482602.0070000002,1294833.4671 L 482746.7260999996,1294368.9667 L 482873.6321,1293933.7163999993 L 483006.88239999954,1293492.2159 L 483098.1947999997,1293116.8406 L 483170.4451000001,1292802.4652999993 L 483264.4138000002,1292550.4649999999 L 483340.6950000003,1292392.7149999999 L 483610.2264999999,1291898.7144 L 483812.4453999996,1291573.9641999993 L 483896.2580000004,1291324.5888999999 L 484033.5703999996,1291083.8386 L 484217.32079999987,1290795.9634 L 484282.78949999996,1290647.2133 L 484385.8207,1290476.5881999992 L 484496.4770999998,1290321.2127999999 L 484640.3521999996,1290215.3378999997 L 484809.6021999996,1289981.7127999999 L 485032.13379999995,1290359.0877999999 L 485542.2593,1290369.8380999994 L 485607.6656999998,1290371.2129999995 L 485907.2285000002,1290361.9628999997 L 485973.2284000004,1290359.9628999997 L 486396.54119999986,1290358.3379999995 L 486722.5728000002,1290359.4628999997 L 487428.47979999986,1290320.7128999997 L 487491.35500000045,1290322.9627 L 488152.19930000044,1290346.5877999999 L 488430.1057000002,1290344.2126 L 488710.41839999985,1290339.4627 L 488927.6687000003,1290344.4626 L 489062.73110000044,1290332.9625 L 489046.8876,1291511.7138999999 L 489070.98819999956,1291597.9351 L 488931.63889999967,1291696.3028999995 L 488864.6327999998,1291754.9451 L 488941.0303999996,1291944.2073 L 489084.4466000004,1292100.3662 L 489149.4939000001,1292436.8154 L 489541.5444,1292777.5898 L 489845.1383999996,1293037.84 L 490067.1699,1293309.5901999995 L 490127.29480000027,1293510.3403999992 L 490204.2324,1293915.9657 L 490287.5451999996,1294316.4662999995 L 490351.4826999996,1294487.9662999995 L 490471.5451999996,1294738.3416 L 490767.6079000002,1295105.3418 L 490906.79590000026,1295349.217 L 490967.17069999967,1295750.9675999992 L 491021.2647000002,1296226.593 L 491014.0147000002,1296575.0932999998 L 491017.0147000002,1296942.5935999993 L 491004.7336,1297398.219 L 491305.5462999996,1297406.3441 L 491536.14020000026,1297379.0938 z\" /></g></g></svg>",
      "text/plain": [
       "<shapely.geometry.multipolygon.MultiPolygon at 0x2626ba30048>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check the shape of each multipolygon or polygon by changing the number in the [] for the specific province\n",
    "data['geometry'][2] # or data.at[2, 'geometry']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "684.3447598239339"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Calculate area of polygon in square km\n",
    "area_pp = data['geometry'][2].area/1000000\n",
    "area_pp"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0    5295.150767\n",
      "1    3253.310484\n",
      "2     684.344760\n",
      "Name: area, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "# Let's create a new column for area and calculate area of all polygons in km2 using dataframe.area \n",
    "data['area'] = data.area/1000000\n",
    "\n",
    "print(data['area'].head(3))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let’s check what is the min, max and mean of those areas using common functions we used to know."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Max area: 14031.82\n",
      "Min area: 152.48\n",
      "Mean area: 7163.4\n"
     ]
    }
   ],
   "source": [
    "# Maximum area\n",
    "max_area = data['area'].max()\n",
    "\n",
    "# Minimum area\n",
    "min_area = data['area'].min()\n",
    "\n",
    "# Mean area\n",
    "mean_area = data['area'].mean()\n",
    "\n",
    "print(\"Max area: {max}\\nMin area: {min}\\nMean area: {mean}\".format(max=round(max_area, 2), \n",
    "                                                                   min=round(min_area, 2), \n",
    "                                                                   mean=round(mean_area, 2)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's try out a bit more difficult analysis :)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "***Problem:*** *Extract provinces with population density more than 20km2 and less than 100 km2 and plot them.*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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>ogc_fid</th>\n",
       "      <th>pro_code</th>\n",
       "      <th>province_k</th>\n",
       "      <th>provinces</th>\n",
       "      <th>households</th>\n",
       "      <th>males</th>\n",
       "      <th>females</th>\n",
       "      <th>total</th>\n",
       "      <th>house_size</th>\n",
       "      <th>area_km2</th>\n",
       "      <th>pop_km2</th>\n",
       "      <th>reference</th>\n",
       "      <th>geometry</th>\n",
       "      <th>area</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>កំពង់ឆ្នាំង</td>\n",
       "      <td>Kampong Chhnang</td>\n",
       "      <td>122925.0</td>\n",
       "      <td>251895.0</td>\n",
       "      <td>274037.0</td>\n",
       "      <td>525932.0</td>\n",
       "      <td>4.3</td>\n",
       "      <td>5521</td>\n",
       "      <td>95</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>MULTIPOLYGON (((440280.561 1383585.908, 440090...</td>\n",
       "      <td>5295.150767</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>កណ្តាល</td>\n",
       "      <td>Kandal</td>\n",
       "      <td>273111.0</td>\n",
       "      <td>580129.0</td>\n",
       "      <td>615418.0</td>\n",
       "      <td>1195547.0</td>\n",
       "      <td>4.4</td>\n",
       "      <td>3179</td>\n",
       "      <td>376</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>MULTIPOLYGON (((481223.477 1313362.233, 481407...</td>\n",
       "      <td>3253.310484</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>12</td>\n",
       "      <td>ភ្នំពេញ</td>\n",
       "      <td>Phnom Penh</td>\n",
       "      <td>399203.0</td>\n",
       "      <td>1039192.0</td>\n",
       "      <td>1090179.0</td>\n",
       "      <td>2129371.0</td>\n",
       "      <td>5.3</td>\n",
       "      <td>679</td>\n",
       "      <td>3136</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>MULTIPOLYGON (((491536.140 1297379.094, 491748...</td>\n",
       "      <td>684.344760</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>14</td>\n",
       "      <td>ព្រៃវែង</td>\n",
       "      <td>Prey Veng</td>\n",
       "      <td>227008.0</td>\n",
       "      <td>501346.0</td>\n",
       "      <td>556082.0</td>\n",
       "      <td>1057428.0</td>\n",
       "      <td>4.7</td>\n",
       "      <td>4883</td>\n",
       "      <td>217</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>MULTIPOLYGON (((536011.301 1311635.984, 536169...</td>\n",
       "      <td>4761.436372</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>20</td>\n",
       "      <td>ស្វាយរៀង</td>\n",
       "      <td>Svay Rieng</td>\n",
       "      <td>131937.0</td>\n",
       "      <td>249446.0</td>\n",
       "      <td>275108.0</td>\n",
       "      <td>524554.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>2966</td>\n",
       "      <td>177</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>MULTIPOLYGON (((587996.231 1282290.102, 588224...</td>\n",
       "      <td>2868.244685</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ogc_fid  pro_code   province_k        provinces  households      males  \\\n",
       "0        1         4  កំពង់ឆ្នាំង  Kampong Chhnang    122925.0   251895.0   \n",
       "1        2         8       កណ្តាល           Kandal    273111.0   580129.0   \n",
       "2        3        12      ភ្នំពេញ       Phnom Penh    399203.0  1039192.0   \n",
       "3        4        14      ព្រៃវែង        Prey Veng    227008.0   501346.0   \n",
       "4        5        20     ស្វាយរៀង       Svay Rieng    131937.0   249446.0   \n",
       "\n",
       "     females      total  house_size  area_km2  pop_km2  \\\n",
       "0   274037.0   525932.0         4.3      5521       95   \n",
       "1   615418.0  1195547.0         4.4      3179      376   \n",
       "2  1090179.0  2129371.0         5.3       679     3136   \n",
       "3   556082.0  1057428.0         4.7      4883      217   \n",
       "4   275108.0   524554.0         4.0      2966      177   \n",
       "\n",
       "                                       reference  \\\n",
       "0  Provisional_Population_Census__00.06.2019.pdf   \n",
       "1  Provisional_Population_Census__00.06.2019.pdf   \n",
       "2  Provisional_Population_Census__00.06.2019.pdf   \n",
       "3  Provisional_Population_Census__00.06.2019.pdf   \n",
       "4  Provisional_Population_Census__00.06.2019.pdf   \n",
       "\n",
       "                                            geometry         area  \n",
       "0  MULTIPOLYGON (((440280.561 1383585.908, 440090...  5295.150767  \n",
       "1  MULTIPOLYGON (((481223.477 1313362.233, 481407...  3253.310484  \n",
       "2  MULTIPOLYGON (((491536.140 1297379.094, 491748...   684.344760  \n",
       "3  MULTIPOLYGON (((536011.301 1311635.984, 536169...  4761.436372  \n",
       "4  MULTIPOLYGON (((587996.231 1282290.102, 588224...  2868.244685  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Re-read the data\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'list'>\n"
     ]
    }
   ],
   "source": [
    "# Create a list for storing result\n",
    "result = []\n",
    "\n",
    "# Iterate over each row of our data\n",
    "for index, row in data.iterrows():\n",
    "    \n",
    "    # Set condition of density between 20 and 100\n",
    "    if 20 < row['pop_km2'] < 100:\n",
    "        \n",
    "        # Get the row info where the population density meets the condition and save it\n",
    "        result.append(row)\n",
    "\n",
    "print(type(result))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Our result is saved as a list. Because we cannot plot a `list` of geometry, it is necessary to convert it to a `Geopandas` GeoDataFrame."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create GeoDataFrame from the list-typed result\n",
    "province_20_100 = gpd.GeoDataFrame(result, crs = 'EPSG:32648') # or quicker way: crs = data.crs"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "So now, we can plot our result because it has been converted from a list to a geodataframe. Let's see how it looks:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWYAAADnCAYAAAAtvfzfAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAAsTAAALEwEAmpwYAABGQElEQVR4nO2dd5xU1fXAv2fK9s7C0tmldwEXELEhFjBExa5RibHEXmKMqFET/ZmoMVFjR8Uuig1LFEFUiiCyVKnSYemwve/OnN8fM+ACW2Z3p7zZvd/P531m5r377j13y5n7zj1FVBWDwWAwWAdbqAUwGAwGw+EYxWwwGAwWwyhmg8FgsBhGMRsMBoPFMIrZYDAYLIYj1AIYDAZDKDlzVKweyHH51HbxivKvVXVMgEUyitlgMLRsDuS4+Onrzj61tbdbnxpgcQCjmA0GQwtHATfuUItxGEYxGwyGFo2iVKpvpoxgYRSzwWBo8ZgVs8FgMFgIRXFZLDWFUcwGg6HF48YoZoPBYLAMCriMYjYYDAZrYVbMBoPBYCEUqDQ2ZoPBYLAOihpThsFgMFgKBZe19LJRzAaDoWXjifyzFkYxGwyGFo7gQkItxGEYxWwwGFo0ns0/o5gNBoPBMnj8mK2lmC2bKF9EJovIXhFZ6WP7i0RktYisEpF3Ay2fwWBoPrhVfDqChZVXzK8DzwJv1tdQRHoA9wAjVTVXRNoEWDaDwdBMMCvmBqCqc4Cc6udEpJuITBeRxSIyV0R6ey9dCzynqrnee/cGWVyDwRCmKIILm09HsLDyirkmJgHXq+p6ERkOPA+cCvQEEJEfADvwN1WdHjoxDQZDOBFMM4UvhI1iFpE44HjgA5FDP8RI76sD6AGcAnQE5opIf1XNC7KYBoMhzFCECrWHWozDCBvFjMfskqeqg2q4lg38qKqVwGYRWYdHUS8KonwGgyEM8QSYWMuqay1p6kBVC/Ao3QsBxMMx3svTgFHe86l4TBubQiGnwWAIP1zeIJP6jmBhWcUsIlOABUAvEckWkauB3wFXi8hyYBVwjrf518ABEVkNfAfcpaoHQiG3wWAIL1QFl9p8OoKFZU0ZqnppLZfG1NBWgT95D4PBYGgQbj+uhkXkNjyeYgK8rKpPiUgK8D6QDmwBLjroRVYTll0xGwwGQzDwbP45fDrqQ0T641HKw4BjgHHeOIuJwCxV7QHM8n6uFUuumFNTUzU9PT3UYhgMBouzePHi/arauil9+Hnzrw8eR4QSABGZDYzHY3Y9xdvmDeB74O7aOrGkYk5PTycrKyvUYhgMBosjIlv90Y/Ldz/mVBGprpwmqeqkap9XAo+ISCugFDgLyALSVHUXgKruqi862ZKK2WAwGILFwcg/H9mvqpm19qW6RkQeA2YCRcByoKqhMtUrjS/JhETkFBFZ5k0gNLva+TEisk5ENohInTYVg8FgCBVutfl0+IKqvqqqQ1T1JDxpJdYDe0SkHYD3tc60Eb6M9Do1eEIcRESS8IRGn62q/YCDfsZ24DlgLNAXuFRE+vownsFgMAQNTxIj/+XKOGimEJHOwHnAFOAzYIK3yQTg07r6qNeUoapzRCS9jiaXAR+r6jZv+4PfBMOADaq6ySvke3gM4KvrG9NgMBiChSJU+jck+yOvjbkSuMmb8fJRYKo3HmMb3gVsbfjDxtwTcIrI90A88LSqvgl0ALZXa5cNDK+tExG5DrgOoHPnzn4Qy2AwGOpHFb8Gj6jqiTWcOwCM9rUPfyhmB3Csd9BoYIGI/Ag1emzXWovWu7M5CSAzM9NiNWvDl43rduOMsFNYUEa/YzqFWhyDwYKIXwNM/IE/FHM2np3KYqBYRObgcazOBqprgo7ATj+MZ6iG262sWraNrz5dwtKFmxCbMO78TMadn4ndYefF/0xnxRKPR9Ht9/2WsecOCbHEBoO1UPy7YvYH/lDMnwLPiogDiMBjrngSWAv0EJEMYAdwCR57tMFPFBeVcfm4Jykprjjs/Bsvfsfe3fnsys5l3epfvwu7924XbBEBqKx0sXn9Hnr2bR+S8Q2G+ghmEnxfqFcxe5MJnYLHsTobeBBwAqjqi16/venACsANvKKqK7333ownwZAdmKyqqwIyixbC/r0FzPlmNePOzyQi0sGsL1ccpZQP8tW0JUedS20dz97d+bRpmxhQOctKK4iMciIiVFRUcdPlL7FjWw5X3TSaC684/lA7VaVabm2DISQowa3n5wu+eGXUlkyoept/Af+q4fyXwJeNE81QnS0b9vLYAx+zaf0e9uzKQwQ+mbKwQX1cdtZ/cLuVIcO70u+Yzpzx20GUllTQpWtrZn25gg6dU+jdv2OD+jywr5DJz82ic3oqF//+BBbN38Df7pzC7649mV79OvDVJ0vYtnk/AK/8dyZLf9rE+EuGgwifffAT/QZ24tjjutGqdQIpqXENGttg8AcKVPqQByOYiCcxm7XIzMzUlhaSXVxUxpefLMZut7P65+04HXa2bNzLwGPTqaioYkXWFrK3+TeTaUSkgw6dWzF0RHemvvkDrdMSePzFCbTvmHKoTfbWA+TsL8ThtLN3dz6nnNH/0DWXy81j93/M7JmraNs+iVPHDmTD2l389MP6BsuS1j6JYcd3Z/gJPRk6sodf5mdo/ojI4roi8XyhU/9Eve2D43xqe1ffGU0ezxes9TXRAsjLLWb3jlw+fHsBfQd2YuCxXVizIpt3XplNbk7xUe03rd8TMFkqyqvYvH4Pm71j7NtTwF+uf4Oo6AiOP7kX/QZ15rOpi8hasOHQPTO/WI6Ip+2+PfkUF5UDsHtnHu++OqfRsuzZmcfnH2YRExtpFLMhqCj4HNUXLIxiDiJFhWVc/psnSU1LYFd2LnNnWS/WZt+eAgDe37If3vjhqOvVlXQgiI2PCmj/BkNNBLM6iS8YxRxgVJUP3prPskWb2bMzj8pKF7uya82P3eIZPrJnqEUwtDBUxayYWxIF+aVcPu5JyssqQy1KWGCzCe07pdTf0GDwI57NP1Mlu0VQVeXiqUc+N0q5IVjradLQYhDLBZhYS5pmxJ5d+SyYvTbUYoQVbpeyfPGWUIthaGF4Nv/EpyNYGMUcIDp0SjnMtczgG3a7+ZM0BB9/pv30B+a/IIBcctVRSaYMdXDciT1NoiVD0DkY+WdWzC2ELl1bc8KpfUItRthQUVGFw2GtTRhDy8CNzacjWBjFHGAu/YNZNfvKkoWbeP2Fb0MthqGFoQqVbptPR7AwijnAdO/VjoweaaEWI2yY+uYPPPrXj9m9My/UohhaCB5Thv9q/vkDo5iDwLW3nU5cgolo85Xvvv6ZKZMbH95tMDQUF+LTESyMYg4Cxw7vxuMvTGDwsK507NyKzhmtsdtt2GyCw2F+BUcy/ISe3HTXWaEWw9BCsKK7nAkwCRLderbl0eeuOPS5uKgMZ4SDay98zjy2V2PYCT3462MXEhFh/jQNwcKEZBu8xMZFsWr5dqOUq5HSKo77H7vIKGVD0Am7mn8iMhkYB+xV1aMiJkTkFDzlpTZ7T32sqg95r20BCgEXUBWMPKbhgqoyd5Yp6HKQqGgn/37lKqOUDUHH45VhLTdNX/4LXgeeBd6so81cVR1Xy7VRqrq/oYI1d9wuZfWK7FCLYRkGZWYclqDfYAgWViwtVa9hRVXnADlBkKVFYXfYaNU6vtbrrdMSgihN6OnSrU2oRTC0YNyIT0ew8JfFe4SILBeRr0SkX7XzCswQkcUicl1dHYjIdSKSJSJZ+/bt85NY1mXxjxv5cc66Gq+ltU/iqclXtyjlfMIoEyFpCA3+9soQkTtEZJWIrBSRKSISJSIpIjJTRNZ7X5Pr6sMfinkJ0EVVjwGeAaZVuzZSVYcAY4GbROSk2jpR1Umqmqmqma1bt/aDWNZm8nOzcLuPrrcYHRPB/Y9eSGqbBG69pzbrUPMiLiGKHn3ahVoMQwvGXwEmItIBuBXI9O7J2YFLgInALFXtAczyfq6VJitmVS1Q1SLv+y8Bp4ikej/v9L7uBT4BhjV1vObC9XecedQ5u93G/Y9dRI8+7QEYenx3BmVmNHqMxKQoEhKtH9hSVFBG1oKNoRbD0EJRFarU5tPhIw4gWkQcQAywEzgHeMN7/Q3g3Po6aBIi0hbYo6oqIsPwKPsDIhIL2FS10Pv+DOChpo7XXBgwpAujxw5k5fJttEqNJzYukvGXHcexw7sdaiMi3DLxN9x0xUuUlTYs4f4ZZyVyzZXv4bSXsWz1SaR3XE9ERNlR7dT7iCaAHHpSU0T00HUQVGu+DvDa2+dis0GVC5ZmlZObU3roms0u9B+YRFw8VFZASQnY7ZDRtYqYmCqKCh1M/18J8YnRDZqfweBPGrD5lyoiWdU+T1LVSQc/qOoOEXkC2AaUAjNUdYaIpKnqLm+bXSJS56aKL+5yU4BTvAJlAw8CTu8ALwIXADeISJVXkEu8SjoN+EQ8/80O4F1Vne7j5FsE19x6OonJMXXmIO7YpRW33TOOJx/5nIryKp/6vepaB+eOfZUIp6eC9XFDAvtjv/Pm5w69Ly5J5J4HL2f92jzadYjn9ttWMbDP23Xe36nTZaSlHW3WMRiCwUEbs4/sr8vt12s7PgfIAPKAD0Tk8obKVK9iVtVL67n+LB53uiPPbwKOaahALYmU1Dif2p06diAnjO7Loh/W89G7P7Jq2bYa28XGRXDXX3aSOfAb7HaXP0X1mdiYfJ74xytsze5Pp3ZriYoqrvee354xBUlq8N+uweA3/OgudxqwWVX3AYjIx8DxwB4RaeddLbcD9tbVifHmDxMiIhyMHNWH4qJyVi3bRmqbWDK6RlJUpFRVKRldldNGrWBA73mhFpUIZzk9Mhb73F7iJyKO7gGUyGCoHT/7MW8DjhORGDwWhNFAFlAMTAAe9b5+WlcnRjGHEaqV5O3fxN33FjFiyEdERpZVu1bdBhxGOPqDvW2opTC0cPzlo6yqC0XkQzzealXAUmASEAdMFZGr8SjvC+vqxyjmsMLNBWc9DHq0eSAslTIgUacjUWNDLYahBaMKVX5Mgq+qD+LZi6tOOZ7Vs08YxRxOVCyrUSmHL1EQWatru8EQNKwWkm0UczhhTwMigIpQS+IXJOFexNmv/oYGQwAJy1wZBusgjnSIbCY1BJ0DIepsVI2bnCH0qIpPR7AwijmM0KrNUDE/1GL4h8pV6N5joWJ2qCUxGJptEiNDgFFVtPRT0NL6G4cFLsCFlk03q2ZDSFG1Xmkpo5jDBBFBokbjDbpsPpR+jBY+HGopDC0aweW2+XQEC7P5F064c/GsNJsXYmv+2QQN1iaY9mNfMCvmcELLAXeopfA7WvQkWrEs1GIYWihWrJJtFHM4Ye8ARIZaisBQsSjUEhhaKuqxM/tyBAujmMMJR0+I8jl4KMwoD7UAhhaM1bwyjI05TFB3Ppp7I1Q2z5WlVq4ErUSkmW1uGiyPejf/rIRRzGGCFv232SplACoWglaAUcyGEGA1j02jmMMGe6gFCCgSex1iiw21GIYWSth5ZYjIZBHZKyIra7l+iojki8gy7/FAtWtjRGSdiGwQkTqLDxpqR7UcqjaFWozAEjEi1BIYWiiejb3wC8l+HRhTT5u5qjrIezwEICJ24Dk8FbL7ApeKSN+mCNtSEYlEEu4FSQq1KAFBkl9HIgaFWgxDCybs3OVUdQ6Q04i+hwEbVHWTqlYA7+GphWVoDBID0kwtT470UEtgaOE0V3e5ESKyXES+EpGDeRw7ANurtcn2nqsREblORLJEJGvfvn1+EqsZ4c4FLQm1FIGhYkmoJTC0YBTB7bb5dAQLfyzBlgBdVLVIRM4CpgE9oEanv1q/c7wlwCcBZGZmWmyP1AI4uoM9HapWh1oSv6MFD6DFLwCRnicDeyvEORBsbSFyJGJLCrWIhmaO1RROkxWzqhZUe/+liDwvIql4VsidqjXtCOxs6ngtF/HmymiGaBFUrf/1cyVo2Vee986hkHAf2LuAliL2VM8tWgElb0H0eYgtOQRCG5oNaj2vjCYrZhFpC+xRVRWRYXjMIweAPKCHiGQAO4BLgMuaOl6LxbUF3PtDLUXwqVyEHjjX816iIeER0EK0ZCoSdYZRygb/YLElc72KWUSmAKcAqSKSjafIoBNAVV8ELgBuEJEqPOW6L1FPgt0qEbkZ+BqPE+5kVV0ViEnkVuynoPLg/mT1b76G/bSTIlJJdKb4TS6/UvYNUBlqKUKLlqL5f/K8j70WibshtPIYmg1ht2JW1Uvruf4s8Gwt174EvmycaL4ze9/nzNs/vcn9nNXuMk5tY1HHEXtbPN9vzS/tZ2MQiQu1CIZmggJud5gp5nAg2t4S/kmF5pjys1FIAkSdFWopDM0FBSy2YrZW5o5GkhLRJtQiBBwtm4HlDGEhwYnE34s4uoRakEZT5XLz/Fuz2ZJ9INSiGLz4y49ZRHpVi4JeJiIFInK7iKSIyEwRWe99rXNzpFmsmKu0wq/9lbvKWFe4nPbRXUiNbOuXPkuqithbvoMIWxSxjngibFFE22N8ulfVBRXz/CJHWGPvjCQ9hTj7h1qSRjF/ySY+/2YFS1dtp7C4nGMHdCG9Y6tQi2UAv615VHUdMAgORT/vAD4BJgKzVPVRb3qKicDdtfXTLBTz9pKNfulH1c33ez/nmz0fUeb2FD1tHdmePvGD6Z0wiK6xfbGLHZG6H3t2lW4ju3QzaVEd2FaygW0lG1hbsJQSVxEOcWIXOykRbbig43V0iumGTep+cBGxQ/xf0IK/+2We4Yok/ScslfKOPXm8+v58vp5zuA/6gqWbGD4oPTRC1YHb7ea9J76gpLCU3D35dOrZjuQ2iYwYN4SElOZoNgxYHozRwEZV3Soi5+BxogB4A/ie5qyYVZWtxevrb+gD3+79lHL34VWo95XvZF/5Tubs/x+Rtihi7PE4bREMSBxGv8RMOkV3O6Socyr2kpUzm3n7v6bEVVjjGFVaSZVWsqtsG89s+CuJzla0iWxHhC2Koqp82kR2IDmiNdH2GASha1wf2kenQ/R5UPB/tNjNv9ibPUEnYUJ5eSVffr+KmfPWsmJtdo2PwQ67NS2JN464n82rso86/0TXNgw4oXcIJAoCgbESXgJM8b5PU9VdAKq6S0TqtL+GvWLOqdjLnvKj/4gaw5FK+ejrZZS7ywCYtfcTZu39hE4x3Ul2tiLWkUBhVR4r8xuWMzm/8gD5lb/aGreWHP0lc3yrM+gQnYHDPYb+jjU43c0809xR2JHYK0MthE+4XG4+nbmcNz5eyP6cojrb9kgPzd7ItnU7+eGzxZQVl+Nw2inKK6ZN51T6HdeDrWt3kL1hT433ud3NdI9DQX33ykgVkaxqnyd5o5YPQ0QigLOBexojUtgr5kRnCrH2eIprWaEGmu0lG9jOhoCOMf/AjEPvbSQyJvk0Kt2QHulmTZkwNnYLTrd/zDmWRGLCJiz7o+lLefq173xqu3NPfoClOZqF05fxt4ufxu1quIfP1jU7OOakPgGQygr4rJj3q2qmD+3GAktU9eC33B4RaeddLbcD9tZ1szWfpRqAw+ZkcPIJoRYjaLiBL3MPMDP/AC/vzWVeQQ737Ypnheu0UIsWOLQU1apQS1Ev87I28swb3/vcPiIi+MUP5n2a1SilDNCqXZJ/hbES6uPhO5fyqxkD4DNggvf9BODTum4Oe8UMsKt0a6hFCDHCl3mFrHWPpsoWvm5kteMGd+0ZB10uN8Ul5cxeuJ45P/1qCiovr2T3vnyqXG72HShk977ArVB/XruD+574tEGP+0XFwS1AO+/TLGa8NbfR93fp09GP0lgMPypmEYkBTgc+rnb6UeB0EVnvvfZoXX2EvSmj0l3BxuLml3GtoeRUVTB5Xw6ZcV05NrYruyocdI0so50uAECw/oqzVuxdEHu7Gi/t2JPHw//9knWb9lBR6dkYzejUipy8EvILD98ziImO4JMX/0hcbKRfxVu3aQ93PfoJVVUNW4lWNXLl2hg2r9zOSxPfbfT9zkgn7TJa+1EiC+HnABNVLQFaHXHuAB4vDZ8Ie8XstEVwSacbeW/786EWxRJkFeWRVW3PaXCsx8wzPE7oim+2T8vh2oy69iL2XzfLtu/K5f0vspg2Y/lRHg+bt9ccuFFSWsGBvGK/Kubd+/L5y6OfUFhU1uB79+wroKCwlIT4aL/JUxNlJeU8fetr7K3l5+ILleWVLJ61kmFnHuNHyayDKcYaAPonDkO2v4CayLijWFrseXzf7erMHV1eQlyb0JIPwRVGm4WSRHllLBs27mTpqu18t+AX1m2q2XOgLjq3T6FLB/8kqcpasZUZc9cwa/5aysob9zQya/46lq/dwUuPXEbb1gl+kasmvnjlW9b81PTf98v3vsexo/tjdzTDwsAmV4b/ibJHc0zSCJblzQ+1KJZEECak34ktsi0wCmL+AFXroHIpWj4fXFuham2oxayV3NKenH3TC03u5/Lxw5rcx669+Tw1+VvmZfnni21/ThEvT5nH/bcGLvdH3t6C+hv5wLZ1O1m9cAMDRvbyS39WQiy2pmsWm38A53e8Brs0w29yPxBjj6NVRNqhzyKCOHsjMZdiS34GafUpkjoDSZ0JMb8DR48QSns0c5d3b3IfSQnRnJjZrUl9LFudzZV3vuE3pXyQnDXZ3DXmn6zN2ojLT3bnhy79L+8+/hnb1u5k4fRlfukT4L5zn+DJmydTUI+Pdljh68ZfEJV3s1gxA0TbY+ka24f1RStDLYrlKHYVsq5wOb0TBtV4XUQOFUSVhAdRLQXXPo9tt/RzKPsseMJWQ4niQMkgXvw4tsl9pXds1SRbrsvl5p/PT6ek1L95WQBKyirZMm8tt53yEPEpsZz1h1FERDiISYxh7ISTiY6LanCf2Rt288Pni3njoY/8Kmt5aQXTX5/Nzg17eGTanURERfi1/9Aglssu12wUM0Ci0ySEqY1VBVm1KuYjEYkGR2dwdEYiT0bdf4Xy79GCf4DmBVROABdp/LD6JB5/M4n8Iv/8wzibaBeds2gD2bvz/CLLkawqLKFj2yRyd+dRmFPM+098cejaB09+yRX3nsvoS0cSGe2bEiw4UMTurYEtaLxi3lq+ePU7zrvpzICOEzQsZsrwpYLJZGAcsFdVa80gIyJDgR+Bi1X1Q++5LUAhngQPVT5GzDSarrF9yMqdHcghwpY9ZY0PWxdbEkSfCxHHoXk3QeXPfpPrSJRoLrj/bPbn+ncFs3t/AS6XG3sj8lMsX5PNYy987Vd5qqMIbXq0JbcGxZ+zO4+nb32dn2as4N7Xb/Bphfra3z6gvMS/K3ubTfjb1NtxRjpJbBXH7i37iE9uRgmNLJbq3Je/0teBMXU18Ka3ewxPGakjGaWqgwKtlAGGJJ/I4KSRgR4mLPGH/V3sbZHkl8HW3g8S1UxRZQ+/K2WA7Ttz+eLbhn2huN3KlM8WccvfplIY4GAQV1rdXhkLvljCbaMeZuuaHXW227hiK7Pe9/8meLdjujB8zCCGjOpHt4FdGHl2JgNPbCYJjQ76MftyBIl6FbOqzgFy6ml2C/AR9cR/BxqHzUGfhMGNuNNizzEBIL/SPxW2xZaCJD8PBMa26LAFrq7hT8u3oD44rKoqWSu2cu09b/Psm7P9tiFXF8sKS+g9PpPYxNpzdG/6eRt/PvMfZH3zM8UFhwfP/PT1cu4951/cdspDfl8tA7TvmlZ/ozBG1LcjWPijSnYHYDxwKjD0iMsKzBARBV6qKQuTvxmYOIIfYr6uMUtbdSLEQZvIBLpFu6hwbSPClsqOimQ2lIT0uyVgFFUV4FZ3vbmffUGcfSHuJrToST9IdjjF5Yl+7/Mg3/+4nhlz13DmSX1rbbN1Rw7/emkGS1f7J2Ohz4iQVVrOkNP788uHP9XarCCniPvOfQK7w85xYwcxeFQ/Vv24nu+mLgioeBXlzbwQsMXWZv7Y/HsKuFtVXTUkkB+pqju9uUdnisha7wr8KETkOuA6gM6dOzdaGIfNwaltxjNv/1esL6r50TXWHklmQiyFFUso9C4uyl25JIjQM3YovxQ3P+Xs0irE9wxa9RP7Byj9CFzb/Ncn4HIFdj/61anzGT4onaSEo1ems+av5bEXZ1AcgBWnr+T4qCFcVS5++HwxP3y+OMASeVgxdy2LZ/3MsaMHBGW8lo4//Jgzgfe8G30XAM+LyLkAqrrT+7oXT3mVWj38VXWSqmaqambr1k2Lye+XeCzXdb2P9lE1J/QZkpBEYcWSmqQg1b6ZGFtzcAE6nHJ3KWsLl/mtP5FIJO52v/V3kJLyhruGNYQdu/N49IUZhyUbqqx08eSrs3jgP1+EVCkDtCm1Zk6T4vwSHrv6JfbvrM+qGZ5YzZTRZMWsqhmqmq6q6cCHwI2qOk1EYkUkHkBEYoEzgKA5GYsIo9PG13ytji3YMtc+hiY23W/Wiry//QV2lfpxhRs1Bmw1JxdqLFt211mj0i/MXbSBf7/yDQWFpaxev4trJr7Nh18tDfi49aLKgRoqh1iF/P2FPPHHV6iqtOaXR6NRPCHZvhxBol7FLCJTgAVALxHJFpGrReR6Ebm+nlvTgHkishz4Cfifqk5vusi+MyBxOG0ij/YgKFdnnfcVVixlcELgPA9CRVFVPm9s+TfrCpf7tAlWHyIOiP6NHyTzUKkd+ejbwNmYqzNtxnLGXvUc197zDhsC7PPrMyLEpwVn/o1l6XeruKzH7Wz82b8mrJBjscg/X7wyLlXVdqrqVNWOqvqqqr6oqi/W0Pb3B32YVXWTqh7jPfqp6iOBmEBd2MTG2HaXHmVbdfjwE06w7Q+UWCFlf8VuXt70D5bk+afqtkSe7pd+APJKOrH8l2aTJaBR2Dr6J8lSIMnfX8hzf3qT1QsDW7knmDQ7U4bVGZA4jCu63EHH6K4ApDrjcLlW+XCntUI0/UXM9tZ0/Ww0AxOG+6dD5yCwpfqlq1ax64iOtNj2eJDZXBUe3g+rFqznjtEPc1mP27j5xAf5ZcnmUIvUNMJtxRzuLD3wFpsL3iU9qoQTktvRL66KCrcv2baan2JWVfY9GsUnD87kuRtfoyivuMl9ighEHN80ubBRqV342xvjKS1vfj/3hpDirNvMZjUO7Mpj/dIt3HbK33ni+pfZ/suuUIvUOIxiDi49E06juOJHSip+pKRiAYUVPqa3bIb6IfG7nmyY7ynD9b+Xv+Hthz/0S78S0bR0mj9tOJdTbzmT7xaZ7IB5VVX0OM5a2f18we1WZr49j2uPvYenbp5MwYHwyT7nqxnDmDL8yM85rzbyzmaomVMqiKpWvaPPcD8pgKizIOKkRt26bvdY7n3W+nbVYHGgrJKliZH0ObVfqEVpFKrKV6/P5ppjJzJ32qJQi+M74eaVEe50iG05FbTro7TrPjoe0/bQ5w3LtvilX7HFeXJoOBqmTBZtHM81/9eJiqpm/2fYICLtNgp3+ieEPlTk7y/k/y5/luf//DZut8UyBNWAWTEHmY6xJxNlNyuyuDUdWXFm+SFTBkD+Po+tvSCnEJfL1aT+RQSJOsPn9orwj9f9s2nY3BhYqWSv3RlqMfzCpy/O5H+vhEGtSWNjDi4iQpvoIaEWI+RUzYmjouzwHf+vX/+OxyY8w7UD7uS5W19j/ZJNTRpDK5f51K6kqi9ZG88NSBa55sC+hCg69e0YajH8xtLvLV7F3oI25maVKL8mVJUKl39qnoUzpbuOdsNyu9x885YndcnnL3zN2oW/8LdP/kKbTo1cydprjwJ0k8r+op58Mqcnb3/Z/ELe/cmW4jLSeqVBsBMpBYiIqDDwNLGYl2azV8zlrlz2la0ItRghwVkUQ9SsTrgKhJ/nbK23/folm3nxzjfIPGMQZ10zusHjSfSlaMlU4PCQ3eLK/tz+9AjWbjErZF/ZU1pB965t2L0p/BNqte1ifZOVWMwM3uwVc5QjhRPaPsLsXXeGWpSgEpEXz+rxlRTnrWnQfXM//JG9W/fRrmsbBp86gNLiMqJjfUssJM5eaOy1UPxrRWsXbfnL88cZpdxAUiKd7N0a/tGnkTERnP67lrUBLyJJwCtAfzxr8T8A64D3gXRgC3CRqta6w9vsbcwAraL60T6moX8cFnu2aSDOnFjsjsb9etct2shfTnuIb9+dy491pJUsLz26qofE3XhYhZMn3j+LFetbxJ+ZX8nIK8UdhAT9gSQqNpK/vX87Hbq3rb9xqPHv5t/TwHRV7Q0cA6wBJgKzVLUHMMv7uVZaxH9MlD2ZVlF9GnaTH5L8hJKi9F20H9C09Kn/vPy/TJ88i12b9lCQU8iOjbsPuz73k4VHeXOIRCKxvwdgw94z+WJus38oCwj5reNDLUKTiEuO5bEv7mbIqDDwx/bj5p+IJAAnAa8CqGqFquYB5wBveJu9AZxbVz8tQjEDpEUHvOSgpYjZ1Zq13zU9f8GSb37mD31u4/aRf2Xl3DXs2bqPorxiVi9Yx+R73qUwp4gd648Iw40cTW5ZJg9ManzBg5ZO9NFFJ8KC1h1TOHH8UJ6adT+9h3YLtTi+478Vc1dgH/CaiCwVkVe8aY/TVHUXgPe1TV2dtJjlzNbCGQ27wQ8lmEJJ7r/8l1O6qtLF9nU7+e+NL2Oz2yirVph0Qo9buP4/E+jQo5pHhr0jM5ZNYPvuwFXTbu6Uo9hsclhCfysTmxjDXZOu5djR/X2q5G05fP8xp4pIVrXPk44omecAhgC3qOpCEXmaeswWNdHsFbNLK/h+5+3sKW1YCR43CUBpve2sSvF+/8t+pB80QGR0BMPHHXvYORFhUP+BQO2K2eGwkTmgC/16tGP7rlwWrdhKbn6Jv0UOW34pLOWYYzPYuKhpvuXBID4lljtfuIYRvwnPeAGhQV4Z+1W1rsfvbCBbVRd6P3+IRzHvEZF2qrpLRNpRT+HqZq+YbTjYX+Z74RSHxFJlO4a5uTsI53wZMSmBLdF0kPx9BXz2zFecetmJdO7za1BE725tueeGM5m/ZBNrN+7G6bBTWeWiZ0YapxzXg+OHdCUhPvpQ+8pKFy+/N493Pg2j/AoBJrJtUqhFqJcR44Zw69MTSElLCrUojcePwSOqultEtotIL1VdB4wGVnuPCcCj3tdP6+qn2SvmUtc+XOpbHbf4iL6sKBRyq3YSzkoZILl/NMwN/Dhut/L91AWMuuzEw86LCONGD2Ccj8U7nU47f7zsROZlbWTrjuZZV67BVDQtTD7QnHz+cCa+dj02W3ib/QB/O2HdArwjIhHAJuAqPPt5U0XkamAbcGFdHfhSWmqyiOwVkTqXnSIyVERcInJBtXNjRGSdiGwQkQbbWfxBtL01raMG1npdsBPj6IDNMZLZucXkVjU9R7EVkN8Gzwe219BuxCbGNDnfht1u4/wxg/0kVfizOdpOQqo1vTOcEQ6ueeTi5qGUwa/ucqq6zFtYeqCqnququap6QFVHq2oP72udqw9ffqqvA2PqaiAiduAx4Osjzj0HjAX6ApeKSF8fxvMrIjai7CkINmIc7UmIGEi0cwRu2/HscQ1meUkX5uU7ycoPb9PFkRQ8lRC0sRZ8lsUfj/kzq35Y1+S+una2fpRYsNhXVknHYdb0bLj4znG06dgq1GL4jbDLlaGqc0QkvZ5mtwAfAUOrnRsGbFDVTQAi8h4eX76gZzQZ1uZ+du9MJ89VRIRGsqZwKaWu5rEyro2ka8vIyOnE5qztAR+rtKiMsuJyTzWTJpKUEF1/oxZEWVxk/Y1CwAnnNDP3U4s5vzTZxiwiHYDxwKkcrpg7ANW1QjZQa6E5EbkOuA6gc2f/+r9G2mO5sNOvRb2X5v7AlG3P4cbaNrymUNx9F+3H9GZzVv1t/YEjwkFkTAQulwu7vfGVSIxnxuFsKjk6utIKWNXE0ijUerky/GEgegq4W1WP1HI1LZ9q/V5S1Uleu0xm69ZNi1irj8HJI7mx+4MkOptvnmapFNa+Frz6a5Xlldx2/H3MfHNOk/pZ6Kfk/c2FkioXjghr7dH3HJJBqzDwGGkQzTAfcybwnohsAS4AnheRc/GskDtVa9cRsEz27/TYXtzT+79cnRGSPcmAIy7HYYEgwaCq0sU3b81GGxnOvntfPrPm11+T0WFvJhtOPtAlNoqqiqr6GwaRs/94WqhF8DthZ2OuD1XNOPheRF4HvlDVaSLiAHqISAawA7gEuKyp4/kTh81JgiOJdlGd2VW2LdTi+BVnUSzlxflBH3fdTxtYNH0Zw8Y23Lvi2/m/sGvv0bmz01JjGNRXGXXcbFKT1gPCzB9+x8x5keTkl/lBautis9h+dHxKLCef37Tiu5Yk3GzMIjIFOAVPKGI28CDgBFDVF2u7T1WrRORmPJ4admCyqq7yh9D+pENMBjd0e5C/r74O11HWmBBRacNZHkVlXOPtra6oMlI6JLF3ywE/ClY/ZSXlPHPzK1x6z3n0Gd6dLv06+exSdenZmbRLS+TxF2dQUFRGSmIUV563naED3sFuP/x3M/6MJzj3dFiz8be8NW0Im7eHT1XmhrClqIxYu80ymebOuPzE8Ay5rosgmyl8wRevjEt97UxVf3/E5y+BLxsuVnCJccRxcacbeHfbsyGVw1EURfSWNux7VVj1wzbSh3ai3TV2iqY7iTsOCk5c7/MzTvk/2rN3y4bAClwLuzfv5cnrPN/Z3Qalc/7t42jVPpk+I3oeldv5QG4Rk977gRt+dyJJCTGMOq4nc3/awOyFv/DY3dOIj639u1wE+nb/nIdun8n0OTfwwZdOKiot8uXqJ1xAm/TW7N64J9SiAHDmFY2rhm5lhOCaKXzBWrsKIaRzTA86xXRne0lolFnsxnb88qdSDmzfeshGu2H+VjbM9zaYCqmdkul+bjs4ay+lbWv3T4/ZkcrCrzcGQer62bhsC4///llsNqH38B7c9MzVJLaKw+1S2nVNQ/V1KiuTeeA/X+B02EhOikVVSUqIJjG+EF8KLDsdZfz21CcZNbwtazaexqr16Sxfa2PX3ubhEpnSq50lFHNcUgyde7evv2EYYhSzRUmNbMtlnW/m9S1PUFRVQHFV4OsExmxrQ/Z9QmrfBOZPrT84Y//2XPY/k0vClDiOuacH+aN+QUSwlUUQl9WJqvVOqoqU3SsKLZeVzO1WVi/4hZsy72bI6QM56cIRlExbyPEXL+eWKzvjsGfww5IMemb0Ykv2fk4e3gq7Lc4nxXyQuNjdDB34NkO9gZ47dg/jnidOCftVtFrEK6O8tJJNK7fTbUAzTOdqrX8Xo5ir0zqyHTd3f5hHVt8Y0HFiN7Vl8z1V7PrFk3h++8qGubUV7C9i7p3r6DSgHWlDElkzbSvF+esDIWpAWDJzBUtmrmDEbzM5+XepVFQuorTsc4b07QqUcWz/kSTE/xmRWVRWbiQ3/x4qyhehNGyjLylhS9gr5VbJscTFx4RaDMDjEnn7qIcYfcnxXHLXb2nbJbBurUHFKGZr4xAHV3S5nZc3/7PB9ybM7Y67TSlFvXYcdS16VytKXkwipouTn9/ZSmFO0x+zt/+8i+0/B89X2d9kfb2M4pIfcER40om6XJ54pPKKhURGHo9ILA57B9qkTqXKtZN9+y+lquoXn/tftPLcQIjtM726ppHRqRX9e7Zn0pR5FBQd/sVy1YUjGNy3E9FRTqIiHVS5FFVl974Cyiuq6JHemrTUBDYv28KiSd+GaBaHU1FWyVevz+bbqQu48q/nMf7GM7A7Gh9QZAmC7ArnC0YxH4HTFkH76Az6JwxlfdFKyt2+5TWOyW7ND3dsoGO/tqS8YkOdbnBBwjc9qdpnI+vZ9VSW7wuw9OHF4NPbH1LKR1JU9Copyc+y78ClxESfQ1zsVURFnkhRAxTzKcMmkZt/J+9/4S+JG8ZZo/pxwVhPjuIBvTrw4rtzWLDEU1Xm7NMGcvVFx9cYxt6ra9phn3sP606vzK6sy7JObubykgpevvc9vpu6gNufuYoegzPqv8nKWEwxtxxP/QYQ70zk9xl/5sTUsT61j1vXgf2PRuF2udm2Yif2/3YnYVkX7GVRzJ24lgX/Xk1lec0KqCVTUVq7Abm07CuKil+ldat3cbtzycm9lZKSjxo8RlJ8aDYAHQ4b4079NeVp9/TWPPLnc7j+dydyx9Wn8sfLTvA5t4jdbuOSP/82UKI2iQ3LtnLryX/npXumBD2gyZ+I27cjWJgVcx2c0fZCNhStZEvJ0au0+P/1Yt83ZbjKXWxYvY/i/F9X1ovfXgtvB1PS8GT5dzuoKI0hIrpmf+38gn9QVPwWyUmPUlGxGLfmNXiMzAGf8eH0P3AgN7jVaAb0bE9UpPOwc5ERDq4YX2u6mDrJPK0/0XFRlBZZL6DG7VY+fmY601//ns69O/D4lxOJjA4vX2ermTLMirkOBCHB5kltGLk/gagXexORF0/8p7344f61rPt+MxsWbDtMKRt8Z/SVnagsq3tjy+Xazv4Dv6OiclmjxoiP3ckzD/yDlKTgVHQ5yCVnD62/UQOIiIpg6Bm15xW3AiWFZaxdtJFrhkzk/X9/QcGBMAn68TVPRjiFZDdHykrKeXXiO6xdtAFHqmL/P8h9KIn1c1fjmGwHfml0PgiDhz+9Hkm/U9/F10yhbnduE0ZzkxDnIK1VPGs2Fjaqh87tU0jvmMKW7BxOG9mLlb/sokd6a75dsO6oMHKHw8YxfTo0Qd6aGXJqP+Z8/JPf+/U3e7cfYPKDH5C3v5A//tPn+LTQYrF/Z6OYa2DSXW/x+QuHcv5zTGRPtmVtATyJegxNo323VvQfXWfJM79SXpGCKow/82fWPJ/e4PsH9u7A7y8YwfBBR9879pR+rN+yj9z8El58dy4VFVUcNyiD+Fj/r9Az+nWqv5GFmPnOXCbcfx5RMdbMKX0QE/kXBpQWlR6mlAGWf+y7J4ChfkaMD65ZISoyh4fveJyCoi7YbRm4GhB806VDCk89cCGRtQR5ZHRKJaOTp+pKq+RY3vpkIRcdUTXcX7Q/wlvD6hTmFLPwq2WcfH7j7OrBRCwWkGVszEfihyochtpp0yWZURO+CeqYIuCwl7Nk1ekNUsoAW3fkMPmD+fU3BE4b2Zs3npjAsf0DExkXl2yNQJOGMPvDhaEWoX6Mjdn6RMVE4nDajcnCz/Qc2o5ug5yMvXkmMUnBzXinCi9P/SvfLWic69x7n2cRHenk9xeM8LNkDePArryQjt8Y5n+xhLWLNtJ7qDVrFx7EmDIsTmV5pVHKfmbcjZ0YP3FKyB5Gftk8ttFKGaCqys2qX0IbYbnku1W8ct97IZWhMagqd4x+mOPOGsyAE3tz0vihpLa3YOUgo5itzar5Ta/0bIDew9tzwkVltOuxmy4D3wuphWj1xqYXZ9+5Nx9V9UvB2YZSnF/C5AemsnFFeBZzcLuV+V8sYf4XS3jp7nfpldmVjj3acsFtY+kaILNPQ7HaitnYmI9g9tQFoRYh7ElLT+bmV2Zx/EWfkTH4J2z20P7VD+6zqMbzDofvf/5bsg/w8DNfUR6CCM6HLnuG9Uu3BH3cQLEuaxOzpszn9lEP848Jz5O3L/CZHOsl3GzMIjIZGAfsVdX+NVw/B3gYcANVwO2qOs97bQtQiCffd5WqWr7mebsw2/m2Gs4IB3e9vyLoduS66Nx+Hp3bj2LbziIuHz+ME4d2p6rKRUJcFJ/OXMGHXy31qZ+Z89Zww+9OpPUREX2B5pFpd7J8zhrcbsVmtxEdG0VleSX3nP0vXFXha3YrL61g9kcL2b8zh79PvYP45NjQCOLnKtk16T0RSQHeB9KBLcBFqlqrc74vpozXgWeBN2u5Pgv4TFVVRAYCU4He1a6PUtX9PoxjCaxSwidcOfmS9qS0/z7UYhyGzebm5iu2UeH6PScO7X5YMderLx7J9l25PlXntttsJCUE3zPC4XRw7OgBh51TVTr1bMeW1dlBl8ffrFqwnk+e+5or/3peSMYPkB/zkXpvIjBLVR8VkYnez3fXdrMvpaXmiEh6Hderx13GYjkzesP44qUZoRYhrMkYZM0w3M7t36JN6/OPqrCdEBfFP+46h6n/W0K7NglkdExl9/4CikvKefylGXRsm8ygvh35bNbPVFRUsWxNNkMHdgnRLH5FRBh65kCSWieQ2iGZXxZvpsfgdGwOG7OmzA+7BcY7j35K76HdGHbmMaERIPCRvOfgqZ0K8AbwPU1RzL4gIuOBfwJtgN9Uu6TADBFR4CVVnVRHH9cB1wF07hyaDYGqyirLlYoPN5LaBr8yt29UkZN7G2mtv8Jmiz/sSlSkkyvP+zUIonu6JwF8RISDgb060Co5luOP7ca/Js1g9fpdllDMAOffPAaXy3WUl0OX3h3YsHwrfYZ244W/vBMi6RrOE9e9zKRF/yCpTULQx27AijlVRLKqfZ5Ug16rSe+lqeouAFXdJSJt6hrEL4pZVT8BPhGRk/DYm0/zXhqpqju9QswUkbWqOqeWPiYBkwAyMzNDsuretWkPObvzQjF0syEpzbpWq6qqjbjc+45SzLUx6rieh94PH5TOe89cQ5WFbLrJaYk1nr/w9rMA2LlpDwU5RbzzaPDC35tCeVkFkTEhyErXsI29/T7slR2l9xoqkl+9MrxKt5uIpHo/7/S+7gU+AYb5czx/06lXB+KSQrQB0Ux4Y2LTXdMCShMeWR1221GpPK1M+65pXHb32XTu1T4sqozYHXbsDfCU8Sf+zMdci97bIyLtALyve+vqo8k/BRHpLl7nThEZAkQAB0QkVkTivedjgTOAlU0dL9Bcdt/5IfFVbS7s2lgQBHNd44iKOgOHIz3UYgQVh9PB1Q9fxAPv3mL5v2u3y43NHt6KuQ699xkwwdtsAlDnY4wv7nJT8BitU0UkG3gQcAKo6ovA+cCVIlIJlAIXez000vCYNw6O866qTq9/aqHlwjt/y4o5q/jx88WhFiUsqSittGy6kbiYyxGx/srR3xx31mAAzrnhdKY9b93N7aQ2CaFRzIo/N/9q1HsisgiYKiJXA9uAC+vqxBevjDoTqqrqY8BjNZzfBIRoi7VpnHfbb1g8Y4VlykGdfeOZLJ31M9vX7UREuOu1m9iwdDObft7K9rU7OLCzKbmK/YvbrXVWJQklTmefUIsQMlSVfdk5oRajTqJjo0K2qveXu1xtek9VDwCjfe3HhGTXwOBTB3Drc9fw72teCLUoJLVJ5OZnrqa0qIxpz3zFoFH96DuiF6ddcRIiQkV5Jc/fOpn/vRzcjG21UVleybeTxzHmpqmhFuUwIiIycTg6hlqMkLFu8SZW/mDtdAM7N+0hb29BrZuaAcVi5jejmGthzB9OZcmsFXw35YeQyjF4dH8qK6qIiY/msnt/dcA/uLKIiHRyw1O/x+aw89Ur31giAVN8svUyidntHVAtR8TaSdsDRdcBnXltxeP8b/J3lJdUsHXNDuZOqzlUPVTc/84tIVHKJlF+mNF1QJeQKuaux3Thnrdvq/fxLjI6klufu4YeQzJ4+oaXQxKmGxHlJCo2itQOKVz4pyvYuftxPBGp1qC09FOKI0YQFzeh/sbNkIhIJxGRTi66wxNmUJBThM1uY8vqbLau2RFi6eD0y08g87QB9TcMBKqWS5RvFHMdpHZsFbKxRYR2GW0aZHMbe/VoXFVunr6h1jgevxIR5eS2F65j5Phh7Nq0h4z+nZn9wQLs9mQiI46jvCK0TxtHUuUKz+xsgSAhJY67X/0jleVVvP3PaXzw1JchkyUuOZY//vOykI0PGFNGODHq0pE4nHbWLdpIQU4hhTlFFBwopOBAEYUHCinIKQpI6Gu7rmncMemPDD614SuI31x3GiIw443vWb0gsCWxKsoqOeXi44mIiqD7oAwATr30BABiYs63nGJ2u/NCLYKl8PgN2/nDQxcy/4vF7NiwJyRyXPfIJaFLYOTFmDLCCLvdzikXj+SUi0fWeF1VKSkooeBAEQd25rDyh3XMemcOW1Zub9K41/9nQqOUMnhW2r+57nSiYqMCrpi7DuxCRFTNkVpxsZcSFTmCouJ3KSx6JqBy+IrD0SPUIliSgv1FFOWFxoumTadWjBg3JCRjH0IBi5kyTD7mJiAixCbG0q5rGv1P6MMld5/LpOX/5j+zH+I4HwtypnVpTbdB6Ty78J/8efKN/N/nExk2dnCTZTtmVD/OusZn75wGE58cyyUTx9fZxuFIJyH+dkTiAiaHL4gkkpjwADHRZ4VUDquSvWE3+fsLG3RPavtkAK762wVMnHw9ADabcOK5Q0nve7j3i81uIzouCmekk/vevIn23TypdZ0RDv780rUkpIT27wMIv3zMhoYhIgw4sQ8DTuzD1jXZfPrMV0x/7bujfKJPuWQkyW0S6X9Cb07y1pLrNbS73+RIbZ/CHZOuZ9z1ZzDv44V8/uIMCnP8k/ktY0BnrnjgQk48/7h624rYCPX3f1LivcTFXhlSGaxMdLxn0/asq07hx6+WEp8Uy+JZK4mIctKpZzsy+ndi65odh5L1j5lwErc8NYHykgqi4qKw220MGzOIvH0FdOiWxo4NuykrrSA+KZa4pBii46IoKSxj5fx1tO6Ywj+m/Zl1izfTZ1g30jqnhnTuB7GaKUPUgvGzmZmZmpWVVX/DMCFndy7zP82iKK+YhFbxdOnbkb4jegbNmV5VuWno3axfshmbTXD7+NjWvntbdm7YfdT5IacP5LGv7/epj4qKZezZN7ZB8vqTCOdgUlu9hd0euo1cq6Oq5OzJp1XbpEPls3L35OOMdByWO2bLqmxsDhsdurfFHqLQ6SMRkcVNLcARn9hRM4+7xae238+Y2OTxfMGsmINASttkxv3x9JCNLyL8fdrdfPPWHE697ATe+Nv7DD51AF+9Oouf56yp8Z5rH7ucs28aQ1FeMe8+8jGfv/D1oWvLZv1M7p48ktOS6h3b6RyA03kMlZXL/TWdBpGS/F+jlOtBRGjVNunQe6g5c116v2YaoBNkM4UvWONrzxBwWndsxaX3jCetS2v+8trNnH7Fydz45FWkeP8hj2TomEFExUSS2j6Fi+46G6c3q9rl91/AtPw3SWrjWyCAiJ0IZ4j8UwGbLSlkYxvCA0+Aifp0BAuzYm7BdB+cwZ9euYEHzn70kHlDROg+OP2wdm3T2zAt93UKDhSS2qHhq8/kpP/DZkuisOh5PKUhA42DCGd/IiIysdutYcM0WByLFXwxK+YWzvCzhvD7h3/NU3XTf//A81mPkzHg8CodEVERjVLKACKRJCXeR6uUl5okqy9ERAylbdps0tp8RVLiQwEfz9A8sNqK2ShmA2OuPpW0Lq3p1LsD59w0JmDjxESPIyry5ID1D1BZuQqH3fOlYvX8wwaL4KurnHGXMwST5DaJPPvTP4OSAMlmax3Q/lUrKC2bTkz0b+pvbDAAYHJlGCxKUuvgZPWKijqZktIP/d9v5MmeYBZbPBHOfn7v39DMsZjbsC8VTCYD44C9qtq/huvn4CnA6gaqgNtVdZ732hjgacAOvKKqj/pRdkMYEhN9HmVlcygp/aBR9zsc3YiJHo/DkY7LtZ3IiBNQKoiMOLbFpvQ0NBH1vZ5fsPBlxfw68CzwZi3XZwGfectJDQSmAr3FU8PnOeB0IBtYJCKfqerqpottCFdEbKQkP4VqKaVlXzTgThtJiQ8SG/M7bDZTMNfgZ8Jtxayqc0QkvY7r1eN8Y/nVRD4M2OAttYKIvAecAxjF3MLxKOd/UVCYgcu1g7Ly73C76yqP5SAl+WliY86ro43B0ASspZf9Y2MWkfHAP4E2wMFdlw5A9TRr2cDwOvq4DrgOoHPnzv4Qy2BhbLYkkhLvBUDVhdt9gMqq9RQXv01J6bRqLYVWKc8TE/3bkMhpaBmI21q2DL8oZlX9BE9l2JPw2JtPwxNQc1TTOvqYBEwCT64Mf8hlCA9E7NjtbbDb2xAZMYKY6PG43AcQiSAqciQ2W1qoRTQ0ZxTLBZj41SvDa/boJiKpeFbInapd7gjs9Od4huaHiI3o6DNCLYahBSEEN3jEF5ocYCIi3cXryS8iQ4AI4ACwCOghIhkiEgFcAnzW1PEMBoPB76j6dgQJX9zlpgCnAKkikg08CDgBVPVF4HzgShGpBEqBi9WTS7RKRG4GvsbjLjdZVVcFZBYGg8HQFCy2YvbFK+PSeq4/BjxWy7UvgdBVeTQYDIb68LON2esqnAXsUNVxIpICvA+kA1uAi1S1LjckkyvDYDAYxO326fCR24Dqic4nArNUtQeeuI+J9XVgFLPBYGjh+Ghf9sHcISId8bgMv1Lt9DnAG973bwDn1tePyZVhMBhaNkpDbMypIlK97t0kr6vvQZ4C/gLEVzuXpqq7AFR1l4i0qW8QSyrmxYsX7xeRrTVcSgX2B1ueAGDmYT2ay1xa2jy61N/EB3y3Me+vreafiBzMKbRYRE5pijiWVMyqWmNuSBHJCkYhxEBj5mE9mstczDwaOZ5/vDJGAmeLyFlAFJAgIm8De0SknXe13A7YW19HxsZsMBgMfrAxq+o9qtpRVdPxxG18q6qX44nfmOBtNgH4tD5xLLliNhgMhqChCq6AxmQ/CkwVkauBbcCF9d0Qbop5Uv1NwgIzD+vRXOZi5tEY/BxgoqrfA9973x8ARjfkflGLRbwYDAZDMEmMaqvHd7zCp7bTNz6xOBi273BbMRsMBoN/UcDU/DMYDAYroaDWyvsZcK8MEekkIt+JyBoRWSUit3nPp4jITBFZ731NrnbPPSKyQUTWiciZ1c4fKyI/e6/9t1pWu0gRed97fmH1iisiMsE7xnoRmUAjEZEoEflJRJZ75/H3cJzHEXOyi8hSEfkiXOciIlu84y876PgfjvPw9pckIh+KyFrv/8uIcJuLiPTy/i4OHgUicrul56F4Nv98OYKFqgb0ANoBQ7zv44FfgL7A48BE7/mJwGPe932B5UAkkAFsBOzeaz8BI/Ak4f8KGOs9fyPwovf9JcD73vcpwCbva7L3fXIj5yFAnPe9E1gIHBdu8zhiTn8C3gW+8H4Ou7ngSQqTesS5sJuHt883gGu87yOApHCdi7dfO7AbTxCIZeeR4GyjYzre6tMBZDX15+LLEfAVs6ruUtUl3veFeJJ7dKD2+PFzgPdUtVxVNwMbgGHiccxOUNUF6vktvHnEPQf7+hAY7f12PROYqao56snmNBMY08h5qP5a39DpPTTc5nEQaVhMv6XnUgNhNw8RSQBOAl4FUNUKVc0Lx7lUYzSwUVW3Wn4e6p9cGf4iqAEm3keOwXhWm4fFj+OpFwg11wrs4D2yazh/2D2qWgXkA63q6Kux8ttFZBmeyJ2ZqhqW8/DyFJ6Y/urPZ+E4FwVmiMhi8dSNDNd5dAX2Aa+Jx7z0iojEhulcDnIJMMX73sLz8FEpN0fFLCJxwEfA7apaUFfTGs5pHecbe0+DUVWXqg7CUyZrmIj0r6O5Zech1WL6fb2lEXIFZS7ASFUdAowFbhJP3cnasPI8HMAQ4AVVHQwUU3d6SCvPBfFULTob+KC+po2Qyb/zUMDt9u0IEkFRzCLixKOU31HVj72n93gfV5DD48drqxWY7X1/5PnD7hERB5AI5NTRV5PwPmJ+j+cxKRzncTCmfwvwHnCqVIvpD6e5qOpO7+te4BNgWDjOw9tftvcpDDyP6EPCdC7g+aJcoqp7vJ+tPY+WtmL22n5eBdao6n+qXaotfvwz4BLvzmsG0AP4yfv4Uygix3n7vPKIew72dQGeGHXFU9bqDBFJ9u4Cn+E915h5tBaRJO/7aDyVwNeG2zygUTH9lpyLiMSKSPzB996+VobbPABUdTewXUR6eU+NBlaH41y8XMqvZowjx7bYPLRFemWc4Jk5K4Bl3uMsPDahWcB672tKtXvuw7M7uw7vTqz3fCaef7yNwLP8GrkYheeRaQOendyu1e75g/f8BuCqJsxjILDUO4+VwAPe82E1jxrmdQq/emWE1Vzw2GWXe49VwH3hOI9q/Q3CU5JoBTANj2dB2M0FiMFTkDmx2jnLziPBnqpntrrWp4MgeWWYkGyDwdCiSXS01hEJ5/rU9uvcV0xItsFgMAQFiy1QjWI2GAwtG9Wgelz4glHMBoPBYFbMBoPBYCUUdblCLcRhGMVsMBhaNopJ+2kwGAyWw2JpP41iNhgMLRoF1KyYDQaDwUKomhWzwWAwWA2rbf6ZyD+DwdCiEZHpQKqPzferqr/zhx+FUcwGg8FgMYKaKN9gMBgM9WMUs8FgMFgMo5gNBoPBYhjFbDAYDBbDKGaDwWCwGP8PB1C7eYyiiH8AAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Result plotting\n",
    "province_20_100.plot(column='pop_km2', legend=True, cmap='viridis');"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Congratulation! Now we have analyzed the shapefile data for first time in Python and plot the result perfectly. Isn't it interesting ?? \n",
    "\n",
    "Anyway, it's not yet enough. Let's learn how to export our result as a shapefile."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 1.c. Exporting Shapefile and GeoJSON"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this section, we will learn how to write and export our result from Python."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's first export the result we analyzed above to a shapefile and a GeoJSON file. When exporting, make sure it's a geopandas dataframe with a correct projection. Because we have defined projection already, so we only just export it using `.to_file()`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'EPSG:32648'"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Confirm the crs of result that we want to export\n",
    "province_20_100.crs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Drop column in khmer langugage to avoid error due to unicode\n",
    "province_20_100 = province_20_100.drop(['province_k'], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Export result as a shapefile\n",
    "outfp = 'result/province_20_100.shp'\n",
    "province_20_100.to_file(outfp, driver='Shapefile') # sometimes, you don't need to write driver='Shapefile'."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Export result as a GeoJSON\n",
    "outfp = 'result/province_20_100.json'\n",
    "province_20_100.to_file(outfp, driver='GeoJSON')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "➡ We finally exported our result into shapefile and geojson file. So what's the difference? How about checking the font within column 'province_k' and also the number of files created in result folder?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2. Map Projection"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Map projection** is a concept of tranforming points from three-dimensional Earth's surface (3D) into plane surface (2D). Whereas, a **coordinate reference system (CRS)** defines how the two-dimensional map relates to real places on the earth, and it is a very important information for analyzing a geodataframe in Python. Deciding the type of map projection and which CRS to use depends on the regional extent of the area you want to work in and on the analysis you want to do.\n",
    "\n",
    "When working on real data, sometimes you might have problem with CRS difference (i.e. one might have coordinates in meter, while the other in decimal degrees). In this case, CRS can be reprojected easily in Python to make all coordinates compatible. After all layers have the same CRS, you will be able to analyze the spatial relationship between layers correctly, for example, when making a clip, union, interection, difference, or other type of analysis.\n",
    "\n",
    "\n",
    "You can find a lot of information and lists of available coordinate reference systems from:\n",
    "\n",
    "* [www.arcgis.com](https://www.arcgis.com/apps/MapJournal/index.html?appid=31484c80dba54a058369dfb8e9ced549)\n",
    "* www.spatialreference.org\n",
    "* www.proj4.org\n",
    "* www.mapref.org"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In analysis in Python or GIS applications, geospatial data (i.e. vector or raster files) should always contain information about coordinate reference system. As for shapefile, this information can be found in `.prj` -file, whereas other type of data such as GeoJSON or Raster files, the projection information is already stored in its metadata (of course if the files is properly projected). \n",
    "\n",
    "When using Geopandas to read the data into `GeoDataFrame`, the information about projection is stored in `.crs` attribute of the GeoDataFrame. \n",
    "\n",
    "- Now, let's work on projection of provincial census data and start by checking the `.crs`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import necessary modules\n",
    "import geopandas as gpd\n",
    "\n",
    "# Set filepath\n",
    "fp = \"data/provisional_census2019/provisional_census2019.shp\"\n",
    "\n",
    "# Read file using gpd.read_file()\n",
    "data = gpd.read_file(fp)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Check coordinate reference system (CRS)**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'init': 'epsg:32648'}"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check the coordinate reference system\n",
    "data.crs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(data.crs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is how data's crs is stored in GeoDataFrames with the class type `pyproj` which is a cartographic projections and coordinate transformations library. As you can see, the crs code is `EPSG:32648` which belongs to the WGS 84 /UTM zone 48N coordinate system (i.e. coordinates are in metre both East and North). The EPSG stands for (*European Petroleum Survey Group*) and tells us the code about the coordinate system of dataset."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Re-project coordinate reference system**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "20    POLYGON ((569781.983 1358558.625, 570417.373 1...\n",
       "21    POLYGON ((644221.694 1481668.343, 644419.819 1...\n",
       "22    POLYGON ((663909.945 1476792.235, 664134.383 1...\n",
       "23    POLYGON ((773959.354 1625122.155, 774046.041 1...\n",
       "24    POLYGON ((666331.270 1613878.300, 666441.020 1...\n",
       "Name: geometry, dtype: geometry"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['geometry'].tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\a9418\\AppData\\Roaming\\Python\\Python37\\site-packages\\pyproj\\crs\\crs.py:68: FutureWarning: '+init=<authority>:<code>' syntax is deprecated. '<authority>:<code>' is the preferred initialization method. When making the change, be mindful of axis order changes: https://pyproj4.github.io/pyproj/stable/gotchas.html#axis-order-changes-in-proj-6\n",
      "  return _prepare_from_string(\" \".join(pjargs))\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "20    POLYGON ((105.64171 12.28868, 105.64754 12.285...\n",
       "21    POLYGON ((106.33200 13.39918, 106.33383 13.399...\n",
       "22    POLYGON ((106.51352 13.35408, 106.51559 13.353...\n",
       "23    POLYGON ((107.54387 14.68585, 107.54467 14.685...\n",
       "24    POLYGON ((106.54411 14.59302, 106.54513 14.591...\n",
       "Name: geometry, dtype: geometry"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Let's make a copy of our data\n",
    "orig_crs = data.copy().drop(['province_k'], axis=1)\n",
    "\n",
    "# Re-project from EPSG:32648 to EPSG:4326 \n",
    "new_crs = orig_crs.to_crs(epsg=4326)\n",
    "\n",
    "# Check the new projection\n",
    "new_crs['geometry'].tail()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "So now we have finally changed the projection of our data from [epsg:32648](https://www.spatialreference.org/ref/epsg/32648/) which covers the area in N hemisphere - 102°E to 108°E -  to [epsg:4326](https://www.spatialreference.org/ref/epsg/4326/) which covers the whole world."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Check the difference of projection in plot**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's finding out what happened when we changed the projection from one to another by plotting our data with original crs and new crs."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import necessary module\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 576x360 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Make subplots that are next to each other\n",
    "fig, (ax1, ax2) = plt.subplots(nrows=1, ncols=2, figsize=(8, 5))\n",
    "\n",
    "# Plot the data in WGS84-Cambodia projection\n",
    "orig_crs.plot(ax=ax1, facecolor='green', edgecolor=\"black\");\n",
    "\n",
    "# Add title\n",
    "ax1.set_title(\"WGS 84 / UTM zone 48N - Cambodia\");\n",
    "\n",
    "# Plot the one with WGS84-World projection\n",
    "new_crs.plot(ax=ax2, facecolor='#6495ED', edgecolor=\"black\");\n",
    "\n",
    "# Add title\n",
    "ax2.set_title(\"WGS 84 - World\");\n",
    "\n",
    "# Remove empty white space around the plot\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now, we can see that our new map's latitude and longitude have changed from meter to decimal degree. \n",
    "\n",
    "Let's save the data in new projection as a GeoJSON file:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define output path\n",
    "outfp = 'result/cambodia_census_epsg4326.json'\n",
    "\n",
    "# Save file\n",
    "new_crs.to_file(outfp, driver='GeoJSON')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Practice"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's learn how to calculate the distance from the centre of one province to another province. \n",
    "\n",
    "In this pratical exercise, we will use `cambodia_census_epsg4326.json` -file which we have just saved as our input data. The purpose is to calculate Euclidean distance from the centroid or center point of Phnom Penh to that of all provinces, Cambodia. After that, we find what provinces are near and far from Phnom Penh city.\n",
    "\n",
    "**Hint**: \n",
    "- `.centroid` for calculating the centroid of a polygon\n",
    "- `.distance()` for calculating the distance from one point to another\n",
    "\n",
    "Back to shapely documentation for details about how to use these fuciton: [Shapely](https://shapely.readthedocs.io/en/stable/manual.html)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import necessary module\n",
    "import geopandas as gpd\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "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>ogc_fid</th>\n",
       "      <th>pro_code</th>\n",
       "      <th>provinces</th>\n",
       "      <th>households</th>\n",
       "      <th>males</th>\n",
       "      <th>females</th>\n",
       "      <th>total</th>\n",
       "      <th>house_size</th>\n",
       "      <th>area_km2</th>\n",
       "      <th>pop_km2</th>\n",
       "      <th>reference</th>\n",
       "      <th>geometry</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>Kampong Chhnang</td>\n",
       "      <td>122925.0</td>\n",
       "      <td>251895.0</td>\n",
       "      <td>274037.0</td>\n",
       "      <td>525932.0</td>\n",
       "      <td>4.3</td>\n",
       "      <td>5521</td>\n",
       "      <td>95</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>MULTIPOLYGON (((104.45035 12.51519, 104.44859 ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>Kandal</td>\n",
       "      <td>273111.0</td>\n",
       "      <td>580129.0</td>\n",
       "      <td>615418.0</td>\n",
       "      <td>1195547.0</td>\n",
       "      <td>4.4</td>\n",
       "      <td>3179</td>\n",
       "      <td>376</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>POLYGON ((104.82759 11.88065, 104.82928 11.878...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>12</td>\n",
       "      <td>Phnom Penh</td>\n",
       "      <td>399203.0</td>\n",
       "      <td>1039192.0</td>\n",
       "      <td>1090179.0</td>\n",
       "      <td>2129371.0</td>\n",
       "      <td>5.3</td>\n",
       "      <td>679</td>\n",
       "      <td>3136</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>POLYGON ((104.92232 11.73615, 104.92428 11.736...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ogc_fid  pro_code        provinces  households      males    females  \\\n",
       "0        1         4  Kampong Chhnang    122925.0   251895.0   274037.0   \n",
       "1        2         8           Kandal    273111.0   580129.0   615418.0   \n",
       "2        3        12       Phnom Penh    399203.0  1039192.0  1090179.0   \n",
       "\n",
       "       total  house_size  area_km2  pop_km2  \\\n",
       "0   525932.0         4.3      5521       95   \n",
       "1  1195547.0         4.4      3179      376   \n",
       "2  2129371.0         5.3       679     3136   \n",
       "\n",
       "                                       reference  \\\n",
       "0  Provisional_Population_Census__00.06.2019.pdf   \n",
       "1  Provisional_Population_Census__00.06.2019.pdf   \n",
       "2  Provisional_Population_Census__00.06.2019.pdf   \n",
       "\n",
       "                                            geometry  \n",
       "0  MULTIPOLYGON (((104.45035 12.51519, 104.44859 ...  \n",
       "1  POLYGON ((104.82759 11.88065, 104.82928 11.878...  \n",
       "2  POLYGON ((104.92232 11.73615, 104.92428 11.736...  "
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# import our input data from result folder\n",
    "fp = 'result/cambodia_census_epsg4326.json'\n",
    "df = gpd.read_file(fp)  \n",
    "\n",
    "df.head(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If we take a look at the latitude and longtitude of our coordinate, they are still in decimal degree which is not appropriate format for calculating distance in meter. Therefore, it's better to convert this crs to another type of crs with latitude and longitude in meter. Do you remember what crs should be used for this data?\n",
    "\n",
    "Now, let's work on re-projecting our data:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'init': 'epsg:4326'}"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check the coordinates of our data\n",
    "df.crs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\a9418\\AppData\\Roaming\\Python\\Python37\\site-packages\\pyproj\\crs\\crs.py:68: FutureWarning: '+init=<authority>:<code>' syntax is deprecated. '<authority>:<code>' is the preferred initialization method. When making the change, be mindful of axis order changes: https://pyproj4.github.io/pyproj/stable/gotchas.html#axis-order-changes-in-proj-6\n",
      "  return _prepare_from_string(\" \".join(pjargs))\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'init': 'epsg:32648', 'no_defs': True}"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# change the coordinates to Cambodia coordinate system\n",
    "df_new_crs = df.to_crs(epsg=32648)\n",
    "\n",
    "# check new coordinate system\n",
    "df_new_crs.crs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "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>ogc_fid</th>\n",
       "      <th>pro_code</th>\n",
       "      <th>provinces</th>\n",
       "      <th>households</th>\n",
       "      <th>males</th>\n",
       "      <th>females</th>\n",
       "      <th>total</th>\n",
       "      <th>house_size</th>\n",
       "      <th>area_km2</th>\n",
       "      <th>pop_km2</th>\n",
       "      <th>reference</th>\n",
       "      <th>geometry</th>\n",
       "      <th>centroid</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>Kampong Chhnang</td>\n",
       "      <td>122925.0</td>\n",
       "      <td>251895.0</td>\n",
       "      <td>274037.0</td>\n",
       "      <td>525932.0</td>\n",
       "      <td>4.3</td>\n",
       "      <td>5521</td>\n",
       "      <td>95</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>MULTIPOLYGON (((440280.561 1383585.909, 440090...</td>\n",
       "      <td>POINT (452120.014 1344277.437)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>Kandal</td>\n",
       "      <td>273111.0</td>\n",
       "      <td>580129.0</td>\n",
       "      <td>615418.0</td>\n",
       "      <td>1195547.0</td>\n",
       "      <td>4.4</td>\n",
       "      <td>3179</td>\n",
       "      <td>376</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>POLYGON ((481223.477 1313362.233, 481407.227 1...</td>\n",
       "      <td>POINT (501957.039 1262761.786)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>12</td>\n",
       "      <td>Phnom Penh</td>\n",
       "      <td>399203.0</td>\n",
       "      <td>1039192.0</td>\n",
       "      <td>1090179.0</td>\n",
       "      <td>2129371.0</td>\n",
       "      <td>5.3</td>\n",
       "      <td>679</td>\n",
       "      <td>3136</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>POLYGON ((491536.140 1297379.094, 491748.953 1...</td>\n",
       "      <td>POINT (485297.045 1278224.175)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ogc_fid  pro_code        provinces  households      males    females  \\\n",
       "0        1         4  Kampong Chhnang    122925.0   251895.0   274037.0   \n",
       "1        2         8           Kandal    273111.0   580129.0   615418.0   \n",
       "2        3        12       Phnom Penh    399203.0  1039192.0  1090179.0   \n",
       "\n",
       "       total  house_size  area_km2  pop_km2  \\\n",
       "0   525932.0         4.3      5521       95   \n",
       "1  1195547.0         4.4      3179      376   \n",
       "2  2129371.0         5.3       679     3136   \n",
       "\n",
       "                                       reference  \\\n",
       "0  Provisional_Population_Census__00.06.2019.pdf   \n",
       "1  Provisional_Population_Census__00.06.2019.pdf   \n",
       "2  Provisional_Population_Census__00.06.2019.pdf   \n",
       "\n",
       "                                            geometry  \\\n",
       "0  MULTIPOLYGON (((440280.561 1383585.909, 440090...   \n",
       "1  POLYGON ((481223.477 1313362.233, 481407.227 1...   \n",
       "2  POLYGON ((491536.140 1297379.094, 491748.953 1...   \n",
       "\n",
       "                         centroid  \n",
       "0  POINT (452120.014 1344277.437)  \n",
       "1  POINT (501957.039 1262761.786)  \n",
       "2  POINT (485297.045 1278224.175)  "
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Let's create a column for storing the centroid result\n",
    "df_new_crs['centroid'] = None\n",
    "\n",
    "# calculate the centroid \n",
    "centroid = df_new_crs.centroid\n",
    "\n",
    "# add centroid result to the centroid column\n",
    "df_new_crs['centroid'] = centroid\n",
    "\n",
    "# Let's check our result\n",
    "df_new_crs.head(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's make an overview plot to clarify what we will do next"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 864x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Make subplots that are next to each other\n",
    "fig, ax = plt.subplots(figsize=(12, 8))\n",
    "\n",
    "# Plot the geometry and the centroid\n",
    "df_new_crs['geometry'].plot(ax=ax, facecolor = 'grey', edgecolor=\"black\")\n",
    "\n",
    "# Add label name of each polygon\n",
    "for i in range(len(df_new_crs)):\n",
    "    ax.text(df_new_crs[\"centroid\"][i].x,\n",
    "            df_new_crs[\"centroid\"][i].y+9000,\n",
    "            df_new_crs[\"provinces\"][i],\n",
    "            horizontalalignment='center',\n",
    "            color='yellow',\n",
    "            fontsize=7)\n",
    "plt.show();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Next, our goal is to calculate the Euclidean distance from the center of Phnom Penh to all provinces. To do that, we need to firstly create a centroid of Phnom Penh and then calculate the distance from that centroid to another centroid of polygon representing the boundary of a province. Importantly, we need to make a loop for calculating one by one polygon and store result of each calculation in an list. \n",
    "\n",
    "Let's get started:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Extracting centroid of Phnom Penh\n",
    "pp_centroid = df_new_crs.loc[df_new_crs['provinces'] == 'Phnom Penh']\n",
    "\n",
    "# Remove the row of Phnom Penh from dataframe because we don't want to calculate its own distance (of course it's 0.0.)\n",
    "df_new_crs.drop(df_new_crs.index[df_new_crs['provinces'] == 'Phnom Penh'], inplace = True)\n",
    "df_new_crs = df_new_crs.reset_index()  # reset index of data frame"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Create a loop calculation**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a list for stroing result\n",
    "distance = []\n",
    "\n",
    "# Create a loop to calculate each row of dataframe\n",
    "for i in range(len(df_new_crs)):\n",
    "    \n",
    "    # calculate distance from phnom penh to another province\n",
    "    distance_from_pp = pp_centroid['centroid'].values[0].distance(df_new_crs['centroid'][i])\n",
    "    \n",
    "    # convert distance from meter to kilometer\n",
    "    distance_in_km = distance_from_pp/1000\n",
    "    \n",
    "    # store each result in the list\n",
    "    distance.append(distance_in_km)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "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>index</th>\n",
       "      <th>ogc_fid</th>\n",
       "      <th>pro_code</th>\n",
       "      <th>provinces</th>\n",
       "      <th>households</th>\n",
       "      <th>males</th>\n",
       "      <th>females</th>\n",
       "      <th>total</th>\n",
       "      <th>house_size</th>\n",
       "      <th>area_km2</th>\n",
       "      <th>pop_km2</th>\n",
       "      <th>reference</th>\n",
       "      <th>geometry</th>\n",
       "      <th>centroid</th>\n",
       "      <th>distance</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>Kampong Chhnang</td>\n",
       "      <td>122925.0</td>\n",
       "      <td>251895.0</td>\n",
       "      <td>274037.0</td>\n",
       "      <td>525932.0</td>\n",
       "      <td>4.3</td>\n",
       "      <td>5521</td>\n",
       "      <td>95</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>MULTIPOLYGON (((440280.561 1383585.909, 440090...</td>\n",
       "      <td>POINT (452120.014 1344277.437)</td>\n",
       "      <td>73.917175</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>Kandal</td>\n",
       "      <td>273111.0</td>\n",
       "      <td>580129.0</td>\n",
       "      <td>615418.0</td>\n",
       "      <td>1195547.0</td>\n",
       "      <td>4.4</td>\n",
       "      <td>3179</td>\n",
       "      <td>376</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>POLYGON ((481223.477 1313362.233, 481407.227 1...</td>\n",
       "      <td>POINT (501957.039 1262761.786)</td>\n",
       "      <td>22.729735</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>14</td>\n",
       "      <td>Prey Veng</td>\n",
       "      <td>227008.0</td>\n",
       "      <td>501346.0</td>\n",
       "      <td>556082.0</td>\n",
       "      <td>1057428.0</td>\n",
       "      <td>4.7</td>\n",
       "      <td>4883</td>\n",
       "      <td>217</td>\n",
       "      <td>Provisional_Population_Census__00.06.2019.pdf</td>\n",
       "      <td>POLYGON ((536011.301 1311635.984, 536169.301 1...</td>\n",
       "      <td>POINT (546308.957 1259850.296)</td>\n",
       "      <td>63.718544</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   index  ogc_fid  pro_code        provinces  households     males   females  \\\n",
       "0      0        1         4  Kampong Chhnang    122925.0  251895.0  274037.0   \n",
       "1      1        2         8           Kandal    273111.0  580129.0  615418.0   \n",
       "2      3        4        14        Prey Veng    227008.0  501346.0  556082.0   \n",
       "\n",
       "       total  house_size  area_km2  pop_km2  \\\n",
       "0   525932.0         4.3      5521       95   \n",
       "1  1195547.0         4.4      3179      376   \n",
       "2  1057428.0         4.7      4883      217   \n",
       "\n",
       "                                       reference  \\\n",
       "0  Provisional_Population_Census__00.06.2019.pdf   \n",
       "1  Provisional_Population_Census__00.06.2019.pdf   \n",
       "2  Provisional_Population_Census__00.06.2019.pdf   \n",
       "\n",
       "                                            geometry  \\\n",
       "0  MULTIPOLYGON (((440280.561 1383585.909, 440090...   \n",
       "1  POLYGON ((481223.477 1313362.233, 481407.227 1...   \n",
       "2  POLYGON ((536011.301 1311635.984, 536169.301 1...   \n",
       "\n",
       "                         centroid   distance  \n",
       "0  POINT (452120.014 1344277.437)  73.917175  \n",
       "1  POINT (501957.039 1262761.786)  22.729735  \n",
       "2  POINT (546308.957 1259850.296)  63.718544  "
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Let's create a column and store the distance result\n",
    "df_new_crs['distance'] = distance\n",
    "\n",
    "# Let's check our result\n",
    "df_new_crs.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "22.729735303077444 km\n",
      "345.3761963080783 km\n"
     ]
    }
   ],
   "source": [
    "# minimum distance\n",
    "min_distance = df_new_crs['distance'].min()\n",
    "# maximum distance\n",
    "max_distance = df_new_crs['distance'].max()\n",
    "\n",
    "print(min_distance, 'km')\n",
    "print(max_distance, 'km')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Nearest and furthest provinces from Phnom Penh**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "# get the name of province of max and min distance\n",
    "min_province = df_new_crs['provinces'].loc[df_new_crs['distance'].idxmin()]\n",
    "max_province = df_new_crs['provinces'].loc[df_new_crs['distance'].idxmax()]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "*Note: check how to use [.idxmin()](https://www.kite.com/python/answers/how-to-find-the-max-value-of-a-pandas-dataframe-column-in-python) or [idxmax()](https://www.kite.com/python/answers/how-to-find-the-max-value-of-a-pandas-dataframe-column-in-python)* "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The nearest province to Phnom Penh is Kandal Province with distance of 22.730 km.\n",
      "The furthest province to Phnom Penh is Ratanak Kiri Province with distance of 345.376 km.\n"
     ]
    }
   ],
   "source": [
    "print('The nearest province to Phnom Penh is', min_province, 'Province with distance of {dist:.3f} km.'.format(dist=min_distance)) \n",
    "print('The furthest province to Phnom Penh is', max_province, 'Province with distance of {dist:.3f} km.'.format(dist=max_distance))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Others"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Reading KML files**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The way to read KML files is quite similar to how we read a Shapefile with GeoPandas. The only difference is that we have to enable the KML-driver as it's not enabled by default. KML file formats can be read by using the Python library `Geopandas` and `Fiona`. First method can done with this method: [Read a KML File into a GeoPandas DataFrame](https://docs.astraea.earth/hc/en-us/articles/360043923831-Read-a-KML-File-into-a-GeoPandas-DataFrame)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'AeronavFAA': 'r',\n",
       " 'ARCGEN': 'r',\n",
       " 'BNA': 'raw',\n",
       " 'DXF': 'raw',\n",
       " 'CSV': 'raw',\n",
       " 'OpenFileGDB': 'r',\n",
       " 'ESRI Shapefile': 'raw',\n",
       " 'GeoJSON': 'rw',\n",
       " 'GPKG': 'rw',\n",
       " 'GML': 'raw',\n",
       " 'GPX': 'raw',\n",
       " 'GPSTrackMaker': 'raw',\n",
       " 'Idrisi': 'r',\n",
       " 'MapInfo File': 'raw',\n",
       " 'DGN': 'raw',\n",
       " 'PCIDSK': 'r',\n",
       " 'S57': 'r',\n",
       " 'SEGY': 'r',\n",
       " 'SUA': 'r'}"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import geopandas as gpd\n",
    "gpd.io.file.fiona.drvsupport.supported_drivers"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Enable the KML-driver by passing the fiona's supported driver of KML"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "gpd.io.file.fiona.drvsupport.supported_drivers['KML'] = 'rw'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now, we have enabled the KML-driver, so let's read the kml file:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "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>Name</th>\n",
       "      <th>Description</th>\n",
       "      <th>geometry</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td>MULTIPOLYGON (((104.45035 12.51519, 104.44859 ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td>MULTIPOLYGON (((104.82759 11.88065, 104.82928 ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td>MULTIPOLYGON (((104.92232 11.73615, 104.92428 ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td>MULTIPOLYGON (((105.33064 11.86490, 105.33209 ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td>MULTIPOLYGON (((105.80715 11.59858, 105.80925 ...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Name Description                                           geometry\n",
       "0                   MULTIPOLYGON (((104.45035 12.51519, 104.44859 ...\n",
       "1                   MULTIPOLYGON (((104.82759 11.88065, 104.82928 ...\n",
       "2                   MULTIPOLYGON (((104.92232 11.73615, 104.92428 ...\n",
       "3                   MULTIPOLYGON (((105.33064 11.86490, 105.33209 ...\n",
       "4                   MULTIPOLYGON (((105.80715 11.59858, 105.80925 ..."
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_kml = gpd.read_file('data/provisional_census2019/provisional_census2019.kml', driver='KML')\n",
    "data_kml.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "geopandas.geodataframe.GeoDataFrame"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(data_kml)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "data_kml.plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "From the geodataframe that we read from kml-file, we can see clearly that there are only 3 columns (i.e. Name, Description, and geometry) while other columns are missing. This is the disadvantage of reading KML-file in Python because KML-files mostly contain unsupported data structures, nested folder, etc., hence, I do not recommend to read data from KML. It's better to manually convert the KML file to other formart such as Shapefile or GeoJSON file using GIS application. So when we read shapefile or geojson, it will return a correct GeoDataFrame."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}