{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data reclassification\n",
    "\n",
    "Reclassifying data based on specific criteria is a common task when doing GIS analysis. The purpose of this lesson is to see how we can reclassify values based on some criteria which can be whatever, such as:\n",
    "\n",
    "```\n",
    "1. if travel time to my work is less than 30 minutes\n",
    "\n",
    "    AND\n",
    "\n",
    "    2. the rent of the apartment is less than 1000 € per month\n",
    "\n",
    "    ------------------------------------------------------\n",
    "\n",
    "    IF TRUE: ==> I go to view it and try to rent the apartment\n",
    "    IF NOT TRUE: ==> I continue looking for something else\n",
    "```\n",
    "\n",
    "In this tutorial, we will:\n",
    "\n",
    "1. Use classification schemes from the PySAL [mapclassify library](https://pysal.org/mapclassify/) to classify travel times into multiple classes.\n",
    "\n",
    "2. Create a custom classifier to classify travel times and distances in order to find out good locations to buy an apartment with these conditions:\n",
    "   - good public transport accessibility to city center\n",
    "   - bit further away from city center where the prices are presumably lower\n",
    "\n",
    "## Input data\n",
    "\n",
    "We will use [Travel Time Matrix data from Helsinki](https://blogs.helsinki.fi/accessibility/helsinki-region-travel-time-matrix/) that contains travel time and distance information for \n",
    "routes between all 250 m x 250 m grid cell centroids (n = 13231) in the Capital Region of Helsinki by walking, cycling, public transportation and car.\n",
    "\n",
    "In this tutorial, we will use the geojson file generated in the previous section:\n",
    "`\"data/TravelTimes_to_5975375_RailwayStation_Helsinki.geojson\"`\n",
    "\n",
    "Alternatively, you can re-download [L4 data](https://github.com/AutoGIS/data/raw/master/L4_data.zip) and use `\"data/Travel_times_to_5975375_RailwayStation.shp\"` as input file in here.\n",
    "\n",
    "\n",
    "\n",
    "## Common classifiers\n",
    "\n",
    "### Classification schemes for thematic maps\n",
    "\n",
    "\n",
    "[PySAL](http://pysal.readthedocs.io/en/latest) -module is an extensive Python library for spatial analysis. It also includes all of the most common data classifiers that are used commonly e.g. when visualizing data. Available map classifiers in [pysal's mapclassify -module](https://pysal.readthedocs.io/en/v1.11.0/library/esda/mapclassify.html):\n",
    "\n",
    " - Box_Plot\n",
    " - Equal_Interval\n",
    " - Fisher_Jenks\n",
    " - Fisher_Jenks_Sampled\n",
    " - HeadTail_Breaks\n",
    " - Jenks_Caspall\n",
    " - Jenks_Caspall_Forced\n",
    " - Jenks_Caspall_Sampled\n",
    " - Max_P_Classifier\n",
    " - Maximum_Breaks\n",
    " - Natural_Breaks\n",
    " - Quantiles\n",
    " - Percentiles\n",
    " - Std_Mean\n",
    " - User_Defined\n",
    "\n",
    "- First, we need to read our Travel Time data from Helsinki:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   car_m_d  car_m_t  car_r_d  car_r_t  from_id  pt_m_d  pt_m_t  pt_m_tt  \\\n",
      "0    29476       41    29483       46  5876274   29990      76       95   \n",
      "1    29456       41    29462       46  5876275   29866      74       95   \n",
      "\n",
      "   pt_r_d  pt_r_t  pt_r_tt    to_id  walk_d  walk_t    GML_ID   NAMEFIN  \\\n",
      "0   24984      77       99  5975375   25532     365  27517366  Helsinki   \n",
      "1   24860      75       93  5975375   25408     363  27517366  Helsinki   \n",
      "\n",
      "       NAMESWE NATCODE                                           geometry  \n",
      "0  Helsingfors     091  POLYGON ((402250.000 6685750.000, 402024.224 6...  \n",
      "1  Helsingfors     091  POLYGON ((402367.890 6685750.000, 402250.000 6...  \n"
     ]
    }
   ],
   "source": [
    "import geopandas as gpd\n",
    "\n",
    "fp = \"data/TravelTimes_to_5975375_RailwayStation_Helsinki.geojson\"\n",
    "\n",
    "# Read the GeoJSON file similarly as Shapefile\n",
    "acc = gpd.read_file(fp)\n",
    "\n",
    "# Let's see what we have\n",
    "print(acc.head(2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As we can see, there are plenty of different variables (see [from here the description](http://blogs.helsinki.fi/accessibility/helsinki-region-travel-time-matrix-2015) for all attributes) but what we are interested in are columns called `pt_r_tt` which is telling the time in minutes that it takes to reach city center from different parts of the city, and `walk_d` that tells the network distance by roads to reach city center from different parts of the city (almost equal to Euclidian distance).\n",
    "\n",
    "**The NoData values are presented with value -1**. \n",
    "\n",
    "- Thus we need to remove the No Data values first.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Include only data that is above or equal to 0\n",
    "acc = acc.loc[acc['pt_r_tt'] >=0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- Let's plot the data and see how it looks like\n",
    "- `cmap` parameter defines the color map. Read more about [choosing colormaps in matplotlib](https://matplotlib.org/3.1.0/tutorials/colors/colormaps.html)\n",
    "- `scheme` option scales the colors according to a classification scheme (requires `mapclassify` module to be installed):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Plot using 9 classes and classify the values using \"Natural Breaks\" classification\n",
    "acc.plot(column=\"pt_r_tt\", scheme=\"Natural_Breaks\", k=9, cmap=\"RdYlBu\", linewidth=0, legend=True)\n",
    "\n",
    "# Use tight layout\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As we can see from this map, the travel times are lower in the south where the city center is located but there are some areas of \"good\" accessibility also in some other areas (where the color is red).\n",
    "\n",
    "- Let's also make a plot about walking distances:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot walking distance\n",
    "acc.plot(column=\"walk_d\", scheme=\"Natural_Breaks\", k=9, cmap=\"RdYlBu\", linewidth=0, legend=True)\n",
    "\n",
    "# Use tight layour\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Okay, from here we can see that the walking distances (along road network) reminds more or less Euclidian distances. \n",
    "\n",
    "### Applying classifiers to data\n",
    "\n",
    "As mentioned, the `scheme` option defines the classification scheme using `pysal/mapclassify`. Let's have a closer look at how these classifiers work."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "import mapclassify"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- Natural Breaks"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "               NaturalBreaks               \n",
       " \n",
       " Lower            Upper               Count\n",
       "===========================================\n",
       "          x[i] <=  22.000               290\n",
       " 22.000 < x[i] <=  31.000               586\n",
       " 31.000 < x[i] <=  38.000               789\n",
       " 38.000 < x[i] <=  45.000               820\n",
       " 45.000 < x[i] <=  53.000               480\n",
       " 53.000 < x[i] <=  63.000               356\n",
       " 63.000 < x[i] <=  77.000               255\n",
       " 77.000 < x[i] <=  95.000               177\n",
       " 95.000 < x[i] <= 155.000                54"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mapclassify.NaturalBreaks(y=acc['pt_r_tt'], k=9)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- Quantiles (default is 5 classes):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "                 Quantiles                 \n",
       " \n",
       " Lower            Upper               Count\n",
       "===========================================\n",
       "          x[i] <=  30.000               792\n",
       " 30.000 < x[i] <=  37.000               779\n",
       " 37.000 < x[i] <=  44.000               821\n",
       " 44.000 < x[i] <=  56.000               685\n",
       " 56.000 < x[i] <= 155.000               730"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mapclassify.Quantiles(y=acc['pt_r_tt'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- It's possible to extract the threshold values into an array:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 21.,  30.,  38.,  45.,  53.,  63.,  76.,  94., 155.])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classifier = mapclassify.NaturalBreaks(y=acc['pt_r_tt'], k=9)\n",
    "classifier.bins"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- Let's apply one of the `Pysal` classifiers into our data and classify the travel times by public transport into 9 classes\n",
    "- The classifier needs to be initialized first with `make()` function that takes the number of desired classes as input parameter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a Natural Breaks classifier\n",
    "classifier = mapclassify.NaturalBreaks.make(k=9)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- Now we can apply that classifier into our data by using `apply` -function"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>pt_r_tt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   pt_r_tt\n",
       "0        8\n",
       "1        7\n",
       "2        8\n",
       "3        8\n",
       "4        8"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Classify the data\n",
    "classifications = acc[['pt_r_tt']].apply(classifier)\n",
    "\n",
    "# Let's see what we have\n",
    "classifications.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.frame.DataFrame"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(classifications)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Okay, so now we have a DataFrame where our input column was classified into 9 different classes (numbers 1-9) based on [Natural Breaks classification](http://wiki-1-1930356585.us-east-1.elb.amazonaws.com/wiki/index.php/Jenks_Natural_Breaks_Classification).\n",
    "\n",
    "- We can also add the classification values directly into a new column in our dataframe:"
   ]
  },
  {
   "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>pt_r_tt</th>\n",
       "      <th>nb_pt_r_tt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>99</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>93</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>146</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>155</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>99</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   pt_r_tt  nb_pt_r_tt\n",
       "0       99           8\n",
       "1       93           7\n",
       "2      146           8\n",
       "3      155           8\n",
       "4       99           8"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Rename the column so that we know that it was classified with natural breaks\n",
    "acc['nb_pt_r_tt'] = acc[['pt_r_tt']].apply(classifier)\n",
    "\n",
    "# Check the original values and classification\n",
    "acc[['pt_r_tt', 'nb_pt_r_tt']].head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Great, now we have those values in our accessibility GeoDataFrame. Let's visualize the results and see how they look."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot\n",
    "acc.plot(column=\"nb_pt_r_tt\", linewidth=0, legend=True)\n",
    "\n",
    "# Use tight layout\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "And here we go, now we have a map where we have used one of the common classifiers to classify our data into 9 classes."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Plotting a histogram\n",
    "\n",
    "A histogram is a graphic representation of the distribution of the data. When classifying the data, it's always good to consider how the data is distributed, and how the classification shceme divides values into different ranges. \n",
    "\n",
    "- plot the histogram using [pandas.DataFrame.plot.hist](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.plot.hist.html)\n",
    "- Number of histogram bins (groups of data) can be controlled using the parameter `bins`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x134e1c160c8>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYkAAAD4CAYAAAAZ1BptAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8li6FKAAAW/UlEQVR4nO3dfbBlVXnn8e/P5l2NLdJo241pNK0Zkhob5oo4JjMKJioYWqc0g2VFdEg6M4MzOuaFRqeiTg1VbUZFrWTQjhjR+NYiSg/qOIiiZdUINogIAqEjHbl2h75GBF8iCj7zx1l3PHSf3ff0y3lp7vdTderstfba9z533T736bX22nunqpAkaZCHTToASdL0MklIkjqZJCRJnUwSkqROJglJUqdDJh3A/jjmmGNq1apVkw5Dkg4q11133XeratkwbQ/qJLFq1Sq2bNky6TAk6aCS5O+Hbet0kySpk0lCktTJJCFJ6mSSkCR1MklIkjqZJCRJnUwSkqROJglJUieThCSp00F9xbX2zqr1nxpYv23DGWOORNLBYuQjiSRLknwtyRWtfHySa5LcnuSjSQ5r9Ye38ta2f9WoY5Mk7dk4ppteDdzSV34zcGFVrQbuBs5p9ecAd1fVrwAXtnaSpAkaaZJIshI4A3hPKwc4Fbi0NbkEeGHbXtvKtP2ntfaSpAkZ9Uji7cCfAj9v5ccA36+q+1t5FljRtlcAdwK0/fe09g+SZF2SLUm2zM3NjTJ2SVr0RpYkkrwA2FlV1/VXD2haQ+z7RUXVxqqaqaqZZcuGuh26JGkfjXJ10zOBM5OcDhwB/BK9kcXSJIe00cJKYHtrPwscB8wmOQR4FPC9EcYnSVrAyEYSVXV+Va2sqlXAWcDnq+plwBeAF7dmZwOXt+3NrUzb//mq2m0kIUkan0lcTHce8NokW+mdc7i41V8MPKbVvxZYP4HYJEl9xnIxXVVdDVzdtr8FnDygzU+Al4wjHknScLwthySpk0lCktTJJCFJ6mSSkCR1MklIkjqZJCRJnUwSkqROJglJUieThCSpk48vlY81ldTJkYQkqZNJQpLUySQhSepkkpAkdTJJSJI6ubpJnbpWPYErn6TFYmQjiSRHJLk2ydeT3JzkTa3+fUnuSHJDe61p9UnyziRbk9yY5KRRxSZJGs4oRxL3AadW1Q+THAp8Ocln2r4/qapLd2n/fGB1ez0duKi9S5ImZGQjier5YSse2l61h0PWAu9vx30FWJpk+ajikyQtbKQnrpMsSXIDsBO4sqquabsuaFNKFyY5vNWtAO7sO3y21UmSJmSkSaKqHqiqNcBK4OQkvw6cD/wq8DTgaOC81jyDvsSuFUnWJdmSZMvc3NyIIpckwZhWN1XV95NcDTyvqt7Squ9L8tfAH7fyLHBc32Erge0DvtZGYCPAzMzMnqavNELe70laHEa5umlZkqVt+0jgOcCt8+cZkgR4IXBTO2Qz8PK2yukU4J6q2jGq+CRJCxvlSGI5cEmSJfSS0aaquiLJ55Msoze9dAPw71v7TwOnA1uBHwOvHGFskqQhjCxJVNWNwIkD6k/taF/AuaOKR5K097wthySpk0lCktTJJCFJ6mSSkCR1MklIkjqZJCRJnUwSkqROJglJUieThCSpk0lCktTJJCFJ6mSSkCR1MklIkjqZJCRJnUwSkqROJglJUieThCSp0yifcX1EkmuTfD3JzUne1OqPT3JNktuTfDTJYa3+8Fbe2vavGlVskqThjHIkcR9walU9FVgDPC/JKcCbgQurajVwN3BOa38OcHdV/QpwYWsnSZqgkSWJ6vlhKx7aXgWcClza6i8BXti217Yybf9pSTKq+CRJCxvpOYkkS5LcAOwErgT+Dvh+Vd3fmswCK9r2CuBOgLb/HuAxA77muiRbkmyZm5sbZfiStOiNNElU1QNVtQZYCZwM/LNBzdr7oFFD7VZRtbGqZqpqZtmyZQcuWEnSbsayuqmqvg9cDZwCLE1ySNu1EtjetmeB4wDa/kcB3xtHfJKkwUa5umlZkqVt+0jgOcAtwBeAF7dmZwOXt+3NrUzb//mq2m0kIUkan0MWbrLPlgOXJFlCLxltqqorknwT+EiS/w58Dbi4tb8Y+ECSrfRGEGeNMDZJ0hBGliSq6kbgxAH136J3fmLX+p8ALxlVPJKkvecV15KkTqOcbtIitGr9pwbWb9twxpgjkXQgOJKQJHUySUiSOpkkJEmdTBKSpE4mCUlSJ5OEJKmTSUKS1MkkIUnqZJKQJHUySUiSOpkkJEmdhkoSSX591IFIkqbPsCOJdyW5Nsl/nH+QkCTpoW+oJFFVvwG8jN7jRbck+VCS3xppZJKkiRv6nERV3Q78V+A84F8D70xya5J/M6h9kuOSfCHJLUluTvLqVv/GJN9JckN7nd53zPlJtia5Lclz9+9HkyTtr6GeJ5HknwOvBM4ArgR+p6quT/J44P8Clw047H7gj1q7RwLXJbmy7buwqt6yy/c4gd4jS38NeDzwuSRPrqoH9uUHkyTtv2FHEn8BXA88tarOrarrAapqO73RxW6qakdfux8AtwAr9vA91gIfqar7quoOYCsDHnMqSRqfYZPE6cCHquqfAJI8LMlRAFX1gYUOTrKK3vOur2lVr0pyY5L3Jnl0q1sB3Nl32CwDkkqSdUm2JNkyNzc3ZPiSpH0xbJL4HHBkX/moVregJI8APg68pqruBS4CngSsAXYAb51vOuDw2q2iamNVzVTVzLJly4YMX5K0L4ZNEkdU1Q/nC237qIUOSnIovQTxwaq6rB17V1U9UFU/B/6KX0wpzdJbPTVvJbB9yPgkSSMwbJL4UZKT5gtJ/gXwT3s6IEmAi4FbquptffXL+5q9CLipbW8GzkpyeJLjgdXAtUPGJ0kagaFWNwGvAT6WZP5/9suBf7vAMc8Efg/4RpIbWt3rgJcmWUNvKmkb8IcAVXVzkk3AN+mtjDrXlU2SNFlDJYmq+mqSXwWeQu/cwa1V9bMFjvkyg88zfHoPx1wAXDBMTJKk0Rt2JAHwNGBVO+bEJFTV+0cSlSRpKgx7Md0H6K1IugGYnwIqwCQhSQ9hw44kZoATqmq3JamaPqvWf2rSIeymK6ZtG84YcySS9sawq5tuAh43ykAkSdNn2JHEMcA3k1wL3DdfWVVnjiQqSdJUGDZJvHGUQUiSptOwS2C/mOSXgdVV9bl236Ylow1NkjRpwz6+9A+AS4F3t6oVwCdHFZQkaToMe+L6XHpXUN8L//8BRMeOKihJ0nQYNkncV1U/nS8kOYQBd2iVJD20DJskvpjkdcCR7dnWHwP+1+jCkiRNg2GTxHpgDvgGvRvyfZqOJ9JJkh46hl3dNP/sh78abTiSpGky7L2b7mDwU+KeeMAjkiRNjb25d9O8I4CXAEcf+HAkSdNkqHMSVfWPfa/vVNXbgVNHHJskacKGnW46qa/4MHoji0cucMxx9G4l/jjg58DGqnpHkqOBj9J7NsU24Her6u72uNN3AKcDPwZeUVXX79VPI0k6oIadbnpr3/b9tD/uCxxzP/BHVXV9kkcC1yW5EngFcFVVbUiynt7KqfOA59N7rvVq4OnARe1dkjQhw65uevbefuGq2gHsaNs/SHILvdt5rAWe1ZpdAlxNL0msBd7fnlnxlSRLkyxvX0eSNAHDTje9dk/7q+ptCxy/CjgRuAZ47Pwf/qrakWT+9h4rgDv7DpttdSYJSZqQvVnd9DRgcyv/DvAlHvxHfaAkjwA+Drymqu7tnXoY3HRA3W7LbpOsA9YBPOEJT1gwcEnSvtubhw6dVFU/AEjyRuBjVfX7ezooyaH0EsQHq+qyVn3X/DRSkuXAzlY/CxzXd/hKYPuuX7OqNgIbAWZmZrx/lCSN0LC35XgC8NO+8k/prU7q1FYrXQzcsst01Gbg7LZ9NnB5X/3L03MKcI/nIyRpsoYdSXwAuDbJJ+hNAb2I3vLWPXkm8HvAN5Lc0OpeB2wANiU5B/g2vQvzoHc/qNOBrfSWwL5y2B9CkjQaw65uuiDJZ4DfbFWvrKqvLXDMlxl8ngHgtAHti95zKyRJU2LY6SaAo4B7q+odwGyS40cUkyRpSgz7+NI30LuW4fxWdSjwN6MKSpI0HYYdSbwIOBP4EUBVbWeB23JIkg5+wyaJn7ZzBgWQ5OGjC0mSNC2GTRKbkrwbWJrkD4DP4QOIJOkhb9jVTW9pz7a+F3gK8GdVdeVII5MkTdyCSSLJEuCzVfUcwMQgSYvIgtNNVfUA8OMkjxpDPJKkKTLsFdc/oXfl9JW0FU4AVfWfRxKVJGkqDJskPtVekqRFZI9JIskTqurbVXXJuALS8FatN29LGq2Fzkl8cn4jycdHHIskacoslCT6b9D3xFEGIkmaPgslierYliQtAguduH5qknvpjSiObNu0clXVL400OknSRO0xSVTVknEFIkmaPnvzPAlJ0iIzsiSR5L1Jdia5qa/ujUm+k+SG9jq9b9/5SbYmuS3Jc0cVlyRpeKMcSbwPeN6A+gurak17fRogyQnAWcCvtWP+Z7tnlCRpgkaWJKrqS8D3hmy+FvhIVd1XVXcAW4GTRxWbJGk4kzgn8aokN7bpqEe3uhXAnX1tZlvdbpKsS7IlyZa5ublRxypJi9q4k8RFwJOANcAO4K2tPgPaDrwuo6o2VtVMVc0sW7ZsNFFKkoAxJ4mququqHqiqn9N7st38lNIscFxf05XA9nHGJkna3ViTRJLlfcUXAfMrnzYDZyU5PMnxwGrg2nHGJkna3bC3Ct9rST4MPAs4Jsks8AbgWUnW0JtK2gb8IUBV3ZxkE/BN4H7g3PawI0nSBI0sSVTVSwdUX7yH9hcAF4wqHi1OXbdT37bhjDFHIh2cvOJaktTJJCFJ6mSSkCR1MklIkjqZJCRJnUa2ukkahquPpOlmkjgIdP0hlaRRc7pJktTJkYQOKk5PSePlSEKS1MkkIUnqZJKQJHUySUiSOpkkJEmdTBKSpE4mCUlSp5EliSTvTbIzyU19dUcnuTLJ7e390a0+Sd6ZZGuSG5OcNKq4JEnDG+XFdO8D/gJ4f1/deuCqqtqQZH0rnwc8n95zrVcDTwcuau9apLwViTQdRvn40i8lWbVL9Vp6z70GuAS4ml6SWAu8v6oK+EqSpUmWV9WOUcU3jfzDKGnajPucxGPn//C392Nb/Qrgzr52s61uN0nWJdmSZMvc3NxIg5WkxW5a7t2UAXU1qGFVbQQ2AszMzAxso8XHUZg0GuMeSdyVZDlAe9/Z6meB4/rarQS2jzk2SdIuxp0kNgNnt+2zgcv76l/eVjmdAtyz2M5HSNI0Gtl0U5IP0ztJfUySWeANwAZgU5JzgG8DL2nNPw2cDmwFfgy8clRxSZKGN8rVTS/t2HXagLYFnDuqWCRJ+8YrriVJnUwSkqROJglJUieThCSpk0lCktTJJCFJ6mSSkCR1MklIkjqZJCRJnUwSkqRO03KrcGmsum4tvm3DGWOORJpuJokJ8NkHkg4WTjdJkjqZJCRJnUwSkqROJglJUqeJnLhOsg34AfAAcH9VzSQ5GvgosArYBvxuVd09ifgkST2THEk8u6rWVNVMK68Hrqqq1cBVrSxJmqBpmm5aC1zSti8BXjjBWCRJTC5JFPB/klyXZF2re2xV7QBo78cOOjDJuiRbkmyZm5sbU7iStDhN6mK6Z1bV9iTHAlcmuXXYA6tqI7ARYGZmpkYVoCRpQkmiqra3951JPgGcDNyVZHlV7UiyHNg5idi0uHm7DunBxp4kkjwceFhV/aBt/zbw34DNwNnAhvZ++bhjO9C8/cZDx55+lyYQPZRNYiTxWOATSea//4eq6n8n+SqwKck5wLeBl0wgNklSn7Eniar6FvDUAfX/CJw27ngkSd28C6w0Zp730MFkmq6TkCRNGZOEJKmT000HgKuYdCA4DaVp5EhCktTJkYQ0Io4w9VBgkpD206iTgdNQmiSThHSQ2tvkZFLRvjBJSIuEIxLtC09cS5I6mSQkSZ1MEpKkTiYJSVInk4QkqZOrm/aCF0dJWmwcSUiSOpkkJEmdpm66KcnzgHcAS4D3VNWGccfgtJIWkwN1kZ3PAX9omqokkWQJ8JfAbwGzwFeTbK6qb042MmnxOZD/WfJq74PXVCUJ4GRga3sONkk+AqwFDniScLQgTd5iTB57+zNPuo+mLUmsAO7sK88CT+9vkGQdsK4Vf5jktn38XscA393HY8dhmuMztn03zfFNTWx5825VUxPbAAcktgE/84FqPyi+Xx724GlLEhlQVw8qVG0ENu73N0q2VNXM/n6dUZnm+Ixt301zfMa2b6Y5Ntj/+KZtddMscFxfeSWwfUKxSNKiN21J4qvA6iTHJzkMOAvYPOGYJGnRmqrppqq6P8mrgM/SWwL73qq6eUTfbr+nrEZsmuMztn03zfEZ276Z5thgP+NLVS3cSpK0KE3bdJMkaYqYJCRJnRZlkkjyvCS3JdmaZP2EYzkuyReS3JLk5iSvbvVHJ7kyye3t/dETjHFJkq8luaKVj09yTYvto22RwaRiW5rk0iS3tj58xrT0XZL/0n6nNyX5cJIjJtV3Sd6bZGeSm/rqBvZTet7ZPh83JjlpQvH9j/Z7vTHJJ5Is7dt3fovvtiTPHXdsffv+OEklOaaVx9p3XbEl+U+tb25O8ud99Xvfb1W1qF70Toj/HfBE4DDg68AJE4xnOXBS234k8LfACcCfA+tb/XrgzROM8bXAh4ArWnkTcFbbfhfwHyYY2yXA77ftw4Cl09B39C4MvQM4sq/PXjGpvgP+FXAScFNf3cB+Ak4HPkPvuqVTgGsmFN9vA4e07Tf3xXdC+9weDhzfPs9Lxhlbqz+O3iKbvweOmUTfdfTbs4HPAYe38rH7029j+9BMywt4BvDZvvL5wPmTjqsvnsvp3bvqNmB5q1sO3DaheFYCVwGnAle0f/zf7fvwPqg/xxzbL7U/xNmlfuJ9xy/uHnA0vVWEVwDPnWTfAat2+WMysJ+AdwMvHdRunPHtsu9FwAfb9oM+s+0P9TPGHRtwKfBUYFtfkhh73w34vW4CnjOg3T7122Kcbhp0648VE4rlQZKsAk4ErgEeW1U7ANr7sRMK6+3AnwI/b+XHAN+vqvtbeZL990RgDvjrNh32niQPZwr6rqq+A7wF+DawA7gHuI7p6Tvo7qdp/Iz8O3r/Q4cpiC/JmcB3qurru+yaeGzAk4HfbNOaX0zytP2JbTEmiQVv/TEJSR4BfBx4TVXdO+l4AJK8ANhZVdf1Vw9oOqn+O4TeUPuiqjoR+BG9aZOJa/P7a+kN6x8PPBx4/oCmE/+3N8A0/Y5J8nrgfuCD81UDmo0tviRHAa8H/mzQ7gF14+67Q4BH05vu+hNgU5Kwj7EtxiQxdbf+SHIovQTxwaq6rFXflWR5278c2DmB0J4JnJlkG/ARelNObweWJpm/EHOS/TcLzFbVNa18Kb2kMQ199xzgjqqaq6qfAZcB/5Lp6Tvo7qep+YwkORt4AfCyanMkTD6+J9FL/l9vn42VwPVJHjcFsdFiuKx6rqU3C3DMvsa2GJPEVN36o2X4i4Fbquptfbs2A2e37bPpnasYq6o6v6pWVtUqev30+ap6GfAF4MWTjK3F9w/AnUme0qpOo3db+Yn3Hb1pplOSHNV+x/OxTUXfNV39tBl4eVupcwpwz/y01Dil9wCy84Azq+rHfbs2A2clOTzJ8cBq4NpxxVVV36iqY6tqVftszNJbfPIPTEfffZLef+hI8mR6Czq+y7722yhPqEzri94KhL+ld3b/9ROO5TfoDfluBG5or9Ppzf1fBdze3o+ecJzP4herm57Y/nFtBT5GW0UxobjWAFta/32S3jB7KvoOeBNwK3AT8AF6q0om0nfAh+mdG/kZvT9q53T1E71pib9sn49vADMTim8rvTn0+c/Fu/rav77Fdxvw/HHHtsv+bfzixPVY+66j3w4D/qb9u7seOHV/+s3bckiSOi3G6SZJ0pBMEpKkTiYJSVInk4QkqZNJQpLUySQhSepkkpAkdfp/W+OSphwyK0kAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Histogram for public transport rush hour travel time\n",
    "acc['pt_r_tt'].plot.hist(bins=50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's also add threshold values on thop of the histogram as vertical lines.\n",
    "\n",
    "- Natural Breaks:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Define classifier\n",
    "classifier = mapclassify.NaturalBreaks(y=acc['pt_r_tt'], k=9)\n",
    "\n",
    "# Plot histogram for public transport rush hour travel time\n",
    "acc['pt_r_tt'].plot.hist(bins=50)\n",
    "\n",
    "# Add vertical lines for class breaks\n",
    "for value in classifier.bins:\n",
    "    plt.axvline(value, color='k', linestyle='dashed', linewidth=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- Quantiles:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Define classifier\n",
    "classifier = mapclassify.Quantiles(y=acc['pt_r_tt'])\n",
    "\n",
    "# Plot histogram for public transport rush hour travel time\n",
    "acc['pt_r_tt'].plot.hist(bins=50)\n",
    "\n",
    "for value in classifier.bins:\n",
    "    plt.axvline(value, color='k', linestyle='dashed', linewidth=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "<div class=\"alert alert-info\">\n",
    "\n",
    "**Task**\n",
    "\n",
    "Select another column from the data (for example, travel times by car: `car_r_t`). Do the following visualizations using one of the classification schemes available from [pysal/mapclassify](https://github.com/pysal/mapclassify):\n",
    "    \n",
    "- histogram with vertical lines showing the classification bins\n",
    "- thematic map using the classification scheme\n",
    "\n",
    "\n",
    "</div>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Creating a custom classifier\n",
    "\n",
    "**Multicriteria data classification**\n",
    "\n",
    "Let's create a function where we classify the geometries into two classes based on a given `threshold` -parameter. If the area of a polygon is lower than the threshold value (average size of the lake), the output column will get a value 0, if it is larger, it will get a value 1. This kind of classification is often called a [binary classification](https://en.wikipedia.org/wiki/Binary_classification).\n",
    "\n",
    "First we need to create a function for our classification task. This function takes a single row of the GeoDataFrame as input, plus few other parameters that we can use.\n",
    "\n",
    "It also possible to do classifiers with multiple criteria easily in Pandas/Geopandas by extending the example that we started earlier. Now we will modify our binaryClassifier function a bit so that it classifies the data based on two columns.\n",
    "\n",
    "- Let's call it `custom_classifier` that does the binary classification based on two treshold values:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "def custom_classifier(row, src_col1, src_col2, threshold1, threshold2, output_col):\n",
    "   # 1. If the value in src_col1 is LOWER than the threshold1 value\n",
    "   # 2. AND the value in src_col2 is HIGHER than the threshold2 value, give value 1, otherwise give 0\n",
    "   if row[src_col1] < threshold1 and row[src_col2] > threshold2:\n",
    "       # Update the output column with value 0\n",
    "       row[output_col] = 1\n",
    "   # If area of input geometry is higher than the threshold value update with value 1\n",
    "   else:\n",
    "       row[output_col] = 0\n",
    "\n",
    "   # Return the updated row\n",
    "   return row"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we have defined the function, and we can start using it.\n",
    "\n",
    "- Let's do our classification based on two criteria and find out grid cells where the **travel time is lower or equal to 20 minutes** but they are further away **than 4 km (4000 meters) from city center**.\n",
    "\n",
    "- Let's create an empty column for our classification results called `\"suitable_area\"`.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "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>car_m_d</th>\n",
       "      <th>car_m_t</th>\n",
       "      <th>car_r_d</th>\n",
       "      <th>car_r_t</th>\n",
       "      <th>from_id</th>\n",
       "      <th>pt_m_d</th>\n",
       "      <th>pt_m_t</th>\n",
       "      <th>pt_m_tt</th>\n",
       "      <th>pt_r_d</th>\n",
       "      <th>pt_r_t</th>\n",
       "      <th>...</th>\n",
       "      <th>to_id</th>\n",
       "      <th>walk_d</th>\n",
       "      <th>walk_t</th>\n",
       "      <th>GML_ID</th>\n",
       "      <th>NAMEFIN</th>\n",
       "      <th>NAMESWE</th>\n",
       "      <th>NATCODE</th>\n",
       "      <th>geometry</th>\n",
       "      <th>nb_pt_r_tt</th>\n",
       "      <th>suitable_area</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>29476</td>\n",
       "      <td>41</td>\n",
       "      <td>29483</td>\n",
       "      <td>46</td>\n",
       "      <td>5876274</td>\n",
       "      <td>29990</td>\n",
       "      <td>76</td>\n",
       "      <td>95</td>\n",
       "      <td>24984</td>\n",
       "      <td>77</td>\n",
       "      <td>...</td>\n",
       "      <td>5975375</td>\n",
       "      <td>25532</td>\n",
       "      <td>365</td>\n",
       "      <td>27517366</td>\n",
       "      <td>Helsinki</td>\n",
       "      <td>Helsingfors</td>\n",
       "      <td>091</td>\n",
       "      <td>POLYGON ((402250.000 6685750.000, 402024.224 6...</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>29456</td>\n",
       "      <td>41</td>\n",
       "      <td>29462</td>\n",
       "      <td>46</td>\n",
       "      <td>5876275</td>\n",
       "      <td>29866</td>\n",
       "      <td>74</td>\n",
       "      <td>95</td>\n",
       "      <td>24860</td>\n",
       "      <td>75</td>\n",
       "      <td>...</td>\n",
       "      <td>5975375</td>\n",
       "      <td>25408</td>\n",
       "      <td>363</td>\n",
       "      <td>27517366</td>\n",
       "      <td>Helsinki</td>\n",
       "      <td>Helsingfors</td>\n",
       "      <td>091</td>\n",
       "      <td>POLYGON ((402367.890 6685750.000, 402250.000 6...</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2 rows × 21 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   car_m_d  car_m_t  car_r_d  car_r_t  from_id  pt_m_d  pt_m_t  pt_m_tt  \\\n",
       "0    29476       41    29483       46  5876274   29990      76       95   \n",
       "1    29456       41    29462       46  5876275   29866      74       95   \n",
       "\n",
       "   pt_r_d  pt_r_t  ...    to_id  walk_d  walk_t    GML_ID   NAMEFIN  \\\n",
       "0   24984      77  ...  5975375   25532     365  27517366  Helsinki   \n",
       "1   24860      75  ...  5975375   25408     363  27517366  Helsinki   \n",
       "\n",
       "       NAMESWE NATCODE                                           geometry  \\\n",
       "0  Helsingfors     091  POLYGON ((402250.000 6685750.000, 402024.224 6...   \n",
       "1  Helsingfors     091  POLYGON ((402367.890 6685750.000, 402250.000 6...   \n",
       "\n",
       "  nb_pt_r_tt  suitable_area  \n",
       "0          8              0  \n",
       "1          7              0  \n",
       "\n",
       "[2 rows x 21 columns]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Create column for the classification results\n",
    "acc[\"suitable_area\"] = None\n",
    "\n",
    "# Use the function\n",
    "acc = acc.apply(custom_classifier, src_col1='pt_r_tt', \n",
    "                src_col2='walk_d', threshold1=20, threshold2=4000, \n",
    "                output_col=\"suitable_area\", axis=1)\n",
    "\n",
    "# See the first rows\n",
    "acc.head(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Okey we have new values in `suitable_area` -column.\n",
    "\n",
    "- How many Polygons are suitable for us? Let's find out by using a Pandas function called `value_counts()` that return the count of different values in our column.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    3798\n",
       "1       9\n",
       "Name: suitable_area, dtype: int64"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Get value counts\n",
    "acc['suitable_area'].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Okay, so there seems to be nine suitable locations for us where we can try to find an appartment to buy.\n",
    "\n",
    "- Let's see where they are located:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot\n",
    "acc.plot(column=\"suitable_area\", linewidth=0);\n",
    "\n",
    "# Use tight layour\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "A-haa, okay so we can see that suitable places for us with our criteria seem to be located in the\n",
    "eastern part from the city center. Actually, those locations are along the metro line which makes them good locations in terms of travel time to city center since metro is really fast travel mode.\n",
    "\n",
    "**Other examples**\n",
    "\n",
    "Older course materials contain an example of applying a [custom binary classifier on the Corine land cover data](https://automating-gis-processes.github.io/2017/lessons/L4/reclassify.html#classifying-data>)."
   ]
  }
 ],
 "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}