{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Analyzing NYC's 311 Street Flooding Complaints from 2010 to 2020\n",
    "## Streets with the Most Street Flooding Complaints\n",
    "\n",
    "Author: Mark Bauer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib\n",
    "from matplotlib.ticker import FuncFormatter\n",
    "from mpl_toolkits.axes_grid1 import make_axes_locatable\n",
    "import seaborn as sns\n",
    "import geopandas as gpd\n",
    "\n",
    "plt.rcParams['savefig.facecolor'] = 'white'\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Printing verions of Python modules and packages with **watermark** - the IPython magic extension.  \n",
    "Documention for installing watermark: https://github.com/rasbt/watermark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Python implementation: CPython\n",
      "Python version       : 3.8.13\n",
      "IPython version      : 8.4.0\n",
      "\n",
      "numpy     : 1.23.1\n",
      "pandas    : 1.4.3\n",
      "geopandas : 0.11.1\n",
      "matplotlib: 3.5.2\n",
      "seaborn   : 0.11.2\n",
      "\n"
     ]
    }
   ],
   "source": [
    "%reload_ext watermark\n",
    "%watermark -v -p numpy,pandas,geopandas,matplotlib,seaborn"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Read in Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "README.md                       street-flooding-query.csv\r\n",
      "street-flooding-complaints.csv  streets-clipped.gpkg\r\n"
     ]
    }
   ],
   "source": [
    "# list items in data folder\n",
    "%ls data/"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Street Flooding Complaints"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "shape of data: (24817, 27)\n"
     ]
    },
    {
     "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>unique_key</th>\n",
       "      <th>created_date</th>\n",
       "      <th>closed_date</th>\n",
       "      <th>agency</th>\n",
       "      <th>agency_name</th>\n",
       "      <th>complaint_type</th>\n",
       "      <th>descriptor</th>\n",
       "      <th>incident_zip</th>\n",
       "      <th>incident_address</th>\n",
       "      <th>street_name</th>\n",
       "      <th>...</th>\n",
       "      <th>community_board</th>\n",
       "      <th>bbl</th>\n",
       "      <th>borough</th>\n",
       "      <th>x_coordinate_state_plane</th>\n",
       "      <th>y_coordinate_state_plane</th>\n",
       "      <th>open_data_channel_type</th>\n",
       "      <th>park_borough</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>location</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>45283755</td>\n",
       "      <td>2019-12-31T22:42:00.000</td>\n",
       "      <td>2020-01-07T11:07:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>131 GRIMSBY STREET</td>\n",
       "      <td>GRIMSBY STREET</td>\n",
       "      <td>...</td>\n",
       "      <td>02 STATEN ISLAND</td>\n",
       "      <td>5.037950e+09</td>\n",
       "      <td>STATEN ISLAND</td>\n",
       "      <td>958363.0</td>\n",
       "      <td>148793.0</td>\n",
       "      <td>ONLINE</td>\n",
       "      <td>STATEN ISLAND</td>\n",
       "      <td>40.575041</td>\n",
       "      <td>-74.093186</td>\n",
       "      <td>{'latitude': '40.57504060779978', 'longitude':...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>45283863</td>\n",
       "      <td>2019-12-31T17:34:00.000</td>\n",
       "      <td>2020-01-01T15:45:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10312.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>03 STATEN ISLAND</td>\n",
       "      <td>NaN</td>\n",
       "      <td>STATEN ISLAND</td>\n",
       "      <td>937878.0</td>\n",
       "      <td>143517.0</td>\n",
       "      <td>PHONE</td>\n",
       "      <td>STATEN ISLAND</td>\n",
       "      <td>40.560476</td>\n",
       "      <td>-74.166889</td>\n",
       "      <td>{'latitude': '40.56047555908232', 'longitude':...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>45279400</td>\n",
       "      <td>2019-12-31T16:11:00.000</td>\n",
       "      <td>2020-01-08T10:10:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10305.0</td>\n",
       "      <td>753 QUINCY AVENUE</td>\n",
       "      <td>QUINCY AVENUE</td>\n",
       "      <td>...</td>\n",
       "      <td>02 STATEN ISLAND</td>\n",
       "      <td>5.038260e+09</td>\n",
       "      <td>STATEN ISLAND</td>\n",
       "      <td>960864.0</td>\n",
       "      <td>149333.0</td>\n",
       "      <td>PHONE</td>\n",
       "      <td>STATEN ISLAND</td>\n",
       "      <td>40.576530</td>\n",
       "      <td>-74.084185</td>\n",
       "      <td>{'latitude': '40.576529751013474', 'longitude'...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>45277773</td>\n",
       "      <td>2019-12-31T15:42:00.000</td>\n",
       "      <td>2020-01-01T05:25:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>11379.0</td>\n",
       "      <td>61-21 70 STREET</td>\n",
       "      <td>70 STREET</td>\n",
       "      <td>...</td>\n",
       "      <td>05 QUEENS</td>\n",
       "      <td>4.029270e+09</td>\n",
       "      <td>QUEENS</td>\n",
       "      <td>1015410.0</td>\n",
       "      <td>201741.0</td>\n",
       "      <td>PHONE</td>\n",
       "      <td>QUEENS</td>\n",
       "      <td>40.720354</td>\n",
       "      <td>-73.887589</td>\n",
       "      <td>{'latitude': '40.72035428730757', 'longitude':...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>45282532</td>\n",
       "      <td>2019-12-31T12:18:00.000</td>\n",
       "      <td>2019-12-31T14:15:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>11375.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>06 QUEENS</td>\n",
       "      <td>NaN</td>\n",
       "      <td>QUEENS</td>\n",
       "      <td>1027498.0</td>\n",
       "      <td>202160.0</td>\n",
       "      <td>PHONE</td>\n",
       "      <td>QUEENS</td>\n",
       "      <td>40.721454</td>\n",
       "      <td>-73.843978</td>\n",
       "      <td>{'latitude': '40.721453503515995', 'longitude'...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 27 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   unique_key             created_date              closed_date agency  \\\n",
       "0    45283755  2019-12-31T22:42:00.000  2020-01-07T11:07:00.000    DEP   \n",
       "1    45283863  2019-12-31T17:34:00.000  2020-01-01T15:45:00.000    DEP   \n",
       "2    45279400  2019-12-31T16:11:00.000  2020-01-08T10:10:00.000    DEP   \n",
       "3    45277773  2019-12-31T15:42:00.000  2020-01-01T05:25:00.000    DEP   \n",
       "4    45282532  2019-12-31T12:18:00.000  2019-12-31T14:15:00.000    DEP   \n",
       "\n",
       "                              agency_name complaint_type  \\\n",
       "0  Department of Environmental Protection          Sewer   \n",
       "1  Department of Environmental Protection          Sewer   \n",
       "2  Department of Environmental Protection          Sewer   \n",
       "3  Department of Environmental Protection          Sewer   \n",
       "4  Department of Environmental Protection          Sewer   \n",
       "\n",
       "             descriptor  incident_zip    incident_address     street_name  \\\n",
       "0  Street Flooding (SJ)       10306.0  131 GRIMSBY STREET  GRIMSBY STREET   \n",
       "1  Street Flooding (SJ)       10312.0                 NaN             NaN   \n",
       "2  Street Flooding (SJ)       10305.0   753 QUINCY AVENUE   QUINCY AVENUE   \n",
       "3  Street Flooding (SJ)       11379.0     61-21 70 STREET       70 STREET   \n",
       "4  Street Flooding (SJ)       11375.0                 NaN             NaN   \n",
       "\n",
       "   ...   community_board           bbl        borough  \\\n",
       "0  ...  02 STATEN ISLAND  5.037950e+09  STATEN ISLAND   \n",
       "1  ...  03 STATEN ISLAND           NaN  STATEN ISLAND   \n",
       "2  ...  02 STATEN ISLAND  5.038260e+09  STATEN ISLAND   \n",
       "3  ...         05 QUEENS  4.029270e+09         QUEENS   \n",
       "4  ...         06 QUEENS           NaN         QUEENS   \n",
       "\n",
       "  x_coordinate_state_plane y_coordinate_state_plane open_data_channel_type  \\\n",
       "0                 958363.0                 148793.0                 ONLINE   \n",
       "1                 937878.0                 143517.0                  PHONE   \n",
       "2                 960864.0                 149333.0                  PHONE   \n",
       "3                1015410.0                 201741.0                  PHONE   \n",
       "4                1027498.0                 202160.0                  PHONE   \n",
       "\n",
       "    park_borough   latitude  longitude  \\\n",
       "0  STATEN ISLAND  40.575041 -74.093186   \n",
       "1  STATEN ISLAND  40.560476 -74.166889   \n",
       "2  STATEN ISLAND  40.576530 -74.084185   \n",
       "3         QUEENS  40.720354 -73.887589   \n",
       "4         QUEENS  40.721454 -73.843978   \n",
       "\n",
       "                                            location  \n",
       "0  {'latitude': '40.57504060779978', 'longitude':...  \n",
       "1  {'latitude': '40.56047555908232', 'longitude':...  \n",
       "2  {'latitude': '40.576529751013474', 'longitude'...  \n",
       "3  {'latitude': '40.72035428730757', 'longitude':...  \n",
       "4  {'latitude': '40.721453503515995', 'longitude'...  \n",
       "\n",
       "[5 rows x 27 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# read data as a dataframe\n",
    "df = pd.read_csv('data/street-flooding-complaints.csv', low_memory=False)\n",
    "\n",
    "# preview data\n",
    "print('shape of data: {}'.format(df.shape))\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 24817 entries, 0 to 24816\n",
      "Data columns (total 27 columns):\n",
      " #   Column                          Non-Null Count  Dtype  \n",
      "---  ------                          --------------  -----  \n",
      " 0   unique_key                      24817 non-null  int64  \n",
      " 1   created_date                    24817 non-null  object \n",
      " 2   closed_date                     24815 non-null  object \n",
      " 3   agency                          24817 non-null  object \n",
      " 4   agency_name                     24817 non-null  object \n",
      " 5   complaint_type                  24817 non-null  object \n",
      " 6   descriptor                      24817 non-null  object \n",
      " 7   incident_zip                    24817 non-null  float64\n",
      " 8   incident_address                16002 non-null  object \n",
      " 9   street_name                     16002 non-null  object \n",
      " 10  cross_street_1                  21821 non-null  object \n",
      " 11  cross_street_2                  21816 non-null  object \n",
      " 12  address_type                    24817 non-null  object \n",
      " 13  city                            24817 non-null  object \n",
      " 14  status                          24817 non-null  object \n",
      " 15  resolution_description          24813 non-null  object \n",
      " 16  resolution_action_updated_date  24817 non-null  object \n",
      " 17  community_board                 24817 non-null  object \n",
      " 18  bbl                             14603 non-null  float64\n",
      " 19  borough                         24817 non-null  object \n",
      " 20  x_coordinate_state_plane        24817 non-null  float64\n",
      " 21  y_coordinate_state_plane        24817 non-null  float64\n",
      " 22  open_data_channel_type          24817 non-null  object \n",
      " 23  park_borough                    24817 non-null  object \n",
      " 24  latitude                        24817 non-null  float64\n",
      " 25  longitude                       24817 non-null  float64\n",
      " 26  location                        24817 non-null  object \n",
      "dtypes: float64(6), int64(1), object(20)\n",
      "memory usage: 5.1+ MB\n"
     ]
    }
   ],
   "source": [
    "# summarize columns\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Neighborhood Tabulation Areas (NTAs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-01-12T12:26:59.199514Z",
     "start_time": "2021-01-12T12:26:56.896376Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "shape of data: 195\n"
     ]
    },
    {
     "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>ntacode</th>\n",
       "      <th>shape_area</th>\n",
       "      <th>county_fips</th>\n",
       "      <th>ntaname</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>boro_name</th>\n",
       "      <th>boro_code</th>\n",
       "      <th>geometry</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>QN08</td>\n",
       "      <td>77412747.847</td>\n",
       "      <td>081</td>\n",
       "      <td>St. Albans</td>\n",
       "      <td>45401.316803</td>\n",
       "      <td>Queens</td>\n",
       "      <td>4</td>\n",
       "      <td>MULTIPOLYGON (((1052996.196 196307.658, 105308...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>BX28</td>\n",
       "      <td>25666124.5948</td>\n",
       "      <td>005</td>\n",
       "      <td>Van Cortlandt Village</td>\n",
       "      <td>21945.719299</td>\n",
       "      <td>Bronx</td>\n",
       "      <td>2</td>\n",
       "      <td>MULTIPOLYGON (((1015481.837 261490.578, 101548...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>QN55</td>\n",
       "      <td>82461393.7368</td>\n",
       "      <td>081</td>\n",
       "      <td>South Ozone Park</td>\n",
       "      <td>36708.1693055</td>\n",
       "      <td>Queens</td>\n",
       "      <td>4</td>\n",
       "      <td>MULTIPOLYGON (((1038120.503 188147.096, 103819...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>BK50</td>\n",
       "      <td>82089678.6389</td>\n",
       "      <td>047</td>\n",
       "      <td>Canarsie</td>\n",
       "      <td>43703.6096661</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>3</td>\n",
       "      <td>MULTIPOLYGON (((1015236.151 174910.303, 101523...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>BX41</td>\n",
       "      <td>14716710.7402</td>\n",
       "      <td>005</td>\n",
       "      <td>Mount Hope</td>\n",
       "      <td>18937.247819</td>\n",
       "      <td>Bronx</td>\n",
       "      <td>2</td>\n",
       "      <td>MULTIPOLYGON (((1013128.525 250637.931, 101284...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  ntacode     shape_area county_fips                ntaname     shape_leng  \\\n",
       "0    QN08   77412747.847         081             St. Albans   45401.316803   \n",
       "1    BX28  25666124.5948         005  Van Cortlandt Village   21945.719299   \n",
       "2    QN55  82461393.7368         081       South Ozone Park  36708.1693055   \n",
       "3    BK50  82089678.6389         047               Canarsie  43703.6096661   \n",
       "4    BX41  14716710.7402         005             Mount Hope   18937.247819   \n",
       "\n",
       "  boro_name boro_code                                           geometry  \n",
       "0    Queens         4  MULTIPOLYGON (((1052996.196 196307.658, 105308...  \n",
       "1     Bronx         2  MULTIPOLYGON (((1015481.837 261490.578, 101548...  \n",
       "2    Queens         4  MULTIPOLYGON (((1038120.503 188147.096, 103819...  \n",
       "3  Brooklyn         3  MULTIPOLYGON (((1015236.151 174910.303, 101523...  \n",
       "4     Bronx         2  MULTIPOLYGON (((1013128.525 250637.931, 101284...  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# importing nta boundaries\n",
    "url = 'https://data.cityofnewyork.us/api/geospatial/cpf4-rkhq?method=export&format=GeoJSON'\n",
    "nta_gdf = gpd.read_file(url)\n",
    "nta_gdf = nta_gdf.to_crs(epsg=2263)\n",
    "\n",
    "# previewing first five rows in data\n",
    "print('shape of data: {}'.format(nta_gdf.shape[0]))\n",
    "nta_gdf.head()"
   ]
  },
  {
   "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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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# sanity plot\n",
    "nta_gdf.plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Streets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "shape of data: (99124, 12)\n",
      "street id is unique: True\n",
      "epsg:2263\n"
     ]
    },
    {
     "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>physicalid</th>\n",
       "      <th>st_label</th>\n",
       "      <th>st_name</th>\n",
       "      <th>full_stree</th>\n",
       "      <th>rw_type</th>\n",
       "      <th>rw_type_name</th>\n",
       "      <th>st_width</th>\n",
       "      <th>frm_lvl_co</th>\n",
       "      <th>to_lvl_co</th>\n",
       "      <th>borocode</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>geometry</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-1</td>\n",
       "      <td>BRUCKNER BLVD</td>\n",
       "      <td>BRUCKNER</td>\n",
       "      <td>BRUCKNER BLVD</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>36.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>2</td>\n",
       "      <td>522.161372</td>\n",
       "      <td>LINESTRING (1010270.223 233448.310, 1010354.99...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>10000</td>\n",
       "      <td>25 AVE</td>\n",
       "      <td>25</td>\n",
       "      <td>25 AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>35.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>254.863947</td>\n",
       "      <td>LINESTRING (1019770.393 217876.440, 1020022.80...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>100000</td>\n",
       "      <td>233 PL</td>\n",
       "      <td>233</td>\n",
       "      <td>233 PL</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>25.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>272.837036</td>\n",
       "      <td>LINESTRING (1052461.825 220583.306, 1052572.26...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>100001</td>\n",
       "      <td>MILBURN ST</td>\n",
       "      <td>MILBURN</td>\n",
       "      <td>MILBURN ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>485.074277</td>\n",
       "      <td>LINESTRING (1051561.903 187846.554, 1051902.84...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>100003</td>\n",
       "      <td>92 AVE</td>\n",
       "      <td>92</td>\n",
       "      <td>92 AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>524.426714</td>\n",
       "      <td>LINESTRING (1057729.808 204117.541, 1058232.69...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  physicalid       st_label   st_name     full_stree rw_type rw_type_name  \\\n",
       "0         -1  BRUCKNER BLVD  BRUCKNER  BRUCKNER BLVD       1       Street   \n",
       "1      10000         25 AVE        25         25 AVE       1       Street   \n",
       "2     100000         233 PL       233         233 PL       1       Street   \n",
       "3     100001     MILBURN ST   MILBURN     MILBURN ST       1       Street   \n",
       "4     100003         92 AVE        92         92 AVE       1       Street   \n",
       "\n",
       "  st_width frm_lvl_co to_lvl_co borocode  shape_leng  \\\n",
       "0     36.0         13        13        2  522.161372   \n",
       "1     35.0         13        13        4  254.863947   \n",
       "2     25.0         13        13        4  272.837036   \n",
       "3     30.0         13        13        4  485.074277   \n",
       "4     30.0         13        13        4  524.426714   \n",
       "\n",
       "                                            geometry  \n",
       "0  LINESTRING (1010270.223 233448.310, 1010354.99...  \n",
       "1  LINESTRING (1019770.393 217876.440, 1020022.80...  \n",
       "2  LINESTRING (1052461.825 220583.306, 1052572.26...  \n",
       "3  LINESTRING (1051561.903 187846.554, 1051902.84...  \n",
       "4  LINESTRING (1057729.808 204117.541, 1058232.69...  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "path = 'data/streets-clipped.gpkg'\n",
    "streets = gpd.read_file(path)\n",
    "\n",
    "print('shape of data: {}'.format(streets.shape))\n",
    "print('street id is unique: {}'.format(streets['physicalid'].is_unique))\n",
    "print(streets.crs)\n",
    "\n",
    "streets.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'geopandas.geodataframe.GeoDataFrame'>\n",
      "RangeIndex: 99124 entries, 0 to 99123\n",
      "Data columns (total 12 columns):\n",
      " #   Column        Non-Null Count  Dtype   \n",
      "---  ------        --------------  -----   \n",
      " 0   physicalid    99124 non-null  object  \n",
      " 1   st_label      99124 non-null  object  \n",
      " 2   st_name       99124 non-null  object  \n",
      " 3   full_stree    99124 non-null  object  \n",
      " 4   rw_type       99124 non-null  object  \n",
      " 5   rw_type_name  99124 non-null  object  \n",
      " 6   st_width      99124 non-null  object  \n",
      " 7   frm_lvl_co    99124 non-null  object  \n",
      " 8   to_lvl_co     99124 non-null  object  \n",
      " 9   borocode      99124 non-null  object  \n",
      " 10  shape_leng    99124 non-null  float64 \n",
      " 11  geometry      99124 non-null  geometry\n",
      "dtypes: float64(1), geometry(1), object(10)\n",
      "memory usage: 9.1+ MB\n"
     ]
    }
   ],
   "source": [
    "# summarize columns\n",
    "streets.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LineString    99124\n",
       "dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# examine counts of geom types\n",
    "streets.geom_type.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "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": [
    "# sanity check plot\n",
    "streets.plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Assigning NTA Information to Street Complaints"
   ]
  },
  {
   "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>unique_key</th>\n",
       "      <th>geometry</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>45283755</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>45283863</td>\n",
       "      <td>POINT (937878.000 143517.000)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>45279400</td>\n",
       "      <td>POINT (960864.000 149333.000)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>45277773</td>\n",
       "      <td>POINT (1015410.000 201741.000)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>45282532</td>\n",
       "      <td>POINT (1027498.000 202160.000)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   unique_key                        geometry\n",
       "0    45283755   POINT (958363.000 148793.000)\n",
       "1    45283863   POINT (937878.000 143517.000)\n",
       "2    45279400   POINT (960864.000 149333.000)\n",
       "3    45277773  POINT (1015410.000 201741.000)\n",
       "4    45282532  POINT (1027498.000 202160.000)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# convert to geodataframe from x,y points\n",
    "crs = 2263\n",
    "geometry = gpd.points_from_xy(\n",
    "    df['x_coordinate_state_plane'],\n",
    "    df['y_coordinate_state_plane']\n",
    ")\n",
    "\n",
    "# make geodataframe\n",
    "gdf = gpd.GeoDataFrame(df, geometry=geometry, crs=crs)\n",
    "\n",
    "# preview geodataframe\n",
    "gdf.iloc[:, [0, -1]].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "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": [
    "# sanity check plot\n",
    "gdf.plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "shape of data: (24814, 36)\n"
     ]
    },
    {
     "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>unique_key</th>\n",
       "      <th>created_date</th>\n",
       "      <th>closed_date</th>\n",
       "      <th>agency</th>\n",
       "      <th>agency_name</th>\n",
       "      <th>complaint_type</th>\n",
       "      <th>descriptor</th>\n",
       "      <th>incident_zip</th>\n",
       "      <th>incident_address</th>\n",
       "      <th>street_name</th>\n",
       "      <th>...</th>\n",
       "      <th>location</th>\n",
       "      <th>geometry</th>\n",
       "      <th>index_right</th>\n",
       "      <th>ntacode</th>\n",
       "      <th>shape_area</th>\n",
       "      <th>county_fips</th>\n",
       "      <th>ntaname</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>boro_name</th>\n",
       "      <th>boro_code</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>45283755</td>\n",
       "      <td>2019-12-31T22:42:00.000</td>\n",
       "      <td>2020-01-07T11:07:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>131 GRIMSBY STREET</td>\n",
       "      <td>GRIMSBY STREET</td>\n",
       "      <td>...</td>\n",
       "      <td>{'latitude': '40.57504060779978', 'longitude':...</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "      <td>81</td>\n",
       "      <td>SI45</td>\n",
       "      <td>55448202.1327</td>\n",
       "      <td>085</td>\n",
       "      <td>New Dorp-Midland Beach</td>\n",
       "      <td>34369.8892724</td>\n",
       "      <td>Staten Island</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>45279697</td>\n",
       "      <td>2019-12-31T07:10:00.000</td>\n",
       "      <td>2019-12-31T09:30:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>131 GRIMSBY STREET</td>\n",
       "      <td>GRIMSBY STREET</td>\n",
       "      <td>...</td>\n",
       "      <td>{'latitude': '40.57504060779978', 'longitude':...</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "      <td>81</td>\n",
       "      <td>SI45</td>\n",
       "      <td>55448202.1327</td>\n",
       "      <td>085</td>\n",
       "      <td>New Dorp-Midland Beach</td>\n",
       "      <td>34369.8892724</td>\n",
       "      <td>Staten Island</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>68</th>\n",
       "      <td>45196140</td>\n",
       "      <td>2019-12-18T15:58:00.000</td>\n",
       "      <td>2019-12-20T09:30:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>101 3 STREET</td>\n",
       "      <td>3 STREET</td>\n",
       "      <td>...</td>\n",
       "      <td>{'latitude': '40.57522353925495', 'longitude':...</td>\n",
       "      <td>POINT (951437.000 148868.000)</td>\n",
       "      <td>81</td>\n",
       "      <td>SI45</td>\n",
       "      <td>55448202.1327</td>\n",
       "      <td>085</td>\n",
       "      <td>New Dorp-Midland Beach</td>\n",
       "      <td>34369.8892724</td>\n",
       "      <td>Staten Island</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79</th>\n",
       "      <td>45188340</td>\n",
       "      <td>2019-12-18T10:16:00.000</td>\n",
       "      <td>2019-12-20T09:30:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>15 LISBON PLACE</td>\n",
       "      <td>LISBON PLACE</td>\n",
       "      <td>...</td>\n",
       "      <td>{'latitude': '40.5817739850288', 'longitude': ...</td>\n",
       "      <td>POINT (954138.000 151251.000)</td>\n",
       "      <td>81</td>\n",
       "      <td>SI45</td>\n",
       "      <td>55448202.1327</td>\n",
       "      <td>085</td>\n",
       "      <td>New Dorp-Midland Beach</td>\n",
       "      <td>34369.8892724</td>\n",
       "      <td>Staten Island</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>80</th>\n",
       "      <td>45188337</td>\n",
       "      <td>2019-12-18T09:30:00.000</td>\n",
       "      <td>2019-12-18T19:30:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>131 GRIMSBY STREET</td>\n",
       "      <td>GRIMSBY STREET</td>\n",
       "      <td>...</td>\n",
       "      <td>{'latitude': '40.57504060779978', 'longitude':...</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "      <td>81</td>\n",
       "      <td>SI45</td>\n",
       "      <td>55448202.1327</td>\n",
       "      <td>085</td>\n",
       "      <td>New Dorp-Midland Beach</td>\n",
       "      <td>34369.8892724</td>\n",
       "      <td>Staten Island</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 36 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    unique_key             created_date              closed_date agency  \\\n",
       "0     45283755  2019-12-31T22:42:00.000  2020-01-07T11:07:00.000    DEP   \n",
       "9     45279697  2019-12-31T07:10:00.000  2019-12-31T09:30:00.000    DEP   \n",
       "68    45196140  2019-12-18T15:58:00.000  2019-12-20T09:30:00.000    DEP   \n",
       "79    45188340  2019-12-18T10:16:00.000  2019-12-20T09:30:00.000    DEP   \n",
       "80    45188337  2019-12-18T09:30:00.000  2019-12-18T19:30:00.000    DEP   \n",
       "\n",
       "                               agency_name complaint_type  \\\n",
       "0   Department of Environmental Protection          Sewer   \n",
       "9   Department of Environmental Protection          Sewer   \n",
       "68  Department of Environmental Protection          Sewer   \n",
       "79  Department of Environmental Protection          Sewer   \n",
       "80  Department of Environmental Protection          Sewer   \n",
       "\n",
       "              descriptor  incident_zip    incident_address     street_name  \\\n",
       "0   Street Flooding (SJ)       10306.0  131 GRIMSBY STREET  GRIMSBY STREET   \n",
       "9   Street Flooding (SJ)       10306.0  131 GRIMSBY STREET  GRIMSBY STREET   \n",
       "68  Street Flooding (SJ)       10306.0        101 3 STREET        3 STREET   \n",
       "79  Street Flooding (SJ)       10306.0     15 LISBON PLACE    LISBON PLACE   \n",
       "80  Street Flooding (SJ)       10306.0  131 GRIMSBY STREET  GRIMSBY STREET   \n",
       "\n",
       "    ...                                           location  \\\n",
       "0   ...  {'latitude': '40.57504060779978', 'longitude':...   \n",
       "9   ...  {'latitude': '40.57504060779978', 'longitude':...   \n",
       "68  ...  {'latitude': '40.57522353925495', 'longitude':...   \n",
       "79  ...  {'latitude': '40.5817739850288', 'longitude': ...   \n",
       "80  ...  {'latitude': '40.57504060779978', 'longitude':...   \n",
       "\n",
       "                         geometry index_right ntacode     shape_area  \\\n",
       "0   POINT (958363.000 148793.000)          81    SI45  55448202.1327   \n",
       "9   POINT (958363.000 148793.000)          81    SI45  55448202.1327   \n",
       "68  POINT (951437.000 148868.000)          81    SI45  55448202.1327   \n",
       "79  POINT (954138.000 151251.000)          81    SI45  55448202.1327   \n",
       "80  POINT (958363.000 148793.000)          81    SI45  55448202.1327   \n",
       "\n",
       "   county_fips                 ntaname     shape_leng      boro_name boro_code  \n",
       "0          085  New Dorp-Midland Beach  34369.8892724  Staten Island         5  \n",
       "9          085  New Dorp-Midland Beach  34369.8892724  Staten Island         5  \n",
       "68         085  New Dorp-Midland Beach  34369.8892724  Staten Island         5  \n",
       "79         085  New Dorp-Midland Beach  34369.8892724  Staten Island         5  \n",
       "80         085  New Dorp-Midland Beach  34369.8892724  Staten Island         5  \n",
       "\n",
       "[5 rows x 36 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# spatial join nta to points\n",
    "gdf = gpd.sjoin(\n",
    "    gdf,\n",
    "    nta_gdf,\n",
    "    how=\"inner\",\n",
    "    predicate='within'\n",
    ")\n",
    "\n",
    "print('shape of data: {}'.format(gdf.shape))\n",
    "gdf.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'geopandas.geodataframe.GeoDataFrame'>\n",
      "Int64Index: 24814 entries, 0 to 24703\n",
      "Data columns (total 36 columns):\n",
      " #   Column                          Non-Null Count  Dtype   \n",
      "---  ------                          --------------  -----   \n",
      " 0   unique_key                      24814 non-null  int64   \n",
      " 1   created_date                    24814 non-null  object  \n",
      " 2   closed_date                     24812 non-null  object  \n",
      " 3   agency                          24814 non-null  object  \n",
      " 4   agency_name                     24814 non-null  object  \n",
      " 5   complaint_type                  24814 non-null  object  \n",
      " 6   descriptor                      24814 non-null  object  \n",
      " 7   incident_zip                    24814 non-null  float64 \n",
      " 8   incident_address                16002 non-null  object  \n",
      " 9   street_name                     16002 non-null  object  \n",
      " 10  cross_street_1                  21821 non-null  object  \n",
      " 11  cross_street_2                  21816 non-null  object  \n",
      " 12  address_type                    24814 non-null  object  \n",
      " 13  city                            24814 non-null  object  \n",
      " 14  status                          24814 non-null  object  \n",
      " 15  resolution_description          24810 non-null  object  \n",
      " 16  resolution_action_updated_date  24814 non-null  object  \n",
      " 17  community_board                 24814 non-null  object  \n",
      " 18  bbl                             14603 non-null  float64 \n",
      " 19  borough                         24814 non-null  object  \n",
      " 20  x_coordinate_state_plane        24814 non-null  float64 \n",
      " 21  y_coordinate_state_plane        24814 non-null  float64 \n",
      " 22  open_data_channel_type          24814 non-null  object  \n",
      " 23  park_borough                    24814 non-null  object  \n",
      " 24  latitude                        24814 non-null  float64 \n",
      " 25  longitude                       24814 non-null  float64 \n",
      " 26  location                        24814 non-null  object  \n",
      " 27  geometry                        24814 non-null  geometry\n",
      " 28  index_right                     24814 non-null  int64   \n",
      " 29  ntacode                         24814 non-null  object  \n",
      " 30  shape_area                      24814 non-null  object  \n",
      " 31  county_fips                     24814 non-null  object  \n",
      " 32  ntaname                         24814 non-null  object  \n",
      " 33  shape_leng                      24814 non-null  object  \n",
      " 34  boro_name                       24814 non-null  object  \n",
      " 35  boro_code                       24814 non-null  object  \n",
      "dtypes: float64(6), geometry(1), int64(2), object(27)\n",
      "memory usage: 7.0+ MB\n"
     ]
    }
   ],
   "source": [
    "# summarize columns\n",
    "gdf.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'geopandas.geodataframe.GeoDataFrame'>\n",
      "Int64Index: 24814 entries, 0 to 24703\n",
      "Data columns (total 33 columns):\n",
      " #   Column                          Non-Null Count  Dtype   \n",
      "---  ------                          --------------  -----   \n",
      " 0   unique_key                      24814 non-null  int64   \n",
      " 1   created_date                    24814 non-null  object  \n",
      " 2   closed_date                     24812 non-null  object  \n",
      " 3   agency                          24814 non-null  object  \n",
      " 4   agency_name                     24814 non-null  object  \n",
      " 5   complaint_type                  24814 non-null  object  \n",
      " 6   descriptor                      24814 non-null  object  \n",
      " 7   incident_zip                    24814 non-null  float64 \n",
      " 8   incident_address                16002 non-null  object  \n",
      " 9   street_name                     16002 non-null  object  \n",
      " 10  cross_street_1                  21821 non-null  object  \n",
      " 11  cross_street_2                  21816 non-null  object  \n",
      " 12  address_type                    24814 non-null  object  \n",
      " 13  city                            24814 non-null  object  \n",
      " 14  status                          24814 non-null  object  \n",
      " 15  resolution_description          24810 non-null  object  \n",
      " 16  resolution_action_updated_date  24814 non-null  object  \n",
      " 17  community_board                 24814 non-null  object  \n",
      " 18  bbl                             14603 non-null  float64 \n",
      " 19  borough                         24814 non-null  object  \n",
      " 20  x_coordinate_state_plane        24814 non-null  float64 \n",
      " 21  y_coordinate_state_plane        24814 non-null  float64 \n",
      " 22  open_data_channel_type          24814 non-null  object  \n",
      " 23  park_borough                    24814 non-null  object  \n",
      " 24  latitude                        24814 non-null  float64 \n",
      " 25  longitude                       24814 non-null  float64 \n",
      " 26  location                        24814 non-null  object  \n",
      " 27  geometry                        24814 non-null  geometry\n",
      " 28  ntacode                         24814 non-null  object  \n",
      " 29  county_fips                     24814 non-null  object  \n",
      " 30  ntaname                         24814 non-null  object  \n",
      " 31  boro_name                       24814 non-null  object  \n",
      " 32  boro_code                       24814 non-null  object  \n",
      "dtypes: float64(6), geometry(1), int64(1), object(25)\n",
      "memory usage: 6.4+ MB\n"
     ]
    }
   ],
   "source": [
    "# exclude specified columns\n",
    "cols = ['shape_leng', 'shape_area', 'index_right']\n",
    "exclude = gdf.columns.isin(cols)\n",
    "\n",
    "gdf = gdf.loc[:, gdf.columns[~exclude]]\n",
    "\n",
    "# sanity check\n",
    "gdf.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Snap Complaints to Streets"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Methodology: https://medium.com/@brendan_ward/how-to-leverage-geopandas-for-faster-snapping-of-points-to-lines-6113c94e59aa\n",
    "\n",
    "The code below is from Brendan's awesome post."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "shape of data: (24814,)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0            [78943, 78313, 78942, 56509]\n",
       "9            [78943, 78313, 78942, 56509]\n",
       "68    [90146, 54999, 95303, 55000, 90147]\n",
       "79                                [98236]\n",
       "80           [78943, 78313, 78942, 56509]\n",
       "dtype: object"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# offset of match (ft.)\n",
    "offset = 80\n",
    "bbox = gdf.bounds + [-offset, -offset, offset, offset]\n",
    "\n",
    "# match points to streets based on distance\n",
    "hits = bbox.apply(lambda row: list(streets.sindex.intersection(row)), axis=1)\n",
    "\n",
    "print('shape of data: {}'.format(hits.shape))\n",
    "hits.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "shape of data: (82408, 15)\n"
     ]
    },
    {
     "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_idx</th>\n",
       "      <th>line_i</th>\n",
       "      <th>physicalid</th>\n",
       "      <th>st_label</th>\n",
       "      <th>st_name</th>\n",
       "      <th>full_stree</th>\n",
       "      <th>rw_type</th>\n",
       "      <th>rw_type_name</th>\n",
       "      <th>st_width</th>\n",
       "      <th>frm_lvl_co</th>\n",
       "      <th>to_lvl_co</th>\n",
       "      <th>borocode</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>geometry</th>\n",
       "      <th>point</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>78943.0</td>\n",
       "      <td>76942</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>GRIMSBY</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>32.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>197.483266</td>\n",
       "      <td>LINESTRING (958315.407 148720.726, 958202.845 ...</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>78313.0</td>\n",
       "      <td>76094</td>\n",
       "      <td>MAPLETON AVE</td>\n",
       "      <td>MAPLETON</td>\n",
       "      <td>MAPLETON AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>18.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>251.356615</td>\n",
       "      <td>LINESTRING (958315.407 148720.726, 958524.763 ...</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>78942.0</td>\n",
       "      <td>76941</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>GRIMSBY</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>22.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>372.785694</td>\n",
       "      <td>LINESTRING (958533.722 149022.897, 958315.407 ...</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>56509.0</td>\n",
       "      <td>52063</td>\n",
       "      <td>NUGENT AVE</td>\n",
       "      <td>NUGENT</td>\n",
       "      <td>NUGENT AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>38.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>556.903050</td>\n",
       "      <td>LINESTRING (958315.973 149159.852, 957997.235 ...</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>9</td>\n",
       "      <td>78943.0</td>\n",
       "      <td>76942</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>GRIMSBY</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>32.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>197.483266</td>\n",
       "      <td>LINESTRING (958315.407 148720.726, 958202.845 ...</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   pt_idx   line_i physicalid      st_label   st_name    full_stree rw_type  \\\n",
       "0       0  78943.0      76942    GRIMSBY ST   GRIMSBY    GRIMSBY ST       1   \n",
       "1       0  78313.0      76094  MAPLETON AVE  MAPLETON  MAPLETON AVE       1   \n",
       "2       0  78942.0      76941    GRIMSBY ST   GRIMSBY    GRIMSBY ST       1   \n",
       "3       0  56509.0      52063    NUGENT AVE    NUGENT    NUGENT AVE       1   \n",
       "4       9  78943.0      76942    GRIMSBY ST   GRIMSBY    GRIMSBY ST       1   \n",
       "\n",
       "  rw_type_name st_width frm_lvl_co to_lvl_co borocode  shape_leng  \\\n",
       "0       Street     32.0         13        13        5  197.483266   \n",
       "1       Street     18.0         13        13        5  251.356615   \n",
       "2       Street     22.0         13        13        5  372.785694   \n",
       "3       Street     38.0         13        13        5  556.903050   \n",
       "4       Street     32.0         13        13        5  197.483266   \n",
       "\n",
       "                                            geometry  \\\n",
       "0  LINESTRING (958315.407 148720.726, 958202.845 ...   \n",
       "1  LINESTRING (958315.407 148720.726, 958524.763 ...   \n",
       "2  LINESTRING (958533.722 149022.897, 958315.407 ...   \n",
       "3  LINESTRING (958315.973 149159.852, 957997.235 ...   \n",
       "4  LINESTRING (958315.407 148720.726, 958202.845 ...   \n",
       "\n",
       "                           point  \n",
       "0  POINT (958363.000 148793.000)  \n",
       "1  POINT (958363.000 148793.000)  \n",
       "2  POINT (958363.000 148793.000)  \n",
       "3  POINT (958363.000 148793.000)  \n",
       "4  POINT (958363.000 148793.000)  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# position1: index of points table\n",
    "# position2: ordinal position of line - access via iloc later\n",
    "points_to_lines_dict = {\n",
    "    'pt_idx': np.repeat(hits.index, hits.apply(len)),\n",
    "    'line_i': np.concatenate(hits.values)\n",
    "}\n",
    "    \n",
    "tmp = pd.DataFrame(points_to_lines_dict)\n",
    "# join back to the lines on line_i\n",
    "# join back to the original points to get their geometry, rename the point geometry as \"point\"\n",
    "tmp = (\n",
    "    tmp\n",
    "    .join(streets, on=\"line_i\")\n",
    "    .join(gdf['geometry'].rename(\"point\"), on=\"pt_idx\")\n",
    ")\n",
    "\n",
    "print('shape of data: {}'.format(tmp.shape))\n",
    "tmp.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "shape of data: (82408, 15)\n"
     ]
    },
    {
     "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_idx</th>\n",
       "      <th>line_i</th>\n",
       "      <th>physicalid</th>\n",
       "      <th>st_label</th>\n",
       "      <th>st_name</th>\n",
       "      <th>full_stree</th>\n",
       "      <th>rw_type</th>\n",
       "      <th>rw_type_name</th>\n",
       "      <th>st_width</th>\n",
       "      <th>frm_lvl_co</th>\n",
       "      <th>to_lvl_co</th>\n",
       "      <th>borocode</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>geometry</th>\n",
       "      <th>point</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>78943.0</td>\n",
       "      <td>76942</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>GRIMSBY</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>32.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>197.483266</td>\n",
       "      <td>LINESTRING (958315.407 148720.726, 958202.845 ...</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>78313.0</td>\n",
       "      <td>76094</td>\n",
       "      <td>MAPLETON AVE</td>\n",
       "      <td>MAPLETON</td>\n",
       "      <td>MAPLETON AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>18.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>251.356615</td>\n",
       "      <td>LINESTRING (958315.407 148720.726, 958524.763 ...</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>78942.0</td>\n",
       "      <td>76941</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>GRIMSBY</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>22.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>372.785694</td>\n",
       "      <td>LINESTRING (958533.722 149022.897, 958315.407 ...</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>56509.0</td>\n",
       "      <td>52063</td>\n",
       "      <td>NUGENT AVE</td>\n",
       "      <td>NUGENT</td>\n",
       "      <td>NUGENT AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>38.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>556.903050</td>\n",
       "      <td>LINESTRING (958315.973 149159.852, 957997.235 ...</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>9</td>\n",
       "      <td>78943.0</td>\n",
       "      <td>76942</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>GRIMSBY</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>32.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>197.483266</td>\n",
       "      <td>LINESTRING (958315.407 148720.726, 958202.845 ...</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   pt_idx   line_i physicalid      st_label   st_name    full_stree rw_type  \\\n",
       "0       0  78943.0      76942    GRIMSBY ST   GRIMSBY    GRIMSBY ST       1   \n",
       "1       0  78313.0      76094  MAPLETON AVE  MAPLETON  MAPLETON AVE       1   \n",
       "2       0  78942.0      76941    GRIMSBY ST   GRIMSBY    GRIMSBY ST       1   \n",
       "3       0  56509.0      52063    NUGENT AVE    NUGENT    NUGENT AVE       1   \n",
       "4       9  78943.0      76942    GRIMSBY ST   GRIMSBY    GRIMSBY ST       1   \n",
       "\n",
       "  rw_type_name st_width frm_lvl_co to_lvl_co borocode  shape_leng  \\\n",
       "0       Street     32.0         13        13        5  197.483266   \n",
       "1       Street     18.0         13        13        5  251.356615   \n",
       "2       Street     22.0         13        13        5  372.785694   \n",
       "3       Street     38.0         13        13        5  556.903050   \n",
       "4       Street     32.0         13        13        5  197.483266   \n",
       "\n",
       "                                            geometry  \\\n",
       "0  LINESTRING (958315.407 148720.726, 958202.845 ...   \n",
       "1  LINESTRING (958315.407 148720.726, 958524.763 ...   \n",
       "2  LINESTRING (958533.722 149022.897, 958315.407 ...   \n",
       "3  LINESTRING (958315.973 149159.852, 957997.235 ...   \n",
       "4  LINESTRING (958315.407 148720.726, 958202.845 ...   \n",
       "\n",
       "                           point  \n",
       "0  POINT (958363.000 148793.000)  \n",
       "1  POINT (958363.000 148793.000)  \n",
       "2  POINT (958363.000 148793.000)  \n",
       "3  POINT (958363.000 148793.000)  \n",
       "4  POINT (958363.000 148793.000)  "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# convert back to a GeoDataFrame, so we can do spatial ops\n",
    "tmp = gpd.GeoDataFrame(\n",
    "    tmp,\n",
    "    geometry='geometry',\n",
    "    crs=gdf.crs\n",
    ")\n",
    "\n",
    "print('shape of data: {}'.format(tmp.shape))\n",
    "tmp.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "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>snap_dist</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>67649.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>15.998275</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>23.749351</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000003</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.377549</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>2.731226</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>28.478873</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>79.996887</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          snap_dist\n",
       "count  67649.000000\n",
       "mean      15.998275\n",
       "std       23.749351\n",
       "min        0.000003\n",
       "25%        0.377549\n",
       "50%        2.731226\n",
       "75%       28.478873\n",
       "max       79.996887"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# discard any lines that are greater than tolerance from points\n",
    "# sort on ascending snap distance, so that closest goes to top\n",
    "tmp[\"snap_dist\"] = tmp['geometry'].distance(gpd.GeoSeries(tmp.point))\n",
    "\n",
    "tmp = (\n",
    "    tmp\n",
    "    .loc[tmp.snap_dist <= offset]\n",
    "    .sort_values(by=[\"snap_dist\"])\n",
    ")\n",
    "\n",
    "# sanity check distance ceiling\n",
    "tmp.loc[:, ['snap_dist']].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "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>line_i</th>\n",
       "      <th>physicalid</th>\n",
       "      <th>st_label</th>\n",
       "      <th>st_name</th>\n",
       "      <th>full_stree</th>\n",
       "      <th>rw_type</th>\n",
       "      <th>rw_type_name</th>\n",
       "      <th>st_width</th>\n",
       "      <th>frm_lvl_co</th>\n",
       "      <th>to_lvl_co</th>\n",
       "      <th>borocode</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>geometry</th>\n",
       "      <th>point</th>\n",
       "      <th>snap_dist</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pt_idx</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>78942.0</td>\n",
       "      <td>76941</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>GRIMSBY</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>22.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>372.785694</td>\n",
       "      <td>LINESTRING (958533.722 149022.897, 958315.407 ...</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "      <td>3.748273</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>87545.0</td>\n",
       "      <td>86900</td>\n",
       "      <td>GETZ AVE</td>\n",
       "      <td>GETZ</td>\n",
       "      <td>GETZ AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>54.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>359.306539</td>\n",
       "      <td>LINESTRING (937877.973 143517.454, 937931.865 ...</td>\n",
       "      <td>POINT (937878.000 143517.000)</td>\n",
       "      <td>0.041074</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>49371.0</td>\n",
       "      <td>44670</td>\n",
       "      <td>QUINCY AVE</td>\n",
       "      <td>QUINCY</td>\n",
       "      <td>QUINCY AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>24.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>151.499515</td>\n",
       "      <td>LINESTRING (960927.392 149386.927, 960816.303 ...</td>\n",
       "      <td>POINT (960864.000 149333.000)</td>\n",
       "      <td>3.560673</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>95619.0</td>\n",
       "      <td>95836</td>\n",
       "      <td>70 ST</td>\n",
       "      <td>70</td>\n",
       "      <td>70 ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>813.495132</td>\n",
       "      <td>LINESTRING (1015284.400 201942.938, 1015707.19...</td>\n",
       "      <td>POINT (1015410.000 201741.000)</td>\n",
       "      <td>2.353387</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>9655.0</td>\n",
       "      <td>13720</td>\n",
       "      <td>71 AVE</td>\n",
       "      <td>71</td>\n",
       "      <td>71 AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>40.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>45.256196</td>\n",
       "      <td>LINESTRING (1027487.293 202138.287, 1027497.95...</td>\n",
       "      <td>POINT (1027498.000 202160.000)</td>\n",
       "      <td>0.339680</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         line_i physicalid    st_label  st_name  full_stree rw_type  \\\n",
       "pt_idx                                                                \n",
       "0       78942.0      76941  GRIMSBY ST  GRIMSBY  GRIMSBY ST       1   \n",
       "1       87545.0      86900    GETZ AVE     GETZ    GETZ AVE       1   \n",
       "2       49371.0      44670  QUINCY AVE   QUINCY  QUINCY AVE       1   \n",
       "3       95619.0      95836       70 ST       70       70 ST       1   \n",
       "4        9655.0      13720      71 AVE       71      71 AVE       1   \n",
       "\n",
       "       rw_type_name st_width frm_lvl_co to_lvl_co borocode  shape_leng  \\\n",
       "pt_idx                                                                   \n",
       "0            Street     22.0         13        13        5  372.785694   \n",
       "1            Street     54.0         13        13        5  359.306539   \n",
       "2            Street     24.0         13        13        5  151.499515   \n",
       "3            Street     30.0         13        13        4  813.495132   \n",
       "4            Street     40.0         13        13        4   45.256196   \n",
       "\n",
       "                                                 geometry  \\\n",
       "pt_idx                                                      \n",
       "0       LINESTRING (958533.722 149022.897, 958315.407 ...   \n",
       "1       LINESTRING (937877.973 143517.454, 937931.865 ...   \n",
       "2       LINESTRING (960927.392 149386.927, 960816.303 ...   \n",
       "3       LINESTRING (1015284.400 201942.938, 1015707.19...   \n",
       "4       LINESTRING (1027487.293 202138.287, 1027497.95...   \n",
       "\n",
       "                                 point  snap_dist  \n",
       "pt_idx                                             \n",
       "0        POINT (958363.000 148793.000)   3.748273  \n",
       "1        POINT (937878.000 143517.000)   0.041074  \n",
       "2        POINT (960864.000 149333.000)   3.560673  \n",
       "3       POINT (1015410.000 201741.000)   2.353387  \n",
       "4       POINT (1027498.000 202160.000)   0.339680  "
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# group by the index of the points and take the first, which is the closest line \n",
    "closest = (\n",
    "    tmp\n",
    "    .groupby(\"pt_idx\")\n",
    "    .first()\n",
    ")\n",
    "\n",
    "# construct a GeoDataFrame of the closest lines\n",
    "closest = gpd.GeoDataFrame(closest, geometry=\"geometry\")\n",
    "\n",
    "closest.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dropped 86 rows or 0.35% of street flooding complaint points, which were more than 80 feet from the closest street center line.\n"
     ]
    }
   ],
   "source": [
    "counts = gdf.shape[0] - closest.shape[0]\n",
    "counts_perc = round((1 - (closest.shape[0] / gdf.shape[0])) * 100, 2)\n",
    "\n",
    "print('Dropped {} rows or {}% of street flooding complaint points, \\\n",
    "which were more than 80 feet from the closest street center line.'.format(counts, counts_perc))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "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>line_i</th>\n",
       "      <th>physicalid</th>\n",
       "      <th>st_label</th>\n",
       "      <th>st_name</th>\n",
       "      <th>full_stree</th>\n",
       "      <th>rw_type</th>\n",
       "      <th>rw_type_name</th>\n",
       "      <th>st_width</th>\n",
       "      <th>frm_lvl_co</th>\n",
       "      <th>to_lvl_co</th>\n",
       "      <th>borocode</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>geometry</th>\n",
       "      <th>point</th>\n",
       "      <th>snap_dist</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pt_idx</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>78942.0</td>\n",
       "      <td>76941</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>GRIMSBY</td>\n",
       "      <td>GRIMSBY ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>22.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>372.785694</td>\n",
       "      <td>POINT (958366.038 148790.805)</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "      <td>3.748273</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>87545.0</td>\n",
       "      <td>86900</td>\n",
       "      <td>GETZ AVE</td>\n",
       "      <td>GETZ</td>\n",
       "      <td>GETZ AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>54.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>359.306539</td>\n",
       "      <td>POINT (937878.041 143517.006)</td>\n",
       "      <td>POINT (937878.000 143517.000)</td>\n",
       "      <td>0.041074</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>49371.0</td>\n",
       "      <td>44670</td>\n",
       "      <td>QUINCY AVE</td>\n",
       "      <td>QUINCY</td>\n",
       "      <td>QUINCY AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>24.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>151.499515</td>\n",
       "      <td>POINT (960866.421 149330.389)</td>\n",
       "      <td>POINT (960864.000 149333.000)</td>\n",
       "      <td>3.560673</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>95619.0</td>\n",
       "      <td>95836</td>\n",
       "      <td>70 ST</td>\n",
       "      <td>70</td>\n",
       "      <td>70 ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>813.495132</td>\n",
       "      <td>POINT (1015407.989 201739.777)</td>\n",
       "      <td>POINT (1015410.000 201741.000)</td>\n",
       "      <td>2.353387</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>9655.0</td>\n",
       "      <td>13720</td>\n",
       "      <td>71 AVE</td>\n",
       "      <td>71</td>\n",
       "      <td>71 AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>40.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>45.256196</td>\n",
       "      <td>POINT (1027497.693 202160.146)</td>\n",
       "      <td>POINT (1027498.000 202160.000)</td>\n",
       "      <td>0.339680</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         line_i physicalid    st_label  st_name  full_stree rw_type  \\\n",
       "pt_idx                                                                \n",
       "0       78942.0      76941  GRIMSBY ST  GRIMSBY  GRIMSBY ST       1   \n",
       "1       87545.0      86900    GETZ AVE     GETZ    GETZ AVE       1   \n",
       "2       49371.0      44670  QUINCY AVE   QUINCY  QUINCY AVE       1   \n",
       "3       95619.0      95836       70 ST       70       70 ST       1   \n",
       "4        9655.0      13720      71 AVE       71      71 AVE       1   \n",
       "\n",
       "       rw_type_name st_width frm_lvl_co to_lvl_co borocode  shape_leng  \\\n",
       "pt_idx                                                                   \n",
       "0            Street     22.0         13        13        5  372.785694   \n",
       "1            Street     54.0         13        13        5  359.306539   \n",
       "2            Street     24.0         13        13        5  151.499515   \n",
       "3            Street     30.0         13        13        4  813.495132   \n",
       "4            Street     40.0         13        13        4   45.256196   \n",
       "\n",
       "                              geometry                           point  \\\n",
       "pt_idx                                                                   \n",
       "0        POINT (958366.038 148790.805)   POINT (958363.000 148793.000)   \n",
       "1        POINT (937878.041 143517.006)   POINT (937878.000 143517.000)   \n",
       "2        POINT (960866.421 149330.389)   POINT (960864.000 149333.000)   \n",
       "3       POINT (1015407.989 201739.777)  POINT (1015410.000 201741.000)   \n",
       "4       POINT (1027497.693 202160.146)  POINT (1027498.000 202160.000)   \n",
       "\n",
       "        snap_dist  \n",
       "pt_idx             \n",
       "0        3.748273  \n",
       "1        0.041074  \n",
       "2        3.560673  \n",
       "3        2.353387  \n",
       "4        0.339680  "
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# position of nearest point from start of the line and get new point location geometry\n",
    "pos = closest['geometry'].project(gpd.GeoSeries(closest.point))\n",
    "new_pts = closest['geometry'].interpolate(pos)\n",
    "\n",
    "# create a new GeoDataFrame from the columns from the closest line and \n",
    "# new point geometries (which will be called \"geometries\")\n",
    "snapped = gpd.GeoDataFrame(closest, geometry=new_pts)\n",
    "\n",
    "snapped.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'geopandas.geodataframe.GeoDataFrame'>\n",
      "Int64Index: 24814 entries, 0 to 24703\n",
      "Data columns (total 33 columns):\n",
      " #   Column                          Non-Null Count  Dtype   \n",
      "---  ------                          --------------  -----   \n",
      " 0   unique_key                      24814 non-null  int64   \n",
      " 1   created_date                    24814 non-null  object  \n",
      " 2   closed_date                     24812 non-null  object  \n",
      " 3   agency                          24814 non-null  object  \n",
      " 4   agency_name                     24814 non-null  object  \n",
      " 5   complaint_type                  24814 non-null  object  \n",
      " 6   descriptor                      24814 non-null  object  \n",
      " 7   incident_zip                    24814 non-null  float64 \n",
      " 8   incident_address                16002 non-null  object  \n",
      " 9   street_name                     16002 non-null  object  \n",
      " 10  cross_street_1                  21821 non-null  object  \n",
      " 11  cross_street_2                  21816 non-null  object  \n",
      " 12  address_type                    24814 non-null  object  \n",
      " 13  city                            24814 non-null  object  \n",
      " 14  status                          24814 non-null  object  \n",
      " 15  resolution_description          24810 non-null  object  \n",
      " 16  resolution_action_updated_date  24814 non-null  object  \n",
      " 17  community_board                 24814 non-null  object  \n",
      " 18  bbl                             14603 non-null  float64 \n",
      " 19  borough                         24814 non-null  object  \n",
      " 20  x_coordinate_state_plane        24814 non-null  float64 \n",
      " 21  y_coordinate_state_plane        24814 non-null  float64 \n",
      " 22  open_data_channel_type          24814 non-null  object  \n",
      " 23  park_borough                    24814 non-null  object  \n",
      " 24  latitude                        24814 non-null  float64 \n",
      " 25  longitude                       24814 non-null  float64 \n",
      " 26  location                        24814 non-null  object  \n",
      " 27  geometry                        24814 non-null  geometry\n",
      " 28  ntacode                         24814 non-null  object  \n",
      " 29  county_fips                     24814 non-null  object  \n",
      " 30  ntaname                         24814 non-null  object  \n",
      " 31  boro_name                       24814 non-null  object  \n",
      " 32  boro_code                       24814 non-null  object  \n",
      "dtypes: float64(6), geometry(1), int64(1), object(25)\n",
      "memory usage: 6.4+ MB\n"
     ]
    }
   ],
   "source": [
    "# summarize columns\n",
    "gdf.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "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>unique_key</th>\n",
       "      <th>created_date</th>\n",
       "      <th>closed_date</th>\n",
       "      <th>agency</th>\n",
       "      <th>agency_name</th>\n",
       "      <th>complaint_type</th>\n",
       "      <th>descriptor</th>\n",
       "      <th>incident_zip</th>\n",
       "      <th>incident_address</th>\n",
       "      <th>street_name</th>\n",
       "      <th>...</th>\n",
       "      <th>rw_type</th>\n",
       "      <th>rw_type_name</th>\n",
       "      <th>st_width</th>\n",
       "      <th>frm_lvl_co</th>\n",
       "      <th>to_lvl_co</th>\n",
       "      <th>borocode</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>geometry</th>\n",
       "      <th>point</th>\n",
       "      <th>snap_dist</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>45283755</td>\n",
       "      <td>2019-12-31T22:42:00.000</td>\n",
       "      <td>2020-01-07T11:07:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>131 GRIMSBY STREET</td>\n",
       "      <td>GRIMSBY STREET</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>22.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>372.785694</td>\n",
       "      <td>POINT (958366.038 148790.805)</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "      <td>3.748273</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>45279697</td>\n",
       "      <td>2019-12-31T07:10:00.000</td>\n",
       "      <td>2019-12-31T09:30:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>131 GRIMSBY STREET</td>\n",
       "      <td>GRIMSBY STREET</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>22.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>372.785694</td>\n",
       "      <td>POINT (958366.038 148790.805)</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "      <td>3.748273</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>45196140</td>\n",
       "      <td>2019-12-18T15:58:00.000</td>\n",
       "      <td>2019-12-20T09:30:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>101 3 STREET</td>\n",
       "      <td>3 STREET</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>204.368178</td>\n",
       "      <td>POINT (951439.252 148866.357)</td>\n",
       "      <td>POINT (951437.000 148868.000)</td>\n",
       "      <td>2.787056</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>45188340</td>\n",
       "      <td>2019-12-18T10:16:00.000</td>\n",
       "      <td>2019-12-20T09:30:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>15 LISBON PLACE</td>\n",
       "      <td>LISBON PLACE</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>308.463539</td>\n",
       "      <td>POINT (954140.677 151248.949)</td>\n",
       "      <td>POINT (954138.000 151251.000)</td>\n",
       "      <td>3.372281</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>45188337</td>\n",
       "      <td>2019-12-18T09:30:00.000</td>\n",
       "      <td>2019-12-18T19:30:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>131 GRIMSBY STREET</td>\n",
       "      <td>GRIMSBY STREET</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>22.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>372.785694</td>\n",
       "      <td>POINT (958366.038 148790.805)</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "      <td>3.748273</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 47 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   unique_key             created_date              closed_date agency  \\\n",
       "0    45283755  2019-12-31T22:42:00.000  2020-01-07T11:07:00.000    DEP   \n",
       "1    45279697  2019-12-31T07:10:00.000  2019-12-31T09:30:00.000    DEP   \n",
       "2    45196140  2019-12-18T15:58:00.000  2019-12-20T09:30:00.000    DEP   \n",
       "3    45188340  2019-12-18T10:16:00.000  2019-12-20T09:30:00.000    DEP   \n",
       "4    45188337  2019-12-18T09:30:00.000  2019-12-18T19:30:00.000    DEP   \n",
       "\n",
       "                              agency_name complaint_type  \\\n",
       "0  Department of Environmental Protection          Sewer   \n",
       "1  Department of Environmental Protection          Sewer   \n",
       "2  Department of Environmental Protection          Sewer   \n",
       "3  Department of Environmental Protection          Sewer   \n",
       "4  Department of Environmental Protection          Sewer   \n",
       "\n",
       "             descriptor  incident_zip    incident_address     street_name  \\\n",
       "0  Street Flooding (SJ)       10306.0  131 GRIMSBY STREET  GRIMSBY STREET   \n",
       "1  Street Flooding (SJ)       10306.0  131 GRIMSBY STREET  GRIMSBY STREET   \n",
       "2  Street Flooding (SJ)       10306.0        101 3 STREET        3 STREET   \n",
       "3  Street Flooding (SJ)       10306.0     15 LISBON PLACE    LISBON PLACE   \n",
       "4  Street Flooding (SJ)       10306.0  131 GRIMSBY STREET  GRIMSBY STREET   \n",
       "\n",
       "   ... rw_type rw_type_name st_width frm_lvl_co to_lvl_co borocode  \\\n",
       "0  ...       1       Street     22.0         13        13        5   \n",
       "1  ...       1       Street     22.0         13        13        5   \n",
       "2  ...       1       Street     30.0         13        13        5   \n",
       "3  ...       1       Street     30.0         13        13        5   \n",
       "4  ...       1       Street     22.0         13        13        5   \n",
       "\n",
       "   shape_leng                       geometry                          point  \\\n",
       "0  372.785694  POINT (958366.038 148790.805)  POINT (958363.000 148793.000)   \n",
       "1  372.785694  POINT (958366.038 148790.805)  POINT (958363.000 148793.000)   \n",
       "2  204.368178  POINT (951439.252 148866.357)  POINT (951437.000 148868.000)   \n",
       "3  308.463539  POINT (954140.677 151248.949)  POINT (954138.000 151251.000)   \n",
       "4  372.785694  POINT (958366.038 148790.805)  POINT (958363.000 148793.000)   \n",
       "\n",
       "  snap_dist  \n",
       "0  3.748273  \n",
       "1  3.748273  \n",
       "2  2.787056  \n",
       "3  3.372281  \n",
       "4  3.748273  \n",
       "\n",
       "[5 rows x 47 columns]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# join back to the original points and drop any that did not join\n",
    "updated_points = (\n",
    "    gdf\n",
    "    .drop(columns=[\"geometry\"])\n",
    "    .join(snapped)\n",
    "    .dropna(subset=[\"geometry\"])\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "updated_points.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Histogram of snap_dist (ft.)')"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAfsAAAGECAYAAAAx/4nGAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAAsTAAALEwEAmpwYAAAiB0lEQVR4nO3de7hddX3n8fdHgglCIiCBBwk2aKkKdERBirdWxUqsWtAWjSMCPrT0UbRi1VbsTKttsTrjfRRmGLSAN4x4gSpKaQRvpWKgKCBQGEGJUIJUyEEgmvCdP/Y6uDmcazj77Jxf3q/n2c9e67fWb+3v75zAZ6/LWStVhSRJatfDhl2AJEkaLMNekqTGGfaSJDXOsJckqXGGvSRJjTPsJUlqnGEvzVCSq5I8e9h1DFOSlyS5KcldSZ487HpmIsnpSf6um35Wkmtncdt/n+SEvvnXJLm1+zk9ahr9P59kxWzVI40y7KU+SW5M8rwxbcck+dbofFXtW1UXTbGd5UkqyYIBlTps7wFeV1U7VNW/DbuYzVVV36yqx0+1XpK3J/nEFOssBY4C/k83vy3wPuD5VbUD8JtJ1k7xUe8CTppW8dIMGPbSPLQFfIn4NeCqIdewpTkGOK+q7unmdwMWMYOfU1VdAixJcuDsl6etmWEvzVD/3n+Sg5KsSbK+O1z7vm61b3Tvd3SHcJ+W5GFJ/luSHyVZl+TMJI/s2+5R3bLbk/z3MZ/z9iRnJ/lEkvXAMd1nX5zkjiS3JPlwkof3ba+SvDbJdUlGkvxtksd1fdYnWdW//pgxjltrkoVJ7gK2Ab6X5P+N0zdJ3t/1uzPJ95Ps1y07PclHkny5q+k7SR7X1/eD3emB9UkuTfKsvmWjP4PPdH0vS/Kkafy+ntytO5LkM/QCeHTZs/v3tpP8RZKfdOtem+SQ7rD624CXd7/L703wUS8Avt5t5zeA0dMDdyS5EPgK8OhuG3clefQE27kIeOFU45JmwrCXHpoPAh+sqiXA44BVXftvd+87doe6L6a353cM8BzgscAOwIcBkuwDnAy8EtgdeCSwx5jPOgw4G9gR+CSwCXgjsAvwNOAQ4LVj+qwADgAOBv4cOLX7jD2B/YBXTDCucWutqg3dIWmAJ1XV48bp+/xu/L/R1fpy4Pa+5a8A3gHsBFzPAw9bfxfYH9gZ+BTw2SSL+pYfBny2b/kXu8Pl4+q+zHwR+HjX57PAH0yw7uOB1wFPrarFwKHAjVX1VeCdwGe63+VEXzB+ky7gq+rfgX279h2r6jn0vgzc3G1jh6q6eYLtXA1M+SVGmgnDXnqwL3Z7y3ckuYNeCE/kl8CvJ9mlqu6qqn+dZN1XAu+rqh9W1V3AicDK7pD8HwL/WFXfqqpfAH8FjH1wxcVV9cWquq+q7qmqS6vqX6tqY1XdSO9c8e+M6fPuqlpfVVcBVwL/1H3+nfT2NCe6uG6yWqfyS2Ax8AQgVXV1Vd3St/zzVXVJVW2k96Vl/9EFVfWJqrq9G9N7gYVA/zn1S6vq7Kr6Jb3z4YvofZGZyMHAtsAHquqXVXU2vS8U49nUfd4+Sbatqhur6kFHLiaxIzAyg/UnMtJtS5o1hr30YIdX1Y6jLx68t9zvWHp7sNck+W6SF02y7qOBH/XN/whYQO/c7qOBm0YXVNXdPHBvmP7l0DtUnORLSf6jO7T/Tnp7+f1u7Zu+Z5z5HRjfZLVOqqq+Ru+IxUeAW5OcmmRJ3yr/0Td9d38NSd6U5Oru8P8d9I5w9I+p/2d0H7C2q3UijwZ+Ug984tePxluxqq4HTgDeDqxLctYkh9rH8zN6X3IeqsXAHbOwHel+hr30EFTVdVX1CmBX4N3A2Um258F75QA307uwbdRjgI30AvgWYNnogiTbAWP/VGvsNk8BrgH27k4jvA3I5o9m2rVOqao+VFUH0DuU/RvAW6bq052f/wvgZcBO3RetO3ngmPbsW/9h9H5mEx0Oh97PdY8k/dt4zCR1f6qqnklv7EXvdwrj/z7H+j69sU64+WlsA+CJwETXBUibxbCXHoIkRyZZ2u1l3tE1bwJuA+6jd7571KeBNybZK8kO/Oo88EZ65+JfnOTp3XnmdzB1cC8G1gN3JXkC8JrZGtcUtU4qyVOT/FZ3Lv3nwL30fiZTWUzvC8VtwIIkfwUsGbPOAUle2p1OOAHYAEx26uTibpt/mmRBkpcCB01Q9+OTPDfJwq7me/rqvhVY3n3BmMh5PPg0Sr9bgUel76LMCfwOvVMs0qwx7KWHZgVwVXeF+geBlVV1b3cY/iTg2925/4OBj9G7UOwbwA30AuX1AN059dcDZ9HbGx0B1tELs4m8Gfiv3br/F/jMLI5rwlqnYUlXz8/oHTK/nd7f5U/lfHoh9+9dv3sZc+oCOIfeBX8/A14FvLQ7fz+u7vqHl9K72PBnXd/PT7D6Qnp/5/5TeqcadqV3tAR6F/YB3J7ksgn6nwn8XndUZrxarqH3JeqH3b+JRyd5ZZL7/zQvyVOBn3d/gifNmjzwVJakLUG3N30HvUP0Nwy5nC1CkrcDv15VRw67lokkeSewrqo+sJn9Pwd8tKrOm9XCtNUb9o05JHWSvBhYTe/w/XuAK4Abh1mTZqaq3jb1WpP2H/fPAqWHysP40pbjMHoXm90M7E3vlICH3qaQ5DF9N6oZ+5rwYjxpa+JhfEmSGueevSRJjTPsJUlqXLMX6O2yyy61fPnyYZchSdKcuPTSS39aVUvHW9Zs2C9fvpw1a9YMuwxJkuZEknFvBQ0expckqXmGvSRJjTPsJUlqnGEvSVLjDHtJkhpn2EuS1DjDXpKkxhn2kiQ1zrCXJKlxhr0kSY0z7CVJapxhL0lS4wz7aagq1q9fT1UNuxRJkmbMsJ+GkZERVr7/y4yMjAy7FEmSZsywn6YFix4x7BIkSdoshr0kSY0z7CVJapxhL0lS4wx7SZIaZ9hLktQ4w16SpMYZ9pIkNW6gYZ/kxiRXJLk8yZqubeckFyS5rnvfqW/9E5Ncn+TaJIf2tR/Qbef6JB9KkkHWLUlSS+Ziz/45VbV/VR3Yzb8VWF1VewOru3mS7AOsBPYFVgAnJ9mm63MKcBywd/daMQd1S5LUhGEcxj8MOKObPgM4vK/9rKraUFU3ANcDByXZHVhSVRdX7+b0Z/b1kSRJUxh02BfwT0kuTXJc17ZbVd0C0L3v2rXvAdzU13dt17ZHNz22XZIkTcOCAW//GVV1c5JdgQuSXDPJuuOdh69J2h+8gd4XiuMAHvOYx8y0VkmSmjTQPfuqurl7Xwd8ATgIuLU7NE/3vq5bfS2wZ1/3ZcDNXfuycdrH+7xTq+rAqjpw6dKlszkUSZLmrYGFfZLtkywenQaeD1wJnAsc3a12NHBON30usDLJwiR70bsQ75LuUP9IkoO7q/CP6usjSZKmMMjD+LsBX+j+Sm4B8Kmq+mqS7wKrkhwL/Bg4AqCqrkqyCvgBsBE4vqo2ddt6DXA6sB3wle4lSZKmYWBhX1U/BJ40TvvtwCET9DkJOGmc9jXAfrNdoyRJWwPvoCdJUuMMe0mSGmfYS5LUOMNekqTGGfaSJDXOsJckqXGGvSRJjTPsJUlqnGEvSVLjDHtJkhpn2EuS1DjDXpKkxhn2kiQ1zrCXJKlxhr0kSY0z7CVJapxhL0lS4wx7SZIaZ9hLktQ4w16SpMYZ9pIkNc6wlySpcYa9JEmNM+wlSWqcYS9JUuMMe0mSGmfYS5LUOMNekqTGGfaSJDXOsJckqXGGvSRJjTPsJUlqnGEvSVLjDHtJkhpn2EuS1DjDXpKkxhn2kiQ1zrCXJKlxhr0kSY0z7CVJapxhL0lS4wx7SZIaZ9hLktQ4w16SpMYZ9pIkNc6wlySpcYa9JEmNM+wlSWqcYS9JUuMMe0mSGmfYS5LUuIGHfZJtkvxbki918zsnuSDJdd37Tn3rnpjk+iTXJjm0r/2AJFd0yz6UJIOuW5KkVszFnv0bgKv75t8KrK6qvYHV3TxJ9gFWAvsCK4CTk2zT9TkFOA7Yu3utmIO6JUlqwkDDPsky4IXAaX3NhwFndNNnAIf3tZ9VVRuq6gbgeuCgJLsDS6rq4qoq4My+PpIkaQqD3rP/APDnwH19bbtV1S0A3fuuXfsewE19663t2vbopse2S5KkaRhY2Cd5EbCuqi6dbpdx2mqS9vE+87gka5Ksue2226b5sZIktW2Qe/bPAH4/yY3AWcBzk3wCuLU7NE/3vq5bfy2wZ1//ZcDNXfuycdofpKpOraoDq+rApUuXzuZYJEmatwYW9lV1YlUtq6rl9C68+1pVHQmcCxzdrXY0cE43fS6wMsnCJHvRuxDvku5Q/0iSg7ur8I/q6yNJkqawYAif+S5gVZJjgR8DRwBU1VVJVgE/ADYCx1fVpq7Pa4DTge2Ar3QvSZI0DXMS9lV1EXBRN307cMgE650EnDRO+xpgv8FVKElSu7yDniRJjTPsJUlqnGEvSVLjDHtJkhpn2EuS1DjDXpKkxhn2kiQ1zrCXJKlxhr0kSY0z7CVJapxhL0lS4wx7SZIaZ9hLktQ4w16SpMYZ9pIkNc6wlySpcYa9JEmNM+wlSWqcYS9JUuMMe0mSGmfYS5LUOMNekqTGGfaSJDXOsJckqXGGvSRJjTPsJUlqnGEvSVLjDHtJkhpn2EuS1DjDXpKkxhn2kiQ1zrCXJKlxhr0kSY0z7CVJapxhL0lS4wx7SZIaZ9hLktQ4w16SpMYZ9pIkNc6wlySpcYa9JEmNM+wlSWqcYS9JUuMMe0mSGmfYS5LUOMNekqTGGfaSJDXOsJckqXGGvSRJjTPsJUlqnGEvSVLjBhb2SRYluSTJ95JcleQdXfvOSS5Icl33vlNfnxOTXJ/k2iSH9rUfkOSKbtmHkmRQdUuS1JpB7tlvAJ5bVU8C9gdWJDkYeCuwuqr2BlZ38yTZB1gJ7AusAE5Osk23rVOA44C9u9eKAdYtSVJTBhb21XNXN7tt9yrgMOCMrv0M4PBu+jDgrKraUFU3ANcDByXZHVhSVRdXVQFn9vWRJElTGOg5+yTbJLkcWAdcUFXfAXarqlsAuvddu9X3AG7q6762a9ujmx7bPt7nHZdkTZI1t91226yORZKk+WqgYV9Vm6pqf2AZvb30/SZZfbzz8DVJ+3ifd2pVHVhVBy5dunTG9UqS1KI5uRq/qu4ALqJ3rv3W7tA83fu6brW1wJ593ZYBN3fty8ZplyRJ0zCtsE/yjOm0jVm+NMmO3fR2wPOAa4BzgaO71Y4GzummzwVWJlmYZC96F+Jd0h3qH0lycHcV/lF9fSRJ0hQWTHO9/wU8ZRpt/XYHzuiuqH8YsKqqvpTkYmBVkmOBHwNHAFTVVUlWAT8ANgLHV9WmbluvAU4HtgO+0r0kSdI0TBr2SZ4GPB1YmuTP+hYtAbYZv1dPVX0fePI47bcDh0zQ5yTgpHHa1wCTne+XJEkTmGrP/uHADt16i/va1wN/OKiiJEnS7Jk07Kvq68DXk5xeVT+ao5okSdIsmu45+4VJTgWW9/epqucOoihJkjR7phv2nwX+N3AasGmKdSVJ0hZkumG/sapOGWglkiRpIKZ7U51/TPLaJLt3T63bOcnOA61MkiTNiunu2Y/eBOctfW0FPHZ2y5EkSbNtWmFfVXsNuhBJkjQY0wr7JEeN115VZ85uOZIkabZN9zD+U/umF9G7A95l9J4tL0mStmDTPYz/+v75JI8EPj6QiiRJ0qza3Efc3k3vqXSSJGkLN91z9v9I7+p76D0A54nAqkEVJUmSZs90z9m/p296I/Cjqlo7gHq2WFXF+vXrWbx4MUmGXY4kSdM2rcP43QNxrqH35LudgF8Msqgt0cYN93DsqRcxMjIyo36jXxKqauqVJUkagGmFfZKXAZcARwAvA76TZKt7xO2ChY+YcZ+RkRFWvv/LM/6SIEnSbJnuYfy/BJ5aVesAkiwF/hk4e1CFtWTBopl/SZAkabZM92r8h40Gfef2GfSVJElDNN09+68mOR/4dDf/cuC8wZQkSZJm06Rhn+TXgd2q6i1JXgo8EwhwMfDJOahPkiQ9RFMdiv8AMAJQVZ+vqj+rqjfS26v/wGBLkyRJs2GqsF9eVd8f21hVa4DlA6lIkiTNqqnCftEky7abzUIkSdJgTBX2303yx2MbkxwLXDqYkiRJ0mya6mr8E4AvJHklvwr3A4GHAy8ZYF2SJGmWTBr2VXUr8PQkzwH265q/XFVfG3hlkiRpVkz3efYXAhcOuJZm+RAdSdIweRe8ObC5D9GRJGk2GPZzZHMeoiNJ0mww7CVJapxhL0lS4wx7SZIaZ9hLktQ4w16SpMYZ9pIkNc6wlySpcYa9JEmNM+wlSWqcYS9JUuMMe0mSGmfYS5LUOMN+jow+5raqhl2KJGkrY9jPER9zK0kaFsN+DvmYW0nSMBj2kiQ1zrCXJKlxhr0kSY0z7CVJapxhL0lS4wx7SZIaN7CwT7JnkguTXJ3kqiRv6Np3TnJBkuu69536+pyY5Pok1yY5tK/9gCRXdMs+lCSDqluSpNYMcs9+I/CmqnoicDBwfJJ9gLcCq6tqb2B1N0+3bCWwL7ACODnJNt22TgGOA/buXisGWLckSU0ZWNhX1S1VdVk3PQJcDewBHAac0a12BnB4N30YcFZVbaiqG4DrgYOS7A4sqaqLq3ev2TP7+mzRRm+RK0nSMM3JOfsky4EnA98BdquqW6D3hQDYtVttD+Cmvm5ru7Y9uumx7Vu8kZERXv2R89m0cdOwS5EkbcUGHvZJdgA+B5xQVZPt5o53Hr4maR/vs45LsibJmttuu23mxQ7AgkXeIleSNFwDDfsk29IL+k9W1ee75lu7Q/N07+u69rXAnn3dlwE3d+3Lxml/kKo6taoOrKoDly5dOnsDkSRpHhvk1fgBPgpcXVXv61t0LnB0N300cE5f+8okC5PsRe9CvEu6Q/0jSQ7utnlUXx9JkjSFBQPc9jOAVwFXJLm8a3sb8C5gVZJjgR8DRwBU1VVJVgE/oHcl//FVNXqy+zXA6cB2wFe6lyRJmoaBhX1VfYvxz7cDHDJBn5OAk8ZpXwPsN3vVSZK09fAOepIkNc6wlySpcYa9JEmNM+wlSWqcYS9JUuMMe0mSGmfYS5LUOMNekqTGGfaSJDXOsJckqXGGvSRJjTPsJUlqnGEvSVLjDHtJkhpn2EuS1DjDXpKkxhn2kiQ1zrCXJKlxhr0kSY0z7CVJapxhL0lS4wx7SZIaZ9hLktQ4w16SpMYZ9pIkNc6wlySpcYa9JEmNM+wlSWqcYS9JUuMMe0mSGmfYS5LUOMN+QKqK9evXD7sMSZIM+0EZGRnh1R85n00bNw27FEnSVs6wH6AFix4x7BIkSTLsJUlqnWE/h0bP41fVsEuRJG1FDPs5tHHDPRx76kWMjIwMuxRJ0lbEsJ9jCxZ6Hl+SNLcMe0mSGmfYS5LUOMNekqTGGfaSJDXOsJckqXGGvSRJjTPsJUlqnGEvSVLjDHtJkhpn2EuS1DjDXpKkxhn2kiQ1zrCXJKlxAwv7JB9Lsi7JlX1tOye5IMl13ftOfctOTHJ9kmuTHNrXfkCSK7plH0qSQdUsSVKLBrlnfzqwYkzbW4HVVbU3sLqbJ8k+wEpg367PyUm26fqcAhwH7N29xm5TkiRNYmBhX1XfAP5zTPNhwBnd9BnA4X3tZ1XVhqq6AbgeOCjJ7sCSqrq4qgo4s6+PJEmahrk+Z79bVd0C0L3v2rXvAdzUt97arm2Pbnps+7iSHJdkTZI1t91226wWLknSfLWlXKA33nn4mqR9XFV1alUdWFUHLl26dNaKkyRpPpvrsL+1OzRP976ua18L7Nm33jLg5q592TjtkiRpmuY67M8Fju6mjwbO6WtfmWRhkr3oXYh3SXeofyTJwd1V+Ef19ZEkSdOwYFAbTvJp4NnALknWAn8NvAtYleRY4MfAEQBVdVWSVcAPgI3A8VW1qdvUa+hd2b8d8JXuJUmSpmlgYV9Vr5hg0SETrH8ScNI47WuA/WaxNEmStipbygV6kiRpQAx7SZIaZ9jPQFWxfv16evf3kSRpfjDsZ2Djhns49tSLGBkZGXYpkiRNm2E/QwsWPmLYJUiSNCOGvSRJjRvYn95pfKPn/QEWL16MT+yVJA2ae/ZzbOOGe/iTMy7hyFMu9Ny/JGlOuGc/BNsu2p5tFmwz7DIkSVsJ9+wlSWqcYS9JUuMMe0mSGmfYS5LUOMNekqTGGfYD0P+39JIkDZthPwAjIyO8+iPns2njpmGXIkmSYT8oCxZ5D31J0pbBsJckqXGGvSRJjTPsJUlqnGEvSVLjDHtJkhpn2EuS1DjDXpKkxhn2kiQ1zrCXJKlxhr0kSY0z7CVJapxhL0lS4wx7SZIaZ9hLktQ4w16SpMYZ9pIkNc6wlySpcYa9JEmNM+wlSWqcYS9JUuMM+xmqKtavX09VDbsUSZKmxbCfoY0b7uHYUy9iZGTkIW3HLw2SpLli2G+GBQsf8ZC3sXHD3bPypUGSpKkY9rNsdI99OmbjS4MkSVMx7GfZyMgIr/7I+WzauGnYpUiSBBj2A7FgkXvskqQth2G/Gby4TpI0nxj2m2G2rsiXJGkuGPabyYvrJEnzhWG/mTyUL0maLwz7zeShfEnSfLFg2AXMZ9s8fLv7/6Z+8eLFJBlyRZIkPZh79g/Bxg338CdnXMKRp1y4WXv48+FUwHyoUZI0uXkT9klWJLk2yfVJ3jrsekZtu2h7tl20PTCzu+fB/DgVMDIywsr3f3mLrlGSNLl5EfZJtgE+ArwA2Ad4RZJ9hlvVr1QVd955J2vXrp3x3fMe6lX9M93z3pw99ZneJGg6nzG6jkcNJGnw5ss5+4OA66vqhwBJzgIOA34w1Ko6GzfczTEf/irQO48/E6NfFO67774HtCdh8eLF3HXXXeywww7cddddVBVVRRKWLFkCwE9+8hP++LRvcOqxz2LJkiXj9gHub68qXvGB8zjrjS9k8eLF94ft6DaTPOgIxVQ19u/1VxUjIyMc99Fvcuqxz2Lx4sUP6rNkyRJGRkY48pQLqSpOfuUB96/Xv83xvgSMXhfRv2yiPv0/w/6fw2i9/X3Gjn90nR122OH+6dHlY8c6Wnv/54/+fkaXb+71HP2fMZNtbG6/udqepLk1X8J+D+Cmvvm1wG/NZQEb7737QWEH8Mt7f859GzfcP7/pF/dMua3RPpt+cQ+bfnEPR773Cw9aZ8HC7fjwMc/kTz/+L3zoVU/nTasu55f33s0v7vk5CxZuxxmvfwEAr3r/F3nYgoUc+d4vTNjnvvvue0A7cP9e9ave/0Xu23Tf/dtcsmTJ/e0PW7CQDx/zTO698/ZJa3ztaat5+PY7ct8vN/CLe35+/7KJ+ozWDr1TGf3r9W/zvk0P/nkvWrLzAz5nsj6j7WN/Dq89bfX9YxvtM3b8x330mwC892X737/+6PJR69ev59Unn88/vPZQAI776Dfv/5zRMY4u7+83E/2fMZNtbG6/udqeJOb0v6XMh0OoSY4ADq2qP+rmXwUcVFWvH7PeccBx3ezjgWtnsYxdgJ/O4va2FK2OC9odm+Oaf1odm+PasvxaVS0db8F82bNfC+zZN78MuHnsSlV1KnDqIApIsqaqDhzEtoep1XFBu2NzXPNPq2NzXPPHvLhAD/gusHeSvZI8HFgJnDvkmiRJmhfmxZ59VW1M8jrgfGAb4GNVddWQy5IkaV6YF2EPUFXnAecNsYSBnB7YArQ6Lmh3bI5r/ml1bI5rnpgXF+hJkqTNN1/O2UuSpM1k2E9hS71N7+ZI8rEk65Jc2de2c5ILklzXve80zBo3R5I9k1yY5OokVyV5Q9c+r8eWZFGSS5J8rxvXO7r2eT2uUUm2SfJvSb7UzbcyrhuTXJHk8iRrurZ5P7YkOyY5O8k13X9rT2tkXI/vflejr/VJTmhhbP0M+0ls6bfp3QynAyvGtL0VWF1VewOru/n5ZiPwpqp6InAwcHz3e5rvY9sAPLeqngTsD6xIcjDzf1yj3gBc3TffyrgAnlNV+/f9+VYLY/sg8NWqegLwJHq/u3k/rqq6tvtd7Q8cANwNfIEGxvYAo7dg9fXgF/A04Py++ROBE4dd10Mc03Lgyr75a4Hdu+ndgWuHXeMsjPEc4HdbGhvwCOAyeneOnPfjonevjNXAc4EvdW3zflxd7TcCu4xpm9djA5YAN9Bd59XKuMYZ5/OBb7c4NvfsJzfebXr3GFItg7JbVd0C0L3vOuR6HpIky4EnA9+hgbF1h7ovB9YBF1RVE+MCPgD8OdB/T+QWxgVQwD8lubS7qyfM/7E9FrgN+Ifu1MtpSbZn/o9rrJXAp7vppsZm2E9uvCd++OcLW6gkOwCfA06oquk/a3gLVlWbqnd4cRlwUJL9hlzSQ5bkRcC6qrp02LUMyDOq6in0Tv8dn+S3h13QLFgAPAU4paqeDPyc+X5Ye4zuhm2/D3x22LUMgmE/uWndpneeuzXJ7gDd+7oh17NZkmxLL+g/WVWf75qbGBtAVd0BXETvmov5Pq5nAL+f5EbgLOC5ST7B/B8XAFV1c/e+jt6534OY/2NbC6ztjiwBnE0v/Of7uPq9ALisqm7t5lsam2E/ha3hNr3nAkd300fTO989r6T3zNWPAldX1fv6Fs3rsSVZmmTHbno74HnANczzcVXViVW1rKqW0/tv6mtVdSTzfFwASbZPsnh0mt454CuZ52Orqv8Abkry+K7pEHqPGJ/X4xrjFfzqED60NTZvqjOVJL9H7/zi6G16TxpuRZsvyaeBZ9N7otOtwF8DXwRWAY8BfgwcUVX/OaQSN0uSZwLfBK7gV+eA30bvvP28HVuS/wKcQe/f3sOAVVX1N0kexTweV78kzwbeXFUvamFcSR5Lb28eeoe+P1VVJzUytv2B04CHAz8EXk3375J5PC6AJI+gd33WY6vqzq5t3v/O+hn2kiQ1zsP4kiQ1zrCXJKlxhr0kSY0z7CVJapxhL0lS4wx7SZIaZ9hLmnNJ3p7kzd303yR53iTrHj7PnzYpDZ1hL2moquqvquqfJ1nlcHqPmJa0mQx7aSvU3db1y0m+l+TKJC9PcmOSdyS5LMkVSZ7QrXtQkn/pnnb2L6O3TE1yTJJzknw1ybVJ/nqKz/zLbr1/Bh7f1356kj/spt+V5AdJvp/kPUmeTu/hJP8zyeVJHjewH4rUsAXDLkDSUKwAbq6qFwIkeSTwbuCnVfWUJK8F3gz8Eb378f92VW3sDre/E/iDbjsHAfsBdwPfTfLlqloz9sOSHEDvPvhPpvf/ncuAS8esszPwEuAJVVVJdqyqO5KcS++Z92fP8s9A2mq4Zy9tna4Anpfk3UmeNXo/cGD0iYGXAsu76UcCn01yJfB+YN++7VxQVbdX1T1d32dO8HnPAr5QVXd3jx8e74FS64F7gdOSvJTeFwhJs8Cwl7ZCVfXvwAH0Qv/vk/xVt2hD976JXx35+1vgwqraD3gxsKh/U2M3PdnHTlHTRnpHCj5H7zz9VycfhaTpMuylrVCSRwN3V9UngPfQezb5RB4J/KSbPmbMst9NsnP3CN7DgW9PsI1vAC9Jsl33CNgXj1PTDsAjq+o84ARg/27RCLB4iiFJmoRhL22dfhO4JMnlwF8CfzfJuv+D3t7/t+k9brfft4CPA5cDnxvvfD1AVV0GfGZ0PXqPJB5rMfClJN8Hvg68sWs/C3hLd4GgF+hJm8FH3EraLEmOAQ6sqtcNuxZJk3PPXpKkxrlnL2nWJHkUsHqcRYdU1e1zXY+kHsNekqTGeRhfkqTGGfaSJDXOsJckqXGGvSRJjTPsJUlq3P8H2+OTVRj2oecAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# distribution of snap distances\n",
    "plt.figure(figsize=(8, 6))\n",
    "\n",
    "sns.histplot(updated_points['snap_dist'])\n",
    "plt.title('Histogram of snap_dist (ft.)')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "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>physicalid</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100019</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>100020</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10003</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>10004</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>100041</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  physicalid  count\n",
       "0     100019      1\n",
       "1     100020      1\n",
       "2      10003      1\n",
       "3      10004      2\n",
       "4     100041      1"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# examine counts per street id\n",
    "gdf_count = (\n",
    "    updated_points\n",
    "    .groupby(by='physicalid')['created_date']\n",
    "    .count()\n",
    "    .reset_index()\n",
    "    .rename(columns={\"created_date\": \"count\"})\n",
    ")\n",
    "\n",
    "gdf_count.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "shape of data: (99124, 13)\n"
     ]
    },
    {
     "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>physicalid</th>\n",
       "      <th>st_label</th>\n",
       "      <th>st_name</th>\n",
       "      <th>full_stree</th>\n",
       "      <th>rw_type</th>\n",
       "      <th>rw_type_name</th>\n",
       "      <th>st_width</th>\n",
       "      <th>frm_lvl_co</th>\n",
       "      <th>to_lvl_co</th>\n",
       "      <th>borocode</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>geometry</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-1</td>\n",
       "      <td>BRUCKNER BLVD</td>\n",
       "      <td>BRUCKNER</td>\n",
       "      <td>BRUCKNER BLVD</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>36.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>2</td>\n",
       "      <td>522.161372</td>\n",
       "      <td>LINESTRING (1010270.223 233448.310, 1010354.99...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>10000</td>\n",
       "      <td>25 AVE</td>\n",
       "      <td>25</td>\n",
       "      <td>25 AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>35.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>254.863947</td>\n",
       "      <td>LINESTRING (1019770.393 217876.440, 1020022.80...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>100000</td>\n",
       "      <td>233 PL</td>\n",
       "      <td>233</td>\n",
       "      <td>233 PL</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>25.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>272.837036</td>\n",
       "      <td>LINESTRING (1052461.825 220583.306, 1052572.26...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>100001</td>\n",
       "      <td>MILBURN ST</td>\n",
       "      <td>MILBURN</td>\n",
       "      <td>MILBURN ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>485.074277</td>\n",
       "      <td>LINESTRING (1051561.903 187846.554, 1051902.84...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>100003</td>\n",
       "      <td>92 AVE</td>\n",
       "      <td>92</td>\n",
       "      <td>92 AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>524.426714</td>\n",
       "      <td>LINESTRING (1057729.808 204117.541, 1058232.69...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  physicalid       st_label   st_name     full_stree rw_type rw_type_name  \\\n",
       "0         -1  BRUCKNER BLVD  BRUCKNER  BRUCKNER BLVD       1       Street   \n",
       "1      10000         25 AVE        25         25 AVE       1       Street   \n",
       "2     100000         233 PL       233         233 PL       1       Street   \n",
       "3     100001     MILBURN ST   MILBURN     MILBURN ST       1       Street   \n",
       "4     100003         92 AVE        92         92 AVE       1       Street   \n",
       "\n",
       "  st_width frm_lvl_co to_lvl_co borocode  shape_leng  \\\n",
       "0     36.0         13        13        2  522.161372   \n",
       "1     35.0         13        13        4  254.863947   \n",
       "2     25.0         13        13        4  272.837036   \n",
       "3     30.0         13        13        4  485.074277   \n",
       "4     30.0         13        13        4  524.426714   \n",
       "\n",
       "                                            geometry  count  \n",
       "0  LINESTRING (1010270.223 233448.310, 1010354.99...      0  \n",
       "1  LINESTRING (1019770.393 217876.440, 1020022.80...      0  \n",
       "2  LINESTRING (1052461.825 220583.306, 1052572.26...      0  \n",
       "3  LINESTRING (1051561.903 187846.554, 1051902.84...      0  \n",
       "4  LINESTRING (1057729.808 204117.541, 1058232.69...      0  "
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# join our street data to our flood complaints data\n",
    "streets_with_count = streets.merge(\n",
    "    gdf_count, \n",
    "    on='physicalid',\n",
    "    how='left'\n",
    ")\n",
    "\n",
    "streets_with_count['count'] = streets_with_count['count'].fillna(0).astype(int)\n",
    "\n",
    "print('shape of data: {}'.format(streets_with_count.shape))\n",
    "streets_with_count.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'geopandas.geodataframe.GeoDataFrame'>\n",
      "Int64Index: 99124 entries, 0 to 99123\n",
      "Data columns (total 13 columns):\n",
      " #   Column        Non-Null Count  Dtype   \n",
      "---  ------        --------------  -----   \n",
      " 0   physicalid    99124 non-null  object  \n",
      " 1   st_label      99124 non-null  object  \n",
      " 2   st_name       99124 non-null  object  \n",
      " 3   full_stree    99124 non-null  object  \n",
      " 4   rw_type       99124 non-null  object  \n",
      " 5   rw_type_name  99124 non-null  object  \n",
      " 6   st_width      99124 non-null  object  \n",
      " 7   frm_lvl_co    99124 non-null  object  \n",
      " 8   to_lvl_co     99124 non-null  object  \n",
      " 9   borocode      99124 non-null  object  \n",
      " 10  shape_leng    99124 non-null  float64 \n",
      " 11  geometry      99124 non-null  geometry\n",
      " 12  count         99124 non-null  int64   \n",
      "dtypes: float64(1), geometry(1), int64(1), object(10)\n",
      "memory usage: 10.6+ MB\n"
     ]
    }
   ],
   "source": [
    "# summarize columns\n",
    "streets_with_count.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "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>physicalid</th>\n",
       "      <th>st_label</th>\n",
       "      <th>st_name</th>\n",
       "      <th>full_stree</th>\n",
       "      <th>rw_type</th>\n",
       "      <th>rw_type_name</th>\n",
       "      <th>st_width</th>\n",
       "      <th>frm_lvl_co</th>\n",
       "      <th>to_lvl_co</th>\n",
       "      <th>borocode</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>geometry</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>93336</th>\n",
       "      <td>93488</td>\n",
       "      <td>157 ST</td>\n",
       "      <td>157</td>\n",
       "      <td>157 ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>35.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>499.593541</td>\n",
       "      <td>LINESTRING (1045395.176 182129.994, 1045149.58...</td>\n",
       "      <td>91</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49354</th>\n",
       "      <td>44654</td>\n",
       "      <td>MILL RD</td>\n",
       "      <td>MILL</td>\n",
       "      <td>MILL RD</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>60.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>404.812271</td>\n",
       "      <td>LINESTRING (952047.247 142027.744, 951842.023 ...</td>\n",
       "      <td>87</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5436</th>\n",
       "      <td>109590</td>\n",
       "      <td>SAPPHIRE ST</td>\n",
       "      <td>SAPPHIRE</td>\n",
       "      <td>SAPPHIRE ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>22.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>3</td>\n",
       "      <td>554.171435</td>\n",
       "      <td>LINESTRING (1023856.014 183443.026, 1023962.36...</td>\n",
       "      <td>71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29929</th>\n",
       "      <td>23726</td>\n",
       "      <td>141 ST</td>\n",
       "      <td>141</td>\n",
       "      <td>141 ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>678.504182</td>\n",
       "      <td>LINESTRING (1039008.416 188480.641, 1039247.01...</td>\n",
       "      <td>71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84116</th>\n",
       "      <td>83475</td>\n",
       "      <td>BEDELL ST</td>\n",
       "      <td>BEDELL</td>\n",
       "      <td>BEDELL ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>651.973881</td>\n",
       "      <td>LINESTRING (1043449.919 189921.878, 1043959.01...</td>\n",
       "      <td>63</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      physicalid     st_label   st_name   full_stree rw_type rw_type_name  \\\n",
       "93336      93488       157 ST       157       157 ST       1       Street   \n",
       "49354      44654      MILL RD      MILL      MILL RD       1       Street   \n",
       "5436      109590  SAPPHIRE ST  SAPPHIRE  SAPPHIRE ST       1       Street   \n",
       "29929      23726       141 ST       141       141 ST       1       Street   \n",
       "84116      83475    BEDELL ST    BEDELL    BEDELL ST       1       Street   \n",
       "\n",
       "      st_width frm_lvl_co to_lvl_co borocode  shape_leng  \\\n",
       "93336     35.0         13        13        4  499.593541   \n",
       "49354     60.0         13        13        5  404.812271   \n",
       "5436      22.0         13        13        3  554.171435   \n",
       "29929     30.0         13        13        4  678.504182   \n",
       "84116     30.0         13        13        4  651.973881   \n",
       "\n",
       "                                                geometry  count  \n",
       "93336  LINESTRING (1045395.176 182129.994, 1045149.58...     91  \n",
       "49354  LINESTRING (952047.247 142027.744, 951842.023 ...     87  \n",
       "5436   LINESTRING (1023856.014 183443.026, 1023962.36...     71  \n",
       "29929  LINESTRING (1039008.416 188480.641, 1039247.01...     71  \n",
       "84116  LINESTRING (1043449.919 189921.878, 1043959.01...     63  "
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# examine highest counts\n",
    "streets_with_count.sort_values(by='count', ascending=False).head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "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>physicalid</th>\n",
       "      <th>st_label</th>\n",
       "      <th>st_name</th>\n",
       "      <th>full_stree</th>\n",
       "      <th>rw_type</th>\n",
       "      <th>rw_type_name</th>\n",
       "      <th>st_width</th>\n",
       "      <th>frm_lvl_co</th>\n",
       "      <th>to_lvl_co</th>\n",
       "      <th>borocode</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>geometry</th>\n",
       "      <th>count</th>\n",
       "      <th>count_per_100ft</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-1</td>\n",
       "      <td>BRUCKNER BLVD</td>\n",
       "      <td>BRUCKNER</td>\n",
       "      <td>BRUCKNER BLVD</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>36.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>2</td>\n",
       "      <td>522.161372</td>\n",
       "      <td>LINESTRING (1010270.223 233448.310, 1010354.99...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>10000</td>\n",
       "      <td>25 AVE</td>\n",
       "      <td>25</td>\n",
       "      <td>25 AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>35.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>254.863947</td>\n",
       "      <td>LINESTRING (1019770.393 217876.440, 1020022.80...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>100000</td>\n",
       "      <td>233 PL</td>\n",
       "      <td>233</td>\n",
       "      <td>233 PL</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>25.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>272.837036</td>\n",
       "      <td>LINESTRING (1052461.825 220583.306, 1052572.26...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>100001</td>\n",
       "      <td>MILBURN ST</td>\n",
       "      <td>MILBURN</td>\n",
       "      <td>MILBURN ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>485.074277</td>\n",
       "      <td>LINESTRING (1051561.903 187846.554, 1051902.84...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>100003</td>\n",
       "      <td>92 AVE</td>\n",
       "      <td>92</td>\n",
       "      <td>92 AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>524.426714</td>\n",
       "      <td>LINESTRING (1057729.808 204117.541, 1058232.69...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  physicalid       st_label   st_name     full_stree rw_type rw_type_name  \\\n",
       "0         -1  BRUCKNER BLVD  BRUCKNER  BRUCKNER BLVD       1       Street   \n",
       "1      10000         25 AVE        25         25 AVE       1       Street   \n",
       "2     100000         233 PL       233         233 PL       1       Street   \n",
       "3     100001     MILBURN ST   MILBURN     MILBURN ST       1       Street   \n",
       "4     100003         92 AVE        92         92 AVE       1       Street   \n",
       "\n",
       "  st_width frm_lvl_co to_lvl_co borocode  shape_leng  \\\n",
       "0     36.0         13        13        2  522.161372   \n",
       "1     35.0         13        13        4  254.863947   \n",
       "2     25.0         13        13        4  272.837036   \n",
       "3     30.0         13        13        4  485.074277   \n",
       "4     30.0         13        13        4  524.426714   \n",
       "\n",
       "                                            geometry  count  count_per_100ft  \n",
       "0  LINESTRING (1010270.223 233448.310, 1010354.99...      0              0.0  \n",
       "1  LINESTRING (1019770.393 217876.440, 1020022.80...      0              0.0  \n",
       "2  LINESTRING (1052461.825 220583.306, 1052572.26...      0              0.0  \n",
       "3  LINESTRING (1051561.903 187846.554, 1051902.84...      0              0.0  \n",
       "4  LINESTRING (1057729.808 204117.541, 1058232.69...      0              0.0  "
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# normalize counts\n",
    "streets_with_count['shape_leng'] = streets_with_count['geometry'].length\n",
    "count_norm = (streets_with_count['count'] / streets_with_count['shape_leng'].replace(0, np.nan) * 100)\n",
    "\n",
    "# counts per 100 ft\n",
    "streets_with_count['count_per_100ft'] = round(count_norm, 2)\n",
    "\n",
    "streets_with_count.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "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>count_per_100ft</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>99124.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.095096</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.979144</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>228.670000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       count_per_100ft\n",
       "count     99124.000000\n",
       "mean          0.095096\n",
       "std           0.979144\n",
       "min           0.000000\n",
       "25%           0.000000\n",
       "50%           0.000000\n",
       "75%           0.000000\n",
       "max         228.670000"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# examine values\n",
    "streets_with_count.loc[:, ['count_per_100ft']].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "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>physicalid</th>\n",
       "      <th>st_label</th>\n",
       "      <th>st_name</th>\n",
       "      <th>full_stree</th>\n",
       "      <th>rw_type</th>\n",
       "      <th>rw_type_name</th>\n",
       "      <th>st_width</th>\n",
       "      <th>frm_lvl_co</th>\n",
       "      <th>to_lvl_co</th>\n",
       "      <th>borocode</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>geometry</th>\n",
       "      <th>count</th>\n",
       "      <th>count_per_100ft</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>12935</th>\n",
       "      <td>155472</td>\n",
       "      <td>W 228 ST</td>\n",
       "      <td>228</td>\n",
       "      <td>W  228 ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>44.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>1</td>\n",
       "      <td>11.807495</td>\n",
       "      <td>LINESTRING (1009588.318 258326.241, 1009580.18...</td>\n",
       "      <td>27</td>\n",
       "      <td>228.67</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39266</th>\n",
       "      <td>3350</td>\n",
       "      <td>E 47 ST</td>\n",
       "      <td>47</td>\n",
       "      <td>E  47 ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>45.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>1</td>\n",
       "      <td>36.576249</td>\n",
       "      <td>LINESTRING (993217.323 213226.959, 993230.240 ...</td>\n",
       "      <td>19</td>\n",
       "      <td>51.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8547</th>\n",
       "      <td>130213</td>\n",
       "      <td>E 68 ST</td>\n",
       "      <td>68</td>\n",
       "      <td>E  68 ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>38.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>3</td>\n",
       "      <td>15.462558</td>\n",
       "      <td>LINESTRING (1007289.058 166879.286, 1007298.11...</td>\n",
       "      <td>6</td>\n",
       "      <td>38.80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29209</th>\n",
       "      <td>22994</td>\n",
       "      <td>SHORE BLVD</td>\n",
       "      <td>SHORE</td>\n",
       "      <td>SHORE BLVD</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>36.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>23.642131</td>\n",
       "      <td>LINESTRING (1004233.755 222267.727, 1004218.39...</td>\n",
       "      <td>9</td>\n",
       "      <td>38.07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25962</th>\n",
       "      <td>199921</td>\n",
       "      <td>HERKIMER ST</td>\n",
       "      <td>HERKIMER</td>\n",
       "      <td>HERKIMER ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>3</td>\n",
       "      <td>17.255823</td>\n",
       "      <td>LINESTRING (1011761.619 185801.742, 1011768.20...</td>\n",
       "      <td>6</td>\n",
       "      <td>34.77</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      physicalid     st_label   st_name   full_stree rw_type rw_type_name  \\\n",
       "12935     155472     W 228 ST       228    W  228 ST       1       Street   \n",
       "39266       3350      E 47 ST        47     E  47 ST       1       Street   \n",
       "8547      130213      E 68 ST        68     E  68 ST       1       Street   \n",
       "29209      22994   SHORE BLVD     SHORE   SHORE BLVD       1       Street   \n",
       "25962     199921  HERKIMER ST  HERKIMER  HERKIMER ST       1       Street   \n",
       "\n",
       "      st_width frm_lvl_co to_lvl_co borocode  shape_leng  \\\n",
       "12935     44.0         13        13        1   11.807495   \n",
       "39266     45.0         13        13        1   36.576249   \n",
       "8547      38.0         13        13        3   15.462558   \n",
       "29209     36.0         13        13        4   23.642131   \n",
       "25962     30.0         13        13        3   17.255823   \n",
       "\n",
       "                                                geometry  count  \\\n",
       "12935  LINESTRING (1009588.318 258326.241, 1009580.18...     27   \n",
       "39266  LINESTRING (993217.323 213226.959, 993230.240 ...     19   \n",
       "8547   LINESTRING (1007289.058 166879.286, 1007298.11...      6   \n",
       "29209  LINESTRING (1004233.755 222267.727, 1004218.39...      9   \n",
       "25962  LINESTRING (1011761.619 185801.742, 1011768.20...      6   \n",
       "\n",
       "       count_per_100ft  \n",
       "12935           228.67  \n",
       "39266            51.95  \n",
       "8547             38.80  \n",
       "29209            38.07  \n",
       "25962            34.77  "
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# sort descending\n",
    "streets_with_count.sort_values(by='count_per_100ft', ascending=False).head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Joining Streets and Counts to Neighborhoods"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "shape of data: (24728, 47)\n"
     ]
    },
    {
     "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>unique_key</th>\n",
       "      <th>created_date</th>\n",
       "      <th>closed_date</th>\n",
       "      <th>agency</th>\n",
       "      <th>agency_name</th>\n",
       "      <th>complaint_type</th>\n",
       "      <th>descriptor</th>\n",
       "      <th>incident_zip</th>\n",
       "      <th>incident_address</th>\n",
       "      <th>street_name</th>\n",
       "      <th>...</th>\n",
       "      <th>rw_type</th>\n",
       "      <th>rw_type_name</th>\n",
       "      <th>st_width</th>\n",
       "      <th>frm_lvl_co</th>\n",
       "      <th>to_lvl_co</th>\n",
       "      <th>borocode</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>geometry</th>\n",
       "      <th>point</th>\n",
       "      <th>snap_dist</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>45283755</td>\n",
       "      <td>2019-12-31T22:42:00.000</td>\n",
       "      <td>2020-01-07T11:07:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>131 GRIMSBY STREET</td>\n",
       "      <td>GRIMSBY STREET</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>22.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>372.785694</td>\n",
       "      <td>POINT (958366.038 148790.805)</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "      <td>3.748273</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>45279697</td>\n",
       "      <td>2019-12-31T07:10:00.000</td>\n",
       "      <td>2019-12-31T09:30:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>131 GRIMSBY STREET</td>\n",
       "      <td>GRIMSBY STREET</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>22.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>372.785694</td>\n",
       "      <td>POINT (958366.038 148790.805)</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "      <td>3.748273</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>45196140</td>\n",
       "      <td>2019-12-18T15:58:00.000</td>\n",
       "      <td>2019-12-20T09:30:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>101 3 STREET</td>\n",
       "      <td>3 STREET</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>204.368178</td>\n",
       "      <td>POINT (951439.252 148866.357)</td>\n",
       "      <td>POINT (951437.000 148868.000)</td>\n",
       "      <td>2.787056</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>45188340</td>\n",
       "      <td>2019-12-18T10:16:00.000</td>\n",
       "      <td>2019-12-20T09:30:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>15 LISBON PLACE</td>\n",
       "      <td>LISBON PLACE</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>308.463539</td>\n",
       "      <td>POINT (954140.677 151248.949)</td>\n",
       "      <td>POINT (954138.000 151251.000)</td>\n",
       "      <td>3.372281</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>45188337</td>\n",
       "      <td>2019-12-18T09:30:00.000</td>\n",
       "      <td>2019-12-18T19:30:00.000</td>\n",
       "      <td>DEP</td>\n",
       "      <td>Department of Environmental Protection</td>\n",
       "      <td>Sewer</td>\n",
       "      <td>Street Flooding (SJ)</td>\n",
       "      <td>10306.0</td>\n",
       "      <td>131 GRIMSBY STREET</td>\n",
       "      <td>GRIMSBY STREET</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>22.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>372.785694</td>\n",
       "      <td>POINT (958366.038 148790.805)</td>\n",
       "      <td>POINT (958363.000 148793.000)</td>\n",
       "      <td>3.748273</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 47 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   unique_key             created_date              closed_date agency  \\\n",
       "0    45283755  2019-12-31T22:42:00.000  2020-01-07T11:07:00.000    DEP   \n",
       "1    45279697  2019-12-31T07:10:00.000  2019-12-31T09:30:00.000    DEP   \n",
       "2    45196140  2019-12-18T15:58:00.000  2019-12-20T09:30:00.000    DEP   \n",
       "3    45188340  2019-12-18T10:16:00.000  2019-12-20T09:30:00.000    DEP   \n",
       "4    45188337  2019-12-18T09:30:00.000  2019-12-18T19:30:00.000    DEP   \n",
       "\n",
       "                              agency_name complaint_type  \\\n",
       "0  Department of Environmental Protection          Sewer   \n",
       "1  Department of Environmental Protection          Sewer   \n",
       "2  Department of Environmental Protection          Sewer   \n",
       "3  Department of Environmental Protection          Sewer   \n",
       "4  Department of Environmental Protection          Sewer   \n",
       "\n",
       "             descriptor  incident_zip    incident_address     street_name  \\\n",
       "0  Street Flooding (SJ)       10306.0  131 GRIMSBY STREET  GRIMSBY STREET   \n",
       "1  Street Flooding (SJ)       10306.0  131 GRIMSBY STREET  GRIMSBY STREET   \n",
       "2  Street Flooding (SJ)       10306.0        101 3 STREET        3 STREET   \n",
       "3  Street Flooding (SJ)       10306.0     15 LISBON PLACE    LISBON PLACE   \n",
       "4  Street Flooding (SJ)       10306.0  131 GRIMSBY STREET  GRIMSBY STREET   \n",
       "\n",
       "   ... rw_type rw_type_name st_width frm_lvl_co to_lvl_co borocode  \\\n",
       "0  ...       1       Street     22.0         13        13        5   \n",
       "1  ...       1       Street     22.0         13        13        5   \n",
       "2  ...       1       Street     30.0         13        13        5   \n",
       "3  ...       1       Street     30.0         13        13        5   \n",
       "4  ...       1       Street     22.0         13        13        5   \n",
       "\n",
       "   shape_leng                       geometry                          point  \\\n",
       "0  372.785694  POINT (958366.038 148790.805)  POINT (958363.000 148793.000)   \n",
       "1  372.785694  POINT (958366.038 148790.805)  POINT (958363.000 148793.000)   \n",
       "2  204.368178  POINT (951439.252 148866.357)  POINT (951437.000 148868.000)   \n",
       "3  308.463539  POINT (954140.677 151248.949)  POINT (954138.000 151251.000)   \n",
       "4  372.785694  POINT (958366.038 148790.805)  POINT (958363.000 148793.000)   \n",
       "\n",
       "  snap_dist  \n",
       "0  3.748273  \n",
       "1  3.748273  \n",
       "2  2.787056  \n",
       "3  3.372281  \n",
       "4  3.748273  \n",
       "\n",
       "[5 rows x 47 columns]"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print('shape of data: {}'.format(updated_points.shape))\n",
    "updated_points.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 24728 entries, 0 to 24727\n",
      "Data columns (total 47 columns):\n",
      " #   Column                          Non-Null Count  Dtype   \n",
      "---  ------                          --------------  -----   \n",
      " 0   unique_key                      24728 non-null  int64   \n",
      " 1   created_date                    24728 non-null  object  \n",
      " 2   closed_date                     24726 non-null  object  \n",
      " 3   agency                          24728 non-null  object  \n",
      " 4   agency_name                     24728 non-null  object  \n",
      " 5   complaint_type                  24728 non-null  object  \n",
      " 6   descriptor                      24728 non-null  object  \n",
      " 7   incident_zip                    24728 non-null  float64 \n",
      " 8   incident_address                15925 non-null  object  \n",
      " 9   street_name                     15925 non-null  object  \n",
      " 10  cross_street_1                  21737 non-null  object  \n",
      " 11  cross_street_2                  21732 non-null  object  \n",
      " 12  address_type                    24728 non-null  object  \n",
      " 13  city                            24728 non-null  object  \n",
      " 14  status                          24728 non-null  object  \n",
      " 15  resolution_description          24725 non-null  object  \n",
      " 16  resolution_action_updated_date  24728 non-null  object  \n",
      " 17  community_board                 24728 non-null  object  \n",
      " 18  bbl                             14536 non-null  float64 \n",
      " 19  borough                         24728 non-null  object  \n",
      " 20  x_coordinate_state_plane        24728 non-null  float64 \n",
      " 21  y_coordinate_state_plane        24728 non-null  float64 \n",
      " 22  open_data_channel_type          24728 non-null  object  \n",
      " 23  park_borough                    24728 non-null  object  \n",
      " 24  latitude                        24728 non-null  float64 \n",
      " 25  longitude                       24728 non-null  float64 \n",
      " 26  location                        24728 non-null  object  \n",
      " 27  ntacode                         24728 non-null  object  \n",
      " 28  county_fips                     24728 non-null  object  \n",
      " 29  ntaname                         24728 non-null  object  \n",
      " 30  boro_name                       24728 non-null  object  \n",
      " 31  boro_code                       24728 non-null  object  \n",
      " 32  line_i                          24728 non-null  float64 \n",
      " 33  physicalid                      24728 non-null  object  \n",
      " 34  st_label                        24728 non-null  object  \n",
      " 35  st_name                         24728 non-null  object  \n",
      " 36  full_stree                      24728 non-null  object  \n",
      " 37  rw_type                         24728 non-null  object  \n",
      " 38  rw_type_name                    24728 non-null  object  \n",
      " 39  st_width                        24728 non-null  object  \n",
      " 40  frm_lvl_co                      24728 non-null  object  \n",
      " 41  to_lvl_co                       24728 non-null  object  \n",
      " 42  borocode                        24728 non-null  object  \n",
      " 43  shape_leng                      24728 non-null  float64 \n",
      " 44  geometry                        24728 non-null  geometry\n",
      " 45  point                           24728 non-null  geometry\n",
      " 46  snap_dist                       24728 non-null  float64 \n",
      "dtypes: float64(9), geometry(2), int64(1), object(35)\n",
      "memory usage: 8.9+ MB\n"
     ]
    }
   ],
   "source": [
    "# summarize columns\n",
    "updated_points.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "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>unique_key</th>\n",
       "      <th>ntacode</th>\n",
       "      <th>county_fips</th>\n",
       "      <th>ntaname</th>\n",
       "      <th>boro_name</th>\n",
       "      <th>boro_code</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>physicalid</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>45283755</td>\n",
       "      <td>SI45</td>\n",
       "      <td>085</td>\n",
       "      <td>New Dorp-Midland Beach</td>\n",
       "      <td>Staten Island</td>\n",
       "      <td>5</td>\n",
       "      <td>372.785694</td>\n",
       "      <td>76941</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>45279697</td>\n",
       "      <td>SI45</td>\n",
       "      <td>085</td>\n",
       "      <td>New Dorp-Midland Beach</td>\n",
       "      <td>Staten Island</td>\n",
       "      <td>5</td>\n",
       "      <td>372.785694</td>\n",
       "      <td>76941</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>45196140</td>\n",
       "      <td>SI45</td>\n",
       "      <td>085</td>\n",
       "      <td>New Dorp-Midland Beach</td>\n",
       "      <td>Staten Island</td>\n",
       "      <td>5</td>\n",
       "      <td>204.368178</td>\n",
       "      <td>89719</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>45188340</td>\n",
       "      <td>SI45</td>\n",
       "      <td>085</td>\n",
       "      <td>New Dorp-Midland Beach</td>\n",
       "      <td>Staten Island</td>\n",
       "      <td>5</td>\n",
       "      <td>308.463539</td>\n",
       "      <td>98849</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>45188337</td>\n",
       "      <td>SI45</td>\n",
       "      <td>085</td>\n",
       "      <td>New Dorp-Midland Beach</td>\n",
       "      <td>Staten Island</td>\n",
       "      <td>5</td>\n",
       "      <td>372.785694</td>\n",
       "      <td>76941</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   unique_key ntacode county_fips                 ntaname      boro_name  \\\n",
       "0    45283755    SI45         085  New Dorp-Midland Beach  Staten Island   \n",
       "1    45279697    SI45         085  New Dorp-Midland Beach  Staten Island   \n",
       "2    45196140    SI45         085  New Dorp-Midland Beach  Staten Island   \n",
       "3    45188340    SI45         085  New Dorp-Midland Beach  Staten Island   \n",
       "4    45188337    SI45         085  New Dorp-Midland Beach  Staten Island   \n",
       "\n",
       "  boro_code  shape_leng physicalid  \n",
       "0         5  372.785694      76941  \n",
       "1         5  372.785694      76941  \n",
       "2         5  204.368178      89719  \n",
       "3         5  308.463539      98849  \n",
       "4         5  372.785694      76941  "
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# retrieve specific columns\n",
    "cols = [\n",
    "    'unique_key',\n",
    "    'ntacode',\n",
    "    'county_fips',\n",
    "    'ntaname',\n",
    "    'boro_name',\n",
    "    'boro_code',\n",
    "    'shape_leng',\n",
    "    'physicalid'\n",
    "]\n",
    "\n",
    "streets_with_nta = updated_points.loc[:, cols]\n",
    "\n",
    "streets_with_nta.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "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>physicalid</th>\n",
       "      <th>ntaname</th>\n",
       "      <th>boro_name</th>\n",
       "      <th>count_complaints</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100019</td>\n",
       "      <td>Lindenwood-Howard Beach</td>\n",
       "      <td>Queens</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>100020</td>\n",
       "      <td>Lindenwood-Howard Beach</td>\n",
       "      <td>Queens</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10003</td>\n",
       "      <td>East Elmhurst</td>\n",
       "      <td>Queens</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>10004</td>\n",
       "      <td>East Elmhurst</td>\n",
       "      <td>Queens</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>100041</td>\n",
       "      <td>Queens Village</td>\n",
       "      <td>Queens</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  physicalid                  ntaname boro_name  count_complaints\n",
       "0     100019  Lindenwood-Howard Beach    Queens                 1\n",
       "1     100020  Lindenwood-Howard Beach    Queens                 1\n",
       "2      10003            East Elmhurst    Queens                 1\n",
       "3      10004            East Elmhurst    Queens                 2\n",
       "4     100041           Queens Village    Queens                 1"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check for duplicates\n",
    "checking_for_duplicates = (\n",
    "    streets_with_nta\n",
    "    .groupby(by=['physicalid', 'ntaname', 'boro_name'])['shape_leng']\n",
    "    .count()\n",
    "    .reset_index()\n",
    "    .rename(columns={\"shape_leng\": \"count_complaints\"})\n",
    ")\n",
    "\n",
    "checking_for_duplicates.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "street id is unique: False\n"
     ]
    }
   ],
   "source": [
    "print('street id is unique: {}'.format(checking_for_duplicates['physicalid'].is_unique))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "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>physicalid</th>\n",
       "      <th>ntaname</th>\n",
       "      <th>boro_name</th>\n",
       "      <th>count_complaints</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>153</th>\n",
       "      <td>101111</td>\n",
       "      <td>Lindenwood-Howard Beach</td>\n",
       "      <td>Queens</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>152</th>\n",
       "      <td>101111</td>\n",
       "      <td>East New York</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>546</th>\n",
       "      <td>10779</td>\n",
       "      <td>Middle Village</td>\n",
       "      <td>Queens</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>547</th>\n",
       "      <td>10779</td>\n",
       "      <td>Ridgewood</td>\n",
       "      <td>Queens</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>562</th>\n",
       "      <td>109590</td>\n",
       "      <td>Lindenwood-Howard Beach</td>\n",
       "      <td>Queens</td>\n",
       "      <td>53</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>561</th>\n",
       "      <td>109590</td>\n",
       "      <td>East New York</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>591</th>\n",
       "      <td>1128</td>\n",
       "      <td>Hudson Yards-Chelsea-Flatiron-Union Square</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>592</th>\n",
       "      <td>1128</td>\n",
       "      <td>Midtown-Midtown South</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>600</th>\n",
       "      <td>1134</td>\n",
       "      <td>Clinton</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>601</th>\n",
       "      <td>1134</td>\n",
       "      <td>Midtown-Midtown South</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    physicalid                                     ntaname  boro_name  \\\n",
       "153     101111                     Lindenwood-Howard Beach     Queens   \n",
       "152     101111                               East New York   Brooklyn   \n",
       "546      10779                              Middle Village     Queens   \n",
       "547      10779                                   Ridgewood     Queens   \n",
       "562     109590                     Lindenwood-Howard Beach     Queens   \n",
       "561     109590                               East New York   Brooklyn   \n",
       "591       1128  Hudson Yards-Chelsea-Flatiron-Union Square  Manhattan   \n",
       "592       1128                       Midtown-Midtown South  Manhattan   \n",
       "600       1134                                     Clinton  Manhattan   \n",
       "601       1134                       Midtown-Midtown South  Manhattan   \n",
       "\n",
       "     count_complaints  \n",
       "153                11  \n",
       "152                 1  \n",
       "546                 1  \n",
       "547                 1  \n",
       "562                53  \n",
       "561                18  \n",
       "591                 2  \n",
       "592                 2  \n",
       "600                 5  \n",
       "601                 3  "
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(checking_for_duplicates\n",
    " .loc[checking_for_duplicates.duplicated(subset=['physicalid'], keep=False) == True]\n",
    " .sort_values(by=['physicalid', 'count_complaints'], ascending=[True, False])\n",
    " .head(10)\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count of duplicates: 126\n",
      "percent duplicates: 0.13%\n"
     ]
    }
   ],
   "source": [
    "count_duplicates = (\n",
    "    checking_for_duplicates\n",
    "    .loc[checking_for_duplicates.duplicated(subset=['physicalid'], keep=False) == True]\n",
    "    .shape[0]\n",
    ")\n",
    "\n",
    "counts = round(count_duplicates / streets_with_count.shape[0] * 100, 2)\n",
    "\n",
    "print('count of duplicates: {:,}'.format(count_duplicates))\n",
    "print('percent duplicates: {}%'.format(counts))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "physical id is unique: True\n"
     ]
    },
    {
     "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>physicalid</th>\n",
       "      <th>ntaname</th>\n",
       "      <th>boro_name</th>\n",
       "      <th>count_complaints</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100019</td>\n",
       "      <td>Lindenwood-Howard Beach</td>\n",
       "      <td>Queens</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>100020</td>\n",
       "      <td>Lindenwood-Howard Beach</td>\n",
       "      <td>Queens</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10003</td>\n",
       "      <td>East Elmhurst</td>\n",
       "      <td>Queens</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>10004</td>\n",
       "      <td>East Elmhurst</td>\n",
       "      <td>Queens</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>100041</td>\n",
       "      <td>Queens Village</td>\n",
       "      <td>Queens</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  physicalid                  ntaname boro_name  count_complaints\n",
       "0     100019  Lindenwood-Howard Beach    Queens                 1\n",
       "1     100020  Lindenwood-Howard Beach    Queens                 1\n",
       "2      10003            East Elmhurst    Queens                 1\n",
       "3      10004            East Elmhurst    Queens                 2\n",
       "4     100041           Queens Village    Queens                 1"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# sorting descending by number of complaints on a street in a given NTA\n",
    "# then removing duplicates\n",
    "unique_streets = (\n",
    "    checking_for_duplicates\n",
    "    .sort_values(by=['physicalid', 'count_complaints'], ascending=[True, False])\n",
    "    .drop_duplicates('physicalid')\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "print('physical id is unique: {}'.format(unique_streets['physicalid'].is_unique))\n",
    "unique_streets.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "shape of data: (99124, 17)\n"
     ]
    },
    {
     "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>physicalid</th>\n",
       "      <th>st_label</th>\n",
       "      <th>st_name</th>\n",
       "      <th>full_stree</th>\n",
       "      <th>rw_type</th>\n",
       "      <th>rw_type_name</th>\n",
       "      <th>st_width</th>\n",
       "      <th>frm_lvl_co</th>\n",
       "      <th>to_lvl_co</th>\n",
       "      <th>borocode</th>\n",
       "      <th>shape_leng</th>\n",
       "      <th>geometry</th>\n",
       "      <th>count</th>\n",
       "      <th>count_per_100ft</th>\n",
       "      <th>ntaname</th>\n",
       "      <th>boro_name</th>\n",
       "      <th>count_complaints</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-1</td>\n",
       "      <td>BRUCKNER BLVD</td>\n",
       "      <td>BRUCKNER</td>\n",
       "      <td>BRUCKNER BLVD</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>36.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>2</td>\n",
       "      <td>522.161372</td>\n",
       "      <td>LINESTRING (1010270.223 233448.310, 1010354.99...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>10000</td>\n",
       "      <td>25 AVE</td>\n",
       "      <td>25</td>\n",
       "      <td>25 AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>35.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>254.863947</td>\n",
       "      <td>LINESTRING (1019770.393 217876.440, 1020022.80...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>100000</td>\n",
       "      <td>233 PL</td>\n",
       "      <td>233</td>\n",
       "      <td>233 PL</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>25.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>272.837036</td>\n",
       "      <td>LINESTRING (1052461.825 220583.306, 1052572.26...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>100001</td>\n",
       "      <td>MILBURN ST</td>\n",
       "      <td>MILBURN</td>\n",
       "      <td>MILBURN ST</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>485.074277</td>\n",
       "      <td>LINESTRING (1051561.903 187846.554, 1051902.84...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>100003</td>\n",
       "      <td>92 AVE</td>\n",
       "      <td>92</td>\n",
       "      <td>92 AVE</td>\n",
       "      <td>1</td>\n",
       "      <td>Street</td>\n",
       "      <td>30.0</td>\n",
       "      <td>13</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "      <td>524.426714</td>\n",
       "      <td>LINESTRING (1057729.808 204117.541, 1058232.69...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  physicalid       st_label   st_name     full_stree rw_type rw_type_name  \\\n",
       "0         -1  BRUCKNER BLVD  BRUCKNER  BRUCKNER BLVD       1       Street   \n",
       "1      10000         25 AVE        25         25 AVE       1       Street   \n",
       "2     100000         233 PL       233         233 PL       1       Street   \n",
       "3     100001     MILBURN ST   MILBURN     MILBURN ST       1       Street   \n",
       "4     100003         92 AVE        92         92 AVE       1       Street   \n",
       "\n",
       "  st_width frm_lvl_co to_lvl_co borocode  shape_leng  \\\n",
       "0     36.0         13        13        2  522.161372   \n",
       "1     35.0         13        13        4  254.863947   \n",
       "2     25.0         13        13        4  272.837036   \n",
       "3     30.0         13        13        4  485.074277   \n",
       "4     30.0         13        13        4  524.426714   \n",
       "\n",
       "                                            geometry  count  count_per_100ft  \\\n",
       "0  LINESTRING (1010270.223 233448.310, 1010354.99...      0              0.0   \n",
       "1  LINESTRING (1019770.393 217876.440, 1020022.80...      0              0.0   \n",
       "2  LINESTRING (1052461.825 220583.306, 1052572.26...      0              0.0   \n",
       "3  LINESTRING (1051561.903 187846.554, 1051902.84...      0              0.0   \n",
       "4  LINESTRING (1057729.808 204117.541, 1058232.69...      0              0.0   \n",
       "\n",
       "  ntaname boro_name  count_complaints  \n",
       "0     NaN       NaN               NaN  \n",
       "1     NaN       NaN               NaN  \n",
       "2     NaN       NaN               NaN  \n",
       "3     NaN       NaN               NaN  \n",
       "4     NaN       NaN               NaN  "
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# joining streets with count complaints to unique streets\n",
    "streets_with_count_nta = streets_with_count.merge(\n",
    "    unique_streets, \n",
    "    left_on='physicalid', \n",
    "    right_on='physicalid', \n",
    "    how='left'\n",
    ")\n",
    "\n",
    "print('shape of data: {}'.format(streets_with_count_nta.shape))\n",
    "streets_with_count_nta.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'geopandas.geodataframe.GeoDataFrame'>\n",
      "Int64Index: 99124 entries, 0 to 99123\n",
      "Data columns (total 17 columns):\n",
      " #   Column            Non-Null Count  Dtype   \n",
      "---  ------            --------------  -----   \n",
      " 0   physicalid        99124 non-null  object  \n",
      " 1   st_label          99124 non-null  object  \n",
      " 2   st_name           99124 non-null  object  \n",
      " 3   full_stree        99124 non-null  object  \n",
      " 4   rw_type           99124 non-null  object  \n",
      " 5   rw_type_name      99124 non-null  object  \n",
      " 6   st_width          99124 non-null  object  \n",
      " 7   frm_lvl_co        99124 non-null  object  \n",
      " 8   to_lvl_co         99124 non-null  object  \n",
      " 9   borocode          99124 non-null  object  \n",
      " 10  shape_leng        99124 non-null  float64 \n",
      " 11  geometry          99124 non-null  geometry\n",
      " 12  count             99124 non-null  int64   \n",
      " 13  count_per_100ft   99124 non-null  float64 \n",
      " 14  ntaname           11989 non-null  object  \n",
      " 15  boro_name         11989 non-null  object  \n",
      " 16  count_complaints  11989 non-null  float64 \n",
      "dtypes: float64(3), geometry(1), int64(1), object(12)\n",
      "memory usage: 13.6+ MB\n"
     ]
    }
   ],
   "source": [
    "# examine columns\n",
    "streets_with_count_nta.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "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>physicalid</th>\n",
       "      <th>full_stree</th>\n",
       "      <th>ntaname</th>\n",
       "      <th>boro_name</th>\n",
       "      <th>count</th>\n",
       "      <th>count_per_100ft</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>93336</th>\n",
       "      <td>93488</td>\n",
       "      <td>157 ST</td>\n",
       "      <td>Springfield Gardens South-Brookville</td>\n",
       "      <td>Queens</td>\n",
       "      <td>91</td>\n",
       "      <td>18.21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49354</th>\n",
       "      <td>44654</td>\n",
       "      <td>MILL RD</td>\n",
       "      <td>Oakwood-Oakwood Beach</td>\n",
       "      <td>Staten Island</td>\n",
       "      <td>87</td>\n",
       "      <td>21.49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5436</th>\n",
       "      <td>109590</td>\n",
       "      <td>SAPPHIRE ST</td>\n",
       "      <td>Lindenwood-Howard Beach</td>\n",
       "      <td>Queens</td>\n",
       "      <td>71</td>\n",
       "      <td>12.81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29929</th>\n",
       "      <td>23726</td>\n",
       "      <td>141 ST</td>\n",
       "      <td>Baisley Park</td>\n",
       "      <td>Queens</td>\n",
       "      <td>71</td>\n",
       "      <td>10.46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84116</th>\n",
       "      <td>83475</td>\n",
       "      <td>BEDELL ST</td>\n",
       "      <td>Baisley Park</td>\n",
       "      <td>Queens</td>\n",
       "      <td>63</td>\n",
       "      <td>9.66</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      physicalid   full_stree                               ntaname  \\\n",
       "93336      93488       157 ST  Springfield Gardens South-Brookville   \n",
       "49354      44654      MILL RD                 Oakwood-Oakwood Beach   \n",
       "5436      109590  SAPPHIRE ST               Lindenwood-Howard Beach   \n",
       "29929      23726       141 ST                          Baisley Park   \n",
       "84116      83475    BEDELL ST                          Baisley Park   \n",
       "\n",
       "           boro_name  count  count_per_100ft  \n",
       "93336         Queens     91            18.21  \n",
       "49354  Staten Island     87            21.49  \n",
       "5436          Queens     71            12.81  \n",
       "29929         Queens     71            10.46  \n",
       "84116         Queens     63             9.66  "
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# retrieve desired columns\n",
    "cols = [\n",
    "    'physicalid','full_stree', 'ntaname', 'boro_name',\n",
    "    'count', 'count_per_100ft'\n",
    "]\n",
    "\n",
    "count_by_nta = (\n",
    "    streets_with_count_nta\n",
    "    .loc[:, cols]\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "# sort on count desc\n",
    "count_by_nta.sort_values(by='count', ascending=False).head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "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>physicalid</th>\n",
       "      <th>full_stree</th>\n",
       "      <th>ntaname</th>\n",
       "      <th>boro_name</th>\n",
       "      <th>count</th>\n",
       "      <th>count_per_100ft</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>12935</th>\n",
       "      <td>155472</td>\n",
       "      <td>W  228 ST</td>\n",
       "      <td>Marble Hill-Inwood</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>27</td>\n",
       "      <td>228.67</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39266</th>\n",
       "      <td>3350</td>\n",
       "      <td>E  47 ST</td>\n",
       "      <td>Turtle Bay-East Midtown</td>\n",
       "      <td>Manhattan</td>\n",
       "      <td>19</td>\n",
       "      <td>51.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8547</th>\n",
       "      <td>130213</td>\n",
       "      <td>E  68 ST</td>\n",
       "      <td>Georgetown-Marine Park-Bergen Beach-Mill Basin</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>6</td>\n",
       "      <td>38.80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29209</th>\n",
       "      <td>22994</td>\n",
       "      <td>SHORE BLVD</td>\n",
       "      <td>Old Astoria</td>\n",
       "      <td>Queens</td>\n",
       "      <td>9</td>\n",
       "      <td>38.07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25962</th>\n",
       "      <td>199921</td>\n",
       "      <td>HERKIMER ST</td>\n",
       "      <td>Ocean Hill</td>\n",
       "      <td>Brooklyn</td>\n",
       "      <td>6</td>\n",
       "      <td>34.77</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      physicalid   full_stree                                         ntaname  \\\n",
       "12935     155472    W  228 ST                              Marble Hill-Inwood   \n",
       "39266       3350     E  47 ST                         Turtle Bay-East Midtown   \n",
       "8547      130213     E  68 ST  Georgetown-Marine Park-Bergen Beach-Mill Basin   \n",
       "29209      22994   SHORE BLVD                                     Old Astoria   \n",
       "25962     199921  HERKIMER ST                                      Ocean Hill   \n",
       "\n",
       "       boro_name  count  count_per_100ft  \n",
       "12935  Manhattan     27           228.67  \n",
       "39266  Manhattan     19            51.95  \n",
       "8547    Brooklyn      6            38.80  \n",
       "29209     Queens      9            38.07  \n",
       "25962   Brooklyn      6            34.77  "
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# sort on count per 100ft desc\n",
    "count_by_nta.sort_values(by='count_per_100ft', ascending=False).head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "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>count</th>\n",
       "      <th>count_per_100ft</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>99124.000000</td>\n",
       "      <td>99124.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.249465</td>\n",
       "      <td>0.095096</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1.308244</td>\n",
       "      <td>0.979144</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>91.000000</td>\n",
       "      <td>228.670000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              count  count_per_100ft\n",
       "count  99124.000000     99124.000000\n",
       "mean       0.249465         0.095096\n",
       "std        1.308244         0.979144\n",
       "min        0.000000         0.000000\n",
       "25%        0.000000         0.000000\n",
       "50%        0.000000         0.000000\n",
       "75%        0.000000         0.000000\n",
       "max       91.000000       228.670000"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# summary statistics\n",
    "(streets_with_count\n",
    " .groupby(by=['physicalid', 'full_stree'])[['count', 'count_per_100ft']]\n",
    " .sum()\n",
    " .reset_index()\n",
    " .describe()\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "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>physicalid</th>\n",
       "      <th>full_stree</th>\n",
       "      <th>ntaname</th>\n",
       "      <th>boro_name</th>\n",
       "      <th>count</th>\n",
       "      <th>count_per_100ft</th>\n",
       "      <th>ntaname_full</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>93336</th>\n",
       "      <td>93488</td>\n",
       "      <td>157 ST</td>\n",
       "      <td>Springfield Gardens South-Brookville</td>\n",
       "      <td>Queens</td>\n",
       "      <td>91</td>\n",
       "      <td>18.21</td>\n",
       "      <td>157 ST (id: 93488), Springfield Gardens South-...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49354</th>\n",
       "      <td>44654</td>\n",
       "      <td>MILL RD</td>\n",
       "      <td>Oakwood-Oakwood Beach</td>\n",
       "      <td>Staten Island</td>\n",
       "      <td>87</td>\n",
       "      <td>21.49</td>\n",
       "      <td>MILL RD (id: 44654), Oakwood-Oakwood Beach, St...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5436</th>\n",
       "      <td>109590</td>\n",
       "      <td>SAPPHIRE ST</td>\n",
       "      <td>Lindenwood-Howard Beach</td>\n",
       "      <td>Queens</td>\n",
       "      <td>71</td>\n",
       "      <td>12.81</td>\n",
       "      <td>SAPPHIRE ST (id: 109590), Lindenwood-Howard Be...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29929</th>\n",
       "      <td>23726</td>\n",
       "      <td>141 ST</td>\n",
       "      <td>Baisley Park</td>\n",
       "      <td>Queens</td>\n",
       "      <td>71</td>\n",
       "      <td>10.46</td>\n",
       "      <td>141 ST (id: 23726), Baisley Park, Queens</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84116</th>\n",
       "      <td>83475</td>\n",
       "      <td>BEDELL ST</td>\n",
       "      <td>Baisley Park</td>\n",
       "      <td>Queens</td>\n",
       "      <td>63</td>\n",
       "      <td>9.66</td>\n",
       "      <td>BEDELL ST (id: 83475), Baisley Park, Queens</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      physicalid   full_stree                               ntaname  \\\n",
       "93336      93488       157 ST  Springfield Gardens South-Brookville   \n",
       "49354      44654      MILL RD                 Oakwood-Oakwood Beach   \n",
       "5436      109590  SAPPHIRE ST               Lindenwood-Howard Beach   \n",
       "29929      23726       141 ST                          Baisley Park   \n",
       "84116      83475    BEDELL ST                          Baisley Park   \n",
       "\n",
       "           boro_name  count  count_per_100ft  \\\n",
       "93336         Queens     91            18.21   \n",
       "49354  Staten Island     87            21.49   \n",
       "5436          Queens     71            12.81   \n",
       "29929         Queens     71            10.46   \n",
       "84116         Queens     63             9.66   \n",
       "\n",
       "                                            ntaname_full  \n",
       "93336  157 ST (id: 93488), Springfield Gardens South-...  \n",
       "49354  MILL RD (id: 44654), Oakwood-Oakwood Beach, St...  \n",
       "5436   SAPPHIRE ST (id: 109590), Lindenwood-Howard Be...  \n",
       "29929           141 ST (id: 23726), Baisley Park, Queens  \n",
       "84116        BEDELL ST (id: 83475), Baisley Park, Queens  "
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Adding nta information\n",
    "count_by_nta['ntaname_full'] = (\n",
    "    count_by_nta['full_stree']\n",
    "    + \" (id: \"\n",
    "    + count_by_nta['physicalid']\n",
    "    + \"), \" + count_by_nta['ntaname']\n",
    "    + \", \"\n",
    "    + count_by_nta['boro_name']\n",
    ")\n",
    "\n",
    "count_by_nta.sort_values(by='count', ascending=False).head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(figsize=(8, 6))\n",
    "\n",
    "data = count_by_nta.sort_values(by='count', ascending=False).head(10)\n",
    "sns.barplot(\n",
    "    data=data,\n",
    "    y='ntaname_full',\n",
    "    x='count',\n",
    "    color='#1f77b4'\n",
    ")\n",
    "\n",
    "label = 'Count of NYC 311 Street Flooding Complaints by Street Segment (2010 - 2020)'\n",
    "fig.suptitle(label, fontsize=12)\n",
    "plt.xlabel('Count', fontsize=12)\n",
    "plt.ylabel('Street Segment\\n', fontsize=12)\n",
    "\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(figsize=(10, 6))\n",
    "\n",
    "data = count_by_nta.sort_values(by='count_per_100ft', ascending=False).head(10)\n",
    "sns.barplot(\n",
    "    data=data,\n",
    "    y='ntaname_full',\n",
    "    x='count_per_100ft',\n",
    "    color='#1f77b4'\n",
    ")\n",
    "\n",
    "label = 'Count of NYC 311 Street Flooding Complaints per 100 ft. by Street Segment (2010 - 2020)'\n",
    "fig.suptitle(label, fontsize=12)\n",
    "plt.xlabel('Count per 100 ft.', fontsize=12)\n",
    "plt.ylabel('Street Segment', fontsize=12)\n",
    "\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAswAAAI8CAYAAADlQ/0DAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAAsTAAALEwEAmpwYAAEAAElEQVR4nOydd7hVxdWH3x9FRcCGDUXFjoKCgr1hL7ERMahY0BhjojExny3R2I0FE2MvMdYodg12FEUQQQWkilhRsVcUwYbr+2PW8W4O+5QLXO69sN7nuc/de+qa2XPOXrNmzRyZGUEQBEEQBEEQ5NOkvgUIgiAIgiAIgoZMKMxBEARBEARBUIZQmIMgCIIgCIKgDKEwB0EQBEEQBEEZQmEOgiAIgiAIgjKEwhwEQRAEQRAEZQiFOQgWQCT1kPSupGmSNqpveYLKSOouaUodlNtekklq5vePSjpsXtfTkKhNX0rqLWnAfJCpj6Rn67qeYP6hxI2SvpD0Qn3LE9QtoTAHQRkkHSRphCueH7iysfV8qNckrTUXRVwMHGtmrczspRLlj5PUJBN2rqSbJLWQ9JqkQ4vynCFpqKQmktpK+o/3ydeSXpF0lqSWOXUt6/k+k/SlpGGStsrEd5L0uKRPJc12MLykY/0ZfCfppnKNlrSIpH9ImuLP7C1Jl2TiJ0vaqVLnzSnef+dWSGOSvnH5pkn6sq7kycPMdjezm+uibElLSPqXpHe8ba/7/bJ1Ud+8wMxuM7NdqknbUJReSR0lDXBF7UtJIyXt4XF1MvEqqr/s91Olz2FjoHiiWYKtgZ2Bdma26XwS7WcknShpvH8HvyXpxKL49pKeljTdv6N3ysS1ldRf0vvezvZFeReVdIOkryR9KOnPZeSYqzEn6ReSnvWx/KGkf0tqXY0sktaR9D9Jn0j63N8l6xaVf7znm+rlLDoncobCHAQl8A/lv4C/AysAqwJXAfvUo1jVshowoUKalYADigPNbAbwa+CfklYAkLQe8GcPXwoYBrQAtjCz1qSXxlLAmjn1TAOOAJYDlgYuBB7MvIh+AO7ysvN4HzgXuKFCewD+AnQDNgVaA9sDs00YSlHh5Tgv6eyTmVZmttR8qrNOkbQIMBDoCOwGLAFsCXxGeh7BvONB4AnS99LywHHAV9Vmng/jfK4+h42I1YDJZvZNXuR86GcBh5K+V3cDjpWU/U7vR+r3NsCpwD2SlvO4n4DHgP1KlH0msDapjdsDJ0nabV43wFmS9B2/ErAe0A7oW6UsSwH9gXVJn4cXgP8VMkraFTgF2BFoD6wBnDVHUppZ/MVf/BX9+Qd4GrB/mTSLkhTq9/3vX8CiHtcHeLYovQFr+fVNwJXAw8DXwPPAmh432NN+4zL0yqm7CXAa8DbwMXCLy7yo5ynkf6OE7AacDLwGNPOwc4GbMmmuBO4mfSk/C5ySSTcOaDIH/doE2MvrX74obq30lVQy7yzylUjzEPCnEnG3kl4SM7yPTiJ9gRpJWX8HGOxpjwAmAl8AjwOrZcrpQFJWPgcmAb/y8KNIyv/3Xv6DZfp+rZzw7sCUzP16wCDgS9LkZ++i8XkL8ImPgdMKzwNoSlph+BR4EzjG6yw850HAkdlx6um/AN4Cds/Us7qPx6+BJ31M/LdEu44EPgJalXk+5dp0E2lC+qj331BgRdLn6gvgFWCjTPrJJMXsZY+/EVisRF+eArzh7XgZ6JGJ60Pms+p9dTTps/GFt1ku+7fATJfvS0+/h5f5NfAecEKJtvfxNl0OTPX27Ohx+wMji9L/H/BATjnLuoxL5cS1JI3vn1zGaSQl5EzgHuC/JMX6SNIY+g/wgct9LtA0U1buZ4Dqvp9Kfg49fiXgXtL4fQs4LhPXArjZ651I+pxmn+Vk4ERgrMvwH5Ki9Cg143TpTPrNgedIY24M0D0TNwg4x5/L18AAYFmPe8fbWejHLYra8Oui8XAWPu5I360fkr5zyr0nCulPIn2PfwDsSxpTr5K+Y/5ai+/Xy4DL/Xod4DugdSZ+CHB0UZ5m3s72ReHvAbtk7s8B7qjFmCvZ7ira8UtgXG1l8bhlvD1t/P524O+Z+B2BD6vt01nKnpNM8Rd/C/ofabb+I65klEhzNjCcZOFZzr+Uz/G4PlRWmD8nWWCaAbdlvwAooVRl4o8AXifNllsB9wG31iK/kWbsI6lRnooV5lakl9N9wAj8ZeptPmsO+nQsSZk04N858fNCYT6N9KL7PbABoKL4ycBOmfv2Ls8t/sXfgvTCep2kIDXzMp/z9C2Bd4HDPW5jkmLaMfNcz60gY0WFGWjuMvwVWATYgfRCX9fjbyFZUVp7G14Ffu1xR5OUsVVIL4+nKa8w/wD8hqRo/470cpPHDyMp04uQlp+/orTCfAdwc5l2V2rTTd6XXYHFgKdIytShLtu5wNNFz3J8pp1DC33P7Arz/qSXeBOgF0nRapv3WfW+eohkuVqVpNTtVuZz/QGwjV8vDWxcov19SN8px3tf9CIpzsuQlIvPgfUy6V8C9sspRyRl/iHSWF2h1DjKhJ3pz3lf74MWwAPAtaQxvTzJMvdbT78vJT4DVX6/lPwcev0jgdN9HKxBmtjt6vEXAM94X7YjfW8UK8zDSUryyiRFcxSwkffjU8AZnnZl0grHHl7vzn6/XOaz8AZJuWzh9xcUfTeUewfMMh68738kraIt6mWWe08U0p/uY+I3pPF2O+mz3ZGklK9RxferfMwc7fc9gIlFaa7AFepM2GwKs/e9kRlbQE8ySmwVY65ku6toy7/w9+EcyLIv8EHmfgyZSR01E8421cgyS9m1zRB/8bcw/AG9qTAL9S/aPTL3u5KW52b7IvWwYoX5+kzcHsAreWlL1D0Q+H3mfl3SC7FZlfmNpKDuQXqxLUqOQgr8wtN2zoS9RpGVohb9uhhwIHBYTty8UJibkiyqQ0nWlfezdVFaYV4jE/Yornz6fRNgOmk5sBcwpKjOa6l5Qd9EdQrzVySL15fAZR7enRqFeRuShapJJl8/kuLT1Nu2fibut8Agv34q+3yAXSivML+eSbu4p12RpCz+CCyeif8vpRXmJ3Blo0R8yTZl+u7fmbg/kHnhkxSvL4ueZbade+ArKuS8wItkGQ3sk/dZ9fZvnbm/i5rVlVnSetg73v9LVHjufchMRjzsBeAQv74aOM+vO5IsrLkWOZIieQXpO+gnktV37VJt93EzOHO/go+hFpmwA/EJCWU+A5k+Kvf9UvJzCGwGvFOU/i/AjX79s/Ls90cyu8LcO3N/L3B10bh5wK9PJmNI8LDHM7IMAk7LxP0eeMxm/W6orcL8Pb7S4WHl3hPdSdbZgjGitde5WSb9SGDfcmPL051FUg4L1utDgOFFac5j9u/4PIV5FQ/LtmPngtw5deeNuZLtrtCOnUljf53aykL6XLwHHFgkx26Z++bF7a32L3yYgyCfz4BlK/igrURaDi/wtodVy4eZ6+kki2615NXdjPQirBoze4T0wj+qRJIJRf8h9U3b2tSTqe9bM+sHnCKp85yUUaH8mWZ2pZltRbIQngfc4D7Y5Xg3c70acKlvQPmSZPkTyVq1GrBZIc7je5MUzNqwsZkt5X/H5cSvBLxrZj9lwt52GZYlWeaKn//K2bxFceX4eRya2XS/bOXlfJ4Jo6jcYiqNi3JtKvBR5npGzn3xZ6S4nbmfP0mHShqdeWadSP1Yitp8NvcjKetvS3pG0hZl0r5n/tbOkflm4CBJIik7d5nZd3mFmNkUMzvWzNYkjclvSKsO5Sge482BDzJ9ci3JGliIL/UZqEiFz+FqwEpFn6G/UvPdVTx+88ZcteNkNWD/orq2ZtZxOjffw3l8YmbfZu4rvSc+M7OZGdmh8rifBUnHklZifpEZM9NI+wiyLEFa1anEtEz62uYtUOv3o6TNSdb1nmb2am1kcd/sAcBV/o4pUNwPhevatAWITX9BUIphpKWwfcukeZ/0hVxgVQ+D9AJbvBAhqbYKVSXy6v6RWb9oq+U00oaQxSsldJ4EeihzwsYc0Jy0FFtnmNkMM7uSZK1YvxBcKnnm+l3S0vRSmb8WZvacxz1TFNfKzH5Xofza8j6wSlEfr0qynnxKWk0ofv7v+fUHJKtMNm5O+ABYRlJ2XKxSKjFpXOyqnJNSnHJtmlOK2/l+cQJJqwH/Bo4lLcMuRXLl0BzUN9vzNbMXzWwfkrL5AMkiXYqVXSGeTWYzG06yTm4DHETyf60skNm7JD/rTqVkzAl/l2T5XTYzjpcws46Z+FKfgVqR8zl8F3irqOzWZraHZ/mAZCksUG7MVeJdkoU5W1dLM7ugGtHnsM7ifOXeE3ONpCPwTW1mlj2pYgKwRva0CaAzlTeDY2ZfkJ5D1qhRLm9eX9Wq3UrHn/YHjjCzgbWRRdLSJGW5v5mdV1T0hJy8H5nZZ6VkKUUozEGQg5lNJfmVXSlpX0mLS2ouaXdJF3myfsBpkpZTOjbrdNKSNaSlsY6SukhajLQkWhs+orxC2Q84XtLqklqRTvK408x+rGU9mNkg0ia+w6rM8k/SLP1mV0aQtLKkf0rasDixpM0lba101FQLSSeTrEnPe7y8jxbx+8Wyx/5IaubxTYGmHp9r+Zf0Jz/iqIXnO4y0zPmSJ6nUrwDXAH+R1NHLXFLS/h73ELCOpEN8PDSXtEnGgl1N+dXwPGnSdZLX0Z20WfIOt0bdBZwnqbU/gz9TM/buAo6T1M5fJKfMiQBm9jbJd/1Mf3ZbuAyluJWkoNwrqYPS8YNtJP1V6cizkm2aE/mcY7ydy5CslHfmpGlJeqF/AiDpcGqUy9ryEdDOTwQpHJ/WW9KSZvYDydVmZpn8y5OeTXMfU+sBj2TibyG5WvxoZrnH10laWukIx7W8j5cl7WkYnpGxjaQlSwlhZh+QFIx/KB0F2ETSmpK28yTlPgOFOkqO8wqfwxeArySd7PFNlY6W3MSz3+V1Ly1pZdJEZ075L7CXpF29nsVcrnYVc6bx8lO5dlZJuffEXCGpN+m7f2czezMb5xba0cAZ3u4ewIYkF5ZC/sVI7ngAi/p9gVtc7qUldSD5V99UQpS8MVd1uyV1Ip3Y8QczezAnSUlZJC1BcrMZamZ533W3AL+WtL5/H55Wph1lCYU5CEpgZv8kKSKnkb483yV9eT/gSc4lKRRjSQrnKA8rfFmdTbK6vUY6iaA2nElSSL+U9Kuc+BtICspg0saob0m+e3PKaaTNRxUxs89Jx4X9ADwv6WuST/VU0kahYhYlWcA+I1kT9yAtHRasDauRlh0LFoMZpNMnsrLNICl+B/v1aSXEmwH8g7TM+inJj3K/zMvkfNIX75eSTijRvvtJm3bukPQVyRq5u8d9TfIJPoBkLfmQmg0+kHbsr+/lP1BCxoqY2ffA3l7vp6TTIw41s1c8yR9IyuebpLF1OzXH7v2b9AIZQxqT982pHCR3ky1Iz+5ckkJayk3gO2An0obDJ0jK4wsk14fnq2jTnHA7SfF70/9mOwPbzF4mjYlhpBf7BiTf2jnhKdI4/VDSpx52CDDZx8rRpDFaiudJm20/Jbkp9CyydN1KUubLWZe/J/nXPknq4/GkZ9IHwPuzH/Cmj8NSy+CHkiaphVNG7sFdFcp9BpwzKf/9VPJz6BO+vYAupO+uT4HrSad2QPrenOJxT7pcuWOuEm5934c0mSp8h59IFbqPuyKdBwz1dm4+JzJQ5j0xDziXdGTci6o51/2aTPwBpOP9viBtpuxpZp9k4gsnBkH63M7IxJ1B8v99m7QJs6+ZPZYnRIkxV5t2/x9pY+B/Mu3IWrPLydID2AQ4PJN3mqRVXbbHgItIm5/f9r8zSshRlsJO6CAIgiAoi6Q7SZtT5+iFM49lmUzavPhkfcsyr5DUgnTqw8Zm9lp9y9MQkPQ74AAz265i4iCoQ8LCHARBEOTi7iZr+pL9biRr3QP1LNaCzO+AFxdmZVnpF+i28jG3Lsn6eH99yxUE8+tXrYIgCILGx4okl442pGXy31nOT60Hc49bzEX5jcYLA4uQTuxYnXTs4h0k950gqFfCJSMIgiAIgiAIyhAuGUEQBEEQBEFQhlCYgyAIgiAIgqAMoTAHQRAEQRAEQRlCYQ6CIAiCIAiCMoTCHARBEARBEARlCIU5CIIgCIIgCMoQ5zAHQRAEQR2y7LLLWvv27etbjCAIKjBy5MhPzWy5vLhQmIMgCIKgDmnfvj0jRoyobzGCIKiApLdLxYXCHARBEAR1yMQpn9H1xFvqW4wgWCgZ2ffQeVJO+DAHQRAEQRAEQRlCYQ6CIAiCIAiCMoTCHARBEARBEARlCIU5CIIgCIIgCMoQCnNQayTdIOljSeOLws+U9J6k0f63h4f3zoSNlvSTpC455e4p6SVJYyS9LOm3kk7N5JuZuT4uJ/++kk7366MlzebpL6l9sdwl2thL0lhJEyRdlAk/WtI4l+FZSesX5VvC++CKTNiOkkZl8qzl4UtKetDbO0HS4R6+iKTBkipuypV0hMszVtJ4SftUylOUv5uky2qTpyh/B2/XS5LWlPRcFXmmlQi/SVLPEnF/lvSKt3WMpH9Kaj4XcneX9NCc5q+i/HUlDfK+mSjpurko66+Z62rHbx9Jn3j9EyTdI2nxOZWhqOxBkrrVIv1z/v9n2ee2/yW1k/Q/Sa9JelPSFZIWndPygiAIKhEKczAn3ATsViLuEjPr4n+PAJjZbYUw4BBgspmNzmZy5ec6YC8z6wxsBAwys/MyeWdkys5T8k4CrvI6rzGzOdqWLqkN0BfY0cw6AitI2tGjbzezDVyei4B/FmU/B3imKOxqoLfnuR04zcOPAV729nYH/iFpETP7HhgI9KogZzvgVGBrM9sQ2BwYW4t2NjOzEWY22+SjFuwL/M/MNjKzN8xsy7koKxdJRwO7AJub2QbAJsDHQItalNF0XstVgcuo+SysB1w+F2X9tXKSXO70+jsC35MznqqZlM0t83pMSBJwH/CAma0NrE0aCxeVzRgEQTAXhMIc1BozGwx8PofZDwT65YS3Jh1z+JnX8Z2ZTaq2UEnrAN+Z2ad+f6akE/y6q1slh5GU1EqsAbxqZp/4/ZPAfi7XV5l0LQHLyNAVWAEYUFSeAUv49ZLA+5nw1q4AtCL16Y8e9wDQu4KcywNfA9Nctmlm9pbLMkjSvyQ955bnTT38TEnXSRoA3JK19HncDZ73zawVX9Lf3ML7hKR+kk5QWkH4E3CkpKc93bRMnhMlvejW77OKhVfiCqXVhIe9PXmcCvzOzL70dn5vZhcUnoWkqyWNcEvqz/VImizpdEnPAvtL2s3b8Czwy0y6lt7uF91Svo+H95F0n6TH3JJ5kYc3dWv4eLd4H58jc1tgSuHGzMZ53sUk3ej5XpK0faau7KrEQ/5sLgBauKX4No9uKunf3t4BkspOHFwpbgl84fc3KVnonwYulNRF0nB/TvdLWtrT5YZnym0i6WZJ50r6nWZdiekj6XK/zl1RqNT/ZdgB+NbMbvS+nQkcDxwqqVWpvvTrXSQNU1rxuVtSKw/vKukZSSMlPS6prYcPknShpBckvSppGw/v6GGjvX/WriBzEASNnFCYg3nNsf4CuaH4Bev0IkdhNrPPgf7A266Q9ZZUm/G5FTCqRNyNwHFmtkU2UNJKkh7JSf860EFpCbkZyYq6SibfMZLeIFm0jvOwJsA/gBNzyjsSeETSFJKF/QIPvwJYj6RAjwP+aGY/edx4kiW1HGOAj4C3XAnbqyi+pVv3fg/ckAnvCuxjZgfllNkB2BXYFDhDUnOl5ff9SFb/XwLdAHwF4RqSJXX7bCGSdiFZ/jYFugBdJW1bVFcPYF1gA+A3wGyWSEmtgVaFiUAJTjWzbsCGwHaSNszEfWtmW5MmIP8G9gK2AVbM5geeMrNNgO2BvpJaelwX0pjdAOglaRUPW9nMOrnF+8YcmS4BnpL0qKTjJS3l4ccAeL4DgZslLVaqYWZ2CjUrK4UJ1NrAlW45/hKfzOXQS9Jo4D1gGeDBTNw6wE5m9n/ALcDJvkoxDjjD05QKhzS5vY00sTwNuIfMJITUZ3eWalcR5fo/j47AyGyAT54mA2uVyiRpWdLqzk5mtjEwAviz0urW5UBPM+tK+qycl8nazMw2JU0OC31wNHCprxp1IzM5CoJgwSQU5mBecjWwJkmh+ICkQP6MpM2A6WaW64NpZkcCOwIvACcwq5JXibbAJ8WBkpYEljKzgpvErZn63jezPXLk+AL4HemFP4T0Iv4xE3+lma0JnEyNe8XvgUfM7N0c2Y4H9jCzdiTlquDGsSswGliJ1GdXSFrC65gJfO8KYy6eZjegJ/AqcImkMzNJ+nm6wcASGaWtv5nNKFHsw27d/5Tk9rACsDXJ7WKGmX3NrIpXKXbxv5dIE5kOJEUvy7ZAPzObaWbvA0/llCNmteLv6la9yZIKCvavJI3yujoCWb/ygtLWAXjLzF4zMwP+WyTrKa5cDgIWA1b1uIFmNtXMvgVeBlYD3gTWkHS5pN2A7KoDAG79XA+4m+RuM1zJx3ZrfAya2SvA2yTltTa8lXFpGgm0L5HuTlfoViQpvNnJ3N1mNjPn83EzsG2p8Ez+a4HxZnaet+UT4E1Jmyu5NK0LDK2yPeX6P49ZxkRReDk2J42NoV7XYaTnuS7QCXjCw08D2mXy3ef/s309DPirpJOB1fI+T5KOUlr5GPHj9K8riBYEQUMnFOZgnmFmH7ny8xPJmrdpUZIDyHfHyJYxzswuAXamtOUsjxmkF20xpV6uZTGzB81sM7dKTwJey0l2B8n6DLAFybo+GbiYtDx8gaTlgM5m9rynu5MaS+rhwH2WeB14i6TYFVgU+LaCnGZmL5jZ+aT+zfZZcbsL99+UKfK7zPVMkiWxkiKSh4DzrcbnfC0z+09OurLPxi2H30ha3e8fdyVwPLCIh59A8jffEHiYWcdBtq2l6hKwX0bWVc1sosfN1h8+oepMUu6OAa4vIfv7ZnaDme1DmnB1onRf/sis38clrc55MklaRTUbYo8uksNIk5yswltuDFTDc8D2RdbxO4Ffkcbg/V5vNZTr/zwm4KscPxeQJporkD6rpfpSwBOZetY3s197+IRM+AZmtksmf6G/C58HzOx2YG/S987jknYoFtLMrjOzbmbWrdniJee9QRA0EkJhDuYZBb8/pwdJqSnENQH2JymZeXlbFfwMnS4k61u1TCRnOdaS3+tUSVt7UCW/4II8y/v/pUnW4+v9Pmsl/QWuSJtZb3/RtycpcLf4cvoXwJJKPtaQJgIFZeAdkkUdSSuQLF1v+n0b4BMz+8HvX8mRcSVJG2eCujBrn/XydFsDU81sajVtz+FZYC8l/9tW3u5KPA4ckfERXbnQpxkGAwco+QS3JS3H53E+cHXBQi5J1ChBS5CUv6neh7uXKOMVYHVJa/r9gUWy/sHLRdJG5RrmS/tNzOxe4G/AxjlpdvOlfiStCLQhuUYMxsegj4lVSUreZKCLkl/wKsw62fxBFU4EMbN3MwrfNTlJtgbeyMk3Ffii4JtLchl6plR4Jut/gEeAu1WzcfA+0gTyQKp3x4AS/e9jZmBO+oHA4vJTcJQ2dP4DuMItvZPJ78vhwFaqOaVmcX8Gk4DlJG3h4c0ldSwnsKQ1gDctbT7uT3IHCoJgAabOd0gHCx6S+pGWmZd1v9wz3Hp4kdJxcUZ6af02k21bYIqZvVmqWOAkSdeSrDbfAH1qIdZg0ikTyrFsHQ7cIGk66eVcaMdKwPV5bhnApZI6+/XZZvaqXx8raSfgB5IyfFg5oczsR0m/Ae6V9JPnOcKjzwFukjSO1P6T3RUCkvL4iMu5LPmWyebAxd6Ob0kuKVnr4hdKR3otkamz1pjZi5L6k3ym3yb5fpZVvs1sgKT1gGGuB00DDia5eRS4n7SBaxzJpaT4dJECVwOLA89L+s7LGgq8ZGZTJb1Esjq+SQk3ADP7VtJRwMOSPiVNAjp59DnAv4CxrrRNBvYs07yVgRtV42P/l5w0u5DGUGGF4EQz+1DSVcA1/sx/BPqY2XeShpJWGMaRJppZf/zrXLZRJH/faunlk6UmJB/bPiXSHeYyLU7qw8MrhANgZv90141bJfU2sy8kvQysb2Yv1ELOUv3flowrVKZek9QDuFLS34DlSO4nBb/j3L40s08k9QH6qeYIutPM7FWl4wwv8/Y0c3kmlJG5F3CwpB+AD4Gza9HeIAgaIap+1SwIGjaSLgUeNLMn61uWuUXSfcBfzGySpD2BNSz/KL1S+QcBJ5jZiHkkTyszm+bK02DgKDMrtckyCOYaSccC75hZ/wrptiS5ev3SzEaWS1tftFxxdetwyGwHxQRBMB8Y2Xe2n2QoiaSRljaRz0ZYmIMFib8Dm9W3EHOLpEVIZ8xOAjCzOvuBjVpwndKPtCwG3BzKclDXmNkVlVOBmT1H2rwXBEFQZ4TCHCwwmNlHJH/CRo2lHy6Zox9dyZTRfd5I83N5eUfQBUEQBMFCQWz6C4IgCIIgCIIyhIU5CIIgCOqQ9dq1YUQt/CiDIGh4hIU5CIIgCIIgCMoQCnMQBEEQBEEQlCEU5iAIgiAIgiAoQyjMQRAEQRAEQVCG2PQXBEEQBHXIxCmf0fXEuTopMgiCImrzgyTzgrAwB0EQBEEQBEEZQmEOgiAIgiAIgjKEwhwEQRAEQRAEZQiFOQiCIAiCIAjKEApzUO9IMkm3Zu6bSfpE0kN+30fSFX59pqQTcsqYVqGOPl7maEmvSDo+E3empPc87jVJ90lav0xZ/5K0rV9fn5c2K3MV7V/C658tvaTLi9smqbvLOkHSM5nwyZLGedyInLJO8L5e1u83kHRTlTJ2lPSUpFe9j/4mSRXyVN0H8xLvh2VLxDX6dhQ953GS9pnH9da6vZI2l/S8yzRR0pke3l3SllXkrypdLeQpOQY8fpCkbvOjriAIFgxCYQ4aAt8AnSS18PudgffqoJ47zawLsBVwqqRVMnGXmFkXM1sbuBN4StJyxQVIWgbY3MwGA5jZkWb28lzKdQ7wTHGgv9CXKgpbCrgK2NvMOgL7F2Xb3tvRrSjfKqR+facQZmbjgHaSVi0nnD+X/sAFZrYO0BnYEvh9NY1rKCwo7XC297HcE7isnmUBuBk4ymXqBNzl4d1JfVyJatMFQRDUC6EwBw2FR4Ff+PWBQL+6qsjMPgNeB9qWiL8TGAAclBPdE3iscJO1VEk63C2Xz5CU8opI6gqs4PVlw5sCfYGTirIcBNxnZu+4rB9XUw9wiZdlReEPAgdUyHsQMNTMBnid04FjgVNc1k0lPSfpJf+/bnEBkn4haZikFSS9qcRSkn7KWOuHSFpL0jKSHpA0VtJwSRt6fKnwNpIGeP3XAqUsxgtKO7IsAXyRke9gSS+4pfdaH0dIulrSCKVVibMy6Tfxto7xfK09aiVJj7kV/qIq5Fge+MD7daaZvSypPXA0cLzLs42kvdwS/ZKkJ70f89ItJ+leSS/631Yu75mSbvDP3ZuSjisnlKSWkh729o2X1CsnTam+mSzpLEmjlCz5HTx8Tp5TEASNnFCYg4bCHcABkhYDNgSer6uKlCyqiwFjyyQbBXTICd8KGJlTZlvgLI/fGVg/E7e3pLNz8jQB/gGcmFPPsUB/M/ugKHwdYGlXGEZKyh5EacAADz8qWz/wnpmNyalnBLBNTniWjhS12czeAFpJWgJ4BdjWzDYCTgf+XtTOHiSldA8z+wh4ldQ/W3u520haFGhnZq+T+vElM9sQ+CtQOMC2VPgZwLNef3+glMV8QWkHwNOSxpNWJk5z+dYDegFbuaV3JtDb05/qqw4bAttJ2lDSIqTVlD+aWWdgJ2CGp+/iZW0A9NKsqzF5XAJMknS/pN9KWszMJgPXULN6MwR4lrRCsxHpM39SiXSX+v0mwH7A9Zm6OgC7ApsCZ0hqXkau3YD3zayzmXUiM9nNMFvfZOI+NbONgauBgitYVc9J0lGuiI/4cfrXZUQMgqAxED9cEjQIzGysW5oOBB6po2p6SdoeWBf4jZl9WyZtKatRW+CTnPDNgEFm9gmApDtJyi1m1p/0Yi3m98AjZvauMm60klYiuVp0z8nTDOgK7Ai0AIZJGm5mr5IUpfclLQ88IekVkkJ8KrBLifZ8DKxUIu5nkZjdMl3ASG4jN0ta2++zCsz2QDdgFzP7ysOGANsCqwPnA78hKX4vevzWJCUJM3vKLXpLlgnfFvilhz8s6WeL6wLaDkguGZ9KWhMYKGkQaUx0BV708dSC9HwBfuWTqGakMby+t/EDM3vR6/wKwPMONLOpfv8ysBrwbilhzOxsSbeRxtlBpM9x95yk7YA7fYK5CPBWiSJ3AtbPfC6WyFi/Hzaz74DvJH1MWqGZUqKcccDFki4EHnJlvJi8vilMpu/z/yPxZ0OVz8nMrgOuA2i54uqlxl0QBI2EsDAHDYn+wMXUnTvGne73uw3wD0krlkm7ETAxJ3wGyTqdR21filsAx0qaTGr3oZIu8LrXAl73uMUlve55pgCPmdk3ZvYpMJjki4uZve//PwbuJ1ng1iQpdGO8rHbAqEzbF6PGqliKCSRl8WckrQFMM7OvST7YT7sFby9m7Z83gdb45MEZQnoGm5ImR0uRlKvBheJzZLAy4dn/WRmP8SX+0T4JaZTtKIdbyD8iKXkCbnYrbRczW9fMzpS0Osk6uqNbtR/2tpWbQHyXuZ5JFcYVM3vDzK4mKe6dJbXJSXY5cIWZbQD8ltKfpSbAFpm2rOzPqFay+USyK0lxPl/S6dn4Mn1ToFBXcT2hAAfBQkYozEFD4gbgbN+MVmeY2TDgVuCPefGS9iNZyvIU94kkZbaY54Hubi1szuyb8fLk6G1mq5pZe9JL+xYzO8XMHjazFc2svcdNN7NCnf8jLf03k7Q4ybI90X01W7v8LV3+8WY2zsyWz5Q1BdjYzD708tYBxnu+TSXl/X7vbcDWknbydC1IG80Kvq1LUrNJs09R3rdJ1rhbJHXM9NWWwE9u5R9NUp4K1r/BuCuBpO6kZfGvqgzfHVja+/fKjML1fmNtRzl8NWF1l28g0NPDCr7Sq5H8nL8BpkpaAdjds79C8lXexNO3llRWMZZ0i6RNc8J/oRpz8NokBfNL4GvSRKNAto8Py4QXpxtAcksqlN+lnFxl5F2J9Pn5L2lSunFRklJ9U45aP6cgCBo/oTAHDQYzm2Jml1aR9DRJUwp/HrZ4NkzSnyuUcSFweGaZ93i3RL4GHAzsUHCvKOJhcpaa3df4TGAY8CTJBxoo7cM8J5jZRJIf5ljgBeB6MxtPWpZ+VtIYD3/YzPL8NYvZntQmSL6Ys1mbzWwGsA+p3yeRrHUvAoWjxy4iWe+GAk1z8k8iKRh3S1rTl9PfBYZ7kiEkZakwUToT6CZpLHABNYpVqfCzgG0ljSJNFH4+CWRBbIfztKTRwNPAKWb2kaXTWk4j+bGPBZ4A2lryXX+JZGG/ARjq7fme5Kd8uY+bJyht8S2wIb65r4hDSD7Mo0mT0d5mNpO0qbSHf7a28bbfLWkI8Gkmf3G64wp95C4hR1eQqxQbAC+4XKcC52YjS/VNBWrznIIgWECQWawsBUFtkPQssKeZfVnfsswNShvUngG2NrMfJfUFbjWzcpshg4UUpY2R/zGziqsnway0XHF163DIWZUTBkFQNSP7Hlo5US2RNNKKjmUtEJv+gqD2/B/JGvtlPcsxt6xKsk7+CGBmead1BAHw86bAUJaDIFgoCYU5CGqJmdXZkXfzEzN7DXitvuUIgiAIgoZO+DAHQRAEQRAEQRnCwhwEQRAEdch67dowog78LYMgmH+EhTkIgiAIgiAIyhAKcxAEQRAEQRCUIRTmIAiCIAiCIChD+DAHQRAEQR0yccpndD0x70c0g6BhUxdnHTdWwsIcBEEQBEEQBGUIhTkIgiAIgiAIyhAKcxAEQRAEQRCUIRTmIAiCIAiCIChDKMxBEARBEARBUIZQmIM6R9KpkiZIGitptKTNMnHNJH0q6fyiPIMkTZI0RtJQSetWEd4tk7+9pPF+3V3SQ37dR9InLscrko7P5DlT0nseV/hbqkiuJpIukzRe0jhJL0paXdLznv6dTPmjJbXP6Y97JK3h148U15GR5YQK/dpG0tOSpkm6oiiuq8v3ussrD19N0kB/FoMktcvkmZmRu38mfAdJo7zNN0tq5uHysl/38jb28EUkDS6kq9CGyZKWLQrbW9IplfIW5blJUs/a5JlflJItO0YzYRWfe12R9ywy4eN8XIyTtM88rrdP8fitIo8knSbpNUmvSnpG0obzUq4gCIIsoTAHdYqkLYA9gY3NbENgJ+DdTJJdgEnArwpKXYbeZtYZuBnoW0V4tdxpZl2ArYBTJa2SibvEzLpk/r4sytsLWAnY0Mw2AHoAX5rZZl7m6YXy/W9yNrOkjkBTM3sTwMz2yKmjWr4F/gbkKVhXA0cBa/vfbh5+MXCLP4uzgexEZUZG7r1d3iakfj7AzDoBbwOHefrdM+Uf5XViZt8DA0l9VWvMrL+ZXTAneYPqqGYyU8T2Pr57ApfNe4lqzTHAlkBnM1sHOA94UFLL+hUrCIIFlVCYg7qmLfCpmX0HYGafmtn7mfgDgUuBd4DNS5QxGFirFuFVYWafAa+7jNXSFvjAzH7yMqaY2Re1yN8b+F/hJmvVU7LET5L0JLBuFfJ/Y2bPkhTnn5HUFljCzIaZmQG3APt69PokZRbgaaCStbAN8J2Zver3TwD7+fU+JOXbzGw4sJTXDfCAt7XWZC2Obp29TNJzkt4sWGrdwniFpJclPQwsn8nf1S2OIyU9XpDJLeoXSnrBrZLbePgjBeukpJckne7X50g60uvqq5pVhV4ZGUqF58pWy37oImm4W+/vl7S0pOUljfT4zpJM0qp+/4akxSXtpbTi8ZKkJyWt4PFnSrpO0gDgFqUVigGe7lqgeMKaxxLAz+Nd0sHen6MlXSupqYdfLWmE0srSWZn0m/izHOP5WnvUSpIec4vxRVXIcTLwBzObDmBmA0jfB729nmmZOntKusmvl5N0r9LK0IuStvLwlpJu8LCX5FZ0H4v3FcsmqamPzcKzP54gCBZoQmEO6poBwCquoFwlabtChKQWwI7AQ0A/kvKcx17AuCrCb/MX92jgkUqCuaKxGDA2E3y8atwSns7Jdhewl8f/Q9JGleopYitgZI4sXYEDgI2AXwKbZOKOlnR0LepYGZiSuZ/iYQBjqFF4ewCtJbXx+8VcyRkuaV8P+xRorhp3l55AwSK/MrOuFmTrGZ9tw1zSFtiatFJRsDz3IE0qNgB+Q7I2Iqk5cDnQ08y6AjeQrI8FmpnZpsCfgDM8bDCwjaQlgB9JzwivcwjpeXQBOpNWSPq6El4qPFe2EqyZGW+jgexzvgU42VcDxgFnmNnHpOe0BLANMMJlXw342BXIZ4HNzWwj4A7gpEyZXYF9zOwgb/+znq4/sGoZOZ9Wch95BjgNQNJ6pFWErdz6PJOaSdKpZtYN2BDYTtKGkhYB7gT+6CtEOwEzPH0XL2sDoJdmXfWZBW97SzN7oyhqBGlCWI5LSatIm5A+B9cX5AWe8vDtSc+yYK3Ok60LsLKZdfKVphtz5DzKP08jfpz+dQWxgiBo6MQv/QV1iplNc2VwG9KL6E5Jp5jZTSQF6Gkzmy7pXuBvko43s5me/TZJM4DJwB8yxZYK721mIyD5h5IU8Tx6SdqepNT8xsyyFtpLzOziMu2ZouQ3vYP/DZS0v5kNLJWniLbAJznh2wD3FyxmyvgQm9k1VZZdIM9SaP7/BOAKSX1IiuJ7JCURYFUze1/Jv/opSePM7A1JBwCXSFqUNAEqpC9Zj5nNlPS9pNZmNrfawgNu0X+5YC0FtgX6+Vh5X9JTHr4u0Al4QsnDpynwQaas+/z/SKC9Xw8BjgPeAh4Gdpa0ONDezCb5ZKVQ10eSniFNBrYuEV5KtjzecGUTSFZg/78ksJSZPeNRNwN3+/VzJKV+W+DvJHcbeTsA2pE+Z22BRbxdBfqbWUFJ3Zak9GNmD0sqt1KyvZl9KmlN0pgfRJrsdgVe9L5uAXzs6X8l6SjSO6YtSZE10urMi17nV95WgIFmNtXvXwZWY9bJWDVUYyHfCVhfNd5fS7iVexdgb9X4jy9GzQQiT7YJwBqSLieNmQHFFZnZdcB1AC1XXN2K44MgaFyEwhzUOa44DAIGSRpH8oG9iWRR3krSZE/ahqRUP+n3PyvARZQKr5Y7zexYJf/qhyU9amYfVpvZ3UseBR6V9BHJ3aFahXkG6WWcW3S1MlRgCklpKtAOeB/A3WF+CSCpFbBfQRkouMqY2ZuuEG1EUuiGkRR6JO0CrJOpJ2sJ/LkeZ1GK3EXmkO8y11mlKK+/BEwwsy0qlDWTmu+/F4FuwJskl5NlSZbhwkpAKUWsnII2m2xKm12v9dvTmXVlozYMIT2P1UjuPSd7fYUJ4uXAP82sv6TuwJmZvN9UkrMcPoH6iKQAC7jZzP6STSNpddLEbBMz+8LdIRbz9KXqyz7j7LPJk+ErSd9IWqOwF8DZmBrFNVtP9vPWBNgiM2koyCzSZ2FSUfhmebJ5uzoDu5L8qX8FHFFK5iAIGj/hkhHUKZLWlbR2JqgL8LYvq25Nsmq2N7P2pBdPKbeMeY4rgrcCf6w2j6SNJa3k101IS85v16LaiZT2x+4hqYVbvPaqRZmzYGYfAF9L2twVgUNxv2lJy7rcAH8huSyg5B+7aCENyYL5st8v7/8XJSlnBYt3f+BQJTYHpnrduJvHJ2b2g9+/MqftKcFg4AAlX9K2pIkWpA2ky/lkCEnNlTZalsQ3Kb5LUnqGkxTSE6ix2A4mrUo0lbQcyTL7QoXw2WQzs+czmyr7UwafxHwh97MGDiG5QxTkORh4zS3vnwN7AEM9fknSygHUbNDMI+vzuzuwdDmZPN3ywOqkMT8Q6JkZH8u4a8gSJMV8qq8I7O7ZXyH5Km/i6VurwuZDSbdI2jQnqi9wmZJbF5J2AjoC93j8R5LW87HeI5NvAHBspvwufvk48Af/vKAKrlb+GWliZveSNt5uXC59EASNn7AwB3VNK+BypaPTfiRtsjuKZOV8qrAZ0PkfcFFBcZtPXAiMkvR3vz9e0sGZ+H2LTrpYHvh3RsYXgNocifUw0J0aKzoAZjZK0p3AaJIyUlDWcJeAXNcMt84vASyi5He8i5m9DPyOZMVvgVvDPUt34HxJRlKYjvHw9YBrJf1Emkhf4OUAnChpTw+/2swKLgaPkBS114HpwOEZ0bb3+IJyUc4aO9brheQjXo3l9X6SS8w44FVcmTSz75U2Bl7mbg3NgH+RltDLMQTY0d2DhpCs5YVncD+wBcn/24CTzOxDSeXCZ5NtDjgMuMbdQ97E+9fMJrteN9jTPQu0y2w+PRO4W9J7pAnA6iXKPwvoJ2mUy/hOGVmeljQTaA6cYmYfkZTS04ABrpj+ABxjZsMlvUTq8zdxRd6fTS/S90EL0mrLThX6YENmdakpcDmwFGnsNCe5nnTKuFedQrK4v0vyp2/l4ccBV0oaSxobg0l+4+eQxslYV5onk1zGSrEycGPR5DMIggUYpU30QRDMD1xReJq0UWpmpfSNFUn3AX9xH+A9gTXMrCEcRxY0EnwV6j9mtn+FdK1Ik5oXzeyv80W4WtJyxdWtwyFnVU4YBA2MkX0PrW8R5iuSRvqG5dkIC3MQzEfMbIakM0gWqnIWvUaL0mkIDxT8Qc2s1ObLICiJbwosqyx7umnAznUvURAECzOhMAfBfMbMHq9vGeoS9wm+pb7lCIIgCIJ5RWz6a+BIWrE24UEQBEEQBMG8JSzMDZ9XSZu6inkZWGY+yxIEQRDUkvXatWHEQuYLGgQLGmFhbvjMdrqAb4b5KSdtEARBEARBMI8JC3MDRdK7pKOqWkgq3hzWhvRT0kEQBEEQBEEdEwpzw+VgknX5EdKPFhQw4KPiX6QKgiAIgiAI6oZQmBsoZvYMpB99MLPp9S1PEARBMGdMnPIZXU+Mg2OCxsfCdg5zOUJhbvj8KOko0k9Kt8pGmFmM5CAIgiAIgjomFOaGzy2kn4d9EPionmUJgiAIgiBY6AiFueGzK7C6mX1Z34IEQRAEQRAsjMSxcg2fd4BF61uIIAiCIAiChZVQmBs+twD/k3SgpB2yf/UtWLDgI+kGSR9LGl8i/gRJJmlZv28j6WlJ0yRdUabcPSW9JGmMpJcl/VbSqZJG+9/MzPVxOfn3lXS6Xx8taTZ/fkntS8mdSbO4pIclvSJpgqQLMnFHSxrnMjwraX0P3z4j22hJ30ra1+NukzRJ0njvu+aZ8rp7+gmSCpt6F5E0WFLF1T5JkzPyjJO0TxV5HpG0VJn4QZK6VSqninoGebvHSBoqad1a5K34nHLytJP0P0mvSXpT0hWSwrAQBEGdES4ZDZ9j/f/fi8INWGM+yxIsfNwEXEGauM2CpFWAnUmrIAW+Bf4GdPK/2XAl8jpgUzOb4opOez8q8TxPM83MupSR6yRgbwAzu6Z2TZqNi83saUmLAAMl7W5mjwK3F8qWtDfwT2A3M3uatAkXScsArwMDvKzbSEdCAtwOHAlc7UrrVZ7/HUnLu+zfSxoI9PK8ldjezD51hXQA8L9yic1sj6p6YN7Q28xG+CblvvjzKYekprWtRJKA+4CrzWwfL+M64CLgj7UtLwiCoBrCwtzAMbPVS/yFshzUOWY2GPi8RPQlJMXVMum/MbNnSYpzKVqTJuufeZ7vanOuuKR1gO/M7FO/P1PSCX7d1a2cw4BjKpVlZtNdAcbMvgdGAe38/qtM0pbZdmboCTxaOPrRzB4xB3ihUBZwEHCfmb3j6T7OlPEA0LuqxtewBPBF4UbSA5JGuvX6qEz4ZEnLSmrplvQxbv3uVVygpF0kDZM0StLdklpJ2lHS/Zk0O0u6r4Jsg4G13HI8xMsbJWlLL6O7r0LcDowrkmENX3nYpEz5OwDfmtmNAGY2EzgeONRl7qPM6oakhyR1L9VGD+8q6Rnvw8cltfXwQZIulPSCpFclbePhHT1stKSxktau0CdBEDRyQmFuBEhqLmmbwkvOX34t61uuYOHFLa7vmdmY2uY1s8+B/sDbkvpJ6i2pNt9FW5EU2zxuBI4zsy2K5F1J0iPlCnUr8F7AwEzYMZLeIFkvZ3MNAQ4g51c33Yp+CPCYB60DLO0K2EjN6kIyHiinIGZ52t0XngFOy4QfYWZdgW7AcZLaFOXbDXjfzDqbWaeMXAV5l/XydjKzjYERwJ+Bp4D1JC3nSQ8n9XE59iIpwh8DO3t5vYDLMmk2BU41s/UzMqwL3AscbmYvlim/IzAyG+CTm8nAWqUylWqjP6vLgZ7ehzfgKx1OMzPbFPgTcIaHHQ1c6qsg3YApZeQNgmABIFwyGjiSNiApF9+RrFV3AtsBh5FeQkEwX5G0OHAqsMuclmFmR/rY3gk4geTa0afK7G2BT3LkWhJYqvCjP8CtwO5e3/tASfcEJR/ifsBlZvZmRs4rgSslHURStg7L5GkLbAA8nlPkVcBgMxvi982ArsCOQAtgmKThZvaqmc2U9L2k1mb2dYW2F1wy1iS5jwwys2kkJbmHp1kFWBu34DvjgIslXQg8lJGrwObA+sDQ5PHAIsAwMzNJtwIHS7oR2AIodf77bZJmkBTXPwDNgSskdQFmkiYNBV4ws7cy98uR3Ev2M7MJFfpA5Fv7VSFfbhuBdUnuQ094eFPgg0y+gkV9JNDer4cBp0pqR1o5eG02YZKl/yiARVoXz1+CIGhshMLc8LkaON3MbpVUWIJ9Bvh3PcoULNysCawOjHEFox0wStKmZvZhtYWY2ThgnCtkb1G9wjwDWDInvJQiVQ3XAa+Z2b9KxN9B+ixm+RVwv5n9MIsQ0hkkBfC3meApwKdm9g3wjaTBQGfgVY9flPJuLLNgZm9I+ghY3ycwOwFbmNl0SYOAxYrSvyqpK2nScL6kAWZ2dlZs4AkzOzCnuhtJ58B/C9xtZj+WEKu3mY34uUDpTNLZ8Z1Jq5nZ9n1TlHcq8C5p9aCSwjwB2C8bIGkJYAVgEkn5za5YFPoit40+cZtQvCqR4Tv/PxN/Z5rZ7ZKeB34BPC7pSDN7KpvJzK4jjStarrj6nI7LIAgaCOGS0fDpCPzXrw2SnyjJShUE8x0zG2dmy5tZezNrT1IGN65WWXY/0+6ZoC7A27UQYSI5S+9+VvlUSVt7UFV+wZLOJSngfyoKz/ql/gIotiIeSJE7hqQjSWenH2hmP2Wi/gdsI6mZK7ibeTtw94lPCoq3pFeqkHl50qTlbZf9C1eWO5AsqcXpVwKmm9l/gYuBjYuSDAe2krSWp19cyVe8YJ1/n2Rhv6mSbBmWBD7wfjiEZLktxffAviQ/5INchpWVNkQWMxBYvODWorTp7x/AFWZWsHB3kdREaWPqphXaOAlYTtIWHt5cUsdyDZO0BvCmmV1GWgHcsHxXBEHQ2AmFueEzmbSU+zOSNiXtzA+COkVSP3zZWtIUSb+uIs9k0okSfTzP+sVJgJOUjiEbDZxF9dZlSJvKNpKbt4s4nORCMYxkiS7IlOvD7Evqp5KW6kf5Jq4jPfpYpU10o0n+vFl3jPYk14dnZi2Ra0iWzmFe1ukAZjaR5Dc8lrQZ8HozKxyltj3wiJe7LOVdC552eZ4GTjGzj7zcZpLGAueQFMNiNgBe8LynAudmI83sE9Iz6OflDAc6ZJLcBrxrZi+Xka2Yq4DDJA0nuWMUW5VnwQ0BewLHKx2Z1xaYzZrtGyp7AD0lvUZyPfnJzAp+x0NJKxbjSJODUeXa6Js9ewIXShoDjAa2rNC2XsB4788O5JwiEwTBgoXSd0/QUJG0J/Af0ov4/0ibUY4GfmNmA8rlDYIFFUmXAg+a2ZP1LcvconTqxF/MbJJ/3tdwy2WDQenUiZfM7D/zsc5jgXfMrH+FdFuSLP2/NLOR5dLWFy1XXN06HHJWfYsRBLVmZN9SWxYWTCSNNLPcs+nDh7mBY2YPSdqddJ7rM8BqNOAXQxDMJ/5Ocmto1Cid/fxA4Vg9M3uonkWaDUkjSdbh/5uf9ZpZyR++KUr3HOl7MQiCoM4IhbkRYGajgN/XtxxB0FBwV4SylsfGgLsDNOjlfD9qLQiCYKEmFOYGjh93dSCwEdAqG2dmR+VmCoIgCIIgCOYZoTA3fP5L2rDzKOmIpiAIgiAIgmA+Egpzw2c3YJUqftAgCIIgaICs164NIxayzVNBsKARx8o1fF4GlqlvIYIgCIIgCBZWwsLc8DkYuF7SAIpcMsysQW8WCoIgCIIgWBAIhbnh0wfYBliazA8xkH71LxTmIAiCIAiCOiYU5obPH4GN/JfCgiAIgkbGxCmf0fXEsG8Edc/C9kMj85PwYW74fAS8U99CBEEQBEEQLKyEhbnhcwlwm6QLgI+zEWb2Zv2IFARBEARBsPAQCnPD50r/v3dRuAFN57MsQRAEQRAECx2hMDdwzCzcZoIgCIIgCOqRUMaCYAFD0kxJoyWNkTRK0pYe3l7SDI8r/B3qcZMljfO/lyWdK2nRKvMtW1R/H0lXVJBxT0kvuYwvS/qtpFMz5c/MXB+Xk39fSaf79dEFeYrStJc0vor+OtDbPVbSY4X2eLnjXIZnJa1flG8JSe9l2yppSEbu9yU94OHdJU3NxBVkX0TSYEkVjReZZzTa/+9TRZ5HJC1VJn6QpG6VyqminkGSJvnzHCpp3Vrkreo5FeVpJ+l/kl6T9KakKwrjNQiCoC4IC3MDR9IQkvtFMd8BU4D7zOzB+StV0MCZYWZdACTtCpwPbOdxbxTictjezD6V1Aq4zv8OqyJfrZDU3Mve1MymuKLT3swmAed5mmkV6jsJd1Mys2vmQpZmwKXA+t72i4BjgTOB2wtlS9ob+CfplzcLnAM8ky3PzLbJlH0v8L9M9BAz27Mo/feSBgK9gNuqELnwjNYFBhSVPxtmtkcVZc4repvZCElHAX2Z3Y1sNiTV2q1MkoD7gKvNbB8v4zrgItKpQkEQBPOcsDA3fAYB7Ukv5v/6/9WAEaQTNG6QdFJ9CRc0eJYAvqhNBjObBhwN7CupLn5lsjVpsv6Z1/edK8tVIWkd4Dsz+9Tvz5R0gl93dSvnMOCYaorzv5auiC0BvO9yfZVJ15LMxFVSV2AFktKaJ2NrYAfggSpkeADoXUW6LLM8V0kPSBopaYIrrIXwyZKWldRS0sPeN+Ml9cqReRdJw5RWJe6W1ErSjpLuz6TZWdJ9FWQbDKzlluMhXl52paO7pKcl3Q6MK5JhDaWVh03KlL8D8K2Z3QhgZjOB44FDXeZZVjgkPSSpe6k2enhXSc94Hz4uqa2HD5J0oaQXJL0qaRsP7+hho5VWJtau0CdBEDRyQmFu+OwC7GpmfzOz68zsb8CuwA5mdgrwC5JyEwQFWviL/BXgepIltMCamtW1Ypu8AlxZfAtYuzb5qsHMPgf6A29L6iept6TafBdtBYwqEXcjcJyZbZENlLSSpEdyZPkB+B1JcXsfWB/4TybfMZLeIFkvj/OwJsA/gBPLyNgDGFikdG/hCuujkjpmwscD5RTELE+7+8IzwGmZ8CPMrCvQDThOUpuifLsB75tZZzPrBDyWjVRyQzkN2MnMNiZNyP8MPAWsJ2k5T3o4qY/LsRepPz8GdvbyegGXZdJsCpxqZj+7ubjV/F7gcDN7sUz5HYGR2QDv58nAWqUylWqjr3hcDvT0PrwBX+lwmpnZpsCfgDM87GjgUl8F6UZa7QuCYAEmXDIaPh2A4uPj3gbWBTCzFyQtP9+lChoyWZeMLYBbJHXyuNq4VihzPc9cMgDM7EhJGwA7AScAO5N+1bIa2gKfFAdKWhJYyswKbhK3Art7fe8Ds7knuLL0O2Aj0ufscuAvwLme70rgSkkHkZStw4DfA4+Y2bvJKJ3LgaTJSoFRwGpmNk3SHiSr8tpex0xJ30tqbWZfV2h7wSVjTWCgpEG+InCcpB6eZhUv+7NMvnHAxZIuBB4ysyFF5W5OmiwM9TYtAgwzM5N0K3CwpBuBLYBSv4xwm6QZJMX1D0Bz4ApJXYCZwDqZtC+Y2VuZ++VI7iX7mdmECn0g8t3USj4MJ7eNpO/STsATHt4U+CCTr2BRH0la7cPznSqpHckt7rXZhEmW/qMAFmldPH8JgqCxEQpzw2cwcKPSJqEpQDuSf+WzAK50fFAyd7BQY2bD3LK2XMXEGdyloD3wKrBkHYiGmY0DxrlC9hbVK8wzSshUSpEqRxeX5Q0ASXcBp+SkuwO42q+3ALaR9HugFbCIks/1KV5GG5IFtaDAzuLeYWaPSLpK0rIFtxJgUeDbaoU2szckfQSsL2lx0sRjCzObLmkQsFhR+lfdjWQP4HxJA8zs7EwSAU+Y2YE51d0IPOjy3W1mP5YQq7eZjfi5QOlMkttYZ9JqZrZ93xTlnQq8S1o9qKQwTwD2ywZIWoLkIjOJpPxmVywKfZHbRv8OnVC8KpHhO/8/E39nmtntkp4nrfA9LulIM3sqm8nMCvsAaLni6rUdl0EQNDDCJaPhcxjpOb0MTCe9LJpSo1x8T7JmBcFsSOpAGi+fVUqbydMKuAp4wMxq5f9cbfkFn1KnC2nVpFomkrP0bmZfAlMlbe1B1fgFv0dSOgsTip29fIr8Un8BvOb19DazVc2sPck6fktBWXb2J1lxf1YQJa0oN19K2pT0mf7M79sAn7h7CO5KUxZfVVqd1G9LAl+4styBZEktTr8SMN3M/gtcDGxclGQ4sJWktTz94kq+4gXr/PskC/tNlWTLsCTwgZn9BBxC+XPjvwf2JfkhH+QyrKy0IbKYgcDiqjmppSnJReYKMytYuLtIaiJpFdLkpVwbJwHL+WoMkpoXuczMhqQ1gDfN7DKSe9GG5bsiCILGTliYGzju73mA+00uR3qx/pSJr3qzVLDQ0ELSaL8WcJgv+4P7ImfS3uAvfUj+sSIpc/eT4/tcIt9YSYUxeRcwFugjad9M+s3NrODnKeAkSdeSrMXfUL11GdKqyz8kycyKLXeHkzbCTgceLwS6wnh98akRZva+pLOAwZJ+ICmgBVmOlbQT8ANpg91hVMcBwAVFYT2B30n6kdTmAzKybw884nIuS3nXgqclzSS5O5xiZh9Jegw4WtJYkvI3PCffBkBff04Fv+2fMbNPJPUB+qnmeLbTSCsMkE7wWM7MXi7f9Fm4CrhX0v7A08xuVZ4FM/tG0p4k14hvSJOZ2azZ7ibSg+Qq8zfS9+KdZlbwOx5KWrEYR/IPH1WujW597wlc5m49zYB/Ud7S3YvkpvID8CFwdpm0QRAsAGj2903Q0JC0HumFu4KZHeubYxY1s7H1LFoQ1AuSLgUeNLMn61uWuUXp1Im/mNkkVxjXyExGGgRKp068ZGb/qZh43tV5LPCOmfWvkG5LoB/wSzMbWS5tfdFyxdWtwyFn1bcYwULAyL6lthgE1SBppJnlnk0fLhkNHLfODAZWpmazTWvSmbBBsLDyd2Dx+hZibpG0CMn1ZRKAmT3UAJXlkSSXg//Oz3rN7IpKyrKne87MVmuoynIQBAsG4ZLR8DmbdDTTaNWcnTqGtJEmCBZKzOwjku9oo8bMvgduqW85yuFHrQVBECzUhIW54bM8SUGGmhMAjNqfBhAEQRAEQRDMAWFhbviMJO0wz1qhDgBeqB9xgiAIgtqwXrs2jAjf0iBo1ITC3PA5Dhgg6dekn+99nPQDALvUr1hBEARBEAQLB6EwN3DM7BU/W3VP4CHS4f4P+a97BUEQBEEQBHVMKMyNADObDtwlaSnSjxX8VD5HEARBEARBMK+ITX8NFEknSvpl5n434B2ST/O7kjarN+GCIAiCIAgWIuKHSxoo/vO4e5vZq37/KnA36fzZPwE7mtkO9SdhEARBUA3xwyVBXRA/UjLviR8uaZy0zSjLawGrAeeb2TfAxaQfEgiCIAiCIAjqmFCYGy7TJS3h11sDYzMb/X4i/M+DIAiCIAjmC6EwN1weAa6TtDdwAnBvJq4z6bSMIAiCIAiCoI4Jhbnh8mdgOnAeMAy4JBO3G3BHfQgVBEEQBEGwsBEKcwPFzKaa2RFmtoGZ/cbMvsvEnWtm59WnfAFImilpdOavvaTukqZKeknSK5IuLsqznKQfJP22KHyypHsz9z0l3ZS5313SCEkTs+VKOlPSCX69uaTnXZaJks7Mkbm7pIdywgdJmpRpyz2SlpL0mSR5mi0kmaR2fr+kpM8lNZF0k6SeHr6nt3+MpJeL2+pp+kj6xOua4PUtXtwmv39L0rpF+f8l6aSi/p4kabCkPcs8s30lne7XR0uabdeMP8fxpcrIpDtP0ruSphWFX5Lpx1clfZmJu8jbO1HSZZm+vc3lHy/pBknNPXwfSWO9rBGStvbwRbytFV2zfGwtWyndvKJQn4+f39dhPUf5Z+EV75vudVVXEARBKMxBMOfMMLMumb/JHj7EzDYCNgL2lLRVJs/+wHDgwJzyuknqWBwoqRNwBXCwma0HdALezMl/M3CUmXXxNHfVsj29M23paWZfAh8C63n8lsBL/h9gc+B5M/v5XHBX9K4D9jKzzqQ+GFSivju9ro7A90CvEunuIP0cfKGOJkBP4E4PGmJmG5nZuqRfxrxC0o4lyjoJuArAzK4xs1tKpKuGB4FNiwPN7PhCPwKXA/e53FsCW5E27HYCNgG282y3AR2ADYAWwJEePhDo7GUdAVzvdXzvcaX6rE6R1LSKZEsBdaIw+6Tot8DWZtYBOAr4r6SV66K+IAiCUJiDoI4wsxnAaCD7Ej8Q+D+gXc7L/WLgrzlFnQScZ2aveLk/mtlVOemWBz7wNDPN7OW5awEAQ6lRkLckuQZl758rSt+atCH1M5fjOzObVK4Ct5K2BL4okaQfGYUZ2BaYbGZvFyc0s9HA2cCxOfWsA3xnZp/6fdY639Ut4sOAY8rJm6lruJl9UCHZgS4/gAGLAYsAiwLNgY+8rEfMAV4A2nn4NKs5+7Oll1HgAaB3NbIWI2lTSc+5Zf65ggXfLf9XZNI9VLDcSpom6WxJzwNbSDpY0gtu/b42R4m+AFjT4/sq0det6OMk9fJyuyutcNzj1uLbCpb3MpwMnFh4lmY2CrgRf3ZZq7qkbpIG+XVLt+C/6G3fx8ObumwvukX/t5Vkk3SB0grKWBWtJAVBsOARCnMQzDktMkvv9xdHSloaWBsY7PerACua2Qsk62+xdfAuYGOlYwSzdCL9YE0lLgEmSbpf0m8lLVbL9tyWaU9fD3uOGgV5DdJZ4IUzKrckKdQ/Y2afA/2BtyX1k9TbLcJ59JI0GngPWIZksZ0NMxsL/CSpswcdQI0SmscokrW2mK08Lo8bgePMbItsoKSVJD1Spq6SSFqN9MucTwGY2TDgadKk5gPgcTObWJSnOXAI8FgmrIfSuewPk6zMBcaTrNRzwivAtr4ScjrpfPdKtATGm9lmpAlRL2Art37PZHbl/RTgDbe2nwj8EuhC2rS8E9BXUltPuxHpfPn1SeNsK8rTkdk/EyM8fzlOBZ4ys02A7V2GlsCvgakevgnwG0mrl5JN0jJAD6CjmW0InFtckbuMjJA04sfpX1cQKwiChk4ozA0clfhFP0mzLQUH852sS0aPTPg2ksaS3BkeMrMPPfwAatwk7mB2t4yZQF/gL3MijJmdTVJmBwAHkVG6qiTrknGihw0FtnTlYbKZfQtIUiugK8kaWizHkcCOHncCcEOJ+u50ZWtFYBxwYol04FZmt0bvQ1LcS1HKOtkW+GS2xNKSwFJm9owH3VqIM7P3zWyPMnWV4wDgHjOb6fWsRXJvaUdaddhB0rZFea4CBpvZkIwM97vbwb7AOZnwmcD3klrPgWxLAncr+WpfQlJAKzGTmtN6diQ9/xd90rMjSZksx9ZAP1/9+Ah4hhqF/wUzm+LuPaOB9tU35WcqWaUBdgFOcZkHkSz+q3r4oR7+PNCGNNktJdtXwLfA9Uq/yDq9uCIzu87MuplZt2aLz8kjCoKgIREKc8PniRLhtVWGgvnHELc6bQD8TlIXDz8Q6CNpMskK21nS2kV5byW5HKyaCZtAUk4qYmZvmNnVJAWms6Q2c9yKVN5rwNLAXqTTWiBZ9g4H3sqcDV6cb5yZXQLsDOxXoQ4jWZeLlccs/YBfkSyTY83s4zJpNwIm5oTPIClIxYhZXR3mFcWW8B7AcHezmAY8SvIDT0JIZwDLkU7ImQ0zG0xycchu4FuUpLjVlnOAp82sE+nZFvrlR2Z9L2T769uC8k/qs5szE6x1zezMCnWWU2i/y1zPpPI58y8z+2diY5KVGWZtR7YNAvbLyL2qW/kF/CETvrqZDSglm5n9SPJfv5c0kYnv4yBYwAmFuYGidPJA03Qp+X3hb23SCyFowFj6pcbzgZPdR7Slma1sZu3NrL3HHVCU5weSxe9PmeC+wF+VfHALY2M2pUrSLzK+n2uTXu5fzoOmDAP+SI3CPMzlK/ZfRlKrgs+r0wWYzdc4h62BN0pFmtkbJDeACyjjjiFpQ+BvwJU50ROBYncXfHPjVPkJFMyhX3CRHOuSJhrDMsHvANtJauauF9u5TEg6EtgVOLBoE+VaGZ/ZjUn+z5/5fRvgEx8zuNtGtSxJcoUB6JMJnwx08TG2CjmbGp2BQE9Jy3vdy7gLSpavST7tBQaT3HCaSlqONEGabYUii6TzJfXIiboIuLAwIfRJaQ/g2kw7Cgp1dsL2OPCHTJ9ulAn/nWpOJ1nHXTVKydUKWNLMHiF9FrqUa0cQBI2fUJgbLj+STg5Y3K9/yPy9jO/0Dxo815AUg78CxX7O95J/WsZ/yFjY3If3T0A/SRNJvqttc/IdQvJhHk2yVPfOWASz7ChpSuav4Leb9WF+MpN+KLAKNda7YaTl99kUZpKl7iT5EXXAWcyqkGXp5XWNJVmFz8nEnZaV0cP6kXyTi/txG/mxciRF+TgzG5hT32Bgo8ykIsvhwJVKm/5m/NyYMj7MSkfETQEWdznPzEQfCNyR2bAHcA9pUjAOGAOMMbOC3/Y1wArAMO+T0z18P2C89+WVQK9MmduTfuAItzqXs+COzfTnP0kK5/mShgLZzXpDgbdcxosp4fPtG0pPAwb483uCojFpZp8BQ5U2+fUlPbex3vangJMy7kql2IDk2lRcf3/S52SopNeBZ4F9zazgcnMWcKmkIaSJY4FzSJstx7o7SmHMXU/6Xh3l4ddS3srdGnjI2/4McHyFdgRB0MjRrN/nQUPBrTUifRlvS82ysZGsSjPKZA+CIAdJlwIPmtmTFRM3cCTdB/zFzCYpHbO2hpldVt9yzUskPW5mu1ZI04y0abMJ6ejFBvdSa7ni6tbhkLPqW4xgAWNk39mOkQ/mEkkjzaxbXlzFQ++D+iFzZNZq8PPZsytUcYxVEASl+TuQu5G2MSFpEeCBwpF9Zjbbj9EsCFRSlj3Nj6TVlSAIgjojXDIaOEq/lnU7aWPP6x62t6TZjjEKgqA8ZvaRL+c3aszse5u7H10JgiAIakEozA2fa4CpJEvz9x42jHr6ha8gCIIgCIKFjXDJaPjsCKxkZj9IMgAz+6SwOz0IgiBo2KzXrg0jwt80CBo1YWFu+EwFsueuImlV/CeQgyAIgiAIgrolFOaGz/XAvZK2B5r4EWA3k1w1giAIgiAIgjomXDIaPheSNvxdSTo/9AbSGaGX1qdQQRAEQRAECwtxDnMQBEEQ1CFxDnMwt8SZy/OHcucwh0tGI0DSzpL+I+lBv+8maYf6lisIgiAIgmBhIBTmBo6kPwBXA6+RfvEP0k/3xjnMQRAEQRAE84FQmBs+fwJ2MrMLgJ887BVg3XqTKAiCIAiCYCEiFOaGT2vgXb8uOJw3p+ZHTIIgCIIgCII6JBTmhs9g4JSisOOAp+tBliAIgiAIgoWOUJgbPn8AekiaDLSWNAnYH/hzvUqVQdIKkm6X9KakkZKGSerhcd0lTZX0kqRXJF2cyddH0hV+faYkk7RWJv54D+vm90dIGidprKTxkvbx8JskvSVptNdxhqTlPWzFTHlXSZpl8iGpiaTLvLxxkl6UtLqk5728dyR94tejJbXPaf89ktbw60ckLZWT5kxJJ1Tox96ZekZL+klSF49bRNJ1kl71Nu7n4atJGuh9MkhSu6Iyl5D0XqGfPew2SZO8zTdIau7he0qquJXfn6lJ2isT9pCk7pXyVouPjU983Lwm6XFJW86r8nPqu0nSdEmtM2GXejuX9fvnyuTt6deDCuN1Hsg0uVB3Tvg4HyPjCp+DeUX2c1mLPJtnPjMTJZ3p4d2reW7VpquFPLl9l4mv8+cUBMGCRSjMDRhJTYD1gG2AXwEHAYcBm5nZh/UpWwFJAh4ABpvZGmbWFTgAyCpuQ8xsI2AjYE9JW5UobpznLdATeNnraQecCmxtZhsCmwNjM2lPNLMuQBdSH7UknWF9seffGNga+EdRnb2AlYANzWwDoAfwpZlt5uWdDtxpZl38b3JR+zsCTc3sTQAz28PMvizRvrKY2W2FeoBDgMlmNtqjTwU+NrN1gPWBZzz8YuAW75OzgfOLij0nk7bAbUAHYAOgBXCkhz8M7C1p8SrEneIy1SV3mtlGZrY2cAFwn6T1qs0sqbbnzL8OFCZhTYDtgfcKkWZWZwr7HLC9j5OewGX1LAukH1M6ymXqBNzl4d2Bavqt2nRBEAT1QijMDRgz+wn4n5nNMLMXzOxuMxvu4Q2FHYDvzeznXx40s7fN7PLihGY2AxgNrFyirAeoUVjWIP0s+CcetzzwNTDNy5pmZm/llLGY//8GuA5YU+lXEq8AjjWzH4rStwU+KPSpmU0xsy/KNbiI3sD/CjdZa5OkU92S+yS136R5INAvc38Ergyb2U9m9qmHrw8M9Oun8f7z+rsCKwADsgWb2SPmAC/gkxu/HwTsWYV8Y4CpknYujpDUVdIzSqsNj0tq6xb/kR7f2S23q/r9G5WUdDN7mvQ8j/I8XSQNd8v6/ZKW9vBBkv4u6Rngj279vUbSELfOl2tbP9IECpICNxT4MdOuaf5fkq6Q9LKkh0ljczYkXS1phKQJWcu9j5GzJI1yC3EHD28jaYBb1a8FVK5PnCWAn8erpIMlveCW3mslNa0gyyaSnpM0xvMVLOwrSXrMrfsXVSHH8sAHAGY208xeVlqNORo43uXZRtJebol+SdKTSqtTeemWk3Sv0orPi4VJttJKzQ3+nN+UdFw5oSS1lPSwt2+8pF45aebHcwqCoJETCnPDZ7CkzetbiDJ0BEZVk9CVmrVJftl5fAW8K6kTSWG8MxM3BvgIeEvSjcq4Azh9JY0mWT7vMLOPXQn+HXAv8KqZ5dV7F7CXv6j/IWmjatqSYStgZHGgK6sHkKzqvwQ2ycQdLenoCuX2whVm1bh4nOMv77slreBhY4D9/LoHyW2njZKF9B/AiaUqUHLFOAR4LBM8grSiUQ3nAqfllHk50NNXG24AzjOzj4HFJC3h5Y8AtpG0GslyPr2K+kaRLOMAtwAnu2V9HHBGJt1SZradmRVWE9oD2wG/AK6RtBj5vAYs5+P0QOCOEul6kCZAGwC/obRl9FQ/AH9DYDtJG2biPjWzjUlHRhZcdc4AnvXVmP7AqiXKBXha0njS6sFpAErW917AVm7pnUma0OXKImkR0mfsj2bWGdiJdGQlpJWaXt7GXpJWKSMLwCXAJJ+8/FbSYr4acw1wia+cDAGeBTb3Nt4BnFQi3aV+vwlpfF+fqasDsCuwKXCGj7lS7Aa8b2adzawTs471AnXynCQd5Yr4iB+nf11GxCAIGgOhMDd83gYedUvZOZLOLvzVt2B5SLrSrTkvZoK3kTQW+BB4qII7yR0kRXNf4P5CoJnNJL38egKvApfI/SSdgkvGisCOcn9Id2kYD1yVV5mZTSEpP38hHds3UNKO1baXZKH+JCd8G+B+M5tuZl+RXqyFOq/JWuSLkbQZMN3MxntQM5IVeKi/vIfhriakl/h2kl4iKYXvkayivwceMbN3Kc1VJFeaIZmwj0kuKhUp5JOUVbDXJS3JP+ETmNOocc95jjTB2Bb4u//fBsjWXw55fUuSlOKCq8nN1JxRDrNOtADucqv8a8Cb1CjdedxHGn+blZFrW6CfW1LfB54qke5XkkYBL5EmlusX1QNpstU+U+5/AczsYTKW4xy2dwVwA+AKSa2AHYGuwIve9zsCa5SRZV3S6sqLXudXZlawqA80s6lm9i3JLWq1MrJgZmcD3UirGQeRr5hCGguPSxpHmsx1LJFuJ2/XaNJnZ4mM9fthM/vOV1k+Jq2ilGIcsJOkCyVtY2ZTc9LUyXMys+vMrJuZdWu2eOu8JEEQNCJq6+MXzH9akFwVYFa/4IbCBGosnJjZMUouCSMyaYaY2Z6S1gGelXR/xje3mAeBvsAIM/tKqlntzLgQvCDpCeBG4MxsZjObJmkQyV+5sEnrJ2rOsJ4NM/sOeJQ0MfmIpKwPLJW+iBnUuIHMVnSVZRRzALO6Y3wGTKdmAnE38GsAV9h+CeBK035mNlXSFqSJyu+BVsAikqaZ2Sme9gxgOeC3RXUvRo2VsRrOI/kyFxQtARPMbIuctENICvJqJDeWk0l99FCVdW0ETKwi3TdF98XPwSTd6OW9b2Z7ZOLuIFmybzazn7Ljr0KZsyBpddJkZhMz+0LSTcw6Tr7z/zOZ9Xu4VmPGzN7wMbs+qe9vNrO/VCmLytT3Xea6WMaSsgBXS/o38ImkNjnJLgf+aWb9lTaJnlmiuCbAFu7GlW1LrWQzs1d9tWcP4HxJA1y5L5Q3X55TEASNn7AwN3DM7PBSf/Utm/MUaan9d5mwXH9UM3uV5Id7cqnC/AV5MkkR+xlJKylt3CvQhWR9pyhdM5J18I1qhJe0saSV/LoJaVl2tnLLMBFYKyd8MOl0kxZuGSt2ISklTxPSKSg/uwP4ROFBkl8tJMthYTPksp4HkpX8Bs/T28xWNbP2JIXgloyyfCRpSftAm90ffh2SRR5JPSQVbyKcBTMbACwNdPagSSS3hi28jOZKGyMLfXIw8JrX+zlJkRlaRb9sR/Jf/rdbCb/IWLYPYfaNjVn2VzoNZU2SxXWSf4a6FCnLmNk7pAlA7opEph0HSGoqqS1pc2AxS5AU96nuPrN7pTZ6ub0BJO1O6teySFoeWJ00ZgcCPT0MScu4y0spWV4h+Spv4ulbq8JGSUm3SNo0J/wXqpldrE1SML8k7TvImleXpGYj5WGZ8OJ0A4BjM+V3KSdXGXlXIq3W/Je0KrNxUZL58pyCIGj8hIW5gSPpczNbJif8YzPL3Ww0PzEzk7QvyUXiJJJ7wjeUVoqvAU5wy06pMvN8R5sDF/sL8FuvJ+sH3FfSacAiJMXhvtmLyGV54N+SFvX7F0gbBKvlYZIi+2Q20MxGSbqTtMnxbTLL+3L/5RJuGdsCU8xP3chwMnCrpH+R2l6YMHUnWc6M9CI/pgqZr3GZhrmOc1/G6rY9SfEGWJPkV16J8/CNj2b2vdIRa5e560Qz4F8kq/Nkr6/gS/4s0M5Kb7LsJWlr0gTsLZL1vGBhPozkj7w4yc2i3ARyEkmhXgE42t0MSmJm15aLJ1n6dyAt979KjrJuZmPcTWaCy1dxUgCcBfRz94BngHfKpH1a0kzS5+IUM/sI+Mg/AwN8EvUDcIyZDc+TxZ9VL+BySS1IKws7VZBxQ3xzXxGHkL4DppNWG3qb2UxJDwL3KB199weSRfluSe8Bw0nKPqQJYTbdccCV7srVjDRmKvn957EB6bvhJ1J/ZCf28+M5BUGwgKBkvAoaKpK+NrPWRWHNgQ/NLG/JM5iPuKLxNGmj1cz6lmducAvb7Wa2o9//FzjezPJ8tBsFvsT+kJndU9+yNHaUNmz+x8z2r29ZGhstV1zdOhxS8YjzICjJyL6H1rcICwWSRvom4NkIC3MDRdIQkp/cYpKKT3doR41/blCPmNkM9wdemcZvaVoV+L/CjZkdXI+yBA0M37waynIQBAsloTA3XK4nbcrZBPhPJtxIx6uV2pkfzGfM7PH6lmFeUDgtYUHCzPrUtwxBEARB4ycU5gaKmd0MIGm4mb1S3/IEQRAEQRAsrITC3EDxo5C+K5zFK2k50uapTqRzeE8ws2n1J2EQBEFQDeu1a8OI8EENgkZNHCvXcPkX6Uc4ClxPOvLrOpLSXM3P1QZBEARBEARzSViYGy7r4UeRKf008u5AJz+Ivz9p09/v60+8IAiCIAiChYOwMDdcmgHf+/XmpGPkXgXwnzteqp7kCoIgCIIgWKgIC3PDZQLpCKe7SD+V/PMPY0haGZhaT3IFQRAEtWDilM/oeuIt9S1G0MCJs5YbNqEwN1xOBh6UdA3pZ2a3zsT1orpfpAqCIAiCIAjmklCYGyhm9qykVUkb/V41s68z0Q8DeT8fHQRBEARBEMxjQmFuwLiSPDInfFI9iBMEQRAEQbBQEpv+giAIgiAIgqAMoTAHQRAEQRAEQRlCYQ6CYI6RdIOkjyWNLxF/giSTtKzfN5d0s6RxkiZK+kuZspeT9IOk3/p9d0nDitI0k/SRpLaSbpL0lqTR/vdciXI3knS9X+8t6ZQS6Sr+kqakHSWN8vqelbSWh0vSZZJelzRW0sYevpikFySNkTRB0lmZsjpLGuZ986CkJTy8jaSnJU2TdEVR/U9KWroKOQdJmuT1viipS6U8c4qkMyWdMLdpKuTf2vvxFW/XMXNaVhAEQTWEwhwEwdxwE7BbXoSkVYCdgXcywfsDi5rZBkBX4LeS2pcoe39gOHCg3w8G2hWl3wkYb2Yf+P2JZtbF/7YsUe5fgcsBzKy/mV1QunkVuRrobWZdgNuB0zx8d2Bt/zvK0wF8B+xgZp2BLsBukjb3uOuBU7xv7gdO9PBvgb8BeQrmrVT/A0a9vd6rgL5V5mlwSFqR1NdHm1kHYCvgCEk96leyIAgWZEJhDoJgjjGzwcDnJaIvAU4CLJsFaCmpGdCC9OM8X5XIfyDwfyQleWUz+wm4m3SsYoEDgH7VyiupNbChmY3x+z4Fq62k1d3C+6Kkc6os0oAl/HpJ4H2/3ge4xRLDgaUktfX7guW6uf8V+mdd0qQA4AlgPwAz+8bMniUpzsX0p2ZCUS3DgJUBJC0j6QG3gg+XtKGHb5ex1L/k/YakE71/xhZZx091S++T3o5C+G88/RhJ90pavFgYSWtKekzSSElDJHWoIP8xwE1mNgrAzD4ljbMTvbybJPXMlD8tc11K/oPdYj1a0rWSmhbySjrP5R8uaQUP31/SeA8vPLMgCBZgQmEOgmCeI2lv4L2CYprhHuAb4AOS5fliM5tN4Xbr9Ipm9gLpx3sKSnI/kpKMpEWBPYB7M1n7ZhS923JE6wbkuo8AlwJXm9kmwIdF8owukedI4BFJU4BDgIK1emXg3Uy6KdQoqU29vI+BJ8zseU8zHtjbr/cHVilR58+Y2RfAopLaVEqbYTfgAb8+C3jJzDYkWd4Lv65xAnCMW863AWZI2oVkMd+UZB3vKmlbSV1Jz2Qj4JfAJpm67jOzTdyyPRH4dY481wF/MLOuXu9VFeTvyOynB40A1i+XqYz865HG11be3plAb8/WEhju8g8GfuPhpwO7evje5CDpKEkjJI34cfrXeUmCIGhExLFyQRDMU9yKeCqwS070piSFZCVgaWCIpCfN7M2idAeQFGVIZ47/B/inmb0oqZWkdYH1SMrMF5l8J5rZPWXEawt8UiJuK9yqS3J1uLAQ4YpUHscDe5jZ85JOBP5JUqKVk9a8rJlAF0lLAfdL6mRm44EjgMsknU6yHH9fph1ZPib152cV0t0mqSXQFNjYw7amxpL9lPtLL0n6YaR/+qTjPjOb4grnLsBLnrcVSQFtDdxvZtMBJPXP1NlJ0rnAUp7+8axAkloBWwJ3Sz932aIV2iFmXbWollLyb0hyD3rRZWhB6lNIz+Ahvx5JcjGC1D83SboLuC+vMjO7jjQZoOWKq8+JvEEQNCBCYQ6CYF6zJrA6MMYVkHbAKEmbAgcBj5nZD8DHkoaSrL7FCvOBwAqSCpa+lSStbWavkRToA0gKc9XuGM4MYLEy8VUrNpKWAzpnLMR3Ao/59RRmtRC3o8ZdI1Vk9qWkQSSL73gzewWfZEhaB/hFlaIsRmpXJXoDY0hW8CtJ1uBcxd7MLpD0MMmCP1zSTp72fDO7NptY0p8o3W83Afua2RhJfYDuRfFNgC/LTEjymEAaM1nFvCvJygzwo5eL0gBcpCBqCfn/ANxsZnkbUH8ws0LbZuLvTDM7WtJmpGc0WlIXM6s0YQmCoBETLhlBEMxTzGycmS1vZu3NrD1JedzYzD4kuWHsoERLYHPglWx+tx63NLOVM2Wcj7tikJTkg4EdmFVpqoaJwFol4oZm6uhdIk2WL4AlXbmFZH2c6Nf9gUO9nZsDU83sA6WTP5YCkNSCtGnxFb9f3v83IW0evKaSAK4QrghM9vuBklYuld4nKqcBm7srwuBCWyV1Bz41s68krenP8UKSItqBZB0+wq3CSFrZZR4M9JDUQsnXea9Mla2BDyQ1J6dPzewr4C1J+xfaI6mzX/eQdH5OM64E+shP+nB3lPOAgt/5ZJICDcmXvLlfl5J/INAz0//LSFqtVB96mjXN7HkzOx34lCrcZ4IgaNyEhTkIgjlGUj+S1XBZ9+M9w8z+UybLlcCNJH9dATea2diiNAeSTonIci/JsnyOmb0saTow0sy+KUrXV9JpmftNzexn1wYze0XSkpJaF/3cPMAfgdsl/ZFZ/aKRNLrYCmpmP0r6DXCvpJ9ICvQRHv0IyTr7OjAdONzD2wI3K20qawLcZWaFJf8DVXM82n3eT4X6J5M2Fy4iaV9gFzN7maQYDndZmpAmA6U2YRbkniHpHyR/4ROBGyWNdTkP82R/krQ9yar6MvComX3nSvYwXzmYBhxsZqMk3QmMBt4GhmSq+xvwvIePIynQxfQGrvbn1pz0nMeQVipm2xDqE4+DgevcfaQ90MfMnvEk/wb+J+kFkjL8jecbUEL+l73uAd6HP5A2Fr5dphv7SlqbNIYHurxBECzAqGa1KQiCYMFH0vHA12Z2fX3LMrdIuhTob2YDJXUCjjCzP9e3XPMCSf8FjjezUj7nhXTHAEcD2xb5szcYWq64unU45KzKCYOFmpF9D61vERZ6JI00s255ceGSEQTBwsbVpPOQFwTGm9lAADMbv6AoywBmdnAlZdnTXWlmGzRUZTkIggWDcMkIgmChwsy+JZ2C0egxs3/XtwxBEAQLA2FhDoIgCIIgCIIyhIU5CIIgCOqQ9dq1YUT4pwZBoyYszEEQBEEQBEFQhlCYgyAIgiAIgqAMoTAHQRAEQRAEQRnChzkIgiAI6pCJUz6j64m31LcYQQMizlxufISFOQiCIAiCIAjKEApzEARBEARBEJQhFOYgCIIgCIIgKEMozEEQBEEQBEFQhlCYgyAIgiAIgqAMoTAHQVArJF0i6U+Z+8clXZ+5/4ekP1dZVn9J4zP3f5b0sqSxkgZKWq1EvlMlTfB0oyVtJul+v35d0lS/Hi1py5z8/5K0rV9fL2n9nDR9JF1RRRsek/SlpIeKwodkZHhf0gMevk9G7hGSts7kuUHSx9k+8fCLJe1QSRZPe6ik8d4/L0s6wcNvktSzXJuLytm3Upo5RZJJujVz30zSJ8V9WMsyp9Uyfffs2KjL9gZB0PgJhTkIgtryHLAlgKQmwLJAx0z8lsDQSoVI+iVQrOS8BHQzsw2Be4CLcvJtAewJbOzpdgLeNbMeZtYFOBIYYmZd/O+5ovzLAJub2WAAMzvSzF6u3OyS9AUOKQ40s20KMgDDgPs8aiDQ2cOPAK7PZLsJ2C2njsuBUyoJIml34E/ALmbWEdgYmJojWzVt3heoKwXyG6CTpBZ+vzPwXh3VVYru+Dh29qXu2hsEQSMnFOYgCGrLUGoUjY7AeOBrSUtLWhRYj6T4lkRSK+DPwLnZcDN72sym++1woF1O9rbAp2b2nef51Mzer4X8PYHHMrIMktTNrw+X9KqkZ4CtqinMzAYCX5eKl9Qa2AF4wNNPMzPz6JZA4RpX4j/PqeNtoI2kFSuI8xfghEJ/mNm3ZvbvHJmybZ4m6TxJYyQNl7SCW173Bvq6JXxNSV08fqxb85fOlHWhpBe877apIGOBR4Ff+PWBQL+MfJtKek7SS/5/XQ/vI+k+t+q/JmmWCVVxOzxsL0nPe1lPevvaA0cDx3v7tstp728kvejl3StpcS/vJkmXuVxvFqz2QRAs2ITCHARBrXBl7EdJq5IU52HA88AWQDdgrJl9X6GYc4B/ANPLpPk1SakqZgCwiitnV7myUxu2AkYWB0pqC5zl8TuTsTZK2lvS2bWsp0APYKCZfZUpr4ekV4CHSVbmahhFZSW+Ezltq0BLYLiZdQYGA79xq3x/4ES3kr8B3AKc7Fb9ccAZmTKamdmmJOv2GVTHHcABkhYDNiSNoQKvANua2UbA6cDfM3FdgF7ABkAvSauUaoeHP0taUdjI6zzJzCYD1wCXePueyWnvfWa2iZc3kTQeC7QFtiatdFyQ1zhJR7nLzYgfp5ecTwVB0EgIhTkIgjmhYGUuKMzDMvfPlcmHpC7AWmZ2f5k0B5OU777FcWY2DegKHAV8AtwpqU8tZG/r+YrZDBhkZp+4wn9nps7+ZnZ6LerIMov11Mu738w6kNwAzqmynI+BleZQhnJ8DxR8h0cC7YsTSFoSWMoVS4CbgW0zSQruJrn58zCzsZ72QOCRouglgbvdl/sSZnX5GWhmU83sW+BloODnXqod7YDHJY0DTiwqqxydlPzQxwG9i/I9YGY/uVvLCiXad52ZdTOzbs0Wb11llUEQNFRCYQ6CYE4o+DFvQHLJGE6yMFfjv7wF0FXSZJL1bx1JgwqRknYCTgX2LrhdFGNmM81skJmdARwL7FcL2WcAi5WIsxLhc4SkNsCmJEvy7JUlF4w1JS1bRXGLkWQvxwTSZKI2/JBxEZkJNKtlfoDCc6pt/v7AxRRNKEiTiKfNrBOwF7M+r+yYyNZXqh2XA1eY2QbAbyn97Iu5CTjW851VRgZVWV4QBI2YUJiDIJgThpKWoz935fVzYCmSMjysXEYzu9rMVjKz9qRl7VfNrDuApI2Aa0nK8sd5+SWtK2ntTFAX4O1ayD4RWCsn/Hmgu6Q2kpoD+9eizFLsDzzk1lAAJK0lSX69MbAI8FkVZa1Dmpwg6XxJPXLSnA9cVPB1lrSopOPmUPavgdYAZjYV+CLjn3wI8EypjF73ypIGVqjjBuBsMxtXFL4kNZsA+9RG6ByyZR2WCf+5fSXuWwMf+FjoPZcyBEHQyAmFOQiCOWEc6XSM4UVhU83s07koty/QirQcP1pS/5w0rYCb5cfPkXyNz6xFHQ+TTkiYBTP7wMsZBjxJ8hkGyvswSxoC3A3sKGmKpF0z0Qcwu/V0P2C8pNHAlUCvgmVUUj+vf10v69ce3pyk5I/wMjYAPsxpwyNe5pOSJpBcE+bEYgzJ3/dE3yy3JknZ7Ot93gWo5NPdFvixXAIzm2Jml+ZEXQScL2ko0LTWks/KmaTxNATIjs0HgR4+zrZh9vb+jTSJeoLkUx0EwUKMalawgiAIFg4kPQvsaWZf1rcs1eDW5I3N7G9+/7iZ7VohW70i6VjgHTPLm/QsVLRccXXrcMhZ9S1G0IAY2ffQ+hYhyEHSSDPrlhc3p5aHIAiCxsz/AasCX9azHNXSjHSqCAANXVkGMLOKP/oSBEHQWAiFOQiChQ4ze75yqoaDmd1d3zIEQRAszITCHARBEAR1yHrt2jAiluCDoFETm/6CIAiCIAiCoAyhMAdBEARBEARBGUJhDoIgCIIgCIIyhMIcBEEQBEEQBGWITX9BEARBUIdMnPIZXU+8pb7FCBoQcQ5z4yMszEEQBEEQBEFQhlCYgyAIgiAIgqAMoTAHQRAEQRAEQRlCYQ6CIAiCIAiCMoTCHATBHCPpBkkfSxpfFL6/pAmSfpLULSffqpKmSTqhRLmDJE2SNFbSK5KukLRUJn6mpNGSxkt6MBtXVE4LSc9IaippJUn3lKlvNjmL0qwmaaDLNEhSOw/vImmYt3espF45eS+XNC1z313SVG/DaEmnZ+JK9enFknYoJ6OnW9flGy1poqTrMnLuUSl/ppwekkxSh0xY+4JckvpIuqLa8uYlktpJ+p+k1yS96eNj0fqQJQiChYNQmIMgmBtuAnbLCR8P/BIYXCLfJcCjFcrubWYbAhsC3wH/y8TNMLMuZtYJ+Bw4pkQZRwD3mdlMM3vfzHpWqLMcFwO3uExnA+d7+HTgUDPrSOqLfxUp992ApZidId6GLmZ2dib8JvL79HLglCrkvAy4xMtdz/MBdAGqVpiBA4FngQNqkafOkSTgPuABM1sbWBtoAVxUr4IFQbBAEwpzEARzjJkNJimsxeETzWxSXh5J+wJvAhOqrON74CRgVUmdc5IMA1Yukb03rmgXWUdbSLrDLcJ3khSuSqwPDPTrp4F9XL5Xzew1v34f+BhYzutpCvR1+auiTJ++DbSRtGKFItoCUzL5xklahKTk93LL82xW8CySWgFbAb+mvMK8iqTHfDXgjEz+BySNdKv7UZnwaZLOkzRG0nBJK3j4/r5aMEZSqUlWgR2Ab83sRm/fTOB44FBJrYot35IektTdr3fx1YBRku72diKpq69EjJT0uKS2Hj5I0oWSXpD0qqRtPLyjh432MbR2BZmDIGjkhMIcBMF8Q1JL4GTgrNrkc6VoDNAhG+4K6Y5A/5y6FgHWMLPJOUX+Dpju1uLzgK6ZfNeXcM8YA+zn1z2A1pLaFNW5KbAI8IYHHQv0N7MPcsrbwhXERyV1zInPYxRJkS3HJcBTXu7xkpbyScfpwJ1ueb6zQhn7Ao+Z2avA55I2LpFuU9KkpAuwf6bfjjCzrkA34LhMP7UEhptZZ9Lqw288/HRgVw/fu4JsHYGR2QAz+wqYDKxVKpOkZYHTgJ3MbGNgBPBnSc1JVvieLvMNpDFRoJmZbQr8CShMCo4GLjWzLt7GKRQh6ShJIySN+HH61xWaFARBQycU5iAI5idnkdwFplVMOTvKXLeQNBr4DFgGeCIn/bLAlyXK2hb4L4CZjQXGFiLM7EgzG5GT5wRgO0kvAdsB7wE//ixcskreChxuZj9JWgnYnxqXiCyjgNVcQbwceKCEnMV8DKxULoFbXtcD7ga6A8PnwL/3QOAOv77D7/N4wsw+M7MZJDeJrT38OEljgOHAKiS3CYDvgYf8eiTQ3q+HAjdJ+g3QtIJsAqxEeDk2J60SDPWxcxiwGrAu0Al4wsNPA9pl8t2XI+8w4K+STiY9xxnFlZnZdWbWzcy6NVu8dQXRgiBo6MQv/QVBMD/ZDOgp6SKSX+9Pkr41s7Kbx9ySvAEw0YNmmFkXSUuSFLBjSL67WWYAi5UpNk/pKp04uVv80uVpBexnZlP9fgngYeA0MxvuWTYiWTxfT263LC7pdTNbyy2ihXIfkXSVpGXN7NMKYizm7apG1huAG9wNpVO17XRr8A5AJ0lGUmBNUp5bSXEfmrs/7ARsYWbTJQ2i5jn8YGaFPDPxd5CZHS1pM+AXwGhJXczssxIiTqDG0l+QeQlgBWCStzVrDCrULZKCf2BR3g2ACWa2RYn6vsuR93ZJz7u8j0s60syeKpE/CIIFgLAwB0Ew3zCzbcysvZm1B/4F/L0KZbk5aYPdu24NzpY3FTgOOMHTZeO+AJpKylOaB5NcCZDUibSxsCySlpVU+M78C0khLbh+3E/aEHh3pv6HzWzFTHunm9lanmdF37xWcONoQrKWV2Id0oZKJJ0vqUeOnLsV+sL9nduQrOFfA9WYOnt6W1Zz2VcB3qLGepxlZ0nLSGpBcuMYCiwJfOHKcgeSZbcsktY0s+fN7HTgU5Jv9MqSBuYkH0iafBzqeZsC/wCucEvvZKCLpCaSViG5jUCydm8lqfAMFpe0DknJXk7SFh7evJKLjKQ1gDfN7DKSO1DF8RMEQeMmFOYgCOYYSf1Iy9PrSpoi6dce3kPSFGAL4GFJj89B8bdJGktSEFvim+yKMbOXSP7FeZvTBpCv6F0NtPLyTwJeyLSplA9zd2CSpFdJ1syCn+uvSC4efVRzTFyXCm3rCYx3t4XLgAMKltcyfdqcZLEuuItsAHyYU/YumbIfB040sw9JGxXXd/l6Seom6fqc/AeSJgBZ7gUOykn7LMkNZTRwr7uyPAY08749h6SoVqKvpHFuDR9Mep5tybi8FPB+6kFaqXiNNNH4ycwKz2MoScEfRzrZZJTn+wToA/Rz2YYDHdy/uydwoffZaGDLCvL2IvXxaJJf/S1VtDEIgkaMalbHgiAIFiwkbQT82cwOqW9Z5ha3Jm9sZn/z+8fNbNd6FqvOkHQs8I6ZzbahsyjdlkA/4JdmNrJc2vqi5YqrW4dDarXPNVjAGdn30PoWIchB0kgzyz2TP3yYgyBYYDGzlyQ9Lampn7TRmGlGcj0AYEFWlgEquepk0j1H2rwXBEFQZ4TCHATBAo2Z3VDfMswLsv7RQRAEwfwlfJiDIAiCIAiCoAxhYQ6CIAiCOmS9dm0YET6rQdCoCQtzEARBEARBEJQhTskIgiAIgjpE0tek854bM8uSzshu7CwI7Yg21B2rmdlyeRHhkhEEQRAEdcukUkdVNRYkjWjsbYAFox3RhvohXDKCIAiCIAiCoAyhMAdBEARBEARBGUJhDoIgCIK65br6FmAesCC0ARaMdkQb6oHY9BcEQRAEQRAEZQgLcxAEQRAEQRCUIRTmIAiCIAiCIChDKMxBEARBUEdI2k3SJEmvSzqlvuWpBkmrSHpa0kRJEyT90cOXkfSEpNf8/9L1LWslJDWV9JKkh/y+UbVB0lKS7pH0ij+PLRphG473cTReUj9JizW2NkAozEEQBEFQJ0hqClwJ7A6sDxwoaf36laoqfgT+z8zWAzYHjnG5TwEGmtnawEC/b+j8EZiYuW9sbbgUeMzMOgCdSW1pNG2QtDJwHNDNzDoBTYEDaERtKBAKcxAEQRDUDZsCr5vZm2b2PXAHsE89y1QRM/vAzEb59dckJW1lkuw3e7KbgX3rRcAqkdQO+AVwfSa40bRB0hLAtsB/AMzsezP7kkbUBqcZ0EJSM2Bx4H0aXxtCYQ6CIAiCOmJl4N3M/RQPazRIag9sBDwPrGBmH0BSqoHl61G0avgXcBLwUyasMbVhDeAT4EZ3K7leUksaURvM7D3gYuAd4ANgqpkNoBG1oUAozEEQBEFQNygnrNGc5SqpFXAv8Ccz+6q+5akNkvYEPjazkfUty1zQDNgYuNrMNgK+oRG4LmRx3+R9gNWBlYCWkg6uX6nmjFCYgyAIgqBumAKskrlvR1qObvBIak5Slm8zs/s8+CNJbT2+LfBxfclXBVsBe0uaTHKF2UHSf2lcbZgCTDGz5/3+HpIC3ZjasBPwlpl9YmY/APcBW9K42gCEwhwEQRAEdcWLwNqSVpe0CGmzU/96lqkikkTym51oZv/MRPUHDvPrw4D/zW/ZqsXM/mJm7cysPanfnzKzg2lcbfgQeFfSuh60I/AyjagNJFeMzSUt7uNqR5JPfGNqAxC/9BcEQRAEdYakPUi+tE2BG8zsvPqVqDKStgaGAOOo8f/9K8mP+S5gVZIitL+ZfV4vQtYCSd2BE8xsT0ltaERtkNSFtGlxEeBN4HCSsbMxteEsoBfp9JWXgCOBVjSiNkAozEEQBEEQBEFQlnDJCIIgCIIgCIIyhMIcBEEQBEEQBGUIhTkIgiAIgiAIyhAKcxAEQRAEQRCUIRTmIAiCIAiCIChDKMxBEARBEARBUIZQmIMgCIIgWOiQdJCkEZKmSfpA0qN+BnVd1mmS1qrLOoK6IRTmIAiCIAgWKiT9mfSDMn8HViD9gMZVwD71KFbQgAmFOQj+n73zDtejKv745wuhhBBa6DVICz2Q0GukqghEwIAIAgKiIEWJovCD0BRFRYp0IYB0KdKrhARIgARSCZ3QpbeQUBLm98fMcjdv3naTXNLm8zz3ubunzjl7dnfOnNnzJkmSJLMNkhYETgIONbMbzexTM/vSzG41s96S5pH0d0lvxN/fJc0TefeT9FBFeV9bjSX1lfQPSbdL+kTSo5JWirj+kWVYWLV7fYPNTqaSVJiTJEmSJJmd2ASYF7ipRvyxwMZAV2BdYEPguFaUvxdwIrAw8DxwKoCZbRnx65rZ/GZ2baslT6YbqTAnSZIkSTI70Ql418wm1IjfGzjJzN42s3dw5XefVpR/o5k9FuVfiSveyUxOKsxJkiRJksxOvAcsKqldjfilgZdL5y9HWLP8r3Q8Dpi/deIlMyKpMCdJkiRJMjsxEPgM2LVG/BvACqXz5SMM4FNgviJC0pJtIF8yA1JrdpUkSZIkSTLLYWYfSToe+IekCcA9wJfAtkAP4GrgOEmPAwYcD/wrsg8D1pTUFXga6NPK6t8CvoX7NiczEWlhTpIkSZJktsLM/gb8Cv+Y7x3gVeAw4GbgFGAwMBwYATwRYZjZs/gOG/cBzwEP0Tr6AJdJ+lDSD6e2Hck3h8xsesuQJEmSJEmSJDMsaWFOkiRJkiRJkjqkwpwkSZIkSZIkdUiFOUmSJEmSJEnqkApzkiRJkiRJktQhFeYkSZIkSZIkqUMqzEmSJEmSJElSh1SYkyRJkiRJkqQOqTAnSZIkSZIkSR1SYU6SJEmSJEmSOqTCnCRJkiRJkiR1SIU5SZIkSZIkSeqQCnMyyyCpp6RXJY2VtN70lidpjKStJb3WBuV2lmSS2sX5nZJ+Mq3rmZFoTV9K2lvSPW0t06yEpCUk9Zf0iaS/TkH+/SQ91BayJdMHOZdK+kDSY9NbnqRtSYU5mQxJP5I0OBTPN0PZ2PwbqNckrTwVRfwFOMzM5jezJ2uUP0LSHKWwUyT1ldRe0nOS9q3Ic4KkhyXNIWkpSf+MPvlE0tOSTpTUoUpdi0a+9yR9KGmgpM1K8WtJulvSu5KsSv7D4hp8LqlvvUZLmlvSXyW9FtfsJUlnlOLHSNq2UedNKdF/pzRIY5I+DfnGSvqwreSphpl9x8wua4uyJS0g6e+SXom2PR/ni7ZFfdMCM7vSzLZvJu2MrOg1cR8tIummGHsvS/pRRfw2cR+Pk/SApBXqVHcw8C6wgJn9WlI/SQdO4yY1haQ1Jd0TitqHkoZI+m7EtckktKL+us/qRs+kmYHKSXcNNge2A5Y1sw2/IdG+RlJvSSPjffSSpN4V8Z1jXI+Lcb5tKW4pSbdIeiPa2bki7zySLpH0saT/SfpVHTmmasxJ+p6kh2Is/0/SRZI6NiOLpFUl/UfSO5Lej+fBahXlHxX5Popy5pkSOVNhTiYhBuLfgT8ASwDLA+cCu0xHsZplBWBUgzRLA3tWBprZeOCnwN8kLQEgaXXgVxG+EDAQaA9sYmYd8QflQsBKVeoZCxwALAYsDPwJuLX08P0SuC7KrsYbwCnAJQ3aA/A7oDuwIdAR6AFMNmGoRYMXwrRk3ZjMzG9mC31DdbYpkuYG7gfWBHYEFgA2Bd7Dr0cyjagxThvdR/8AvsCfZXsD50laM8pbFLgR+D9gEWAwcG0dEVYAnjKzyRTz6cCtwL14uxYHDgc+bjbzN3DPT9UzaSZiBWCMmX1aLfIb6GcB++LvmB2BwySV329X4/3eCTgW+LekxSLuK+AuYLcaZfcBVsHb2AP4jaQdp3UDggXx993SwOrAssDpTcqyEHALsBp+PzwG/KfIKGkH4BhgG6Az8C3gxCmS0szyL/8ws2LQjgX2qJNmHlyhfiP+/g7ME3H7AQ9VpDdg5Tjui7/Abgc+AR4FVoq4/pH205ChV5W65wCOA14G3gYuD5nniTxF/hdqyG7Ab4HngHYRdgrQt5TmH8D1+IPoIeCYUroRwBxT0K9zAN+P+heviFvZb8OaeSeRr0aa24Aja8RdgT8Yx0cf/QZ/aBiuZLwC9I+0BwCjgQ+Au4EVSuV0wV/Q7wPPAD+M8INxpeWLKP/WOn2/cpXwrYHXSuerA/2AD/HJz84V4/Ny4J0YA8cV1wOYE19heBd4ETg06iyucz/gwPI4jfQfAC8B3ynVs2KMx0+A+2JM/KtGuw4E3gLmr3N96rWpLz4hvTP672FgSfy++gB4GlivlH4Mrow8FfGXAvPW6MtjgBeiHU8BPUtx+1G6V6OvDsHvjQ+izQrZPwMmhnwfRvrvRpmfAK8DR9do+37RprOBj6I921Rc038Cb0Y5pwBzVuQ9Ax93p9Tp48nuI6ADPi5XrbgfTiuN3Ucq0o8HulQpvy+TjvOHo08+i/NzmngO1OwLYA9gSEX6XwM3Vyln0bheC1WJK9rwVcg1FldC+gD/Bv6FK9YH1uv7es8DmntW13wmRfzSwA34vfwScHgprj1wWdQ7Gn9mlcf1GKA3MDxk+CeuKN1Jyz27cCn9xsAj+P03DNi6FNcPODmuyyfAPcCiEfdKtLPox00q2vBTJr03TiTuQfw98z98vNV7Zxbpf4O/094EdsXvr2fxcf/7RmOrJNNZwNlxvCrwOdCxFD8AOKQiT7toZ+eK8NeB7UvnJwPXtGLM1Wx3E+34ATCitbJE3CLRnk5xfhXwh1L8NsD/mu3TScqekkz5N2v+4TPUCYSSUSPNScAg3KqxWDyITo64/WisML+PWx3aAVeWBz01lKpS/AHA8/gMcX7cOnRFK/IbPksdQovyVKkwz48/kG/ELU7Fy3sQcOIU9Olw/CVrwEVV4qeFwnwc/nD/BbA2oIr4McC2pfPOIc/l8bBrjz+kn8cVpHZR5iORvgPwKrB/xK2PK6Zrlq5rTWWm3rWhpOQBc4UMvwfmBr6Nv8RWi/jLcctBx2jDs8BPI+4QXAFZDn9gPkB9hflL4CBc0f45/kBXxA/Elem58SXXj6mtMF8DXFan3Y3a1Df6shswL/BfXIHYN2Q7BXig4lqOLLXz4aLvmVxh3gN/cc0B9MKVi6Wq3avRV7fh1prlcUVmxzr39ZvAFnG8MLB+jfbvhz9Tjoq+6IUri4tE/M3ABfgYWxy3Dv2sIu8v8XHXvk4/V1OY1wPGV4QdTUzqgDOB8yriRwK71aijL6VxXh5TTT4LavYFrly8D6xeSv9kNVnwicxzcb12BZaodU+VwvrgY37XGA/tG/T9rtR4HtS7n5t5JkX9Q4Dj8XviW/gkd4eIPw14MMbVsvgztFJhHoQrycvgiuYTcb3nwe+hEyLtMvhqz3ej3u3ifLHSNXwBVy7bx3kxoepM6RlS55o+VNH3E/AVxXmizHrvzCL98TEmDsLvvavw59yauFL+rSbGl2LMHBLnPYHRFWnOIRTqUthkCnP0vVEaW8DulJTYJsZczXY30Za/E7rBFMiyK/Bm6XwYpUkdLRPOTs3eu1/nbW2G/Jt1//Aly7ozr3i4fLd0vgO+JDXZwyPCKhXmi0tx3wWerpa2Rt33A78ona+GvwTaNZnf8Bfrd/GH+TxUUUiB70XadUthz1ExM29Fv84L7AX8pErctFCY58Qtqg/jFoU3ynVRW2H+VinsTkL5jPM5gHH4ElgvYEBFnRfQ8lLqS3MK88e4ledD4KwI35oWhXkL3CozRynf1fjLfs5o2xqluJ8B/eL4v+XrA2xPfYX5+VLa+SLtkriyOAGYrxT/L2orzPcSL9ga8TXbVOq7i0pxv6T0ksOVjQ8rrmW5nd8lVlSo8tKqkGUosEu1ezXav3np/DpaVlcmSRthr0T/L9Dguu9HaTISYY8B++AKz+eUFGH8PnmglPeVJu+xagrzFlQ8z3CFpBgz/6y8dvg9tF+NOvoy9Qpz1b6I4/OAU+N4TdzCWtUihyuS5+DP469wq+8qtcYBfg/1L5036vuaz4PSeKn3rK35TAI2qryu+KrJpXH8tfIc5wcyucK8d+n8BkoTH/weujmOf0vJqBJhd5dk6QccV4r7BXBXHHdmyhTmL4hVnwir987cGrfOFoaZjlHnRqX0Q4BdmxhfJ+LKYWG93gcYVJHmVCZ/31VTmJeLsHI7tivkrlJ3tTFXs90N2rEdPvZXba0s+H3xOrBXhRw7ls7nqmxvs3/pw5yUeQ9YtIHf1dL4cnjByxHWLP8rHY/DLbrNUq3udvjDv2nM7A78hX9wjSSjKv6D981SramnVN9nZnY1cIykdaekjAblTzSzf5jZZriF8FTgkvDBrserpeMVgDPjo4sPcWuXcAvNCsBGRVzE740rmK1hfTNbKP4OrxK/NPCqmX1VCns5ZFgUt0ZVXv9lynkr4urx9Tg0s3FxOH+U834pjIpyK2k0Luq1qeCt0vH4KueV90hlO6vef5L2lTS0dM3WwvuxFq25N3fDlfWXJT0oaZM6aV+3eFNVyLwC/vJ6syTjBbhFqqBe3zdiLO5TXmYB3MLfTHxbUKsvwN0QfiRJuLJznZl9Xq0QM3vNzA4zs5XwfvwUX4GpR+X9Xq/v6z0PGtLgmbQCsHTF8+T3tDzHK+/lamOg2XtmBWCPiro2Z9J7dmreSdV4x8w+K503eme+Z2YTS7JD42fAJEg6DF+V+l5pzEzN+B5bSt/avAWt1hUkbYxb13c3s2dbI0v4Zt8DnBvv24LKfiiOW32fp8KclBmIL//sWifNG/hDqGD5CAN/aM9XREhqrULViGp1T2DSh0uzHId/BDFfo4TBfUBPlXbYmALmwpcf2wwzG29m/8Bn6GsUwbWSl45fxZdjFyr9tTezRyLuwYq4+c3s5w3Kby1vAMtV9PHyuMXgXXw1ofL6vx7Hb+KWiHLclPAmsIik8rhYrlZifFzsoCo7pQT12jSlVLbzjcoEsdvDRcBh+NLjQri7gaagvsmur5k9bma74ArWzbhFuhbLhBJYKfOruPVx0dK4WsDM1qxXdyt4FmgnaZVS2LpMOiH+egIb13AlGn84PDWy1eoLzGwQbp3cAvgR7v/aWAizV3Gf87UayFV5v9fr+3rPg1ZR5Zn0KvBSRdkdzey7keVN3FJYUO/+a8SruIW5XFcHMzutGdGnsM7KfPXemVONpAOIj9rMrLxTxSjgW+XdJph0/NfEzD7Ar0PZwFMvb7W+alW75VvB3gIcYGb3t0YWSQvjyvItZnZqRdGjquR9y8zeqyVLLVJhTr7GzD7Cfan+IWlXSfNJmkvSdyT9OZJdDRwnabH4yvx4fMkafDloTUldJc2LLwO2hreor1BeDRwlaUVJ8+M7eVxrZhNaWQ9m1g//iO8nTWb5Gz4zvSyUESQtI+lvktapTCxpY0mby7dXai/pt7gF5dGIV/TR3HE+b3mrG0ntIn5OYM6Ir2r5l3SkfFuf9pHvJ/jS3pORpFG/ApwP/K60g8CCkvaIuNuAVSXtE+NhLkkblCzYzZTfDI/ik67fRB1b4x9LXhMWmOuAUyV1jGvwK1rG3nXA4ZKWjYfnMVMigJm9jPuu94lrt0nIUIsr8JfyDZK6yLcf7CTp9/Jtvmq2aUrkCw6Ndi6CW+aq7ezQAX+JvQMgaX9aFKrW8hawrHxHkGLLsL0lLWhmX+KuNhPr5F8cvzZzxZhaHbjDzN7EX3J/lW/NN4eklSRt1axg9e4j850LbgROktRBvq3jLrQoojcBa0naLco4HhhuZk+3ol9aO+6r9kUp/nLc1WKCmVXdyk/SwvLtLFeOPlsU/75jUEmuTpIWrCVEE31f73nQsO0NnkmPAR9L+m3EzynfHnCDyH5d1L2wpGXwSd+U8i/g+5J2iHrmDbmWbZjT752v6rWzSeq9M6cKSXvj78HtzOzFclxYaIcCJ0S7ewLr4C4sRf55cddEgHnivODykHthSV1wd6a+NUSpNuaabrektfAdO35pZrdWSVJTFkkL4G42D5tZtef+5cBPJa0R74bj6rSjLqkwJ5NgZn/DFZHj8AfGq/gD6+ZIcgquUAzHFc4nIqy4QU/CrW7P4TsRtIY+uEL6oaQfVom/BH/Z9cc/jPoM91ebUo7DP7hpiJm9j28X9iXwqKRPcJ/qj/CPYyqZB7f6vIdbE7+LL5cVM+wV8KW2YpY8Ht99oizbeFzx+3EcH1dDvPHAX/GlxXdx38HdSg/QP+IPmw8lHV2jfTfhH6pcI+lj3Br5nYj7BPcJ3hO3EPyPlo9awH1B14jyb64hY0PM7Atg56j3XXz3iH1LCswvceXzRXxsXUXLtnsX4Q/NYfiYvHFK5cDdTTbBr90puEJaa2n8c2Bb/IPDe3Hl8THc9eHRJto0JVyFKzsvxt9ke2Cb2VP4mBiIv8zWxv1Jp4T/4uP0f5LejbB9gDExVg7Bx2gtHsU/tn0XX5rfvWTd2RdXdotdP/5N61yfGt1Hv8A/vHobf4H/3MxGAZjZO7hryalR90ZU2XKyDmcCu8v3Qj4LQNKoUGJqUa8vwJ9va1HfuvwF7l97Hz7eRuLjc79o19PR1hfjnqy1DF6z7+s9D4I+1H9W13wmxeT3+0BX/Dn+LnAxvmsH+DvktYi7L+Sqev81Iqzvu+ATy+J91psmdJ9wyzoVeDjaufGUyECdd+Y04BR8y7jH1bLH/fml+D3x7f0+wD+m3D3GfUGxexL4M2x8Ke4E3P/3ZfwjzNPN7K5qQtQYc61p96/xDwP/WWpH2ZpdT5aewAbA/qW8YyUtH7LdBfwZ/xD85fg7oYYcdSm+Ck+SJEmqIOla/OPUKXrITmNZxuAfmt03vWVpBkn74fK2+Q8fzQpIKpT79c3suektz4yApJ8De5pZ0ysPSdIWpIU5SZKkhNzdZKVYpt4Rt1DdPJ3FSmYPfg48Pjsry/JfoNss7r/VcOvjTdNbriT5pn7hK0mSZGZhSdyloxO+NPxzq/JT60kyLYnVA1H/o+vZgbnxHTtWxLegvAZ3ZUqS6Uq6ZCRJkiRJkiRJHdIlI0mSJEmSJEnqkApzkiRJkiRJktQhFeYkSZIkSZIkqUMqzEmSJEmSJElSh1SYkyRJkiRJkqQOua1ckiRJkrQhiy66qHXu3Hl6i5EkSQOGDBnyrpktVi0uFeYkSZIkaUM6d+7M4MGDp7cYSZI0QNLLteJSYU6SJEmSNmT0a+/Rrffl01uMJJktGXL6vtOknPRhTpIkSZIkSZI6pMKcJEmSJEmSJHVIhTlJkiRJkiRJ6pAKc5IkSZIkSZLUIRXmJEmSJEmSJKlDKszJbI+kMyQdWTq/W9LFpfO/SvpVnfzzSbpd0tOSRkk6rRT3K0lPSRou6X5JK5Ti/hzpR0s6S5KqlL2xpEclDY10fSTtH+dDJX0haUQcn1Yl/3pFWyTtLOmYGm0Y20Q/HSbpeUkmadFS+NaSPirJdHwpbkxJvsn21ZJ0dLk8SXuXyhkq6StJXRv08WGS9m9C/v2irm1KYT0jbPdG+SvK6lstT/TFba0op7OkkRVhfSQdHccnSdo2jvtJ6h7HY8rXoJR3P0nntKYt05qy/HXSTLNrUVFmq9ou6UhJ85XOfz8ldSdJMuuTCnOSwCPApgCS5gAWBdYsxW8KPNygjL+YWRdgPWAzSd+J8CeB7ma2DvBv4M9Rz6bAZsA6wFrABsBWVcq9DDjYzLpGuuvM7FIz6xphbwA94ryaMvx74GwAM7vFzCZTqlvBw8C2QLV9KgcUMpnZSRVxhXzdy4GSlgO2A14pwszsylLb9gHGmNnQiK7Vx5cAhzfZhhHAXqXzPYFhTeYt5P7GtuM0s+PN7L5vqr5vmKm+FtOAI4H5SuepMCdJUpVUmJPEFcFN43hNYCTwiaSFJc0DrI4rvlUxs3Fm9kAcfwE8ASwb5w+Y2bhIOqgIBwyYF5gbmAeYC3irSvGLA29GWRPN7KlmGyWpI7COmQ2L868tcJJWlDRQ0uOSTm6mPDN70szGNFt/E5wB/Abvi2rsBVwdddfr43HAGEkbNlHnAGBDSXNJmh9YGRhaREo6PvpkpKQLC6t/WHf/IOlB4IhIvq2kAZKelbRTZUWSOki6JMp7UtIuTchXWUZVS3Yr8p4l6RFJLxblSDpX0s5xfJOkS+L4p5JOieNfRR+M1KSrL7XCj5X0jKT7gNWaFHFqrsWfJD0Wfb9FqcylJd0l6TlJfy6VdZ6kwbE6cWKEHQ4sDTwg6YFYtWgvX9m4MtLcLGlI5Du4VN5YSadKGiZpkKQlmmxzkiQzKakwJ7M9ZvYGMEHS8rjiPBB4FNgE6A4MDyWtIZIWAr4P3F8l+qfAnVHnQOABXBl+E7jbzEZXyXMG8EwoNj+TNG8rmtYdV/6rcSZwnpltAPyvog1DW1FHwSahPNwpqWydN+CeUDrKCsfOwOuFMl+DXoTCXCHfQkzex4OBLSrTVsGA+4AdgF2AWyrizzGzDcxsLaA9UFaEFzKzrczsr3HeGV8V+B5wfpVrcyzw3+jjHsDpkjpUkWklldxQgEOaaEezLAVsHu0oVhf609JXywBrxPHmwABJ3YD9gY2AjYGD5K499cL3xC3/P8BXS5phaq5FOzPbELcQn1AK74qPm7WBXrGKAXBsrHCsA2wlaR0zO4uWFZoesUIzPlY49o58B5hZN/xeOlxSpwjvAAwys3Xx/jyosnGSDg4lffCEcZ802SVJksyopMKcJE5hZS4U5oGl80eaKSCW6q8GzjKzFyvifoy/dE+P85Vxy/WyuNLybUlbVpYZ7g3dgXuAHwF3taJNSwHv1IjbjBZl9IqKOru2og5wa+8KoTycDdxcrsfM1ge+AxwqaUu5z+ixwPGTlRRI2ggYZ2aV/r21+vht3FrYDNfgCt6eTK6Q95D7jI8Avs2krjnXVqS9zsy+MrPngBeBLhXx2wPHhBLcD19RWL6KPC+U3Fm6Auc32Y5muDlkfAoorKADgC0krQE8BbwlaSl8gvgIrjjfZGafmtlY4EZcwa4VvkWEjzOzj5lc8a3HlF6LG+P/EHziUnC/mX1kZp9F24pvBn4o6Ql8pWhNWiYJjThc0jB8dWg5YJUI/wIofNUrZQDAzC40s+5m1r3dfB2brC5JkhmV/GnsJHEKP+a1cavsq8CvgY9xH9lmuBB4zsz+Xg6Uf7R1LLCVmX0ewT1xC9XYSHMnbrXrX1momb0AnCfpIuAdSZ3M7L0m5BmPK2m1qOUK0SpCSSqO74gl/0XN7N2w3mNmb0u6CdgQ+ABYERgWq+zLAk9I2tDMCmt3NQUKavQx3s7xTcr7mKS1cGvisyEDYSE+F/c5f1VSHybtv08ri2pwLmA3M3umGbmmBEmH0mLd/G6VJJ+XkwOY2euSFgZ2xMfbIsAPgbFm9knh+lCtujqiTNFYmoprUbRrIpO+x8rtnQi0k7QicDSwgZl9IKkv9e+LQoatcZ/9TcxsnKR+pXxfmlnR5koZkiSZBUkLc5I4D+NLvu+Hr/D7wEK41W1go8zh+7kgvkRcDl8PuADY2czeLkW9gi8Nt5M0F760P5lLhqTvlRSYVfCX84dNtmk07hdajYdxpRRg7xppmkLSkiX/0g3x58p7ch/ejhHeAbe4jjSzEWa2uJl1NrPOwGvA+oWyLP/wcg/c+liup2ofB6sS7ifyXTMOayD275j8A69CGXpX7lPbyHd4D0lzSFoJ+BZQqRjfDfyy1DfrNSiv1ZjZP0rW6TdakXUg3o/9cYvz0fGfCNtVvjNJB3xyN6BBeE9J7eN6f7+o5Bu8FvVYAJ/sfBS+xt8pxX0ClM2/X8b9CD7WPghluQs+oU2SZDYlZ8VJ4ozAd8e4qiJsfjN7t15GScviFuSncUspuP/lxbgLxvzA9RH+ipntjO+Y8e2ow4C7zOzWKsXvA5whaRwwAdjbzCY20yAze1rSgpI6mlmlE+URwFWSjgBuqGjP0GpuGfKPpH4DLAkMl3SHmR2IKzM/lzQBt/LuaWYWyslN0e52wFVm1oxLyZbAa2WXiwZ9DO5icmIcd6HBriZmdmeVsA/Dij8CGAM83kDOZ4AHcVeHQ8zsswrj7MnA3/G+UpQ52ceB04kBwPZm9rykl3Er8wAAM3sirLCPRdqLzexJ8A8Ja4Rfi3+w9zItijd8c9eiXvnDJD0JjMJdZ8ryXAjcKelNM+sR58PDfeMA4BBJw/FrPWhKZUiSZOZHLatKSZLMakg6CvikpFjOcoTl9ldmtk+c3wb8oNkPNZO2I6+F02HJFa3LPic2TpgkyTRnyOn7Np1W0hCr2AK1IF0ykmTW5jwm9eucFVkU+L/ixMx2mt0VtBmFvBZJkswqpEtGkszCxG4BVzRMOBNjZvdObxmSJEmSWZu0MCdJkiRJkiRJHdLCnCRJkiRtyOrLdmJwK/wokySZ8UgLc5IkSZIkSZLUIRXmJEmSJEmSJKlDKsxJkiRJkiRJUof0YU6SJEmSNmT0a+/Rrffl01uMaUJr9rRNklmJtDAnSZIkSZIkSR1SYU6SJEmSJEmSOqTCnCRJkiRJkiR1SIU5SZIkSZIkSeqQCnMy2yFpoqShpb9jmsy3uyST1D3Oe1SU85mkXavk21jSo5FmtKQ+kvYv5ftC0og4Pq1K/vUkXRzHO9eSV9LYJtrwT0nDJA2X9G9J80f4LhE2VNJgSZuX8owpyTe4FL6IpHslPRf/F47wtSX1bSDH2qX2vy/ppTi+r1EbIn9nST8qnW8t6bZm8pbyj486h0l6RNJqzeZvUHY/Sc+U2vfvKShjkvZViTNJJ5fCFpX0paRz4vwQSZN9nRV5R8ZxV0nfba1s0wJJfSWNk9SxFHZmtGvRqShz91akX0jSL0rnNfs8SZIkFeZkdmS8mXUt/U2mpFYSL/bDgUeLMDN7oCgD+DYwDrinSvbLgIMj3VrAdWZ2aSnvG0CPOK+mDP8eODvqvKUZeetwlJmta2brAK8Ah0X4/cC6Ic8BwMUV+Qr5upfCjgHuN7NVIv8xIeMIYFlJy9cSwsxGlNp/C9A7zrdt1ABJ7YDOwNQqNy9Enevi1+j3U1lemb1L46tpJa5EZ+q370Vgp9L5HsCo4sTMzjezRtsydAWmi8IcPA/sAiBpDqAH8Po3WP9CwC9K552Z+jGVJMksSirMSdIcJwN/Bj6rEb87cKeZjasStzjwJoCZTTSzp5qtNBT1dcxsWJzvV7IirihpoKTHy9bGepjZx5FXQHvAInysmVkk61CEN2AXXNEk/u9airsV2LMZmcqEdbaw4C8qaUwc7yfpekm34pOS04AtwoJ7VEUZHSRdEv3ypKRdmqh6AeCDyN9Z0gBJT8TfphF+RbksSVdK2rkVbft+rDQ8Kek+SUtE+FYla/STcc1rti8YD4wu+groBVxXqquPpKPjuFtY0QcCh0bY3MBJQK+oo1esGNwcKw2DJK0TaUeENVaS3iss19Ef28a1uVHSXfLVhj832SVXh9wAWwMPAxNKbbhZ0hBJoyQdXAofK+nUaNOgoh+DLWO14MXC2ixpfkn3x7UcUbqGpwErRftPr+zzOuNg6xin/5b0dIwDNdnmJElmUlJhTmZH2mtSV4pe9RJLWg9YzszqLfnviSsA1TgDeEbSTZJ+JmneVsjaHRhZI+5M4Dwz2wD4X4XMQ2sVKOnSSN+FsFxHeE9JTwO341bmAgPuCeXl4FL4EmZWTATexCcGBYOBLeo3rdVsAvzEzL6NW7MHhAX3jIp0xwL/jX7pAZwuqUOV8gpl6QXgV8DfIvxtYDszWx9X6M6K8IuB/QEkLQhsCtxRQ9YrS+Pr9Ah7CNjYzNYDrgF+E+FHA4eGtX0LXBmu176Ca4A9JS0LTMRXKqpxKXC4mW1SBJjZF8DxwLVRx7XAicCTsfrwe6CwUD8MbAasiVu2i+u6MTAojrvifbU2roQvV0OWMs8Bi8ldefaK9pQ5wMy64ffA4ZI6RXgHYFCsDPQHDirlWQrYHLe+FysxnwE943r2AP4aCu4xtKwy9GbyPq81DgDWA44E1gC+Ff2TJMksTCrMyexIpUvGtbUSypeKzwB+XSfNUriicHe1eDM7CX/p34Mv+d7VClmXAt6pEbcZLUr6FRV1dq1VoJntDywNjKbFwoeZ3WRmXXBLcdlivVkoDd8BDpW0ZRNyvx11TEvuNbP3m0i3PXBMTBr6AfMC1dxDCmVpJVz5uTDC5wIukjQCuB5XijCzB4GVJS2OK3g3mNmEyYsFJnXJ6B1hywJ3R7m9cQUUXCH9m6TDgYXqlFnJXcB2IUvVMRyK/UIhO1SMkwo2L+LN7L9Ap8g/ANgy/s4D1pa0DPC+mRV+8/eb2Udm9hnwFLBCk224EZ9sbhT1lDlc0jBcKV8OWCXCvwCKyesQ3JWi4GYz+ypWcQrLs4A/SBoO3AcsU4qrR9VxEDxmZq+Z2VfA0AoZvFLpYPn3AIMnjPukieqSJJmRSYU5SerTEfc77id3D9gYuKW0FA7wQ+AmM/uyViFm9oKZnQdsA6xbspY1Yjyu8NUsuslyKuWZiCtZu1WJ649bXxeN8zfi/9vATcCGkfStmCwUk4a3S8XMG7K3lgm0PJcq2/1pk2UI2K2ksC5vZqMb5LkFVwgBjgLeAtbFJzpzl9JdAeyNW5ovBZB0d1iSK/2+KzkbOMfM1gZ+RrQvfNIPxF1kBknq0kwjw0o8BJ/M3VAjmWh+jFRzKzDcirtF/PXDJ3C7M6mC+3npeCLN/4rsNfjk7N5QPl0QaWtgW2CTsCQ/Sct4+LLkPlRZV1mOoj17A4sB3WIi+Rb176mCeuOgYXvN7EIz625m3dvN17EyOkmSmYxUmJOkDmE1W9TMOptZZ9zatbOZDS4l24va7hhI+l7Jx3EV/AX7YZMijAZWrhH3MC1+wns3Kih8UFcujoHvA0/H+cqFjJLWx5WD9+T+wB0jvANuvS1cRG4BfhLHPwH+U6pu1SKdpA0lNfu7wGOAbnFc72O5T/DJTDXuBn5Zas96TdS7OfBCHC8IvBkK3D7AnKV0fXFrNGY2Kv7vEIr5gQ3qWJCWj9qKfkPSSvER5J9wV5YuDdpX5q/Ab83svWqRZvYh8JFadj0pj5PKOvoX8aGwvmtmH5vZq8CiwCpm9iLuWnI0k1uEJ0PS5ZI2rBVvZq/gLjTnVkQtCHxgZuNiArFxo7rqsCDwtpl9KakHLdbvyvZXntcbB0mSzGY0awVIklmJ9hU+vndZ9d0pGiKpM75c/GCdZPsAZ0gah1tQ9w4Lb0PM7GlJC0rqaGaV67pHAFdJOoIKC6OkoVXcMgRcJmmBOB4G/DzidgP2lfQlbhnuZWYWH1TdFLpnO+AqMytcSk4DrpP0U3zHjT1KdfXAfaHB3SGatTb/JcrcB/hvnXTDgQmxZN8Xt0AWnAz8HRgeSvMYJt1RomClGAfCl/kLhfdc4AZJewAPULJsm9lbkkYDNzdox5WSija/G7t/9AGul/Q6PvFaMeKPDEVuIu7OcCfwVbl9tfyYQ2kfVS2uxP7AJTH+ym5DD9DiuvLHkO/ScF0YR0mpx3eHKRTGAZH+oQb1AqxDfPBaCzO7oErwXcAhIcsztPhKTwlXArfKt0QcSkwSzew9SQ/Lt9m7E/fbLo+pmuMgSZLZD7WsbCVJMiMi3yXhEzNrtOQ/QyBpHnwCsbmZTYiP3q4ws+HTWbSpRtJ8wAhgfTP7aHrLMyMTE7N/mtkeDRPP4nRYckXrss+J01uMacKQ0yfb3jtJZhkkDbFJt0/9mnTJSJIZn/OY1GdyRmd54Jji4zUz6z2LKMvb4tbJs1NZbky4c8z2ynKSJLMG6ZKRJDM4sfNAvd0NZijM7Dl8y7BZCjO7j+q7bSRJkiSzOGlhTpIkSZIkSZI6pMKcJEmSJEmSJHVIl4wkSZIkaUNWX7YTg/NjuSSZqUkLc5IkSZIkSZLUIRXmJEmSJEmSJKlDKsxJkiRJkiRJUof0YU6SJEmSNmT0a+/RrXezvw7/zZE/QpIkzZMW5iRJkiRJkiSpQyrMSZIkSZIkSVKHVJiTJEmSJEmSpA6pMCdJkiRJkiRJHWYrhVnSRElDS3/HNJHnh5KekjRK0lWl8D9H2GhJZ0lSlbwbS3o06hotqY+k/Uv1fyFpRByfViX/epIujuOda8kraWwT7ThM0vOSTNKipfBdJA0PGQZL2rwUt6OkZyLfMaXw0yU9HflukrRQhHeS9ICksZLOqaj/LknDos/OlzRnSa79G8lfkuexqHuopGslLd9M3mmNpIUk/eIbrtMkXVE6byfpHUm3tbKcpSX9exrJ1FfSS3E9npC0SSvzNzN2x5TukxGSdplyiactbS2bpP0q76Ua6baO8fHTUth6EXZ0nJ8kads47iepe6kNi1Ypc5q0rVzvFOTtLGl8yDBM0iOSVpuSsqqU3afom4rwvpJ2nxZ1JEky6zC77ZIx3sy6NptY0irA74DNzOwDSYtH+KbAZsA6kfQhYCugX0URlwE/NLNhoSCuZmZPAZdGOWOAHmb2bg0Rfg+cAmBmtwC3NCt7FR4Gbqsi4/3ALWZmktYBrgO6hLz/ALYDXgMel3RLyH8v8DszmyDpT3gf/Rb4DPg/YK34K/NDM/s4Jhb/BvYArgEuCdkurSe8pLWAs4GdzWx0hO0MdAZeaWVfVJbdzswmtDLbQsAvgHOnpu5W8imwlqT2ZjYevzavt6aAaOsbwLRUCHqb2b8lbQ9cQMt9UU8OAZNNMuvQw8zeDWXpHuA/zWaUNKeZTWxFXa1limWbxowAegH/jPM9gWFFpJkdPwVlTnXbprDeMi8Uz21JP8Ofiz8pJ5jCezhJkqRpZisL8xRwEPAPM/sAwMzejnAD5gXmBuYB5gLeqpJ/ceDNyDsxlM2mkNQRWMfMhsX515YmSStKGijpcUknN1OemT1pZmOqhI81M4vTDtE2gA2B583sRTP7Aldud4k895ReToOAZSP8UzN7CFecK+v5OA7b4f1mET4OGCNpwwZN+C3wh0JZjry3mFl/AEkrhRV7iKQBkrpE+AqS7g9r+P2FRTqsSH+T9ADwp8g/KPr0pLLlU1LvCB8u6cQIPg1YKSxfp8s5XdLIsMb1irznhmKP3Bp/SRz/VNIpYUEbLekiufX9Hknt6/TDncD34ngv4OqSnBuGBe7JsiUuxs71km4F7ok6R5biboy+e07Sn0vlbR/j7InIP3+Da9QfWFnS/NHXT5Qtk6W2ngs8ASxXqmvRqOt7NcouWAD4oJTvx/JVh6GSLlDLysXYuI6PAptEfz8rt6xeVLqXFpN0Q1zfxyVtFuF9JF0S6V+UdHgDuVoj23ny1ZxRpfGEpA3iug2LfB0jaulq16cKrwDzSlpCkoAd8fFSlD81ltPKtt0c99ooSQdH2JxRR3EPHFVZr9xqfWJpbHSZUjmqjOtFQq7h8nt5nUhXNbyMpIMk3Vm+9yRtI+mm0vl2km6M47GSTo1rNUjSEq1sR5IkMxmzm8LcXpO6ZPRqkH5VYFVJD8dDcUcAMxsIPIArw28Cd5cVuRJnAM/IFaWfSZq3FbJ2B0bWiDsTOM/MNgD+V46QNLQVdRR5ekp6GrgdOCCClwFeLSV7LcIqOYDSS7lBPXcDbwOf4FbmgsHAFg2yr4krWbW4EPilmXUDjqbF8nsOcLmZrQNcCZxVyrMqsK2Z/Rrv0zOjT98oybw9sAo+gegKdJO0JXAMYfkys97ADyJ+XWBb4HRJS+FKZNG2ZYA14nhzYEAcr4JPzNYEPgR2q9POa4A9YyytAzxainsa2NLM1gOOB/5QitsE+ImZfbtKmV1xy+TaQC9Jy8mX6I+L/lkfv0a/qiMXwPdxK+dnQM/I1wP4ayhwAKvh12M9M3sZIJSN24Hjzez2GmU/IFfyHwy5kLR6yL1ZWCAnAntH+g7ASDPbCHgRX/nYGLfKl5W0M4Ez4rrvBlxciusC7IBf+xMkzTWNZDvWzLrj128rSetImhu4FjjCzIoxND7Sd6Xi+tSQA1pWbzbF75fP66RthsnaFhwQ91p34HBJnULOZcxsLTNbm9qrRu/G2DgPv1cbUUxMX8DH4N9KceVxfSLwZNzrvweKjY9rhQPuFoaP3V1j5abgv8DqkhaL8/1LbeoADIpr1R83riRJMguTLhn1aYcrM1vjVtQBcteARYHVIwzgXklbFtbOAjM7SdKVwPbAj3CL4NZN1r0U8E6NuM1oUaquAP5UqrNrk+WX5bwJuCkUwZPxl3W15XIrn0g6FpiAK6LN1LNDKHpXAt/GXTvAleimLU3xcr4fmA9XlM/HFYTrW/Qy5on/m+DKLHhflS1015eW6jcBdo3jq4C/xPH28fdknM+Pj4lKN5DNgaujvLckPQhsgCvFR0paA3gKWDgU6U2Aw4FOwEtmNjTKGYK7mVTFzIZL6oyPpTsqohcELpO7Ehm+8lFwr5m9X6PY+83sIwBJTwEr4C4nawAPR5/ODQyskf90Scfh4/Wn+Nj5Q4ynr/CJQmGBe9nMBpXyzoVfy0PN7MFa7abFNWAl4H5J/YBtgG64uxBAe3wsgSuoN8TxhsCDRfslXY9PlsDH+hqlcbNAybJ7u5l9Dnwu6e1ow2vTQLYfhlW2HX6fr4FfrzfN7HFoWZGJvNWuT3kyW+Y6XPHugq8+bFojXbNM1jYzG4sryT0jzXL4PfEM8C1JZ+MToHtqlHlj/B9Cy71Zj7JLRi/8nt8x4srjenPiuWhm/5V/U7FgnXCAffBruquZfVmuNNzUrgB+LOlS/J4tfunjC9zFrWjHdpVCxzU+GGDujp2aaGaSJDMys5vC3Fpew60IXwIvSXqGFgV6ULw4kHQnbr3qX1mAmb0AnCfpIuAdSZ3M7L0m6h6Pu33UwurETRFm1l/umrAo3vayJWtZJrW8/gTYCdim5NLRTB2fSboFd+8oFOZ5abGm1WIUsD4wLPqvq/yDnfnxlZIPm5wslGX9tIn0Av5oZhdMEuhKa2W6ySsze13SwvgLvj+wCPBDYKyZfRLKf9kKOBFfCVkOuDXCzjez80tpbsEV+q1xhbvgZOABM+sZ8vUrxdVra2X97aI995rZXnXyFfQ2s69XDCTtBywGdDOzL+W++sVYrpRjAq5w7IBbMZF0KuF2UnlNzewFSW/hSqaAy8zsd1Vk+qw0GarnKz0HsEmFZbFQVKv1S02akU3SirhVdQPz7yL64n0jat/Tk8kRyuoJEXZgSYb/SfoSV+COYOoV5qLcr9smaT58orGJmY2LCcK80Z518Wt5KD7OD6hSXNGehn1ahVuY1HJdHk+1Jvn1Jv8jccv4ssBLVdJdit+Hn+ET7MIV7cvSc69qO8zsQly5p8OSK07z53WSJN8ss5tLRmu5GV9SJpTIVfHl3VfwpdR2sUy7FTCZS4ak75WWolfBH6wfNln3aGDlGnEP4x/0QMsy7xQhaeVCRknr45bE94DHgVXk/tJzR323RLodcZ/incMHuVEd84dVFUntgO/i7gMFqxLuJ/JdMw6rUsyfgWNjqbtgPvjaGveSpD2iDMWLG+ARJu2rh2qIOYgWq/2epfC7gQMU/ruSlpF//PkJ0LGUrj++XD5nLOFuCTwWcQOBIyPNAFxhGkAdzOzVcPfoWqEsg38oeZKZjagIX5CWjwD3q1d+EwwCNpO0MoCk+SSt2iBPWY63Q1nugVtEa2G4UtVFsROLmR1btL0ycfT9isDLuGV6d7V8jLuIpGp1PYbfrwvH+Cu7vNwDfD3eJE1WZ7M0KdsCuJL3kdwV5TuR/WncV3mDSN8xZK2Kmd1UGh+DK6KPB35r0/BDx4q2LQh8EMpyF9xYUDwj5zCzG3AXmPVbUf6Gkpr57ejNgRdqxPUnnoeStsZdPz6uEw6+cvQz4BZJS1cWaP6B7Bu4O0rfphqTJMksyexmYW6vSX187zKzelvL3Q1sH8ugE3FL2nvyLbm+jftrWpRza5X8+wBnSBqHW9L2bvYlZmZPS1pQUkcz+6Qi+gjgKklH0LLsDLgPcw1F43DgN8CSwHBJd5jZgbjysG9YpcYDvcJyMiEU17uBOYFLzGxUFHcO7vJwb+jag8zskKhnDK4UzC1pV9yd4T38hTRPlPVf3I2iYDPczxB8KfnhKv0xItp7eSyZv4dPXAor2964Jf84fJn/GnyHgMOBSyT1xl0Gam1hdyTwL0m/xpeTP4p67wklfWC0dSzw47C4PSz377wz+naTqNOA35hZ4V8+ANjezJ6X9DJuZa6rMNfDzF7DfW8r+TPukvErvI+nGDN7JyzFV8d1A1canm0i+5XArZIGA0OZdHJUra6JkvaMPB+bWbWdRx6QNBG/tseY2Vu468tx+AdfcwBf4pbNlyvKf13SH3B/7zdw15iPIvpw4B+ShuPPw/7AIU20cYpkM7NBkp7EV0xeJMa6mX0hdzc4W/7h2XjcittqzOyRKclXg8naJuku4JDos2fwyRW4682l0V7w3XOaZXlqrzKtFM9t4a4QB9ZI1yfqHw6Mo2UnjVrhAJjZQ/LVqtslTeZagY/nxawVH20nSTLroVaspiffMPKvzD8xs4sbJp5JkbQe8Csz2yfObwN+YL4zxzcpx3y4j7uF8raXmc0w+/0mU4ek+c1sbFhtb8IngDc1ypd8M0g6HbjCzIZPb1kqke+o8qSZ/bNh4hp0WHJF67LPiY0TfsMMOX3fxomSZDZC0hDzj7InY3azMM9snId/8T4rsyi+fAuAme00neToBpwT7ikfUt33Mpl56SP/8Yx5cTeMm6evOEkZ851mZjgkDcFdaH49vWVJkmT6kgrzDIyZfYbv7DDLYmb3Nk7V9pjZAHxLuGQWxMya2b4sSSbBfOu8JEmS/OgvSZIkSZIkSerRlIVZ0pKlD5gahidJkiRJ4qy+bCcGp79wkszUNGthrvVlfH41nCRJkiRJkszSNKswT7bxu6QF8F/xSpIkSZIkSZJZlrouGZJexfeUbS+p8qeAO+E/vZokSZIkSZIksyyNfJh/jFuX78B/hKPAgLfM7Jm2EixJkiRJkiRJZgTqKsxm9iD4T5428xPISZIkSZJMyujX3qNb72Z++fubI3+0JElaR7P7ME+QdDDQFZi/HGFmedclSZIkSZIksyzNKsyXA+sAtwJvtZ04SZIkSZIkSTJj0azCvAOwopl92IayJEmSJEmSJMkMR7Pbyr0CzNOWgiRJkiRJkiTJjEizCvPlwH8k7SXp2+W/thQuSZL6SDpW0ihJwyUNlbRRhPeT1L2UrrOkkaXzzSU9Junp+Du4FNdH0utR3lOS9irF9ZX0UsQNlfRIFZm2lvRRxA+XdJ+kxSNuP0nnlNL2k7RDRf4jJZ0bMo+X9KSk0SHvT+r0xXqSLo7jnSUdUyPd2Pq9CpKulPSMpJGSLpE0V4TvHW0aLukRSeuW8hwR6UdJOrIUvq6kgZJGSLo19rAv17W8pLGSji6F3Sdp4SbknFvS3yW9IOk5Sf+RtGyjtsZ13L1GXDtJ70r6YxP17yppjUbpquQ7RNIUf/9SMX6fkXTolJaVJEnSDM0qzIcBSwB/AP5Z+ru4jeRKkqQBkjYBdgLWN7N1gG2BV5vItyRwFXCImXUBNgd+Jul7pWRnmFlXYBfggkJhDHqbWdf427RGNQMifh3gcaCWQnM1sGdF2J607PH+gpmtZ2arR/hRkvavUdbvgbMBzOwWMzutRrpmuBLoAqwNtAcOjPCXgK2iXScDFwJIWgs4CNgQWBfYSdIqkedi4BgzWxu4CehdUdcZwJ0VYVcAv2hCzj8AHYFVzWwV4GbgRkmT/dhUK9geeAb4YRPl7Aq0SmGW1M7MzjezKdo2osr43Qw4QFLPKSkvSZKkGZpSmM1sxRp/32prAZMkqclSwLtm9jmAmb1rZm80ke9QoK+ZPVHkA34DTGaRNbPngHFAQ2tnNULh6gh8UCPJv3Hlcp5I3xlYGnioiiwvAr8CDq9ST0dgHTMbFudfW7IlrRgW3sclndyM3GZ2hwXAY8CyEf6ImRVtGVSEA6sDg8xsnJlNAB4ECgVuNaB/HN8L7FaSe1fgRWBUhQi3AHtRB0nzAfsDR5nZxJDvUuBz4NsVaSXpnFgxuB1YvE7RewFn4q54G5fKOC3yD5f0F0mbAjsDp8dqwkqSukoaFGluKqzksZLwB0kPAkfIVzGOjriD4toMk3RDtKsetcZv7yhvEut52couqXfUNVzSiaXwH4fFeqikCyTNWeSVdGrINkjSEhG+R6wmDJNUXNskSWZhmrUwI2kuSVtI6hXnHSR1aDvRkiRpwD3AcpKelbswbFURf2UoAEPxHx8qWBMYUpF2cIRPgqT1gefM7O1ScKEgDZV0ZQ3Ztoh6X8Et35dUS2Rm7+EK6Y4RtCdwbSiq1XgCt/xW0h0YWSUcXPk7z8w2AP5XjggZaxKW9X2Au6pE/5QWy/BIYEtJnULh+y6wXClu5zjeowiP5+dvga8Vt4JQyueR1KmOeCsDr5jZxxXh1a5lT1xxXxu3hFddGZDUHtgGuA238u8V4YtEGWuGdf0UM3sEV+yLFYcXcPe930aaEcAJpeIXMrOtzOyvFdXeaGYbmNm6wGi8X+tRa/zWtXRL2h5YBV8F6Ap0k7SlpNWBXsBmsaoyEdg7snXAJ0Lr4pOegyL8eGCHCN+ZKkg6WNJgSYMnjPukQZOSJJnRaUphlrQ28CxwEe6KAbAVNV6CSZK0PWY2FugGHAy8A1wrab9Skr0L1wlcgSsQ/mudkxVZOj5K0jPAo0CfinRll4y9qU7hkrEccCnw5zpNKbtllN0xqlHLRWApvA+qsVmpzCvKEdE39TgX6G9mAyYRQuqBK3a/jXJGA3/CLch3AcOACZH8AOBQSUNwa/sXEX4i7vpSy6f6bdzaXota17Fa+JbA1WY2MVYh/lujzJ2AB+KHqm4Aeoa19WPgM+BiST/AVx0mrVRaEFeKH4ygy6Legmtr1LmWpAGSRuCK6mQTtyba1wzbx9+TtEy8VsEnCN2Ax2MCtQ1QrJ5+gU8ewJX0znH8MNBX0kHAnNUqM7MLzay7mXVvN1/HKRA3SZIZiWYtzOcBx4e/2JcR9iDu+5gkyXQiFKB+ZnYC/q3Bbo3y4Mv/3SvCugFPlc7PMLPVcMvb5ZLmnQoxb2FSxamSm4Ftwprdvlhqr8F6uBWykvFAPRlbrWBJOgFYDHcDKYevg/sl7xIWcq/A7J9mtr6ZbQm8DzwX4U+b2fZm1g1X3F+ILBsBf5Y0BjgS+L2kw0pVzRvtqsXzwArhjlJmfSa9ll+LWKesgr2AbUOmIUAnoEe4mWyIK9G7Ut3i3ohPa4T3BQ4LH+8TqX8dofb4HRzHE4h3W7gEzR3hAv5YmuytbGb/jPDLSuGrmVmfyPNlabVjIrEVq5kdAhyHrxYMbbASkCTJLECzCvOawL/i2ADM7FP8Y5gkSaYDklZTy4dl4MvMLzeR9R/AfpK6RjmdcOvoZFZgM7sRV0Rq7k7RBJvToiRORlhY++ErVjWty+Hf/Bfiw74KRuMuCtV4mBYLdi2LeGVdB+L7z+9lZl+VwpcHbgT2MbNnK/IsXkrzg6ItpfA5cCXrfAAz28LMOptZZ+DvwB/MrPC7FrAkMCbO75e0TLm+eAZfBvyt5HO7LzAfk1uQ+wN7SppT0lJAjyptXgC/VsuX5DoU2EvS/MCCZnYHrtx3jWyf4FZzzOwj4ANJW0TcPrhhpREdgTfD/eXr6yOpp6rv1FFt/J6Kf4QJ3mfd4ngXoPhg9W7848D5I98ycW3uB3YvXadFJK1QT2BJK5nZo2Z2PPAuLe43SZLMojT7wyVjmHQGj6QNcQtHkiTTh/mBsyUthFvVnsfdM+piZm9K+jFwUVgnBfzdzG6tkeUk4CpJF8X56ZKOK8VvaGZfVOQpfJgFfETLLhPgys6upfONceXyRibfMWMlSU/iVsdPgLPjw7bKNj0taUFJHc2s0mH0iJD/CNxC+jWShtZwyzgfn3wMdN2VG83sJNx3tRNwboRPMLPC2nlDKG9fAoeWPg7cSy3bnt2Iu6g0ohvuOzshFO2Vcat1Jb/DJxHPSvoKeBroWcUH/Cb8Q8ARuHtdNUX2B8B/i49Ig//gE6mTgOtjpUHAURF/DT6ODgd2xydW54cf94v4R4mN+D/c9eflkK+wmK+Eu4JMQmn8XhhuIJ2B/UquIBfh26A+hivDn0a+e8JfubimY4Efm9lTMZ7vib7+Ep8o1Jt8nh6TVUUdw5poZ5IkMzGq/W1NKZG0E+67fD7wa3w2fwhwkJnd06YSJkmSNIGko4BPzGym3+5S0pnALWZ2v3zLugPM7FeN8s1KSPoXvgNILd/0It2h+Ptoy9IkZYaiw5IrWpd9Jvu2c7oy5PQp3gY7SWZZJA0pGUEmodlt5W4DvoP78z0IrAD8IJXlJElmIM7Dt1SbFRhpZvcDmNnI2U1ZBjCzHzdSliPdP8xs7RlVWU6SZNagWZcM4kOcZjbST5Ik+cYxs8+o2AVjZsXMLmqcKkmSJPmmaEphltQO/3p6Pdxv8mvMrKHPZJIkSZIkSZLMrDRrYf4XvuH9ncBbbSdOkiRJksxarL5sJwanz3CSzNQ0qzDvCCxX5evzJEmSJEmSJJmlaXYf5qeARdpSkCRJkiRJkiSZEWnWwvxj/CdR76HCJcPMLp/mUiVJkiRJkiTJDEKzCvN+wBbAwkz6U60GpMKcJEmSJDUY/dp7dOs9/V+Vufdykkw5zSrMRwDrmdnothQmSZIkSZIkSWY0mvVhfgt4pS0FSZIkSZIkSZIZkWYtzGcAV0o6DXi7HGFmL05zqZIkSZIkSZJkBqFZhfkf8X/ninAD5px24iRJkiRJkiTJjEVTCrOZNeu6kSRJkiRJkiSzFKkIJ8kMhqSxFef7STonjvtIel3S0NLfQpK2lvSRpCclPS3pLzXyzyHpMkmXyBkjadGIM0lXlPK1k/SOpNtK5bxTUfcakjpLGh/nT0m6XNJcVdo1h6SzJI2UNELS45JWlPRo5H2lovzOVcr4t6RvxfEdkhaqkqaPpKMb9HEnSQ9IGlv0TSmul6ThkkZJ+nMpfAVJ90dcP0nLluL+FO0aKalXKfxKSc9E+CVFv0jqImmgpM/LskqaW1J/SQ2NGZIWjL5+If4ul7Rgo3xtQXkcxfnWpXGzs6Rj4vjrayOpr6TdG5RbHu9PSzpP0jR5b1XKXAofWy19kiSzN009eCQNiId45d+9ki6V9P22FjRJkq85w8y6lv4+jPABZrYesB6wk6TNypkkCTgfmAs40MysotxPgbUktY/z7YDXK9JcW1H3UxH+gpl1BdYGlgV+WEXuXsDSwDpmtjbQE/jQzDaKvMdXlD+mQv41gTmL7ybM7LultreWz4D/AyZRrCV1Ak4HtjGzNYElJG0T0X8BLjezdYCTgD9Gnu8B6wNdgY2A3pIWiDxXAl3wfmkPHBjh7wOHR5lfY2ZfAPfjfdWIfwIvmtlKZrYS8BJwcTON/yYxs1vM7LSpKOKMGB9r4P24VWWCZiYYSZIkU0OzM/V+QGfgQeBf8X8FYDC+g8Ylkn7TBvIlSdJKzGw8MBRYpiLqTKATsK+ZfVUj+53A9+J4L+DqVtY9EXisSt0ASwFvFnWb2Wtm9kErit8b+E9xUmEdPzYsufcBqzUh56dm9hCuOJf5FvCsmb0T5/cBu8XxGrgyC/AAsEsp/EEzm2BmnwLDgB2jnjsswPtl2Qh/28weB76sIt7N0daaSFoZ6AacXAo+CeguaaVI85uw5A+Tf7CNpJUk3SVpSBhCukT498PS/6Sk+yQtEeF9wjLeT9KLkg6vJ1cNWb9e4ZhK5gbmBT6IcvtJ+oOkB4EjJG0T8o8ImeeJdFXDS/K1jz45qCL8Ckm7lM6vDGv5fpJujDzPlVchkiSZdWlWYd4e2MHM/s/MLjSz/wN2AL5tZsfgL9hD2krIJJnNaK+S2wOuCJU5qhT/QGVmSQsDqwD9S8E/whWsPc1sQp26rwH2lDQvsA7waEV8L03qktG+HBn5NgLuqlL2dcD3I99fJa1XR45qbAYMqQyU1A3YE7es/wDYoBR3iKTWPJueB7rI3UzaAbsCy0XcMFqU555Ax7BIDwO+I2m+UOB7lPIUcswF7EP1fqlkZLkNNVgDGBoTFODrycpQYE1J3wnZNzKzdYFCqbsQ+KWZdcOt6+dG+EPAxrFCcQ1QNoB0wZ/3GwInqIq7TfBAacxOS0v3UVHmm/hkZmgpbiEz2wr/ML0v0CtWL9oBP4/xOFl4Kf/8wK3AVWZ2UUW9FwP7g7u/AJsCd0RcV3wVYG38nliuIi+SDpY0WNLgCeM+mbKWJ0kyw9CswtwFqNw+7mXCkmNmjwGLT0O5kmR2ZnzZ7QF3VShTdsnoUQrfQtJw4H/AbWb2v1LcE/iq0Ib1Kjaz4fhq0l60KAdlKl0yil/+XCmUmveAV6KcyrJfw58ZvwO+Au4vuTs0w1LAO1XCtwBuMrNxZvYxcEupzvPN7PxmKwiL98+Ba4EBwBigmGAcDWwl6UncLeB1YIKZ3YP31SO4RX5gKU/BuUB/MxvQhAwTgS8kdayTTPguRbXCtwUuNbNxUeb7kubHlb7r41pdgPcpuOX7bkkjgN7AmqUybzezz83sXXxb0SVqyNSjNGYPrJFmSihcMhYHOkjasxR3bfxfDXjJzJ6N88uALeuEF/wH76fJfobPzB4EVpa0OH4/3FCabN5vZh+Z2WfAU/i9VZn/QjPrbmbd281X71ImSTIz0KzC3B+4VNLKkuaN5cCLcKsEktbGZ/9Jkkw/BoR/7dq4da1rKe5p3K/42vAFrsctuG9ta9wxCh/mlYGNJVVuQQlAKF53mllv4A+4FbRZxuNL8lWLbkU5dTGzW8OvehPgGeC5CH/DzH4QVthjI+yj+H9qKIvb4Urrc0V5kk4AFgN+1Qox5mFyd5Eyo4D1VPoALo7XBUZTXaGeA/cZL094Vo+4s4Fzwgr7Mybt589LxxNpfjvSaYqZfYlb6MsK76fxXzWy1QoveBhfHaiV7grcPWZ/4NJS+AzRJ0mSfHM0qzD/JNI+BYzDH9ZzAvtF/Bf4DDxJkulMWNP+CPy2IvwR3HXqdknL1yniEuAkMxsxBXW/CRyDW5EnQdL6kpaO4zlwl4+XW1H8aFwhr6Q/0DN8UTsCU/URclgUC9eWXxDuBZIWLSmov8P7CUlzhmsGktbB23VPnB+IuzPsVcdvvLL+TsA7oSAi6enKNGb2PPAkcFwp+DjgiYi7BzhA0nxRxiJhfX9J0h4RJknrRt4FafnA8yfNyDktkfRHST0bpBFuIX+hSvTTQOcw5oC7vzxYJ7zgeHxV5Fyq0xc4EsDMRjVsSJIksyxNKcxm9r6Z7YlbHZYC2pvZXrFEh5k9Y2aD21DOJElaKPswV91+Dd8NY0tJK5YDzew24ETgrkLJqyQ+xjuzRt2VPsybVklzMzCfpC0qwhcHbpU0EhiOuy205mOw24Gtq8j7BL40PxS4AXelAOr7MEsaA/wN2E/Sa5LWiKgzJT2FWx9PKy3nbw08I+lZ3C3h1AifCxgQeS4Eflxauj8/0g6M/jo+6l5S0mu41fm4qL/YWaMH4Q4TPtG1rJ8/BVaV9LykF4BVIwwzuwtfKRgc7hfFbiB7Az+VNAw3fBQftfXBXTUGAO/WqK8tWRt3JapG4cM8ErfkTqbchmvE/ngbRuAuP+fXCq/IfiQwr6p8vGdmb+ETtUsr45Ikmb2QTbazVI2E0urA7sASZnaYpNWAear5KiZJkkxr4gPDB4DNyh+7zWpIuhH4nZk9I2kn4Ftmdtb0lqstkXS3me0wveWoJCz0I4D1C/ebKaHDkital31OnHaCTSFDTt93eouQJDM0koaYWfdqcc3uw7wHvuy5DFDccR1x60ySJEmbEx8YnkD1LetmCSTNDdxsZs+ArwjM6soywAyqLG+Lu3ScPTXKcpIkswbNfqhwErCdmQ1Vy69YDcM/MEmSJPlGMLO7p7cMbYn5D5dMtmND8s1jZvcB9Xz9kySZjWj2o7/FcQUZWr68Nqbhl+lJkiRJkiRJMiPSrIV5CP51cdnysSf+y1VJkiRJktRg9WU7MTj9h5NkpqZZhflw4B5JP8U3jr8b/yJ7+zaTLEmSJEmSJElmAJpSmM3saUldgJ2A24BX8V8SG9uWwiVJkiRJkiTJ9KbpXyeKn1i9TtJCwIr4fpZJkiRJkiRJMktTV2GW1Bv/ydsb43xH4DpgfuADSd81s0fbXswkSZIkmTkZ/dp7dOs9/TY/yf2Xk2TqabRLxk/xX1cqOAs4m5Y9mP/YRnIlSZIkSZIkyQxBI4V5qeJnYSWtDKwA/NHMPgX+AqzTxvIlSZIkSZIkyXSlkcI8TtICcbw5MLz0od9XtMIHOkmSJEmSJElmRhopzHcAF0raGTgauKEUty6+W0aSJEmSJEmSzLI0Uph/BYwDTgUGAmeU4nYErmkjuZJZAEk9JVlsSViEdZY0skravpLGSepYCjsz8i8a5xMlDS39HRPh/SQ9I2m4pKclnRO7uZTLP0rSZ5IWbCDzJOlCrp9VpNlV0h31ZKpS7t8lbRnHF0tao0qa/SSdU0++SHeXpA8l3VYj/mxJY0vnknSWpOejj9YvxR0haaSkUZKOLIWvK2mgpBGSbi1WmiStLalvEzJOdp0l9ZF0dKO8bU2tMdggTztJ70qaob/biD5+vWJMLlQlXT9J3aeDiNOEuAeL+32kpN2nt0xJksza1FWYzewjMzvAzNY2s4PM7PNS3Clmdmrbi5jMxOwFPIT/KmQzPA/sAiBpDqAH8HopfryZdS39nVaK29vM1sH96j8H/lNFlseBnk3IXE53dRX594zwRjIRbVkE2NjM+gOY2YFm9lQDOepxOv7Lm5MRStBCFcHfAVaJv4OB8yLtWsBBwIb4itFOklaJPBcDx5jZ2sBNQO+QfQSwrKTlp0L+mZHtgWeAH0pStQSS5pyaCiRNKxe3MyrG5IfTqNxpzpS0WdK6+Dc0u5hZF+D7wJ8kdZvW8iVJkhQ0sjAnyRQhaX5gM3ynlWYV5quBXnG8NfAwMKE19ZrZF8BvgOXjxYqklfCtEI/DFeJaMldLdx/QRdJSkWY+YFvg5laItTtwV6mer617kvaX9KykB/H+aqaN9wOfVJF/TlyZ/k1F1C7A5eYMAhaK9qwODDKzcWY2AXiQlonCakD/OL4X2K1U3q00f02rIukgSY9LGibphujXwqJ/nqQHJL0oaStJl0gaXbZsSxor6U+Shki6T9KG0a8vyl3IkDSnpNOjnuGVKwWRZk1Jj4UldnhpwlDJXsCZwCvAxqX8YyQdL+kh4DeSHivFdZY0PI67SXow5L27NJ76SfpDXP8j4vxPIdOzkrZoti0N+ru9pGsi77VA+1LcT6OufpIuUqxySFosrs3j8bdZhPeRdJmke6L9P5D0Z/lqxF2S5mplm6umq8PRwB/M7CWA+P8H4Nel8ov7a1FJYxr1oaTepfATS9dvdPTJqGhv+4g7XNJTkT5XWpNkNiAV5qSt2BW4K3ZZeV8lN4A6PAcsJmlhXEGpfBG116RLzb0mLwLMbCIwDChcQfbClfEBwGqSFq9R/2TpoqwbgR9Gmp2BB8ysUFibkWkzYEhlYCgGJ0b8dsAapbidJZ1UQ85aHAbcYmZvVoQvw6TfG7wWYSOBLSV1kius3wWWizQjo60Ae5TCAQYDWzQhz0rlvgEOKcXdaGYbmNm6wGh8YlWwMPBt4ChcOT8DWBNYW1LXSNMB6Gdm3fDJwyl4H/YEin77KfCRmW0AbAAcJGnFChkPAc40s65A9+ibSQglaRv8V06vZvJJ12dmtrmZ/RGYW9K3IrwX/mNPc+Hbce4e8l6Cu7kVLGRmW5nZX+O8nZltCBwJnNCKthQcVer3ByLs58C4WIU5FegWbVsa+D98ErAdLfcM+AThjKhzN3zVoWAl4Hv4ZOxf+D2xNjAe+F6zbaZlq9Ja6aqxJpPfT4Mp3T81qNqHkrbHV182BLoC3RTuUxH+DzNbE/iQlonjMcB60Z/lcZ0kySxK7nKRtBV7AX+P42vi/Ikm8t2IWy83AiqtaONDsWmG8rL5nkBPM/tK0o24AviPKnlqpbsat9yeGWnKv0DQjExLAe9UCd8IV/reAQjL36oAZnYLcEuDcr8mFJ89cMv8ZNFVwszMRkv6E25BHotPMgqL/gHAWZKODzm+KOV9G1i6CbFeKPeNpD6luLUknYK7j8wP3F2Ku9XMTNII4K1wA0HSKKAzMDTkKaz2I4DPzezLyNM5wrcH1lGLf+uCuAL0bKmugcCxkpbFlfjnqrRjJ1whHCfpBuD/JB0VkymAa0tpr8MnV6fhCnMv3Fq/FnCv3JtjTqA8qSnnB78HwJXCRm15qYq8Z5jZXyrCtsSVU8xsuMLyjSuJD5rZ+wCSrifGIL6SsoZaPFAWUMs3BneW+ntOJr0WnVvR5kbpqiHAqoQ1olYfbh9/T0b4/BH+CvCSmQ2N8PL1GA5cKelmaqw2SToYd4Fi7o6dmhAvSZIZmaYUZkkbVftFP0kbmtlj1fIksy+SOuEWwrUkGf4SNEmVrgLVuAZXrC8LxXVK6p8TWBsYLWkd/OVXvJDnBl6kQmFukO5hYCm5i8emtN4dYTwwb424yhf/lLIesDLwfMg/n6TnzWxl3GpathAvC7wBYGb/BP4JIOkPkRYzexpXIpC0Km5NLJgXb9PU0BfY1cyGSdqPSRX94luJr0rHxXnxzPrSzKwyXYyZIo2AX5pZWRlHUufi2MyukvQo3r67JR2Iu6ocFEm+i0/2NiuW9oFOuH/9fXH+aan4a4HrY8JlZvacpLWBUWa2SY2++LTivGjzxFJ7a7Xl1JCdJiZu1cZavRtsDmATM5vkWsf4Kvd35bVoF+U20+ZG6aoxCl8NGF4KWx+3MoNP+orV0/J9V6sPd8B/X+CCivDOTDr+JtLiyvI9fBKyMz6BWjPcmr7GzC4ELgTosOSK0+o+T5JkOtGsS8a9NcLvqhGezN7sjvvMrmBmnc1sOdwStnmjjGb2CnAscO6UVBxLwX8EXjWz4biy0yfk6GxmSwPLSFqhImvNdKEMXAdcBtxhZp+1UqzRuDJbyaPA1uESMRduIZ4izOx2M1uykB9ffi/qvAXYV87G+LL0mwCFe4r8I74fEB8zlsLnwH26zy9VtyrxC6By3+Ep+c3fjsCb0e69pyB/M9wN/FwtPrWrSupQThDuEy+a2Vl4P61jZv8oPpjDLe+bA8uX+vZQavjCm9kLuGL1f7RYUZ/BXY02iTrnkrTmtGiLmR1bkrUe/Yl+ln/sWfzo1GPAVpIWjolG2Vf9HtzNh8jXqI4yzba5ZjpJh0k6rEqevwC/KyY+8f9IfBUIYAzhcoI/iwpqjYe7gQPk310gaRnVdtsq7onlzOwB/HuBhXCrdJIkszB1FWZJc4S1Lt61mqP0twqt/CArmW3YC99ZocwNwI/ieDVJr5X+JlEUzeyCUDwqqfQXLu9IcWUsM4/E/Vt3ifA9q8hyE9V3vqiX7mp8J4lGftWT7ZIB3E4VV4lQWvvgbgH3UXJZUR0fZkkDgOuBbaL/dqiWrsQduLX8eeAi4BeluBskPYX7Ch9qZh9E+F6SngWexq3Rl5by9Ig2ASzPlFmb/w+fMNwbdbQFFwNPAU/It5G7gMlX1XoBI+U+1l2Y1N0GfBLxXyvtEITvwLKzpHlq1Hst8GN8klV8iLo7vpPDMNylZNM2aEvBURVjsjO+M8r8cY/8BleUMbPX8Q/mHsXH4FPAR1HO4UB3+YdtT9EKX91m29wgXRfgvSp5hgK/BW6NMfos8HMzeyaS/AVXjB8BFi1lrdqHZnYPcBUwUO5i8m98QleLOYF/RdoncReYD+v1R5IkMz9qWUmrEil9Re0l46+AU82sTxvIlSSzFPJdFHaa2V+soSQ+CGxuZhMknQ5cEdb8ZCZE0vxmNjYszDcBl5hZ5eRxesh1G/CDUKrrpTsN/x5gh0ZppxcdllzRuuxz4nSrf8jp+063upNkZkLSEDOrukd9Ix/mFXG/rwdxf63iYwsD3qn0bUuSpCa/xq2xH05nOaaW5fH9mScAmFnv6SxPMvX0kbQt7u97D63bMrHNMLOdmkxX9ceCkiRJpiV1FWYzezkOV4CvfbeWsMm3rUqSpA7VPpqdGYldJKrtJJHMpJjZdP/1xSRJkhmdpj76k7SQpKuAz3A/yMLH8pS2FC5JkiRJkiRJpjfN7pJxPv4hyAq07Mc6kJZfZUuSJEmSJEmSWZJmf7hkG2Dp2KjeAMzsnXpb7yRJkiRJAqsv24nB+eFdkszUNGth/ohJt+cp9m1NX+YkSZIkSZJklqZZhflifL/WHsAcscn8ZUz6YwZJkiRJkiRJMsvRrEvGn/AP/v4BzAVcgm/6fmYbyZUkSZIkSZIkMwR1f7gkSZIkSZKpY3r8cEn+WEmStJ56P1zSrEsGkraT9E9Jt8Z5d0nfnlZCJkmSJEmSJMmMSLP7MP8SOA//wYItI3g8kPswJ0mSJEmSJLM0zVqYjwS2NbPTgK8i7GlgtbYQKkmSJEmSJElmFJpVmDsCr8Zx4fQ8Fy0/YpIkSZIkSZIksyTNKsz9gWMqwg4HHpi24iQzI5KWkHSVpBclDZE0UFLPiNta0keSnpT0tKS/lPLtJ+mcOO4jySStXIo/KsK6x/kBkkZIGi5ppKRdIryvpJckDY06TpC0eIQtWSrvXEmTjGNJc0g6K8obIelxSStKejTKe0XSO3E8VFLnKu3/t6RvxfEdkhaqkqaPpKMb9OPepXqGSvpKUteIm1vShZKejTbuFuErSLo/+qSfpGUrylxA0utFP0fYlZKeiTZfImmuCN9JUsMvk+KamqTvl8Juk7R1o7zNEmPjnRg3z0m6W9Km06r8KvX1lTROUsdS2JnRzkXj/JE6eXeP437FeJ0GMo0p6q4SPiLGyIjiPphWlO/LVuTZuHTPjJbUJ8K3bua6NZuuFfJU7btSfJtfpyRJZi2aVZh/CfSUNAboKOkZYA/gV20lWDJzIEnAzUB/M/uWmXUD9gTKitsAM1sPWA/YSdJmNYobEXkLdgeeinqWBY4FNjezdYCNgeGltL3NrCvQFfgJ0AHfDvEvkX99YHPgrxV19gKWBtYxs7WBnsCHZrZRlHc8cK2ZdY2/MRXtXxOY08xeBDCz75rZhzXaVxczu7KoB9gHGGNmQyP6WOBtM1sVWAN4MML/AlwefXIS8MeKYk8upS24EugCrA20Bw6M8NuBnSXN14S4r4VMbcm1Zraema0CnAbcKGn1ZjNLanbbzILngWISNgfQA3i9iDSzNlPYp4AeMU52B86azrKA78t/cMi0FnBdhG8NNNNvzaZLkiSZLjRUmOPFsTqwBfBD4Ee4QrKRmf2vbcVLZgK+DXxhZl//iI2ZvWxmZ1cmNLPxwFBgmRpl3UyLwvIt/Bcm34m4xYFPgLFR1lgze6lKGfPG/0+BC4GV5D+4cw5wmJl9WZF+KeBNM/sqyn3NzD6o1+AK9gb+U5yUrU2Sjg1L7n203t9/L+Dq0vkBhDJsZl+Z2bsRvgZwfxw/QPRf1N8NWAK4p1ywmd1hAfAYMbmJ837ATk3INwz4SNJ2lRGSukl6UL7acLekpcLiPyTi1w3L7fJx/kIjJd3MHsCv58GRp6ukQWFZv0nSwhHeT9IfJD0IHBHW3/MlDQjrfL22XY1PoMAVuIeBCaV2jY3/knSOpKck3Y6PzcmQdJ6kwZJGlS33MUZOlPREWIi7RHgnSfeEVf0CQPX6JFgA+Hq8SvqxpMfC0nuBpDkbyLKBpEckDYt8hYV9aUl3hXX/z03IsTjxy69mNtHMnpKvxhwCHBXybCHp+2GJflLSffLVqWrpFpN0g3zF5/Fiki1fqbkkrvOLkg6vJ5SkDpJuj/aNlNSrSppv4jolSTKT01BhDkXiP2Y23sweM7PrzWxQoWAksz1rAk80kzCUmlVwF59qfAy8KmktXGG8thQ3DHgLeEnSpSq5AwSnSxqKWz6vMbO3Y4z+HLgBeNbMqtV7HfD9eFH/VdJ6zbSlxGbAkMrAUFb3xK3qPwA2KMUdIumQBuX2IhRmtbh4nBwv7+slLRFhw4Dd4rgnvgLUST7R/SvQu1YFcleMfYC7SsGD8clxM5wCHFelzLOB3WO14RLgVDN7G5hX0gJR/mBgC0kr4JbzcU3U9wRuGQe4HPhtWNZHACeU0i1kZluZWbGa0BnYCvgecL6keanOc8BiMU73Aq6pka4nPgFaGziI2pbRY2M/z3WArSStU4p718zWx3cfKlx1TgAeitWYW4Dla5QL8ICkkfjqwXEAcut7L2CzsPROxCd0VWWRNDd+jx1hZusC2+K7H4Gv1PSKNvaStFwdWQDOAJ6JycvPJM0bqzHnA2fEyskA4CFg42jjNcBvaqQ7M843wMf3xaW6ugA7ABsCJ8SYq8WOwBtmtq6ZrcWkY72gLa9TkiSzCE37MEvauE0lSWYJJP0jrDmPl4K3kDQc+B9wW4OViWtwRXNX4KYi0Mwm4i+/3YFngTMUfpJB4ZKxJLCNwh8yXBpGAudWq8zMXsOVn9/hO8DcL2mbZtuLW6jfqRK+BXCTmY0zs4/xF2tR5/lli3wlkjYCxpnZyAhqh1uBH46X90DC1QR/iW8l6UlcKXwdt4r+ArjDzF6lNufirjQDSmFv4y4qDSnySSor2KvhS/L3xgTmOFrccx7BJxhbAn+I/1sA5frroahvQVwpLlxNLqNlu0uYdKIFcF1Y5Z8DXqRF6a7Gjfj426iOXFsCV4cl9Q3gvzXS/VDSE8CT+MRyjYp6wCdbnUvl/gvAzG6nZDmuQo9QANcGzpE0P7AN0A14PPp+G+BbdWRZDV9deTzq/NjMCov6/Wb2kZl9hrtFrVBHFszsJKA7vprxI6orpuBj4W5JI/DJ3Jo10m0b7RqK3zsLlKzft5vZ57HK8ja+ilKLEcC2kv4kaQsz+6hKmja5TpIODsv14AnjPqkjYpIkMwPN+vi9DNwp6T/4bhlf/zygmR3fFoIlMw2jaLFwYmaHyl0SBpfSDDCznSStCjwk6aaSb24ltwKnA4PN7GOpZbWz5ELwmKR7gUuBPuXMZjZWUj/cX7n4SOsrWrZDnAwz+xy4Ex/jb+HK+v210lcwnhY3kMmKbrKMSvZkUneM94BxtEwgrgd+ChAK2w8AQmnazcw+krQJPlH5BTA/MLeksWZ2TKQ9AVgM+FlF3fPSYmVshlNxX+ZC0RIwysw2qZJ2AK4gr4C7sfwW76PbmqxrPWB0E+k+rTivvA4m6dIo7w0z+24p7hrckn2ZmX1VHn8NypwESSvik5kNzOwDSX2ZdJx8Hv8nMulzuFVjxsxeiDG7Bt73l5nZ75qURXXq+7x0XCljTVmA8yRdBLwjqVOVZGcDfzOzW+QfifapUdwcwCbhxlVuS6tkM7NnY7Xnu8AfJd0Tyn1RXptdJzO7EHcjosOSK+ZP6ibJTE6zFub2uH+p4RaC5Up/yezNf/Gl9p+Xwqr6o5rZs7gf7m9rFRYvyN/iitjXSFpa/uFeQVd8IkdFuna4dfCFZoSXtL6kpeN4DnxZdrJy6zAaWLlKeH/8Q9n2YRmrdCGpJc8c+Ae1X7sDxEThVtyvFtxyWHwMuWjkAbeSXxJ59jaz5c2sM64QXF5Slg/El7T3quJatSpukUdST0mVHxFOgpndAywMrBtBz+BuDZtEGXPJP4ws+uTHwHNR7/u4IvNwE/2yFe6/fFFYCT8oWbb3YfIPG8vsId8NZSXc4vqMme0fy/9lZRkzewWfAFRdkSi1Y09Jc0paCv84sJIFcMX9o3Cf+U6jNka5ewNI+g7er3WRtDiwIj5m7wd2jzAkLRIuL7VkeRr3Vd4g0ndUgw8lJV0uacMq4d9Ty+xiFVzB/BD/7qBjKemCtHxI+ZNSeGW6e4DDSuV3rSdXHXmXxldr/oWvyqxfkeQbuU5Jksz8NGVhNrP921qQZObEzEzSrriLxG9w94RPqa0Unw8cHZadWmVW8x2dC/hLvAA/i3rKfsCnSzoOmBtXHG6cvIiqLA5cJGmeOH8M/0CwWW7HFdn7yoFm9oSka/GPHF+mtLyv8F+u4ZaxJfCaxa4bJX4LXCHp73jbi3tya9xyZviL/NAmZD4/ZBoYOs6NJatbD1zxBlgJ9ytvxKnEh49m9oV8i7WzwnWiHfB33Oo8JuorfMkfApa12h9Z9pK0OT4Bewm3nhcW5p/g/sjz4W4W9Z5Rz+AK9RLAIeFmUBMzu6BePG7p/za+3P8sVZR1MxsWbjKjQr6GkwLgRODqcA94EHilTtoHJE3E74tjzOwt4K24B+6JSdSXwKFmNqiaLHGtegFnS2qPryxs20DGdYiP+yrYB38GjMNXG/Y2s4mSbgX+Ld/67pe4Rfl6Sa8Dg3BlH3xCWE53OPAPuStXO3zMNPL7r8ba+LPhK7w/yhP7b+I6JUkyiyA3XjVIJL1vZotUCX/bzKp+IZ4kswOhaDyAf2g1cXrLMzWEhe0qM9smzv8FHGVm1Xy0Zwpiif02M/v39JZlZkf+weY/zWyP6S3LzEaHJVe0Lvs03OJ8mjLk9H2/0fqSZFZA0pD4CHgymnXJmOwrZPmXyXNOjWBJMrMTLiQnUHurvJmJ5YFfFydm9uOZWVlOpi3xUWAqy0mSzJY08lcbgPstzyupckuuZWn5qCpJZlvM7O7pLcO0oNgtYVbCzPab3jIkSZIkMz+NfJgvxr+k3gD4Zync8D1xa22nlCRJkiRJkiSzBM36MHcxs6e/AXmSJEmSZJaie/fuNnjw4MYJkySZrkyxD7P8J27XKpRl+c+VXin/YYrzY9/XJEmSJEmSJJllafTR39/xX04ruBjfp/VC/Ne8/tw2YiVJkiRJkiTJjEEjH+bVif1jJS2Eb+q+Vvx60i34R3+/aFMJkyRJkiRJkmQ60sjC3A74Io43Bv4Xv9aGmb0KLNR2oiVJkiRJkiTJ9KeRhXkU/jO91wF7Uvo1M0nLAB+1nWhJkiRJMvMz+rX36Nb78m+0zvzhkiSZtjRSmH8L3CrpfGAisHkprhfN/YxokiRJkiRJksy01FWYzewhScvjH/o9a2aflKJvB65pS+GSJEmSJEmSZHrTyMJMKMlDqoQ/0yYSJUmSJEmSJMkMRKOP/pIkSZIkSZJktma6KcySzpB0ZOn8bkkXl87/KulXDco4VdKrksbWiN9dkkmq+qstkiZKGipppKRbY+s8JHWWNF7Sk5JGS3pM0k/qyLFeIbuknSUdUyNdVTkr0nxb0hMh02WS2pXitg55R0l6MMLmDfmGRfiJpfQnSxoeee6RtHQp7neSnpf0jKQdSuH3SVq4CTn7Rd6h0UcHN8rT1kjqK+mlkOkJSZs0SP9IE2UeKWm+Jup7WtIJTcq4exz3qzU2G+UthTUcU1XKaXWeOmX1kfR69MFTkvaawnJa1RdtSWvHUZX8zdznYySNiDpGSNplyiWuW08fSUfXiNs3njOj4todHeHT7VrEM+62JtKtKem/kp6V9IKkEyWlAShJkjZjej5gHgE2BYgH3aLAmqX4TWn8UeGtwIbVIiR1BA4HHq2Tf7yZdTWztYD3gUNLcS+Y2Xpmtjq+Q8hRkvavUc7vgbMBzOwWMzutgdxViX64DNgzZHoZ+EnELQScC+xsZmviu5cAfA5828zWBboCO0raOOJON7N1zKwrcBtwfJS1RrRpTWBH4FxJc0aeK2h+b+29o+zNgD9JmrtKm+acLFfb0jtkOga4oF5CM9u0ifKOBKoqzBX1dQV+ImnFpqScDsiZqnu+PIErcUb0wS7ABZLmmpo6ZhCaHkcFU9C/PaKO3YGzpkF5TSPpO/jY3j6eJ+szk+x6JKk9cAtwmpmtCqyNvweOmK6CJUkySzM9FeaHCYUZV9xGAp9IWljSPPiPpjxZrwAzG2Rmb9aIPhn/JcLPmpRnILBMjXpeBH6FK+CTEIr5OmY2LM73k3ROHK8oaaCkxyWd3IQMnYDPi72ugXuB3eL4R8CNZvZKyPR2/DczKyxac8WfRdzHpbI7FOG4YnONmX1uZi8Bz9My8bgFaK2VcH7gU3wnFSSNlXSSpEeBTST9OKzgQyVdUCjRkraP/nlC0vWS5pfUPdIVljeTtJKkJ4rKJK0iaTK/+gr6AytH+l+FJW2kJl3VGBv/tw6r2r/DUnxlKCuHA0sDD0h6oEF988b/T6PMbpIelDREvnqyVL3M1fqiQX2V+eeXdH/k/9piKV8tGS3pXOAJYLkI/2ukvV/SYhHWVdIg+arETYqVhuibP8hXNWoqJWb2HDAOWDj67/To8xGSepVk/U2EDZM0yeRS0hzylZVT4vzm6MNRilUMST+U9Lc4PkLSi3G8kqSH4vj4uO9GSrow5JnicdTa/o24ReOafq9BHQsAH9Qqr1o/1pIn4o6Vr/7cB6xWo87fAUeb2RsAZvaZmV1Uit9Dfs8+K2mLkmwDos4nJBUGj6r3T8SNkVt/Czm7RHgHSZfENXpSrbOw/wh42MzuCdnHAYcBvaPsSazq0Xed47jpZ1ED+bdSy3PqSfl7IEmSWZjppjDHg3qCfBeOTXGF9VFgE6A7MNzMvqhTRE0krQcsZ2YNl/Yi/ZzANriyWIsngC5Vwrvjyn41zgTOM7MNgP9V1Dm0Svp3gbnUshy6Oy0v4FVxRaRfKBBfb7Ipac4o723gXjN7tBR3qqRXgb0JCzM+MXi1VO9rEYaZfQDMI6lTjTaVuVLScOAZ4GQzmxjhHYCRZrYR8B6+BeFmYU2bCOwtaVHgOGBbM1sfGAz8yswGh9W/K3AX8BczewH4SFLXKH9/oG8D2b4PjJDULdJvhP/4zkExPipZD7e4rQF8K+Q9C3gDtwT2qFHP6dH3r+GTkLflFtazgd3NrBtwCXBqLUFr9UW9+oq/UvhnQM/I3wP4a6G04ErT5bFi8jJ+fZ6ItA8ChSvJ5cBvzWwdYEQpHGAhM9vKzP5apx3rA8/FZO4HuNV9XWDbkHspuWVzV2CjWBX5c6mIdsCV+I48x0XYAdGH3YHDY1z2B7aI+C2A9+T7wm9O/DIpcI6ZbRArNe2BnaZmHNG6/kXSEvhOQseb2e01yn5A0kj8GhxXCv+6vGh3Vyr6sZY8Md73xMfzD4ANatS9FlU+5i7Rzsw2xO+JYhy8DWwXdfZiUqv4ZPdPKe7dyHMeUCiyxwL/jWdjj2hXhzrylFmzUva4tu0VbnXVkLQ6rXgWNZD/aODQKGcLYHyV+g6WNFjS4AnjPqmMTpJkJqPhLhltTGFl3hT4G660bYovDTb0L62GfAnzDGC/JpK3D6WjM/4Avrde0TXClwLeqRG3GS0W4iuAPxUR8aCdBDMzSXsCZ8it7PcAEyK6HdANV+zbAwMlDTKzZ0NR7Rovi5skrWVmI6PMY4FjJf0Ot8KcUKMtVjp+G7esvlejXQV7m9lguYXyEUl3hcIwEbgh0mwTcj8e+kX7KH9j/OX6cITPjU+aALci4svE20fQxcD+cr/2XtRwxcFfvMfh1+SnUf9NZlZYfm/EX3CVqxePmdlrkWYoPiYeatB+8KX7f4dF6v6wun2MKyT3RtvmBGqthECDvqhWX3GiFn9ZAX+QtCXwFX4vLRFxL5vZoFIZXwHXxvG/gBslLYgrxQ9G+GXA9aU811KboyQdhCtKO0bY5sDVMTbfklunNwC2Ai4NqyBm9n6pnAuA68ysPLk4XFLPOF4OWMXMBsktrB0j7CpgS/y63hhpe0j6De5Oswj+I0y3MuXjqDX9OxdwP65QPUhtepjZu5JWwsdOvyrl1erHO2vIswU+3scBSKpnBKhH0Y9D8HuhaNc5MeGYiE/iC+rdP+WyfhDH2wM7lyzB8wLLNymbmPR5VQ6vxxQ9i2rI/zDwN0lX4it/r1VWZmYXAhcCdFhyxWryJkkyEzG9P5Io/JjXxq20g3ALczP+y7XoiCsr/SSNwR+Gt6j6RyzjQ3FdAX9IHlolTcF6wOhqZdCyHF+NVj0ozWygmW0R1p3+wHMR9Rpwl5l9ambvRty6FXk/BPrRorSUuYoW5f01SkvHwLK4JbVgXqpYTOrI/A5ugd8ogj4rWZsFXFZYjc1sNTPrE+H3lsLXMLOfgn/QA5yI+3IX5dwAfAfYCRhiZrWU+d5R3nYxaWj0Ei34vHQ8kSqTSUk9S9bdScZTuMX0wxUcAaNKbVvbzLavLK9cNDX6ohXsDSwGdIsx/RYVbiJ1aGaMFhOOU6tYt88ws9VwBfRySfNSu99rKTvgz4MekR9JW+NW1U3CGv0kLW0aiFuIn8Gtylvgz46HI/+5uIV/beCiUr4pHUet6d8JuHJV/pi2Wr8BX1tH38KVtsryavVjPXmauZ6jcOWxFsX9UL4Xjop61sUt33NXSV+Zp1ZZAnYrjfnlzaza87WW7JPcf5K+hVuCP8T7v/xuK/ql1c+iWvKbf6dyIK50DypcNZIkmXWZ3grzw/iL630zmxjWpoXwF18tC1tdzOwjM1vUzDqbWWdcCd/ZzAbXy4P7Jx+tKh8syf3f/kJ82FfBaMJXtgoP48uj4C+4hkhaPP7Pg//S4vkR9R9gC0nt5Ls2bASMlrSYWnb3aI8rGE/H+SqloncuwnHXkz0lzSP/SG0V4LHII2BJYEyc3x/L3fVkng+fULxQJfp+YPdSuxaRtAJ+XTaTVPgZzydp1bB0XgPsG4o44D6WwN34suil9eSpoD+wa5TfAehJy7J9M3yCT8Iws5tKL9VJxpP8Y7iN8D54BlhMsbuCpLliElCLqn3RChkBFgTeNrMvJfXAJ4G1mAN39wH3B30o7oEPFP6qwD64q8AkmNmx1uIyUxl3I76c/RO833vJ3YUWwy3Aj+GrJgfEmEHSIqUi/gncAVwf/bkg8IGZjQuFZONS2v74snh/XJHugfv/f0SLgvRuWP6/3llkKsZRa/rXgAOALoodc+r1W9wbK+If+VZSqx9rydMf6CmpfVjgv19Dxj8Cf5a0ZMgwj9xnvx4LAm+a2Vf4+JiaD3rvBn4Zz5vCjW4SJG0oqdrvSV8JbC5p20jXHncPKVxHxuCrU4WbUPEhbqueRfWEl7SSmY0wsz/hYz4V5iSZxZneLhkj8N0xrqoImz+sqHWR9Gf8hT+fpNeAi8Ni0GrM7ElJw3AFdwCwkqTCovUJcLaZTfaCNbOnJS0oqaNN+kuI4B9IXSXpCFpcFArZh1Z7eQK9Je2EKzXnmdl/o57Rku4ChuNLsBeb2UhJ6wCXyf2w58CXtAvf7dMkrRbpXwYOibJGSboOeAq3xhxasuR2AwaZ2QS5e8vK+A4i1bhS0nhgHqCvmVX7gZunYmn7nijvy6hvkKT9gKtjcgDuR7gJ/vK/KN6lZfeVK/El0XtqyDMZZvaEpL7EhADvt7ofk1ZwIXCnpDetuh9zsXQ/N/5CvtHMTL7921kxAWgH/B23jFWT8Z0affFstfQ1uBL/GfvBwFBaJkfV+BRYU/7B20e4ZRhc0T0/lNkXcQtuazkJv5/XwK/lMFyB/I2Z/Q+4S76kP1jSF7iC/Psis5n9LfrsCtyt6hC1+MmX3R4G4Ksk/c1sotxP/+ko40NJF+HPkjHA4xUytnoc0br+JWTaM/J8bGbnVkn2gKSJuKvDMWb2VkzOy9xElX6UuwJMJk+M92sj7GVqTA7N7A65n/V9obQa7mtfj3OBGyTtATxA45WLepyM3xPDo/4xuPGkzPJUWekys/GSdgbOln8cuQxwipldGUluAPYNa/7jxH00Bc+ievffkTFRmYg/R+9sRduTJJkJkVm6Vk0tko4CPjGzixsmnsGRdCZwi5ndL2kt/KOruvthf1PI/R0XNLP/m96yJDMvOY5mDiSdDlxhZsMbpNsV/wamh8VHlzMaHZZc0brsc2LjhNOQIafv2zhRkiSTIGmImVXdh356W5hnFc6jZV/kmZ2RZnY/QPhuzijK8k3ASsC3p7csycxLjqOZBzPr3WS6m4Gb21SYJElme1JhngaEX+QV01uOaYFNuhfrDIOZ9WycKknqk+MoSZIkmRKm90d/SZIkSZIkSTJDkxbmJEmSJGlDVl+2E4PTpzhJZmrSwpwkSZIkSZIkdUiFOUmSJEmSJEnqkApzkiRJkiRJktQhfZiTJEmSpA0Z/dp7dOtd7UcLpx2573KStC1pYU6SJEmSJEmSOqTCnCRJkiRJkiR1SIU5SZIkSZIkSeqQCnOSJEmSJEmS1CEV5iRJkiRJkiSpQyrMSdKGSDpD0pGl87slXVw6/6ukXzUoo5ek4ZJGSfpzKXx5SQ9IejLiv1sj/7GRd7ikoZI2knRTHD8v6aM4Hipp0yr5/y5pyzi+WNIaVdLsJ+mcBu3oKmlgSZZepbh/ShoW4f+WNH+E71KSe7CkzSN8tZLMQyV9XPSzpD6SXi/FfTfC15bUt56MkW5rSbdVhPWVtHujvNMKSUdI+nvp/AJJ95XOfynprFaW2bXOGJlP0pWSRkgaKemh0jV4pEaeKe6TGC8maZtSWM8Im5oy647BKnmOlDRf6fz3U1J3kiSzPqkwJ0nb8giwKYCkOYBFgTVL8ZsCD9fKLKkTcDqwjZmtCSxRUjKOA64zs/WAPYFzq+TfBNgJWN/M1gG2BV41s55m1hU4EBhgZl3j75GK/IsAG5tZfwAzO9DMnmptJwTjgH2jHTsCf5e0UMQdZWbrhoyvAIdF+P3AuiHrAcDFIcczhcxAtyj7plJdZ5TadEfkGQEsK2n5KZS/zZA0Z0XQ1+Mm6AosWEpXd9zUoCtQVWEGjgDeMrO1zWwt4KfAlwBmNtkkahoxAtirdL4nMKyN6qrFkcB8pfNUmJMkqUoqzEnStjxMi+KzJjAS+ETSwpLmAVYHnqyT/1vAs2b2TpzfB+wWxwYsEMcLAm9Uyb8U8K6ZfQ5gZu+aWbV0tdgduKs4kdRPUvc43l/Ss5IeBDZrVJCZPWtmz8XxG8DbwGJx/nGUKaB9tA0zG2tmFkV0KMIr2AZ4wcxebqI9t+KK2RQjaYykP0l6LP5WjvC+ks6XNCD6ZacIn1PS6ZIeD2v5zyJ861ghuApXHss8Cawqqb2kBfEJwVBg7YjfFHhE0kqS7pI0JOrtEmXvEZbiYZL6S5obOAnoFVb3XhX1LQW8XpzEhOTzKGts/JekcyQ9Jel2YPFSn3ST9GDIcbekpZroygHAhpLmCmv2ytHGoszjo89GSrowxkYxBov+f1bSFqUyl47+eE6TrsacJ1+hGCXpxAg7HFgaeCCuw2lA++ifKyPNzdGmUZIOLpU3VtKp0b+DJC3RRHuTJJmJSYU5SdqQUAwnhFVzU2Ag8CiwCdAdGG5mX9Qp4nmgi6TOktoBuwLLRVwf4MeSXgPuAH5ZJf89wHKhWJwraatWNmEzYEhlYChEJ0b8dsAapbidJZ1Ur1BJGwJzAy+Uwi4F/gd0Ac4uhfeU9DRwO25lrmRP4OqKsMNCOb1E0sKl8MHAFkw9H5vZhsA5wN9L4Z2BrYDvAedLmhe31n5kZhsAGwAHSVox0m8IHGtmk7i5mNkEXHncANgYHzODgE0lLQ3IzF4FLgR+aWbdgKNpWWU4HtjBzNYFdo4xdjxwbVjdr61ozyXAb+UuM6dIWqVKm3sCq+FK+0G0rJzMhV+v3UOOS4BTG3UgPvm5D9gB2AW4pSL+HDPbICze7fGVkoJ20f9HAieUwrsCvULGXpKKe+VYM+sOrANsJWkdMzsLn2T2MLMeZnYMMD76Z+/Id0C0qTtweKz4gE/eBkX/9o/+mARJB4eSPnjCuE+a6I4kSWZkUmFOkransDIXCvPA0nlV/9ACM/sA+DlwLW6RGwNMiOi9gL5mtiy+1H6F3O2jnH8s7rJwMPAOcK2k/Voh+1KRr5KNgH5m9k4oY18rYGZ2i5kdX6vAULavAPY3s69K+fbHLX6jcaWnCL/JzLrgk4WTK8qaG9gZuL4UfB6wEq48vQn8tRT3dtRRj2pW7Mrwq0v/NymFX2dmX4Ul/UVc+d8e2FfSUFzx7QQUCuljZvZSjfpqjZvNcOvy/HF+fZR9AX69irx9JR0EVLp7TN4ws6H4asbpwCLA45JWr0i2JXC1mU2MieB/I3w1YC3g3pDjOGDZRnUG1+ATnmqTnh6SHpU0Avg2k7oy3Rj/h+CTlIL7zewjM/sMeApYIcJ/KOkJ3HK/JqUJXgMOlzQMn6wsR8t1+wIo/NwrZQDAzC40s+5m1r3dfB2brC5JkhmV/GnsJGl7Cn/UtXGXjFeBXwMf49a4upjZrbgrAbEsPDGifor7AmNmA8OauSiuFJbzTwT6Af1C+fgJ0LdJ2ccD89YSrckyvkbSAril+DgzGzRZgWYTJV0L9AYurYjrHy4Ii5rZuxH8HeAJM3urlO7rY0kX0aLYEG0Z30DM94CFK8IWAd4tnVsTx8W5cCvw3eUISVsDn9aR4xHgZyHzP/CJyxrx/2Hc4PFh+HFPWqnZIZI2wi3dQyVNlqZKnrG4InqjpK/wSdjoKu2pRMAoM9ukSlyjOh+TtBZu2X02vC6IsXwu0N3MXpXUh0nH4efxfyKTvsc+Lx1PBNqFNf9oYAMz+0D+4WetMd3SKL8+2wKbmNk4Sf1K+b4suQpVypAkySxIWpiTpO15GF9Ofj+sc+8DC+GWyYGNMktaPP4vDPyC+PAN/zhum4hbHX+Zv1ORd7WK5fWuQDO+vgWjcd/SSh4FtpbUKZbk92iiHXPjH+ZdbmbXl8KlFj9gAd8Hno7zlUu+q+vjbhzvlYrdiwrLZIX/bE98klKwanEuaUNJl1cR9TncF3b1SLcCsC4l/1paLOC9mPQa7iFpDkkr4RbbZ4C7gZ9HPyFpVUkdqtRbySO4O8ZiZvZ2KGjv4O4Lj4Tf90uS9ohyJWndOF7JzB4NS/+7uHX0E6CqqVPSZoXrSlynNZh8nPQH9pT7ZC8F9IjwZ4DF5B+YIvdJXjOOD5N0GPX5HZN/bFcopu+GJX1qdihZAJ+YfBS+xt8pxVX2yZfFdcK/C/gglOUu+LVIkmQ2JWfFSdL2jMAtv1dVhM1fspTW48xCEQJOMrNn4/jXwEWSjsItf/uVrF4F8wNny3ejmID7RB9M89yOWzkvLgea2Zth9RuIuz08QSz9S9oZtwxWumX8EF/W71RyC9kPGA5cFtZn4Tsl/Dzid8PdGb7ELcO9ijbKtwPbLuQr8+ewqBruwlKO7xFtAlieKtZmM/tc0o+BS8PS+SVwoJl9VEo2j6RHcaNDeaeHZ4AHgSWAQ8zsM/k2gp2BJ0L5fwd3L6lLWEPfAUaVggfiLhnFbhJ7A+dJOg6YC3dxGAacHhMl4TuNDMMnWMeE28QfK/yYV4pyFG26HbihQqSbcNeIEcCz0U7M7Av5VnBnyT9QbIf7dY/CXVLq7uZhZndWCfswVgdG4Nfw8XplNCh/mKQnQ54XK+S5ELhT0ptm1iPOh4f7xgHAIZKG49d1shWRJElmHzT5+zVJkqQFSQ8BO5nZh9NblqlBvivJg8DmZjZB0unAFWY2vJXljMEnBO9WhPcFbjOzf08jkWd65PtZ/6DBh62zPB2WXNG67HNim9Yx5PR927T8JJkdkDQkPhCejLQwJ0nSiF/j1tgPp7McU8vywDGxAwVm1ns6yzPLY2Y7NU6VJEky45MKc5IkdTGzR6e3DNOC2LniuWlQTuca4ftNbdlJkiTJjEl+9JckSZIkSZIkdUgLc5IkSZK0Iasv24nB6WOcJDM1aWFOkiRJkiRJkjqkwpwkSZIkSZIkdUiFOUmSJEmSJEnqkD7MSZIkSdKGjH7tPbr1rvajktOO3Ic5SdqWtDAnSZIkSZIkSR1SYU6SJEmSJEmSOqTCnCRJkiRJkiR1SIU5SZIkSZIkSeqQCnOSJEmSJEmS1CEV5mSWRNIlkt6WNLJG/NGSTNKicT63pEsljZA0TNLWdcpeTNKXkn4W51tLGliRpp2ktyQtJamvpJckDY2/R2qUu56ki+N4Z0nH1Eg3ton2f1vSE5JGSrpMUrsI712SY6SkiZIWibiFJP1b0tOSRkvaJMJPj7Dhkm6StFCjPpN0n6SFm5Czn6TuFWHdJZ3VKG9Fnj6Sjm5Nnm+KerJVXktJ+0k655uRbDJZJrsWpfBnYsyMlnTwNK53a0m3TUG+g2NcPi1pcL17NkmSZGpJhTmZVekL7FgtQtJywHbAK6XggwDMbO2I+6ukWvfHHsAgYK847w8sK6lzKc22wEgzezPOe5tZ1/jbtEa5vwfODjluMbPTajevNiH3ZcCeZrYW8DLwkyj39EIO/r+9e4/XqqrzOP75KggKyOQNDW8EmIoJeMsGJc0Zs6YJSS2MTErHxrxkmo6N5r0sm/KSlzI1HGPwkmA6mpdIBfHGJUBBUSod8BLiLcRbB3/zx1qPZ/P4PPucoxyec+D7fr18nb3XXnvt39r7OZ7fs/baG/gucG9EvJR3vRC4PSK2BQYDj+Xyu4AdImJH4Im8H5Sfs2uAb76f+CNiekQc+372tdapfIFqg9H5MzMM+JGkdVZ+VK0n6XPAN4A98uf1CODXkvo2Mi4zW305YbbVUkRMBl6qs/l84CQgCmXbA5PyvouBV4D3jLZlBwMnkJLkvhHxDnAD8KVCnVHA+NbGK6kXsGNEzM7r7440Suon6QFJ0ySd3YrmNgTeiogn8vpdwAF1+jE+H2N9YDhwJUBEvB0Rr+TlOyOiKe/zILB5Xi47ZzfT/IWiTYojjnl09qo8yvlnSccW6p2SRz5/D3y0UN5f0u2SZkiaImnbXD5W0kWS7s9tHZjLL5X0+bw8UdJVefkwSefk5ePziPyjko4rHKteec3Y2ngetpI0KY/sT5K0paS1c+zKdwTekTQ8158iaYCk3XIf/5h/fjRvHyPpBkm3AHdKWlfStbn964B1WxFWT2AZsDy3uW/+bM7MbffM5aflz+ujki6XpFw+IN99mJ336V9pV813N8ZV6pf4D9KX0CUAETET+BVwVD7OU2q+e7SLpHvyco/8eZqWz8+IXL620p2Uafl8FO8e3VMrNkk/lDQv1/+vVpw7my6ifwAAD2RJREFUM+vEnDDbGiUnRs9UEtOC2cAIpakU/YCdgS1q7L8FsGlEPAxcT3OSPJ6UJCOpG/BZ4MbCrj9W81SIcTVC2wWoOX2ENPJ7WUTsCjxfFc+sGvWXAF3VfHv9wOq+SFqPNAJfifEjwAvAr3IicYWkHjXa/jrwu7xc95xFxMtAN0kb1ulTW2wLfBrYDThdUldJO5PO91DgC8CuhfqXA8dExM7Ad4BLC9s2A/YAPgdURvAnA3vm5b6kLwLkelPysb4GfBzYHfg3pekzZeX1Yqu2buFzMQs4q7DtYuC/88j+OOCiiFhOGuXfPsc3A9gzf+Y2j4gFwOPA8IgYCpwG/KDQ5ieAQyPiU8CRwOu5/e+Trl894yTNAeYDZ0fE8pyQngr8U0TsBEwHjq/EHhG75jsc65LON7kfl0TEYOAfgcodmKHAcblfHyGNZJcZlPteNJ3ma1fPKcAf8u/S3qTfyx7AYcCruXxX0rXsVy82pWlMI4FB+fydU30gpSkj0yVNb3p9aQthmVlH53/pz9YYOUk8Bdi3xuargO1If3SfBu4HmmrUG0VKlAGuJY3I/jQipknqmUfztgMezEljxYkR8ZuS8DYjJay1DKN5hPga4EeVDfk2+QoiIiSNAs7PidSdNfryr8DUwnSMLsBOpETzIUkXAicD36vsIOmU3E4l4W/pnC0GPgy8WLfXrXNrRLwFvCVpMdCHlOBOjIjXc2w35589SYnYDYVBym6Ftm7KdwTmSeqTy6YAx0naHpgHfEjSZqTk8ljSl4SJEbEsH2NCPr7qlK9VK7Y63iheQ0ljaB6l/wQp4YZ03c8rxDsc6AecS5oacy8wLW/vDVwtaSDpLkrXwvHuKlzz4cBFABExJyfE9YyOiOmSNgbul3Q78DFSEjk1n+t1gMpc/r0lnQSsB2wAzM2jvH0jYmI+5pu5zwAPR8SivD4L2Bq4rySeWloalYb0u/95Nc8p7w5smct3VL7rQDqHA4G368T2IPAmcIWkW4H3zMGOiMtJX97osWm/qN5uZp2LE2Zbk/QnJRmz8x/pzYGZknaLiOeBb1cqKj2Y92SNNg4G+kgandc/LGlgRDxJSqBHkZLIVk/HyN4g/fGup01/cCPiAfKoqaR9gW2qqlRPGVkELIqIh/L6b0gJM7mNQ0mjhPtERORjNFF+zrqT+vVBvVVYXk7z/7dqnZO1gFdqfZGo0ZYAIuIZpQcU9yONNm8AfBF4LSKWlkwPKEvQ3hNbvjtxS179eUT8vGT/sjanAP9O+jJyGnAisFeOHeBs4O6IGKk0r/6eQhvLWoqzNICIFyTNJI2qv0FKwFeYeiOpO2lUf5eIWCjpDNJnoex81bvG9cwjjYj/oVBWGeWG9MWtcge1+Hsl4ICImF8Vs0hfFu+oKt+rVmwR0SRpN2Af0u/S0cCnWojZzDoxT8mwNUZEPBIRm0TE1hGxNSlJ3Ckinpe0XmUKgqR/BpoiYl5x/zx63CMi+hbaOJc8FYOUgH6F9IezbFSxlseAAXW2TS0cY3SdOiuQtEn+2Y003/PnhW29gU8Cv62U5S8MC3MfISUC83L9/XIbn6+MmubyuucsJyCbAk/l9UlauQ9kTQZGKs3D7UUaMSci/gb8RdJBlTgkDW5Few+QbrtPJiWk38k/K8fav9DfkXlbWXmt2BYWHvxsTbJ8Pyte98qI60OkUfR38ijtLNIDcJV4ewPP5OUxJe1Pzu0iaQdgx5YCyndphgJ/Io2yDpM0oLJN0jY0J6hL8oj/gfDutVkkaf9cv1tur+x450oaWWPTeaSHDzfM9YaQzv8v8vanaJ5iUpy/fwdwTOVLkKShhfIjJXXN5duo9pSkSlw9gd4RcRvpczOkrB9m1vk5YbbVkqTxpCToo5IWSTqshV02IY02P0ZKDg+pUedgYGJV2Y25nJwsvk6aI1k9klecwzxLVW8ZiIjHgd45war2LeAoSdNIyVCxn7Pq9OfE3Jc5wC0RURyJGwncWSPGY2ieqzqE5rmvFwO9gLty7JVkr+yc7UyaltKk9OaMAdR/CPPWfI0WSbqhTp0V5Ie8riMlizfSnCxCSgIPkzQbmAuMaEWTU0gjhwuAmaRR5imFY40FHiYlq1dExB9bKK8XW1scC3wtX49DSJ8D8vSUhaSEtRJ7L+CRvH4ecK6kqcDaJe1fRnrYbg7pIdiHS+qOy5+1GcDYiJgRES+QEvLxuY0HgW3zw6K/zPHcRPNUEXI/js317yd9qSrzMarm7UN6iwxpOtRUSQtIXyb2zzEBnAlcKGkK+QHF7GzSFJU5Sq+crDxEewXpC+LMXP4Lyke5ewH/m/txL4U7LWa2elK+u2pmDSbp28DSiLii0bF8UEpzoG+OiEl59PLrEXF8S/uZFUm6IyI+3UKdLqQ3ZKwFfCU64B+1Hpv2i20PObNdjzHjx19t1/bN1gSSZkREzTdkeQ6zWcdxGekdz6uDRyOi8sq5R2l+e4JZq7WULOc6TdS+I2RmttI4YTbrIPJ81GsaHcfKEBG/bHQMZmZmK4vnMJuZmZmZlfAIs5mZWTvabvMNme45xmadmkeYzczMzMxK+C0ZZmZm7UjSUtI/K96ZbQQsaXQQH5D70DF05D5sFREb19rgKRlmZmbta369V1V1FpKmuw+N5z40jqdkmJmZmZmVcMJsZmZmZlbCCbOZmVn7urzRAawE7kPH4D40iB/6MzMzMzMr4RFmMzMzM7MSTpjNzMzaiaT9JM2XtEDSyY2OpzUkPSXpEUmzJE3PZRtIukvSk/nnhxodZzVJV0laLOnRQlnduCV9N1+X+ZI+3ZioV1SnD2dIeiZfj1mSPlvY1qH6IGkLSXdLekzSXEnfyuWd6jrU4oTZzMysHUhaG7gE+AywPXCwpO0bG1Wr7R0RQwqv/zoZmBQRA4FJeb2jGQvsV1VWM+58HUYBg/I+l+br1WhjeW8fAM7P12NIRNwGHbYPTcAJEbEdsDtwVI6zs12H93DCbGZm1j52AxZExJ8j4m3gWmBEg2N6v0YAV+flq4H9GxdKbRExGXipqrhe3COAayPirYj4C7CAdL0aqk4f6ulwfYiI5yJiZl5eCjwG9KWTXYdanDCbmZm1j77AwsL6olzW0QVwp6QZko7IZX0i4jlISRGwScOia5t6cXe2a3O0pDl5ykZlOkOH7oOkrYGhwEOsBtfBCbOZmVn7UI2yzvBqqmERsRNpKslRkoY3OqB20JmuzWVAf2AI8Bzwk1zeYfsgqSdwI3BcRPytrGqNsg7Rh2pOmM3MzNrHImCLwvrmwLMNiqXVIuLZ/HMxMJF0i/yvkjYDyD8XNy7CNqkXd6e5NhHx14hYHhHvAL+kecpCh+yDpK6kZHlcREzIxZ3+OjhhNjMzax/TgIGS+klah/Rw080NjqmUpB6SelWWgX2BR0lxH5qrHQr8tjERtlm9uG8GRknqJqkfMBB4uAHxtaiSaGYjSdcDOmAfJAm4EngsIn5a2NTpr0OXRgdgZma2OoqIJklHA3cAawNXRcTcBofVkj7AxJT30AX4n4i4XdI04HpJhwH/BxzUwBhrkjQe2AvYSNIi4HTgh9SIOyLmSroemEd6s8NREbG8IYEX1OnDXpKGkKYqPAV8AzpsH4YBhwCPSJqVy/6TTnYdavG/9GdmZmZmVsJTMszMzMzMSjhhNjMzMzMr4YTZzMzMzKyEE2YzMzMzsxJOmM3MzMzMSjhhNjMzMzMr4YTZzMzMzKyEE2YzMzMzsxJOmM3MzMzMSjhhNjMzMzMr4YTZzMzMzKyEE2YzMzOz1YikPpImS1oq6SeNjmd14ITZzMzMVhlJX5Y0XdJrkp6T9DtJe6yC44akAe19nJLj7yDpDklLJEWN7RtImihpmaSnJX25avs+kh6X9LqkuyVtVXK4I4AlwPoRcYKkeyQdvpK7tEZxwmxmZmarhKTjgQuAHwB9gC2BS4ERDQxrpZPUpUbx34HrgcPq7HYJ8DbpvIwGLpM0KLe3ETAB+B6wATAduK4khK2AeRHxnsTc3h8nzGZmZtbuJPUGzgKOiogJEbEsIv4eEbdExIm5TjdJF0h6Nv93gaRuedsYSfdVtfnuqLGksZIukXRrnorwkKT+edvkvMvsPLL9pRrxjZE0VdLPJL2aR3P3KcYv6co8Kv6MpHMkrV217/mSXgLOqG4/IuZHxJXA3BrH7gEcAHwvIl6LiPuAm4FDcpUvAHMj4oaIeDO3P1jStjXaGgscCpyU+zoV2BO4OK9fXOv6WDknzGZmZrYqfALoDkwsqXMKsDswBBgM7Aac2oZjHAycCXwIWAB8HyAihuftgyOiZ0TUG539OPBnYCPgdGCCpA3ytquBJmAAMBTYFzi8xr6bVI7bBtsAyyPiiULZbGBQXh6U18n9WQb8qbCdwrYxwDjgvNzXYcAU4Oi8fnQbYzOcMJuZmdmqsSGwJCKaSuqMBs6KiMUR8QIp+T2kpH61CRHxcD7GOFLi3RaLgQvyyPd1wHzgXyT1AT4DHJdHxhcD5wOjCvs+GxE/i4imiHijjcftCbxaVfYq0KuV262d1ZpjY2ZmZrayvQhsJKlLSdL8YeDpwvrTuay1ni8sv05KNNvimap5v5XjbwV0BZ6TVNm2FrCwULe43FavAetXla0PLG3ldmtnHmE2MzOzVeEB4E1g/5I6z5KS04otcxnAMmC9ygZJm67k+AD6qpARF46/EHgL2Cgi/iH/t35EFKdEfJAH7J4AukgaWCgbTPN857l5HXh3znN/asyHrsMP/31ATpjNzMys3UXEq8BpwCWS9pe0nqSukj4j6bxcbTxwqqSN85shTgN+nbfNBgZJGiKpOzUerGvBX4GPtFBnE+DYHNdBwHbAbRHxHHAn8BNJ60taS1J/SZ9s7cGVdAfWyevdKw805jnJE4CzJPWQNIz05pBr8u4TgR0kHZDbOA2YExGPr8S+WwknzGZmZrZKRMRPgeNJD/K9QBq5PRq4KVc5h/TKtDnAI8DMXEZ+IO4s4PfAk8AKb8xohTOAqyW9IumLdeo8BAwkvcP4+8CBEfFi3vZVUrI7D3gZ+A2wWRuOvxXwBs2jwm+Q5khXfBNYlzSPejxwZETMBcjzuQ/IMb1MesCwOH+6JRcCB0p6WdJFAJLmShrdhjbWaPIr+szMzGxNJ2kMcHhEtPs/omKdj0eYzczMzMxKOGE2MzMzMyvhKRlmZmZmZiU8wmxmZmZmVsIJs5mZmZlZCSfMZmZmZmYlnDCbmZmZmZVwwmxmZmZmVsIJs5mZmZlZif8H/zGxDwF2fVsAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 720x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axs = plt.subplots(2, 1, figsize=(10, 8))\n",
    "\n",
    "# first plot\n",
    "data = count_by_nta.sort_values(by='count', ascending=False).head(10)\n",
    "sns.barplot(\n",
    "    data=data,\n",
    "    y='ntaname_full',\n",
    "    x='count',\n",
    "    color='#1f77b4',\n",
    "    ax=axs[0]\n",
    ")\n",
    "\n",
    "label = 'Count of NYC 311 Street Flooding Complaints by Street Segment from 2010 to 2020'\n",
    "axs[0].set_title(label, fontsize=12, pad=10, x=-.1)\n",
    "axs[0].set_xlabel('Count', fontsize=12)\n",
    "axs[0].set_ylabel('Street Segment\\n', fontsize=12, labelpad=10)\n",
    "\n",
    "# second plot\n",
    "data = count_by_nta.sort_values(by='count_per_100ft', ascending=False).head(10)\n",
    "sns.barplot(\n",
    "    data=data,\n",
    "    y='ntaname_full',\n",
    "    x='count_per_100ft',\n",
    "    color='#1f77b4',\n",
    "    ax=axs[1]\n",
    ")\n",
    "\n",
    "label = 'Count of NYC 311 Street Flooding Complaints per 100 ft. by Street Segment from 2010 to 2020'\n",
    "axs[1].set_title(label, fontsize=12, pad=10, x=-.24)\n",
    "axs[1].set_xlabel('Count per 100 ft.', fontsize=12, labelpad=10)\n",
    "axs[1].set_ylabel('Street Segment', fontsize=12, labelpad=10)\n",
    "\n",
    "fig.tight_layout(pad=.9)\n",
    "plt.savefig('figures/count-street-segment.png', dpi=250, bbox_inches='tight')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}