{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "import pandas as pd\n",
    "from sklearn.cluster import KMeans\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "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>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>cod_localidade_tse</th>\n",
       "      <th>nom_localidade</th>\n",
       "      <th>nom_bairro</th>\n",
       "      <th>num_local</th>\n",
       "      <th>nom_local</th>\n",
       "      <th>des_endereco</th>\n",
       "      <th>codigo</th>\n",
       "      <th>lqtd_secoes</th>\n",
       "      <th>lqtd_aptos</th>\n",
       "      <th>indigenas</th>\n",
       "      <th>grupos</th>\n",
       "      <th>efetivo</th>\n",
       "      <th>crimes_eleitorais</th>\n",
       "      <th>boca_de_urna</th>\n",
       "      <th>roubo</th>\n",
       "      <th>furto</th>\n",
       "      <th>desacato</th>\n",
       "      <th>desobediencia</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-56.124416</td>\n",
       "      <td>-15.280069</td>\n",
       "      <td>90670</td>\n",
       "      <td>CUIABÁ</td>\n",
       "      <td>AGUAÇU</td>\n",
       "      <td>2470</td>\n",
       "      <td>ESCOLA MUNICIPAL UDENEY GONÇALVES DE AMORIM</td>\n",
       "      <td>RUA PRINCIPAL, SN</td>\n",
       "      <td>1906702470</td>\n",
       "      <td>3</td>\n",
       "      <td>925</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-56.019846</td>\n",
       "      <td>-15.544380</td>\n",
       "      <td>90670</td>\n",
       "      <td>CUIABÁ</td>\n",
       "      <td>ALTOS DA GLÓRIA</td>\n",
       "      <td>1210</td>\n",
       "      <td>ESCOLA MUNICIPAL PROFESSORA GRACILDES MELO DANTAS</td>\n",
       "      <td>RUA QUINZE QUADRA 60 S/N</td>\n",
       "      <td>51906701210</td>\n",
       "      <td>5</td>\n",
       "      <td>1945</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>17</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-56.024079</td>\n",
       "      <td>-15.579122</td>\n",
       "      <td>90670</td>\n",
       "      <td>CUIABÁ</td>\n",
       "      <td>ALTOS DA SERRA</td>\n",
       "      <td>2100</td>\n",
       "      <td>E. M. CELINA FIALHO BEZERRA</td>\n",
       "      <td>RUA PRINCESA DAYANE, S/N</td>\n",
       "      <td>39906702100</td>\n",
       "      <td>9</td>\n",
       "      <td>3513</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>16</td>\n",
       "      <td>29</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-56.024712</td>\n",
       "      <td>-15.635798</td>\n",
       "      <td>90670</td>\n",
       "      <td>CUIABÁ</td>\n",
       "      <td>ALTOS DO COXIPÓ</td>\n",
       "      <td>1473</td>\n",
       "      <td>CCI - CENTRO DE CONVIVÊNCIA DO IDOSO JOÃO GUER...</td>\n",
       "      <td>RUA 01, S/N</td>\n",
       "      <td>55906701473</td>\n",
       "      <td>2</td>\n",
       "      <td>611</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.6</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-56.081131</td>\n",
       "      <td>-15.579708</td>\n",
       "      <td>90670</td>\n",
       "      <td>CUIABÁ</td>\n",
       "      <td>ALVORADA</td>\n",
       "      <td>2488</td>\n",
       "      <td>ESCOLA MUNICIPAL CÂNDIDO MARIANO DA SILVA RONDON</td>\n",
       "      <td>RUA PIRATININGA, 101</td>\n",
       "      <td>1906702488</td>\n",
       "      <td>12</td>\n",
       "      <td>4571</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>34</td>\n",
       "      <td>64</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 17,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "locais = pd.read_excel('Planilha para distribuicao do efetivo.xlsx', sheet_name='dados')\n",
    "locais[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
   ],
   "source": [
    "# Crimes eleitorais obteve muito baixa distribuicao, com valores iguais a 0 (maioria), 1 (14), 2 (2) e 3 (1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">boca_de_urna</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c_boca_de_urna</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>1362.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>28.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.00</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.00</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>80.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.0</td>\n",
       "      <td>4.5</td>\n",
       "      <td>0.707107</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.25</td>\n",
       "      <td>4.5</td>\n",
       "      <td>4.75</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.00</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.00</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 57,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "aux = 'c_boca_de_urna'\n",
    "aux1 = 'boca_de_urna'\n",
    "kmeans = KMeans(n_clusters=5, random_state=0).fit(locais[aux1].values.reshape(-1,1))\n",
    "locais[aux] = kmeans.labels_\n",
    "locais[[aux, aux1]].groupby([aux]).describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f4072872ba8>"
      ]
     },
     "execution_count": 58,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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"
     },
     "execution_count": 58,
     "metadata": {
      "image/png": {
       "height": 250,
       "width": 383
      }
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "locais[aux1].hist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "collapsed": false
   },
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">indigenas</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c_indigenas</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>1443.0</td>\n",
       "      <td>0.167706</td>\n",
       "      <td>3.191030</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>71.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>12.0</td>\n",
       "      <td>355.500000</td>\n",
       "      <td>64.281342</td>\n",
       "      <td>267.0</td>\n",
       "      <td>306.25</td>\n",
       "      <td>363.0</td>\n",
       "      <td>392.0</td>\n",
       "      <td>479.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>17.0</td>\n",
       "      <td>167.470588</td>\n",
       "      <td>48.687932</td>\n",
       "      <td>95.0</td>\n",
       "      <td>122.00</td>\n",
       "      <td>158.0</td>\n",
       "      <td>215.0</td>\n",
       "      <td>242.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5.0</td>\n",
       "      <td>603.600000</td>\n",
       "      <td>56.906063</td>\n",
       "      <td>544.0</td>\n",
       "      <td>586.00</td>\n",
       "      <td>591.0</td>\n",
       "      <td>599.0</td>\n",
       "      <td>698.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>921.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>921.0</td>\n",
       "      <td>921.00</td>\n",
       "      <td>921.0</td>\n",
       "      <td>921.0</td>\n",
       "      <td>921.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 54,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "aux = 'c_indigenas'\n",
    "aux1 = 'indigenas'\n",
    "kmeans = KMeans(n_clusters=5, random_state=0).fit(locais[aux1].values.reshape(-1,1))\n",
    "locais[aux] = kmeans.labels_\n",
    "locais[[aux, aux1]].groupby([aux]).describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f4072b00c50>"
      ]
     },
     "execution_count": 55,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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"
     },
     "execution_count": 55,
     "metadata": {
      "image/png": {
       "height": 250,
       "width": 383
      }
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "locais[aux1].hist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">lqtd_aptos</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c_lqtd_aptos</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>570.0</td>\n",
       "      <td>360.615789</td>\n",
       "      <td>195.368108</td>\n",
       "      <td>3.0</td>\n",
       "      <td>200.25</td>\n",
       "      <td>335.0</td>\n",
       "      <td>503.75</td>\n",
       "      <td>784.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>91.0</td>\n",
       "      <td>4829.219780</td>\n",
       "      <td>755.592862</td>\n",
       "      <td>4073.0</td>\n",
       "      <td>4316.00</td>\n",
       "      <td>4569.0</td>\n",
       "      <td>5106.50</td>\n",
       "      <td>8300.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>272.0</td>\n",
       "      <td>2120.143382</td>\n",
       "      <td>291.995333</td>\n",
       "      <td>1665.0</td>\n",
       "      <td>1876.75</td>\n",
       "      <td>2074.0</td>\n",
       "      <td>2362.25</td>\n",
       "      <td>2687.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>211.0</td>\n",
       "      <td>3259.241706</td>\n",
       "      <td>376.906081</td>\n",
       "      <td>2700.0</td>\n",
       "      <td>2930.50</td>\n",
       "      <td>3197.0</td>\n",
       "      <td>3547.00</td>\n",
       "      <td>4004.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>334.0</td>\n",
       "      <td>1210.173653</td>\n",
       "      <td>244.468695</td>\n",
       "      <td>794.0</td>\n",
       "      <td>997.25</td>\n",
       "      <td>1201.0</td>\n",
       "      <td>1402.50</td>\n",
       "      <td>1654.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 52,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "aux = 'c_lqtd_aptos'\n",
    "aux1 = 'lqtd_aptos'\n",
    "kmeans = KMeans(n_clusters=5, random_state=0).fit(locais[aux1].values.reshape(-1,1))\n",
    "locais[aux] = kmeans.labels_\n",
    "locais[[aux, aux1]].groupby([aux]).describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f40729e64e0>"
      ]
     },
     "execution_count": 53,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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"
     },
     "execution_count": 53,
     "metadata": {
      "image/png": {
       "height": 250,
       "width": 377
      }
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "locais[aux1].hist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">roubo</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c_roubo</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>1304.0</td>\n",
       "      <td>0.643405</td>\n",
       "      <td>1.363707</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>6.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2.0</td>\n",
       "      <td>181.000000</td>\n",
       "      <td>14.142136</td>\n",
       "      <td>171.0</td>\n",
       "      <td>176.0</td>\n",
       "      <td>181.0</td>\n",
       "      <td>186.0</td>\n",
       "      <td>191.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>39.0</td>\n",
       "      <td>35.282051</td>\n",
       "      <td>8.404099</td>\n",
       "      <td>24.0</td>\n",
       "      <td>29.0</td>\n",
       "      <td>33.0</td>\n",
       "      <td>42.5</td>\n",
       "      <td>52.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>9.0</td>\n",
       "      <td>73.444444</td>\n",
       "      <td>12.238373</td>\n",
       "      <td>58.0</td>\n",
       "      <td>65.0</td>\n",
       "      <td>71.0</td>\n",
       "      <td>82.0</td>\n",
       "      <td>96.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>124.0</td>\n",
       "      <td>12.177419</td>\n",
       "      <td>4.433884</td>\n",
       "      <td>7.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>23.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 59,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "aux = 'c_roubo'\n",
    "aux1 = 'roubo'\n",
    "kmeans = KMeans(n_clusters=5, random_state=0).fit(locais[aux1].values.reshape(-1,1))\n",
    "locais[aux] = kmeans.labels_\n",
    "locais[[aux, aux1]].groupby([aux]).describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f40727c1cf8>"
      ]
     },
     "execution_count": 60,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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"
     },
     "execution_count": 60,
     "metadata": {
      "image/png": {
       "height": 250,
       "width": 390
      }
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "locais[aux1].hist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">furto</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c_furto</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>1200.0</td>\n",
       "      <td>1.187500</td>\n",
       "      <td>2.081495</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.00</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>13.0</td>\n",
       "      <td>119.461538</td>\n",
       "      <td>30.269939</td>\n",
       "      <td>88.0</td>\n",
       "      <td>94.00</td>\n",
       "      <td>112.0</td>\n",
       "      <td>127.00</td>\n",
       "      <td>187.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>56.0</td>\n",
       "      <td>44.892857</td>\n",
       "      <td>12.132119</td>\n",
       "      <td>31.0</td>\n",
       "      <td>35.75</td>\n",
       "      <td>42.5</td>\n",
       "      <td>50.25</td>\n",
       "      <td>80.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.0</td>\n",
       "      <td>308.500000</td>\n",
       "      <td>16.263456</td>\n",
       "      <td>297.0</td>\n",
       "      <td>302.75</td>\n",
       "      <td>308.5</td>\n",
       "      <td>314.25</td>\n",
       "      <td>320.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>207.0</td>\n",
       "      <td>15.821256</td>\n",
       "      <td>6.127444</td>\n",
       "      <td>9.0</td>\n",
       "      <td>11.00</td>\n",
       "      <td>14.0</td>\n",
       "      <td>20.50</td>\n",
       "      <td>29.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 68,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "aux = 'c_furto'\n",
    "aux1 = 'furto'\n",
    "kmeans = KMeans(n_clusters=5, random_state=0).fit(locais[aux1].values.reshape(-1,1))\n",
    "locais[aux] = kmeans.labels_\n",
    "locais[[aux, aux1]].groupby([aux]).describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f40727559b0>"
      ]
     },
     "execution_count": 62,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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"
     },
     "execution_count": 62,
     "metadata": {
      "image/png": {
       "height": 250,
       "width": 383
      }
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "locais[aux1].hist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">desacato</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c_desacato</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>1232.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>36.0</td>\n",
       "      <td>3.361111</td>\n",
       "      <td>0.487136</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>126.0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>12.0</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>1.414214</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>10.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>72.0</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 63,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "aux = 'c_desacato'\n",
    "aux1 = 'desacato'\n",
    "kmeans = KMeans(n_clusters=5, random_state=0).fit(locais[aux1].values.reshape(-1,1))\n",
    "locais[aux] = kmeans.labels_\n",
    "locais[[aux, aux1]].groupby([aux]).describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f40727c19b0>"
      ]
     },
     "execution_count": 64,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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"
     },
     "execution_count": 64,
     "metadata": {
      "image/png": {
       "height": 250,
       "width": 383
      }
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "locais[aux1].hist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">desobediencia</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c_desobediencia</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>186.0</td>\n",
       "      <td>1.263441</td>\n",
       "      <td>0.441688</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1227.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2.0</td>\n",
       "      <td>22.000000</td>\n",
       "      <td>4.242641</td>\n",
       "      <td>19.0</td>\n",
       "      <td>20.5</td>\n",
       "      <td>22.0</td>\n",
       "      <td>23.5</td>\n",
       "      <td>25.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>17.0</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>1.322876</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>9.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>46.0</td>\n",
       "      <td>3.239130</td>\n",
       "      <td>0.431266</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 65,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "aux = 'c_desobediencia'\n",
    "aux1 = 'desobediencia'\n",
    "kmeans = KMeans(n_clusters=5, random_state=0).fit(locais[aux1].values.reshape(-1,1))\n",
    "locais[aux] = kmeans.labels_\n",
    "locais[[aux, aux1]].groupby([aux]).describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f40729e64e0>"
      ]
     },
     "execution_count": 53,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAvIAAAH0CAYAAABfKsnMAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAAWJQAAFiUBSVIk8AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAAIABJREFUeJzt3XuUbVV9J/rvT0h4pUB8RE2IjXp9ECVphZiIHTwxo72+TSLe5g4TMUa92hKjgh2vYkI7fNAJRgVy5aoJGM0Y0OLVblrUdIIlUWwVNEMdGsXIweAjKsiheB08Mu8fa1XcbqrOOVC7ap9Z5/MZY43FnmvOteaqPdnnW7PWXqtaawEAAPpyl3l3AAAAuOMEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADq077w7sKeoqiuTHJxk65y7AgDA5nZ4kutba/dby04E+R85+IADDrjbEUcccbeNPOjS0lKSZGFhYSMPyyZkLDErxhKzYBwxK5txLH3pS1/KzTffvOb9CPI/svWII4642+WXX76hB11cXEySbNmyZUOPy+ZjLDErxhKzYBwxK5txLB111FH5zGc+s3Wt+3GNPAAAdEiQBwCADs00yFfVr1fV+6rq21W1vaq+WVUfrqonrlD3mKq6qKquraqbq+pzVfWSqtpnJ/t/clUtVtW2qrqhqj5ZVSfM8hwAAKAHMwvyVfUnSf42ydFJ/nuSNyb5QJJ7JtkyVfdpSS5JcmyS9yU5K8lPJnlTkvNW2f+JSS5M8rAk707y9iQ/k+Tcqjp9VucBAAA9mMmXXavqeUlenuSdSZ7fWrt1avtPTPz3wRlC+A+TbGmtXTaWvzrJxUmOq6rjW2vnTbQ5PMnpSa5NcnRrbetY/pokn05yUlW9t7X2iVmcDwAA7OnWPCNfVfsleV2Sr2eFEJ8krbUfTLw8LsMs/XnLIX6sc0uSU8aXL5zaxXOS7JfkrOUQP7b5fpLXjy9fsLYzAQCAfsxiRv7fZwjmb05yW1U9KcPlL7ck+dQKs+SPHdcfWmFflyS5KckxVbVfa237brT54FQdAADY9GYR5H9pXN+S5LMZQvy/qqpLkhzXWvvuWPTgcf2V6R211naMT1h9aJL7J/nSbrT5VlXdmOSwqjqwtXbTWk4GAAB6MIsg/9Pj+uVJvpjkV5P8Q5L7Zbiu/XFJ3pMffeH1kHG9bZX9LZffdaJsd9ocNNbbaZCvqtWe+PSQpaWlf33owEZZflrZRh+XzcdYYlaMJWbBOGJWNuNYWj6ntZrFXWuW97EjyVNbax9rrd3QWvt8kt9McnWSx1TVo2ZwLAAAILOZkb9uXH928ouoSdJau6mqPpzk95I8Mskn8qNZ9UOysuXy6ybKtiW5x7jtmp20WW3GfrJPR61UXlWXLywsPGKjH/+7GR87zHwYS8yKscQsGEfMymYcSwsLCzPZzyxm5L88rq9bZfv3x/UBU/UfNF2xqvbNcEnOjiRfW+EYK7W5T4bLaq52fTwAAHuLWQT5v0vSkvx8Va20v+Uvv145ri8e149foe6xSQ5McunEHWt21eYJU3UAAGDTW3OQb61dleGJq/dN8geT26rqcUn+9wyz9cu3jrwgyfeSHF9VR0/U3T/Ja8eXb506zDlJtic5cXw41HKbQ5O8cnx59lrPBQAAejGTJ7smeVGShyf5s/E+8p/NcInMb2R4gutzW2vbkqS1dv34JNgLkixW1XkZntj61Ay3mbwgyfmTO2+tXVlVL09yRpLLqur8JLdmeLjUYUne6KmuAADsTWYS5FtrV1fVUUn+KEMgPzbJ9Rlm6t/QWvvUVP33V9VjkrwqydOT7J/kq0leluSM1lpb4RhnVtXWJCcneVaGvyZ8MckprbV3zuI8AACgF7Oakc/4wKffH5fdqf/xJE+8g8e4MMMvBwAAsFebxZddAQCADTazGXnuvC98Y1ue/YoPzLsbG2rraU+adxcAALpmRh4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0aCZBvqq2VlVbZfn2Km2OqaqLquraqrq5qj5XVS+pqn12cpwnV9ViVW2rqhuq6pNVdcIszgEAAHqy7wz3tS3Jm1cov2G6oKqeluS9SW5Jcn6Sa5M8Jcmbkjw6yTNWaHNikjOTXJPk3UluTXJcknOr6sjW2smzOQ0AANjzzTLIX9daO3VXlarq4CRvT/LDJFtaa5eN5a9OcnGS46rq+NbaeRNtDk9yeobAf3RrbetY/pokn05yUlW9t7X2iRmeDwAA7LHmcY38cUnumeS85RCfJK21W5KcMr584VSb5yTZL8lZyyF+bPP9JK8fX75gvToMAAB7mlnOyO9XVb+d5L5JbkzyuSSXtNZ+OFXvseP6Qyvs45IkNyU5pqr2a61t3402H5yqAwAAm1611ta+k6qtSf7NCpuuTPK7rbWPTtT9dJKjM1wic/kK+/pCkocm+fnW2pfGsu8muUeSe7TWrlmhzQ1JDkpyUGvtpl309XbHHD3kgQ984IFve9vbdtZ85paWlnLLD27Lv9y8oYedu4f97CHz7sKms7S0lCRZWFiYc0/onbHELBhHzMpmHEvPf/7zc8UVV3ymtXbUWvYzq0trzkny60nunSFQH5nk/01yeJIPVtUvTtRdTnDbVtnXcvld70Qb6RAAgL3CTC6taa3956miLyR5wThTflKSU5P85iyOtVar/eZTVZcvLCw8YsuWLRvan8XFxVz1jW05/fOzvMppz7f1mVvm3YVNZ3FxMUmy0WOYzcdYYhaMI2ZlM46lWf11Yb2/7Hr2uD52omxXs+fL5dfdiTarzdgDAMCmst5B/rvj+qCJsi+P6wdNV66qfZPcL8mOJF/bzTb3Gfd/9a6ujwcAgM1ivYP8r4zryVB+8bh+/Ar1j01yYJJLJ+5Ys6s2T5iqAwAAm96ag3xVHVFVB61QfniSs8aX757YdEGS7yU5vqqOnqi/f5LXji/fOrW7c5JsT3LiuN/lNocmeeX48uwAAMBeYhbfsPwPGZ6sekmSq5IsJXlAkicl2T/JRRmeypokaa1dX1XPyxDoF6vqvAxPbH1qkgeP5edPHqC1dmVVvTzJGUkuq6rzk9ya4eFShyV5o6e6AgCwN5lFkP9IhgD+8CSPznC9+nVJPpbkXUne1aZuVt9ae39VPSbJq5I8PUPg/2qSlyU5Y7r+2ObM8X71Jyd5Voa/JnwxySmttXfO4DwAAKAbaw7y48OePrrLirdv9/EkT7yDbS5McuEdPRYAAGw26/1lVwAAYB0I8gAA0CFBHgAAOiTIAwBAhwR5AADokCAPAAAdEuQBAKBDgjwAAHRIkAcAgA4J8gAA0CFBHgAAOiTIAwBAhwR5AADokCAPAAAdEuQBAKBDgjwAAHRIkAcAgA4J8gAA0CFBHgAAOiTIAwBAhwR5AADokCAPAAAdEuQBAKBDgjwAAHRIkAcAgA4J8gAA0CFBHgAAOiTIAwBAhwR5AADokCAPAAAdEuQBAKBDgjwAAHRIkAcAgA4J8gAA0CFBHgAAOiTIAwBAhwR5AADokCAPAAAdEuQBAKBDgjwAAHRIkAcAgA4J8gAA0CFBHgAAOiTIAwBAhwR5AADokCAPAAAdEuQBAKBDgjwAAHRIkAcAgA4J8gAA0CFBHgAAOiTIAwBAhwR5AADokCAPAAAdEuQBAKBDgjwAAHRoXYJ8Vf12VbVxee4qdZ5cVYtVta2qbqiqT1bVCbvY7wlV9amx/rax/ZPX4xwAAGBPNvMgX1U/l+SsJDfspM6JSS5M8rAk707y9iQ/k+Tcqjp9lTanJzk3yX3G+u9OcmSSC8f9AQDAXmOmQb6qKsk5Sa5JcvYqdQ5PcnqSa5Mc3Vp7UWvtpUl+Ick/JTmpqh411eaYJCeN23+htfbS1tqLkhw17uf0cb8AALBXmPWM/IuTPDbJ7ya5cZU6z0myX5KzWmtblwtba99P8vrx5Qum2iy/ft1Yb7nN1iR/Pu7vd9fYdwAA6MbMgnxVHZHktCRvaa1dspOqjx3XH1ph2wen6qylDQAAbFr7zmInVbVvkncl+XqSV+6i+oPH9VemN7TWvlVVNyY5rKoObK3dVFUHJfnZJDe01r61wv6uGNcP2s2+Xr7KpocsLS1lcXFxd3YzM0tLS7nXAcnJR+7Y0OPO20b/nPcGS0tLSfxsWTtjiVkwjpiVzTiWls9prWYS5JP8UZKHJ/l3rbWbd1H3kHG9bZXt25IcNNa7aTfrJ8ldd6+rAADQvzUH+ar65Qyz8G9srX1i7V1aX621o1Yqr6rLFxYWHrFly5YN7c/i4mKu+sa2nP75Wf1O1Yetz9wy7y5sOsszFRs9htl8jCVmwThiVjbjWFpYWJjJftZ0jfx4Sc1fZbhM5tW72Wx5Bv2QVbZPz8Dvbv3rdvP4AADQvbV+2fWnMlybfkSSWyYeAtWS/PFY5+1j2ZvH118e17e7pr2q7pPhspqrW2s3JUlr7cYk30jyU+P2aQ8c17e75h4AADartV7PsT3JX6yy7REZrpv/WIbwvnzZzcVJHp3k8RNly54wUWfSxUl+Z2xzzm62AQCATWtNQX78YutzV9pWVadmCPLvbK29Y2LTOUn+U5ITq+qc5XvJV9Wh+dEdb6YfJnV2hiD/qqp6//K95MeHQL0owy8U0wEfAAA2rQ3/hmVr7cqqenmSM5JcVlXnJ7k1yXFJDssKX5ptrV1aVX+W5GVJPldVFyT5yST/Icndkvz+5MOlAABgs5vLrVJaa2dW1dYkJyd5VoZr9b+Y5JTW2jtXaXNSVX0+wwz885PcluQzSf60tfY/NqTjAACwh1i3IN9aOzXJqTvZfmGSC+/gPs9Ncu4augUAAJvCWu9aAwAAzIEgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6NC+8+4Ae6fDX/GBeXdhw2097Unz7gIAsImYkQcAgA4J8gAA0CFBHgAAOiTIAwBAhwR5AADo0EyCfFX9l6r6u6r656q6uaqurarPVtUfV9XdV2lzTFVdNNa9uao+V1Uvqap9dnKcJ1fVYlVtq6obquqTVXXCLM4BAAB6MqsZ+ZcmOSjJ/0zyliR/nWRHklOTfK6qfm6yclU9LcklSY5N8r4kZyX5ySRvSnLeSgeoqhOTXJjkYUneneTtSX4myblVdfqMzgMAALowq/vIH9xau2W6sKpel+SVSf7vJP9xLDs4Qwj/YZItrbXLxvJXJ7k4yXFVdXxr7byJ/Rye5PQk1yY5urW2dSx/TZJPJzmpqt7bWvvEjM4HAAD2aDOZkV8pxI/+67h+4ETZcUnumeS85RA/sY9TxpcvnNrPc5Lsl+Ss5RA/tvl+ktePL19wpzoPAAAdWu8vuz5lXH9uouyx4/pDK9S/JMlNSY6pqv12s80Hp+oAAMCmN6tLa5IkVXVykp9KckiSo5P8uwwh/rSJag8e11+Zbt9a21FVVyZ5aJL7J/nSbrT5VlXdmOSwqjqwtXbTLM4FAAD2ZDMN8klOTnKvidcfSvLs1tp3J8oOGdfbVtnHcvld72Cbg8Z6Ow3yVXX5KpsesrS0lMXFxZ01n7mlpaXc64Dk5CN3bOhx2XjrPbaWlpY25DhsfsYSs2AcMSubcSwtn9NazfTSmtbavVtrleTeSX4rw6z6Z6vqEbM8DgAA7O1mPSOfJGmt/UuS91XVZzJcDvNXGW4bmfxoVv2QldpOlF83UbYtyT3GbdfspM1qM/aTfTtqpfKqunxhYeERW7Zs2dUuZmpxcTFXfWNbTv/8urwV7EG2PnPLuu5/eaZio8cwm4+xxCwYR8zKZhxLCwsLM9nPun7ZtbV2VZIvJnloVd1jLP7yuH7QdP2q2jfJ/TLcg/5rE5t21uY+GS6rudr18QAA7C3W+641yfDQpmS4b3wy3Cs+SR6/Qt1jkxyY5NLW2vaJ8p21ecJUHQAA2PTWHOSr6kFVdbvLZKrqLuMDoX46QzD//rjpgiTfS3J8VR09UX//JK8dX751anfnJNme5MTx4VDLbQ7N8MCpJDl7recCAAC9mMWF2U9M8oaq+liSKzNcw36vJI/J8GXXbyd53nLl1tr1VfW8DIF+sarOy/DE1qdmuM3kBUnOnzxAa+3Kqnp5kjOSXFZV5ye5NcPDpQ5L8kZPdQUAYG8yiyD/t0n+twz3jH94httG3pjhS67vSnJGa+3ayQattfdX1WOSvCrJ05Psn+SrSV421m/TB2mtnVlVWzPc4vJZGf6a8MUkp7TW3jmD8wAAgG6sOci31r6Q5MQ70e7jGWbz70ibC5NceEePBQAAm81GfNkVAACYMUEeAAA6JMgDAECHBHkAAOiQIA8AAB0S5AEAoEOCPAAAdEiQBwCADgnyAADQIUEeAAA6JMgDAECHBHkAAOiQIA8AAB0S5AEAoEOCPAAAdEiQBwCADgnyAADQIUEeAAA6JMgDAECHBHkAAOiQIA8AAB0S5AEAoEOCPAAAdEiQBwCADgnyAADQIUEeAAA6JMgDAECHBHkAAOiQIA8AAB0S5AEAoEOCPAAAdEiQBwCADgnyAADQIUEeAAA6JMgDAECHBHkAAOiQIA8AAB0S5AEAoEOCPAAAdEiQBwCADgnyAADQoX3n3QHYWxz+ig+s6/5PPnJHkuTZ63ycO2LraU+adxcAYNMyIw8AAB0S5AEAoEOCPAAAdEiQBwCADgnyAADQIUEeAAA6JMgDAECHBHkAAOiQIA8AAB0S5AEAoEOCPAAAdEiQBwCADgnyAADQIUEeAAA6tOYgX1V3r6rnVtX7quqrVXVzVW2rqo9V1e9V1YrHqKpjquqiqrp2bPO5qnpJVe2zk2M9uaoWx/3fUFWfrKoT1noOAADQm31nsI9nJHlrkm8l+UiSrye5V5LfSvKOJE+oqme01tpyg6p6WpL3JrklyflJrk3ylCRvSvLocZ8/pqpOTHJmkmuSvDvJrUmOS3JuVR3ZWjt5BucCAABdmEWQ/0qSpyb5QGvttuXCqnplkk8leXqGUP/esfzgJG9P8sMkW1prl43lr05ycZLjqur41tp5E/s6PMnpGQL/0a21rWP5a5J8OslJVfXe1tonZnA+AACwx1vzpTWttYtbaxdOhvix/NtJzh5fbpnYdFySeyY5bznEj/VvSXLK+PKFU4d5TpL9kpy1HOLHNt9P8vrx5QvWdiYAANCP9f6y6w/G9Y6JsseO6w+tUP+SJDclOaaq9tvNNh+cqgMAAJveLC6tWVFV7ZvkWePLyQD+4HH9lek2rbUdVXVlkocmuX+SL+1Gm29V1Y1JDquqA1trN+2iX5evsukhS0tLWVxc3FnzmVtaWsq9DkhOPnLHrivDTtzrgGG9J42ljf7/idlYWlpK4v1jbYwjZmUzjqXlc1qr9ZyRPy3Jw5Jc1Fr78ET5IeN62yrtlsvveifaHLLKdgAA2FTWZUa+ql6c5KQk/5jkd9bjGHdWa+2olcqr6vKFhYVHbNmyZUP7s7i4mKu+sS2nf37d/jjCXmJ5Jn5PGktbn7ll3l3gTlie9droz0M2F+OIWdmMY2lhYWEm+5n5jPx4m8i3JPlikl9rrV07VWVXs+fL5dfdiTarzdgDAMCmMtMgX1UvyXCv9y9kCPHfXqHal8f1g1Zov2+S+2X4cuzXdrPNfZIclOTqXV0fDwAAm8XMgnxV/WGGBzr9Q4YQ/51Vql48rh+/wrZjkxyY5NLW2vbdbPOEqToAALDpzSTIjw9zOi3J5Ul+vbX2vZ1UvyDJ95IcX1VHT+xj/ySvHV++darNOUm2JzlxfDjUcptDk7xyfHl2AABgL7Hmb8VV1QlJXpPhSa1/n+TFVTVdbWtr7dwkaa1dX1XPyxDoF6vqvAxPbH1qhttMXpDk/MnGrbUrq+rlSc5IcllVnZ/k1gwPlzosyRs91RUAgL3JLG5vcb9xvU+Sl6xS56NJzl1+0Vp7f1U9Jsmrkjw9yf5JvprkZUnOaK216R201s6sqq1JTs5wf/q7ZPhC7SmttXfO4DwAAKAbaw7yrbVTk5x6J9p9PMkT72CbC5NceEePBQAAm816PhAKAABYJ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6NC+8+4AsHkd/ooPzLsLG27raU+adxcA2EuYkQcAgA4J8gAA0CFBHgAAOiTIAwBAhwR5AADokCAPAAAdEuQBAKBDgjwAAHRIkAcAgA4J8gAA0CFBHgAAOiTIAwBAhwR5AADokCAPAAAdEuQBAKBDgjwAAHRIkAcAgA4J8gAA0CFBHgAAOiTIAwBAhwR5AADokCAPAAAdEuQBAKBDgjwAAHRIkAcAgA4J8gAA0CFBHgAAOiTIAwBAhwR5AADokCAPAAAdEuQBAKBDgjwAAHRIkAcAgA4J8gAA0CFBHgAAOiTIAwBAhwR5AADokCAPAAAdEuQBAKBDgjwAAHRoJkG+qo6rqjOr6u+r6vqqalX17l20OaaqLqqqa6vq5qr6XFW9pKr22UmbJ1fVYlVtq6obquqTVXXCLM4BAAB6su+M9nNKkl9MckOSq5M8ZGeVq+ppSd6b5JYk5ye5NslTkrwpyaOTPGOFNicmOTPJNUneneTWJMclObeqjmytnTyjcwEAgD3erC6teWmSByU5OMkLd1axqg5O8vYkP0yypbX2e621lyf5t0k+keS4qjp+qs3hSU7PEPiPbq29qLX20iS/kOSfkpxUVY+a0bkAAMAebyZBvrX2kdbaFa21thvVj0tyzyTntdYum9jHLRlm9pPb/zLwnCT7JTmrtbZ1os33k7x+fPmCO9l9AADozjy+7PrYcf2hFbZdkuSmJMdU1X672eaDU3UAAGDTm9U18nfEg8f1V6Y3tNZ2VNWVSR6a5P5JvrQbbb5VVTcmOayqDmyt3bSzg1fV5atsesjS0lIWFxd34xRmZ2lpKfc6IDn5yB0belw2n3sdMKyNpfna6M+Q9bC0tJRkc5wL82McMSubcSwtn9NazWNG/pBxvW2V7cvld70TbQ5ZZTsAAGwq85iRn6vW2lErlVfV5QsLC4/YsmXLhvZncXExV31jW07//F73VjBjyzPxxtJ8bX3mlnl3Yc2WZ702+vOQzcU4YlY241haWFiYyX7mMSO/q9nz5fLr7kSb1WbsAQBgU5nH1N2Xkxyd4XaVP3a9elXtm+R+SXYk+dpUm3uMbT4x1eY+SQ5KcvWuro8HWG+Hv+ID8+7Cmi3/defZu3kuW0970np2B4BVzGNG/uJx/fgVth2b5MAkl7bWtu9mmydM1QEAgE1vHkH+giTfS3J8VR29XFhV+yd57fjyrVNtzkmyPcmJ48OhltscmuSV48uz16m/AACwx5nJpTVV9RtJfmN8ee9x/aiqOnf87++11k5Oktba9VX1vAyBfrGqzsvwxNanZrjN5AVJzp/cf2vtyqp6eZIzklxWVecnuTXDw6UOS/LG1tqPXXIDAACb2ayukf+3SU6YKrv/uCTJVUlOXt7QWnt/VT0myauSPD3J/km+muRlSc5Y6QmxrbUzq2rruJ9nZfhrwheTnNJae+eMzgMAALowkyDfWjs1yal3sM3HkzzxDra5MMmFd6QNAABsRvO4Rh4AAFgjQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0aN95dwCAvh3+ig/MuwsbbutpT5p3FwDMyAMAQI8EeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIf2nXcHAKA3h7/iA/PuwobaetqT5t0FYAVm5AEAoEOCPAAAdEiQBwCADgnyAADQIUEeAAA61FWQr6rDquovq+qbVbW9qrZW1Zur6tB59w0AADZSN7efrKoHJLk0yU8n+W9J/jHJI5P8QZLHV9WjW2vXzLGLAACwYboJ8kn+nwwh/sWttTOXC6vqz5K8NMnrkrxgTn0DgE3rztw3/+QjdyRJnt3pPffdO58edHFpzTgb/7gkW5P8+dTmP05yY5LfqaqDNrhrAAAwF10E+SS/Nq7/prV22+SG1tpSko8nOTDJr2x0xwAAYB56ubTmweP6K6tsvyLDjP1dtqdgAAAKO0lEQVSDkvzdhvQIANi07szlRL1zOVF/qrU27z7sUlW9LcnzkjyvtfaOFba/Lskrk7yytfaGXezr8lU2/eJ+++23z33ve9819/eOuO2223Jba9lx267rws7sO/59zVhirYwlZsE4YlbWcyzt/xP7zH6nu+HrX/96tm/ffm1r7e5r2U8vM/Ib4Yfbt2/fdsUVV2zd4OM+ZFz/4wYfl83HWGJWjCVmwThiVjbjWDo8yfVr3UkvQX7buD5kle3L5dftakettaNm0qMZWf4LwZ7WL/pjLDErxhKzYBwxK8bS6nr5suuXx/WDVtn+wHG92jX0AACwqfQS5D8yrh9XVT/W56paSPLoJDcl+V8b3TEAAJiHLoJ8a+2fkvxNhuuJXjS1+T8nOSjJu1prN25w1wAAYC56uUY+Sf5jkkuTnFFVv57kS0l+OcM95r+S5FVz7BsAAGyoLmbkk3+dlT86ybkZAvxJSR6Q5C1JfqW1ds38egcAABuri/vIAwAAP66bGXkAAOBHBHkAAOiQIA8AAB0S5AEAoEOCPAAAdEiQBwCADgnyAADQIUF+TqrqsKr6y6r6ZlVtr6qtVfXmqjp03n1j/VTV3avquVX1vqr6alXdXFXbqupjVfV7VbXi/5NVdUxVXVRV145tPldVL6mqfXZyrCdX1eK4/xuq6pNVdcIu+ndCVX1qrL9tbP/ktZ43G6Oqfruq2rg8d5U66z4uqmqfqnrpOE5vHsftRVV1zFrPkfVTVb8+fjZ9e/x36ZtV9eGqeuIKdX0msaKqelJV/U1VXT2Oja9V1Xuq6lGr1DeW1qK1ZtngJcMTaf8lSUvy/iSnJbl4fP2PSe4+7z5a1u29f8H4Pn8zyV8neUOSv0xy3Vh+QcYHtU20eVqSHUluSPIXSf50HCctyXtWOc6J4/bvJfnzJG9K8s9j2emrtDl93P7PY/0/T3LNWHbivH92ll2OrZ8bx9HS+J49dx7jIkklec/E59mfjuP2hnEcP23ePyvLiu/zn0y8z29L8vokb0/ymSR/MlXXZ5JltXH0Xybe53eM+eaCJLcmuS3JbxtLM/6Zz7sDe+OS5MPj4Pn9qfI/G8vPnncfLev23j82yVOS3GWq/N5Jvj6+/0+fKD84yXeSbE9y9ET5/kkuHesfP7Wvw5PcMn5IHT5RfmiSr45tHjXV5pix/KtJDp3a1zXj/g5fy7lb1nVcVZK/TfJP4z+EtwvyGzUukvyfY5uPJ9l/ovyXxnH8nSQL8/6ZWX7sPXve+J6dm+QnV9j+ExP/7TPJsto4uneSHyb5dpKfntr2a+P7+TVjabaLS2s2WFU9IMnjkmzN8BvhpD9OcmOS36mqgza4a2yA1trFrbULW2u3TZV/O8nZ48stE5uOS3LPJOe11i6bqH9LklPGly+cOsxzkuyX5KzW2taJNt/PMMuWDH8ZmLT8+nVjveU2WzOM0/2S/O6uz5A5eXGGXxJ/N8NnyEo2alwsj8dTxnG63ObTSc7PMJ6P252TYv1V1X5JXpdhIuH5rbVbp+u01n4w8dJnEqv5Nxku2f5ka+07kxtaax/J8NfCe04UG0szIMhvvF8b13+zQphbyjCLdWCSX9nojjF3y/9Y7pgoe+y4/tAK9S9JclOSY8Z/jHenzQen6qylDXuAqjoiw5+v39Jau2QnVdd9XFTV/hlmv25K8vd34DjMz7/PEKb+vyS3jdc3/2FV/cEq1zT7TGI1V2S4hOaRVXWPyQ1VdWyShQx/OVxmLM2AIL/xHjyuv7LK9ivG9YM2oC/sIapq3yTPGl9OftisOl5aazuSXJlk3yT3380238owY3tYVR04HvugJD+b5IZx+zRjcg81jpt3ZZhNfeUuqm/EuHhAkn0y/Pl8x+2bGEt7oF8a17ck+WyS/5HhF8M3J7m0qj5aVZOzqD6TWFFr7dokf5jkXkm+WFVvq6o3VNV/TfI3Sf5nkv9roomxNAOC/MY7ZFxvW2X7cvldN6Av7DlOS/KwJBe11j48UX5nxsvutjlkam1M9uePkjw8ybNbazfvou5GjAtjqT8/Pa5fnuE64l/NMHP6CxnC17EZvry8zGcSq2qtvTnJb2UI4M9L8ookz8jwJdNzpy65MZZmQJCHOauqFyc5KcM39X9nzt2hE1X1yxlm4d/YWvvEvPtDt5ZzwI4kT22tfay1dkNr7fNJfjPJ1Ukes9qtA2FSVf2nDHepOTfDX+gOSnJUkq8l+euq+pP59W5zEuQ33vRvi9OWy6/bgL4wZ1V1YpK3JPlikl8b/zQ56c6Ml91ts21qbUx2Yryk5q8y/Hn51bvZbCPGhbHUn+X34rOTXx5MktbaTRnuspYkjxzXPpNYUVVtyXD7yf/eWntZa+1rrbWbWmufyfBL4TeSnFRVy5fKGEszIMhvvC+P69Wux3rguF7tGno2iap6SZIzk3whQ4j/9grVVh0vY5i7X4aZtK/tZpv7ZJghuXr8RzqttRszfMD+1Lh9mjG55/mpDO/vEUlumXgIVMtw96skeftY9ubx9UaMi3/KcPu5+4/jc3faMF/L42K1ILN8l48Dpur7TGLa8sOVPjK9YXxvP5Uhdz58LDaWZkCQ33jLA/xxNfUUz6paSPLoDN/U/l8b3TE2TlX9YYaHUvxDhhD/nVWqXjyuH7/CtmMz3OHo0tba9t1s84SpOmtpw/xsz/DwlJWWz451Pja+Xr7sZt3HxXjbuEszjMtfvQPHYX7+LsO18T8//W/S6GHj+spx7TOJ1SzfXeaeq2xfLl++xamxNAvzvpH93rjEA6H26iXDpRAtyWVJ7raLugcn+W7u2AMz7hcPzNhrlySnZuUHQm3IuMjuPRDq4Hn/nCw/9p79t/E9e+lU+eMyPI3z+0kOGct8JllWG0f/x/iefTvJz05te8I4lm7O+PR6Y2lGP/d5d2BvXDJ8AeRfxoH1/iRvyPDbYMvwZ6O7z7uPlnV7708Y3+cdGWbkT11hefZUm9/Ijx5h/Y4Mj1L/10dYJ6kVjvP7ueOPsH5jbv8I6+9lEzzCem9askqQ36hxkeEps+8Zt39pHK9/MY7fHUmeNu+fkeV279lh+dGTpf82w9OBLxjfrx9k4mnTY32fSZaV3q+7ZLjFZEtyfZJ3ZrxmPkOIb0n+wFia8c993h3YW5ckP5fknCTfyvBnpqsy3Lf30Hn3zbKu7/tyyNrZsrhCu0cnuSjDzNjNST6f5KVJ9tnJsZ6S5KMZnqZ3Y5JPJzlhF/179ljvxrHdR5M8ed4/N8udGmO3C/IbNS4y3HrupeM4vXkctxclOWbePx/Lqu/ZPTN8Z+eq8d+k7yV5X5JHrlLfZ5JlpffrJ5K8JMPlwddnCOnfyfB8gscZS7Nfajw5AACgI77sCgAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHRLkAQCgQ4I8AAB0SJAHAIAOCfIAANAhQR4AADokyAMAQIcEeQAA6JAgDwAAHfr/ATyqm9D/rsn5AAAAAElFTkSuQmCC"
     },
     "execution_count": 53,
     "metadata": {
      "image/png": {
       "height": 250,
       "width": 377
      }
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "locais[aux1].hist()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (Ubuntu Linux)",
   "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}