PoliceStopRI.ipynb

policestopri.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.8.3"
    },
    "colab": {
      "name": "PoliceStopRI.ipynb",
      "provenance": [],
      "include_colab_link": true
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/TanabutT/0a2e334ab8ad27bbfae56abea23c2f1c/policestopri.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "K8D0G52YX7Qe"
      },
      "source": [
        "# DATA EXPLORATION\n",
        "\n",
        "analyzing a dataset of traffic stops in Rhode Island that was collected by the Stanford Open Policing Project.\n",
        "\n",
        "Before beginning your analysis, it's important that to familiarize with the dataset. \n",
        "We will read the dataset into pandas, examine the first few rows, and then count the number of missing values.\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_rf9-Y1RX7Qf"
      },
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import missingno as msno\n",
        "import datetime as dt"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "scrolled": false,
        "id": "eo-tipkUX7Qi",
        "outputId": "22e9b7e9-14fb-4562-f115-2a98a66890ae"
      },
      "source": [
        "# Read 'police.csv' into a DataFrame named ri and set index with date and time combile column 'date' and 'stop_time'\n",
        "ri = pd.read_csv('PoliceRI2020.csv', parse_dates= [['date', 'stop_time']], index_col='date_stop_time')\n",
        "\n",
        "# Examine the head of the DataFrame\n",
        "ri.head()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Unnamed: 0</th>\n",
              "      <th>raw_row_number</th>\n",
              "      <th>district</th>\n",
              "      <th>subject_race</th>\n",
              "      <th>subject_sex</th>\n",
              "      <th>arrest_made</th>\n",
              "      <th>citation_issued</th>\n",
              "      <th>warning_issued</th>\n",
              "      <th>contraband_found</th>\n",
              "      <th>contraband_drugs</th>\n",
              "      <th>contraband_weapons</th>\n",
              "      <th>contraband_alcohol</th>\n",
              "      <th>frisk_performed</th>\n",
              "      <th>search_conducted</th>\n",
              "      <th>reason_for_stop</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>date_stop_time</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>2005-11-22 11:15:00</th>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>X3</td>\n",
              "      <td>white</td>\n",
              "      <td>male</td>\n",
              "      <td>False</td>\n",
              "      <td>True</td>\n",
              "      <td>False</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.0</td>\n",
              "      <td>False</td>\n",
              "      <td>Speeding</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2005-10-01 12:20:00</th>\n",
              "      <td>1</td>\n",
              "      <td>2</td>\n",
              "      <td>X3</td>\n",
              "      <td>white</td>\n",
              "      <td>male</td>\n",
              "      <td>False</td>\n",
              "      <td>True</td>\n",
              "      <td>False</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.0</td>\n",
              "      <td>False</td>\n",
              "      <td>Speeding</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2005-10-01 12:30:00</th>\n",
              "      <td>2</td>\n",
              "      <td>3</td>\n",
              "      <td>X3</td>\n",
              "      <td>white</td>\n",
              "      <td>female</td>\n",
              "      <td>False</td>\n",
              "      <td>True</td>\n",
              "      <td>False</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.0</td>\n",
              "      <td>False</td>\n",
              "      <td>Speeding</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2005-10-01 12:50:00</th>\n",
              "      <td>3</td>\n",
              "      <td>4</td>\n",
              "      <td>X3</td>\n",
              "      <td>white</td>\n",
              "      <td>male</td>\n",
              "      <td>False</td>\n",
              "      <td>True</td>\n",
              "      <td>False</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.0</td>\n",
              "      <td>False</td>\n",
              "      <td>Speeding</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2005-10-01 13:10:00</th>\n",
              "      <td>4</td>\n",
              "      <td>5</td>\n",
              "      <td>X3</td>\n",
              "      <td>white</td>\n",
              "      <td>female</td>\n",
              "      <td>False</td>\n",
              "      <td>True</td>\n",
              "      <td>False</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.0</td>\n",
              "      <td>False</td>\n",
              "      <td>Speeding</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                     Unnamed: 0  raw_row_number district subject_race  \\\n",
              "date_stop_time                                                          \n",
              "2005-11-22 11:15:00           0               1       X3        white   \n",
              "2005-10-01 12:20:00           1               2       X3        white   \n",
              "2005-10-01 12:30:00           2               3       X3        white   \n",
              "2005-10-01 12:50:00           3               4       X3        white   \n",
              "2005-10-01 13:10:00           4               5       X3        white   \n",
              "\n",
              "                    subject_sex arrest_made citation_issued warning_issued  \\\n",
              "date_stop_time                                                               \n",
              "2005-11-22 11:15:00        male       False            True          False   \n",
              "2005-10-01 12:20:00        male       False            True          False   \n",
              "2005-10-01 12:30:00      female       False            True          False   \n",
              "2005-10-01 12:50:00        male       False            True          False   \n",
              "2005-10-01 13:10:00      female       False            True          False   \n",
              "\n",
              "                    contraband_found contraband_drugs contraband_weapons  \\\n",
              "date_stop_time                                                             \n",
              "2005-11-22 11:15:00              NaN              NaN                NaN   \n",
              "2005-10-01 12:20:00              NaN              NaN                NaN   \n",
              "2005-10-01 12:30:00              NaN              NaN                NaN   \n",
              "2005-10-01 12:50:00              NaN              NaN                NaN   \n",
              "2005-10-01 13:10:00              NaN              NaN                NaN   \n",
              "\n",
              "                    contraband_alcohol  frisk_performed  search_conducted  \\\n",
              "date_stop_time                                                              \n",
              "2005-11-22 11:15:00                NaN              0.0             False   \n",
              "2005-10-01 12:20:00                NaN              0.0             False   \n",
              "2005-10-01 12:30:00                NaN              0.0             False   \n",
              "2005-10-01 12:50:00                NaN              0.0             False   \n",
              "2005-10-01 13:10:00                NaN              0.0             False   \n",
              "\n",
              "                    reason_for_stop  \n",
              "date_stop_time                       \n",
              "2005-11-22 11:15:00        Speeding  \n",
              "2005-10-01 12:20:00        Speeding  \n",
              "2005-10-01 12:30:00        Speeding  \n",
              "2005-10-01 12:50:00        Speeding  \n",
              "2005-10-01 13:10:00        Speeding  "
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 2
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "zHTPymgsX7Ql",
        "outputId": "80183114-fad3-4282-e601-1d7dbea30730"
      },
      "source": [
        "# Examine the shape of the DataFrame\n",
        "print(ri.shape)\n",
        "\n",
        "# Drop the 'county_name' and 'state' columns\n",
        "ri.drop(['raw_row_number', 'Unnamed: 0', 'contraband_found'], axis='columns', inplace=True)\n",
        "\n",
        "# rename to meaningful name for driver detail\n",
        "ri.rename(columns={'subject_race': 'driver_race', 'subject_sex':'driver_gender'}, inplace=True)\n",
        "\n",
        "# Examine the shape of the DataFrame (again)\n",
        "print(ri.shape)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "(509681, 15)\n",
            "(509681, 12)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jfDGKuCRX7Qo",
        "outputId": "4dc3672c-9e09-4026-c9f7-f77be3562ee5"
      },
      "source": [
        "ri.info()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "Index: 509681 entries, 2005-11-22 11:15:00 to nan nan\n",
            "Data columns (total 12 columns):\n",
            " #   Column              Non-Null Count   Dtype  \n",
            "---  ------              --------------   -----  \n",
            " 0   district            509671 non-null  object \n",
            " 1   driver_race         480608 non-null  object \n",
            " 2   driver_gender       480584 non-null  object \n",
            " 3   arrest_made         480608 non-null  object \n",
            " 4   citation_issued     480608 non-null  object \n",
            " 5   warning_issued      480608 non-null  object \n",
            " 6   contraband_drugs    15988 non-null   object \n",
            " 7   contraband_weapons  11795 non-null   object \n",
            " 8   contraband_alcohol  1217 non-null    object \n",
            " 9   frisk_performed     509681 non-null  float64\n",
            " 10  search_conducted    509681 non-null  bool   \n",
            " 11  reason_for_stop     480608 non-null  object \n",
            "dtypes: bool(1), float64(1), object(10)\n",
            "memory usage: 47.1+ MB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "gjknMRCkX7Qq"
      },
      "source": [
        "# Cleaning and manipulation data\n",
        "\n",
        "manage the missing value and catergorize to the proper type  \n",
        "change nan values in contraband columns to True and False"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "H7uGHgNCX7Qr",
        "outputId": "907a2cf5-4192-408e-8725-a888ccd5aeb3"
      },
      "source": [
        "# Count the number of missing values in each column\n",
        "ri.isnull().sum()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "district                  10\n",
              "driver_race            29073\n",
              "driver_gender          29097\n",
              "arrest_made            29073\n",
              "citation_issued        29073\n",
              "warning_issued         29073\n",
              "contraband_drugs      493693\n",
              "contraband_weapons    497886\n",
              "contraband_alcohol    508464\n",
              "frisk_performed            0\n",
              "search_conducted           0\n",
              "reason_for_stop        29073\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ENe1aFdIX7Qt",
        "outputId": "012cbcd7-1696-4189-bae9-93bcd4084080"
      },
      "source": [
        "msno.matrix(ri)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x1ee6558a100>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAABeYAAALFCAYAAACmmjNIAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nOzdedytU/3/8df74JiTITQavkKDBkRKJalfSUKTkqlMZYxklpmQeR4zpUjKnFSKRCEUSZIpmUWZOe/fH5+12XbnSHXvve9z7vfz8TgP5772de3HOvdy7b2uz1rr85FtIiIiIiIiIiIiIiJiMMYNuwEREREREREREREREWNJAvMREREREREREREREQOUwHxERERERERERERExAAlMB8RERERERERERERMUAJzEdEREREREREREREDFAC8xERERERERERERERA5TAfERERERERERERETEACUwHxERERERERERERExQAnMR0REREREREREREQMUALzEREREREREUMgSS/lWEREREx5EpiPiIiIiIiIGDBJsu3297dJerekqTvHIiIiYsqWwHxERERERETEAPUE5VcDvg98Cnj9UBsWERERA5PAfERERERERMQAdQXlVweOBo4HjrP9h+7zJOWZPSIiYgql7JKLiIiIiIiIGCxJCwJnAycB37T9eDv+FmBa4Hrbj0kaZ3vCEJsaERERfZDZ94iIiIiIiIjBmxOYHTjT9uOS5pb0XeBc4BfAryTNnKB8RETElCmB+YiIiIiIiIgBkaT210eAh4CvS9od+DnwdmDb9mceYP2hNDIiIiL6LoH5iIiIiIiIiD7pCsQDz+eXB/4MHAcsBLwPOB94g+2TgO8BDwL3D7CpERERMUBTD7sBEREREREREVMiSeoq9LossDTwLHCB7askfRM4HJjG9n3tvBmBZaiFdLcOo90RERHRfyn+GhEREREREdFHktYADqZS18wKzACsafvbPee9CfgQsAuwu+29Bt3WsULSFsAvbV8+7LZERMTYlMB8RERERERExAjqWSk/L3Aa8J32Zz5gM2BlYF3bx7fzlga2Bv4PONL2Ae34uBSAHVmSXgNcA9wHrGb76iE3KSIixqCksomIiIiIiIgYQV1B+fdTK+TvAM6wfRdwl6T7gCeAY1oM/1vA76nA/e22f9GuT1C+D2zfKekjwPHASZLWsH3VsNsVERFjS1bMR0RERERERIwwSbMCvwVeB1wFvMf2E12vLwB8HfgUsInto3pW2j/39+gPSe8ATgQmAAnOR0TEQI0bdgMiIiIiIiIipjS2HwI+C1wKvAn4oKSpul6/GdgZ+AFwhKQ3dgfiE5TvP9u/AdagYiMnSlpsyE2KiIgxJCvmIyIiIiIiIv4Hk1rdLmka4O1UypRxwFrAr7vPlbQQMI/tCwfU3DHpRfpoKmBR4CTgWbJyPiIiBiSB+YiIiIiIiIj/Uk/6mYWB1wAzAVfbvr0dXxw4GTATCc53vVdyyvfBf9BHpwDPkOB8REQMQALzEREREREREf8jSWsAOwGzAdMDTwLbAafavr8rn/kzwHrA5UlXM1gvsY9OasfXaaluIiIi+iI55iMiIiIiIiL+B5JWAo6kAu8rAqsAZwH7A5tKmgG4ElgdmAE4A5hzOK0dm/6DPvo8tZr+TEmvGFJzI4ZO0lskTT/sdkRMybJiPiIiIiIiYhTpzYU9qdzYMXySxgHTAKcDjwNr236svTYe2APYBFjR9gXt/CWBBWyfNKRmjynpo4j/nKQNgMOoAtY/tP3EkJsUMUVKYD4iIiIiImKU6MmF/WbgYdt3DLlZ8SJagdcbgF/ZXqM7T7ykuYAfAQ8CH7X9eM+1mXQZgPRRxH+m7RY5E5gP+Apwdu+9ERH/u6SyiYiIiIiIGAV6gvKfBb4D7CNp1uG2LF6M7aeBB4B52s8TWiAY2/cANwFzULnle69NwHcA0kcRL12buLqPSvn0B+AgYMWW7ikiRlAC8xEREREREaNAV1B+deBY4NvAgbYfGmrDAqiJkxd5+WjgPZL2gOcCwUiaDngauBmY6t+8R/yP0kcR/5s2QTyh/fgKYHdq0moHYIXknI8YWVMPuwERERERERFRJL2dynm9A3BYJ3WApM5K39uG2Lwxq2c3w1LAgsBswHlUQPdM4H3AVyW9HNgNmBV4J7AysFFyNA9O66P/AyYA32+/+4uAk4At0kcRE9f1ObcWsCvwa+C3VEqb/dtrZ+VeiRgZyTEfERERERExSkhaHjgYWM72XyS9rP28OBVoPBDYxfajQ2zmmCVpbaoPnqUKikKleTgQELAtsA6VEuXJ9t+Dbe/Rrk++8hEmaTXg0s6kVQso7kP1z/TAX4AVbN8saSHgy8C6pI8iJkrSe4DzqcD8CVQaqEWpwPz8VLHk5JyPGAEJzEdERERERAzBxAKAkj5Orb5en0ofsDowHZWGYzZgC2BZ2xcPtrVjU89K+bdTfXMocCHwMLA5sAFVD2Bj4ClgAeDjwB3ArbZ/3q4f15UiIkaApEWBK4EzgM2oe+QM4CjgZ8AbgW2Amang/LWSZgFeR/ooYqIkbQZsBbzH9s1dx18DnA3M0l4/1/Zjw2llxJQhqWwiIiIiIiKGoCvguyzwqO0rbP9Q0uHAkcDVVBqBdWw/01b7fh5IAb4B6eqjt1EB998DJ7aCoQCbSLof2An4he1jgN+1P89JwLdvfg+sTe0q2Y0Kyl9F9dG9kq4GbgcOAM6VtLzt60gfRfyLronI6al44bPt+DjbE2zfKekoanJyL2BaSafafnZ4rY6YvKX4a0RERERExAB1F5eUNBOVp3xXSUsC2N6QWun7UdtrtaD8tMB7gMeAu4fQ7DFL0rzUJMnJwHSdoLyk8QC2d6H6cGNJE33GTsC3P2w/RRVJ3hj4DHAK1Uf3ttcNXAJsCtwH/FDSW+FfC8Wmj2Ks6twLXTu4LgNmp2ov9LqLyjn/FDBjgvIR/5sE5iMiIiIiIgakJzXK8tQK+D8DywE7SVoCwPaNXQHgBamUNgcAh9u+eiiNH7vuolZl3w+8XdK7Wz8+JamzC/13wNzAy4fVyLHK9tPAqVTe+KeAt0h6a1ewcQJwKZUX+zHgUkmzJ498jGU9E1NTS5qu80NL7XQksK+kz3UmrSRNA7yB2pXyVttHDrLNEVOipLKJiIiIiIgYkK6g/BpUOoATqBW/r6GC73tL2tL2b9p5S1EpA14H7GR733Y8BSoHpAXgTweeBo4AtgS+CtzcdjNMDcwE3AuMS9/018R+v62PftB+PBLYHvgKcGd7fYKkX1Ir6+ey/cAg2xwxmvRMEK8CrAUsLOk24DRqoms3arLxZEnLAbdSn3MbAVu23Sr5Lor4H6X4a0RERERExABJmh/4MXA6sJvtf7a0KO+nioheDWxj+9eSFgCWBe6wfX67Prmw+6AnWDUemN72w12vzwB8ggrO/5oKXt0MLAbsCmxt+4CBN3wM6emj11GBwpls/7odG0dNcB0OnANsYfuOSbxX7qMY0yStThUW/x61M+gdwELAr6jdXLNRKaI2Bl5GTT4ebXu/oTQ4YgqUwHxERERERMQASXo9laP3K7aPbsdk25I+DxwPnAvsavuqnmBkVif2wURWkK4BLA78Bjjf9lHttemp4PxBVNqaK6hV2T+xfUTve0V/SFoN+BowPyDgD8BWwC9tP9l2pBwB/BDYyvbtQ2vsGCDpFbbvG3Y74qVrKdLOA04C9rf9SDv+APBH4NO272zH5gYmAOO7jmViK2IEJMd8REREREREn/QWmGymB56lVvsiaequQO5PgNuAFamCsLO0gH1vcb4YQT0pho4DHgC2A+YBdpC0SzvvceBM4MvAg8A9VOC3E5SfOn3UX5I+TfXRhVQ/bA+Mp3abrNzule8A6wGfAo5sRZajDyTtBJwo6Q3Dbkv8Rzo7Ts7vCsqfSdVh+JLtOyXNJ2l623e3gsp/becpQfmIkZHAfERERETEZKYTZGppG2IU6wr4Lth17DrgR8A2kua1/UzPZddThSqXowKPCcgPgKT3A7sAu9v+InA+sCCVW369FoDE9qNUmpSvAP8P+Iak17RgVW9fxghRmR3YFDgG+Lrtk1r6oI8ANwB7A69u+a+/B2wAnG37n8Nq9xgwHfAuYLsE50evznhB0rTt0CxUepr72vFzqbRcK9i+VtLiVC2N13Xeo/M9lO+jiJGTgXxERERExGRE0rbA9yXN1QoaZkw/yklaFLhR0lZdh/ehVlxfLOkdkqaRNCOwPPB64CJq9fzykqZNP/eXpGmoHP8X295H0sJU/vgTgA8DdwPbStoRoAV6TwPWpYLC3wJmHULTx4wWDJxA5cB+wPZjXTtJ7qIC9rMAW7djTwDH2j4MJrl7Jf5LXb/7rakJkeWp3SVvGmrD4jmS3iZpMUnj23jhs8Ca7fvkDmpSZQVJ5wBv4fmg/DRUbZNFhtf6sWVSn0/53JryZXAXERERETF5eQ3wJuCABOcnGw8Ax1KpabZox66mcmTfA1wGXEoVhD2MCibeSD2v3Wf7yaQN6C/bT1O5lr/X8sifAJwF7Gj7Jmrl6OPAOpL2b9c8CXwX2AK41faDQ2n8FGoSAanpqOD8LO3ncZ3PP9vXUrmx5+mc3L2yN6t8R56kqQFs7w6cDLyXWjm/0FAbFp0C1p+jPqMWl7Q+cArwDHU7/JoqknwgsDSwou3rJM0MfJaa4Pq27T8O5R8whvTUOHmDpHdLWkrSdPncmvJNPewGRERERETEv9d5cLP9ZUmPUA/Oh0jayPY9KcQ2Okys8Kft21qO8qeAfdo5+0o6G7gcWIcqNPoocIDt0yS9l1rBeOCA/wlTvEkVZ7X9J+BPkt4MvBLYzfYD7eVZqf65Hbiu65qnJR1j+8gXe+/4z/QEqhajfv+/sf03SScDm0n6se1zuq6ZEfgHVYw3fdFn7Xf7jKS1qQDwTFT9jFWpCZOd2gRjDIHtpyQdRu3oOQOYkyo4flzXaQdTk11rUSvpPwG8Avg0sG8KWg9G12fdmsAewGzUeOEOSRsCv271TWIKlJU1EREREYGkHSW9Z9jtiBfXWZ0I7E4VPlwcOFDSK7JyfnToesCeo3vFr+07gG9QK+L3lrR5m2i51/YetlexvTpwditueQJwhe292vtlO/sI6An4LiDpLZLe3/P7nYXamTJtO29aYG5qRfDyto/vvBeA7Wc7FyZ4NTK6+mh14PtUEdfXt5e/A/wKOEXS51oaqFe2c5YALu5+j+gfSR8DjqR2+2xGfScdCqwCfD0r54fL9q3U59Zc1M6tW7vGEbSJk+2BbYF3UhP+UwObtF0QtEn/3Et90P29I+kDwCFUWrRPUzVMHgF+AHyi9/yYcij3V0RERMTYJul11EP17FTQ6ddDblK8iLY68aPAm6k+m53aqr6p7Xuzcn74JC1L9cmnqZzl7nptXmpF3KrABraPasfHAeOBlYCNgT/ZXqvzWvp0ZElaA9iOWkU6LfA7YC/qs9DA6cC7gaOBaYAvANvYPqRdnxWkfSbpU8CJwE7AmS2lUOe1DwJbUgWSb6HSc7wC2K8TUIz+aQHCaaj7Yz7g47Yf6np9FyrgexqQlfMD1DP5OI6asHpD++/0VGHxC1uB5O7rZgQEPN6ZbMx3z2BIei2wADUxsoXtf7Tjr6DS4C0BvMv2LfnumfIkMB8RERExxrUHtyWBb1IrEj9m+/LhtiomRtJKVKBjG+BKKiC1N/BBqlDoxgnOD15PIGRuanX1CVRqh7WBS3qC8x8AzqMCWzt0BxLbyt/X2P5N+zl9OcJauoZTgN2ogPzd1ErFBYD1bJ/e+mhd6t66CzjO9v5DavKYI2kOaqX8TVT6jU6gaqquoOE8wFJU0dE/Ab/tpLbJfTMYLR3XXLaXaD+P7wR8JZ1BFRD9MbCr7d8Nr6VjQ8930TLA/MBltm9sizDOA2akgvMXtFRc46i6DA87dTIGTtKS1A6gB4Hv2d6g5/WFqfHd+bbXGUITo8+y1TUiIiJiDGtBjgm2fwVsDtwAnC5p8SE3LXqoCrl9gspJfpztn9u+w/ZngW8DK1MFYZPWZsC6AiHrA0dRuchXox60TwLe09MfD1H9+G1qq3r3e/2tKyivBBdHjsoswBeBY4BDbP/Q9hXA/VQh3usBbP+EmlR5K7WTaP/2HrmvRpikhSVN1XP4ZVSNhSs6QXl4Ydog4C7b37G9hu1dE5QfHEnjWp/9BXitpCXa59VTXalSbqcmH1cGXj2sto4lPbnKO7t+XtFeux1YAfgnVbvkQ5JmpXZpXUTtfIjBe5QaC4wHXtnuLXU+E9tukz8C8w6vidFPGVRERMRkL/n2Iv477SG6s/LwI1QgcRz1AP09SUsMs33xL54FXks9ez8EzwXrsb0JFehdGThK0isTmOq/nvyw/0ftZLgCuNP276mCevdQ6TiW7QpYvZMqUPlV2wdP6v2zXX1ktd+nqYDvvbb/DiDpfCo11Gds3yBpKUlz2X7c9p2tPkAmSvpA0jrUhPDyPcH5TlqNmSZx3duAtVr+/xdIH42siY2z24T+s8ARVB99lRY4tP1M+256htp18g7bFwyuxWObpBWBw4E9qTRCl7TjajnnO8H5M4CzqMnj02xfNZwWj21trLAP1R8fo1LZuGt8Pi3wGPCYpGnz3DvlSWA+IiImOz2BkKlsO4OUiP9c18qq1YAfUoHfE6iVVKaKUC45vBZGR1sB+ixwFbBAZ9KkrU6cpp12FfAw8F7g7cNp6djSdQ+9gwp2/AE41vbj7fXrqVXXdwHfo4pVHkelH7rM9t1DafgY1DVOeDlV3PDhdvx84E3ACravlfRqYGcqPcoLZKKkL34O/JTawfCRruD8H4G/Ap9uaW2eI2k6apXve4GZB9jWMacnNcpykraWdJykdSQtZPsGYAMqoHi0pDXauGGjdvxJ29e06xN/6jNJ01OLLH4EnNAzqWgA27cBS1Np8W6lUuBt085LH/VJz/PrjJJml/QyANvXAvtRK+e/IWn3tpNoYWANKqXaD20/me+hKU9yzEdExGRL0oZUYb3lbD897PZETI4kzQlc3P5sbvuJdvz91AqeVwMrdlJrRP91P0BP5LUPAecCJwN7uhVDbCuq9qNWnl6VGgH9I+mdnd9ve9BemMr3fx/wO9sfa69158KeBdgXeBe1UvEE24d13iMP2v3VdgQtDXy9reY9hho//I6qB/Ap21e3Sa41ga8Am7R0NtFnkuajUkC9ndplcmGbdFyBClT9BNje9vWqYogrUJ9329g+YkjNHlNURccPBn4PzAFMR62IX9X25ZKWoyZXZqdScvwT2Mf2XkNq8pjUvmuuBX5ge7NJnPMK2/e1v0/XNe5LCqg+6Zng+iSwDrAIVd/kCmDDttDsTcBWwOeBB4DfUpOPZ9nes/e9YsqQ2bCIiJhs9Kw0WALYEvgFk9jmHBEvyVRU8P0W2090pdr4BfANYC5qlW9Wzg9Az8Pb+yVtKWl/SetLmsn2hcCmVPBwX0mflPRmamXi54E/dwWNM9YfYe2B+jJJX4ZaQW37D8Ae1L3yQUlLtdee7Xxv2X7Y9rpUkeXluoLy4/KA3V9tBfa6wKpUKiiA71BFRZeggvVXt5XyXwAOoHY9JCg/ILb/AqxPBaG+BXyovfQTqvbJe4BLJV0DnE/10T6doHx2TfaXpKWpXT7bAivZXgBYD3gdsLekGWxfBCwOfBRYBfhwJyif76L+mMT/99MDTwCzSRrfe46kNwLrSXoVQCco3/6eoHyfdI3rPk8VHn+Q2qF6H7Wr7peSZm277L4JHEc9315je6muoHzGDFOgrJiPiIjJjiqP75LAx4Ev2X5wyE2KmGy1bc+3AmfY/nI7Nk1nF4qkK4B30PKbJ/XGYLTViYdQK3pfQ6XeeARYua0aXZXa0fBK4On2Z8/Ow1v0h6TXA1tTW8s37QTY22ubUJNZPwG2tX1d12v/shIxq976Y2K/V0mvpO6lM2yv3459HtiQCs5fDMzW/hzeFVBMHw1QG98dASwKrGX77BbUnR/YDJgT+BNVEPasdk1W+faZpI2oya2V2iQKks6l+uXztq+SNIvthydybfqnzyQtAtze+f1LOpKaiPyI7cu6zhtPTewvD3yh05cxGJLmBX5M7QLa2/ajLZXNitQOoOtsL9fOfQtVt+HzwFdsH5jvoylXAvMRETFZaVv8fgf8HTjf9mrteAYrES/i36RH+QbwJSp1w7e6js9J5SD9PrWi/pxBtHWsk/Q+qgjY7sCptu+WtDxwDtUfa9t+XNICVBqOVwB/tf3rdn0CIX0k6bXUjq2NgHVtH9v12teoArA/o4ruXTfxd4l+k7Q4cHXnXmjp7/YENrD97XZsfuADVAqVG4Df2764vZb7qA/+zXeRqGBvJzi/JvCjSaUrTB8NhqouxnvbSnkknUel4ejUZXgXlV5oT9v/GGJTx5y2Av73VGB3N9t/b2ODU6mJ+82oiceZqD7aA9jB9oHDafHY0/nMk/RW4HKqyPhZnc8vSTNSux73Bj5n+7vtujdQ44nPU6m89hjWvyH6a+p/f0pERMSocjuwI7Ad8FZJC9q+KUH5iEnrSY/yZmrV4SuAH7cdJ8cBSwE7S3qZ7YPaCtNl23mX2b6yXZ9ASP8tQX3Wndm1Q2FjaqXoPi0oP5Xtm4Gbuy9M//RHCxiq/W5nA66jClMeLWmC7eMBbO/dzt0aeFbSbq6ibjFAkj4KnA38RtL2wNVU+prPUMVEL7V9u+1bgFsmcn3uoz7o+S76IPBOalLkLOp75iZJt1BBqiOotDZrSrpwYsH59FF/dfXXdcCHVUWud6KC8iu2oPzLqB2scwLTAgnMD9btVLD9q8BTkvawfXPbwbU7NZn/IPA41T97dILyWdTUX127T6el0gtN1/4+ddc549rK+eOo/vq/zmu2/yBpT6puw5sG2vgYqKyYj4iIUWtSA0ZJs1G5LXen8ozuZvuhQbcvYnIjaU1gF2BG6gHhH8CuwPHAm6n8sSsAd1JF3V4D7G57t6E0eIzpWlV1BjCf7UXb8d7Vie8HlgN2dCsuGoMh6YvA14E/AE8B7wdmAL7sriKUkrYEdgZ+SRVHfGAIzR2z2srEn1OfdZcDfwH2ooKHP6HSb5wqaWpXMdgE4gdI0hpUHuVrqTRpi7S/b+fK999ZOX8IVbR3DdtnDqu9Y0HPpMlU3d8tbffJJVTKtIeoFCk3tNQoq1L31la2TxpC08eMF3kumomqxfB1KsXdzrYfb6+tSdUCuAf4g+1L2vF85vWBpMWAJf18HZkv0dIKUd9HP6LG12u1e6gz7pub+q7ax/ah3f0j6VW272p/z2TKFCgr5iMiYlTqeUB4NfWdNZPt620/KOlAKrC4A/CMpL0SnI+YNEkrAofzfLDwdiqtwyHABNtHSNoMOBb4NLUa+Le2T2vX52FghPX+Trv+fjmwVAsu7koFrT7WgvKzUIUR5wZeDiTgOyCS3gnsT01unWj73pbC4UvAYa07jwSwvU/bnv63BOX7axKfTX+mJu7np3aVzAtcSa0q/RXwDUmX2L4TsvJ6kCR9jEq7saftb7aA1B1ULZP9JW1q+5q2cn5j4GRq51b0UdeY+yPAcm1y5HvAtbavbAHebwPXAwtLmoPaVbcFtQr7pHZ9xgojqPVDp9B4p49eC9zfCb7b/qek/dolXwcmSNrH9kO2T5jIeyYo3weqQuNvAnaRtCg11j4E+Jrtx4DHJH2L6qPd2o66q9uukw9TY7o/Qn0nde6lBOWnfAnMR0TEqNQ1+FyNWgUyH/C0pF9SA5rrqaDiBJ4fhO6d4HzEC6kK540HVqO2NB/VuU8kzUClcbgUwPZtwG1ULvMXvEce4kZeTyDkdZ2gLlVHY1qqSNiTwDK2/yxpGmAlYHVqdWICvoM1L2DgZ7bvBbB9maQHgTmAwyU91glQ2d6pc2EeqPun6z5aDljA9hEtUHUpVVTvImqC6xIqDccT1G6gnSRtaPvJ4bR87GnB3NWBI1pQ/q3U98+x1K6GXYEDJW3SJiL/DPw/T6SoaIw8SZ+jdtDdCCxE5bY+VNL+tk+T9ASVB/tQavXvdcDWtg9t12esMPLmtv23zi4GSctQY7QNJJ3RE5w/AJiVSqX2D0lHTWyckD7qj9Y/FwBvoCYV1wQ2tn1YJ62NK1XkrMD6wI8lXULl/18S2Mv2RV3v5573zxhiCjVu2A2IiIiYFEmfoXJf/wjYqv1ZlAouLtkepvejAvNbUSsUxg+puRGjUnsAewZ4K/CPrqD8+cBiwCq2fy9pGUkLtdc0kfeIEaYyE3AgsJ2kLwDYvoAKUM0B3ATM21Zrfw04DDjU9ilDavZYNjswM9BZvTYewPaNQCeFwwmSvtJ7YR6o+6frPtqTGgecL2m+FuA4hbpnXuuqA7A8VVj5AeDKBOUHy/b91I6Fn0maixrPnU4VHv8G8F0qQHW4pHe21aIPw79+L8XIkTSVpGmplBtbUwWRZ6F2mWwIbCtpFttnUem7lgIWB1ZKUL5/JG0K/FXSW1vQV9RkyO+pCZKPS5q+c77tR6jPvL9T6T63bxP6MQBtAv5eKi3XtFSarqUAbD8tabr2952p++oUauHZncCXbO/e3idx2jEmK+YjImLU0PPV6UXlgd2EShuwVxtsImldKlh1Pzy3QuRgauXOXbafGk7rx4YXW/WZFaGjQ28/tIeyzgOC2rHzqJzyK9i+TtIrgK8Al0na18lbPhCtn/6pSjP0beBrqpzXR9k+QNLTwLrAD6jcvn+iVsofAgmEDMG5VPHxfagc5U/p+eJut1FBrNuoey0GpOc+Wo6qlXGlpIOogq8LA/tKWtf29ZJ2Bw7rpLGJwehKy7B/+3nV9tJBtO8mKoXa36kURK/uvj7ji5HVPVZoQV+osfQv2wQKkj5OTZ58sf28h+2/TeK98l008v5MBeJ/JmlZ29cAD7Zddt8HDgaQdFZLlQLwGPAbKiXKLZ5I0eQYWV2fbW7PsLdTY7e3A2tIOtH2GrafkDSt7SddNTPOlDSj7Ue73ivjujEogfmIiBg6Se+w/Rt35dNrqwUWBo7vCsqfR20/X9H2nyQtZvsq2w9L2jGDz/7qfoiTtDCV83Uq4E7bN3cGpC20kqoAACAASURBVHl4Hq6uPnqX7cvaffG0pJOB3SW9lypW2SkkOg2V7mFh4MgE5ftnIpMmAqayfWMLUn0P+IokWnD+UElnU9ucJwAPd4IieXgbivuAb1EP2t+0vUVbBTcNlR/7r8CmbvlgY3Da/fA34CRJp1O7UD4HrE2tLp0BeCfwoxYEebTrutxHAzCRscGCVAqvawDaiu3xwHbAr2zfMOAmjildY4UVgU9Qu0hmAx5sx6drgcRPUbsa1gCmkrRrZ1ze+14xsmyfo0oftAtwSRvX/c72Q5I+Qe3+OQgYL+l7wONUseSngF06EyzRPz3PRh+gdnZ/y5Xm7hxq7LZWV3D+yTb2ex9wQ1th/5x8H41N2SIRERFD1VI3XNFWwtMVlJ8NeBlVEKyTduPNVFD+WknzUXkvV27XJSjfZ10DzzWBn1BBxJ8C50rauvucGK42cXKppHO7Dv8IuJAKhpzQ7qMFqFU9BwFH2z5v8K0dO7ruoWU7aRqAZ9sq+ZuAT1E5zLeV9MV2ze22b3ClS7m7XZ/ViQPWfuePUgHfn1AP2j+XtDOVb3kv4CJ3FWkbXmvHns790PrpCdvrU0UpL6LS1ywDbNSbIiD30VD9DHhS0kmqIsobUBMp93eC8knp0F9tQvj7VIHxVamUd1sAdK3ufYb6broa2Iwai0cfqUzVfvwztaNuAnCxpDcC2H4QWIVKm3IMlXf+VGqn8UUJyg9G17huDaqfFml/Oqm79gROAD4m6cS2Q/XT1PPT8kNpdIw6yvNzREQMk6T3UNvOFwV2sH1UOz4tNcicm1qlOD+VC/tqVV7fLwLrUUV1Lh1K48egtq3528BuwAVUEHFj6mF6fdtHD7F50UiajcpfuTVwoe2V2/EPUffNKlSB0Zmp/PPH2N67nZNdD30kaX7gF8A9wAa2f9O1cv6Z9tD9K2or9OG2Dxtic8cMtcJ6/+acTrq1OahA1RpUgcTbgeNsH9TOyz3UBy+lj9p547oC9dMAH6YmTw6yvW+fmzmmvdQ+aue+jKoPtB6Vz/wfwD629+pjE6NpAcIDgWuAQ4DXUoH39YFv2t6ynTdtW+U7NVWI99xJvWeMrDZBvzGVym4q4G3UffK+zk6Tdt4+1K6tCcB3up6l8l00AG1XyfFUzbPvuidNmqqexleBL1P9NwP1WbfroNsao1MC8xERMXSSFge2B94FbGP72HZ8XWqQMyvwWdtnSZoTWAE4gArkHzikZo857aHs5Pbjl9tqHST9DHglsJrtq4bVvrFqYulR2s6TWamAx27AebY/3l5/JfBG6n77E5WD9NfttaR1GGETezCWtBE1cfIAsLntX7eVoeNacP77wAeBR4AP2b5+4A0fIyR92FVs9yX9/z+R+20O4Gk/X6Ay99AI+0/7aBLvMYefz5udYNUI+2/vI0kzUsUP5wXuzXfRYEj6JFVk923A9ravaMfnoerNbALsZ/ur7fh0tp/ouj7902eSlqMWKG0FnGP7z22X8ebAPMC7bV/Xdf7UwHi3XPPpo8GQNAuVUugm4CtuBcVbqqG5qXQ1P2tj8vdT4+8bbX+vnZd+iuSYj4iI4WgrRDvpGO4Efk7luD5I0tO2T7R9dFtl8HngaEmfoXLML0AVhD2w8155yB5ZklYCfm/75q7D01M5ek/tCsqfS/XHR11FRN8HTGP7ooE3eozq2kY7r+1bW7BDrhykR7XTdpP0fduruPIw/41Kx/GcpEcZed2fTZLeDMxk+3Lbh0h6EvgasJ+kr9q+HJgg6eVU/uuNgScSlO8fSatT3y37296mrYZ/0RW/Xf05zvaE7nQBuYdG3n/TRxOToHz//Lf3UeuLR6kaAL/ver8EqkZYz3fRjDyfsuZRni+8i+3bJO3XftxclWZts+6gfDsv/dN/76B21v2AltbT9nGS7gWOpNLavNv2H9r99oykZyHfRQM2HfAG4PS2s+TN1OKxxajU4TNLWtX2aVTaqO93LsxnXXQkZ1tERAyFy4S2TfOXwMpU/uTpgUMkbdDO2w3YCDia2ur8U2Bd23vAc4OaPGSPEJUPUgPHLSTN2/Xy48Bd1OQIqqJGi1BFRK+T9CpgNWARVbqhGBBJSwC3SFoPXhD0eIjKPXoAsJKk47uuecECjdxHI6snEPI54LvA6pIWAnClfdobmJOakFxa0uxUId6lgUtsf6fzXsP4N4wBFwPnAZ+VtAeA7Wf1fG7fSZrYw3Tuob64mP+yjyYmfdQXF/Nf9NGk+iKBqpHX9V20GrWLbn+qyO6MwBckvbrr3NuBbwKHAZtIWnrwLQ7g1cCMtm9rz0vjoQrCUrtXXw5cLWnxziRYp5/zOTc4tu+hnmO/KekiapfDrMBHgCWAS4ENJU2t1DiJSUhgPiKmKAleTF7aYP9gKrflqraXoQrhXAXsoecLwl5ke3vbK9je2a1AZVYajLw2YfJj6sFtfeBrqpzYuAqAXQ98WNKV1IqrD7mKiE7F8wX2/mj7qaH8A8aIiXzWPUIV4z2obXV+rpCy7QeAfYG/Amu2B4dOf0afdAVCVgeOAk4DjrD9x07/teD8N4BpqLzzVwGHU4V4/9z7XjFyJE1j+w6q4OSvgVUl7QkvPfDbfR9m/DHy0kejX/podOv53b6XKkL5F+BZ23tS3z/rAF9SpbkDoPXpvsAyTh2ngej0VVfw9hxgJkmbAdh+SlUzA+C31C6TW6ngbwzXdtQuhluBA2wv1nZB3kmNz6+1/UyeWWNSksomIqYYPasT30itNAD4q+0bhteyeBFvpAYsZ1GpNbB9gaR/AkcAB0t63PbJ8K9FxTLAGXntIftp2ztKeoIK0D8t6TDbf6TSa7yN2qK5g+0bJb0G+CiwH/D1zsRJ9EfPZ92rbf+19cO2wBNUSgFsH9d1j7yc2gp9OvDH4bR87GnfRbsBe1APa4+1l+aVNIvta2wfK+lq6p6ak3qAO7ddn8nHPmj30NPtx/HUat9FgfUlPdEmgJ99sXQcPffhqsB4SSdlEmVkpI9Gv/TR6Nf1u12ASrlxBHCsK4UQtrdpkyfb1mk62Pbd7bVbqUBjvov6pPv/f2BaagzX+flPwCXAFyXdb/tk20+34Pwb2mt7275t4A2PF7D9J2qXcXfh8ZmBjwGLAycNs30x+mXFfERMMboGn2sCFwEnAmcDP5O0+TDbFpM0IxWIurut7p0GoK3O2Zd60DtC0ibt+H+UUzb+M90P2W03w8XAg8DawEaSFnTlGf04cCWwmaQ7qfttK2Bn2/t23msI/4QpXk8Q4xPAmapCorjqAewCnAIcJWl9SdNImpYq8nY3sL/tIzvvNZR/xNjyOmohzDG2H5M0q6RTgB9TW9B/AGD7t7aPsb1HgvL913UPrUWtPPw4cDPwLPBVSbu18ya64rfnPtwE+DbwSIKJIyd9NPqljyYPkpaiVld/F5jK9qNdq7Kx/TVqzL0lNa57Ve975LuoP7r+//8YcKyk06g+mKXtmtuFqgGwq6QDJH0a2JHqqys6QfmM50aHrqD8+6g+OhQ42PZ3h9qwGPWyYj4ipiiSVqRyIu5BbQGcGvgCsK+kB2yfMMz2RekKOF1FrZjfVtJuth9XFZp6Bvg7cHv78/gQmztm9ExuHUyl3jiP2n2yITBO0n62/yzpnVRdgPmBW4A7bV/Rrk9AsU96AiEHUavf7ux6/WZJuwBPUZ+FqwP/AN4D7OTanv6C94qR0RNk6twD9wOzUZ9x91CTXOOo+2smYBdJ69g+pvf9cg/1l6TFqTRqu1Mphh6SNB+VSmgdSRNs79i74rennzemcjGvZ/sHQ/qnTLHSR6Nf+miy8ChwAfBeYA6o75fu/rD9NVXdma8BP6TqCcUAqPL+H0vlKZ8HWBb4kKTVbV/SxnsbAGtQu1bvAna0fWLnPTKeG4yX8nwjaR6q3tbbgG1sH/FSr42xS7mHI2JK0FYKjKNWigr4ku0H22sXAfMCn7L926E1cozqefiaCXiiBd5pK3lPA95BpXs4vgXnxwNfpoK+38w2zcGRtAi1Av4I6nf/SNvJsAu1Kv5w4CBXWpuJXa88IPSXpGWB71CBkONs/6Mdf7ntv7e/z0AF5demVsqf68pnnj7qg57PuaWAmamJxyeAzYFNqJWk1wEb2n5G0puA84FNbZ85nJaPXS0YcjDwbtt/6ASpVEUQf0g9VO9qe+eua3qDiQcA609sYiX+d+mj0S99NHloY7sdgE9Sk/S7tOMvSDMk6d22fzmkZo5Jkr4PXA4c2nYz7Ah8kUoj9Anb90uasZ0+D/Bo10r5BHv7pOdz6k3AjX6JO7clLUTFWm9sP6ef4kVlxXxETBFsuwV5lwBO6wrKnwssBHzU9nWSPgQ8afvnQ2zumNI1qFmFChTO2frlPNvXSPoclTJle+Ajks6ncieuA2zevU0zwcSBeBUVVPy57UcAXOlttpH0MmA94ElJR9i+qffi9NFAvIMq3naS7X+0FAF7AG9rk5SHA2fZPlLSt4Cnu7bX5uFghPU8vH0e2As4l6pvcr2kb1DFX6eyfVc7b3oqp/zTwD3DafmY9yRVe2G69vMEVY2Nv6rSapwPrCtpNtubTiSYuD8JJvZb+mj0Sx+NEj2/2+mB6YF/As/Y/p1aaiFgc0nPuFKnvWAnQycon7FC/0n6LPBOYAJwsVvef6og7+PU6vgzJK3cea4Fbui6Xumj/um6l9YGNqMWWLxo/KBzD3YvXko/xUuRHPMRMVlqwacXcBXVuxeYr51zNrAIsEILys8NfApYuq3IjgFpwfdTqJzxBrYG9pP0vjYQfR9VlPJ1VAHRDwDb2T688x4J+A7MBCo/7GydA217M1Rw8R9UWpttVIWNoo96P+vaz/MAswLzSfoM8BtgTWpl/ELUSvpZ2iVPdQXl83Awgjp90/XwthpwNHAglVP0+vb6U7bv6QrKv5HayXAYcKTty4bR/uB2KpXaFyTN2R6mO4UsX0alf/gLlTu7u583I8HEQUkfjX7po1GgJyj/SeAHwPXAr4ADJU1v+zpqEv9CYGtJW8PE6zdlrNBfbVfjB6jg+3uoek5IGm/7SereOBh4LXC2pNl73yPPRf3RPe5uv/etqGfYq//dtV33oLqPTSxuEdEtgfmImOz0DD6XkvR+STO0L73LgXdL+i21fXY529e2FaUfowLA19h+amj/gLHpHcDXgVVtLw18lcpbvlcLzj8GfIWqXL8wsIzt/aBW7QypzWPCRAaLV1H5/b/QCby7pR5qrqEKiP3OLYVK9EfPZ91Ckl7Xft6XCrz/knrIvhN4o+01gXWpCa654IUPbnmIG1ndv09VTuUtgT2pVE+/b8ffL2lZSW9tP7+H6rMtqByxe7fjeWjrg54H7Jklvbzzs+1fA8dTuXvXkvSadt701OTXD4GVbX+rHe98Fy1Gpcs7diD/iClc+mj0Sx+Nfj27tk6hAr3HAA9Ru1UvlzSj7WuoyftzgZ0l7TqkJo9p7blnH2oifw5go3b8qbbj5BkqOH808BZgmSE1dczpupc+SqV+uonajf+Snnl6xu5rSlo84+/4d5JjPiImW5LWoAaX1wBb2b5B0mzUNrM3AXvZ3lbSvMCHqByWO9red0hNHnMkrUStrp6Ryml5YddrawPbAA8AW9q+dCLXJ31NH/QMGjvFdrtfXwk4lQrAf932bapUUWsDnwY+6IkUcIuR09NHn6XylF9F9cc9kl4BvAu4288X3Z2OCviuBKxk+6/Daf2UTdLBVLHjb3QdW5CaKFnP9pmS5qe+c5agVo3+Dfhs++9ywO22f9KuTcqAPpP0aWB9akfdOcAPbP+0vXYCFbj6VfszB/AZatdWZ4L4BbsjYuSlj0a/9NHoIml14CrbN7Sf5wV+Qo3f9nTlK58OWAvYlVpB//9sP6nKOf8NKu3dEUNo/pjxYuNkVS7yTamJrd1s79iOT2P7aVWNp0Vs/9vV2jFyVDUyLgBeD/wJeLurNtCLjtd6xu4bUxMvq9o+bRDtjslXAvMRMVlq2zRPBralcpXf2PkylDQHcDa1alTUNloBR3WvTsyDQX+p0p/sTVWmn5oqDHZj2077eDtnbWqV6WPAFk7u/77rGTQuTwXa5wPuBza2fZdqi+3a1OrfvwF/oHJhrwjs0LmPov/aBORh1Cr5821foZ5ibe28uYCPUqmgdrB98OBbO+VTpUTbAzih+/NKlZ7mW9R9dC/P543dnApQ7dmu2b7zwN2uy3dRn0n6FHACcB5VjHdlKkC1b+dhWdLXqLQCb6XSbpxq+6DhtHjsSR+Nfumj0UXS0cAngKXc8llLWhS4lNqh8CM9X4h3Oiodx1ZUkPCsdv5sfj53efRBz5j7ndTCsbmBW4DvtOfW/6MWVfQG58e7a4d3JvEHqy2K2ZBaBPMx2+f+m0mWiRW1Xi+7guKlSGA+IiYrbbXNbMAZVAGcr9n+Z9drU7cVBi+jAiOLAjcCd7XtthnYDFDbwfDV9ucS2x9ox6d15VBE0jrUzoeNs6JgcCStCRxErXq7hcpR/iCwme2L2zlvp4ryvgZ4GDjD9pHttQQU+0zS4tQk477A4W3rM5LmpD7rOjnLPwp8mdrufKjtvdrx9FEfSJrB9mOSPg4s1vUQ/SVqtwLAlcD27aF7OuAy4HTbew6n1WOTKh3XhtTk/AG2H5f0buAk6jNtb9untnNnAGYAJvj5AvIZL/RZ+mj0Sx+NLm1X45HAarYvkjSv7VslLUbVnFmtqz+mbit9p6NqBO1ie9ee98tYoc/aQqT9qHoMrwSmosYJq7gKJb+eSum5AW3H99AaO8b8m2D7KtRuk7mAT9j++cTOn0RQPvUz4iVL3t6ImKy0L72pqPzxN3eC8p3XOqsQbT9i+0Lbe9n+QVdQPsUP+6CzPblXeyjbF/gmsLik09vxJ9UK8LZByzIJyg+OpP8H7EU9oK0GnAa8HPg/4ERJy7SHud8CqwJLUSuwOkH5cXmIG1mSNpH02p7D81MPcce1QPD0ko4FfgTcLGmbdt5jVOHXr3YF5dNHfdL6YiZgDaqA3o7t+OFU6oaP296uBeVnpnalzEWlXYsBaRNWP6ImHW9uwcRxtn9J7eSaBdhSlZ4D24/Zvr8rmJjxQp+lj0a/9NGoNI6a/HhU0ueAG1tg9x7gj8D6kt4MVSNIldd/DmqccG/vm2Ws0F+SPkgthNmNyhU/K7AZtXL+Qkkz2/4TFbg/hhpXvHNSz1YxcnoC6gtKerekD0h6A4Dt7wM7AbcBp6jqov1LMdeu99iIBOXjv5DAfERMjl4OTEcFo5A0dfcXpKR3SfrExC7M4HPk9QxqlpO0raQTJK0n6Q1dwfkjgGUlnQHPFTiatv39D+36fC/1WVvN9j7gTNvfbA9vvwS+Q9VieBw4nCqiPI3tp9tDded+y0P2CFNtP9+K2g3U6/XAByVtQuWYX45KJXASsLukJW3/jNpx8t32flmd2GdtUngHqg7DZpJ2asf/DjwFIOkt1Oq3g4FDbJ8/nNaOWYtSabpeSdUyAZiq3R+/ooKKMwE7Slqt9+KMFwYifTT6pY9Gn/uAW6n0ad+iVlrfYvtOKqf1e6ng7pLt/JmBZal++vOA2xr1u/8zVZT3VtuPUkVdN6Puq+MAbN9MpQD9gO3Lc+/0V8/z6xpUfYYLgB8DP5a0O4Dt06nFTPcC35K0zMT6pgXlD6LS1yQoH/+RBEAiYnJ0G/AzYPsW+H2G2l5LW4W9PLVaZM4htnHM6BrUrA38EPgYtcJ6R+BHbXXBA1SO5aOogO8P27VP9rxXgon99xRwOXCcpFmoB4UfULmwf0P14ULAsdTKHuD5fs6DQl9cC7zN9rVttc587fgFVAD+O1TO/6uB19veDjieCpJMB7VKsfNmuY8Gw1Vwb3eqnzaRtEM7PqGlFDiMClpt75bCJpOP/df5HbvSNexN1Tg5QNLCbVeduoKKa1OBkdwzA5Q+Gv3SR6NPZxGS7UuoccP8wF3AjW51Z1yFXLcBVgHOknQO8D3gUKoewEXDaPtYJamzy3uC7bvbauupbT9BjR3OBhZT1QnC9s1tsUXGC33Sdjx2P7+uRD2fHgV8hJpIuQLYRtKh7dzTqR0P/wTOkfSqnkWBcwFLAus4OeXjv5Ac8xExKvXMYk8DjAee8vMF89YCdqYGpBvZvkrSK6nih/sA27TBaQyApKWBM6k8fKfZvlvSh6mVvZcBH7b9T0kvp3KWbw6sYPu8oTV6DOi+j3qOT2f7CUnLUdtmV2vb0jurRr5E7Uz5ZlZ9DI6kV1Gr4C4B1rJ9Rzu+CPAP27e2n8cDa1G1Gz5p+7phtDeKpIWpicgPA/u3QBaSVgDus31F+zk7GfpgUp9zXa9vCWxC1ZvZyPYfW7DEbRJlbtt3D6q9Y1H6aPRLH41uPc9Fb6ECur8CFqcm6be0/Yuu81emCvG+m0qj9lPbJ7XX8l3UBz19NB54ugXit6N22H3E9s9aQHecqzDv+lQKmzfb/svwWj82SNoHuB04wlWTbjy1+GVq6lnoH+28eaidKF8CNu3EFCR9huq7Uyfy3nPYvn9A/5SYwiQwHxGjTs/AZmXgk1Qh10uAH9s+pb32VWB94LXUypHpgVcB+9neo/e9on8kbUj1xUq2b2nHzqVW86xm+2pJs9h+WFUQdmHblw2xyVO8nvvoVcAMbZts9zlrUqt6l3cVNJqGWgE8HtihM0CNwZA0NbXK7VBq98KXbN/Wc84CVCqiA4Edbe838IbGv+gKzi8HHGV7+57X813UBz2fc4sBC1P5/H9k+/qu87amCiTfBHzZ9k2SpmqBEbXgSYJVfZA+Gv3SR5MPSetRtUx2t/3TtphiR+BBqs7ML3rOn9Zdu1PTP/3Rcw99lJoQOdv2ryQtS6WruQnY1vaV7bxpqd3E7wY+mqBuf0naiwq2f8D2pe3Yy6gYwgW2v9R2Kbh9li0EnAtcaXvVibzfuDYpmfFd/M8SmI+IUUvS6sAh1BbMm4GPAwsCO9s+sJ3zPuBdPL8i5HLb57TXMvgcEEnHAMvanr/9fB6wCLUq/lpJSwErAnvbfqjruvRRn7X7aBeq8NdN1Jb0c2w/KmlB4Epq1dUF1IqR7ah85Z2VVRlwDlBbgfhx6iHuUmDDTnBe0nuoLepvBA61vU87nj4aBdpD3G7AJ4B3uhUdj/5rwamdgGepOhkLAl+gPuseaedsDawH3EFNet0wnNaOTemj0S99NPr0BHxnBy6kpabp6pM1qRXZLwjOZ4w9eKod3ftSecoP7+qLTag+uoPa2X0PleJmN2Br2wcNpcFjhKR5qRzyB9s+oC38+53tmyVdCMwJLGf7/s5kY7vuW8DSwFtdtQEi+iJ5qyJiVJL0AWoVwS62v0gVN3oz8DCws6RNAWz/3PaetlewvX2C8v3Vtl92/t79HXIdML2kJdtK+UWAFVtQfmZgJSr/6NTd75c+6i9J7wX2B74PfB14hsqhuI6kl9u+CVgZeCuVhmhzahXWSZ33SMB3sNrDwA+pYMjSwKFtSy1U//2YSiPQCcqPSx+NDrb/SAW1PpKg/OBI+iS1y+RI4C3AFtSun6OAz+v5fLJ7UbUz3k7V0YgBSR+Nfumj0akrKP9Bqpj4P4HTbT/SGZPbPoEaw80G7CVpmXY8Y+wBan10EPX8ulH37oUWeN+KqvN0CrUYZmPg652gfPczVoy4x4EngGUkfRk4A1iivXYJ8HpgPUmzdgXlZ6LSel7dro/om6yYj4hRoWdFyDRUcGNm25tIeiNVrPJk4FTgYOqhYQPbR7Vrnpvdjv5rKw3mAk60/Zikt1OreydQK3aWt31926b5Gaqa/VbdAd8Yeb0rpyV9gkp7srmrSDKSfkqlhtoeOM723yW9BngZ9Qz4h3ZeJreGqGfl/C+otAF3SprGz9faSB/10f/6vZL+6b+2Cu5Y4Je2d2zjhSuoycipqFR4GwPf7Vpdupjtq4bT4rEnfTT6pY9GN1U6wp8CswN32n57O/5cjv/28+pUOsLHqF2sdw2pyWNKV0qTg6kdjavavq+9JmCqrjH4HMA81H3197ZAJuOFPmuLyb5GTTjOBmzXJhk7r59PPS8dQ02sTA8sQ8UcNrZ93KDbHGPL1P/+lIiI/usKyi8C/InK6TZzW219AlVYdBtXjvJ9gBOB/SXN3lbMJyjfRxNJlbEnMCPwrKRTbf+2PRB8B7gbeEMbfC5LrcLeI6lR+qtncmsBapJkCWCC7Wckjbf9lO1lJf2E2j47QdIJtu+cyHvlAWGI/j979x1mV1m9ffy7UmihSosiRToIEkUFpAYFERQSaSJVyg/pTUCqICV0QkKTXqKEGnoTJYiAgCIgKCqoINI7oSbkfv9Yz0n2nCSUl9Nm5v5c11yZOefscz0zT/bZe6+9nrWUNXuvIZu8XgL8KiLWlTSu8hrPUZNExMbAMhFxkqTXP8F2Xeos+/OuJe4ARkfE/MBtwGXAHsCiZPPDY4C+EfFLSW/WgokOhLSU56jzeY46lKRnIuIAcuXjchGxtaQLy3lC1OZA0sURMSPwnoPyrVP5/7888HotKF+eE7nakYiYlwzGd7mh5XPu5qqcj71K3tx6ndyPPiPpFQBJ34mIS8hz7l3JhspBriI+r7yPz+esaZwxb2YdIyK2I+snby9pbHlsEHAd2RX9xnJg3Yy8QHgcGC3p7DYNudeJ7Ea/DJlFsBLwDBngHVUy59cFTgRmA2YmG+pcIun0sr0v4JosstbokWQG/LvAWEmbludmkPRu+f5W8mL7YOCEWha2dZaSEbcxMLukM9s9np6q7sbWbMDhwO5ko7Dz9DEaIde9x2KS/tnMMVuKiEUkPRERR5H9ZjaX9L/y3LVkFtwswJclPdTGofZanqPO5znqDB8W/Cvn2CcA0wP7SLq6tg0Z15lY93oHElsoIq4H5qusaOhXyZRfGtgCOFfSE20cZq8VEduS10aLkL2AxgK7q9J0N7IE6DLAG8CTku4sj/v61ZrKGfNmry9ojgAAIABJREFU1jZ1QYzZybvU5wD3V172OWA+4KUSlO9ffh4NnCzpudaOuveKiB+Qtf5PAE4n644eQGbPKyJ+JenGiPgTMANZm/QVSS+X7X1S0wR1+9EqZHPXC8mbJhsDG0fEE5IOlPRuLTgvae2IuJ/M7nFQvkOVjLhLK3PsC+0mqPx9NwU2A2YqT50IDIiIEdXVCvXq9sO9gRMiYlFJ/2ry0HuF+v/31eNJJcixBHncqZUQmIu81tkJeNzBxObyHHU+z1FnqzuOLAvMTda4/oukf5Zz7OnJG8dHRwSSri6rtKZ4P58rtEZlP7oQuDQiTpS0TyUoPx2wKlkS6qo2DrVXU6UcTURMBDYBRkTEpOC8si/A76rb+frVWsGBeTNrm8rJ5zrkCUs/4Dp17Xr+e+Bu4MqIOIU8Sd2JrJn9XNnegaomKxdmewC/AobV5igixpDLn48C+kTEKEnPT2V7L9Nsksp+NB+wMHnSf6SyMdj1wKHALuUCrj44/7U2Dr1X+Ijst4/12VV9jT/rmieyJ8MosoneHcCpZI+MI8gSDidPLThfF0zZDTia7AngoPynVPnb9iFLp30PWBdYKLJfxt2S7iovf4NsmLxmRPwL+CoZZHxKpRmvL7Abz3PU+TxH3UPlOLINuTJYZD+nf0bEjZL2kjQmIiaQKyN/HtkL5UqfG7RPZV+4k+zVsGtEzAkcD8wFrECWITpE0h/bM0qDLr2D9iL3r02AkRGxm6SXYiq9hfxZZ63gUjZm1jZl6eWcZC3LzwMvSlqqPFdd/rc2Wad8deBp4ExJJ7Zn1L1TZK3/R4GrJO1ZHusvaXxEfIE8GR1HZpdeJOm99o2294mI5cmVJv8jm7P9pPLcomRwfggwQtLB5fFJJ5++udUcdQHbFYFBwEvAw/qYDb/q3mNSPUxrnHIsmh64lmyat5mkd8pz8wD7A3sCB5LHn9er29YF5YcDO0o6p7W/Rc8TEQeR8/JzZZ+MHwFnAo+UlyxK1or9maTzI2IA8CfgC2R92FnIG8lHt370vYPnqPN5jrqXctNkNHne9hty9eMw4EfA4ZIOL69bj1zBOiuwqm8Ed4ZyTbQj8GNy5clEsvfWLyQdX17jc+42ql3/lHO/k4Hvk82ud5H0QntHZ72VM+atx5nanU7rTOWk5KWI2JPMMFwxIvaRdGK5eOgnaYKkWyObVS5MNjR6Cpyx02LTkRdon4+IAZLeKkH5AP4D/AX4Nlmv/O/A7zw/LfUfYCSwG7B0RMxbW7kg6fGI+DnwAbBvRMwsac/q56QvEJqjErDdmsy+fguYB7ivZF9fqizRNdV9pS7ouwewZEQcIOm1Fv4aPZ4klQzEz5I3Td6pHH9eiIgzgbXIDMXxkWVtJlTnzUH5xoqImciSQp8B3oyIi8iasPuTPU1eKjftdwHOjIi3JV1ablLuTfbXeFzSmPJ+DoQ0mOeo83mOupfInjJDgZuAC1XKa0TEQmRyzDW110q6ISJmAKZ3UL5zSPp3RBxO3vxak0yYeU6lBJSvjdqvBOVrwfm9yJjoduRqh5vbOzrrrZwxbz1CRPQB+qpSJzki5lNpWmSdaSrZpCOBgeRSvwvK45My56e1rbVGCQyeBPxI0kWVx2cBRpAXDMcAj0ka0p5R9l4RMTfwUzKz96fA6aqUhYqIxYBjgV9LOqM9o+wd6j7bPk+W5DoVGAMsTu4n05FZiBeV13W5WKt7j13JfWxHudl100Q2OFxI0pfKz9NJer98fw6ZVTUrsJWkX9XmKCL2ITMad3ZQ/tOr/F3nAi4nM3cvB75L9qK5r7JvfI1cqTUDMHRq530OhDSe56jzeY66n3Ij5QHgDkk7lsduBJYFvivpoYhYGZhbpfFrZVtfF3U4z1FnqcucX1VZX96sLfq0ewBmDbIRcFJkcxUi4g7ggsgGOdahqicnkv5A1nt7Bji4LLWllpX4Ydtay5wHXAKcHRF7R8QiETGQrMG8LvA4edG3SkTMW050rEUkvUiuPDmdDBLuVJak157/J3lTxUH5JqsEO74JLEc2krpQ0hOSbiJXNrwOHBQRW5VtJtY+6+qC8rsBpwDbOyj/6X3E59IZwCIlq5RKUH4AeSPlMLLEwJERMbAEvb5ClrjZw0H5xih/174lW3Rj4L9kIHFW8savaud7ku4nm5J/tTw/tfdzMLHBPEedz3PULX0APAvMFhF9I+IGYBkmB+UHkpm9i9Zf4/q6qHkadT3jOWquTzpPlcx51YLyvna1dnFg3rq9suzvHfJEZUzJLFiQzLp2netuRNLvgX3Ikin7R8R25XFfDHQASW+SNS9/Qda1vAu4j1zpcLKkR8ieAY8Db/gEtPUkvUw2mDqTzMreMSJmrjz/OvjEsxUiYhHgQuAKYKCkFyOiXwm6/w7YF3iV/Kyr3YicOJWgfK08ynnt+U16jrq/7aoRsWtE7BQRnysv+QP5efb9iLg2IhaNiC+TNx/XIvs4/AmYg6zZDHkzebBveDVWuWDuV4KKQ4CHyFJDwyL7m7wfEf3Lyx8lm7h9tk3D7ZU8R53Pc9SZpnUOVq5b7wPWB/5IBuXXKUH5vsB3gNXIGyu+xm2iuqSwqHuu78d8j/rtHHtrsLq/8SeeJ03Z6FWeJ2sH15i3bq+cdN5MZoGMJmv4fq9kYFs3I+n3EbE3GRw5NiLulvS3do/LkrKO5e4RcT2ZWdUPuFvSbZHliIYAF6s0TrTWk/RKRBxKZl6dAMwUEceoUhLKN02aT9ITEXEiedP4axGxqLLef39gvKQ7I+InZImaYRFxj6THKoHjXXDN8oaq/G23Jht+TQBmBo6IiKFlTk4GXgB+QvbOGE9e7B0j6Z6IWIvMPFV5z+fIxm72KdUv8699Zkl6OSI2IW9ybQQ8FxFHK/ucTAesArxJ3tS3JvIcdT7PUWeru0E8CJiPPBb9R9LfJe0fEUuQwfmfAU9HxALl52OBwyRd36bh9wpljmr9Y9YBNoqI94E/Sjqvkmk9zZ52dfO8jKRHnGjWeJW/sefJujXXmLduLbo2XtuJbMw2A3AnsImkN9o5vt6u7mD3iZryRsRgYB5JlzZtgPap5qjyHrMDPyAzgB+RtEH9e9v/v5iy9vjHqvMaEXMCxwN/ljSymWPs7T7s/3o5Nh0KvAKsJ+k/JVNxfHl+MFkv9rLKNjuQK1O2d6b8p1f3ObcEGZi6ALiOrPm/HzAI2FjSLaVEwJzABsA44AlJd0fWYb4OuFzSbq3/TXquujlaCJgdGCDprspr5gKuBFYgy0PdSTZT3ho4WtIxLR52r+I56nyeo+4jIrYhb8z3AWYCniQb8h4SEfOSKx+/Q94oHg9MBM6SdHzZ3ufYDRYRw8hmx+eWn7cAzgYeBOYn96dLJO1Qnp/qdVPdfrgHsD15fvFYa36T3iUiNgfOwfNk3ZgD89ZtVT9kI5ehz0lmy69C1uO9F9hM0qvtG6UBlAydBYBTVGnQO43XTnGi6ZPP5vskc1TZJsgLihXJoPxzkn5cnnOTsE8pImaR9Gbt/39ELKasE/9J3mN6eblzU9Wd2C9AXhBMBF6T9HR5fFeyh8abwAaSnqwG5+vfKyIWB74uaVRLf5keqO4G/orA3MCWwJ6SnimPf4XMRFwR2FDSrXXvMSfZ+PUg4EGV5tY+NjVG3T60ObA3sBDwBvAUOScvlefnJFdHfhP4F3A+8FAtg9THnubwHHU+z1Fnq5ufZYHfAicBtwJ9yfkaApwvaafyuvXJY9ZLwFOS/lwe9/w0WETMDfwKWJO8SXUVcANwI9l/ZnZgF/JG/q8kbVm26xL0rZvnWo+gHeUeQU0REbMC1+B5sm7O9ZOsW6oLyo8kswoWUJbZuBLYk8wEuSQiZimvmy4iDi4BD2uiErCtfb8e2TD0LWDGj9q2cpCM8m+fEqhyTewG+jRzVFX2wz8Buzso3zgRsRzw04hYvfz/3x64JSKW+iTvUwvKe/9pnspn1hbAb4B7gIeBmyJi2/KaU8nSKbMCV0bEQsryAVH/XuX49g8H5T+diNiy3JiqBeUHAr8mL+DmrAXlASQ9QF7E/QEYHRHfLtvU5mcpMqN+TCUo38dB+cao7EObkdmJ1wKrko2sVwVujIgFy2tfJmv+/4Gs9X+Dg4nN5znqfJ6jzlaZn+WANcg+TWdI+pOk+8jyaSOBTSJi57LNtZLOlXRNJSgfnp/Gk/QisDtwOXAusAV5Q+RGSeNKosVw4OfA5jG5SfwHEdEPpgj27l5ev4ODvc0RERviebIewhnz1u3UfZheDnwZOBW4UtJ/y+MDgA3JD9oHgLOAbwM/ApaWlyi1RETMQ558rgAcJOndj7lddY4/X8s6tcZr9Bw5g7QxImI1spTJW2Swd19gD/IibsKHbVt5j+ocOXO+iSJiI+CXwInA74GB5PFmZTIze0R53U5k1vV44EvAOO8vjRdZIuBAst/M38tj0wPfIss7zU1mwN+lrmWiBpHnDasBC9bOKcpzn5X0bPnegasGK3/7C4HRkoZFxKLkTd+7gGXJC+8NJD1VXj8PsLqky9s15t7Gc9T5PEedLSKWB8aSTcMflLRplEaTyubviwDXAw9L2rR9I+1douvKuqXIoO6G5DytKunftXPqklm/M3mOcZWkzabyfrvhHkFNVRIvRwHfA54mP8c8T9Z9SfKXv7rlFxmk+i8wGOhbHovK8wPIutfPkLV9/wUs1+5x95YvcingG+Xv/7NPsF11Dvcs23+u3b9PT/zyHHX2F9no6xmyLMrwT7htdY5+BOwITNfu36knfpVjzW/IC4SZKo8PIjOv3gK+W3l8L2Cbdo+7J3+RDV2XKt9/BZihfD8DsA7wLHAHsMRUtv0qMORD3jsaPd7e+FX/dyRvEI8kyxIuSgYQzyo/71I+B8eSN0zq36tPu3+fnvjlOer8L89R9/siVzNMBJ4HFimP9a3NJXAa8D9g9naPtTd8Te2YDnwROA/4gFwRXP/8XGTwfiKwdt1zu5fttmv379bTv4Dlyueb58lf3f7LpWys40VE3/JvfSmGlYC/khlvH8CkMgC1zIO3JI0mL8p/CKws6aHWjbzXmwF4BJgFqC0d6/NhJTWmUu/tBDJg/My0trFPxXPUgWqfYWQGyKzkhfWqJYueKD5k++oc7UouyX1d0vvNHXnPFxHblYy2qpnITMS/S3q7tlRW0oNkY7d3yBvIlMdPlnRBeT+XGGqwkvk2TtLfSnbibcAZETGDckXQ7cC2wJLALyJiyer2kv4o6erae9W/f23fsk+n8hn1/YhYh+wLdJGyxMaRZFPKg8vP5wD/IVcy/D4iZq57L69eaALPUefzHHUftetZZUPKE8mg4WERsYCkD8o17Izkiq7HAZ+zNVnd+fLgiNg2ImaX9Ch5fXMFcEJE/LC6nbJXw2nAiqr0pImIb5H73Y9VGsjapzetc+US1xlJljH2PFm35sC8dbSImAl4IiJWrhw4+0bEDORF9euS3o+I/rVtNHkp2tcjYjZJz0m6WWUJurWGpBvJu9SPAgdFxBBJE8uJ5xQH2KkEfGtLy1zvrUk8R52l9jdXLmeeiZyXNYD9yQzgk6LUnJ9WcHAac7RDuUlpn0JEDAEOA6ave+pN4EVgxcj68BMqwfk7gYeAb1SPUzUO8jZeXXDpH8BN5I2R4SU4/x65wmEbsnb8aTGN3g0OVDVe9dgSERsDFwGLAe9Luj8ipiOzFf8r6YXy0gWAV8mVkvtKGtfiYfcqnqPO5znqfpQ1rmvB+X3JRpUbAGdHxKCIWAXYnCzNcbmkt9s32t6hcr68Ndn4dWNgifLcX4GfkX1pLohsqFzd9nllb4DqTfz7yRWSvi5qkLrrmq9ExA8j4v/KjUgk/QU4hOyp4Xmybqtfuwdg9hEWI++CPlJ5bKKkdyPij8CQEnx/PSKmq2WElszSXcm7oQ+3fNS9SN0Bsz8ZtHqrxA5vLtcOPwPOLC+9phb4rWw3rYCv72I3gOeo89X9fb8HrAtcV26e/DEiJpAnnidGxN6Sfldeuw4wj6SLomuNTM9Rg0m6OiIelvSviPgaeWP4H8AEsn7vhsA2EXGRsrFrH3I1Sh+yXuz49o2+56vuQ5Wf34yIHcmVC98tj+9ZziF+A2wFXAr8MiLWlPRaWwbfi9TdjPoime12rsrKR7I01MzAZyNidnIJ+grkypObJD0O7mfSTJ6jzuc56p5qwXllhvyuEfEBsBvZnPd5skfNIcqG8Z6fFoiIDcibJAeRN0Qm9TWT9FhEHFJ+PLucZ19c/x4loaaPpNfJVSrWIJVro23IHkHjydUm/SLiYmB/SX+PiIMB4XmybsoZ89bRlEuU9iuB93MjYpPKCcpo8gP4+oiYqRKUHwhsSd7xfrEtA+8l6oKJGwKXAH8GroiIfQEk3QwcQS7LPLsEHbtcVFTeYy9yeaebsDSI56h7qMvauYgM9r5def5i4GiytM3wiNg8IjYjM3nmKK+pBeV3xc2MGqqW7V6C8kuTF89HRsTiyma8PyWPNz8HflI2+yzZJ+Br+AKgqeo+5+aJbNQqAGVW6B7ArWRwvpY5/z5Z1mYrsqmyg/ItEhEbRsRjwNrAX1QyQ8sF86vk/jQUuJNshPgL8kbl47X3cLCquTxHnc9z1D2pa+b8HsDJZK3ru4Bhkk6AXCHu+WmeyNKdA8jSdmPIG1tPl+ciJpfGfQw4mDyHuDAilpja+8kr7JomIr5DlqQ5mVwBuRw5J0PJkoQzlnk6DLgFz5N1Qw7MW8eqBEI+iIjPkA3ZRteChuQJzInkUvS/RcRPImIY2axlY2BLuXxNU1UCIVsCvyTrId4EzEaWRhlTXlcrmfI3YFTkstsuImJNMji8m4OJjeM56j4iYn3gVHL1wpGSxlafV9YlP5Jc7XYecDpwhKRTKu+xH5kdvIPn6NOLiH4l6Du+/DyLcnnzcLLM0MERsZSkV8iMt/8Ch0bE2+QxagR5of3L9vwGvUPlc+6H5E2QhyPigYhYq8zZm3QNzp9YCc5fr7KcOcI1/5uhBDmqf9vPkKtJvk4mWBAR/WsXzJIuJVegvEQ2wN5d0rG192rl2HsLz1Hn8xz1HHXB+X3I5vHrAHtExHy117RxiD1S9f992U/eI/efZyW9UXlOlWSX6ST9nQwEf7d8by1Qma+hwB+B0yX9XdLfyPPwncn95hAAZW+AQ4D1PE/W3dS6f5t1lOhakmE4GahaCBhGfgB/X1lWYCayFt825BLN18jSNQeVD2drsnJH+kayqdQZkl6LiFnJ8kMCVpP0ZHnteuQcjlRdXbeIWBaYTdLvW/oL9AKeo84XWQ/2DLKR6FaVQPA+wOeBfpJ2K499HZgdmCDpt+WxPmWJ5j7Au5JOa8fv0ZOUv/Mg4FpJz0XEzsB6wEaS3omII8iSadcBx0j6a9mv1gKWB54jG8LeUt5v0nHNGqMuU35tStYbMI68cbIksA8wpnzuzQKcBAwBbga2cfCjeSJicfJz6l/l5w3IlUB3AFsDhwJvACtIGhcR/coKlNr2/cv2tTn2PtRgnqPO5znqXiKbh36sFVglK/6D8v1Issb8beSKx1ebOMxerSQfTQdcBjwB3CBpp/JcdU5WAL5BXhNV9ynvQy1QAvMB3AO8JunbdfPzGfKcb3Hgm5Keq9ve82TdhmvMW8cpF9q1oPwIYDvgGkm3R8RhQF/gqojYUNKYiLhc0qURsQgZCEHSW+0afy80D1nH8reVE9FRZCmOoZKejIglyh3uGyLiL5Keqn8TZfMWaw7PUeebACxMBtXHR8RgsnTNYmQW9rIRMVDSxipNjGqqJ56STmz1wHuicjEwB3AKsFxEPE6u0NqXrNWLpENKMs+uZZthJYvnyvJVfT9fHDRBJdA0L3kz5DTgQGUD3jmAC8g5jIi4qgTn9yFLQo11UL55ypzsC8wdEbuQy88vBH4o6f2IGFVeegxwe0SsXB6fFFRUXV8G70ON5TnqfJ6j7iUitgC+E7lK9SP/1upac363iJgTGOegfGPV3cT/PnA+mVndn7yhv0NE/EbSFZWgb39yJeQPyASMagko70NNUJ0nmHSOp4j4MzA0Ij4n6ZmyMmi8pFci4lHy5skU53OeJ+tOXMrGOkrdgXMBYFEye+AegBKQOgT4NXBlRGxQ+dD9j6S3HJRvnmksfZ0HmBuoZfLcSGaZDpX0UER8CTggIr4MUAv4ehltc3iOuo+6v6/I+v8rR8QLwNlk2aHlgW+Sjd2+EtnErQufeDZeOQ79Dtge2AE4jmwMdrKk9yKiX3ndIWT5oe8B+5XMxqm9n+eoSSJiKFkr/nvkCoUJ5VziVWCz8txw8qJuDuVy9S1UmiL7c645JD0PPAp8iwxqXADsRPY36SPpHeBisg72IsBdkSUDJtT2L2suz1Hn8xx1rsj65LXva8eRzYEXyjH/45YlmFg5p/ihpP+re0/7lKqrRcgV+KcDv1D2ZbgUeAw4LiK2i6w9vwR5/ncocKEqfRmsOepiQGtExNCImLE8fSOZFHNWRMylyauKZwDmJD8jJ0ztfc26CwfmraNUPpDPJZu7zgv8WdK7lZOWWnD+VuDyiNioPO7MtyarzM9aJZgLWbfydWC7iLgFWBZYvwR8pydLPyxApZFl9b2ssTxHna3uQmuOiJg7sga2yIvrH5IZvj+VtLqkJ5X1y/uS9f/fa/2oe6cS8HiBXF3Yh7xRPFd5bkJ0Dc6PADYFjomI2doz4t6hug+VbNKHyIDUisCCkJ9dJWj1Nhmcvw04E9gssmzUhNp7+XOu8WpzJGk4eUH9JfLz688lM3Riyeh9l/zc2588Bt0fEdOrUjLAmsNz1Pk8R50rIg4F7o2IeWDSMacvmQgzrvbYx3ifUJoQEbtExGklMOxjU4NF9nF6hrx58o9yfoCku8nEiyfJpJgngd+QsYZhkkaW7X2jpEnqgvJbkT3RdiBXEkPelLyI7Dd4Q0R8PSJWA35ElvO6wqtMrLtzYN46QgkOVj0OLEOehC4JkwIhtQ7pteD8A+Td05l9wGyNyPIAVwO7AUi6hzyBOZrMwt5M0oORtXw3IZfgXio3YWkZz1Hnqpx4bkbWuH4U+HdEnAIsKel6SUdJuqK8bs7IJdFbkHWy32nX2HuTyvHkX8D6wF7AlsDRETEQJh2Tas3bfkaWUblV0uttGHKvUdmHtiZXz71B3mx8Fdg2sk8GJWhVC85vQTbjlaT3a+/hwEdzlCBVv7IfDQCuJ3tlHFJZmTUhsoRDLah4CDmPQ9s17t7Ec9T5PEedqdyUfwoYCFwaEXPDpASx8cAr5XUfGmepC0buTq6MvFfSRB+bmmI2MklpEJnsMin+IOkmMkP+++T101HA5pKGldf18Zw0T2U/+AFwFnACsLdKv8Dy/AHA8WSPrT8AtwAHAodLOr1s71iQdVtu/mptUwIaqwJ/KCeUlODUicDzZBBkBHmXdE9Jz5bXVBvDfgV4SVOph23NUQ56x5Mn/T+QdH9ZavZLspTAxWQjncXIgNaJko6qbesTm+bzHHW2EpS/gLwI+wfwWfKC4B2ybuwfy+sGAxsDGwHDJR1dHvccNcGH/V0jl6xvA5xMZu0cpCwxQESsDjwl6d8f573s/09dEGNh4Pfk+cJFkl6MiGXI4Pt/yBUnN5XX9lWljm+bht8rTO3/fcnonRARe5FBw98Dh0l6oLYN2VT8tYhYStmnwZrEc9T5PEedr5xTf48sZfcYea72EvBH4CRJF3/E9vVB+ZOAH0s6p6kD74Vqf+tyQ2UT4GfATGSz5GciSz+9/yHbu0dQC0TEfMC1wA3kZ1st1rMuMAPwT0l/iezDsBp5k+VVSX8ur/M8WbfmjHlrpy+SdzrHAETE5WQZhwGS3iODiD8hg4tHRC5Zr2XB1bIUH3BQvrXKieS1wHzASuWxdyR9n7yRMh9Z/1LA7pWAr7MNWsRz1LlKtvXeZLmawyWdJelwsozQa+SJZi0QvA4ZtN+/EpT3HDVB3UXy1yNi84jYKyLWhEkNxS8iM+e3Io9JK5Xsntsp+1mN56jxKvOzJpmpeBswqgTl+0p6BFiFrB97bESsU7b7oPqvM6qao24f+mJErBgRy2tyA8qTgSPJOTosIpYrm34fuC4iFqkFEz8q09T+/3iOOp/nqHtQrl68HtidXNl9CVnubnZgqYhYMiIWj4ivRMRXI+LLtfOJujnejbzh76B8g9Qf42t/67IPXQYcTl7//C4i5lZplvwh2zvY2zpzAI+XWM+iEXED2aj3CuCqiFhb0suSxkj6bSUoH54n6+6cMW9tExEzkyU0dmZy3eTBwL8qF9AzANsxOUvxQEkvtGG4vUYls6BvZR5qmTr9ahcHEXEW8F3g65Kerm4PzCzpzcpjvovdQJ6j7qM+8y0ilgXuBLaVdFV57Hpyae16yrr/y5BZv32BmTSV1ULWHJFlg44HngM+QzbgvUzSgeX5mcnVXKeRy9WnB46X9PP2jLh3iYiFyJryswB3A2tUPu9qmfHLAmOBF8mbWte0Z7S9U2SJoRPIjMQZyca7p0l6ojy/N7kk/Tkyu3Rz4Khyg9JawHPU+TxHnacuoN5f0vhyTrAemTn/ElkuBbLWPMAHQJC9avZQqVde3mN3ctXXTg7KN0bdHH0DWAJYikz2+4+k1yuZ88eS8YcVJb1UvX6y1isZ8/eQK1DGkQmc75JJmq+S53VnSNq3XWM0aybfSbe2KAfOceRd6+eAzwH/Bv5dLqz7AyhL3JxLZiluBoyMUsvPmmZ16JJduAFZx3/xuhOW68gTzSHldbVGiKoGfMtjDiY2lueom6hcIKxRHupDXqS9Ux6/geylUQvKL01ebC8v6fVKUN7ZIE0W2Uh8JLkMfRB5U3gBYK+IGAEgaZykM4AVyBqkm9SC8s5ObInngJ8CD5PZiYvCFOVq/gKsCSxO1mW2JqpmF0aWFzyODChuDRxM9jo5MiK+CCDpJLLR3otkL6F9asFEr2ZoDs9R5/NIa6y8AAAgAElEQVQcdba6gO/a5FzMW65lr6X0dAJmBjYkg8FfBZYmj0WD6oLyW5I3WxyUb6DKHG0FjAb2IROUfgfsGhELVDLn9ycTYB6IiHkclG+NaX0+SfofWTlhJvKG1mWSlpP0a2WJzz9RGiub9UTOmLeWq2V9lg/mz5MNKd8FNgDuBTYsy8r6Sxpftpke2IPMsP9SLVhljRURO5CBqUWBZ0ugYxTZC+Cz5HKyG2sZiBFxLbCopKXLz66r3GSeo+4nstzJr8il5ncAj5DZvjOTF9TrSXq43DjZkQwI/1jZ5NpaICIWBM4E7pH088jyAHeStS4/ADYFTpa03zS292qGJpnKqpMZyIu3I4GXyWy3t+qC8x9ExGckvdKucfc2EbEo8E1gZWCX2s3fiPghcCFwFfBzlWZuETEreR1SK9/lfajJPEedz3PU2cpKhuPI7N3zJd1cHp+ZDACPBP5C3rR/qbJdl5WuEbEn8LSkK1r+S/RwEfF9so/T4WTZyC8AfyeDuqcBp0v6bznn3hQ4A9hN0oXtGXHvUXeDa0VgQfJ69hrgSUlvRsQs6rqiexayH9rJwHaSrmvD0M2azoF5a6noWnpjHeBPyvqwA5hc1uZ+Mjj/bjlo9gFmkfRyRMwh6dW2/QI9XEQsAfST9GhELCrp8fL4fGT5hi3J+r23kF3T3yFLDJ0k6ZT2jLp38Rx1L5G9MU4FHgDOKp9jPyyPzQYMlvS7iJiNDNyfAhwsaUTbBt0L1AcvIuJzwKFkBttbZGO92yRtVwIlvyeXpp8paed2jLk3qbt4GwD0qbtQm4FcRXcs8CzwjRKcr5byqgVCHKhqsnKBfTd50/FWST8pj9cSMTYjj0OXk+U2Hq3b3jeMm8xz1Pk8R50tIjYkk18OA34l6bm652cgA4jDgaeAIfWvseaKiPmB84C7JB0WWdrubnLeZiZXoBxLnss9FblC/wuS/tG2QfdCZcXIMLKv1lxkSaHzgFMkvVo5f1sZ+Brwc2CYpGFtG7RZkzkwby1TF5Q/H1gOuAk4ulxQ12rO7wTcR5bf6Es2q/wysIo+pGu6NU5ErEDWedtX0omVx5ckl2YeRnZIf5/M0r4F2LqWsWPN5znqfOUi7svAGuQ83VMen4tSD5bMrPovMB3wDWC4Jjd69UV2g5UyAM/WMqnLaoYnJN0f2QTsxYg4hDz+bEzWJJ1YVqUsDywCfFvS7e36HXq6uqD8UPKG/eJkg+QjgN9Ier4uOP9fYLVyLuH9pg0i4hIy+/ABYH1Jz9Q9vynZIPEmYHNJr7V+lL2b56jzeY46Q0R8VpXV2RExE3Al8D+y/ExtRffmwPzAX4FfkyvsNiRXN/zQGfGtVbKr9yD3j+fJoPxtwI/J0p5jyfm6mOzZ8GRlW9/Eb4FybXQBuaLhJLIPwKNkksVFwDHKXgDzk6tW+5GrHE4t23uerEfq99EvMWuMSlB+NHn3cy/g/sqF9LiIOKG8fFfgn+VrRTKr1EH5JqkLhMxG/t2vAY6PiHclnQYg6THgschmlUOB75HZ2WMd8G0uz1Hnq5ujGYHVyLqj75EXawAom0z9gryxsiswN9m87QJJV5ftfeLZYBExB7ALeVN45bIk/XyydND9kl4sLx0EjJf0r7Ld7MDs5AqU+yX9vuWD70Uq+9BW5MqSUeTF2/5khtXZEXF2Cc5fAohcaVJbReQ6sS1QyWjrJ2mCpM0i4i1gW+DHETGysk8h6dLyuTizg4mt4TnqfJ6jzlPOz2aOiB0kvV0enpEMIN4BKLLc3XDyfGECMCdZgvCsyBKSX5T0zzYMv9ep7ENBlqs5XdIrEXEA8DR5Q/8DZZncf5PngD8BrgYmBeZ9zt18EbEQed1zjKQTImIQWf//AmBeYD9y/zpOWW5oC2AGldKevjaynsyBeWupiNierJv4A+APyjp7swLzRdaUfzgijgGeAdYms0hXql+uaY1VCYT8GDiEbFa0P1nSYWQ55zm9vKZ/uRg4Hzg/IgZJerA850zFJvEcdb7KHP2QrB1/OPAmcCCwfUQ8VVnW/J6k+yJim/qTTJ94Ns27wG+ADSPi78BiZDb2xXWvuxcYFhHfAp4AViEv5A6V9AB4jpotslnyYcDhkk6MiMXI1SevAz/Ll8TZkp4rN/tnIC+8HZRvorrjxxwRMRHoTzagRNL2kaWHDiYvrk8tq1BC6YJpvJc1iOeo83mOOt5NwBuS3o5S71pZhvAO8vx7A3Il6vPAt4B/kzeQt4+IiyS9RSbP+FyhSer+3/cDxgPTSXoPqPWWWRKYS9K/yzazktdMq5On7Pe2eNiWfYEeAW6OiAXIBLPLlWUj+5OriLcAZoiIoyQ9XNuwzLn3Jeux+rR7ANYzRcQsEXF2RMxT99TCwFOS7gL6RsQ3gLvI5X8PRsQBkt4BzpG0Idk8x0H5JomIvpXvlyWze88C+irr7R1FLpk9NSJ2AZA0PiL6RkTt8+Ohsn0fXxw0nueo85Usndr3a5KB3mfJLKpDyWZT2wHbRsTckFcE0zrJ9IlnY0XEzpHL0t+RdCVZn3cx8mL6elVqkpdNrgVuBm4lg/Rnk/VIH6i9p+eoser2ob7AF8nVCSdGlue6j2ygvCA5Lz8BtouIz0l6Fzhb0tn172WNUw2ERMQm5H7yT+CRiDgpshYskjYDLiUDWDtHxDxTO+74WNR4nqPO5znqfJKulvTbyCail0bEl8pTu5FZ8vcBx0laQdKfyFWRbwEPlu+r7+VzhQar24fWB34REb8DLoyIVSsvfYwM8O4aEYuTJYbWIzOw7y3bOxbWZLW/cbkGfRM4oOw3W5HXSkdFxHTK8lD/AOYgSw8tWX0ff9ZZT+eMeWuWNcgL6HF1j78MrBQR+5FLAjcnl5JdT5a3OSIiLldpaFmC9NZgJZjxDDCx/Lw8OV9PAL8AXgWQ9LeIOLJsNjIiJko6Q6UsUXmNyr8++Wwgz1H3UblAWIjM3D0NOFdlCXRE7E4eb39efj5L0ks+yWy+cmG9O3An8Gy5QHgbOBf4LnB5RAxVpUGbpMciYkcyq2ou4B+Sbirv5+y3JqjsQ2uSS8uvAx6KiOnJubqFXLGgiDiNzFL8CTAgIo6onit4v2qOyhxtTq7GOptcgTIbsCewQslwu1FZjmM8ubphQEQcWm6gWBN5jjqf56hzVY/vETEdEMA6wFvlb/834KC6bWYlzyVWB/by8af5KvvQ1uT10DXAa8Dngdsi4mBJx5N1/r8DHEmef/clS6iMrbyXz+eaoG5FQy1ZonYtWosNDSJvktTKRs5CzuNmwLslidOs13Bg3hoqshnb/JKui4hblPXcdgVuKEvJfgUsRdYQuwfYXdJZZdt+ZAbjW20afq8QEfsDm0fE1pL+HBELktkfAdxRC1BFadZbCfx+AJwWETNKOql9v0HP5znqfiJiFXLlz9vAxcol0LVl54qInctLDwH6RcSZkl5o24B7CUlXRcRDkp6IiBWBf0nar1wA3AyMBK6OiO+ra5O9cZJ+WX0vB+WbK7J3xvXAJZK2A54qq4QWBE7Q5DrLE8iVDBOAF3wDv3Uil57vT+43h1RuPv6WDILsERF/l/SEpK1K0OppBxNbx3PU+TxHnaVyrlYLym9F3pQ/jcyyHk2u8j5ElVXcEbEWmYi2E3mM+uUUb25NEVnj/3Cy3NM5kl6LXJH6H2CDyJJCz5RVKd8BZgEel3Rj2d7nc01St6Lhu8DQiPg88EJEDAOeUJYcuh9YvdxguQ34NlnG+FS5prz1Ql6+Yw1TAutXAGMia1q/HxFfB0YAwyNiPknPStqerL+8ZSUo/xky2+B/gC+ym0vkCcoJZZ6eJOu5PQUsGxGrlAPhB7XlZyVL5Fhyya0PkM3nOep+3gfGkhk5s8GkcjW1+RFZz3wUWTt7gbaMshcpxyRKUH5pMuv6/HIsepMMzO9OzsWVETFvRPQvF3L3R8Tnqu/ni4PGiuhackbZnPoAYP2I2Lg83I/8LFysbNMP+BJ5gb2mpOEtHLJlE+QvAA/Wbj6WY9G1ZEO3tYCv1F4saYikEW0aa2/lOep8nqMOEVlDvtY4lMhSQheUp/tLGkOu7l6PXNW9dHndnMD65Oqtn0o6ujzu2EprLEj2Zbhdk5sgXwg8B+ymbA4/p6TnJJ0vaYSD8q1Rt6LhCvLz7gPy3O0usjTX9MANZE35M4A/kvGiU2pB+fJenifrNXzwsIZR1um9k2zYenIJKN5HLklaHTijZIlQDpSvwaQmb8cDQ4BdKwdYawJJx5F/7wXIGybLSboE2JcMghxQnkPSxEpg8VHgRw6ENJ/nqHuoXUwDlM+6g8nPwK0jYq/y+MQofQLKyer/Ad+U9Mc2DbtXKBk7tdrxn5H0V+AUsnb5iBKcf4ts8rY7MD95YXABWV5gTF0GvTVY5eJtYOXh35B1YTct2W9PkauFto+Ii8ibj4eRtXwp27umfBNU/64RMW/5diJ583FSrwwmL1O/nMxWXK9s029q72WN4znqfJ6jzhURvySbUE5XgvOLkk3GfwGcpVJyQ9IVdA3OLyHpZeAIYPNKkpkDvk0wjf/3ywCzKGuVExE3lce+r1xpvBKZiDFv/Yaeo+aLLL96BLlKeFtJ6wKrkIkW3yTn7hEyYWln8vx8U0nDyvaOUVqv4//01hC1g6akY8kP1/nIgOKXJF1KNvEYTAZE5q9stwNwHLA8sHr5kLYmKEHEWiPRc4GryIyDUyJiaUmXAzsCq5G1yr8AUwR+X629V8t/gV7Ac9T5qn/X6tLn8vOfyFqwNwCHRtaWp6xs6FvZ5vbyXj4GN0EJyteCvhsBF0fE7pIOJRslf50pg/ObA4+SNUr3lbRf2d5z1ESRPQDGRsTPS1DjEeBU8kb9t0vwYy9yblYjlzkfVM0erc21Nc5U9qGzInsDPQr8lbz5OB/k51vZbE5gPFDrETSh9n6eo8bzHHU+z1HnioiDyPrxBylXeK9L1irfHXhF0rjq8b8SnP82cGJEfFHSCyo90cpcO+DbYHX70KoRsU556o7y2K4RcQ2ZdDFE0kMRMROwKtnzaeZ2jLu3mco15zzl31uUqyEhz7//S5bveikiZpD0mKQLJB0j6YbyXr7BZb2SLzitUar/l64jMw+XIIOHS0saDexA3iUdWQnOPwScDHxP0sOtHHBvUwKCH0TEdsCtZICjDxnsOCMili03UbYnayaeXA381r9XSwffS3iOOlvdBcK3IuKEiLguIg4s2b1IeoBsMnUnmVm1a3n8g/r384lnc1TmaGtyafNfmBzkOAC4mLrgvKQ7JK0DbCjp9LK9Lw6aKLInzerA4uTN+0cj4ptkOa4R5A3JRUuw/kfAcsA6kk4p2/sctkmmsg/9DXikPL4vMBAYFRGDyusGkAGruaisZrDm8Rx1Ps9RZ4rsMbMS2f9sbESsT67u7gssSgZ5uyS9lJ+vALYF1gUWqr6nz7kbr+6ce0uyFOQBEbEY2ST+fuAE4BvAtyQ9EBEzAhuTzeEvk/REe0bfu1Q/6yJiJBnv6VOL7UTEjWQpmyHKFQ1rAueWmyj17+XzbuuVwscR+7TqDpxXkndJZwfeI2sk3kmWqPlLRPwAOJtskribpP9Vt7fmKhkhV5NNp24H/g4cRAZ6HyPn6ZHIGsujgLvJmyZvtmnIvY7nqPNFxDbkSp8HyYbVPwIuA0ZocsOirwEHkk2nDlWWJ7IWiexvci1wInB6yYyvPn80sCXZhHwvSf+re97HpQab2t80IlYDziHLBy1AXszdRX7urUV+5v20/vPN89N809qHSvDwu2S5tVnIuRoHrAAcI+mo9oy49/EcdT7PUWeKiDFkcP4McqXjd4GHyUavXyHP204or+1bTa4oN4wfb/2oe6eI2Aw4j7wWullZmpCIWAq4EpieXGH8EJl0sTVwXG0f8vlC89TFgGqJFbuTn2WjyPPsjcjPtfVLUH4mspfGt4HtJf27LYM36zD9PvolZh+u8oF8LJnZuwHwj7JM6WCyW/3IiNhF0uiImEie+LwbEVtVl2la85Ssj7XJJbQXS3qpPHVwRLwCDANOi4idJV1WshkHOODbOp6jzhcRtQvp4yQdXy4MtiWzrQZGxAGS7pd0f0QMI29SvtHGIfdWy5A3h6+rBuUjop+kCZIOjIj3yAuI8yJiqKS3a6/zRVzjVc4VvgQ8I+klSb+LiMuAPYBFyJVAG5E3tfqQZfGWBu6d2ntZU02xD5WL8Lci4gryBsq+5OrIJ4Gzy4ourzZpHc9R5/McdZBKIHEr8sbvQWQJ1tslvRMRm5JB3l0jYrykU8pK1knBeU0uX+P5abKIWJCco2PI5Jda76A1gZfI3k5rk/X/tyCz6PeUdH55neeoiSrndZ8FRK4MGk2W5PotWZb1HWCQpKfLdesm5IqGAx2UN5vMgXlriJL58RXyQ/ie2uOSjizBj2OB00tw/rKImAD81UH51ilLMucBZq4FfCMbHr0v6aQSLNkCODsidpN0UW1bZxu0hueos0XE7MCGwCUlKL808AcmrwIaBRwSEUdJulfSfRGxqaQX2jjs3mo5YCZJj8Hki7PKRd1ikg4vy57/WQ3KW/NENtd7ELgzIkZJOlvSwWWFyalkc+Q7ybr/I8gyNwOn+YbWTFPdh2BS34wZJe1RnqtmzTkQ0jqeo87nOeoglfPk1ckV3i+TQd3REfEn5UrujchM7L0iYqKkkXI5wnaZnkxwuR/4ICIWAEYCK5LNk+8gb+TvSq48eVvSe+B9qFUi4hvA74EXgV+VG5BvRcQIch8bCGwSEc+RzZV3JFcFnVO29/WrGa4xb43zHnlAnF1FRPQHkHQ8ubRpObKW4jKSrqqdpFpLPQDMHRHrASgbHvUvzz1OnqAujGsntpPnqHONA24GfhkRc5GNwq4CfgrcCFxOLoc+OCJWAqgF5SPcjLfFHgNmjYihMOmmVwBE9gM4PCKGSPqppHPL456jJiuZhmsAARwYETdExELkfvRZsgn8G5IuK6/7tqRr2jPaXu+j9qGfRdb9hZxPaq9r+Uh7L89R5/Mcdaa/AZuSq7zfI3vPfC0i+kv6L5mE8Qx5nNq/fcPs9cYBs5LlPM8HbiNX1+1MniOsTp4nTJD0KvA+uBlvi/0LuAIYQPbHAEDZzHVvJpdnPYFcAbmXpKNh0s0TX7+a4cC8Nc5EsuHrlyJiMICk8RHRtzz/AfAsecB02Y32GQNMAPaOrHtZm6f+5AH1aGAtSVe2cYy9neeoQ5Vs66sl3UvWRhxPlrR5o2ToPEHePFmPLMFR3dYnnq11K/A2sFtErAA5B2UZ7XrAyuTF+CSeo9aQ9DtyKfMxZEb8beT+shSwTeV1j0n6NbjRa5t81D60KvBCedwBkPbwHHU+z1EHkvRESRK7l+wT9D5ZhmP5SnD+B8DrlPmx1pP0DDCULAk1F3kOvky5BrqPTGZ6vfJ6Vf+15pP0HFkW8jpg84j4ceW528mbKEuSTZU3rSTDeEWDWYWbv1rDRMQS5EHyPrJpzj3l8TmB08g73fdKeq19o7Ry4+R6MovnErJ276rkUsBtS6aiD5ht5DnqfBGxN3Ao8A1Jfy3lvI4j+wP8yp9z7RcRa5OZOo+Ty9L/BnyDzLw6UtIxbRxer1eyRmcmzw+WJDPm5yOzqU5p59gseR/qfJ6jzuc56mzlWPRV8jp1OrJh5QMlKWZmSePaOkCrlcx9t1ZSqPw8hMzC/pGkm9s5PoOImJcsSbgh8H+VUjX9NLmMZJ/aqiHfPDHryoF5a6iIWIvM+H2aLO3wH+BbwCrA8nKTj44QEV8mG7IsCswEvAKcKOnYtg7MJvEcdbaIWJK8CTkKGAt8BjgS2EVu3NYxImJFMvC7KDAD8DBwoaRTy/Oeow4QERuSq1C2p3JBZ+3nfajzeY46n+eos1WC82eTNc23IBvz1lY4OJDYIcrKk6+TK4iP8o2tzlEXnN9e0nltHpJZt+HAvDVcRCwDnEguO+sL/I+8m/1wWwdmXUTEHExuyvKypEfK47446BCeo85WVjZcTTanepO8ceILhA4TEbOSPVBmBF7T5MbK3o/arK7Z4XTAYpIebfOwrI73oc7nOep8nqPOVoLzXyNXNRwk6aI2D8nqRMTCZELMZ4DTJY0oj3sf6hAlOH8KWbJwN0mntXlIZt2CA/PWFBExE5nlOwvwiqTXP2IT6wA+sel8nqPOEhELkM1436uU7/IcdThnv3U270Odz/tQ5/McdT7PUWcpwfm5JbmufAcqveuWB/pJurs85vOFDhMRA8nSULdIGt7u8Zh1Bw7Mm5mZNYgvEMzMzMy6N9806Xyeo84VETNJervd4zDrLhyYNzMzMzMzMzMzs4bwzROzj8eBeTMzMzMzMzMzMzOzFurT7gGYmZmZmZmZmZmZmfUmDsx/DBGxUUSMjIg7I+KNiFBEjGr3uMzMzMzMzMzMzMys++nX7gF0EwcDywHjgKeBJds7HDMzMzMzMzMzMzPrrpwx//HsBSwOzArs1OaxmJmZmZmZmZmZmVk35oz5j0HS7bXvI6KdQzEzMzMzMzMzMzOzbs4Z82ZmZmZmZmZmZmZmLeTAvJmZmZmZmZmZmZlZC7mUTQutscYaavcYbOqGDx8OwJ577tnmkdi0eI46n+eo83mOOp/nqLPV5mfQoEFtHomZWXM9+OCDPhZ1MJ8vdDbPT/cxduzYnliv+lPHHgcPHtyIcXSk/v37c+utt36STZr6f8QZ82ZmZmZmZmZmZmbWo1133XXtHkIXzpg3MzMzMzMzMzMzsx7j9ttvb/cQPpIz5s3MzMzMzMzMzMzMWsiBeTMzMzMzMzMzMzOzFnJg3szMzMzMzMzMzMyshVxj/mOIiCHAkPLjwPLvShFxQfn+JUk/afnAzMzMzMzMzMzMzKzbcWD+4xkEbF332MLlC+BJwIF5MzMzMzMzMzMzM/tILmXzMUg6TFJ8yNdC7R6jmZmZmZmZmZmZmXUPDsybmZmZmZmZmZmZmbWQA/NmZmZmZmZmZmZmZi3kwLyZmZmZmZmZmZmZWQs5MG9mZmZmZmZmZmZm1kL92j0AMzMzMzMzMzMzM7NGGTx48BSPnXPOOSyyyCJtGM3UOWPezMzMzMzMzMzMzHo0Se0eQhfOmDczMzMzMzMzMzOzHuP2229v9xA+kjPmzczMzMzMzMzMzMxayIF5MzMzMzMzMzMzM7MWcikbMzMzMzMzMzMzM+sxRowYAUBEEBHMOeecbLLJJvTt27fNI5vMgXkzMzMzMzMzMzMz6zHGjBkzxWPzzDMP3/zmN9swmqlzKRszMzMzMzMzMzMz69EWXnjhdg+hCwfmzczMzMzMzMzMzKxHe//999s9hC5cysbMzMzMzMzMzMzMeozbb7+93UP4SM6YNzMzMzMzMzMzMzNrIQfmzczMzMzMzMzMzMxayIF5MzMzMzMzMzMzM7MWcmDezMzMzMzMzMzMzKyFHJg3MzMzMzMzMzMzM2shB+bNzMzMzMzMzMzMzFrIgXkzMzMzMzMzMzMzsxZyYN7MzMzMzMzMzMzMrIUcmDczMzMzMzMzMzMzayEH5s3MzMzMzMzMzMzMWsiBeTMzMzMzMzMzMzOzFnJg3szMzMzMzMzMzMyshfq1ewBmZmZmZmZmZmZmZo0yePDgKR675JJLGDhwYBtGM3XOmDczMzMzMzMzMzOzHu35559v9xC6cMa8mZmZmZmZmZmZmfUYY8aMISIm/dyvXz8GDBjQxhFNyYF5MzMzMzMzMzMzM+sxhg4dOsVjw4YNY8UVV2zDaKbOpWzMzMzMzMzMzMzMrEd77bXX2j2ELpwxb2ZmZmZmZi21xhprtHsINg3Dhw9v9xDMzMw+tXnnnbfLz/PNNx8rr7xym0YzdQ7Mm5mZmZmZWUuNHTu23UOwD/Hggw+2ewhmZmafyujRo9s9hI/kUjZmZmZmZmZmZmZmZi3kwLyZmZmZmZmZmZmZWQs5MG9mZmZmZmZmZmZm1kIOzJuZmZmZmZmZmZmZtZCbv5qZmZmZmZmZmZlZjzF48OApHrvkkksYOHBgG0Yzdc6YNzMzMzMzMzMzM7Me7eqrr273ELpwxryZmZmZmZmZmZmZ9Rjzzz8/EUFEADDffPOxxRZbtHlUXTkwb2ZmZmZmZmZmZmY9xkUXXdTuIXwkB+bNzMzMzMzMzMzMrMeYWo350aNHM++887ZhNFPnGvNmZmZmZmZmZmZm1qONGjWq3UPowhnzZmZmZmZmZmZmZtZjbLPNNkycOBFJTJw4kTnmmIMhQ4a0e1hdODBvZmZmZmZmZmZmZj3G/PPPjyQAJDHrrLPSp09nFY9xYN7MzMzMzMzMzMzMeowjjjhiiscOPfTQqdaebxcH5s3MzMzMzMzMzMysx1hjjTWICCICgLnnnptVVlmlzaPqyoF5MzMzMzMzMzMzM+sx9ttvP4BJgfk+ffrQv3//dg5pCg7Mm5mZmZmZmZmZmVmPse66607x2GGHHcbqq6/ehtFMXWdVvDczMzMzMzMzMzMza7A333yz3UPowoF5MzMzMzMzMzMzM+vR5plnnnYPoQuXsjEzMzMzMzMzMzOzHqNPn8n56BHB/PPPz2KLLdbGEU3JgXkzMzMzMzMzMzMz6zFWXHHFLj/PO++8DBgwoE2jmToH5s3MzMzMPoE11lij3UOwaRg+fDgAe+65Z5tHYtNSm6NBgwa1eSRmZmbWk919991TPDb//PMzdOjQNoxm6hyYNzMzMzP7BMaOHdvuIdhH8ByZmZmZWb2BAwe2ewhdODBvZmZmZvYJOGO+czkb28zMzMym5cknn2SllVZq9zAmcWDezMzMzOwTcDa2mZmZmVn3s8QSS7R7CF04MP//2Lv/KMvL+k7w76e6+Q1tI9KtYIOB9gdisHCwDbJp7gX3OG4IOqtrsknWE8PORHTP6UKUSU4WRWUQOVGuGoPnsIJBZoYh7q5mctiJxqmKsysO7uYYxoFVejEYNxoV0H7x30EAACAASURBVN0xoNj93T+qCu/tquJ2u93f59vfer3OqXO5T91769398eDlfZ96vgAAAAAA9Mb8/HztCFPN1A4AAAAAAADriR3zMMavpnefGXWfGXWfGXWfGQEAHN68nwOmUczDGBdz667li7nNzc1VTsJazKj7zKj7zKjbXFgUANhf+oXu8+EJtSnmAQDgAPgP7e7y4QkAAEmyZ8+eJEkp5cmvrlHMwxiflnafGXWfGXWfGXWfGXWb+QAA03i/AHW94hWvWLF2ww035KUvfWmFNKtTzMMYO+C6y/EO3WdG3WdG3WdG3WY3NgCwv/QL3efDk/VlZmYmZ555Zu0YE2ZqBwAAAAAAgENl7969ue+++2rHmGDHPAAAAAAAvXHGGWdM3D/llFNy7rnnVkqzOsU8AAAAAAC98bGPfax2hKkU8wAAAAAA68i73vWuXp+zf911103cP/nkk/Obv/mbOeKIIyolWkkxDwAAAACwjmzZsqV2hEPqs5/97Iq1M888MxdddFGFNKtTzAMAAAAArCOXX355Lr/88hXrw+GwQpqD73d+53eSJKWUJMkJJ5yQX/iFX6gZaQXFPAAAAAAAvXH99ddP3H/GM56Rm266Kc94xjMqJVpppnYAAAAAAAA4VL73ve/loYceqh1jgh3zAAAAAAD0xvz8fO0IUynmAQAAAADojVe96lUT97dt25YbbrghmzdvrpRoJUfZAAAAAADQG48//vjE1wMPPJCvfvWrtWNNsGMeAAAAAIDeuOuuuybuz8zM5KijjqqUZnWKeQAAOACDwaB2BNYwGo2SJHNzc5WTsJblGc3OzlZOAgD02THHHFM7wlSKeQAAOAALCwu1IzCFGQEArG+7du1KkjRNk6Zp8sxnPjNvfetbO1XYK+YBAAAAAOiNe++9d+L+V77ylfziL/5idu7cWSnRSop5AAAAAAB648Ybb0wpJUlSSsmxxx6b7du3V041STEPY/zac/eZUfeZUfeZUfeZEQDA4c37OajrcLiejWIexriYW3e5mFv3mVH3mVH3mVG3mU/3mVH3ufgrsF7oF7rPhyfUppgHAIAD4D/ius+MAADoupnaAQAAAAAAYD1RzAMAAAAAQIsU8wAAAAAA0CLFPAAAAAAAtEgxDwAAAAAALVLMAwAAAABAixTzAAAAAADQIsU8AAAAAAC0aGPtAAAAAAAAcLC8853vTJKUUpIkW7duzWWXXZYjjzyyZqwJinkAAAAAAHrj85///Iq1F7zgBRkOhxXSrE4xDwAAAABAb1xzzTVpmubJrxNOOCHnnXde7VgTFPMAAAAAAPTGhRdeWDvCVC7+CgAAAAAALVLMAwAAAABAixTzAAAAAADQImfMw5iFhYXaEZjCjLrPjLrPjLrPjAAADm/ezwHTKOZhzGAwqB2BNYxGoyTJ3Nxc5SSsxYy6z4y6z4y6bXk+s7OzlZMAAF2nX+g+H57023A4nLj/tKc9LTfffHNOPvnkSolWcpQNAAAAAAC99YMf/CB/8zd/UzvGBMU8AAAAAAC9duSRR9aOMEExDwAAAABAr5144om1I0xwxjwAAAAAAL0xPz9fO8JUdswDAAAAAECLFPMAAAAAANAixTwAAAAAALRIMQ8AAAAAAC1y8VcYs7CwUDsCU5hR95lR95lR95kRAMDhzfs5YBrFPIwZDAa1I7CG0WiUJJmbm6uchLWYUfeZUfeZUbctz2d2drZyEgCg6/QL3efDE2pzlA0AAAAAALRIMQ8AAAAAAC1ylA0AAAAAAL1x8cUXJ0lKKUmS008/Pe9///uzefPmmrEm2DEPAAAAAEBv7N27N3v37s2ePXuyZ8+ePPjgg/na175WO9YEO+YBAAAAAOiNP//zP0/TNEny5O0RRxxRM9IKinkY44rc3WdG3WdG3WdG3WdGAACHN+/noK4NGzbUjjCVYh7GDAaD2hFYw2g0SpLMzc1VTsJazKj7zKj7zKjbluczOztbOQkA0HX6he7z4Um/DYfDFWsf//jHc/rpp1dIszpnzAMAAAAA0GvXXXdd7QgTFPMAAAAAAPTay1/+8toRJijmAQAAAADotU2bNtWOMMEZ8wAAcACcGdtdrtPQfa7VAADU8tBDD9WOMEExD2Nc+KP7zKj7zKj7zKj7zKjbzKf7zAiA2vx/EXTPKaecUjvCBMU8AAAAAAC9ccUVVzz5z6WUbNq0KTt37qyYaCXFPIzxq+nd5VfTu8+Mus+Mus+Mus0RHADA/tIvdN96/62GJ554Ig8//PDEWimlUpqD79JLL60dYSrFPAAAAADAOvLrv/7r+e53v1s7xro2UzsAAAAAAADt2bVrV7Zu3frk15YtW7Jly5basdYVO+YBAOAA+NX07nIcVPc5EgoAuuGCCy7IBRdcsGJ9OBxWSLM+KeYBAOAArPfzSA8HZgQAQNc5ygYAAAAAAFqkmAcAAAAAgBYp5gEAAAAAoEWKeQAAAAAAaJFiHgAAAAAAWqSYBwAAAACAFm2sHQAAAAAAAA6W4XC4Yu2DH/xgzjnnnAppVmfHPAAAAAAAvfbd7363doQJinkAAAAAAHrt8ccfrx1hgmIeAAAAAIDe2rBhQ84777zaMSY4Yx4AAAAAgN6Yn5+vHWEqO+YBAAAAAKBFinkAAAAAAGiRYh4AAAAAAFqkmAcAAAAAgBa5+CsAAAAAAL1x5513JkmapknTNNm8eXNe+cpXppRSOdlPKeYBAAAAAOiNm266acXaEUcckYsvvrhCmtUp5gEAAAAA6I3Xve51SZJSSkopOemkkzIYDOqG2odiHgAAAACA3njLW95SO8JUinkAAAAAAHpjOByuWPvwhz+cF73oRRXSrG6mdgAAAAAAADiU/vIv/7J2hAl2zAMAAAAA0Bu/8iu/MnH/6U9/el772tdWSrM6xTwAAAAAAL3xpje9qXaEqRTzAABwAAaDQe0IrGE0GiVJ5ubmKidhLcszmp2drZwEAKAuxTwAAByAhYWF2hGYwowAAOg6F38FAAAAAIAWKeYBAAAAAKBFinkAAAAAAGiRYh4AAAAAAFqkmAcAAAAAgBYp5gEAAAAAoEWKeQAAAAAAaJFiHgAAAAAAWqSYBwAAAACAFinmAQAAAACgRYp5AAAAAABokWIeAAAAAABapJgHAAAAAIAWKeYBAAAAAKBFinkAAAAAAGiRYh4AAAAAAFqkmAcAAAAAgBYp5gEAAAAAoEWKeQAAAAAAaJFiHgAAAAAAWqSYBwAAAACAFinmAQAAAACgRYp5AAAAAABo0cbaAQAAAAAAaM91112Xz372s7VjHDLD4XDF2vvf//685CUvqZBmdXbMAwAAAACsI8cdd1ztCK3atGlTtm3bVjvGBDvmAQAAAADWkV27dmXXrl0r1lfbaX44mp+frx1hKjvmAQAAAACgRYp5AAAAAABokWIeAAAAAABapJgHAAAAAIAWKeYBAAAAAKBFinkAAAAAAGiRYh4AAAAAAFqkmAcAAAAAgBYp5gEAAAAAoEWKeQAAAAAAaJFiHgAAAAAAWqSYBwAAAACAFm2sHQAAAAAAAA6Wq666KqWUJEkpJVu3bs2b3/zmHHXUUZWT/ZRiHgAAAACA3vjSl760Yu3cc8/NYDBoP8waHGUDAAAAAECvdWm3fGLHPAAAAAAAPfL0pz89TdM8ef/UU0/N2WefXTHRSop5AAAAAAB645FHHpm4/+ijj+b73/9+Nm3aVCnRSo6yAQAAAACg1z71qU/VjjBBMQ8AAAAAQK/9/M//fO0IExxlAwAAAABAb+zcuXPi/sknn5wLLrigUprVKeYBAOAADAaD2hFYw2g0SpLMzc1VTsJalmc0OztbOQkA0Gfvete7akeYSjEPAAAHYGFhoXYEpjAjAAC6zhnzAAAAAADQIsU8AAAAAAC0yFE2AABwAJwx313OmO8+Z8wDACxSzAMAwAFwfnn3mREAAF3nKBsAAAAAAGiRYh4AAAAAAFrkKBsY49eeu8+Mus+Mus+Mus+MAAAOb97PAdMo5mGMi7l1l4u5dZ8ZdZ8ZdZ8ZdZuLVgIA+0u/0H0+PKE2xTwAAAAAAL0xHA5XrN12223Ztm1bhTSrc8Y8AAAAAAC99tBDD9WOMMGOeRjj15i6z4y6z4y6z4y6z4wAAA5v3s9B9xxzzDG1I0xQzMMYZ8B1l3OXu8+Mus+Mus+Mus0Z8wDA/tIvdJ8PT/ptfn6+doSpHGUDAAAAAAAtsmMeAAAAAIDe+NznPpe9e/emaZrs3bs3mzZtyvnnn59SSu1oT1LMAwAAAADQG9dee+2KtauvvjoXXXRRhTSrU8wDAAAAANAbw+EwpZTMzMyklJItW7Zk586dtWNNUMwDAAAAANAb73jHO2pHmEoxDwAAAABAb9x2220ppTx5pvyJJ56YV73qVZmZmamc7KcU8wAAAAAA9Matt966Yu3oo4/OxRdfXCHN6rrzEQEAAAAAABwCGzd2a496t9JAZQsLC7UjMIUZdZ8ZdZ8ZdZ8ZAQAc3ryfg7rOPvvsiftbt27Njh07KqVZnWIexgwGg9oRWMNoNEqSzM3NVU7CWsyo+8yo+8yo28yn+8yo+5ZnNDs7WzkJwKGlX+i+9f7hyd13350PfehDtWMcMn/wB39QO8JUinkAADgA6/0/4g4HZgQA8NRGo1G+853v1I6xrinmAQAAAADWkU984hN5+OGHV6z/2q/9WoU0B99wOFyxdvPNN2f79u0V0qxOMQ9j7K7qPjPqPjPqPjPqPjMCADi8eT9H1x155JF51rOeVTtGq0optSNMUMzDGGfAdZczY7vPjLrPjLrPjLrN2dgAwP7SL3SfD0/6bX5+vnaEqRTzAAAAAAD0xmpH2VxxxRW59NJLK6RZ3UztAAAAAAAAcCht3ry5doQJdswDAAAAANAbh8NRNnbMAwAAAABAixTzAAAAAADQIsU8AAAAAAC0SDEPAAAAAAAtUswDAAAAAECLFPMAAAAAANCijbUDAAAAAADAwTIcDlesffSjH83zn//8CmlWZ8c8AAAAAAC99qY3val2hAmKeQAAAAAAeu24446rHWGCYh4AAAAAgF5TzAMAAAAAQIsuueSS2hEmuPgrAAAAAAC9sXXr1iRJ0zRJklNPPTWvec1rakZaQTEPAAAAAEBv3HHHHbUjTKWYhzELCwu1IzCFGXWfGXWfGXWfGQEAHN68n4O6PvKRj2RmZiallMzMzOSkk07Ka17zmmzYsKF2tCcp5mHMYDCoHYE1jEajJMnc3FzlJKzFjLrPjLrPjLpteT6zs7OVkwAAXadf6D4fnvTbJz/5yRVrmzdvzsUXX1whzeoU8wAAAAAA9Mbll1+evXv3pmma7N27N5s3b85wOKwda4JiHgAAAACA3nj9619fO8JUM7UDAAAAAADAeqKYBwAAAACAFinmAQAAAACgRYp5AAAAAABokWIeAAAAAABapJgHAAAAAIAWKeYBAAAAAKBFinkAAAAAAGiRYh4AAAAAAFqkmAcAAAAAgBYp5gEAAAAAoEUbawcAAAAAAICDZTgcrli75ZZb8nM/93MV0qzOjnkAAAAAAHrtJz/5Se0IE+yYBwAAAACgN+bn52tHmMqOeQAAAAAAaJFiHgAAAAAAWqSYBwAAAACAFjljHgAAAACA3hgOhyvWPvzhD+dFL3pRhTSrs2MeAAAAAIBeO/HEE2tHmGDHPAAAHIDBYFA7AmsYjUZJkrm5ucpJWMvyjGZnZysnAQD67IorrkiSlFJSSsnmzZtzyimnVE41STEPAAAHYGFhoXYEpjAjAICn9nd/93f5i7/4iyRJ0zQTt31w4403rli7+uqrc9FFF1VIszrFPAAAAADAOnLZZZflhz/8Ye0Yh8wll1wy8YHDSSedlJ07d1ZONUkxDwAAAACwjvzhH/5h/vRP//TJ+6WUJMmdd95ZK9JBdeWVV9aOMJViHgAAAABgHTnttNPy5je/ecV6X4r5w8FM7QAAAAAAALCeKOYBAAAAAKBFinkAAAAAAGiRYh4AAAAAAFrk4q8wZmFhoXYEpjCj7jOj7jOj7jMjAIDDm/dzwDSKeRgzGAxqR2ANo9EoSTI3N1c5CWsxo+4zo+4zo25bns/s7GzlJABA1+kXus+HJ9SmmIcx/qXcfWbUfWbUfWbUfWYEAHB4834OmEYxD2N8ot1ddpF2nxl1nxl1nxl1mx3zAMD+0i90nw9PqM3FXwEAAAAAoEWKeQAAAAAAaJGjbAAAAAAA6I3hcLhi7eabb8727dsrpFmdHfMAAAAAAPTaF7/4xdoRJtgxD2Nc+KP7zKj7zKj7zKj7zAgA4PDm/Rx0z6c//en8xm/8Ru0YT1LMwxhXTe+u0WiUJJmbm6uchLWYUfeZUfeZUbctz2d2drZyEgCg6/QL3efDk/XnDW94Q+0IExxlAwAAAABAr5155pm1I0xQzAMAAAAA0Gt33nln7QgTFPMAAAAAAPTa29/+9toRJjhjHgAAAACA3ti+fXtmZmae/Dr11FOzYcOG2rEmKOYBAAAAAOiN3bt3T9y/7777cuSRR+Ztb3tbpUQrOcoGAAAAAIBeu+yyy2pHmGDHPAAAAAAAvTE/P187wlR2zAMAAAAAQIvsmAcAgAMwGAxqR2ANo9EoSTI3N1c5CWtZntHs7GzlJAAAdSnmAQDgACwsLNSOwBRmBABA1znKBgAAAAAAWmTHPIyxu6r7zKj7zKj7zKj7zAgA4PDm/RwwjWIexjgztrucGdt9ZtR9ZtR9ZtRtzsYGAPaXfqH7fHhCbY6yAQAAAACAFinmAQAAAACgRYp5AAAAAABokWIeAAAAAABapJgHAAAAAIAWKeYBAAAAAKBFG2sHgC5ZWFioHYEpzKj7zKj7zKj7zAgA4PDm/RwwjWIexgwGg9oRWMNoNEqSzM3NVU7CWsyo+8yo+8yo25bnMzs7WzkJANB1+oXu8+EJtSnmAQAAAADojeuvvz579+5NkuzduzfPetaz8lu/9VsppVRO9lOKeQAAAAAAeuPP/uzPVqw98MADuf766yukWZ2LvwIAAAAA0GvnnXde7QgTFPMAAAAAAPTa8ccfXzvCBMU8AAAAAAC99q1vfat2hAnOmAcAgAMwGAxqR2ANo9EoSTI7O1s5CQAAXTMcDmtHmKCYBwCAA7CwsFA7AgAAcIC+/vWv5znPeU7tGE9ylA0AAAAAAL3WpVI+UcwDAAAAANBzTzzxRO0IExxlAwAAAABAb8zPz9eOMJViHgAAAABgHfnyl7+cW265pXaMdU0xDwAAAACwjrz73e/Oo48+WjvGuqaYBwAAAABYR26//fbs3r17xfquXbsqpFmfFPMAAAAAAOvIsccem3POOad2jHVtpnYAAAAAAABYTxTzAAAAAADQIsU8AAAAAAC0SDEPAAAAAAAtUswDAAAAAECLFPMAAAAAANAixTwAAAAAALRIMQ8AAAAAAC1SzAMAAAAAQIsU8wAAAAAA0CLFPAAAAAAAtEgxDwAAAAAALdpYOwAAAAAAABwsw+FwxdpHPvKRvPCFL6yQZnV2zAMAAAAA0GsnnHBC7QgT7JgHAAAAAKA35ufna0eYSjEPAAAAAEBvrHaUze23355TTz21QprVOcoGAAAAAIBeu+6662pHmKCYBwAAAACg197+9rfXjjDBUTYAAHAABoNB7QisYTQaJUlmZ2crJwEAoCZnzAMAQM8sLCzUjgAAADyF5WK+aZokyfHHH5+XvvSlKaXUjDVBMQ8AAAAAQG+8+93vXrH2jne8Y9WLwtaimAcAAAAAoDcuvPDCJ/+5lJItW7bkggsuqJhoJcU8AAAAAAC9cc0119SOMJViHgAAAACA3ljtyJqrr746F110UYU0q1PMAwDAARgMBrUjsIbRaJQkmZ2drZwEAICu+dGPflQ7wgTFPAAAHICFhYXaEQAAgAP04he/uHaECTO1AwAAAAAAwKH08MMP144wwY55AAAAAAB6Y35+vnaEqeyYBwAAAACAFinmAQAAAACgRYp5AAAAAABokWIeAAAAAABa5OKvMGZhYaF2BKYwo+4zo+4zo+4zIwCAw5v3c8A0inkYMxgMakdgDaPRKEkyNzdXOQlrMaPuM6PuM6NuW57P7Oxs5SQAQNfpF7rPhyfU5igbAAAAAABokWIeAAAAAABapJgHAAAAAIAWKeYBAAAAAKBFinkAAAAAAGiRYh4AAAAAAFqkmAcAAAAAgBYp5gEAAAAAoEWKeQAAAAAAaJFiHgAAAAAAWqSYBwAAAACAFinmAQAAAACgRYp5AAAAAABokWIeAAAAAABapJgHAAAAAIAWKeYBAAAAAKBFG2sHAACAw8lgMKgdgTWMRqMkydzcXOUkrGV5RrOzs5WTAADUpZiHMQsLC7UjMIUZdZ8ZdZ8ZdZ8ZdZv5dJ8ZAVCb/y8CplHMwxg74LrLDrjuM6PuM6PuM6Nus9MXANhf+oXu8+EJtTljHgAAAAAAWmTHPIzxaWn3mVH3mVH3mVH3mREAwOHN+zlgGsU8jPGrZt3leIfuM6PuM6PuM6Nuc5QNALC/9Avd58MTanOUDQAAAAAAtEgxDwAAAAAALVLMAwAAAABAixTzAAAAAADQIsU8AAAAAAC0aGPtAAAAAAAAtOczn/lM3vve99aOsa7ZMQ8AAAAAsI7cfvvttSOse3bMAwAAAACsI7fddtuq68PhsOUk65cd8wAAAAAA0CLFPAAAAAAAtEgxDwAAAAAALVLMAwAAAABAixTzAAAAAADQIsU8AAAAAAC0SDEPAAAAAAAtUswDAAAAAECLFPMAAAAAANAixTwAAAAAALRIMQ8AAAAAAC1SzAMAAAAAQIs21g4AAAAAAAAHy7XXXpuZmZmUUlJKyZYtW/KGN7whGzd2pw7vThIAAAAAAPj/6XOf+9yKtcceeyxvectbKqRZnaNsAAAAAADotUsvvbR2hAl2zAMAAAAA0Bvz8/O1I0ylmAcAAAAAoDeGw+GKteuvvz4ve9nLKqRZnaNsAAAAAADotZtvvrl2hAmKeQAAAAAAem3btm21I0xwlA0AAAAAAL2xdevWbNiwIRs2bMjMzEy2bduWq666qnasCYp5AAAAAAB644477qgdYSpH2QAAAAAAQIsU8wAAAAAA0CJH2QAAAAAA0BvD4XDF2mg0yotf/OIKaVZnxzwAAAAAAL01MzOTrVu31o4xwY55AAAAAAB6Y35+vnaEqeyYBwAAAACAFinmAQAAAACgRYp5AAAAAABokWIeAAAAAABapJgHAAAAAIAWKeYBAAAAAKBFG2sHgC5ZWFioHYEpzKj7zKj7zKj7zAgA4PDm/RwwjWIexgwGg9oRWMNoNEqSzM3NVU7CWsyo+8yo+8yo25bnMzs7WzkJANB1+oXu8+EJtTnKBgAAAAAAWqSYBwAAAACAFinmAQAAAACgRYp5AAAAAABokWIeAAAAAABapJgHAAAAAIAWbawdAAAAAAAADpbbbrtt4v6JJ56YX/qlX8rMTHf2qSvmYczCwkLtCExhRt1nRt1nRt1nRgAAhzfv56CuW2+9dcXaMccck1e84hUV0qxOMQ9jBoNB7QisYTQaJUnm5uYqJ2EtZtR9ZtR9ZtRty/OZnZ2tnAQA6Dr9Qvf58GT9KaXUjjBBMQ8AAAAAQG9ccsklaZomSdI0TU466aRceOGFlVNNUswDAAAAANAbV155Ze0IUynmYYxfY+o+M+o+M+o+M+o+MwIAOLx5P0fX/d7v/V6+8IUv1I6xrinmYYwz4LrLucvdZ0bdZ0bdZ0bd5ox5AGB/6Re6b71/eHLGGWco5itTzAMAAAAArCOXXXZZLrvsshXrw+GwQpr1aaZ2AAAAAAAAWE8U8wAAAAAA0CLFPAAAAAAAtEgxDwAAAAAALVLMAwAAAABAixTzAAAAAADQIsU8AAAAAAC0SDEPAAAAAAAtUswDAAAAAECLFPMAAAAAANCijbUDAAAAAADAwTIcDles3XrrrXnOc57Tfpg12DEPAAAAAECv/dVf/VXtCBPsmIcxCwsLtSMwhRl1nxl1nxl1nxkBABzevJ+D7vmTP/mTvPrVr64d40mKeRgzGAxqR2ANo9EoSTI3N1c5CWsxo+4zo+4zo25bns/s7GzlJABA1+kXus+HJ+vPgw8+WDvCBEfZAAAAAABAixTzAAAAAAD02oUXXlg7wgTFPAAAAAAAvfaNb3yjdoQJinkAAAAAAHrtzDPPrB1hgmIeAAAAAIBe2759e+0IExTzAAAAAAD02kc/+tHaESYo5gEAAAAA6LWuFfMbawcAAAAAAICDZX5+vnaEqeyYBwAAAACAFinmAQAAAACgRYp5AAAAAABokWIeAAAAAABapJgHAAAAAIAWKeYBAAAAAKBFinkAAAAAAGiRYh4AAAAAAFqkmAcAAAAAgBYp5gEAAAAAoEWKeQAAAAAAaJFiHgAAAAAAWqSYBwAAAACAFinmAQAAAACgRYp5AAAAAABokWIeAAAAAABapJgHAAAAAIAWKeYBAAAAAKBFinkAAAAAAGiRYh4AAAAAAFqkmAcAAAAAgBYp5gEAAAAAoEWKeQAAAAAAaNHG2gEAAAAAAOBg+eEPf5hSSkopSZINGzbkyCOPrJxqkmIeAAAAAIDeuOSSS1asve9978uOHTsqpFmdYh4AAAAAgN445phj0jRNkqRpmmzbti3Pe97zKqeapJgHAAAAAKA37rrrrtoRpnLxVwAAAAAAaJFiHgAAAAAAWuQoGwAAAACAdeSWW27JJz7xidoxDpnhcLhi7QMf+EDOPffcCmlWZ8c8AAAAAMA6snv37toRWnXCCSfk2c9+du0YE+yYBwAAAABYR6677rpV11fbaX44mp+frx1hKjvmAQAAAACgRYp5AAAAAABokWIeAAAAAABapJgHAAAAAIAWKeYBAAAAAKBFinkAAAAAAGiRYh4AAAAAAFq0sXYAAAAAAAA4WIbD4Yq1P/qjP8ppp51W933JRgAADFBJREFUIc3q7JgHAAAAAKDXdu/eXTvCBMU8AAAAAAC9duyxx9aOMEExDwAAAABAr33zm9+sHWGCYh4AAAAAgF57wQteUDvCBMU8AAAAAAC9dt9999WOMEExDwAAAABAr33/+9+vHWGCYh4AAAAAgF57/vOfXzvCBMU8AAAAAAC9duaZZ9aOMEExDwAAAABAr33605+uHWGCYh4AAAAAgF4799xza0eYoJgHAAAAAKDX/vZv/7Z2hAmKeQAAAAAAem3Hjh21I0zYWDsAAAAAAAAcLPPz87UjTGXHPAAAAAAAvXDEEUfUjrBf7JiHMQsLC7UjMIUZdZ8ZdZ8ZdZ8ZAQAc3ryfg3qeeOKJg/ZapZSdSd6W5B8kOSXJG5um+fjS945Icm2SVyU5M8n/k2Q+ye80TfONaa+tmIcxg8GgdgTWMBqNkiRzc3OVk7AWM+o+M+o+M+q25fnMzs5WTgIAdJ1+oft8eMJ+Oj7JV5LctvQ17tgkL0nyz5J8OcnTkrw/yb8ppZzTNM1PnuqFFfMwxr+Uu8+Mus+Mus+Mus+MAAAOb97PQXfs2bMn99xzTx544IE897nPzY4dO7Jhw4b9em7TNHcluStJSikf3+d7P0jyn4+vlVJ+O8l/THJWkv/wVK+tmIcxPtHuLrtIu8+Mus+Mus+Mus2OeQBgf+kXus+HJ+vDnj17ctVVV+X+++/P448/nqOPPjpnnXVWbrjhhv0u5w/QpqXbR6c9UDEPAAAAAEBvDIfDVdcfe+yx3Hfffbnnnnty/vnnH9SfWUo5MotH2fzrpmm+Oe3xMwf1pwMAAAAAQEf96Ec/yu7duw/qa5ZSNia5PcnmJG/cn+fYMQ8AAAAAQG/Mz88nSe6+++685z3vyWOPPfbk94466qhs3779oP2spVL+Xyb5+SSDpmke3p/n2TEPAAAAAEDv7NixI2eddVaOPvrolFJy9NFH54UvfGF27NhxUF6/lHJEkn+V5Jwkw6Zpvr2/z7VjHgAAAACA3tmwYUNuuOGG3HPPPdm9e3e2b9+eHTt27PeFX0spxydZ3l4/k+S0UspskkeS/G2SP07y0iS/nKQppTxz6bE/aJrmsX1fb5xiHgAAAACAXtqwYUPOP//8n/Vir+clmR+7/66lrz9Kck2SVy+t/x/7PO+NST7+VC+smAcAAAAAgH00TbOQpDzFQ57qe0/JGfMAAAAAANAixTwAAAAAALRIMQ8AAAAAAC1SzAMAAAAAQIsU8wAAAAAA0CLFPAAAAAAAtEgxDwAAAAAALVLMAwAAAABAixTzAAAAAADQov0u5kspf11Kadb4+vYaz3l5KeWuUsojpZS/L6XcW0qZK6VsWOPxZ5RSPlZK+ZtSyo9LKd8upfzLUsoLpmR7TinlplLKg6WUx0spD5dS/n0p5co1Hv9LpZTPlFK+WUp5bOl5f1xKOX+Vxx5RStlVSrm1lPLlpVxNKeW/3Z+/NwAAAAAAGLfxAB//gySjVdb/074LpZRXJ/kfkzye5F8leSTJLye5MckFSf6rfR7/kiTzSTYl+bdJ7kiyLclrk/xyKeUVTdN8cZWf88ok/9PSn+VPl37W8Umen+QfJXn/Po9/X5Krkjyc5FNJvpdke5JXJ3ltKeUNTdPcPvaU48b+zH+X5NtLuQAAAAAAWlFK+d0k/2UWe88fJflikt9tmuYrVYPxMznQYv77TdNcM+1BpZRNSW5OsifJoGma/31p/eoslu6vK6X8atM0d4w97WNZLOXf2jTNjWOvdX6Szye5rZRydtM0T4x974wkn8xiyf6Kpmm+tk+OI/a5/8wkb8tiwX5O0zTfGfvecCnbu5OMF/N/n+S/SPLlpmm+VUq5Jsk7p/0dAAAAAAAcRIMkf5jkS0lKFnvMPy+lvLBpmkdqBuPAHaoz5l+X5OQkdyyX8knSNM3jSf77pbuXL68vFeyzSb6T5IPjL9Q0zd1JPp3kuUn+4T4/55os7o6/fN9Sfum5T+yzdHoW/8z/fryUX3rsfJL/dyn3+PqPm6b5X5qm+dZT/HkBAAAAAA6Zpmle2TTNrU3TfKVpmv+Q5L/JYpd5wYG8zp49e3L33Xfntttuy9133509e/Yckrw8tQPdMX9UKeU3kpyW5IdJ7k3y+aZp9p3eRUu3/2aV1/h8Fnehv7yUclTTND9K8syl7/110zR7V3nOg0u3Fyf518mTu+Ffl8Uy/65Syo4s/o9wY5L7k3ymaZof7/M6DyT5cZIdpZRnNE3zveVvlFJ2Jjkhi8fbAAAAAAB02QlZ3IT86P4+Yc+ePbnqqqty//335/HHH8/RRx+ds846KzfccEM2bFj1sqAcIgdazD8zySf2Wft6KeWNTdP8xdja85duV9vF/pNSyteTnJ3kjCyW6MsF+emllNI0TbPP085Yuh2/COyLkhyT5O4snkf/+n2e841SyuuapvnS2M9+pJTyT5N8IMl9pZRPZfEYnDOTXJrks0l+e/U/OgAAAABAZ3wwyZez2I/ul3vuuSf3339/HnvssSTJY489lnvvvTe///u/n9NOO+0QxWQ1ZWUHvsYDS3lnkn+X5D9m8ciXM5L8d0n+SRYv8Hp+0zR/tfTYr2Xx6JnnNk2ze5XX+t+SvDzJy5eOqkkp5atJnpdkV9M0Hxp77MuS/K9Z/BDhnqZpXra0/sos7sjfk+SxJLuyuNv9+CRvyeIFXr+X5KzxnfFLz31NkluSnDi2vDvJO5um+RdT/h6uyeIZ8/+4aZr/4akeCwAAAABwsJVSPpDkV5P8Z03TPDjt8cuGw+HVWTwefPyI871J3jk/P3/tQQ3JU9rvHfNN07xrn6WvJHlTKeU/JbkyiwP9R/v5cmX5ZcfWfjuLRfsHSym/nMVPe56dxSsN35fknCyW8Ms2jN3+btM0tyzdfyTJPy2lbF967j9O8t4nf3ApVyW5LsmHkvxBkm9ncSf+e5P881LKbNM0V+3nnwMAAAAAoDWllBuzWMoPD6SUT5L5+fn3JHnPIQnGATkYF3/96NLtzrG1HyzdPm2N52za53FpmmYhyY4kf5zFEn7X0v1rk1y99LDxC7aOn530P6/yM5bXdiwvlFIGSd6X5E+apnlr0zQPNk3z903T/GUWP1T4v5NcuXQxWgAAAACAziilfDDJryW5qGma/7N2Hn52B6OYXy7Ljxtb++rS7fP2fXApZWOSn0vyk/z0oq5JkqZp7m2a5vVN02xtmubIpmnObJrmPUn+wdJDvjT28K+O/fP3V8m1XNwfM7Z2ydLt/L4Pbprm75Pck8W/k3NXeT0AAAAAgCpKKR9J8sYk/3WSR0spz1z6Or5yNH4GB6OYP3/pdrxk/7dLt/9wlcfvTHJski80TfOjaS9eSjkqyRuyeNbRHcvrTdM8ksXjbpLFC8Hua3ntr8fWjlq6PXmNH7e8/uNpuQAAAAAAWvTmJCck+VySb419va1mKH42+1XMl1LOLqU8fZX107N4TnuS3D72rU9m8cKrv1pKOW/s8Udn8WiaJLlpn9c6rpSyYZ+1I5Ye95wkNzVN83/tE+EjS7f/bOm1l5/37CRXLN29Y+zx/27p9p+UUk7d52e9KskFWbyQ7Rf2/bMCAAAAANTSNE1Z4+v/a+8OXYRI4zCOf+dQMF8Q+4FyFu0Gy6U7kRXkMBoFg0bBss2sWe7w1iomBcVg8B+wqmCwi3DhFuF8De8GWdZzD2QMfj5x5jcz70x8GJ5381uvjf9vGWN8eWhZNqtrzQqY19Xf1U/Vb9Wh6mF1bozx/pNrNpoB/XYzHH9bna2O7Rz/fXzy8GVZzlS3qyfVm2YP/a/NUP5BdX6Msb1rXT9U96qN6kX1qFmps1H9WN0aY1zZNf+o+mXnHe43N3/9uVlzs1RXxxg3dz3nWnOD2KqT1YlmeP9y59izMcbtL35IAAAAAAC+e/sN5k9Xl5rd60ea4fe7ZpXMVrU19rjRsiynquvNuptD1avqj2Zg/u+u2aPVjeZmrYerf6rn1Z/VX2OMD59Z24HqcrNf6Wiz8uZ58w/7u3vMH9yZv1Adb9bqvG32y98aYzze45qn1enPfZ/qzhjj4n+cBwAAAACAap/BPAAAAAAA8HV8jc1fAQAAAACAfRLMAwAAAADAigTzAAAAAACwIsE8AAAAAACsSDAPAAAAAAArEswDAAAAAMCKBPMAAAAAALAiwTwAAAAAAKxIMA8AAAAAACsSzAMAAAAAwIo+Arj4/cQ883b8AAAAAElFTkSuQmCC\n",
            "text/plain": [
              "<Figure size 1800x720 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "1u6gJdKcX7Qv",
        "outputId": "943607cf-02ad-4871-ff60-74c50ccdf5e1"
      },
      "source": [
        "# Drop all rows that are missing 'driver_gender'\n",
        "ri.dropna(subset=['driver_gender'], inplace=True)\n",
        "print('\\n')\n",
        "# Count the number of missing values in each column (again)\n",
        "print(ri.isnull().sum())\n",
        "\n",
        "# Examine the shape of the DataFrame\n",
        "print(ri.shape)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\n",
            "\n",
            "district                   0\n",
            "driver_race                0\n",
            "driver_gender              0\n",
            "arrest_made                0\n",
            "citation_issued            0\n",
            "warning_issued             0\n",
            "contraband_drugs      464596\n",
            "contraband_weapons    468789\n",
            "contraband_alcohol    479367\n",
            "frisk_performed            0\n",
            "search_conducted           0\n",
            "reason_for_stop            0\n",
            "dtype: int64\n",
            "(480584, 12)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RjeXIcYgX7Qx"
      },
      "source": [
        "# check unique value in contraband_ column\n",
        "ri.contraband_drugs.replace(np.nan, False, inplace= True)\n",
        "ri.contraband_weapons.replace(np.nan, False, inplace= True)\n",
        "ri.contraband_alcohol.replace(np.nan, False, inplace= True)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eNIXVZ1xX7Qz",
        "outputId": "c521ebb1-d4af-4ce9-bb1c-f4e0373e52a1"
      },
      "source": [
        "ri.isnull().sum()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "district              0\n",
              "driver_race           0\n",
              "driver_gender         0\n",
              "arrest_made           0\n",
              "citation_issued       0\n",
              "warning_issued        0\n",
              "contraband_drugs      0\n",
              "contraband_weapons    0\n",
              "contraband_alcohol    0\n",
              "frisk_performed       0\n",
              "search_conducted      0\n",
              "reason_for_stop       0\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "iXIp45puX7Q1",
        "outputId": "28484480-1efd-481b-dc8b-3c74e30a3a4c"
      },
      "source": [
        "msno.matrix(ri)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x1ee654623d0>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1800x720 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "G7AKHLHgX7Q3"
      },
      "source": [
        "## check posible value type and how many value in each column"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "XxbQXYp8X7Q4",
        "outputId": "ddf8ad81-a94d-4700-b4ea-62e0f0ab9896"
      },
      "source": [
        "for i in ri.columns:\n",
        "#     if i != 'raw_row_number' and i != 'date' and i != 'time' and i != 'department_id' and i != 'vehicle_make' and i != 'vehicle_model' and i != 'raw_BasisForStop'and i != 'raw_SearchResultOne' and i != 'raw_SearchResultTwo' and i != 'raw_SearchResultThree':\n",
        "        print(ri[i].value_counts())"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "X4    125670\n",
            "K3    108868\n",
            "K2     97281\n",
            "X3     89431\n",
            "K1     46110\n",
            "X1     13224\n",
            "Name: district, dtype: int64\n",
            "white                     344716\n",
            "black                      68577\n",
            "hispanic                   53123\n",
            "asian/pacific islander     12824\n",
            "other                       1344\n",
            "Name: driver_race, dtype: int64\n",
            "male      349446\n",
            "female    131138\n",
            "Name: driver_gender, dtype: int64\n",
            "False    463981\n",
            "True      16603\n",
            "Name: arrest_made, dtype: int64\n",
            "True     428378\n",
            "False     52206\n",
            "Name: citation_issued, dtype: int64\n",
            "False    451744\n",
            "True      28840\n",
            "Name: warning_issued, dtype: int64\n",
            "False    475819\n",
            "True       4765\n",
            "Name: contraband_drugs, dtype: int64\n",
            "False    480085\n",
            "True        499\n",
            "Name: contraband_weapons, dtype: int64\n",
            "False    479464\n",
            "True       1120\n",
            "Name: contraband_alcohol, dtype: int64\n",
            "0.0    471262\n",
            "1.0      9322\n",
            "Name: frisk_performed, dtype: int64\n",
            "False    462822\n",
            "True      17762\n",
            "Name: search_conducted, dtype: int64\n",
            "Speeding                            268736\n",
            "Other Traffic Violation              90228\n",
            "Equipment/Inspection Violation       61250\n",
            "Registration Violation               19830\n",
            "Seatbelt Violation                   16324\n",
            "Special Detail/Directed Patrol       13642\n",
            "Call for Service                      7605\n",
            "Violation of City/Town Ordinance      1036\n",
            "Motorist Assist/Courtesy               989\n",
            "APB                                    485\n",
            "Suspicious Person                      342\n",
            "Warrant                                117\n",
            "Name: reason_for_stop, dtype: int64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wwZzF8cSX7Q6"
      },
      "source": [
        "## Using proper dtype"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RZjKGOufX7Q6",
        "outputId": "bb13c89c-0c77-4554-b117-b8a9676e458b"
      },
      "source": [
        "#arrest_made is object then should be change to 'bool'\n",
        "\n",
        "ri['district'] = ri.district.astype('category')\n",
        "ri['driver_race'] = ri.driver_race.astype('category')\n",
        "ri['driver_gender'] = ri.driver_gender.astype('category')\n",
        "ri['arrest_made'] = ri.arrest_made.astype('bool')\n",
        "ri['citation_issued'] = ri.citation_issued.astype('bool')\n",
        "ri['warning_issued'] = ri.warning_issued.astype('bool')\n",
        "ri['frisk_performed'] = ri.frisk_performed.astype('bool')\n",
        "\n",
        "ri['reason_for_stop'] = ri.reason_for_stop.astype('category')\n",
        "\n",
        "print(ri.dtypes)\n",
        "print('\\n')"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "district              category\n",
            "driver_race           category\n",
            "driver_gender         category\n",
            "arrest_made               bool\n",
            "citation_issued           bool\n",
            "warning_issued            bool\n",
            "contraband_drugs          bool\n",
            "contraband_weapons        bool\n",
            "contraband_alcohol        bool\n",
            "frisk_performed           bool\n",
            "search_conducted          bool\n",
            "reason_for_stop       category\n",
            "dtype: object\n",
            "\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "yf7-tDFZX7Q8"
      },
      "source": [
        "# change index to timestamp format\n",
        "ri.index = pd.to_datetime(ri.index)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fwjQ4vr6X7Q-",
        "outputId": "bb45933d-1451-41a2-e8c4-51f085ce7c35"
      },
      "source": [
        "#check info() for memory usage reduce when group into proper dtype.\n",
        "print('previously memory usage: 40+ ish MB', '\\n')\n",
        "ri.info()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "previously memory usage: 40+ ish MB \n",
            "\n",
            "<class 'pandas.core.frame.DataFrame'>\n",
            "DatetimeIndex: 480584 entries, 2005-11-22 11:15:00 to 2015-10-30 11:09:00\n",
            "Data columns (total 12 columns):\n",
            " #   Column              Non-Null Count   Dtype   \n",
            "---  ------              --------------   -----   \n",
            " 0   district            480584 non-null  category\n",
            " 1   driver_race         480584 non-null  category\n",
            " 2   driver_gender       480584 non-null  category\n",
            " 3   arrest_made         480584 non-null  bool    \n",
            " 4   citation_issued     480584 non-null  bool    \n",
            " 5   warning_issued      480584 non-null  bool    \n",
            " 6   contraband_drugs    480584 non-null  bool    \n",
            " 7   contraband_weapons  480584 non-null  bool    \n",
            " 8   contraband_alcohol  480584 non-null  bool    \n",
            " 9   frisk_performed     480584 non-null  bool    \n",
            " 10  search_conducted    480584 non-null  bool    \n",
            " 11  reason_for_stop     480584 non-null  category\n",
            "dtypes: bool(8), category(4)\n",
            "memory usage: 9.2 MB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6GYmsC11X7RA",
        "outputId": "26bc85d8-8528-4008-fbe8-2e6c8ff68707"
      },
      "source": [
        "ri.head()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>district</th>\n",
              "      <th>driver_race</th>\n",
              "      <th>driver_gender</th>\n",
              "      <th>arrest_made</th>\n",
              "      <th>citation_issued</th>\n",
              "      <th>warning_issued</th>\n",
              "      <th>contraband_drugs</th>\n",
              "      <th>contraband_weapons</th>\n",
              "      <th>contraband_alcohol</th>\n",
              "      <th>frisk_performed</th>\n",
              "      <th>search_conducted</th>\n",
              "      <th>reason_for_stop</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>date_stop_time</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>2005-11-22 11:15:00</th>\n",
              "      <td>X3</td>\n",
              "      <td>white</td>\n",
              "      <td>male</td>\n",
              "      <td>False</td>\n",
              "      <td>True</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>Speeding</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2005-10-01 12:20:00</th>\n",
              "      <td>X3</td>\n",
              "      <td>white</td>\n",
              "      <td>male</td>\n",
              "      <td>False</td>\n",
              "      <td>True</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>Speeding</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2005-10-01 12:30:00</th>\n",
              "      <td>X3</td>\n",
              "      <td>white</td>\n",
              "      <td>female</td>\n",
              "      <td>False</td>\n",
              "      <td>True</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>Speeding</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2005-10-01 12:50:00</th>\n",
              "      <td>X3</td>\n",
              "      <td>white</td>\n",
              "      <td>male</td>\n",
              "      <td>False</td>\n",
              "      <td>True</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>Speeding</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2005-10-01 13:10:00</th>\n",
              "      <td>X3</td>\n",
              "      <td>white</td>\n",
              "      <td>female</td>\n",
              "      <td>False</td>\n",
              "      <td>True</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>Speeding</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                    district driver_race driver_gender  arrest_made  \\\n",
              "date_stop_time                                                        \n",
              "2005-11-22 11:15:00       X3       white          male        False   \n",
              "2005-10-01 12:20:00       X3       white          male        False   \n",
              "2005-10-01 12:30:00       X3       white        female        False   \n",
              "2005-10-01 12:50:00       X3       white          male        False   \n",
              "2005-10-01 13:10:00       X3       white        female        False   \n",
              "\n",
              "                     citation_issued  warning_issued  contraband_drugs  \\\n",
              "date_stop_time                                                           \n",
              "2005-11-22 11:15:00             True           False             False   \n",
              "2005-10-01 12:20:00             True           False             False   \n",
              "2005-10-01 12:30:00             True           False             False   \n",
              "2005-10-01 12:50:00             True           False             False   \n",
              "2005-10-01 13:10:00             True           False             False   \n",
              "\n",
              "                     contraband_weapons  contraband_alcohol  frisk_performed  \\\n",
              "date_stop_time                                                                 \n",
              "2005-11-22 11:15:00               False               False            False   \n",
              "2005-10-01 12:20:00               False               False            False   \n",
              "2005-10-01 12:30:00               False               False            False   \n",
              "2005-10-01 12:50:00               False               False            False   \n",
              "2005-10-01 13:10:00               False               False            False   \n",
              "\n",
              "                     search_conducted reason_for_stop  \n",
              "date_stop_time                                         \n",
              "2005-11-22 11:15:00             False        Speeding  \n",
              "2005-10-01 12:20:00             False        Speeding  \n",
              "2005-10-01 12:30:00             False        Speeding  \n",
              "2005-10-01 12:50:00             False        Speeding  \n",
              "2005-10-01 13:10:00             False        Speeding  "
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "efhvbGuXX7RC",
        "outputId": "d74ff4e6-4e6d-4ca5-cb96-e06f7c29ccd8"
      },
      "source": [
        "# check type of index and columns\n",
        "print(ri.index)\n",
        "print(ri.columns)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "DatetimeIndex(['2005-11-22 11:15:00', '2005-10-01 12:20:00',\n",
            "               '2005-10-01 12:30:00', '2005-10-01 12:50:00',\n",
            "               '2005-10-01 13:10:00', '2005-10-01 15:50:00',\n",
            "               '2005-09-11 11:45:00', '2005-09-11 11:45:00',\n",
            "               '2005-10-04 11:55:00', '2005-10-04 11:55:00',\n",
            "               ...\n",
            "               '2015-12-29 13:28:00', '2015-12-27 12:45:00',\n",
            "               '2015-12-27 13:43:00', '2015-12-28 02:29:00',\n",
            "               '2015-12-30 11:42:00', '2015-08-16 13:37:00',\n",
            "               '2015-08-04 10:40:00', '2015-12-20 11:17:00',\n",
            "               '2015-11-09 23:35:00', '2015-10-30 11:09:00'],\n",
            "              dtype='datetime64[ns]', name='date_stop_time', length=480584, freq=None)\n",
            "Index(['district', 'driver_race', 'driver_gender', 'arrest_made',\n",
            "       'citation_issued', 'warning_issued', 'contraband_drugs',\n",
            "       'contraband_weapons', 'contraband_alcohol', 'frisk_performed',\n",
            "       'search_conducted', 'reason_for_stop'],\n",
            "      dtype='object')\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "AuCxpnANX7RF",
        "outputId": "52c7620a-d37a-4406-c07b-49a0517a1849"
      },
      "source": [
        "# check for general statistics\n",
        "ri.describe()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>district</th>\n",
              "      <th>driver_race</th>\n",
              "      <th>driver_gender</th>\n",
              "      <th>arrest_made</th>\n",
              "      <th>citation_issued</th>\n",
              "      <th>warning_issued</th>\n",
              "      <th>contraband_drugs</th>\n",
              "      <th>contraband_weapons</th>\n",
              "      <th>contraband_alcohol</th>\n",
              "      <th>frisk_performed</th>\n",
              "      <th>search_conducted</th>\n",
              "      <th>reason_for_stop</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>480584</td>\n",
              "      <td>480584</td>\n",
              "      <td>480584</td>\n",
              "      <td>480584</td>\n",
              "      <td>480584</td>\n",
              "      <td>480584</td>\n",
              "      <td>480584</td>\n",
              "      <td>480584</td>\n",
              "      <td>480584</td>\n",
              "      <td>480584</td>\n",
              "      <td>480584</td>\n",
              "      <td>480584</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>unique</th>\n",
              "      <td>6</td>\n",
              "      <td>5</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "      <td>12</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>top</th>\n",
              "      <td>X4</td>\n",
              "      <td>white</td>\n",
              "      <td>male</td>\n",
              "      <td>False</td>\n",
              "      <td>True</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>Speeding</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>freq</th>\n",
              "      <td>125670</td>\n",
              "      <td>344716</td>\n",
              "      <td>349446</td>\n",
              "      <td>463981</td>\n",
              "      <td>428378</td>\n",
              "      <td>451744</td>\n",
              "      <td>475819</td>\n",
              "      <td>480085</td>\n",
              "      <td>479464</td>\n",
              "      <td>471262</td>\n",
              "      <td>462822</td>\n",
              "      <td>268736</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "       district driver_race driver_gender arrest_made citation_issued  \\\n",
              "count    480584      480584        480584      480584          480584   \n",
              "unique        6           5             2           2               2   \n",
              "top          X4       white          male       False            True   \n",
              "freq     125670      344716        349446      463981          428378   \n",
              "\n",
              "       warning_issued contraband_drugs contraband_weapons contraband_alcohol  \\\n",
              "count          480584           480584             480584             480584   \n",
              "unique              2                2                  2                  2   \n",
              "top             False            False              False              False   \n",
              "freq           451744           475819             480085             479464   \n",
              "\n",
              "       frisk_performed search_conducted reason_for_stop  \n",
              "count           480584           480584          480584  \n",
              "unique               2                2              12  \n",
              "top              False            False        Speeding  \n",
              "freq            471262           462822          268736  "
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "7h-lYYRJX7RH"
      },
      "source": [
        "## Exploring the relationship between driver gender and policing"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "E_pNpRP-X7RI",
        "outputId": "e8f393f9-7584-4cb7-fad1-d46ffba9c47e"
      },
      "source": [
        "# Count the unique values in 'violation'\n",
        "print(ri.reason_for_stop.value_counts())\n",
        "print('\\n')\n",
        "\n",
        "# Express the counts as proportions\n",
        "print(ri.reason_for_stop.value_counts(normalize= True))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Speeding                            268736\n",
            "Other Traffic Violation              90228\n",
            "Equipment/Inspection Violation       61250\n",
            "Registration Violation               19830\n",
            "Seatbelt Violation                   16324\n",
            "Special Detail/Directed Patrol       13642\n",
            "Call for Service                      7605\n",
            "Violation of City/Town Ordinance      1036\n",
            "Motorist Assist/Courtesy               989\n",
            "APB                                    485\n",
            "Suspicious Person                      342\n",
            "Warrant                                117\n",
            "Name: reason_for_stop, dtype: int64\n",
            "\n",
            "\n",
            "Speeding                            0.559186\n",
            "Other Traffic Violation             0.187747\n",
            "Equipment/Inspection Violation      0.127449\n",
            "Registration Violation              0.041262\n",
            "Seatbelt Violation                  0.033967\n",
            "Special Detail/Directed Patrol      0.028386\n",
            "Call for Service                    0.015824\n",
            "Violation of City/Town Ordinance    0.002156\n",
            "Motorist Assist/Courtesy            0.002058\n",
            "APB                                 0.001009\n",
            "Suspicious Person                   0.000712\n",
            "Warrant                             0.000243\n",
            "Name: reason_for_stop, dtype: float64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Et-AM5ojX7RK",
        "outputId": "f6c268b5-f279-4cf6-ecd2-bb3eb88f3c9b"
      },
      "source": [
        "ri.reason_for_stop.value_counts(normalize= True).plot(kind='bar', figsize=(12,5))\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x360 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "C34f2TKIX7RM"
      },
      "source": [
        "## separate by driver_gender"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7eDvdXd5X7RM",
        "outputId": "17d5d495-e373-4a70-edb2-36fcc1e3ea4a"
      },
      "source": [
        "# slice to new df as only female and male DataFrame\n",
        "female = ri[ri.driver_gender == 'female']\n",
        "male = ri[ri.driver_gender == 'male']\n",
        "\n",
        "# value_counts(normalize= True) on reason_for_stop\n",
        "print('female reason_for_stop counts \\n', female.reason_for_stop.value_counts(normalize= True))\n",
        "print('\\n')\n",
        "print('male reason_for_stop counts \\n', male.reason_for_stop.value_counts(normalize=True))\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "female reason_for_stop counts \n",
            " Speeding                            0.657308\n",
            "Other Traffic Violation             0.136581\n",
            "Equipment/Inspection Violation      0.107055\n",
            "Registration Violation              0.043077\n",
            "Seatbelt Violation                  0.027071\n",
            "Call for Service                    0.018057\n",
            "Special Detail/Directed Patrol      0.005071\n",
            "Motorist Assist/Courtesy            0.002532\n",
            "Violation of City/Town Ordinance    0.001647\n",
            "APB                                 0.000831\n",
            "Suspicious Person                   0.000564\n",
            "Warrant                             0.000206\n",
            "Name: reason_for_stop, dtype: float64\n",
            "\n",
            "\n",
            "male reason_for_stop counts \n",
            " Speeding                            0.522364\n",
            "Other Traffic Violation             0.206948\n",
            "Equipment/Inspection Violation      0.135102\n",
            "Registration Violation              0.040581\n",
            "Special Detail/Directed Patrol      0.037136\n",
            "Seatbelt Violation                  0.036555\n",
            "Call for Service                    0.014987\n",
            "Violation of City/Town Ordinance    0.002347\n",
            "Motorist Assist/Courtesy            0.001880\n",
            "APB                                 0.001076\n",
            "Suspicious Person                   0.000767\n",
            "Warrant                             0.000258\n",
            "Name: reason_for_stop, dtype: float64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0rVttaZ7X7RO",
        "outputId": "86a66fb5-6581-4e34-bda8-38788d39a2b6"
      },
      "source": [
        "# Create 2 subplot to compare female and male case for reasone to stop\n",
        "fig, ax = plt.subplots(1,2, figsize=(18,5), sharey= True)\n",
        "ax[0].bar(female.reason_for_stop.value_counts(normalize= True).index, female.reason_for_stop.value_counts(normalize= True))\n",
        "ax[1].bar(male.reason_for_stop.value_counts(normalize= True).index, male.reason_for_stop.value_counts(normalize= True))\n",
        "ax[0].set_title('female')\n",
        "ax[1].set_title('male')\n",
        "plt.setp(ax[0].xaxis.get_majorticklabels(), rotation=90)\n",
        "plt.setp(ax[1].xaxis.get_majorticklabels(), rotation=90)\n",
        "plt.tight_layout()\n",
        "\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1296x360 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "bcr99YlhX7RQ"
      },
      "source": [
        "<b><i> the female speeding case is more than male?</i></b>\n",
        "\n",
        "from 'bar chart show the speeding violate by female more than 65 percent."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "apSzrNBSX7RQ",
        "outputId": "3b753293-2493-4eb4-b95a-417d2aca2c39"
      },
      "source": [
        "# find out how many male and femele for further investigation\n",
        "print('male on record {} males'.format(male.shape[0]))\n",
        "print('female on record :',female.shape[0], '\\n')\n",
        "print('=> male and female proportion is different.')"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "male on record 349446 males\n",
            "female on record : 131138 \n",
            "\n",
            "=> male and female proportion is different.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "U7gweNEHX7RS"
      },
      "source": [
        "# Create a DataFrame of female drivers stopped for speeding\n",
        "female_and_speeding = ri[(ri.driver_gender == 'female') & (ri.reason_for_stop == 'Speeding')]\n",
        "\n",
        "# Create a DataFrame of male drivers stopped for speeding\n",
        "male_and_speeding = ri[(ri.driver_gender == 'male') & (ri.reason_for_stop == 'Speeding')]"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CCYAB0khX7RU",
        "outputId": "24549a3e-a663-48a5-e766-7b27281b8bbd"
      },
      "source": [
        "# Compute the stop outcomes for female drivers (as proportions)\n",
        "print(female_and_speeding.citation_issued.value_counts(normalize= True))\n",
        "\n",
        "# Compute the stop outcomes for male drivers (as proportions)\n",
        "print(male_and_speeding.citation_issued.value_counts(normalize= True))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "True     0.953247\n",
            "False    0.046753\n",
            "Name: citation_issued, dtype: float64\n",
            "True     0.944636\n",
            "False    0.055364\n",
            "Name: citation_issued, dtype: float64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ONyoYPtCX7RW"
      },
      "source": [
        "### <i>the data fails to show that gender has an impact on who gets a ticket for speeding.</i>\n",
        "<i><b>The numbers are similar for males and females: about 95% of stops for speeding result in a ticket. Thus, </i></b>  \n",
        "<i>So, be careful on assume the comparison on different sample size."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "xXjIaH6JX7RX"
      },
      "source": [
        "## Does gender affect whose vehicle is searched?\n",
        "\n",
        ".value_counts() will separate the count for each in pd.series , count() is count every datapoint"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_UK5GorbX7RX",
        "outputId": "c7a8ad5a-97a6-43c0-cb4d-aa8e2ad63ee8"
      },
      "source": [
        "# Check the data type of 'search_conducted'\n",
        "print(ri.search_conducted.dtypes)\n",
        "\n",
        "# Calculate the search rate by counting the values\n",
        "print(ri.search_conducted.value_counts(normalize=True))\n",
        "\n",
        "# Calculate the search rate by taking the mean\n",
        "print(ri.search_conducted.mean())"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "bool\n",
            "False    0.963041\n",
            "True     0.036959\n",
            "Name: search_conducted, dtype: float64\n",
            "0.036959199640437465\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "MhWcwy0mX7Ra"
      },
      "source": [
        " the search rate is about 3.8%."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "CDikEkm5X7Ra"
      },
      "source": [
        "## Is the search rate varies by driver gender."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-NagurUBX7Ra",
        "outputId": "dd36d9aa-34aa-4fc1-a727-f28248e6f823"
      },
      "source": [
        "# Calculate the search rate for both groups simultaneously\n",
        "print(ri.groupby('driver_gender').search_conducted.mean())\n",
        "print('\\n')\n",
        "\n",
        "# calculate by mean with out groupby() วิธีที่สองได้ผมเหมือนกัน\n",
        "# print(ri[ri.driver_gender=='female'].search_conducted.mean())\n",
        "# print(ri[ri.driver_gender=='male'].search_conducted.mean())\n",
        "print('search was conducted in male 4.4 percent and in female 1.9 percent')"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "driver_gender\n",
            "female    0.018751\n",
            "male      0.043792\n",
            "Name: search_conducted, dtype: float64\n",
            "\n",
            "\n",
            "search was conducted in male 4.4 percent and in female 1.9 percent\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "VdM5f65pX7Rc"
      },
      "source": [
        "## compare Search_conduct rate that consequence from reason_for_stop and driver_gender\n",
        "\n",
        "<b>An all-points bulletin (APB)</b> is a broadcast issued from any American or Canadian law enforcement agency to its personnel, or to other law enforcement agencies. It typically contains information about a wanted suspect who is to be arrested or a person of interest, for whom law enforcement officers are to look. They are usually dangerous or missing persons. As used by American police  \n",
        "\n",
        "An all-points bulletin can also be known as a BOLO or BOL, which stands for \"be on (the) look-out\". Such an alert may also be called a lookout or ATL (\"attempt to locate\")."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "KB2GDk5BX7Rd",
        "outputId": "f60c0188-b3ad-4bcb-8df5-e6f3cafa2d8d"
      },
      "source": [
        "# Calculate the search rate for each combination of gender and violation\n",
        "print(ri.groupby(['driver_gender', 'reason_for_stop']).search_conducted.mean())"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "driver_gender  reason_for_stop                 \n",
            "female         APB                                 0.165138\n",
            "               Call for Service                    0.042230\n",
            "               Equipment/Inspection Violation      0.040245\n",
            "               Motorist Assist/Courtesy            0.033133\n",
            "               Other Traffic Violation             0.038021\n",
            "               Registration Violation              0.054700\n",
            "               Seatbelt Violation                  0.017746\n",
            "               Special Detail/Directed Patrol      0.018045\n",
            "               Speeding                            0.007738\n",
            "               Suspicious Person                   0.216216\n",
            "               Violation of City/Town Ordinance    0.060185\n",
            "               Warrant                             0.148148\n",
            "male           APB                                 0.255319\n",
            "               Call for Service                    0.092419\n",
            "               Equipment/Inspection Violation      0.070916\n",
            "               Motorist Assist/Courtesy            0.089802\n",
            "               Other Traffic Violation             0.059156\n",
            "               Registration Violation              0.103589\n",
            "               Seatbelt Violation                  0.031705\n",
            "               Special Detail/Directed Patrol      0.010249\n",
            "               Speeding                            0.026630\n",
            "               Suspicious Person                   0.305970\n",
            "               Violation of City/Town Ordinance    0.073171\n",
            "               Warrant                             0.311111\n",
            "Name: search_conducted, dtype: float64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Jsc7sZvTX7Re"
      },
      "source": [
        "it hard to compare between gender , re order of groupby"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "scrolled": true,
        "id": "on0U5CxtX7Rf",
        "outputId": "f5b7656e-04e7-41da-b02a-4528e5f937bb"
      },
      "source": [
        "ri.groupby(['reason_for_stop', 'driver_gender']).search_conducted.mean().head(30)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "reason_for_stop                   driver_gender\n",
              "APB                               female           0.165138\n",
              "                                  male             0.255319\n",
              "Call for Service                  female           0.042230\n",
              "                                  male             0.092419\n",
              "Equipment/Inspection Violation    female           0.040245\n",
              "                                  male             0.070916\n",
              "Motorist Assist/Courtesy          female           0.033133\n",
              "                                  male             0.089802\n",
              "Other Traffic Violation           female           0.038021\n",
              "                                  male             0.059156\n",
              "Registration Violation            female           0.054700\n",
              "                                  male             0.103589\n",
              "Seatbelt Violation                female           0.017746\n",
              "                                  male             0.031705\n",
              "Special Detail/Directed Patrol    female           0.018045\n",
              "                                  male             0.010249\n",
              "Speeding                          female           0.007738\n",
              "                                  male             0.026630\n",
              "Suspicious Person                 female           0.216216\n",
              "                                  male             0.305970\n",
              "Violation of City/Town Ordinance  female           0.060185\n",
              "                                  male             0.073171\n",
              "Warrant                           female           0.148148\n",
              "                                  male             0.311111\n",
              "Name: search_conducted, dtype: float64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 28
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "WyMj6mLrX7Rh"
      },
      "source": [
        "For all types of violations, the search rate in males is higher than females  \n",
        "\n",
        "that from above the max search rate in female is about 3.8%.\n",
        "that indicated gender does affect on search rate"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CmRA-o6VX7Rh",
        "outputId": "e9f603d6-d257-4f7c-ca1d-7c811a93998c"
      },
      "source": [
        "ri.groupby(['reason_for_stop', 'driver_gender']).search_conducted.mean().unstack(level=-1)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>driver_gender</th>\n",
              "      <th>female</th>\n",
              "      <th>male</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>reason_for_stop</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>APB</th>\n",
              "      <td>0.165138</td>\n",
              "      <td>0.255319</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Call for Service</th>\n",
              "      <td>0.042230</td>\n",
              "      <td>0.092419</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Equipment/Inspection Violation</th>\n",
              "      <td>0.040245</td>\n",
              "      <td>0.070916</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Motorist Assist/Courtesy</th>\n",
              "      <td>0.033133</td>\n",
              "      <td>0.089802</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Other Traffic Violation</th>\n",
              "      <td>0.038021</td>\n",
              "      <td>0.059156</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Registration Violation</th>\n",
              "      <td>0.054700</td>\n",
              "      <td>0.103589</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Seatbelt Violation</th>\n",
              "      <td>0.017746</td>\n",
              "      <td>0.031705</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Special Detail/Directed Patrol</th>\n",
              "      <td>0.018045</td>\n",
              "      <td>0.010249</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Speeding</th>\n",
              "      <td>0.007738</td>\n",
              "      <td>0.026630</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Suspicious Person</th>\n",
              "      <td>0.216216</td>\n",
              "      <td>0.305970</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Violation of City/Town Ordinance</th>\n",
              "      <td>0.060185</td>\n",
              "      <td>0.073171</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Warrant</th>\n",
              "      <td>0.148148</td>\n",
              "      <td>0.311111</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "driver_gender                       female      male\n",
              "reason_for_stop                                     \n",
              "APB                               0.165138  0.255319\n",
              "Call for Service                  0.042230  0.092419\n",
              "Equipment/Inspection Violation    0.040245  0.070916\n",
              "Motorist Assist/Courtesy          0.033133  0.089802\n",
              "Other Traffic Violation           0.038021  0.059156\n",
              "Registration Violation            0.054700  0.103589\n",
              "Seatbelt Violation                0.017746  0.031705\n",
              "Special Detail/Directed Patrol    0.018045  0.010249\n",
              "Speeding                          0.007738  0.026630\n",
              "Suspicious Person                 0.216216  0.305970\n",
              "Violation of City/Town Ordinance  0.060185  0.073171\n",
              "Warrant                           0.148148  0.311111"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 29
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "scrolled": true,
        "id": "xSUjVMKTX7Rj",
        "outputId": "93dbf9ef-448c-4d5b-f3e9-72665f598827"
      },
      "source": [
        "ri.groupby(['reason_for_stop', 'driver_gender']).search_conducted.mean().unstack(level=-1).plot(kind= 'bar', figsize=(15,3))\n",
        "# plt.tight_layout()\n",
        "plt.title('Search conducted after stop for each reason_for_stop compare between driver_gender')\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1080x216 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "tFUJbbibX7Rk"
      },
      "source": [
        "## Does gender affect who is frisked during a search?\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "AUo4cJzbX7Rl",
        "outputId": "373a130d-1f81-44ca-8e64-ace5b2ceaec6"
      },
      "source": [
        "# Take the sum of 'frisk'\n",
        "print(ri.frisk_performed.sum())"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "9322\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "i807rgt5X7Rm"
      },
      "source": [
        "## compare frisk by gender"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ctt0QT0KX7Rn",
        "outputId": "b2f83bcb-c82a-4eb3-e0a4-4cd42c748a47"
      },
      "source": [
        "# Create a DataFrame of stops in which a search was conducted\n",
        "searched = ri[ri.search_conducted == True]\n",
        "\n",
        "# Calculate the overall frisk rate by taking the mean of 'frisk'\n",
        "print(searched.frisk_performed.mean())\n",
        "\n",
        "# Calculate the frisk rate for each gender\n",
        "print(searched.groupby('driver_gender').frisk_performed.mean())"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "0.5248282851030289\n",
            "driver_gender\n",
            "female    0.437983\n",
            "male      0.538783\n",
            "Name: frisk_performed, dtype: float64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "7rCs3e9ZX7Ro"
      },
      "source": [
        "<i>The frisk rate is higher for males than for females around 10 percent, <br>   though we can't conclude that this difference is caused by the driver's gender."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ziz8UkFlX7Rp"
      },
      "source": [
        "## Chance of drugs founded with search was conducted"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Zc0I8aO2X7Rp",
        "outputId": "495fcf21-4af6-4e56-e2cf-688c45df5cb1"
      },
      "source": [
        "ri.groupby('search_conducted').mean() #.contraband_drugs.mean()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>arrest_made</th>\n",
              "      <th>citation_issued</th>\n",
              "      <th>warning_issued</th>\n",
              "      <th>contraband_drugs</th>\n",
              "      <th>contraband_weapons</th>\n",
              "      <th>contraband_alcohol</th>\n",
              "      <th>frisk_performed</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>search_conducted</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>False</th>\n",
              "      <td>0.022505</td>\n",
              "      <td>0.902863</td>\n",
              "      <td>0.060950</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>True</th>\n",
              "      <td>0.348328</td>\n",
              "      <td>0.591882</td>\n",
              "      <td>0.035525</td>\n",
              "      <td>0.268269</td>\n",
              "      <td>0.028094</td>\n",
              "      <td>0.063056</td>\n",
              "      <td>0.524828</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                  arrest_made  citation_issued  warning_issued  \\\n",
              "search_conducted                                                 \n",
              "False                0.022505         0.902863        0.060950   \n",
              "True                 0.348328         0.591882        0.035525   \n",
              "\n",
              "                  contraband_drugs  contraband_weapons  contraband_alcohol  \\\n",
              "search_conducted                                                             \n",
              "False                     0.000000            0.000000            0.000000   \n",
              "True                      0.268269            0.028094            0.063056   \n",
              "\n",
              "                  frisk_performed  \n",
              "search_conducted                   \n",
              "False                    0.000000  \n",
              "True                     0.524828  "
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 33
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "rMGjSF-7X7Rs"
      },
      "source": [
        "<i><b> each searh has change that relate with drug 26.8 percent. \n",
        "   "
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qYV6ylSiX7Rs"
      },
      "source": [
        "## Chance of illegal contraband founded with search was conducted separated by driver race"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "NKL2U114X7Rt",
        "outputId": "2fe5c30e-32fe-4fe8-edc4-a8cea65689ce"
      },
      "source": [
        "ri.loc[ri['search_conducted']== True].groupby('driver_race').mean()[['contraband_weapons','contraband_alcohol', 'contraband_drugs']] "
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>contraband_weapons</th>\n",
              "      <th>contraband_alcohol</th>\n",
              "      <th>contraband_drugs</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>driver_race</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>asian/pacific islander</th>\n",
              "      <td>0.017857</td>\n",
              "      <td>0.060714</td>\n",
              "      <td>0.207143</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>black</th>\n",
              "      <td>0.033411</td>\n",
              "      <td>0.048260</td>\n",
              "      <td>0.269838</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>hispanic</th>\n",
              "      <td>0.017247</td>\n",
              "      <td>0.048605</td>\n",
              "      <td>0.236751</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>other</th>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.066667</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>white</th>\n",
              "      <td>0.029595</td>\n",
              "      <td>0.074238</td>\n",
              "      <td>0.279695</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                        contraband_weapons  contraband_alcohol  \\\n",
              "driver_race                                                      \n",
              "asian/pacific islander            0.017857            0.060714   \n",
              "black                             0.033411            0.048260   \n",
              "hispanic                          0.017247            0.048605   \n",
              "other                             0.000000            0.000000   \n",
              "white                             0.029595            0.074238   \n",
              "\n",
              "                        contraband_drugs  \n",
              "driver_race                               \n",
              "asian/pacific islander          0.207143  \n",
              "black                           0.269838  \n",
              "hispanic                        0.236751  \n",
              "other                           0.066667  \n",
              "white                           0.279695  "
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 217
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FV616b8oX7Rw",
        "outputId": "20fd5736-7f3b-460a-a990-1256e84d7199"
      },
      "source": [
        "ri.loc[ri['search_conducted']== True].groupby('driver_race').mean()[['contraband_weapons','contraband_alcohol', 'contraband_drugs']].plot.bar()\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ZdNDZA4XX7Ry"
      },
      "source": [
        "<i><b>from the chart above show no significant connection for specific driver_race to the contraband illegal subject."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qKYzil6HX7Ry"
      },
      "source": [
        "## What violations are caught in each district?\n",
        "\n",
        "pd.crosstab(df.column1,df.column2) # df.column is pd.series\n",
        ".loc[]"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "by_LLr-mX7Rz",
        "outputId": "7106b009-9257-4343-d15d-0431c93211ff"
      },
      "source": [
        "# group the table and see frequency in all districts and violations\n",
        "all_area = pd.crosstab(ri['district'], ri['reason_for_stop'])\n",
        "all_area.head(10)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>reason_for_stop</th>\n",
              "      <th>APB</th>\n",
              "      <th>Call for Service</th>\n",
              "      <th>Equipment/Inspection Violation</th>\n",
              "      <th>Motorist Assist/Courtesy</th>\n",
              "      <th>Other Traffic Violation</th>\n",
              "      <th>Registration Violation</th>\n",
              "      <th>Seatbelt Violation</th>\n",
              "      <th>Special Detail/Directed Patrol</th>\n",
              "      <th>Speeding</th>\n",
              "      <th>Suspicious Person</th>\n",
              "      <th>Violation of City/Town Ordinance</th>\n",
              "      <th>Warrant</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>district</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>K1</th>\n",
              "      <td>32</td>\n",
              "      <td>281</td>\n",
              "      <td>3786</td>\n",
              "      <td>78</td>\n",
              "      <td>7127</td>\n",
              "      <td>628</td>\n",
              "      <td>1</td>\n",
              "      <td>1009</td>\n",
              "      <td>33067</td>\n",
              "      <td>72</td>\n",
              "      <td>21</td>\n",
              "      <td>8</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>K2</th>\n",
              "      <td>101</td>\n",
              "      <td>1036</td>\n",
              "      <td>11285</td>\n",
              "      <td>118</td>\n",
              "      <td>16440</td>\n",
              "      <td>4056</td>\n",
              "      <td>2897</td>\n",
              "      <td>3539</td>\n",
              "      <td>57500</td>\n",
              "      <td>59</td>\n",
              "      <td>237</td>\n",
              "      <td>13</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>K3</th>\n",
              "      <td>144</td>\n",
              "      <td>1227</td>\n",
              "      <td>12959</td>\n",
              "      <td>258</td>\n",
              "      <td>16218</td>\n",
              "      <td>3871</td>\n",
              "      <td>3660</td>\n",
              "      <td>2011</td>\n",
              "      <td>68234</td>\n",
              "      <td>68</td>\n",
              "      <td>194</td>\n",
              "      <td>24</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>X1</th>\n",
              "      <td>6</td>\n",
              "      <td>198</td>\n",
              "      <td>1725</td>\n",
              "      <td>33</td>\n",
              "      <td>3711</td>\n",
              "      <td>192</td>\n",
              "      <td>451</td>\n",
              "      <td>503</td>\n",
              "      <td>6393</td>\n",
              "      <td>5</td>\n",
              "      <td>6</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>X3</th>\n",
              "      <td>64</td>\n",
              "      <td>1328</td>\n",
              "      <td>11520</td>\n",
              "      <td>323</td>\n",
              "      <td>17178</td>\n",
              "      <td>3532</td>\n",
              "      <td>4445</td>\n",
              "      <td>1996</td>\n",
              "      <td>48687</td>\n",
              "      <td>41</td>\n",
              "      <td>282</td>\n",
              "      <td>35</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>X4</th>\n",
              "      <td>138</td>\n",
              "      <td>3535</td>\n",
              "      <td>19975</td>\n",
              "      <td>179</td>\n",
              "      <td>29554</td>\n",
              "      <td>7551</td>\n",
              "      <td>4870</td>\n",
              "      <td>4584</td>\n",
              "      <td>54855</td>\n",
              "      <td>97</td>\n",
              "      <td>296</td>\n",
              "      <td>36</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "reason_for_stop  APB  Call for Service  Equipment/Inspection Violation  \\\n",
              "district                                                                 \n",
              "K1                32               281                            3786   \n",
              "K2               101              1036                           11285   \n",
              "K3               144              1227                           12959   \n",
              "X1                 6               198                            1725   \n",
              "X3                64              1328                           11520   \n",
              "X4               138              3535                           19975   \n",
              "\n",
              "reason_for_stop  Motorist Assist/Courtesy  Other Traffic Violation  \\\n",
              "district                                                             \n",
              "K1                                     78                     7127   \n",
              "K2                                    118                    16440   \n",
              "K3                                    258                    16218   \n",
              "X1                                     33                     3711   \n",
              "X3                                    323                    17178   \n",
              "X4                                    179                    29554   \n",
              "\n",
              "reason_for_stop  Registration Violation  Seatbelt Violation  \\\n",
              "district                                                      \n",
              "K1                                  628                   1   \n",
              "K2                                 4056                2897   \n",
              "K3                                 3871                3660   \n",
              "X1                                  192                 451   \n",
              "X3                                 3532                4445   \n",
              "X4                                 7551                4870   \n",
              "\n",
              "reason_for_stop  Special Detail/Directed Patrol  Speeding  Suspicious Person  \\\n",
              "district                                                                       \n",
              "K1                                         1009     33067                 72   \n",
              "K2                                         3539     57500                 59   \n",
              "K3                                         2011     68234                 68   \n",
              "X1                                          503      6393                  5   \n",
              "X3                                         1996     48687                 41   \n",
              "X4                                         4584     54855                 97   \n",
              "\n",
              "reason_for_stop  Violation of City/Town Ordinance  Warrant  \n",
              "district                                                    \n",
              "K1                                             21        8  \n",
              "K2                                            237       13  \n",
              "K3                                            194       24  \n",
              "X1                                              6        1  \n",
              "X3                                            282       35  \n",
              "X4                                            296       36  "
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 34
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "EBsgj9wCX7R0",
        "outputId": "30961589-5df3-41f4-87f6-93945c3f30ab"
      },
      "source": [
        "all_area.plot(kind='bar', figsize= (12,5))\n",
        "plt.tight_layout()\n",
        "plt.legend(loc=\"upper left\")\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x360 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EjwQbsKhX7R3"
      },
      "source": [
        "<i>each district must have a different population size of people but we saw the most stop is \"Speeding\"."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8mQJJMIlX7R3"
      },
      "source": [
        "# all_area_nrm = (all_area-all_area.min())/(all_area.max()-all_area.min()) == need?\n",
        "# all_area_stded = (all_area-all_area.mean())/all_area.std() == not reasonable to use Standardization "
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "QcArV2K4X7R5"
      },
      "source": [
        "# How Driver Race influence police activity?"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pLwK6BbXX7R5",
        "outputId": "dd6a4881-0541-40ce-9915-9bcad20e6cc6"
      },
      "source": [
        "# show each race count\n",
        "ri.loc[ri.index.year == 2015].driver_race.value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "white                     28676\n",
              "hispanic                   7926\n",
              "black                      7411\n",
              "asian/pacific islander     1134\n",
              "other                        52\n",
              "Name: driver_race, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 133
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4KdqW3f5X7R7",
        "outputId": "abe85936-e41d-40ba-da61-3c1bdbcecd92"
      },
      "source": [
        "# find the stop count for each race in year 2015\n",
        "race_stop = pd.DataFrame(ri.loc[ri.index.year == 2015].driver_race.value_counts())\n",
        "race_stop"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>driver_race</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>white</th>\n",
              "      <td>28676</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>hispanic</th>\n",
              "      <td>7926</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>black</th>\n",
              "      <td>7411</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>asian/pacific islander</th>\n",
              "      <td>1134</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>other</th>\n",
              "      <td>52</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                        driver_race\n",
              "white                         28676\n",
              "hispanic                       7926\n",
              "black                          7411\n",
              "asian/pacific islander         1134\n",
              "other                            52"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 135
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ZN9nr42mX7R-"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "e8-VIlqoX7SA",
        "outputId": "d44f4676-0d34-46b1-b102-2958c3de6ea5"
      },
      "source": [
        "Ri_pop = pd.read_csv('dataset/RIpopulation.csv')\n",
        "Ri_pop"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>date</th>\n",
              "      <th>black</th>\n",
              "      <th>hispanic</th>\n",
              "      <th>other</th>\n",
              "      <th>white</th>\n",
              "      <th>asian/pacific islander</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>2011</td>\n",
              "      <td>62682</td>\n",
              "      <td>127816</td>\n",
              "      <td>66414</td>\n",
              "      <td>863294</td>\n",
              "      <td>31935</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2012</td>\n",
              "      <td>64711</td>\n",
              "      <td>131316</td>\n",
              "      <td>64291</td>\n",
              "      <td>859686</td>\n",
              "      <td>32213</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2013</td>\n",
              "      <td>66569</td>\n",
              "      <td>135317</td>\n",
              "      <td>64602</td>\n",
              "      <td>855594</td>\n",
              "      <td>32767</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>2014</td>\n",
              "      <td>66827</td>\n",
              "      <td>139832</td>\n",
              "      <td>61994</td>\n",
              "      <td>856605</td>\n",
              "      <td>33530</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>2015</td>\n",
              "      <td>68243</td>\n",
              "      <td>143788</td>\n",
              "      <td>61085</td>\n",
              "      <td>854859</td>\n",
              "      <td>34586</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>2016</td>\n",
              "      <td>68886</td>\n",
              "      <td>148375</td>\n",
              "      <td>61218</td>\n",
              "      <td>854026</td>\n",
              "      <td>35173</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>2017</td>\n",
              "      <td>68346</td>\n",
              "      <td>153910</td>\n",
              "      <td>59967</td>\n",
              "      <td>854801</td>\n",
              "      <td>36315</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>2018</td>\n",
              "      <td>69254</td>\n",
              "      <td>158858</td>\n",
              "      <td>58136</td>\n",
              "      <td>854502</td>\n",
              "      <td>36526</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   date  black  hispanic  other   white  asian/pacific islander\n",
              "0  2011  62682    127816  66414  863294                   31935\n",
              "1  2012  64711    131316  64291  859686                   32213\n",
              "2  2013  66569    135317  64602  855594                   32767\n",
              "3  2014  66827    139832  61994  856605                   33530\n",
              "4  2015  68243    143788  61085  854859                   34586\n",
              "5  2016  68886    148375  61218  854026                   35173\n",
              "6  2017  68346    153910  59967  854801                   36315\n",
              "7  2018  69254    158858  58136  854502                   36526"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 136
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "wMbXne6cX7SB"
      },
      "source": [
        "# proper change the colomn name and adjust table\n",
        "Ri_pop2015 = pd.DataFrame(Ri_pop.loc[Ri_pop['date'] ==2015])\n",
        "Ri_pop2015.drop(columns=['date'], inplace= True)\n",
        "Ri_pop2015 = Ri_pop2015.transpose()\n",
        "Ri_pop2015.rename(columns={4: \"pop2015\"},inplace=True)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3-p6UWwhX7SD",
        "outputId": "d938ef47-a379-4657-aea0-36a30f69ab83"
      },
      "source": [
        "Ri_pop2015"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>pop2015</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>black</th>\n",
              "      <td>68243</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>hispanic</th>\n",
              "      <td>143788</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>other</th>\n",
              "      <td>61085</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>white</th>\n",
              "      <td>854859</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>asian/pacific islander</th>\n",
              "      <td>34586</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                        pop2015\n",
              "black                     68243\n",
              "hispanic                 143788\n",
              "other                     61085\n",
              "white                    854859\n",
              "asian/pacific islander    34586"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 138
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "N37KVz47X7SF"
      },
      "source": [
        "## Find out the stop rate on each race\n",
        "\n",
        "by merging 2 tables and add stop_rate column "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Pom4sEVhX7SF"
      },
      "source": [
        "race_stop2015 = race_stop.merge(Ri_pop2015, left_on=race_stop.index, right_on=Ri_pop2015.index)\n",
        "race_stop2015.rename(columns={'key_0': \"race\", 'driver_race':'stop_number', 'pop2015':'num_people'},inplace=True)\n",
        "race_stop2015['stop_rate'] = race_stop2015['stop_number'] / race_stop2015['num_people']"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "MHHTYgckX7SH",
        "outputId": "de07fa7b-e283-4788-953c-4a7a6cb7db86"
      },
      "source": [
        "race_stop2015"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>race</th>\n",
              "      <th>stop_number</th>\n",
              "      <th>num_people</th>\n",
              "      <th>stop_rate</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>white</td>\n",
              "      <td>28676</td>\n",
              "      <td>854859</td>\n",
              "      <td>0.033545</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>hispanic</td>\n",
              "      <td>7926</td>\n",
              "      <td>143788</td>\n",
              "      <td>0.055123</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>black</td>\n",
              "      <td>7411</td>\n",
              "      <td>68243</td>\n",
              "      <td>0.108597</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>asian/pacific islander</td>\n",
              "      <td>1134</td>\n",
              "      <td>34586</td>\n",
              "      <td>0.032788</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>other</td>\n",
              "      <td>52</td>\n",
              "      <td>61085</td>\n",
              "      <td>0.000851</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                     race  stop_number  num_people  stop_rate\n",
              "0                   white        28676      854859   0.033545\n",
              "1                hispanic         7926      143788   0.055123\n",
              "2                   black         7411       68243   0.108597\n",
              "3  asian/pacific islander         1134       34586   0.032788\n",
              "4                   other           52       61085   0.000851"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 140
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Fn5KjyoMX7SJ",
        "outputId": "f2a26a05-58b4-4b2c-b6b0-df47423e8f11"
      },
      "source": [
        "race_stop2015.set_index('race').stop_rate.sort_values(ascending= False).plot(kind= 'bar', figsize= (7,3))\n",
        "plt.xticks(rotation=45)\n",
        "plt.yticks([0.1,0.2,0.3])\n",
        "plt.ylabel('stop_rate')\n",
        "# plt.gca().axes.get_xaxis().set_visible(False) use to hide xtick and x-axis\n",
        "\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 504x216 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "UWsQ-ANfX7SK"
      },
      "source": [
        "<b><i> In Rhod Island stop rate for black people is higher than the rest race base on population proportion.\n",
        "Black drivers are stopped at a rate 3.2 times higher than white drivers. Hispanic drivers are stopped at a rate 1.6 times higher than white drivers."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "BPPah5A4X7SL"
      },
      "source": [
        "## Search rates and frisk rate by each race"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4M1Gq2UMX7SM",
        "outputId": "3781661d-79e3-4e72-ae79-37dd8d93a377"
      },
      "source": [
        "# fns2015 = ri.loc[ri.index.year == 2015].groupby('driver_race').mean()[['frisk_performed','search_conducted']]\n",
        "fns2015 = ri.groupby('driver_race').mean()[['frisk_performed','search_conducted']]\n",
        "fns2015"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>frisk_performed</th>\n",
              "      <th>search_conducted</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>driver_race</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>asian/pacific islander</th>\n",
              "      <td>0.010449</td>\n",
              "      <td>0.021834</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>black</th>\n",
              "      <td>0.033641</td>\n",
              "      <td>0.062849</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>hispanic</th>\n",
              "      <td>0.029592</td>\n",
              "      <td>0.060030</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>other</th>\n",
              "      <td>0.005208</td>\n",
              "      <td>0.011161</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>white</th>\n",
              "      <td>0.015381</td>\n",
              "      <td>0.028917</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                        frisk_performed  search_conducted\n",
              "driver_race                                              \n",
              "asian/pacific islander         0.010449          0.021834\n",
              "black                          0.033641          0.062849\n",
              "hispanic                       0.029592          0.060030\n",
              "other                          0.005208          0.011161\n",
              "white                          0.015381          0.028917"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 191
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "e6MUsfxoX7SO",
        "outputId": "65104a38-df84-4f19-f02b-34f6033001ee"
      },
      "source": [
        "fns2015.sort_values(by='frisk_performed', ascending=False).plot.bar(color=['brown', 'green'], figsize= (12,5))\n",
        "plt.xticks(rotation=35)\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x360 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "SwWViqLvX7SQ",
        "outputId": "edfe13ed-cdc7-4cdc-eae7-a9dcb4f57e54"
      },
      "source": [
        "# compare value how many fold base on white race \n",
        "fns2015.loc['white']['frisk_performed']\n",
        "fns2015.loc['white']['search_conducted']\n",
        "fns2015_twhite = fns2015.copy()\n",
        "fns2015_twhite['div_by_whith_frisk'] = fns2015_twhite.frisk_performed / (fns2015.loc['white']['frisk_performed'])\n",
        "fns2015_twhite['div_by_whith_sch'] = fns2015_twhite.frisk_performed / (fns2015.loc['white']['search_conducted'])\n",
        "fns2015_twhite"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>frisk_performed</th>\n",
              "      <th>search_conducted</th>\n",
              "      <th>div_by_whith_frisk</th>\n",
              "      <th>div_by_whith_sch</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>driver_race</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>asian/pacific islander</th>\n",
              "      <td>0.010449</td>\n",
              "      <td>0.021834</td>\n",
              "      <td>0.679365</td>\n",
              "      <td>0.361356</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>black</th>\n",
              "      <td>0.033641</td>\n",
              "      <td>0.062849</td>\n",
              "      <td>2.187212</td>\n",
              "      <td>1.163382</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>hispanic</th>\n",
              "      <td>0.029592</td>\n",
              "      <td>0.060030</td>\n",
              "      <td>1.923941</td>\n",
              "      <td>1.023348</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>other</th>\n",
              "      <td>0.005208</td>\n",
              "      <td>0.011161</td>\n",
              "      <td>0.338626</td>\n",
              "      <td>0.180116</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>white</th>\n",
              "      <td>0.015381</td>\n",
              "      <td>0.028917</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.531902</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                        frisk_performed  search_conducted  div_by_whith_frisk  \\\n",
              "driver_race                                                                     \n",
              "asian/pacific islander         0.010449          0.021834            0.679365   \n",
              "black                          0.033641          0.062849            2.187212   \n",
              "hispanic                       0.029592          0.060030            1.923941   \n",
              "other                          0.005208          0.011161            0.338626   \n",
              "white                          0.015381          0.028917            1.000000   \n",
              "\n",
              "                        div_by_whith_sch  \n",
              "driver_race                               \n",
              "asian/pacific islander          0.361356  \n",
              "black                           1.163382  \n",
              "hispanic                        1.023348  \n",
              "other                           0.180116  \n",
              "white                           0.531902  "
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 195
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "B-c9pna1X7SR"
      },
      "source": [
        "Here we see that among drivers who were stopped, <i><b>black drivers were searched at a rate 2.19</i></b> times higher than white drivers, and <i><b>Hispanic drivers were searched at a rate 1.92</i></b> times higher than white drivers. <i><b>Black drivers were frisked at a rate 1.16</i></b> times higher than white drivers were, and <i><b>Hispanic drivers were frisked at a rate 1.02</i></b> times higher than white drivers were."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "tZNMIFjOX7SS",
        "outputId": "9d7ccdf5-1e09-417f-93c6-1eb741dc1e4b"
      },
      "source": [
        "print(\"Here we see that among drivers who were stopped, black drivers were searched at a rate {:.2f} times higher than white drivers, and Hispanic drivers were searched at a rate {:.2f} times higher than white drivers. Black drivers were frisked at a rate {:.2f} times higher than white drivers were, and Hispanic drivers were frisked at a rate {:.2f} times higher than white drivers were\".format(fns2015_twhite.loc['black']['div_by_whith_frisk'], fns2015_twhite.loc['hispanic']['div_by_whith_frisk'], fns2015_twhite.loc['black']['div_by_whith_sch'], fns2015_twhite.loc['hispanic']['div_by_whith_sch']))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Here we see that among drivers who were stopped, black drivers were searched at a rate 2.19 times higher than white drivers, and Hispanic drivers were searched at a rate 1.92 times higher than white drivers. Black drivers were frisked at a rate 1.16 times higher than white drivers were, and Hispanic drivers were frisked at a rate 1.02 times higher than white drivers were\n"
          ],
          "name": "stdout"
        }
      ]
    }
  ]
}