{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "fe2eed0f-4ff1-4587-aa6c-3589c0f41e07",
   "metadata": {},
   "source": [
    "# Data Preparation and Quality\n",
    "Lecture Data Engineering and Analytics<br>\n",
    "Eva Zangerle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "792af709-0621-4d64-8166-8c8cc28cc73c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# import required packages\n",
    "import psycopg2\n",
    "import json\n",
    "import math\n",
    "import glob\n",
    "import os\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from scipy.stats import norm, kstest, median_abs_deviation\n",
    "import statsmodels.api as sm\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import MinMaxScaler, StandardScaler\n",
    "from sklearn.neighbors import KNeighborsRegressor\n",
    "\n",
    "# set seaborn style\n",
    "sns.set_style('darkgrid')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "82672d3c-d574-47f1-b2f1-9a42b414e278",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_dir='../data'"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "747aa842-23a2-4659-abdc-3131a07894e2",
   "metadata": {},
   "source": [
    "## Anomaly Detection"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d2bb2faf-e715-4232-9d0a-723729393f0a",
   "metadata": {},
   "source": [
    "### Missing Data: JSON\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b1505590-6757-4f9a-ab78-7ee2bbe9086b",
   "metadata": {},
   "source": [
    "Example for JSON and dealing with sentinel values (adopted from CleanData)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "8da778a9-c262-42ce-9ff3-b2330101a394",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[nan, None, inf]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "json.loads('[NaN, null, Infinity]') "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "161f29a5-e0a6-478b-85f9-e5fe19fdfdb4",
   "metadata": {},
   "outputs": [],
   "source": [
    "json_data = '''\n",
    "{\"a\": {\"1\": NaN, \"2\": 1.23, \"4\": 3.45, \"5\": 6.78, \"6\": 9.01},\n",
    " \"b\": {\"1\": \"Not number\", \"2\": \"A number\", \"3\": \"A null\",\n",
    "       \"4\": \"Santiago\", \"5\": \"\"}\n",
    "}'''"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "8b476b3a-d82d-48ba-9175-b0ba5f9e2a83",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>a</th>\n",
       "      <th>b</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NaN</td>\n",
       "      <td>Not number</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.23</td>\n",
       "      <td>A number</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>A null</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3.45</td>\n",
       "      <td>Santiago</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6.78</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>9.01</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      a           b\n",
       "1   NaN  Not number\n",
       "2  1.23    A number\n",
       "3   NaN      A null\n",
       "4  3.45    Santiago\n",
       "5  6.78            \n",
       "6  9.01         NaN"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.read_json(json_data).sort_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "e4c7eadb-fab7-4b52-8a67-cac1f910509c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Row 1, Col a: Not a Number\n",
      "Row 3, Col a: Missing\n",
      "Row 5, Col b: Empty value ''\n",
      "Row 6, Col b: Missing\n"
     ]
    }
   ],
   "source": [
    "data = json.loads(json_data)\n",
    "rows = {row for dct in data.values() \n",
    "            for row in dct.keys()}\n",
    "\n",
    "for row in sorted(rows):\n",
    "    for col in data.keys():\n",
    "        val = data[col].get(row)\n",
    "        if val is None:\n",
    "            print(f\"Row {row}, Col {col}: Missing\")\n",
    "        elif isinstance(val, float) and math.isnan(val):\n",
    "            print(f\"Row {row}, Col {col}: Not a Number\")\n",
    "        elif not val:\n",
    "            print(f\"Row {row}, Col {col}: Empty value {repr(val)}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b00ee68e-a37e-442f-b494-1882101e99a1",
   "metadata": {},
   "source": [
    "### Missing Data: Textual Data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d320d948-16a2-46f9-a71f-573f85fc2d51",
   "metadata": {},
   "source": [
    "Real-World data from United States National Oceanic and Atmospheric Administration: weather station at Sorstokken, Norway (adopted from CleanData)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "43c7d634-fb1b-47ce-80e4-666d2e362400",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION</th>\n",
       "      <th>DATE</th>\n",
       "      <th>TEMP</th>\n",
       "      <th>VISIB</th>\n",
       "      <th>GUST</th>\n",
       "      <th>DEWP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>2019-01-01</td>\n",
       "      <td>39.7</td>\n",
       "      <td>6.2</td>\n",
       "      <td>52.1</td>\n",
       "      <td>30.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>2019-01-02</td>\n",
       "      <td>36.4</td>\n",
       "      <td>6.2</td>\n",
       "      <td>999.9</td>\n",
       "      <td>29.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>2019-01-03</td>\n",
       "      <td>36.5</td>\n",
       "      <td>3.3</td>\n",
       "      <td>999.9</td>\n",
       "      <td>35.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>UNKNOWN</td>\n",
       "      <td>45.6</td>\n",
       "      <td>2.2</td>\n",
       "      <td>22.0</td>\n",
       "      <td>44.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>2019-01-06</td>\n",
       "      <td>42.5</td>\n",
       "      <td>1.9</td>\n",
       "      <td>999.9</td>\n",
       "      <td>42.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>294</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>2019-12-16</td>\n",
       "      <td>39.1</td>\n",
       "      <td>6.2</td>\n",
       "      <td>999.9</td>\n",
       "      <td>36.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>295</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>2019-12-17</td>\n",
       "      <td>40.5</td>\n",
       "      <td>6.2</td>\n",
       "      <td>999.9</td>\n",
       "      <td>39.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>296</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>2019-12-18</td>\n",
       "      <td>38.8</td>\n",
       "      <td>6.2</td>\n",
       "      <td>999.9</td>\n",
       "      <td>38.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>297</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>2019-12-19</td>\n",
       "      <td>45.5</td>\n",
       "      <td>6.1</td>\n",
       "      <td>999.9</td>\n",
       "      <td>42.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>298</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>2019-12-20</td>\n",
       "      <td>51.8</td>\n",
       "      <td>6.2</td>\n",
       "      <td>35.0</td>\n",
       "      <td>41.2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>299 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        STATION        DATE  TEMP  VISIB   GUST  DEWP\n",
       "0    1001499999  2019-01-01  39.7    6.2   52.1  30.4\n",
       "1    1001499999  2019-01-02  36.4    6.2  999.9  29.8\n",
       "2    1001499999  2019-01-03  36.5    3.3  999.9  35.6\n",
       "3    1001499999     UNKNOWN  45.6    2.2   22.0  44.8\n",
       "4    1001499999  2019-01-06  42.5    1.9  999.9  42.5\n",
       "..          ...         ...   ...    ...    ...   ...\n",
       "294  1001499999  2019-12-16  39.1    6.2  999.9  36.8\n",
       "295  1001499999  2019-12-17  40.5    6.2  999.9  39.2\n",
       "296  1001499999  2019-12-18  38.8    6.2  999.9  38.2\n",
       "297  1001499999  2019-12-19  45.5    6.1  999.9  42.7\n",
       "298  1001499999  2019-12-20  51.8    6.2   35.0  41.2\n",
       "\n",
       "[299 rows x 6 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sorstokken = pd.read_csv(os.path.join(data_dir, 'sorstokken-no.csv.gz'))\n",
    "sorstokken"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "97b89d82-42a9-4711-836d-f396c92f3998",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION</th>\n",
       "      <th>DATE</th>\n",
       "      <th>TEMP</th>\n",
       "      <th>VISIB</th>\n",
       "      <th>GUST</th>\n",
       "      <th>DEWP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>2019-01-01</td>\n",
       "      <td>27.2</td>\n",
       "      <td>1.2</td>\n",
       "      <td>17.1</td>\n",
       "      <td>16.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>UNKNOWN</td>\n",
       "      <td>88.1</td>\n",
       "      <td>999.9</td>\n",
       "      <td>999.9</td>\n",
       "      <td>63.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      STATION        DATE  TEMP  VISIB   GUST  DEWP\n",
       "0  1001499999  2019-01-01  27.2    1.2   17.1  16.5\n",
       "1  1001499999     UNKNOWN  88.1  999.9  999.9  63.5"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame([sorstokken.min(), sorstokken.max()])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "19b41f7f-7e52-4078-9c30-c1e03fe0d7a0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Normal max:\n",
      "VISIB 6.8 ...standard deviation w/ & w/o sentinel: 254.4 / 0.7\n",
      "GUST 62.2 ...standard deviation w/ & w/o sentinel: 452.4 / 8.1\n"
     ]
    }
   ],
   "source": [
    "print(\"Normal max:\")\n",
    "for col in ['VISIB', 'GUST']:\n",
    "        s = sorstokken[col]\n",
    "        print(col, s[s < 999.9].max(), \n",
    "              \"...standard deviation w/ & w/o sentinel:\",\n",
    "              f\"{s.std():.1f} / {s[s < 999.9].std():.1f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "7279b418-c3a3-4066-a71c-e729b54764d9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION</th>\n",
       "      <th>DATE</th>\n",
       "      <th>TEMP</th>\n",
       "      <th>VISIB</th>\n",
       "      <th>GUST</th>\n",
       "      <th>DEWP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>2019-01-01</td>\n",
       "      <td>39.7</td>\n",
       "      <td>6.2</td>\n",
       "      <td>52.1</td>\n",
       "      <td>30.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>2019-01-02</td>\n",
       "      <td>36.4</td>\n",
       "      <td>6.2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>29.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>2019-01-03</td>\n",
       "      <td>36.5</td>\n",
       "      <td>3.3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>35.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>NaT</td>\n",
       "      <td>45.6</td>\n",
       "      <td>2.2</td>\n",
       "      <td>22.0</td>\n",
       "      <td>44.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1001499999</td>\n",
       "      <td>2019-01-06</td>\n",
       "      <td>42.5</td>\n",
       "      <td>1.9</td>\n",
       "      <td>NaN</td>\n",
       "      <td>42.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      STATION       DATE  TEMP  VISIB  GUST  DEWP\n",
       "0  1001499999 2019-01-01  39.7    6.2  52.1  30.4\n",
       "1  1001499999 2019-01-02  36.4    6.2   NaN  29.8\n",
       "2  1001499999 2019-01-03  36.5    3.3   NaN  35.6\n",
       "3  1001499999        NaT  45.6    2.2  22.0  44.8\n",
       "4  1001499999 2019-01-06  42.5    1.9   NaN  42.5"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sorstokken = pd.read_csv(os.path.join(data_dir,'../data/sorstokken-no.csv.gz'), \n",
    "                         na_values={'DATE': 'UNKNOWN', \n",
    "                                    'VISIB': '999.9',\n",
    "                                    'GUST': '999.9'},\n",
    "                         parse_dates=['DATE'])\n",
    "sorstokken.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "171f078b-8e0f-42e6-bae7-538eda9758c1",
   "metadata": {},
   "source": [
    "### Sentinel Values\n",
    "\n",
    "Example for sentinel value in Python (adopted from CleanData)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "6cc05d4a-9a2c-417d-91f7-4fa556b927e1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "n=7:\n",
      "  method1: 1.109\n",
      "  method2: 1.109\n",
      "n=8:\n",
      "  method1: 1.229\n",
      "  method2: 1.229\n",
      "n=9:\n",
      "  method1: nan\n",
      "  method2: 1.510\n"
     ]
    }
   ],
   "source": [
    "for n in range(7, 10):\n",
    "    exp1 = 2**n\n",
    "    a = (22/7) ** exp1 \n",
    "    b = math.pi ** exp1\n",
    "    # Compute answer in two \"equivalent\" ways\n",
    "    res1 = (a * a) / (b * b)\n",
    "    res2 = (a / b) * (a / b)\n",
    "    print(f\"n={n}:\\n  \"\n",
    "          f\"method1: {res1:.3f}\\n  \"\n",
    "          f\"method2: {res2:.3f}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8ba3ee54-458c-49d7-84ae-aa6beb4bdcea",
   "metadata": {},
   "source": [
    "### Miscoded Data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d3594e67-0140-43ac-b99a-93d9eff810ff",
   "metadata": {},
   "source": [
    "#### Ordinals"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "70a7f971-ff24-4edb-9f94-3cb82b214d5f",
   "metadata": {},
   "source": [
    "Miscoded data: for ordinals, we need to check minimum, maximum and whether data type is integer; adopted from CleanData."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "7b89a886-33ab-480c-bdf6-d2ac032991b5",
   "metadata": {},
   "outputs": [],
   "source": [
    "np.random.seed(1)\n",
    "\n",
    "# Histopathological Attributes: (values 0, 1, 2, 3)\n",
    "# Clinical Attributes: (values 0, 1, 2, 3, unless indicated)\n",
    "features = [\n",
    "    \"erythema\",\n",
    "    \"scaling\",\n",
    "    \"definite borders\",\n",
    "    \"itching\",\n",
    "    \"koebner phenomenon\",\n",
    "    \"polygonal papules\",\n",
    "    \"follicular papules\",\n",
    "    \"oral mucosal involvement\",\n",
    "    \"knee and elbow involvement\",\n",
    "    \"scalp involvement\",\n",
    "    \"family history\",  # 0 or 1\n",
    "    \"melanin incontinence\",\n",
    "    \"eosinophils in the infiltrate\",\n",
    "    \"PNL infiltrate\",\n",
    "    \"fibrosis of the papillary dermis\",\n",
    "    \"exocytosis\",\n",
    "    \"acanthosis\",\n",
    "    \"hyperkeratosis\",\n",
    "    \"parakeratosis\",\n",
    "    \"clubbing of the rete ridges\",\n",
    "    \"elongation of the rete ridges\",\n",
    "    \"thinning of the suprapapillary epidermis\",\n",
    "    \"spongiform pustule\",\n",
    "    \"munro microabcess\",\n",
    "    \"focal hypergranulosis\",\n",
    "    \"disappearance of the granular layer\",\n",
    "    \"vacuolisation and damage of basal layer\",\n",
    "    \"spongiosis\",\n",
    "    \"saw-tooth appearance of retes\",\n",
    "    \"follicular horn plug\",\n",
    "    \"perifollicular parakeratosis\",\n",
    "    \"inflammatory monoluclear inflitrate\",\n",
    "    \"band-like infiltrate\",\n",
    "    \"Age\",  # linear; missing marked '?'\n",
    "    \"TARGET\"  # See mapping\n",
    "]\n",
    "\n",
    "targets = {\n",
    "    1:\"psoriasis\",                 # 112 instances\n",
    "    2:\"seboreic dermatitis\",       # 61\n",
    "    3:\"lichen planus\",             # 72\n",
    "    4:\"pityriasis rosea\",          # 49\n",
    "    5:\"cronic dermatitis\",         # 52\n",
    "    6:\"pityriasis rubra pilaris\",  # 20\n",
    "}\n",
    "\n",
    "\n",
    "data = os.path.join(data_dir, 'dermatology.data')\n",
    "metadata = os.path.join(data_dir, 'dermatology.names')\n",
    "df = pd.read_csv(data, header=None, names=features)\n",
    "df['TARGET'] = df.TARGET.map(targets)\n",
    "\n",
    "derm = df.copy()\n",
    "derm.loc[derm.Age == '?', 'Age'] = None\n",
    "derm['Age'] = derm.Age.astype(float)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "45f6a92b-4b9c-4a81-bcb3-1fbac980f682",
   "metadata": {},
   "source": [
    "**Todo for all:** have a look at dermatology.names and dermatology.data for further information on the data, its provenance and structure."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "0348f05a-931a-43b1-8361-eb95e6a0118d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>min</th>\n",
       "      <th>max</th>\n",
       "      <th>dtype</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>erythema</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>int64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>scaling</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>int64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>definite borders</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>int64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>itching</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>int64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>koebner phenomenon</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>int64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>perifollicular parakeratosis</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>int64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>inflammatory monoluclear inflitrate</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>int64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>band-like infiltrate</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>int64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Age</th>\n",
       "      <td>0.0</td>\n",
       "      <td>75.0</td>\n",
       "      <td>float64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>TARGET</th>\n",
       "      <td>cronic dermatitis</td>\n",
       "      <td>seboreic dermatitis</td>\n",
       "      <td>object</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>35 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                   min                  max  \\\n",
       "erythema                                             0                    3   \n",
       "scaling                                              0                    3   \n",
       "definite borders                                     0                    3   \n",
       "itching                                              0                    3   \n",
       "koebner phenomenon                                   0                    3   \n",
       "...                                                ...                  ...   \n",
       "perifollicular parakeratosis                         0                    3   \n",
       "inflammatory monoluclear inflitrate                  0                    3   \n",
       "band-like infiltrate                                 0                    3   \n",
       "Age                                                0.0                 75.0   \n",
       "TARGET                               cronic dermatitis  seboreic dermatitis   \n",
       "\n",
       "                                       dtype  \n",
       "erythema                               int64  \n",
       "scaling                                int64  \n",
       "definite borders                       int64  \n",
       "itching                                int64  \n",
       "koebner phenomenon                     int64  \n",
       "...                                      ...  \n",
       "perifollicular parakeratosis           int64  \n",
       "inflammatory monoluclear inflitrate    int64  \n",
       "band-like infiltrate                   int64  \n",
       "Age                                  float64  \n",
       "TARGET                                object  \n",
       "\n",
       "[35 rows x 3 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(pd.DataFrame(\n",
    "    [derm.min(), derm.max(), derm.dtypes])\n",
    "     .T\n",
    "     .rename(columns={0:'min', 1:'max', 2:'dtype'})\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2510cb5c-6bed-4fe5-8492-b07f1a3d12c2",
   "metadata": {},
   "source": [
    "#### Categorical Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "5286816f-dbef-4a9f-8f86-b04c6f7f0696",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Hair_Length</th>\n",
       "      <th>Favorite</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>21492</th>\n",
       "      <td>176.958650</td>\n",
       "      <td>72.604585</td>\n",
       "      <td>14.0</td>\n",
       "      <td>red</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9488</th>\n",
       "      <td>169.000221</td>\n",
       "      <td>79.559843</td>\n",
       "      <td>0.0</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16933</th>\n",
       "      <td>171.104306</td>\n",
       "      <td>71.125528</td>\n",
       "      <td>5.5</td>\n",
       "      <td>red</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12604</th>\n",
       "      <td>174.481084</td>\n",
       "      <td>79.496237</td>\n",
       "      <td>8.1</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8222</th>\n",
       "      <td>171.275578</td>\n",
       "      <td>77.094118</td>\n",
       "      <td>14.6</td>\n",
       "      <td>green</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Height     Weight  Hair_Length Favorite\n",
       "21492  176.958650  72.604585         14.0      red\n",
       "9488   169.000221  79.559843          0.0     blue\n",
       "16933  171.104306  71.125528          5.5      red\n",
       "12604  174.481084  79.496237          8.1     blue\n",
       "8222   171.275578  77.094118         14.6    green"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "humans = pd.read_csv(os.path.join(data_dir, 'humans-err.csv'))\n",
    "# random_stae for deterministic sample\n",
    "humans.sample(5, random_state=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "1cb4ad60-1d4b-4f87-bd51-340c5012a218",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['red', 'green', 'blue', 'Red', ' red', 'grееn', 'blüe',\n",
       "       'chartreuse'], dtype=object)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# observe unique values\n",
    "humans.Favorite.unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "aeb97307-c7cd-4aca-ac0e-ca43325ac5ad",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "red           9576\n",
       "blue          7961\n",
       "green         7458\n",
       "Red              1\n",
       " red             1\n",
       "grееn            1\n",
       "blüe             1\n",
       "chartreuse       1\n",
       "Name: Favorite, dtype: int64"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# how rare are such variations?\n",
    "humans.Favorite.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "e0d9609a-1a45-4727-b2a0-f5153a83e3e0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "       red [32, 114, 101, 100]\n",
      "       Red [82, 101, 100]\n",
      "      blue [98, 108, 117, 101]\n",
      "      blüe [98, 108, 252, 101]\n",
      "chartreuse [99, 104, 97, 114, 116, 114, 101, 117, 115, 101]\n",
      "     green [103, 114, 101, 101, 110]\n",
      "     grееn [103, 114, 1077, 1077, 110]\n",
      "       red [114, 101, 100]\n"
     ]
    }
   ],
   "source": [
    "# look at labels more closely\n",
    "for color in sorted(humans.Favorite.unique()):\n",
    "    print(f\"{color:>10s}\", [ord(c) for c in color])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "5e76c750-1925-45f1-8909-73853079737a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "red      9578\n",
       "blue     7962\n",
       "green    7459\n",
       "Name: Favorite, dtype: int64"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# transform troublesome values\n",
    "humans.loc[humans.Favorite.isin(['Red', ' red']), 'Favorite'] = 'red'\n",
    "humans.loc[humans.Favorite == 'chartreuse', 'Favorite'] = None\n",
    "humans.loc[humans.Favorite == 'blüe', 'Favorite'] = 'blue'\n",
    "humans.loc[humans.Favorite == 'grееn', 'Favorite'] = 'green'\n",
    "humans.Favorite.value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d09918c6-2e4b-4e19-88b8-cf26f639a057",
   "metadata": {},
   "source": [
    "### Fixed Bounds"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d023b7dd-59b2-4fd4-a115-45da44647d1c",
   "metadata": {},
   "source": [
    "Continues previous example of humans, adapted from CleanData."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "420205a3-2266-4441-a8de-4d86d5ad9605",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# any humans exceeding the given bounds?\n",
    "((humans.Height < 92) | (humans.Height > 213)).any()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "8aea02dd-a13a-4753-9d12-c8834de31c1e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Hair_Length</th>\n",
       "      <th>Favorite</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1984</th>\n",
       "      <td>165.634695</td>\n",
       "      <td>62.979993</td>\n",
       "      <td>127.0</td>\n",
       "      <td>red</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8929</th>\n",
       "      <td>175.186061</td>\n",
       "      <td>73.899992</td>\n",
       "      <td>120.6</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14673</th>\n",
       "      <td>174.948037</td>\n",
       "      <td>77.644434</td>\n",
       "      <td>130.1</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14735</th>\n",
       "      <td>176.385525</td>\n",
       "      <td>68.735397</td>\n",
       "      <td>121.7</td>\n",
       "      <td>green</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16672</th>\n",
       "      <td>173.172298</td>\n",
       "      <td>71.814699</td>\n",
       "      <td>121.4</td>\n",
       "      <td>red</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17093</th>\n",
       "      <td>169.771111</td>\n",
       "      <td>77.958278</td>\n",
       "      <td>133.2</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Height     Weight  Hair_Length Favorite\n",
       "1984   165.634695  62.979993        127.0      red\n",
       "8929   175.186061  73.899992        120.6     blue\n",
       "14673  174.948037  77.644434        130.1     blue\n",
       "14735  176.385525  68.735397        121.7    green\n",
       "16672  173.172298  71.814699        121.4      red\n",
       "17093  169.771111  77.958278        133.2     blue"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "humans.query('Hair_Length > 120')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "a78e7b9f-20f3-4dba-bb1d-0f775a1c530f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Hair_Length</th>\n",
       "      <th>Favorite</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1984</th>\n",
       "      <td>165.634695</td>\n",
       "      <td>62.979993</td>\n",
       "      <td>120.0</td>\n",
       "      <td>red</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4146</th>\n",
       "      <td>173.930107</td>\n",
       "      <td>72.701456</td>\n",
       "      <td>119.6</td>\n",
       "      <td>red</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8929</th>\n",
       "      <td>175.186061</td>\n",
       "      <td>73.899992</td>\n",
       "      <td>120.0</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9259</th>\n",
       "      <td>179.215974</td>\n",
       "      <td>82.538890</td>\n",
       "      <td>119.4</td>\n",
       "      <td>green</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14673</th>\n",
       "      <td>174.948037</td>\n",
       "      <td>77.644434</td>\n",
       "      <td>120.0</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14735</th>\n",
       "      <td>176.385525</td>\n",
       "      <td>68.735397</td>\n",
       "      <td>120.0</td>\n",
       "      <td>green</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16672</th>\n",
       "      <td>173.172298</td>\n",
       "      <td>71.814699</td>\n",
       "      <td>120.0</td>\n",
       "      <td>red</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17093</th>\n",
       "      <td>169.771111</td>\n",
       "      <td>77.958278</td>\n",
       "      <td>120.0</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Height     Weight  Hair_Length Favorite\n",
       "1984   165.634695  62.979993        120.0      red\n",
       "4146   173.930107  72.701456        119.6      red\n",
       "8929   175.186061  73.899992        120.0     blue\n",
       "9259   179.215974  82.538890        119.4    green\n",
       "14673  174.948037  77.644434        120.0     blue\n",
       "14735  176.385525  68.735397        120.0    green\n",
       "16672  173.172298  71.814699        120.0      red\n",
       "17093  169.771111  77.958278        120.0     blue"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "humans2 = humans.copy()  # Retain prior versions of data set\n",
    "humans2['Hair_Length'] = humans2.Hair_Length.clip(upper=120)\n",
    "humans2[humans2.Hair_Length > 119]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "122cdada-e0b8-422a-a97d-3b7cc4d5d964",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Hair_Length</th>\n",
       "      <th>Favorite</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>177.297182</td>\n",
       "      <td>81.153493</td>\n",
       "      <td>0.0</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>217</th>\n",
       "      <td>171.893967</td>\n",
       "      <td>68.553526</td>\n",
       "      <td>0.0</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>240</th>\n",
       "      <td>161.862237</td>\n",
       "      <td>76.914599</td>\n",
       "      <td>0.0</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354</th>\n",
       "      <td>172.972247</td>\n",
       "      <td>73.175032</td>\n",
       "      <td>0.0</td>\n",
       "      <td>red</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>371</th>\n",
       "      <td>179.866011</td>\n",
       "      <td>80.418554</td>\n",
       "      <td>0.0</td>\n",
       "      <td>red</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24818</th>\n",
       "      <td>171.537554</td>\n",
       "      <td>72.619095</td>\n",
       "      <td>0.0</td>\n",
       "      <td>green</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24834</th>\n",
       "      <td>170.991301</td>\n",
       "      <td>67.652660</td>\n",
       "      <td>0.0</td>\n",
       "      <td>green</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24892</th>\n",
       "      <td>177.002643</td>\n",
       "      <td>77.286141</td>\n",
       "      <td>0.0</td>\n",
       "      <td>green</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24919</th>\n",
       "      <td>169.012286</td>\n",
       "      <td>74.593809</td>\n",
       "      <td>0.0</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24967</th>\n",
       "      <td>169.061308</td>\n",
       "      <td>65.985481</td>\n",
       "      <td>0.0</td>\n",
       "      <td>green</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>517 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           Height     Weight  Hair_Length Favorite\n",
       "6      177.297182  81.153493          0.0     blue\n",
       "217    171.893967  68.553526          0.0     blue\n",
       "240    161.862237  76.914599          0.0     blue\n",
       "354    172.972247  73.175032          0.0      red\n",
       "371    179.866011  80.418554          0.0      red\n",
       "...           ...        ...          ...      ...\n",
       "24818  171.537554  72.619095          0.0    green\n",
       "24834  170.991301  67.652660          0.0    green\n",
       "24892  177.002643  77.286141          0.0    green\n",
       "24919  169.012286  74.593809          0.0     blue\n",
       "24967  169.061308  65.985481          0.0    green\n",
       "\n",
       "[517 rows x 4 columns]"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "humans2[humans2.Hair_Length == 0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "02eda6a2-6702-4c97-b7d1-89d54609f4be",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Hair_Length</th>\n",
       "      <th>Favorite</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>493</th>\n",
       "      <td>167.703398</td>\n",
       "      <td>72.567763</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>528</th>\n",
       "      <td>167.355393</td>\n",
       "      <td>60.276190</td>\n",
       "      <td>-20.7</td>\n",
       "      <td>green</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>562</th>\n",
       "      <td>172.416114</td>\n",
       "      <td>60.867457</td>\n",
       "      <td>-68.1</td>\n",
       "      <td>green</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>569</th>\n",
       "      <td>177.644146</td>\n",
       "      <td>74.027147</td>\n",
       "      <td>-5.9</td>\n",
       "      <td>green</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>738</th>\n",
       "      <td>178.094818</td>\n",
       "      <td>76.963924</td>\n",
       "      <td>-57.2</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24042</th>\n",
       "      <td>174.608922</td>\n",
       "      <td>64.846422</td>\n",
       "      <td>-22.7</td>\n",
       "      <td>green</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24055</th>\n",
       "      <td>172.831608</td>\n",
       "      <td>74.096660</td>\n",
       "      <td>-13.3</td>\n",
       "      <td>red</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24063</th>\n",
       "      <td>172.687488</td>\n",
       "      <td>69.466838</td>\n",
       "      <td>-14.2</td>\n",
       "      <td>green</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24386</th>\n",
       "      <td>176.668430</td>\n",
       "      <td>62.984811</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>green</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24944</th>\n",
       "      <td>172.300925</td>\n",
       "      <td>72.067862</td>\n",
       "      <td>-24.4</td>\n",
       "      <td>red</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>118 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           Height     Weight  Hair_Length Favorite\n",
       "493    167.703398  72.567763         -1.0     blue\n",
       "528    167.355393  60.276190        -20.7    green\n",
       "562    172.416114  60.867457        -68.1    green\n",
       "569    177.644146  74.027147         -5.9    green\n",
       "738    178.094818  76.963924        -57.2     blue\n",
       "...           ...        ...          ...      ...\n",
       "24042  174.608922  64.846422        -22.7    green\n",
       "24055  172.831608  74.096660        -13.3      red\n",
       "24063  172.687488  69.466838        -14.2    green\n",
       "24386  176.668430  62.984811         -1.0    green\n",
       "24944  172.300925  72.067862        -24.4      red\n",
       "\n",
       "[118 rows x 4 columns]"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "neg_hair = humans2[humans2.Hair_Length < 0]\n",
    "neg_hair"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "c29e21b4-1bec-4ab7-9328-bf7122a14278",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    118.000000\n",
       "mean     -24.348305\n",
       "std       22.484691\n",
       "min      -95.700000\n",
       "25%      -38.075000\n",
       "50%      -20.650000\n",
       "75%       -5.600000\n",
       "max       -0.700000\n",
       "Name: Hair_Length, dtype: float64"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "neg_hair.Hair_Length.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "0fec5b37-cfd8-456f-b97d-fd16785bc86e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    24365.000000\n",
       "mean        26.675485\n",
       "std         21.206516\n",
       "min          0.100000\n",
       "25%          9.900000\n",
       "50%         21.700000\n",
       "75%         38.400000\n",
       "max        120.000000\n",
       "Name: Hair_Length, dtype: float64"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pos_hair = humans2[humans2.Hair_Length > 0]\n",
    "pos_hair.Hair_Length.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "77d46cf5-721f-487f-a834-2bb52a27ce9c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([ 2.,  0.,  0.,  0.,  0.,  2.,  0.,  0.,  2.,  3.,  0.,  1.,  5.,\n",
       "         1.,  4.,  1.,  3.,  5.,  4.,  3.,  6.,  3.,  8.,  7.,  2.,  4.,\n",
       "         9.,  8., 12., 23.]),\n",
       " array([-95.7       , -92.53333333, -89.36666667, -86.2       ,\n",
       "        -83.03333333, -79.86666667, -76.7       , -73.53333333,\n",
       "        -70.36666667, -67.2       , -64.03333333, -60.86666667,\n",
       "        -57.7       , -54.53333333, -51.36666667, -48.2       ,\n",
       "        -45.03333333, -41.86666667, -38.7       , -35.53333333,\n",
       "        -32.36666667, -29.2       , -26.03333333, -22.86666667,\n",
       "        -19.7       , -16.53333333, -13.36666667, -10.2       ,\n",
       "         -7.03333333,  -3.86666667,  -0.7       ]),\n",
       " <BarContainer object of 30 artists>)"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Distribution of invalid negative hair length')"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'Hair length')"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Number of humans')"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.set_style('darkgrid')\n",
    "plt.hist(neg_hair.Hair_Length, bins=30)\n",
    "plt.title(\"Distribution of invalid negative hair length\")\n",
    "plt.xlabel('Hair length')\n",
    "plt.ylabel('Number of humans')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "e2ed85e9-4aa8-4621-959f-89a0c61222d6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([2455., 2545., 2315., 2181., 1934., 1786., 1625., 1484., 1269.,\n",
       "        1132.,  971.,  814.,  718.,  571.,  487.,  444.,  354.,  309.,\n",
       "         241.,  170.,  137.,  105.,   77.,   77.,   44.,   43.,   27.,\n",
       "          15.,   13.,   22.]),\n",
       " array([1.00000000e-01, 4.09666667e+00, 8.09333333e+00, 1.20900000e+01,\n",
       "        1.60866667e+01, 2.00833333e+01, 2.40800000e+01, 2.80766667e+01,\n",
       "        3.20733333e+01, 3.60700000e+01, 4.00666667e+01, 4.40633333e+01,\n",
       "        4.80600000e+01, 5.20566667e+01, 5.60533333e+01, 6.00500000e+01,\n",
       "        6.40466667e+01, 6.80433333e+01, 7.20400000e+01, 7.60366667e+01,\n",
       "        8.00333333e+01, 8.40300000e+01, 8.80266667e+01, 9.20233333e+01,\n",
       "        9.60200000e+01, 1.00016667e+02, 1.04013333e+02, 1.08010000e+02,\n",
       "        1.12006667e+02, 1.16003333e+02, 1.20000000e+02]),\n",
       " <BarContainer object of 30 artists>)"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Distribution of positive hair length')"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'Hair length')"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Number of humans')"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.hist(pos_hair.Hair_Length, bins=30,)\n",
    "plt.title('Distribution of positive hair length')\n",
    "plt.xlabel('Hair length')\n",
    "plt.ylabel('Number of humans')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "a50e0d11-b2e4-4630-8fb0-83e0a0afca5a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-1.0     19\n",
       "-41.6     2\n",
       "-10.9     2\n",
       "-6.8      2\n",
       "-8.5      2\n",
       "         ..\n",
       "-19.4     1\n",
       "-25.1     1\n",
       "-13.5     1\n",
       "-42.2     1\n",
       "-24.4     1\n",
       "Name: Hair_Length, Length: 93, dtype: int64"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "neg_hair.Hair_Length.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "a829de93-fba0-4669-a533-28cf61a0196e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([2919., 2559., 2324., 2198., 1959., 1776., 1646., 1496., 1278.,\n",
       "        1143.,  979.,  802.,  733.,  579.,  496.,  441.,  361.,  311.,\n",
       "         243.,  171.,  141.,  105.,   75.,   80.,   44.,   45.,   26.,\n",
       "          16.,   13.,   22.]),\n",
       " array([  0.,   4.,   8.,  12.,  16.,  20.,  24.,  28.,  32.,  36.,  40.,\n",
       "         44.,  48.,  52.,  56.,  60.,  64.,  68.,  72.,  76.,  80.,  84.,\n",
       "         88.,  92.,  96., 100., 104., 108., 112., 116., 120.]),\n",
       " <BarContainer object of 30 artists>)"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Distribution of corrected hair lengths')"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'Hair length')"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Number of humans')"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAEWCAYAAACXGLsWAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAAAx3ElEQVR4nO3de1hU5d4+8HsYRFEQAmVI5XWnYpZH8EAGig6gKB5QILOtW9E2eSQlD6iJZuGh15TSInkrs3e7aysiVpgnPKBZ6s4DWZravhAEGZTkKIc5PL8/fF0/SWCNKMMw3J/r6rpgzVrP+j6zcO7WemY9SyGEECAiIqqFVUMXQERE5o9hQUREshgWREQki2FBRESyGBZERCSLYUFERLIYFhYuJiYGH3744RNpKycnBx4eHtDr9QCAyZMnY+fOnU+kbQB49dVXsXv37ifWnrE2btwILy8veHt7m3zfDaW2Y7dp0yYsWLCgTu1+/fXXmDZtmtHr37hxA88++yx0Ol2d9vc4kpKSMHHiRJPvt7GybugCqO7UajVu374NpVIJpVKJLl26YOzYsZgwYQKsrO79f8CqVauMbuudd97Biy++WOM67dq1w7lz555I7Zs2bcL169exfv16adknn3zyRNp+FDk5Odi6dSuOHDkCZ2dnk++/Lm7cuAE/Pz/88ssvsLY2r3/CY8aMwZgxYxq6jIeY83vWWPBda+Q+/vhjvPjiiyguLsbp06cRGxuL9PR0rFmz5onuR6fTWeQ/spycHDg6OtZ7UPz5/RNCQAghhXpTYKl/Q01F0/lLtXD29vbw8/NDXFwcdu/ejStXrgAAoqOjsXHjRgDAH3/8gddeew39+vXDgAED8Morr8BgMGDhwoXIycnBjBkz4OHhgf/5n/+RLg/s3LkTQ4YMwZQpU6q9ZJCZmYnQ0FB4enpi5syZKCgoAACcOnUKgwcPrlKjWq3GyZMnkZaWhi1btuC7776Dh4eH9H+iD14aMRgM+OijjzB06FAMHDgQixYtQnFxMYD/f+li9+7dGDJkCLy8vBAfH1/je1NcXIxFixbhhRdewNChQ/HRRx/BYDDg5MmTmDZtGvLy8uDh4YHo6Ohqtz906BDGjh0LT09P+Pv7Iy0tDQCg0WgwY8YMDBgwAAEBAdixY4e0zaZNmxAZGYkFCxbA09MTu3fvxuTJk7Fx40a8/PLL6N27N7KysvD7778jPDwcAwYMwPDhw7F3716pjfLycqxduxZDhw5F3759MXHiRJSXl2PSpEkAgP79+8PDw0M620tMTMSIESPQv39/TJ8+HdnZ2VJb33//PQIDA9G3b1+sWrUKchM3aLVaLFq0CB4eHggKCsLPP/8svZaQkAB/f394eHhg5MiROHjwoPTany/tPPvss9i+fTuGDRuGYcOG1brP+8dq6dKl8PHxwaBBg7Bx40bpsuf9ttetW4f+/ftDrVbj2LFj0rZZWVn461//Cg8PD0ydOhVvvfWWdDmtpvcMQI3tJSUlwc/PDx4eHlCr1fj6669l67doghqtoUOHiu+///6h5b6+vmL79u1CCCEWL14sNmzYIIQQYv369WL58uWisrJSVFZWijNnzgiDwVBtW1lZWaJr165i4cKForS0VJSVlUnLtFqtEEKISZMmCR8fH/Hbb7+J0tJSMWfOHPHGG28IIYT48ccfxaBBg2qs94MPPpDWvW/SpElix44dQgghdu7cKfz9/UVmZqYoKSkRs2fPFgsWLKhS27Jly0RZWZm4dOmS6N69u7h27Vq179PChQvFjBkzRHFxscjKyhLDhg2T9lNdnQ+6cOGC8PT0FCdOnBB6vV7k5uZK+3nllVfEihUrRHl5ufj111+Fl5eXOHnypNS/559/Xhw8eFDo9XpRVlYmJk2aJHx9fcWVK1eEVqsVRUVFYvDgwSIxMVFotVrxyy+/iAEDBoirV68KIYRYuXKlmDRpksjNzRU6nU789NNPoqKi4qHjIIQQBw8eFP7+/uLatWtCq9WKDz/8UEyYMEEIIUR+fr7o06eP+O6770RlZaXYunWreO6556T34M8++OAD0aNHD3H06FGh0+nE+vXrRVhYmPT63r17RW5urtDr9SIlJUX07t1baDQaIYQQu3btEi+//LK0bteuXcXUqVPFnTt3RFlZ2UP7+nNfZs2aJZYvXy5KS0vF7du3RUhIiPjyyy+ltp9//nnxr3/9S+h0OrF9+3bh7e0t/Q2/9NJLYu3ataKiokKcOXNGeHh4SH9j1b1ntbVXWloqPDw8xO+//y6EEEKj0YgrV67U+HfSFPDMwgK5uLigsLDwoeXW1ta4desWcnJy0KxZM/Tr1w8KhaLWtubOnYuWLVuiRYsW1b4+duxYdO3aFS1btsTrr7+Offv2Sf8n+Di++eYbTJ06FW5ubmjVqhWioqKwd+/eKmc1c+bMQYsWLdCtWzd069YNly9ffqgdvV6PvXv34o033oCdnR06dOiA8PBwo/8vMTExESEhIfD29oaVlRVUKhU6d+6Mmzdv4uzZs1iwYAGaN2+O5557DmFhYdizZ4+0bZ8+feDv7w8rKyvp/Rs3bhzc3d1hbW2N48ePo3379ggJCYG1tTWef/55DB8+HPv27YPBYMCuXbuwbNkyqFQqKJVKeHp6wsbGpto6v/rqK0RERKBz586wtrbGjBkzcOnSJWRnZyMtLQ3u7u4IDAxEs2bNMGXKFLRp06bWfvft2xe+vr5QKpUYO3Zslfd2xIgRUKlUsLKywsiRI9GxY0ekp6fX2FZERAQcHR1r/Bu67/bt2zh27BiWLl2Kli1bwtnZGVOnTkVKSoq0Trt27fDSSy9BqVRi3LhxuHXrFm7fvo2cnBz8/PPPiIyMhI2NDfr16we1Wl3r/mprDwCsrKxw9epVlJeXw8XFBe7u7rLtWTJeQLRAGo0GDg4ODy2fPn06Nm/eLH1bZcKECYiIiKi1LVdX11pff/rpp6Wf27VrB61Wizt37tSh6qry8vLQvn176ff27dtDp9MhPz9fWvbgB56trS3u3r37UDt37tyBVqtFu3btqtSp0WiMquPmzZvw9fWttj4HBwfY2dlVaffixYvS79W9dw++X9nZ2UhPT0e/fv2kZXq9HmPGjMGdO3dQUVEBNzc3o+rMycnB6tWrsW7dOmmZEAIajQZ5eXlValEoFFXqqM6D722LFi1QUVEhjTkkJydj69at0mWuu3fv1nrM5fb1YB90Oh18fHykZQaDocr2fz7mD+7fwcFBWnZ/vzdv3jS6nw+217ZtW2zcuBGfffYZli1bBk9PTyxevBidO3c2qi+WiGFhYdLT06HRaNC3b9+HXrOzs0N0dDSio6Nx5coVTJkyBT179sTAgQNrbE/uzOPBf4w3b95Es2bN8NRTT8HW1hbl5eXSa3q9Hn/88YfR7bq4uFS55p6TkwNra2s4OzsjNze31m0f9NRTT6FZs2bIyclBly5dpDpVKpVR2z/99NPIzMystr7CwkKUlJRIgfHndqvr44PLnn76afTv3x9bt259aD2DwYDmzZsjKysL3bp1q7GNB9uaMWNGtd9Eun79epX3TAgh+yFak+zsbLz55pv4/PPP4eHhIZ151EbuWN/n6uoKGxsb/Pjjj488EN62bVsUFhairKxM+tB/sI/G1vCgQYMGYdCgQSgvL0dcXByWL1+Of/7zn4/cjqXgZSgLUVJSgiNHjiAqKgpjxozBs88++9A6R44cwfXr1yGEgL29PZRKpfSPqE2bNsjKynrk/X799de4du0aysrK8P7772P48OFQKpV45plnUFFRgaNHj0Kr1SI+Ph6VlZXSds7OzsjOzobBYKi23VGjRmHbtm3IyspCaWkpNm7ciBEjRjzyh4hSqURgYCA2btyIkpISZGdnY+vWrUZ/vTM0NBRJSUn44YcfYDAYoNFo8Pvvv+Ppp5+Gh4cHNmzYgIqKCly+fBmJiYmP9LXRIUOGICMjA8nJydBqtdBqtUhPT8fvv/8OKysrhISEYM2aNdBoNNDr9Th37hwqKyvh5OQEKyurKsfr5ZdfRkJCAq5evQrg3kDxd999BwDw9fXF1atXceDAAeh0OnzxxRfSpZZHVVZWBoVCAScnJwDArl27pH0+LhcXF3h7e2Pt2rUoKSmBwWBAZmYmTp8+Lbtt+/bt0aNHD2zatAmVlZU4d+4cjhw5Ir1e3XtWm9u3b+PQoUO4e/cubGxs0LJlyyb1zbXqNO3eW4D732Dy9fXFxx9/jPDw8Bq/Nnv9+nWEh4fDw8MDEyZMwMSJE/HCCy8AuHddOT4+Hv369cOnn35q9P7Hjh2L6OhoeHt7o7KyEsuWLQNw79tZK1aswJtvvonBgwfD1ta2yqWQwMBAAICXlxfGjRv3ULshISEYM2YMJk2aBD8/P9jY2GD58uVG1/Wg5cuXw9bWFv7+/njllVcwatQohISEGLVtr169sGbNGqxevRp9+/bFpEmTkJOTAwDYsGEDsrOzMWjQIMyZMwdz586t9T6VP7Ozs8Onn36KvXv3YtCgQfDx8cH69eulUF28eDG6du2K0NBQDBgwAOvXr4fBYICtrS1mzJiBiRMnol+/fjh//jwCAgLw6quvIioqCp6enhg1apT0rS0nJye8//77eO+99+Dl5YXr16/D09PzEd/Fe7p06YJp06bh5ZdfxosvvogrV67Uua3qvPvuu9BqtRg5ciT69++PyMhI3Lp1y6ht169fj/Pnz8PLywtxcXEYOXKkNMZT3XtWG4PBgM8//xyDBg3CgAEDcObMGaxcufIxe9e4KYTgw4+IyPLMmzcPnTp1QmRkZEOXYhF4ZkFEFiE9PR2ZmZkwGAxIS0tDamoq/P39G7osi8EBbiKyCLdv38bcuXNRUFAAV1dXrFy5Es8//3xDl2UxeBmKiIhk8TIUERHJssjLUAaDAXp93U+YlErFY21vLiylHwD7Yq4spS+W0g/g8frSrJmyxtcsMiz0eoGCgofv5jWWo2PLx9reXFhKPwD2xVxZSl8spR/A4/WlbVv7Gl+rt8tQFRUVCA0NxZgxYxAUFIQPPvgAwL2ZIcPCwhAQEIB58+ZJ3ymvrKzEvHnzEBAQgLCwMNy4cUNqa8uWLQgICMDw4cNx/Pjx+iqZiIhqUG9hYWNjg23btuHrr79GcnIyjh8/jvPnz2P9+vWYOnUqDh48iNatWyMxMREAsHPnTrRu3RoHDx7E1KlTpYfiXLt2DSkpKUhJScEnn3yCt95664lMVEdERMart7BQKBRo1aoVgHsPPdHpdFAoFPjxxx8xfPhwAPdm4ExNTQUAHD58WLqTd/jw4fjhhx8ghEBqaiqCgoJgY2MDNzc32RkuiYjoyavXMQu9Xo/x48cjMzMTr7zyCtzc3NC6dWtpfh9XV1dp9k+NRiPNLmltbQ17e3vcuXMHGo0GvXv3ltpUqVSyM4YqlQo4Orasc91KpdVjbW8uLKUfAPtiriylL5bSD6D++lKvYaFUKrFnzx4UFRVh9uzZ+M9//lOfu5NwgPseS+kHwL6YK0vpi6X0A2iEA9wPat26Nby8vHD+/HkUFRVJD7DJzc2VpnRWqVTSlMI6nQ7FxcV46qmnoFKpqkyvrNFojJ5emoiInox6C4s//vgDRUVFAO49S/jkyZPo3LkzvLy8sH//fgDA7t27padZqdVq7N69GwCwf/9+vPDCC1AoFFCr1UhJSUFlZSWysrKQkZGBXr161VfZRERUjXq7DJWXl4fo6Gjo9XoIIRAYGIihQ4eiS5cumD9/PuLi4qRHUQL3nhuwcOFCBAQEwMHBARs3bgQAuLu7Y8SIERg5ciSUSiViYmKgVNZ84wgRET15Fjk3lFar55gFLKcfAPtiriylL5bSD6D+xiws8g7ux6VH7W/afWUVOpQUldV/QUREDYxhUY0WzZT4S3SK7HoZa4NQYoJ6iIgaGmedJSIiWQwLIiKSxbAgIiJZDAsiIpLFsCAiIlkMCyIiksWwICIiWQwLIiKSxbAgIiJZDAsiIpLFsCAiIlkMCyIiksWwICIiWQwLIiKSxbAgIiJZDAsiIpLFsCAiIlkMCyIiksWwICIiWQwLIiKSxbAgIiJZDAsiIpLFsCAiIlnWDV1AY1au1aNtW3vZ9coqdCgpKjNBRURE9aPewuLmzZtYtGgR8vPzoVAo8NJLL2HKlCnYtGkTduzYAScnJwBAVFQUfH19AQBbtmxBYmIirKys8Oabb2LQoEEAgLS0NMTGxsJgMCAsLAwRERH1VfYjadFMib9Ep8iul7E2CCUmqIeIqL7UW1golUpER0eje/fuKCkpQUhICLy9vQEAU6dOxfTp06usf+3aNaSkpCAlJQUajQbh4eHYv38/AGDVqlXYunUrVCoVQkNDoVar0aVLl/oqnYiI/qTewsLFxQUuLi4AADs7O3Tq1AkajabG9VNTUxEUFAQbGxu4ubmhY8eOSE9PBwB07NgRbm5uAICgoCCkpqYyLIiITMgkYxY3btzApUuX0Lt3b5w9exbbt29HcnIyevTogejoaDg4OECj0aB3797SNiqVSgoXV1fXKsvvh0hNlEoFHB1b1k9n6qgh6lEqrczufagr9sU8WUpfLKUfQP31pd7DorS0FJGRkVi6dCns7OwwceJEzJo1CwqFAu+//z7Wrl2LNWvWPNF96vUCBQV367y9MYPWj+px6qkrR8eWDbLf+sC+mCdL6Yul9AN4vL7U9tlXr1+d1Wq1iIyMxOjRozFs2DAAQJs2baBUKmFlZYWwsDD8/PPPAO6dMeTm5krbajQaqFSqGpcTEZHp1FtYCCGwbNkydOrUCeHh4dLyvLw86edDhw7B3d0dAKBWq5GSkoLKykpkZWUhIyMDvXr1Qs+ePZGRkYGsrCxUVlYiJSUFarW6vsomIqJq1NtlqJ9++gl79uxB165dMXbsWAD3vib77bff4vLlywCA9u3bY9WqVQAAd3d3jBgxAiNHjoRSqURMTAyUSiUAICYmBq+++ir0ej1CQkKkgCEiItOot7Do168ffvvtt4eW37+nojozZ87EzJkzq92mtu2IiKh+cboPIiKSxbAgIiJZDAsiIpLFsCAiIlkMCyIiksWwICIiWQwLIiKSxYcfmQAfkkREjR3DwgT4kCQiaux4GYqIiGQxLIiISBbDgoiIZDEsiIhIFsOCiIhkMSyIiEgWw4KIiGTxPgszwpv3iMhcyYZFZmYmXF1dYWNjg1OnTuG3335DcHAwWrdubYr6mhTevEdE5kr2MtTcuXNhZWWF69evIyYmBjdv3sQbb7xhitqIiMhMyIaFlZUVrK2tcfDgQUyaNAmLFy/GrVu3TFEbERGZCdmwsLa2xrfffovk5GQMGTIEAKDT6eq7LiIiMiOyYbFmzRqcP38eM2bMgJubG7KysjBmzBhT1EZERGZCdoC7S5cuePPNN6Xf3dzcEBERUa9FERGReZENi59++gmbN29GTk4OdDodhBBQKBRITU01RX1ERGQGZMNi2bJlWLJkCXr06AErK97DR0TUFMmGhb29PXx9fU1RCxERmSnZsPDy8sK6deswbNgw2NjYSMu7d+9er4UREZH5kA2LCxcuAAAuXrwoLVMoFPjiiy9q3e7mzZtYtGgR8vPzoVAo8NJLL2HKlCkoKCjA/PnzkZ2djfbt2yMuLg4ODg4QQiA2NhbHjh1DixYtsHbtWimQdu/ejfj4eADAzJkzMW7cuDp3mIiIHp1sWPzv//5vnRpWKpWIjo5G9+7dUVJSgpCQEHh7eyMpKQkDBw5EREQEEhISkJCQgIULFyItLQ0ZGRk4cOAALly4gJUrV2Lnzp0oKCjA5s2bsWvXLigUCowfPx5qtRoODg51qouIiB6dURMJHj16FFevXkVFRYW0bM6cObVu4+LiAhcXFwCAnZ0dOnXqBI1Gg9TUVCmAgoODMXnyZCxcuBCpqakIDg6GQqFAnz59UFRUhLy8PJw+fRre3t5wdHQEAHh7e+P48eMYNWpUXfpLRER1IBsWMTExKC8vx6lTpxAWFob9+/ejZ8+ej7STGzdu4NKlS+jduzfy8/OlEGnbti3y8/MBABqNBq6urtI2rq6u0Gg0Dy1XqVTQaDS17k+pVMDRseUj1djYGNM/pdLKYt4H9sU8WUpfLKUfQP31RTYszp07h2+++QajR4/GnDlzEB4ejr///e9G76C0tBSRkZFYunQp7OzsqrymUCigUCgevWoZer1AQcHdOm9vzDThDc2Y/jk6tnys98GcsC/myVL6Yin9AB6vL7V99sneONGiRQsAgK2tLTQaDZo1a2b0RIJarRaRkZEYPXo0hg0bBgBwdnZGXl4eACAvLw9OTk4A7p0x5ObmStvm5uZCpVI9tFyj0UClUhm1fyIiejJkw2LIkCEoKirC9OnTpcHloKAg2YaFEFi2bBk6deqE8PBwablarUZycjIAIDk5GX5+flWWCyFw/vx52Nvbw8XFBT4+Pjhx4gQKCwtRWFiIEydOwMfHp47dtQz3H5Ik95++oQslIoshexlq9uzZAIDhw4dj6NChqKiogL29/GWan376CXv27EHXrl0xduxYAEBUVBQiIiIwb948JCYmol27doiLiwMA+Pr64tixYwgICICtrS1Wr14NAHB0dMSsWbMQGhoq1XN/sLupepSHJBWboB4isnyyYaHX63H06FFkZ2dDr////6/64NlCdfr164fffvut2te2bdv20DKFQoEVK1ZUu35oaKgUFkREZHqyYTFjxgw0b94cXbt25dxQRERNlGxY5Obm4ptvvjFFLUREZKZkTxUGDx6MEydOmKIWIiIyU7JnFn369MGcOXNgMBhgbW0tPc/i7NmzpqiPiIjMgGxYrFmzBl999RWeffbZermBjoiIzJ/sZainn34aXbt2ZVAQETVhsmcWbm5umDx5MgYPHlzleRZyX50lIiLLIRsWHTp0QIcOHaDVaqHVak1RExERmRnZsJCbipyIiCyfbFhMnjy52vEKuSflERGR5ZANi8WLF0s/V1RU4MCBA1AqlfVaFD0Z9yccNEZZhQ4lRWX1XBERNVayYdGjR48qv/ft25fzNDUSxk44CNybdLCknushosZLNiwKCgqknw0GA3755RcUF3MuUyKipkQ2LMaPHw+FQgEhBKytrdGhQwfExsaaojYiIjITsmFx+PBhU9RBRERmTDYsAODs2bMPPc8iODi4vmoiIiIzIxsWCxcuRFZWFrp16yZ9C0qhUDAsiIiaENmwuHjxIvbu3cu5oYiImjDZiQTd3d1x69YtU9RCRERmqsYzixkzZgAASktLERQUhF69eqFZs2bS6x9//HH9V0cmY+wNfLx5j6hpqjEspk2bZso6qIEZewMfb94jappqDIsBAwaYsg4iIjJjsmMWREREDAsiIpJVY1hMmTIFAPDf//3fJiuGiIjMU41jFrdu3cLZs2dx+PBhBAUFQQhR5fXu3bvXe3FERGQeagyLyMhIfPTRR8jNzcWaNWuqvKZQKGQffrRkyRIcPXoUzs7O+PbbbwEAmzZtwo4dO+Dk5AQAiIqKgq+vLwBgy5YtSExMhJWVFd58800MGjQIAJCWlobY2FgYDAaEhYUhIiKi7r0lIqI6qTEsAgMDERgYiA8//BCzZ89+5IbHjx+PSZMmVXl4EgBMnToV06dPr7Ls2rVrSElJQUpKCjQaDcLDw7F//34AwKpVq7B161aoVCqEhoZCrVajS5cuj1wPERHVnex0H7Nnz0Zqair+/e9/A7j3ldqhQ4fKNty/f3/cuHHDqCJSU1MRFBQEGxsbuLm5oWPHjkhPTwcAdOzYEW5ubgCAoKAgpKamMiyIiExMNizee+89pKenY/To0QDuPXv73LlziIqKqtMOt2/fjuTkZPTo0QPR0dFwcHCARqNB7969pXVUKhU0Gg0AwNXVtcry+yFSG6VSAUfHlnWqj+Q1xHurVFpZzDFlX8yPpfQDqL++yIbF0aNHsWfPHlhZ3fvi1Lhx4xAcHFynsJg4cSJmzZoFhUKB999/H2vXrn1oPORJ0OsFCgru1nl7Y59b3RSVa/Vo0Uz+GexPeloQR8eWj3VMzQn7Yn4spR/A4/Wlts8+o55nUVRUBEdHRwB4rEeqtmnTRvo5LCxMmn9KpVIhNzdXek2j0UClUgFAjcupYXBaEKKmSTYsXnvtNYwbNw5eXl4QQuDMmTNYsGBBnXaWl5cHFxcXAMChQ4fg7u4OAFCr1XjjjTcQHh4OjUaDjIwM9OrVC0IIZGRkICsrCyqVCikpKXjvvffqtG8iIqo72bAYNWoUBgwYgJ9//hkAsGDBArRt21a24aioKJw+fRp37tzB4MGDMXfuXJw+fRqXL18GALRv3x6rVq0CcG8a9BEjRmDkyJFQKpWIiYmRHrQUExODV199FXq9HiEhIVLAEBGR6Rh1GcrFxQV+fn6P1PCGDRseWhYWFlbj+jNnzsTMmTMfWu7r6yvdi0FERA2Dc0MREZEshgUREcmqNSz0ej0CAwNNVQsREZmpWsNCqVTimWeeQU5OjqnqISIiMyQ7wF1UVCQ9g9vW1lZazmdwExE1HbJh8frrr5uiDiIiMmOyYTFgwABkZ2fj+vXrePHFF1FWVga9Xm+K2oiIyEzIfhtqx44diIyMRExMDIB7U27UZcpyIiJqvGTDYvv27fjyyy9hZ2cHAPjLX/6CP/74o94LIyIi8yEbFjY2NrCxsZF+1+l09VoQERGZH9kxi/79++Pjjz9GeXk5vv/+e/zzn/+EWq02RW3UiJVr9UZN9f6kpzInovohGxYLFixAYmIiunbtin/961/w9fWtdY4nIoBTmRNZGtmwsLKyQnBwMHr16gWFQoFnnnkGCoXCFLUREZGZMOpJeStWrMB//dd/QQiBGzdu4K233uJMsERETYhsWKxduxZffPEFOnbsCADIzMxEREQEw4KIqAmR/TZUq1atpKAAADc3N7Rq1apeiyIiIvNS45nFgQMHAAA9evTA3//+d4wYMQIKhQL79u1Dz549TVYgERE1vBrD4siRI9LPbdq0wZkzZwAATk5OqKioqP/KiIjIbNQYFmvWrDFlHUREZMZkB7izsrLwj3/8A9nZ2VXu3uYU5URETYdsWMyePRuhoaEYOnQorKz4FFZ6soy907tcy5mOiRqSbFg0b94cf/vb30xRCzVBj3Knd7EJ6iGi6smGxd/+9jds3rwZ3t7eVSYU7N69e70WRkRE5kM2LK5cuYI9e/bgxx9/lKb5UCgU+OKLL+q9OCIiMg+yYbFv3z4cOnSoylkFERE1LbIj1u7u7igu5tViIqKmTPbMori4GCNGjEDPnj3RrFkzaTm/OktE1HTIhsXcuXPr1PCSJUtw9OhRODs749tvvwUAFBQUYP78+cjOzkb79u0RFxcHBwcHCCEQGxuLY8eOoUWLFli7dq00gL57927Ex8cDAGbOnIlx48bVqR4iIqo72bAYMGBAnRoeP348Jk2ahMWLF0vLEhISMHDgQERERCAhIQEJCQlYuHAh0tLSkJGRgQMHDuDChQtYuXIldu7ciYKCAmzevBm7du2CQqHA+PHjoVar4eDgUKeaiIiobmTHLDw8PODp6QlPT0/07NkTzz33HDw9PWUb7t+//0Mf6qmpqQgODgYABAcH49ChQ1WWKxQK9OnTB0VFRcjLy8OJEyfg7e0NR0dHODg4wNvbG8ePH69DN4mI6HHInlmcO3dO+lkIgdTUVJw/f75OO8vPz4eLiwsAoG3btsjPzwcAaDQauLq6Suu5urpCo9E8tFylUkGj0cjuR6lUwNGxZZ1qJPNlKcdUqbRiX8yMpfQDqL++yIbFgxQKBfz9/bF582YsWLDgsXasUCjq7fGser1AQcHdOm9vzPQTZFrlWj1aNFPKrldWoUNJUZkJKqo7R8eWj/X3aU4spS+W0g/g8fpS22efbFjcf64FABgMBly8eBHNmzevUyHOzs7Iy8uDi4sL8vLy4OTkBODeGUNubq60Xm5uLlQqFVQqFU6fPi0t12g0dR5DocbtUaYFKTFBPURNjeyYxZEjR6T/Tpw4gVatWuGjjz6q087UajWSk5MBAMnJyfDz86uyXAiB8+fPw97eHi4uLvDx8cGJEydQWFiIwsJCnDhxAj4+PnXaNxER1Z3smUVdn2sRFRWF06dP486dOxg8eDDmzp2LiIgIzJs3D4mJiWjXrh3i4uIAAL6+vjh27BgCAgJga2uL1atXAwAcHR0xa9YshIaGArg3A66jo2Od6iEiorqrMSw2b95c40YKhQKzZ8+uteENGzZUu3zbtm3VtrdixYpq1w8NDZXCgoiIGkaNYdGy5cOj6Xfv3sWuXbtQUFAgGxZERGQ5agyLadOmST+XlJTgiy++QFJSEkaOHFnlNSIisny1jlkUFBRg69at+OabbzBu3Djs3r2bd08TETVBNYbFunXrcPDgQbz00kv45ptv0KpVK1PWRUREZqTGsNi6dStsbGwQHx9fZYZZIQQUCgXOnj1rkgKJiKjh1RgWly9fNmUdRERkxmRvyiMiImJYEBGRrEeaSJDI3JVr9UZNBNkYJhwkMicMC7IonHCQqH7wMhQREcliWBARkSyGBRERyeKYBTVJxg6EAxwMJwIYFtREGTsQDnAwnAjgZSgiIjICw4KIiGQxLIiISBbDgoiIZDEsiIhIFsOCiIhkMSyIiEgWw4KIiGQxLIiISBbv4CaSwWdkEDEsiGTxGRlEDRQWarUarVq1gpWVFZRKJZKSklBQUID58+cjOzsb7du3R1xcHBwcHCCEQGxsLI4dO4YWLVpg7dq16N69e0OUTUTUZDXYmMW2bduwZ88eJCUlAQASEhIwcOBAHDhwAAMHDkRCQgIAIC0tDRkZGThw4ADefvttrFy5sqFKJiJqssxmgDs1NRXBwcEAgODgYBw6dKjKcoVCgT59+qCoqAh5eXkNWCkRUdPTYGMW06dPh0KhwIQJEzBhwgTk5+fDxcUFANC2bVvk5+cDADQaDVxdXaXtXF1dodFopHWro1Qq4OjYsn47QFQNY/7ulEori/n7tJS+WEo/gPrrS4OExZdffgmVSoX8/HyEh4ejU6dOVV5XKBRQKBR1bl+vFygouFvn7Y19KA7Rg8q1erRopjRqveLH+Ps0J46OLR/r35q5sJR+AI/Xl9o++xokLFQqFQDA2dkZAQEBSE9Ph7OzM/Ly8uDi4oK8vDw4OTlJ6+bm5krb5ubmStsTmZNH+dZUsQnqIXqSTD5mcffuXZSUlEg/f//993B3d4darUZycjIAIDk5GX5+fgAgLRdC4Pz587C3t6/1EhQRET15Jj+zyM/Px+zZswEAer0eo0aNwuDBg9GzZ0/MmzcPiYmJaNeuHeLi4gAAvr6+OHbsGAICAmBra4vVq1ebumQioibP5GHh5uaGr7/++qHlTz31FLZt2/bQcoVCgRUrVpiiNCKT4B3h1BjxDm4iE+Md4dQYmc19FkREZL4YFkREJIthQUREsjhmQWSmOBBO5oRhQWSmOBBO5oSXoYiISBbDgoiIZPEyFFEjx7ENMgWGBVEjx7ENMgVehiIiIlkMCyIiksWwICIiWRyzIGoiOBBOj4NhQdREcCCcHgcvQxERkSyGBRERyWJYEBGRLI5ZEFEVxg6E31+XmgaGBRFVYexAOHBvMLy4nush88CwIKI649dxmw6GBRHVGb+O23QwLIio3vEMpPFjWBBRveMZSOPHsCAis2HsGUi5Vo8WzZSy6/FM5clhWBCR2XiUMxCeqZgWb8ojIiJZjebMIi0tDbGxsTAYDAgLC0NERERDl0REZu5RLmtxAL52jSIs9Ho9Vq1aha1bt0KlUiE0NBRqtRpdunRp6NKIyIw96ctal98ONPru9icdLHatbWHbXP4ju77uqm8UYZGeno6OHTvCzc0NABAUFITU1FSGBRGZ1KPc3W5ssBg7WA/A6OCrj7vqFUIIUQ/tPlH79u3D8ePHERsbCwBITk5Geno6YmJiGrgyIqKmgQPcREQkq1GEhUqlQm5urvS7RqOBSqVqwIqIiJqWRhEWPXv2REZGBrKyslBZWYmUlBSo1eqGLouIqMloFAPc1tbWiImJwauvvgq9Xo+QkBC4u7s3dFlERE1GoxjgJiKihtUoLkMREVHDYlgQEZEshsUD0tLSMHz4cAQEBCAhIaGhy3kkN2/exOTJkzFy5EgEBQVh27ZtAICCggKEh4dj2LBhCA8PR2FhYQNXahy9Xo/g4GC89tprAICsrCyEhYUhICAA8+bNQ2VlZQNXaJyioiJERkYiMDAQI0aMwLlz5xrtMfn8888RFBSEUaNGISoqChUVFY3muCxZsgQDBw7EqFGjpGU1HQchBN555x0EBARg9OjR+OWXXxqq7GpV15d169YhMDAQo0ePxuzZs1FUVCS9tmXLFgQEBGD48OE4fvx43XcsSAghhE6nE35+fiIzM1NUVFSI0aNHi6tXrzZ0WUbTaDTi4sWLQgghiouLxbBhw8TVq1fFunXrxJYtW4QQQmzZskW8++67DVmm0T777DMRFRUlIiIihBBCREZGim+//VYIIcTy5cvF9u3bG7I8oy1atEjs2LFDCCFERUWFKCwsbJTHJDc3VwwdOlSUlZUJIe4dj127djWa43L69Glx8eJFERQUJC2r6TgcPXpUTJ8+XRgMBnHu3DkRGhraIDXXpLq+HD9+XGi1WiGEEO+++67Ul6tXr4rRo0eLiooKkZmZKfz8/IROp6vTfnlm8X8enFLExsZGmlKksXBxcUH37t0BAHZ2dujUqRM0Gg1SU1MRHBwMAAgODsahQ4casErj5Obm4ujRowgNDQVw7//0fvzxRwwfPhwAMG7cuEZxbIqLi3HmzBmpHzY2NmjdunWjPCbAvbO98vJy6HQ6lJeXo23bto3muPTv3x8ODg5VltV0HO4vVygU6NOnD4qKipCXl2fqkmtUXV98fHxgbX3vy619+vSR7ktLTU1FUFAQbGxs4Obmho4dOyI9Pb1O+2VY/B+NRgNXV1fpd5VKBY1G04AV1d2NGzdw6dIl9O7dG/n5+XBxcQEAtG3bFvn5+Q1cnbzVq1dj4cKFsLK69+d5584dtG7dWvrH4Orq2iiOzY0bN+Dk5IQlS5YgODgYy5Ytw927dxvlMVGpVJg2bRqGDh0KHx8f2NnZoXv37o3yuNxX03H482dBY+vXrl27MHjwYABP9nONYWFhSktLERkZiaVLl8LOzq7KawqFAgqFooEqM86RI0fg5OSEHj16NHQpj02n0+HXX3/FxIkTkZycDFtb24fGwhrDMQGAwsJCpKamIjU1FcePH0dZWdnjXf82M43lOMiJj4+HUqnEmDFjnnjbjeKmPFOwhClFtFotIiMjMXr0aAwbNgwA4OzsjLy8PLi4uCAvLw9OTk4NXGXtzp49i8OHDyMtLQ0VFRUoKSlBbGwsioqKoNPpYG1tjdzc3EZxbFxdXeHq6orevXsDAAIDA5GQkNDojgkAnDx5Eh06dJBqHTZsGM6ePdsoj8t9NR2HP38WNJZ+JSUl4ejRo/j888+l4HuSn2s8s/g/jX1KESEEli1bhk6dOiE8PFxarlarkZycDODebL1+fn4NVKFx3njjDaSlpeHw4cPYsGEDXnjhBbz33nvw8vLC/v37AQC7d+9uFMembdu2cHV1xX/+8x8AwA8//IDOnTs3umMCAO3atcOFCxdQVlYGIQR++OEHdOnSpVEel/tqOg73lwshcP78edjb20uXq8xVWloaPvnkE8THx8PW1lZarlarkZKSgsrKSmRlZSEjIwO9evWq0z54B/cDjh07htWrV0tTisycObOhSzLav//9b/z1r39F165dpWv9UVFR6NWrF+bNm4ebN2+iXbt2iIuLg6OjY8MWa6RTp07hs88+w5YtW5CVlYX58+ejsLAQzz33HNavXw8bG5uGLlHWpUuXsGzZMmi1Wri5uWHNmjUwGAyN8ph88MEH2Lt3L6ytrfHcc88hNjYWGo2mURyXqKgonD59Gnfu3IGzszPmzp0Lf3//ao+DEAKrVq3C8ePHYWtri9WrV6Nnz54N3QVJdX1JSEhAZWWl9HfUu3dvrFq1CsC9S1O7du2CUqnE0qVL4evrW6f9MiyIiEgWL0MREZEshgUREcliWBARkSyGBRERyWJYEBGRLIYFEQAPD48qvyclJUlfPaxJamqqUbMTnzp1Spo990k6dOgQrl27Jv0+efJk/Pzzz098P0QAw4Kozvz8/BAREfHQcp1OZ5L9/zksiOoTp/sgknH48GHEx8dDq9XC0dER69evR5s2bZCUlISLFy8iJiYG0dHRsLGxwaVLl+Dp6YklS5ZU29bdu3fx9ttv4+rVq9DpdJgzZw78/f2RlJSEw4cPo6ysDFlZWfD398eiRYsAADt37sQnn3wCe3t7dOvWDTY2Nhg1ahQOHz6M06dPIz4+Hps2bQIA7Nu3D2+99RaKi4sRGxuLfv36mex9IsvGsCACUF5ejrFjx0q/FxYWSlNX9O3bFzt27IBCoZA+uKOjox9qQ6PR4KuvvoJSqaxxPx9//DFeeOEFrFmzBkVFRQgLC8OLL74I4N7d3snJybCxsUFgYCAmT54MKysrxMfHIykpCa1atcKUKVPQrVs3eHp6Qq1WY8iQIQgMDJTa1+v1SExMxLFjx7B582Z8/vnnT+gdoqaOYUEEoEWLFtizZ4/0+/2zBuDeRHLz58/HrVu3UFlZiQ4dOlTbRmBgYK1BAQAnTpzA4cOH8dlnnwEAKioqcPPmTQDAwIEDYW9vDwDo3LkzsrOzUVBQgP79+0vTOAQGBiIjI6PG9gMCAgAA3bt3R3Z2tnzHiYzEsCCS8c4772Dq1Knw8/PDqVOnsHnz5mrXe3ACt9p88MEH6NSpU5VlFy5cqDKnklKphF6vf+Ra77dhZWVVp+2JasIBbiIZxcXF0rTO92cprSsfHx/84x//wP0p2X799dda1+/ZsyfOnDmDwsJC6HQ6HDhwQHqtVatWKC0tfax6iIzFsCCSMWfOHLz++usYP378Y88OO2vWLOh0OowZMwZBQUF4//33a11fpVLhtddeQ1hYGCZOnIj27dtLl6pGjhyJTz/9FMHBwcjMzHysuojkcNZZIjNXWlqKVq1aSd+eCgkJkcYmiEyFYxZEZm7z5s04efIkKioq4OPjA39//4YuiZognlkQEZEsjlkQEZEshgUREcliWBARkSyGBRERyWJYEBGRrP8HtKoaUWd3+FUAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "humans3 = humans2.copy()     # Versioned changes to data\n",
    "\n",
    "# The \"sentinel\" negative value means missing\n",
    "humans3.loc[humans3.Hair_Length == -1, 'Hair_Length'] = None\n",
    "\n",
    "# All other values simply become non-negative\n",
    "humans3['Hair_Length'] = humans3.Hair_Length.abs()\n",
    "\n",
    "plt.hist(humans3.Hair_Length, bins=30)\n",
    "plt.title('Distribution of corrected hair lengths')\n",
    "plt.xlabel('Hair length')\n",
    "plt.ylabel('Number of humans')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e31b017b-036a-4ba0-8216-c2a3ceb0555e",
   "metadata": {},
   "source": [
    "### Outlier Detection"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "62b43554-02b5-495f-858f-a21de1e91549",
   "metadata": {},
   "source": [
    "#### Z-Score"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f5d85e2b-8f25-4859-96c2-2a5d1e9799a3",
   "metadata": {},
   "source": [
    "Tests for normal distribution"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "f0787b5f-1c1e-4d23-a561-e8d6160a80b7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_distribution(data):\n",
    "    # fit normal distribution -> compute mean and std\n",
    "    mean, std = norm.fit(data)\n",
    "    \n",
    "    plt.hist(data, bins=50)\n",
    "    \n",
    "    # compute probability density function for given distribution\n",
    "    xmin, xmax = plt.xlim()\n",
    "    x = np.linspace(xmin, xmax, 100)\n",
    "    p = norm.pdf(x, mean, std)\n",
    "    plt.plot(x, p, 'k')\n",
    "    \n",
    "    title = \"Fit Values: {:.2f} and {:.2f}\".format(mean, std)\n",
    "    plt.xlabel(\"Height\")\n",
    "    plt.ylabel(\"Number of humans\")\n",
    "    plt.title(title)\n",
    "    plt.show()\n",
    "\n",
    "plot_distribution(humans.Height)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "e2a8f65e-1d9d-468a-a614-65ffd512e492",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# test for normal distribution\n",
    "# plot boxplot (in this case, via pandas)\n",
    "humans.Height.plot(kind = 'box')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "4dfb45f0-8114-4c8f-b4c5-1cc1924740c5",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/eva/.local/share/virtualenvs/data-engineering-analytics-notebooks-Qx0adyYX/lib64/python3.9/site-packages/statsmodels/graphics/gofplots.py:993: UserWarning: marker is redundantly defined by the 'marker' keyword argument and the fmt string \"bo\" (-> marker='o'). The keyword argument will take precedence.\n",
      "  ax.plot(x, y, fmt, **plot_style)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "## QQ plot\n",
    "sm.qqplot(humans.Height, line='45',fit=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "c388b2eb-5dcb-4556-8eae-9fb309355765",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0 0.0\n"
     ]
    }
   ],
   "source": [
    "# Kolmogorov-Smirnov test\n",
    "ks_statistic, p_value = kstest(humans.Height, 'norm')\n",
    "print(ks_statistic, p_value)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "204e833c-0f26-49c3-ae4e-1fe6f82b6fbc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Height', 'Weight', 'Hair_Length', 'Favorite', 'zscore_Height',\n",
       "       'zscore_Weight', 'zscore_Hair_Length'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# compute z-scores\n",
    "\n",
    "humans4 = humans3.copy()\n",
    "\n",
    "for var in ('Height', 'Weight', 'Hair_Length'):\n",
    "    zscore = (humans4[var] - humans4[var].mean()) / humans4[var].std()\n",
    "    humans4[f\"zscore_{var}\"] = zscore\n",
    "\n",
    "humans4.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "f439a5f5-9710-4cd7-989f-9907dfac9bca",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Hair_Length</th>\n",
       "      <th>Favorite</th>\n",
       "      <th>zscore_Height</th>\n",
       "      <th>zscore_Weight</th>\n",
       "      <th>zscore_Hair_Length</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>138</th>\n",
       "      <td>187.708718</td>\n",
       "      <td>86.829633</td>\n",
       "      <td>19.3</td>\n",
       "      <td>green</td>\n",
       "      <td>3.105616</td>\n",
       "      <td>2.084216</td>\n",
       "      <td>-0.320304</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>174</th>\n",
       "      <td>187.537446</td>\n",
       "      <td>79.893761</td>\n",
       "      <td>37.5</td>\n",
       "      <td>blue</td>\n",
       "      <td>3.070170</td>\n",
       "      <td>1.047496</td>\n",
       "      <td>0.532971</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>412</th>\n",
       "      <td>157.522316</td>\n",
       "      <td>62.564977</td>\n",
       "      <td>6.8</td>\n",
       "      <td>blue</td>\n",
       "      <td>-3.141625</td>\n",
       "      <td>-1.542673</td>\n",
       "      <td>-0.906345</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1162</th>\n",
       "      <td>188.592435</td>\n",
       "      <td>86.155948</td>\n",
       "      <td>53.1</td>\n",
       "      <td>red</td>\n",
       "      <td>3.288506</td>\n",
       "      <td>1.983518</td>\n",
       "      <td>1.264351</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1383</th>\n",
       "      <td>188.454995</td>\n",
       "      <td>74.021469</td>\n",
       "      <td>13.6</td>\n",
       "      <td>green</td>\n",
       "      <td>3.260062</td>\n",
       "      <td>0.169753</td>\n",
       "      <td>-0.587539</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22769</th>\n",
       "      <td>188.463987</td>\n",
       "      <td>81.222376</td>\n",
       "      <td>17.0</td>\n",
       "      <td>red</td>\n",
       "      <td>3.261923</td>\n",
       "      <td>1.246087</td>\n",
       "      <td>-0.428136</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22945</th>\n",
       "      <td>157.293031</td>\n",
       "      <td>44.744929</td>\n",
       "      <td>18.4</td>\n",
       "      <td>red</td>\n",
       "      <td>-3.189077</td>\n",
       "      <td>-4.206272</td>\n",
       "      <td>-0.362499</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23039</th>\n",
       "      <td>187.845548</td>\n",
       "      <td>88.554510</td>\n",
       "      <td>6.9</td>\n",
       "      <td>blue</td>\n",
       "      <td>3.133934</td>\n",
       "      <td>2.342037</td>\n",
       "      <td>-0.901657</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24244</th>\n",
       "      <td>158.153049</td>\n",
       "      <td>59.725932</td>\n",
       "      <td>13.8</td>\n",
       "      <td>green</td>\n",
       "      <td>-3.011091</td>\n",
       "      <td>-1.967031</td>\n",
       "      <td>-0.578162</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24801</th>\n",
       "      <td>189.310696</td>\n",
       "      <td>85.406727</td>\n",
       "      <td>2.3</td>\n",
       "      <td>green</td>\n",
       "      <td>3.437154</td>\n",
       "      <td>1.871531</td>\n",
       "      <td>-1.117320</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>51 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           Height     Weight  Hair_Length Favorite  zscore_Height  \\\n",
       "138    187.708718  86.829633         19.3    green       3.105616   \n",
       "174    187.537446  79.893761         37.5     blue       3.070170   \n",
       "412    157.522316  62.564977          6.8     blue      -3.141625   \n",
       "1162   188.592435  86.155948         53.1      red       3.288506   \n",
       "1383   188.454995  74.021469         13.6    green       3.260062   \n",
       "...           ...        ...          ...      ...            ...   \n",
       "22769  188.463987  81.222376         17.0      red       3.261923   \n",
       "22945  157.293031  44.744929         18.4      red      -3.189077   \n",
       "23039  187.845548  88.554510          6.9     blue       3.133934   \n",
       "24244  158.153049  59.725932         13.8    green      -3.011091   \n",
       "24801  189.310696  85.406727          2.3    green       3.437154   \n",
       "\n",
       "       zscore_Weight  zscore_Hair_Length  \n",
       "138         2.084216           -0.320304  \n",
       "174         1.047496            0.532971  \n",
       "412        -1.542673           -0.906345  \n",
       "1162        1.983518            1.264351  \n",
       "1383        0.169753           -0.587539  \n",
       "...              ...                 ...  \n",
       "22769       1.246087           -0.428136  \n",
       "22945      -4.206272           -0.362499  \n",
       "23039       2.342037           -0.901657  \n",
       "24244      -1.967031           -0.578162  \n",
       "24801       1.871531           -1.117320  \n",
       "\n",
       "[51 rows x 7 columns]"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "humans4[humans4.zscore_Height.abs() > 3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "a247492b-ecca-4d7b-911e-df8d68e78ca0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "25000"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "75.0"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Outlier weight: 67\n",
      "Outlier hair length: 285\n"
     ]
    }
   ],
   "source": [
    "# total observations\n",
    "len(humans4)\n",
    "# 68-95-99.5 rule -> 75 observations beyond 3std\n",
    "len(humans)*0.003\n",
    "# \n",
    "print(\"Outlier weight:\", (humans4.zscore_Weight.abs() > 3).sum())\n",
    "print(\"Outlier hair length:\", (humans4.zscore_Hair_Length.abs() > 3).sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "cfd069b8-0ab7-4572-acad-e86ca17bc2c1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Hair_Length</th>\n",
       "      <th>Favorite</th>\n",
       "      <th>zscore_Height</th>\n",
       "      <th>zscore_Weight</th>\n",
       "      <th>zscore_Hair_Length</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>13971</th>\n",
       "      <td>153.107034</td>\n",
       "      <td>63.155154</td>\n",
       "      <td>4.4</td>\n",
       "      <td>green</td>\n",
       "      <td>-4.055392</td>\n",
       "      <td>-1.454458</td>\n",
       "      <td>-1.018865</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14106</th>\n",
       "      <td>157.244415</td>\n",
       "      <td>45.062151</td>\n",
       "      <td>70.7</td>\n",
       "      <td>red</td>\n",
       "      <td>-3.199138</td>\n",
       "      <td>-4.158856</td>\n",
       "      <td>2.089496</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22945</th>\n",
       "      <td>157.293031</td>\n",
       "      <td>44.744929</td>\n",
       "      <td>18.4</td>\n",
       "      <td>red</td>\n",
       "      <td>-3.189077</td>\n",
       "      <td>-4.206272</td>\n",
       "      <td>-0.362499</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Height     Weight  Hair_Length Favorite  zscore_Height  \\\n",
       "13971  153.107034  63.155154          4.4    green      -4.055392   \n",
       "14106  157.244415  45.062151         70.7      red      -3.199138   \n",
       "22945  157.293031  44.744929         18.4      red      -3.189077   \n",
       "\n",
       "       zscore_Weight  zscore_Hair_Length  \n",
       "13971      -1.454458           -1.018865  \n",
       "14106      -4.158856            2.089496  \n",
       "22945      -4.206272           -0.362499  "
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cond = (\n",
    "    (humans4.zscore_Height.abs() > 4) |\n",
    "    (humans4.zscore_Weight.abs() > 4) |\n",
    "    (humans4.zscore_Hair_Length.abs() > 4.5))\n",
    "humans4[cond]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "58f4d658-5205-4595-9ea2-bdd23eab1279",
   "metadata": {},
   "source": [
    "#### Inter-quartile Range"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "1d4b9cac-fb7b-402f-a687-0d1df322fefa",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Function defined but not run in this cell\n",
    "def show_boxplots(df, cols, whis=1.5):\n",
    "    # Create as many horizontal plots as we have columns\n",
    "    fig, axes = plt.subplots(len(cols), 1, figsize=(10, 2*len(cols)))\n",
    "    # For each one, plot the non-null data inside it\n",
    "    for n, col in enumerate(cols):\n",
    "        data = df[col][df[col].notnull()]\n",
    "        axes[n].set_title(f'{col} Distribution')\n",
    "        # Extend whiskers to specified IQR multiplier\n",
    "        axes[n].boxplot(data, whis=whis, vert=False, sym='x',meanline=True)\n",
    "        axes[n].set_yticks([])\n",
    "    # Fix spacing of subplots at the end\n",
    "    fig.tight_layout()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "be1da3fc-ab92-4405-9618-c49a2ff49401",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x432 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "show_boxplots(humans4, [\"Height\", \"Weight\", \"Hair_Length\"], 1.5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "7c744e08-b7e6-47e4-93b4-6b391b5ac424",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0.25</th>\n",
       "      <td>169.428884</td>\n",
       "      <td>68.428823</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0.50</th>\n",
       "      <td>172.709078</td>\n",
       "      <td>72.930616</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0.75</th>\n",
       "      <td>175.953541</td>\n",
       "      <td>77.367039</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1.00</th>\n",
       "      <td>190.888112</td>\n",
       "      <td>98.032504</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Height     Weight\n",
       "0.25  169.428884  68.428823\n",
       "0.50  172.709078  72.930616\n",
       "0.75  175.953541  77.367039\n",
       "1.00  190.888112  98.032504"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "quartiles = (\n",
    "    humans4[['Height', 'Weight']]\n",
    "    .quantile(q=[0.25, 0.50, 0.75, 1.0]))\n",
    "quartiles"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "405e7234-23ec-4de4-8ef1-dc26acbfc41e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Height    6.524657\n",
       "Weight    8.938216\n",
       "dtype: float64"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "IQR = quartiles.loc[0.75] - quartiles.loc[0.25]\n",
    "IQR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "10425651-3f8e-4792-a871-e93ba807f9e8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Inliers for Height: [153.117, 192.265]\n",
      "Inliers for Weight: [46.083, 99.713]\n"
     ]
    }
   ],
   "source": [
    "for col, length in IQR.iteritems():\n",
    "    high = quartiles.loc[0.75, col] + 2.5*IQR[col]\n",
    "    low = quartiles.loc[0.25, col] - 2.5*IQR[col]\n",
    "    print(f\"Inliers for {col}: [{low:.3f}, {high:.3f}]\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "c3faa603-3df2-4410-8de7-005ab92a8332",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Hair_Length</th>\n",
       "      <th>Favorite</th>\n",
       "      <th>zscore_Height</th>\n",
       "      <th>zscore_Weight</th>\n",
       "      <th>zscore_Hair_Length</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>13971</th>\n",
       "      <td>153.107034</td>\n",
       "      <td>63.155154</td>\n",
       "      <td>4.4</td>\n",
       "      <td>green</td>\n",
       "      <td>-4.055392</td>\n",
       "      <td>-1.454458</td>\n",
       "      <td>-1.018865</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14106</th>\n",
       "      <td>157.244415</td>\n",
       "      <td>45.062151</td>\n",
       "      <td>70.7</td>\n",
       "      <td>red</td>\n",
       "      <td>-3.199138</td>\n",
       "      <td>-4.158856</td>\n",
       "      <td>2.089496</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22945</th>\n",
       "      <td>157.293031</td>\n",
       "      <td>44.744929</td>\n",
       "      <td>18.4</td>\n",
       "      <td>red</td>\n",
       "      <td>-3.189077</td>\n",
       "      <td>-4.206272</td>\n",
       "      <td>-0.362499</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Height     Weight  Hair_Length Favorite  zscore_Height  \\\n",
       "13971  153.107034  63.155154          4.4    green      -4.055392   \n",
       "14106  157.244415  45.062151         70.7      red      -3.199138   \n",
       "22945  157.293031  44.744929         18.4      red      -3.189077   \n",
       "\n",
       "       zscore_Weight  zscore_Hair_Length  \n",
       "13971      -1.454458           -1.018865  \n",
       "14106      -4.158856            2.089496  \n",
       "22945      -4.206272           -0.362499  "
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cond = (\n",
    "    (humans4.Height > 192.265) |\n",
    "    (humans4.Height < 153.117) |\n",
    "    (humans4.Weight > 99.713)  |\n",
    "    (humans4.Weight < 46.083))\n",
    "humans4[cond]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "673f2b39-0c86-4126-852c-53288b6c6229",
   "metadata": {},
   "source": [
    "#### Absolute Deviation around Median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "a7363c31-b87d-42e4-9fbb-b0454cecbf36",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4.46943080294767"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "median_abs_deviation(humans4.Weight)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "a91ef5c0-4ad9-4e3d-8332-ac38020e7014",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Height 162.92343589999987 182.49472010000008\n",
      "Weight 59.5223235797511 86.33890839743712\n"
     ]
    }
   ],
   "source": [
    "for var in ('Height', 'Weight'):\n",
    "    mad = median_abs_deviation(humans4[var])\n",
    "    lower, upper = humans4[var].median() - 3*mad, humans4[var].median() + 3*mad, \n",
    "    print(var, lower, upper)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "18c58acb-510d-4b85-91de-cbaee6a04516",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Height</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Hair_Length</th>\n",
       "      <th>Favorite</th>\n",
       "      <th>zscore_Height</th>\n",
       "      <th>zscore_Weight</th>\n",
       "      <th>zscore_Hair_Length</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>176.272800</td>\n",
       "      <td>87.767722</td>\n",
       "      <td>77.1</td>\n",
       "      <td>green</td>\n",
       "      <td>0.738890</td>\n",
       "      <td>2.224434</td>\n",
       "      <td>2.389549</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>161.242121</td>\n",
       "      <td>56.151093</td>\n",
       "      <td>19.3</td>\n",
       "      <td>red</td>\n",
       "      <td>-2.371791</td>\n",
       "      <td>-2.501369</td>\n",
       "      <td>-0.320304</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>176.589182</td>\n",
       "      <td>59.248055</td>\n",
       "      <td>52.6</td>\n",
       "      <td>red</td>\n",
       "      <td>0.804367</td>\n",
       "      <td>-2.038460</td>\n",
       "      <td>1.240909</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>162.675189</td>\n",
       "      <td>61.203784</td>\n",
       "      <td>38.7</td>\n",
       "      <td>red</td>\n",
       "      <td>-2.075210</td>\n",
       "      <td>-1.746133</td>\n",
       "      <td>0.589231</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>56</th>\n",
       "      <td>178.831672</td>\n",
       "      <td>89.414827</td>\n",
       "      <td>9.6</td>\n",
       "      <td>blue</td>\n",
       "      <td>1.268463</td>\n",
       "      <td>2.470630</td>\n",
       "      <td>-0.775072</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24969</th>\n",
       "      <td>161.589491</td>\n",
       "      <td>66.386446</td>\n",
       "      <td>15.3</td>\n",
       "      <td>red</td>\n",
       "      <td>-2.299901</td>\n",
       "      <td>-0.971470</td>\n",
       "      <td>-0.507837</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24980</th>\n",
       "      <td>177.290019</td>\n",
       "      <td>88.578140</td>\n",
       "      <td>57.1</td>\n",
       "      <td>blue</td>\n",
       "      <td>0.949409</td>\n",
       "      <td>2.345569</td>\n",
       "      <td>1.451884</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24983</th>\n",
       "      <td>162.000362</td>\n",
       "      <td>63.945097</td>\n",
       "      <td>26.1</td>\n",
       "      <td>green</td>\n",
       "      <td>-2.214869</td>\n",
       "      <td>-1.336383</td>\n",
       "      <td>-0.001498</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24988</th>\n",
       "      <td>167.897480</td>\n",
       "      <td>59.293594</td>\n",
       "      <td>1.8</td>\n",
       "      <td>red</td>\n",
       "      <td>-0.994428</td>\n",
       "      <td>-2.031653</td>\n",
       "      <td>-1.140762</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24991</th>\n",
       "      <td>182.668062</td>\n",
       "      <td>73.576570</td>\n",
       "      <td>31.2</td>\n",
       "      <td>green</td>\n",
       "      <td>2.062425</td>\n",
       "      <td>0.103253</td>\n",
       "      <td>0.237607</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2032 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           Height     Weight  Hair_Length Favorite  zscore_Height  \\\n",
       "2      176.272800  87.767722         77.1    green       0.738890   \n",
       "22     161.242121  56.151093         19.3      red      -2.371791   \n",
       "30     176.589182  59.248055         52.6      red       0.804367   \n",
       "39     162.675189  61.203784         38.7      red      -2.075210   \n",
       "56     178.831672  89.414827          9.6     blue       1.268463   \n",
       "...           ...        ...          ...      ...            ...   \n",
       "24969  161.589491  66.386446         15.3      red      -2.299901   \n",
       "24980  177.290019  88.578140         57.1     blue       0.949409   \n",
       "24983  162.000362  63.945097         26.1    green      -2.214869   \n",
       "24988  167.897480  59.293594          1.8      red      -0.994428   \n",
       "24991  182.668062  73.576570         31.2    green       2.062425   \n",
       "\n",
       "       zscore_Weight  zscore_Hair_Length  \n",
       "2           2.224434            2.389549  \n",
       "22         -2.501369           -0.320304  \n",
       "30         -2.038460            1.240909  \n",
       "39         -1.746133            0.589231  \n",
       "56          2.470630           -0.775072  \n",
       "...              ...                 ...  \n",
       "24969      -0.971470           -0.507837  \n",
       "24980       2.345569            1.451884  \n",
       "24983      -1.336383           -0.001498  \n",
       "24988      -2.031653           -1.140762  \n",
       "24991       0.103253            0.237607  \n",
       "\n",
       "[2032 rows x 7 columns]"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cond = (\n",
    "    (humans4.Height > 182.495) |\n",
    "    (humans4.Height < 162.923) |\n",
    "    (humans4.Weight > 86.339)  |\n",
    "    (humans4.Weight < 59.52))\n",
    "humans4[cond]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eaa459f7-51e3-4fb4-9671-6d10cb3effef",
   "metadata": {},
   "source": [
    "## Data Quality"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3cd4df48-5181-4387-a969-012d6b327518",
   "metadata": {},
   "source": [
    "### Missing Data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "252f9c49-ce08-4028-8600-ec3d6ecc0df5",
   "metadata": {},
   "source": [
    "Persons with names, ages, genders and favorite flowers and colors, example adopted from CleanData."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "7b5d12ec-818b-418e-941b-2a9784ef44b5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Name</th>\n",
       "      <th>Favorite_Color</th>\n",
       "      <th>Favorite_Flower</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>48</td>\n",
       "      <td>F</td>\n",
       "      <td>Lisa</td>\n",
       "      <td>Yellow</td>\n",
       "      <td>Daisy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>62</td>\n",
       "      <td>F</td>\n",
       "      <td>Karen</td>\n",
       "      <td>Green</td>\n",
       "      <td>Rose</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>26</td>\n",
       "      <td>M</td>\n",
       "      <td>Michael</td>\n",
       "      <td>Purple</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>73</td>\n",
       "      <td>F</td>\n",
       "      <td>Patricia</td>\n",
       "      <td>Red</td>\n",
       "      <td>Orchid</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>13</td>\n",
       "      <td>F</td>\n",
       "      <td>Ava</td>\n",
       "      <td>Green</td>\n",
       "      <td>Violet</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6337</th>\n",
       "      <td>36</td>\n",
       "      <td>M</td>\n",
       "      <td>Michael</td>\n",
       "      <td>None</td>\n",
       "      <td>Violet</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6338</th>\n",
       "      <td>11</td>\n",
       "      <td>M</td>\n",
       "      <td>Jacob</td>\n",
       "      <td>Red</td>\n",
       "      <td>Lily</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6339</th>\n",
       "      <td>20</td>\n",
       "      <td>M</td>\n",
       "      <td>Jacob</td>\n",
       "      <td>Green</td>\n",
       "      <td>Rose</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6340</th>\n",
       "      <td>72</td>\n",
       "      <td>M</td>\n",
       "      <td>Robert</td>\n",
       "      <td>Blue</td>\n",
       "      <td>Lily</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6341</th>\n",
       "      <td>64</td>\n",
       "      <td>F</td>\n",
       "      <td>Debra</td>\n",
       "      <td>Purple</td>\n",
       "      <td>Rose</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6342 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Age Gender      Name Favorite_Color Favorite_Flower\n",
       "0      48      F      Lisa         Yellow           Daisy\n",
       "1      62      F     Karen          Green            Rose\n",
       "2      26      M   Michael         Purple            None\n",
       "3      73      F  Patricia            Red          Orchid\n",
       "4      13      F       Ava          Green          Violet\n",
       "...   ...    ...       ...            ...             ...\n",
       "6337   36      M   Michael           None          Violet\n",
       "6338   11      M     Jacob            Red            Lily\n",
       "6339   20      M     Jacob          Green            Rose\n",
       "6340   72      M    Robert           Blue            Lily\n",
       "6341   64      F     Debra         Purple            Rose\n",
       "\n",
       "[6342 rows x 5 columns]"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "6342"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# read parquet file (Apache Hadoop ecosystem, column-wise storage format with compression features)\n",
    "df = pd.read_parquet(os.path.join(data_dir, 'usa_names.parq') )\n",
    "df\n",
    "len(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "c0d58bbd-556b-4e81-9e7b-853cda50d789",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Name</th>\n",
       "      <th>Favorite_Color</th>\n",
       "      <th>Favorite_Flower</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>6342.000000</td>\n",
       "      <td>6342</td>\n",
       "      <td>6342</td>\n",
       "      <td>5599</td>\n",
       "      <td>5574</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>NaN</td>\n",
       "      <td>2</td>\n",
       "      <td>69</td>\n",
       "      <td>6</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>NaN</td>\n",
       "      <td>F</td>\n",
       "      <td>Michael</td>\n",
       "      <td>Yellow</td>\n",
       "      <td>Orchid</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>NaN</td>\n",
       "      <td>3190</td>\n",
       "      <td>535</td>\n",
       "      <td>965</td>\n",
       "      <td>1356</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>42.458846</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>27.312662</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>19.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>39.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>63.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>101.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                Age Gender     Name Favorite_Color Favorite_Flower\n",
       "count   6342.000000   6342     6342           5599            5574\n",
       "unique          NaN      2       69              6               5\n",
       "top             NaN      F  Michael         Yellow          Orchid\n",
       "freq            NaN   3190      535            965            1356\n",
       "mean      42.458846    NaN      NaN            NaN             NaN\n",
       "std       27.312662    NaN      NaN            NaN             NaN\n",
       "min        2.000000    NaN      NaN            NaN             NaN\n",
       "25%       19.000000    NaN      NaN            NaN             NaN\n",
       "50%       39.000000    NaN      NaN            NaN             NaN\n",
       "75%       63.000000    NaN      NaN            NaN             NaN\n",
       "max      101.000000    NaN      NaN            NaN             NaN"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe(include='all')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "708dbcd3-d704-4ea7-9db8-735aa15b4de8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "768"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "743"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# roughly 10% are NaN -> could be discarded or imputed\n",
    "df['Favorite_Flower'].isna().sum()\n",
    "df['Favorite_Color'].isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "144c901e-9909-4f2b-9ba6-9b76287fbcfa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>768.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>25.350260</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.905908</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>21.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>23.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>25.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>28.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>30.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              Age\n",
       "count  768.000000\n",
       "mean    25.350260\n",
       "std      2.905908\n",
       "min     21.000000\n",
       "25%     23.000000\n",
       "50%     25.000000\n",
       "75%     28.000000\n",
       "max     30.000000"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "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>Age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>743.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>35.401077</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.869695</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>31.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>33.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>35.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>38.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>40.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              Age\n",
       "count  743.000000\n",
       "mean    35.401077\n",
       "std      2.869695\n",
       "min     31.000000\n",
       "25%     33.000000\n",
       "50%     35.000000\n",
       "75%     38.000000\n",
       "max     40.000000"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "missing_flower_preference = df.loc[df['Favorite_Flower'].isna()]\n",
    "missing_color_preference = df.loc[df['Favorite_Color'].isna()]\n",
    "missing_flower_preference.describe()\n",
    "missing_color_preference.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "1f268cfe-b74f-4826-8bae-30315ae5497e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Age Group', ylabel='count'>"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Distribution of Flower Preference by Age')"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Number of Persons')"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Age Group', ylabel='count'>"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Distribution of Color Preference by Age')"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Number of Persons')"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x360 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# check distribution of missing data\n",
    "df['Age Group'] = df.Age//10 * 10\n",
    "fig, axes = plt.subplots(1,2, figsize=(20,5))\n",
    "sns.countplot(x=\"Age Group\", hue=\"Favorite_Flower\", ax=axes[0], palette='tab10', data=df)\n",
    "axes[0].set_title('Distribution of Flower Preference by Age')\n",
    "axes[0].set_ylabel('Number of Persons')\n",
    "\n",
    "sns.countplot(x=\"Age Group\", hue=\"Favorite_Color\", ax=axes[1], palette='tab10', data=df)\n",
    "axes[1].set_title('Distribution of Color Preference by Age')\n",
    "axes[1].set_ylabel('Number of Persons')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "id": "b57b6ceb-9491-4dd7-965c-5c944709ff32",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_18709/3021732049.py:1: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  missing_flower_preference['Age Group'] = df.Age//10 * 10\n",
      "/tmp/ipykernel_18709/3021732049.py:2: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  missing_color_preference['Age Group'] = df.Age//10 * 10\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Age Group', ylabel='count'>"
      ]
     },
     "execution_count": 135,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Distribution of MISSING Flower Preference by Age ')"
      ]
     },
     "execution_count": 135,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Number of Persons')"
      ]
     },
     "execution_count": 135,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Age Group', ylabel='count'>"
      ]
     },
     "execution_count": 135,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Distribution of MISSING Color Preference by Age')"
      ]
     },
     "execution_count": 135,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Number of Persons')"
      ]
     },
     "execution_count": 135,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABJIAAAFNCAYAAABbvUVCAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAABIqklEQVR4nO3deViU9f7/8dcAoqggoixqVGZmRS6kiGhpgjuimJplaVK5lEYuUbZqmujxWFJZKdXxqC3H9AjkkiK4YLnlXp3KzNxQBkMRFRUY5veHP+cryTIoAyM8H9fVdTH33PO533M798y792e5DWaz2SwAAAAAAACgBA4VHQAAAAAAAABuDhSSAAAAAAAAYBUKSQAAAAAAALAKhSQAAAAAAABYhUISAAAAAAAArEIhCQAAAAAAAFahkIQK9eabb+rDDz8sk7aOHz8uf39/mUwmSdKQIUO0ZMmSMmlbkp555hnFxcWVWXvWmj17tgIDA9WhQ4dyP7Y92rZtmzp27FjRYdiM2WzWK6+8ooCAAA0YMKCiw7kuy5Yt02OPPVbRYQAArgO5WcnIzUrPnnODgwcPqm/fvvL399fChQsrOpzrUtbXFlASCkmwmeDgYLVo0UL+/v5q06aNHn30UX311VfKz8+37DNlyhSNHj3aqrY2b95c7D4NGzbU7t275ejoeMOxf/DBB3rxxRcLbPv000/Vr1+/G267NI4fP6758+dr1apV+v777695ftu2bWrWrNk15/DXX39Vs2bNNGTIEMu2Zs2a6fDhw5KkrKwsvfLKK+rQoYP8/f3VvXt3xcbGWvZNSkpS3759df/99yswMFBDhw7V0aNHJV17bpo1a6awsLAC/66zZ8/WxIkTLY9zcnI0Z84cde/eXa1atdKDDz6oZ555Rt99912R771Zs2Zq1aqV/P39LZ8he/XBBx/Iz8+vwGd99+7d19XWzp079f3332vjxo1aunRpGUd685o4caLuvfdepaenV3QoAHDTIje7cVU5NzObzVq4cKF69+6tVq1aqWPHjoqMjNRvv/1m7ekrM1d/ltu3b6+JEyfq/Pnz19XWp59+qsDAQO3evVtDhw4t40hvTufPn5e/v7+eeeaZig4FdsqpogNA5TZ37ly1b99eZ8+e1fbt2zVt2jTt27dP06dPL9Pj5OXlycmp8n2cjx8/Lnd3d9WrV6/IfTw8PLRnzx6dPn1adevWlSTFxcXp9ttvL/I106dPV3Z2tlatWiVXV1f9+eef+v333yVJhw8f1ssvv6w5c+aoXbt2On/+vL7//vtik8D09HStXLlSYWFhhT4fGRmp9PR0zZw5U/fcc48kaevWrdqwYYMeeOCBIttNSEjQbbfdVuTzFaGoz1rPnj01a9Ys5ebmavbs2Xr++ee1adMmGQyGAvuZTKZiz2VqaqoaNWqkmjVrlllsN7vs7GytWbNGrq6u+uabb0hqAOAGkJvdmKqcm02bNk0bNmzQ1KlT1bp1a5lMJq1du1YbN25Us2bNiozlRpjNZpnNZjk4XDv+4cpn2Wg06umnn9bHH398TbHRms/h8ePHFRoael3xVdbPeWJiopydnbV582adPHlSnp6eFR0S7AwjklAuXF1dFRISopiYGMXFxWn//v2SLo8ymD17tiTp1KlTGjlypNq0aaO2bdtq8ODBys/PV1RUlI4fP65Ro0bJ399fn3zyiY4dO6ZmzZppyZIleuihh/Tkk09atuXl5VmOe+TIEQ0YMED333+/nn32WWVmZkoqfHrUlZ61lJQUzZs3T99++638/f3Vp08fSQWHjObn5+ujjz5S586dFRQUpJdeeklnz56VJEsccXFxeuihhxQYGKiPP/64yHNz9uxZvfTSS2rXrp06d+6sjz76SPn5+dq8ebOeeuoppaeny9/fv0Av0tWqVaumkJAQrVq1StLlQsWqVauKTBwk6ccff1RYWJjq1KkjBwcHNWnSRD169JAk/fLLL7rlllsUFBQkg8Gg2rVrq3v37mrYsGGR7T399NP64IMPCpz7KzZv3qzNmzfro48+UsuWLeXs7CxnZ2d17NhRr7/+epFtWuuPP/7QkCFD1KZNG4WGhio5OVmSdPToUbVp08bSG/f6668rKCjI8rqoqCj9+9//lnT53+DVV1/VAw88oAcffFCzZ8+2DMNftmyZHn30UUVHRyswMFAffPBBsfFUq1ZN/fr108mTJ3X69GlNnDhRkyZN0vDhw9WqVStt27ZNRqNRzz//vNq1a6fg4GDLMOolS5bo9ddf1549e+Tv76/3339fkrR+/Xr17dvX0nv866+/Wo4XHBys2NhYhYWFqVWrVsrLy9OePXv06KOPqk2bNurTp4+2bdtm2X/IkCGKiYnRo48+Kn9/fz311FM6deqU5fkdO3ZYXtupUyctW7ZM0uWey3/84x966KGH1L59e7355pu6ePFikefBbDZrypQpat26tXr06KEtW7ZIkr799ls9/PDDBfadP3++nn322SLbSkxMlJubm5577jnFx8cXeO7ixYt6+eWXFRAQoJ49e+qTTz4pcG0Xda4BoKojNyM3K01udujQIX3xxRd69913FRQUJGdnZ7m4uKhPnz4aMWJEseetMLt27VL//v3VunVr9e/fX7t27bI8N2TIEM2ePVuPPvqoWrZsaRl5VRRvb289+OCDlsJbs2bN9MUXX6hbt27q1q2bpKJzqaFDh2rbtm2aMmWK/P399eeffxab81z5nMbGxqpDhw565ZVXlJ+fr9jYWHXp0kWBgYF64YUXLJ/rkj57JpNJc+fOVZcuXeTv76+HH35YJ06ckHQ5x42IiFDbtm3VvXt3y+epKEVdWyNGjNCiRYsK7BsWFqa1a9cW2VZcXJweffRRNWvWTN98802B537++WeFh4fL399fkZGRGjt2rOU7o7hzjcqFQhLKVYsWLeTj46MdO3Zc89z8+fPl7e2tLVu26Pvvv9f48eNlMBj0z3/+Uw0bNtTcuXO1e/duDR8+3PKaH374QatWrdJnn31W6PHi4+MVHR2t7777Tk5OTnr77bdLjLFjx44aOXKkevbsqd27d1/z5SldLi7ExcVp4cKFSkpKUnZ2tqZMmVJgn507d2r16tVasGCBPvzwQ/3xxx+FHm/q1Kk6e/askpKStGjRIiUkJOi///2v2rdvr08++UReXl7avXu3ZsyYUWTM4eHhlv/B/u6773TXXXfJ29u7yP1btmyp2bNn67///a8OHTpU4Dk/Pz8dPHhQ0dHR2rp1q1XDhLt166batWsXuk7B5s2b1bJlS/n4+JTYTmnl5uZq1KhR6tChgzZv3qzXX39dL774og4ePChfX1/Vrl1b//vf/yRd/qzUrFnT8u/www8/qG3btpIuJ81OTk5KTExUfHy8vv/++wLzzPft2ydfX199//33xRY8pMsFl2XLlqlBgwby8PCQJK1YsUKjRo3Srl275O/vr2effVbNmjVTSkqKFixYoAULFmjTpk0aOHCg3nrrLbVq1Uq7d+9WZGSk/ve//+nVV1/VlClTtG3bNg0aNEjPPfeccnJyLMdcuXKlYmNjtWPHDmVkZGjkyJF69tlntX37dr388suKjIwsUCxasWKFpk+fri1btig3N1f/+te/JF0eDTV8+HA98cQT2rJli+Lj4y29lLNmzdKff/6p+Ph4JSYmKj09vdg1NPbt26dbb71VW7duVWRkpMaMGaPMzEyFhITo2LFjBa6HhIQEhYeHF9lWXFycQkNDFRoaqoMHD+qnn36yPDdnzhylpqYqKSlJ8+fPL3C95ufnF3muAQCXkZtdi9zsWlu2bJGPj49atGhR5D5Fnbe/y8zM1MiRIzVkyBBt27ZNERERGjlypE6fPm3ZJyEhQVOnTtWuXbuKLZhJ0okTJ5SSkmLJWaTLUwG//vprrVq1qthcauHChWrTpo3efPNN7d69W40bNy4x5/nrr7905swZrV+/XlOnTtWiRYuUlJSkzz//XJs2bVKdOnWs/uzNnz/fksft2rVL0dHRqlGjhrKzs/XUU0+pd+/e2rx5s2bPnq233npLBw4cKPI8FHVthYeHF7hmfv31V6Wnp6tTp06FtpOamqrt27crLCxMYWFhBTrxcnJyNGbMGPXr10/bt29X7969lZSUZHnemrwVlQOFJJQ7Ly8vnTlz5prtTk5OOnnypI4fP65q1aqpTZs210wL+rvnn39eNWvWVI0aNQp9vm/fvrrrrrtUs2ZNvfDCC1q9erVlpMmNWL58uYYNGyZfX1/VqlVL48eP16pVqwr0+owZM0Y1atTQ3XffrbvvvrvQavyVHqoJEyaodu3auuWWWxQREVFoglSc+++/X2fOnNHBgwcVHx+vvn37Frv/G2+8obCwMH3xxRcKDQ1V165dtXHjRkmSr6+vFi1aJKPRqLFjx6pdu3Ylzjs3GAx64YUX9NFHH13zQ3H69GnVr1/f8jgzM1Nt2rRR69at1bx582Lj7Nevn9q0aaM2bdoUmmju3btX2dnZGjFihJydnRUUFKTOnTtr5cqVkqSAgAD98MMPOnnypCSpe/fu2r59u44ePapz587p7rvv1l9//aWNGzfq1VdfVc2aNVWvXj0NGzbM0oZ0+TM7ZMgQOTk5FflZW716tWUUz88//6w5c+ZYngsJCVHr1q3l4OCg/fv369SpUxozZoycnZ3l6+urRx55pMhepsWLF2vQoEFq2bKlHB0d1a9fP1WrVk179uyx7DNkyBA1aNBANWrUUEJCgjp27KhOnTrJwcFBHTp00H333Wf595Wkhx9+WI0bN1aNGjXUo0cP/fLLL5IuF5jat2+v3r17q1q1aqpbt67uuecemc1mff3113r11Vfl7u6u2rVra+TIkQXO0d95eHjoySefVLVq1dSrVy81btxYGzZskLOzs3r27Gn5jP/+++9KTU1V586dC23n+PHj2rZtm8LCwlS/fn0FBQUVSGi+/fZbjRw5UnXq1JGPj0+BtQ1+/PHHUp1rAKiqyM3+D7lZ4blZZmZmsdObSnPeNmzYoNtuu03h4eFycnJS7969dccdd2j9+vWWffr166emTZvKyclJ1apVK/SYo0ePVps2bTR48GAFBARo1KhRludGjBghd3d31ahRw6pc6gprch4HBwdFRkbK2dlZNWrU0H/+8x+NGzdOPj4+cnZ21pgxY7RmzRqrPntLlizRCy+8oDvuuEMGg0F333236tatqw0bNqhRo0bq37+/nJycdO+996p79+5avXp1kf8GRV1bISEhOnTokKVAmZCQoJ49e8rZ2bnQdhISEtSsWTPdeeedCg0N1YEDBywds3v37lVeXp6GDh2qatWqqVu3bgU+M6U517i5Vb4JnbB7RqNRderUuWb7008/rTlz5uipp56SJA0aNMgyVLYoJfWkNGjQwPJ3w4YNlZubW6C343qlp6erUaNGlseNGjVSXl6eMjIyLNuu/oF2cXFRdnb2Ne2cPn1aubm5BXpaGjZsKKPRWOqY+vTpoy+++ELbtm1TdHS0VqxYUeS+NWrU0KhRozRq1CidO3dOsbGxGjt2rNavXy93d3e1atVK7733nqTLI0vGjRunuXPnasKECUW22alTJ3l7e2vx4sUFtru7u1sWkrzyeMeOHTp8+LBluHFR4uLiil0jKT09XT4+PgXmzV99/tq2bavk5GR5e3srICBAgYGBSkhIUPXq1dWmTRs5ODjo+PHjysvLK7AeQH5+foHPjjU9dj169NCsWbMKfe7qtlJTU5Wenl5g8XCTyVTkYuLHjx9XfHy8Pv/8c8u23NzcAotOX93+8ePHtXr16gLJWF5engIDAy2Pr04Er/5snjhxQrfeeus1MZw6dUoXLlwoMCXNbDYXOVxdujzM/Or/2WjYsKEl5n79+mn8+PEaO3asVclMkyZNLL2MYWFhmjFjhl5++WVVq1ZN6enpRf5blfZcA0BVRW72f8jNCs/N3N3dLR1zhSnNeUtPT79mlNHf9736c1KUDz/8UO3bty/0ub/nRiXlUldYk/PUrVtX1atXL9D+6NGjC+SjDg4OVn320tLSCs29UlNTtW/fvmtymCvTOkt6z1dfW/Xr17d04o0ZM0YrVqywLJ9QmISEBA0cOFCSLDl0XFyc5aYnf8/xrvdc4+ZGIQnlat++fTIajWrduvU1z9WuXVsTJ07UxIkTtX//fj355JNq3rx5gXVt/q6kXrErc4yv/H1llIWLi0uB9V1MJlOBqT8ltevl5aXU1FTL4+PHj8vJyUn16tVTWlpasa+9Wt26dVWtWjUdP35cd955pyXO4oY+F6Vv377q1q2bwsPD5eLiYvXrrvS0zJs3T8eOHZO7u3uB51u0aKFu3bpZ5p0XZ9y4cZowYUKBBQuDgoL0+eefKy0trcynt3l5eSktLU35+fmWH+8TJ05YFrMMCAjQzJkz5ePjo4CAALVu3VqTJk1S9erVFRAQIEmW3qOtW7cWuVhiSZ+H0mjQoIFuueUWJSYmWr3/qFGjip1S9/cf8759+1o1VaCwY+3bt++a7XXr1lWNGjW0cuVKqz+bRqNRZrPZEtuJEycUHBwsSWrVqpWqVaumHTt2aMWKFUUW4KTLw7RPnDhhucVyXl6eMjMztXHjRnXp0kWenp5KS0uzXD9XX3+lPdcAUBWRmxVEbla4oKAgTZkyRT/++GOho5ZKc968vLx0/PjxAttOnDihBx980PL4RnOvv+dGJeVSV1iT8/w9Nh8fH0VHRxd6DR07dqzY4/n4+OjIkSO66667Cmxv0KCBAgICNH/+/BJjvqKoa0u63In30ksvqXXr1nJxcZG/v3+hbezatUuHDh1SbGys5djnz5/X77//rpdfflmenp6F5ni+vr6WuK0917i5MbUN5eLcuXNav369xo8frz59+hR6Z4f169fr8OHDMpvNcnV1laOjo+ULqn79+iUutFeYb775RgcOHNCFCxf03nvvqXv37nJ0dFTjxo116dIlbdiwQbm5ufr4448LDPutV6+eUlNTixxx0bt3by1YsEBHjx7V+fPnNXv2bPXs2bPUd21wdHRUjx49NHv2bJ07d06pqamaP39+sb0NRbky7Hns2LEl7vvhhx9q3759ysnJ0aVLl7Rw4UK5ubmpcePG2rFjh77++mtLL8off/yhdevWqWXLliW2GxgYqKZNmxaYevTAAw8oMDBQzz33nPbu3aucnBzl5uaWyRDXFi1aqEaNGvr000+Vm5urbdu2ad26derVq5ck6fbbb1f16tX1zTffqG3btqpdu7bq1aunNWvWWApJXl5e6tChg2bMmKFz584pPz9fR44c0fbt2284vqJirlWrlmJjY3Xx4kWZTCbt37+/0AKOJA0cOFD/+c9/tHfvXpnNZmVnZ2vDhg06d+5cofv36dNH69ev16ZNm2QymXTp0iVt27bNqiQ6LCxMmzdvtkwFOH36tH755Rc5ODho4MCBio6OtnwujEZjsWsNnTp1SgsXLlRubq6+/fZb/fHHHwXm4oeHh2vKlClycnIqcoTQ7t27dfToUS1ZskTx8fGKj4/XihUr1Lt3byUkJEi6fLe8efPm6cyZMzIajQV6wEp7rgGgKiE3Kxy5WeFuv/12DR48WBMmTNC2bdsscV5Z36c0561Tp046dOiQli9frry8PK1atUoHDhzQQw89VOL7uR6lyaWuJ+d57LHHFBMTYylknjp1qsC6QSXF9t577+nQoUMym8369ddfdfr0aT300EM6dOiQ4uPjlZubq9zcXO3bt6/Idb2koq8tSfL395eDg4NmzJhR7Gc5Pj5eHTp00MqVKy251/Lly3Xx4kWlpKSoVatWcnR01Oeff668vDwlJSXpxx9/LPB+SpO34uZFIQk2deVuHp06ddLcuXMVERFR5O1lDx8+rIiICPn7+2vQoEF67LHH1K5dO0mX5zl//PHHatOmTZGLNxamb9++mjhxojp06KCcnBy99tprki7fqWTSpEl6/fXX1bFjR7m4uBTokblyl4zAwED169fvmnb79++vPn366IknnlBISIicnZ31xhtvWB3X1d544w25uLioS5cuGjx4sHr37q3+/ftfV1tt2rSxqsfMYDDo1VdfVbt27fTggw9q8+bNmjdvnmrVqiU3NzetW7dOYWFh8vf31/Dhw9WlSxerb7k+duxYy10irpgzZ446d+6sqKgoBQQEKCQkRMuXLy/Vv2VhnJ2dNXfuXKWkpKhdu3Z66623NHPmTDVp0sSyT9u2beXu7m4Zdtu2bVuZzWb5+flZ9pk5c6Zyc3PVq1cvBQQEKDIystjh2zfC0dFRc+fO1a+//qqQkBC1a9dOr7/+epE/sM2bN9fUqVM1ZcoUBQQEqFu3bpY7qRWmQYMG+uijjzRv3jwFBQWpU6dO+uyzz4qdhnZFw4YN9cknn2j+/Plq27atwsPDLXP4o6KidNttt+mRRx7R/fffr2HDhunPP/8ssq0WLVro8OHDateunWJiYvT+++9besWky9fm77//XmwyExcXp5CQEDVr1kyenp6W/5588kmtX79emZmZGj16tHx8fBQSEqJhw4ape/fulmlypT3XAFAVkJuVjNyscK+//roef/xxS07SpUsXrV271rLOobXnrW7dupo7d67mz5+vwMBAffrpp5o7d67lJiVlrbS5VGlznqFDhyo4OFhPPfWU/P399cgjj1jdaRUREaGePXvqqaee0v3336/XXntNly5dUu3atfXZZ59p1apVevDBB/XAAw9o1qxZxS5aXdS1dfXz+/fvL3K9rkuXLunbb7/VE088USDv8vX1Vd++fRUfHy9nZ2d98MEHWrp0qQICAvTNN9/ooYcesuRepT3XuHkZzGazuaKDAABULRcvXlRQUJDi4uIsUxHLwpdffqlVq1YVGJkEAABQ1cXHx2vx4sX66quvyrTdgQMH6tFHH73uYituToxIAgCUu6+++krNmze/4SJSenq6du7cqfz8fB08eFDz589Xly5dyiZIAACASuDChQv68ssvNWjQoBtua/v27Tp58qTy8vIUFxen3377rcD6VqgaWGwbAFCugoODZTab9eGHH95wW7m5uZo0aZKOHTsmV1dXhYaGavDgwWUQJQAAwM1v06ZNev755xUUFKTevXvfcHt//vmnxo4dqwsXLuiWW27R+++/Ly8vrzKIFDcTprYBAAAAAADAKoxIAgAAqEQOHjyocePGWR4fPXpUkZGRCg8P17hx45SamqpGjRopJiZGderUkdls1rRp07Rx40bVqFFDM2bMKHBDAgAAgKsxIgkAAKCSMplM6tixo77++mt98cUXcnd314gRIxQbG6szZ84oKipKGzdu1KJFi/TJJ59o7969mjZtmpYsWVLRoQMAADt1U49Iys/Pl8lEHQwAgMqqWjXHig7hprZlyxb5+vqqUaNGSk5O1qJFiyRJ4eHhGjJkiKKiopScnKzw8HAZDAa1atVKWVlZSk9PL3bNC3IwAAAqt+JysJu6kGQymZWZmV3RYQAAABvx9HSt6BBuaitXrrQsrpqRkWEpDnl6eiojI0OSZDQa5ePjY3mNj4+PjEZjsYUkcjAAACq34nKwm7qQBAAAgMLl5ORo3bp1mjBhwjXPGQwGGQyG627b0dEgd/eaNxIeAAC4SVFIAgAAqIRSUlLk5+en+vXrS5Lq1atnmbKWnp4uDw8PSZK3t7fS0tIsr0tLS5O3t3exbTMiCQCAyq24EUkO5RgHAAAAysnKlSsVGhpqeRwcHKz4+HhJUnx8vEJCQgpsN5vN2rNnj1xdXYud1gYAAKq2m/qubbm5JnrDAACoxFgj6fpkZ2erc+fOSkpKkqvr5XN4+vRpjR07VidOnFDDhg0VExMjd3d3mc1mTZkyRZs2bZKLi4uio6PVvHnzYtsnBwMAoHIrLgejkAQAAOwWhST7RA4GAEDlViGLbR88eFDjxo2zPD569KgiIyMVHh6ucePGKTU1VY0aNVJMTIzq1Kkjs9msadOmaePGjapRo4ZmzJghPz8/W4UHAAAAAACAUrLZGkl33HGHEhISlJCQoGXLlsnFxUVdu3ZVbGysgoKClJiYqKCgIMXGxkq6vCDkoUOHlJiYqKlTp2ry5Mm2Cg0AAAAAAADXoVwW296yZYt8fX3VqFEjJScnKzw8XJIUHh6upKQkSbJsNxgMatWqlbKyspSenl4e4QEAAAAAAMAK5VJIWrlypXr37i1JysjIsNwJxNPTUxkZGZIko9EoHx8fy2t8fHxkNBrLIzwAAAAAAABYwWZrJF2Rk5OjdevWacKECdc8ZzAYZDAYrrttR0eD3N1r3kh4AAAAAAAAsJLNC0kpKSny8/NT/fr1JUn16tVTenq6vLy8lJ6eLg8PD0mSt7e30tLSLK9LS0uTt7d3sW2bTGbuGAIAQCXGXdsAAADsi80LSStXrlRoaKjlcXBwsOLj4zVixAjFx8crJCTEsv3zzz9XaGio9u7dK1dXV8sUuIpU262GXKpXq+gwALt34VKuzmVdrOgwAACVBDkYYB1yMADlzWA2m822ajw7O1udO3dWUlKSXF0v9yiePn1aY8eO1YkTJ9SwYUPFxMTI3d1dZrNZU6ZM0aZNm+Ti4qLo6Gg1b9682PZzc002H5Hk6emq1lELbXoMoDLY+c+hOnnybEWHAaCSYUSSfSIHA+wHORgAWyguB7PpiKSaNWtq27ZtBbbVrVtXCxYsuGZfg8GgSZMm2TIcAAAAAAAA3IByuWsbAAAAAAAAbn4UkgAAAAAAAGAVCkkAAAAAAACwCoUkAAAAAAAAWIVCEgAAAAAAAKxCIQkAAAAAAABWoZAEAAAAAAAAq1BIAgAAAAAAgFUoJAEAAAAAAMAqFJIAAAAAAABgFQpJAAAAAAAAsAqFJAAAAAAAAFiFQhIAAAAAAACsQiEJAAAAAAAAVqGQBAAAAAAAAKtQSAIAAAAAAIBVKCQBAAAAAADAKhSSAAAAAAAAYBUKSQAAAAAAALAKhSQAAAAAAABYhUISAAAAAAAArEIhCQAAoJLJyspSZGSkevTooZ49e2r37t3KzMxURESEunXrpoiICJ05c0aSZDab9fbbb6tr164KCwvTzz//XMHRAwAAe0YhCQAAoJKZNm2aHnzwQa1evVoJCQlq0qSJYmNjFRQUpMTERAUFBSk2NlaSlJKSokOHDikxMVFTp07V5MmTKzZ4AABg1ygkAQAAVCJnz57VDz/8oAEDBkiSnJ2d5ebmpuTkZIWHh0uSwsPDlZSUJEmW7QaDQa1atVJWVpbS09MrKnwAAGDnKCQBAABUIseOHZOHh4deeeUVhYeH67XXXlN2drYyMjLk5eUlSfL09FRGRoYkyWg0ysfHx/J6Hx8fGY3GCokdAADYP6eKDgAAAABlJy8vT//73//0xhtvqGXLlnr77bct09iuMBgMMhgM130MR0eD3N1r3mioAMoI1yOA8kQhCQAAoBLx8fGRj4+PWrZsKUnq0aOHYmNjVa9ePaWnp8vLy0vp6eny8PCQJHl7eystLc3y+rS0NHl7exd7DJPJrMzMbNu9CUmenq42bR+oTGx9PQKoeor7HWZqGwAAQCXi6ekpHx8fHTx4UJK0ZcsWNWnSRMHBwYqPj5ckxcfHKyQkRJIs281ms/bs2SNXV1fLFDgAAIC/s+mIpKysLL3++uvav3+/DAaDoqOj1bhxY40bN06pqalq1KiRYmJiVKdOHZnNZk2bNk0bN25UjRo1NGPGDPn5+dkyPAAAgErpjTfe0Isvvqjc3Fz5+vpq+vTpys/P19ixY7V06VI1bNhQMTExkqROnTpp48aN6tq1q1xcXBQdHV2xwQMAALtm00LSlVvPvv/++8rJydHFixc1d+5cBQUFacSIEYqNjVVsbKyioqIK3Hp27969mjx5spYsWWLL8AAAACqle+65R8uWLbtm+4IFC67ZZjAYNGnSpPIICwAAVAI2m9rGrWcBAAAAAAAqF5sVkrj1LAAAAAAAQOVis6lt3HoWqHq4HgEAAACgcrNZIYlbzwJVD7eeBVDW+B0GAACwLzab2satZwEAAAAAACoXm961jVvPAgAAAAAAVB42LSRx61kAAAAAAIDKw2ZT2wAAAAAAAFC5UEgCAAAAAACAVSgkAQAAAAAAwCoUkgAAAAAAAGAVCkkAAAAAAACwCoUkAAAAAAAAWIVCEgAAAAAAAKxCIQkAAAAAAABWoZAEAAAAAAAAq1BIAgAAAAAAgFUoJAEAAAAAAMAqFJIAAAAAAABgFQpJAAAAAAAAsAqFJAAAAAAAAFiFQhIAAAAAAACsQiEJAAAAAAAAVqGQBAAAAAAAAKtQSAIAAAAAAIBVKCQBAAAAAADAKhSSAAAAAAAAYBUKSQAAAAAAALAKhSQAAAAAAABYxamiAwAAAEDZCg4OVq1ateTg4CBHR0ctW7ZMmZmZGjdunFJTU9WoUSPFxMSoTp06MpvNmjZtmjZu3KgaNWpoxowZ8vPzq+i3AAAA7BQjkgAAACqhBQsWKCEhQcuWLZMkxcbGKigoSImJiQoKClJsbKwkKSUlRYcOHVJiYqKmTp2qyZMnV2DUAADA3lFIAgAAqAKSk5MVHh4uSQoPD1dSUlKB7QaDQa1atVJWVpbS09MrMFIAAGDPKCQBAABUQk8//bQefvhhLV68WJKUkZEhLy8vSZKnp6cyMjIkSUajUT4+PpbX+fj4yGg0ln/AAADgpsAaSQAAAJXMV199JW9vb2VkZCgiIkJ33HFHgecNBoMMBsN1t+/oaJC7e80bDRNAGeF6BFCeKCQBAABUMt7e3pKkevXqqWvXrtq3b5/q1aun9PR0eXl5KT09XR4eHpZ909LSLK9NS0uzvL4oJpNZmZnZtnsDkjw9XW3aPlCZ2Pp6BFD1FPc7zNQ2AACASiQ7O1vnzp2z/P3999+radOmCg4OVnx8vCQpPj5eISEhkmTZbjabtWfPHrm6ulqmwAEAAPydTUckcetZAACA8pWRkaHRo0dLkkwmk3r37q2OHTuqefPmGjt2rJYuXaqGDRsqJiZGktSpUydt3LhRXbt2lYuLi6KjoyswegAAYO9sPrVtwYIFlqHT0v/denbEiBGKjY1VbGysoqKiCtx6du/evZo8ebKWLFli6/AAAAAqFV9fX33zzTfXbK9bt64WLFhwzXaDwaBJkyaVR2gAAKASKPepbdx6FgAAAAAA4OZk8xFJTz/9tAwGgwYNGqRBgwaV+tazxc3R544hgH3hegQAAACAys2mhSRb33qWO4YA9oU7hgAoa/wOAwAA2BebTm0r7tazkm741rMAAAAAAAAoPzYrJHHrWQAAAAAAgMqlVFPb8vPzlZ2drdq1a5e4L7eeBQAAKBulycEAAABsqcRC0oQJE/TWW2/JwcFBAwYM0Llz5zR06FA988wzxb6OW88CAABcv+vNwQAAAGypxKltBw4cUO3atZWUlKSOHTsqOTlZCQkJ5REbAABAlUUOBgAA7FGJhaS8vDzl5uYqKSlJwcHBqlat2g3daQ0AAAAlIwcDAAD2qMRC0qBBgxQcHKwLFy4oICBAqampzM8HAACwMXIwAABgjwxms9lc2hfl5eXJyalU63TbRG6uSZmZ2TY9hqenq1pHLbTpMYDKYOc/h+rkybMVHQaASsbT07WiQ7Ar5GAA/o4cDIAtFJeDlZiJ5OTkaM2aNUpNTVVeXp5l+5gxY8omOgAAAFyDHAwAANijEgtJzz77rFxdXeXn5ydnZ+fyiAkAAKDKIwcDAAD2qMRCktFo1GeffVYesQAAAOD/IwcDAAD2qMTFtv39/fXbb7+VRywAAAD4/8jBAACAPSpxRNLOnTsVFxenRo0aFRhWvXz5cpsGBgAAUJWRgwEAAHtUYiHpk08+KY84AAAAcBVyMAAAYI9KnNrWqFEjnT17VuvXr9f69et19uxZNWrUqDxiAwAAqLLIwQAAgD0qsZC0YMECvfjii8rIyFBGRoaioqK0aNGi8ogNAACgyiIHAwAA9qjEqW1Lly7V119/rZo1a0qShg8frkGDBmnIkCE2Dw4AAKCqIgcDAAD2qMQRSZLk6OhY6N8AAACwHXIwAABgb0ockfTwww9r4MCB6tq1q8xms5KTk9W/f//yiA0AAKDKIgcDAAD2qMRCUkREhNq2baudO3dKkqZPn657773X5oEBAABUZeRgAADAHpVYSDpy5IiaNm0qPz8/bd26VTt27NAtt9wiNze38ogPAACgSiIHAwAA9qjENZKef/55OTg46PDhw5o0aZJOnDihCRMmlEdsAAAAVRY5GAAAsEclFpIcHBzk5OSkxMREPfHEE3r55Zd18uTJ8ogNAACgyiIHAwAA9qjEQpKTk5NWrFihhIQEPfTQQ5KkvLw8W8cFAABQpZGDAQAAe1RiIWn69Onas2ePRo0aJV9fXx09elR9+vQpj9gAAACqLHIwAABgj4pdbNtkMunjjz/WO++8Y9nm6+urESNG2DwwAACAqoocDAAA2KtiRyQ5Ojrq+PHjysnJKa94AAAAqjxyMAAAYK+KHZEkXe79euyxxxQcHKyaNWtatkdERNg0MAAAgKrsRnIwk8mk/v37y9vbW/PmzdPRo0c1fvx4ZWZmys/PTzNnzpSzs7NycnL00ksv6eeff5a7u7tmz56tW265xZZvCwAA3ORKXCPp1ltvVefOnWU2m3X+/HnLfwAAALCdG8nBFi5cqCZNmlgez5o1S8OGDdPatWvl5uampUuXSpKWLFkiNzc3rV27VsOGDdOsWbNs8l4AAEDlUeKIpDFjxkiSLly4IBcXF5sHBAAAgOvPwdLS0rRhwwaNGjVK//73v2U2m7V161bLekv9+vXTnDlzNHjwYK1bt85ynO7du2vKlCkym80yGAxl/4YAAEClUOKIpN27d6tXr17q2bOnJOnXX3/V5MmTbR0XAABAlXa9OVh0dLSioqLk4HA5zTt9+rTc3Nzk5HS5/9DHx0dGo1GSZDQa1aBBA0mSk5OTXF1ddfr0aRu8GwAAUFmUOCIpOjpan332mZ599llJ0t13360dO3bYPDAAAICq7HpysPXr18vDw0P33Xeftm3bZrPYHB0NcnevWfKOAMoF1yOA8lRiIUmSpafqiis9XNZgsUcAAIDrU9ocbNeuXVq3bp1SUlJ06dIlnTt3TtOmTVNWVpby8vLk5OSktLQ0eXt7S5K8vb114sQJ+fj4KC8vT2fPnlXdunVLjMtkMiszM/v635gVPD1dbdo+UJnY+noEUPUU9ztcYkWoQYMG2rVrlwwGg3Jzc/XZZ58VWLyxJCz2CAAAUHrXk4NNmDBBKSkpWrdund599121a9dO77zzjgIDA7VmzRpJUlxcnIKDgyVJwcHBiouLkyStWbNG7dq1Y30kAABQrBILSZMnT9YXX3who9Gojh076pdfftGbb75pVeNXFnscMGCAJFkWe+zevbuky4s9JicnS5LWrVunfv36Sbq82OOWLVtkNpuv600BAADc7G4kB/u7qKgozZ8/X127dlVmZqYGDhwoSRowYIAyMzPVtWtXzZ8/Xy+++GJZvgUAAFAJFTu1LSkpSYcPH1Z4eLjlTh+lcWWxxyu3qr2exR49PDxKfVwAAICb2Y3mYJIUGBiowMBASZKvr69lFPjVqlevrvfff/+GYgUAAFVLkYWkyZMn68CBA/L399d7772nffv2afTo0VY3XB6LPbLQI2BfuB4B4MbdaA4GAABgS0UWknbs2KGEhAQ5OjrqwoULevzxx0uVxJTHYo8s9AjYFxZ6BFDWquLv8I3mYAAAALZU5BpJ1apVk6OjoyTJxcWl1OsVsdgjAABA6d1oDgYAAGBLRY5IOnjwoMLCwiyPjxw5UuDx8uXLr+uAUVFRGjdunGJiYnTPPfcUWOwxKipKXbt2VZ06dTR79uzrah8AAOBmZqscDAAAoCwUWUhatWpVmR2ExR4BAACsU5Y5GAAAQFkrspDUqFGj8owDAAAAIgcDAAD2rcg1kgAAAAAAAICrUUgCAAAAAACAVYosJD355JOSpH/+85/lFgwAAEBVRw4GAADsWZFrJJ08eVK7du3SunXrFBoaes2tZ/38/GweHAAAQFVDDgYAAOxZkYWkyMhIffTRR0pLS9P06dMLPGcwGLRw4UKbBwcAAFDVkIMBAAB7VmQhqUePHurRo4c+/PBDjR49ujxjAgAAqLLIwQAAgD0rspB0xejRo5WcnKwdO3ZIktq2bavOnTvbPDAAAICqjBwMAADYoxLv2vbOO+9o4cKFatKkiZo0aaKFCxfq3XffLY/YAAAAqixyMAAAYI9KHJG0YcMGJSQkyMHhcs2pX79+Cg8P1/jx420eHAAAQFVFDgYAAOxRiSOSJCkrK8vy99mzZ20WDAAAAP4PORgAALA3JY5IGjlypPr166fAwECZzWb98MMPevHFF8sjNgAAgCqLHAwAANijEgtJvXv3Vtu2bfXjjz9Kkl588UV5enraPDAAAICqjBwMAADYoxILSZLk5eWlkJAQW8cCAACAq5CDAQAAe2PVGkkAAAAAAAAAhSQAAAAAAABYpdhCkslkUo8ePcorFgAAAIgcDAAA2K9iC0mOjo5q3Lixjh8/Xl7xAAAAVHnkYAAAwF6VuNh2VlaWQkND1aJFC7m4uFi2z50716aBAQAAVGXkYAAAwB6VWEh64YUXyiMOAAAAXIUcDAAA2KMSC0lt27ZVamqqDh8+rPbt2+vChQsymUzlERsAAECVRQ4GAADsUYl3bfv6668VGRmpN998U5JkNBo1evRomwcGAABQlZGDAQAAe1RiIemLL77QV199pdq1a0uSbr/9dp06dcrmgQEAAFRl5GAAAMAelVhIcnZ2lrOzs+VxXl6eTQMCAAAAORgAALBPJa6RFBAQoLlz5+rixYv6/vvv9eWXXyo4OLg8YgMAAKiyrjcHu3Tpkh5//HHl5OTIZDKpe/fuioyM1NGjRzV+/HhlZmbKz89PM2fOlLOzs3JycvTSSy/p559/lru7u2bPnq1bbrmlHN4hAAC4GZU4IunFF1+Uh4eH7rrrLi1evFidOnXS2LFjyyE0AACAqut6czBnZ2ctWLBA33zzjeLj47Vp0ybt2bNHs2bN0rBhw7R27Vq5ublp6dKlkqQlS5bIzc1Na9eu1bBhwzRr1iwbvzMAAHAzK3FEkoODg8LDw9WiRQsZDAY1btxYBoOhPGIDAACosq43BzMYDKpVq5aky9Ph8vLyZDAYtHXrVr3zzjuSpH79+mnOnDkaPHiw1q1bpzFjxkiSunfvrilTpshsNpPvAQCAQpVYSNqwYYMmTZqkW2+9VWazWceOHdNbb72lTp06lUd8AAAAVdKN5GAmk0kPP/ywjhw5osGDB8vX11dubm5ycrqc+vn4+MhoNEq6fDe4Bg0aSJKcnJzk6uqq06dPy8PDw3ZvDgAA3LRKLCTNmDFDCxcu1G233SZJOnLkiEaMGFFiEsP8fAAAgOt3vTmYJDk6OiohIUFZWVkaPXq0Dh48WKaxOToa5O5es0zbBHD9uB4BlKcSC0m1atWyJDCS5OvraxkuXZwr8/Nr1aql3NxcDR48WB07dtT8+fM1bNgwhYaG6s0339TSpUs1ePDgAvPzV65cqVmzZikmJuaG3hwAAMDN6npzsKu5ubkpMDBQe/bsUVZWlvLy8uTk5KS0tDR5e3tLkry9vXXixAn5+PgoLy9PZ8+eVd26dYtt12QyKzMzu/RvqhQ8PV1t2j5Qmdj6egRQ9RT3O1zkYtuJiYlKTEzUfffdp+HDh2vZsmWKi4vTqFGj1Lx58xIPWtz8/O7du0u6PD8/OTlZkrRu3Tr169dP0uX5+Vu2bJHZbLb+XQIAAFQCN5qDnTp1SllZWZKkixcvavPmzWrSpIkCAwO1Zs0aSVJcXJzlDnDBwcGKi4uTJK1Zs0bt2rVjfSQAAFCkIkckrV+/3vJ3/fr19cMPP0iSPDw8dOnSJasaZ34+AABA6dxoDpaenq6JEyfKZDLJbDarR48e6ty5s+68806NGzdOMTExuueeezRw4EBJ0oABAxQVFaWuXbuqTp06mj17tm3eGAAAqBSKLCRNnz79hhtnfj5QtXA9AsCNu9Ec7O6771Z8fPw12319fbV06dJrtlevXl3vv//+DR0TAABUHSWukXT06FF9/vnnSk1NVV5enmX73LlzrT4I8/OBqoH5+QDKWlX+HS6LHAwAAKCslVhIGj16tAYMGKDOnTvLwaHIJZWucerUKTk5OcnNzc0yP3/48OGW+fmhoaGFzs/39/dnfj4AAKjyrjcHAwAAsKUSC0nVq1fX0KFDS90w8/MBAACu3/XmYAAAALZkMJdwa7Tly5fr8OHD6tChg5ydnS3b/fz8bB5cSXJzTeUyta111EKbHgOoDHb+c6hOnjxb0WEAqGSq8tQ2cjByMMAa5GAAbKG4HKzEEUn79+9XQkKCtm7daplqZjAYtHAhP+wAAAC2Qg4GAADsUYmFpNWrVyspKalATxgAAABsixwMAADYoxJXbmzatKnOnmWoJAAAQHkiBwMAAPaoxBFJZ8+eVc+ePdW8eXNVq1bNsp1bzwIAANgOORgAALBHJRaSnn/++fKIAwAAAFchBwMAAPaoxEJS27ZtyyMOAAAAXIUcDAAA2KMSC0n+/v6WO4Xk5uYqLy9PLi4u2rVrl82DAwAAqKrIwQAAgD0qsZC0e/duy99ms1nJycnas2ePLWMCAACo8sjBAACAPSrxrm1XMxgM6tKli7777jtbxQMAAIC/IQcDAAD2osQRSYmJiZa/8/Pz9dNPP6l69eo2DQoAAKCqIwcDAAD2qMRC0vr16y1/Ozo6qlGjRvroo49sGhQAAEBVRw4GAADsUYmFpOnTp5dHHAAAALgKORgAALBHRRaS5syZU+SLDAaDRo8ebZOAAAAAqjJyMAAAYM+KLCTVrFnzmm3Z2dn673//q8zMTJIYAAAAGyAHAwAA9qzIQtJTTz1l+fvcuXNauHChli1bpl69ehV4DgAAAGWHHAwAANizYtdIyszM1Pz587V8+XL169dPcXFxqlOnTnnFBgAAUCWRgwEAAHtVZCHpH//4h9auXatHHnlEy5cvV61atcozLgAAgCqJHAwAANgzg9lsNhf2xN133y1nZ2c5OjrKYDBYtpvNZhkMBu3atavcgixKbq5JmZnZNj2Gp6erWkcttOkxgMpg5z+H6uTJsxUdBoBKxtPTtaJDKHfkYJeRgwHWIQcDYAvF5WBFjkj69ddfbRIMAAAAikYOBgAA7JlDRQcAAAAAAACAmwOFJAAAAAAAAFiFQhIAAAAAAACsQiEJAAAAAAAAVqGQBAAAAAAAAKtQSAIAAAAAAIBVKCQBAAAAAADAKhSSAAAAKpETJ05oyJAh6tWrl0JDQ7VgwQJJUmZmpiIiItStWzdFRETozJkzkiSz2ay3335bXbt2VVhYmH7++eeKDB8AANg5CkkAAACViKOjoyZOnKhVq1Zp8eLF+vLLL3XgwAHFxsYqKChIiYmJCgoKUmxsrCQpJSVFhw4dUmJioqZOnarJkydX7BsAAAB2zWaFJHrDAAAAyp+Xl5f8/PwkSbVr19Ydd9who9Go5ORkhYeHS5LCw8OVlJQkSZbtBoNBrVq1UlZWltLT0ysqfAAAYOdsVkiiNwwAAKBiHTt2TL/88otatmypjIwMeXl5SZI8PT2VkZEhSTIajfLx8bG8xsfHR0ajsULiBQAA9s/JVg17eXlZkpW/94YtWrRI0uXesCFDhigqKqrI3rArbQAAAMB658+fV2RkpF599VXVrl27wHMGg0EGg+G623Z0NMjdveaNhgigjHA9AihPNiskXe1GesMoJAEAAJRObm6uIiMjFRYWpm7dukmS6tWrZ+mkS09Pl4eHhyTJ29tbaWlpltempaXJ29u72PZNJrMyM7Nt9wYkeXq62rR9oDKx9fUIoOop7nfY5oUkesOAqoPrEQAqntls1muvvaY77rhDERERlu3BwcGKj4/XiBEjFB8fr5CQEMv2zz//XKGhodq7d69cXV3pyAMAAEWyaSGJ3jCgaqE3DEBZ43e49Hbu3KmEhATddddd6tu3ryRp/PjxGjFihMaOHaulS5eqYcOGiomJkSR16tRJGzduVNeuXeXi4qLo6OgKjB4AANg7mxWS6A0DAAAof23atNFvv/1W6HNX7qJ7NYPBoEmTJtk6LAAAUEnYrJBEbxgAAAAAAEDlYrNCEr1hAAAAAAAAlYtDRQcAAAAAAACAmwOFJAAAAAAAAFiFQhIAAAAAAACsQiEJAAAAAAAAVqGQBAAAAAAAAKtQSAIAAAAAAIBVKCQBAAAAAADAKhSSAAAAAAAAYBUKSQAAAAAAALAKhSQAAAAAAABYhUISAAAAAAAArEIhCQAAAAAAAFahkAQAAAAAAACrUEgCAAAAAACAVSgkAQAAAAAAwCoUkgAAAAAAAGAVCkkAAAAAAACwCoUkAAAAAAAAWIVCEgAAAAAAAKxCIQkAAAAAAABWoZAEAAAAAAAAq1BIAgAAAAAAgFUoJAEAAAAAAMAqFJIAAAAAAABgFQpJAAAAAAAAsAqFJAAAAAAAAFiFQhIAAAAAAACsQiEJAACgEnnllVcUFBSk3r17W7ZlZmYqIiJC3bp1U0REhM6cOSNJMpvNevvtt9W1a1eFhYXp559/rqiwAQDATYJCEgAAQCXy8MMP69NPPy2wLTY2VkFBQUpMTFRQUJBiY2MlSSkpKTp06JASExM1depUTZ48uQIiBgAANxObFZLoDQMAACh/AQEBqlOnToFtycnJCg8PlySFh4crKSmpwHaDwaBWrVopKytL6enp5R0yAAC4idiskERvGAAAgH3IyMiQl5eXJMnT01MZGRmSJKPRKB8fH8t+Pj4+MhqNFRIjAAC4OTjZquGAgAAdO3aswLbk5GQtWrRI0uXesCFDhigqKqrI3rArCQ8AAADKhsFgkMFguKE2HB0NcnevWUYRAbhRXI8AypPNCkmFKW1vGIUkAACAG1evXj1LJ116ero8PDwkSd7e3kpLS7Psl5aWJm9v7xLbM5nMyszMtlm8kuTp6WrT9oHKxNbXI4Cqp7jf4XItJF2N3jCg8uF6BAD7FBwcrPj4eI0YMULx8fEKCQmxbP/8888VGhqqvXv3ytXVlY48AABQrHItJNEbBlRu9IYBKGv8Dpfe+PHjtX37dp0+fVodO3bU888/rxEjRmjs2LFaunSpGjZsqJiYGElSp06dtHHjRnXt2lUuLi6Kjo6u2OABAIDdK9dCEr1hAAAAtvXuu+8Wun3BggXXbDMYDJo0aZKtQwIAAJWIzQpJ9IYBAAAAAABULjYrJNEbBgAAAAAAULk4VHQAAAAAAAAAuDlQSAIAAAAAAIBVKCQBAAAAAADAKhSSAAAAAAAAYBWbLbYNADcrjzrV5Ohco6LDAOyeKeeiTp3JregwAACVBDkYYJ2KzsEoJAHA3zg619CRKc0rOgzA7t365o+SKCQBAMoGORhgnYrOwZjaBgAAAAAAAKtQSAIAAAAAAIBVKCQBAAAAAADAKhSSAAAAAAAAYBUKSQAAAAAAALAKhSQAAAAAAABYhUISAAAAAAAArEIhCQAAAAAAAFahkAQAAAAAAACrUEgCAAAAAACAVSgkAQAAAAAAwCoUkgAAAAAAAGAVCkkAAAAAAACwCoUkAAAAAAAAWIVCEgAAAAAAAKxCIQkAAAAAAABWoZAEAAAAAAAAq1BIAgAAAAAAgFUoJAEAAAAAAMAqFJIAAAAAAABgFQpJAAAAAAAAsAqFJAAAAAAAAFjFrgpJKSkp6t69u7p27arY2NiKDgcAAKBKIAcDAADWsptCkslk0pQpU/Tpp59q5cqVWrFihQ4cOFDRYQEAAFRq5GAAAKA07KaQtG/fPt12223y9fWVs7OzQkNDlZycXNFhAQAAVGrkYAAAoDTsppBkNBrl4+Njeezt7S2j0ViBEQEAAFR+5GAAAKA0nCo6gBtRrZqjPD1dbX6cnf8cavNjAJVBeVyP5eXWN3+s6BCAm0Jluu5hPXIwwL5Upu9icjDAOhV53dvNiCRvb2+lpaVZHhuNRnl7e1dgRAAAAJUfORgAACgNuykkNW/eXIcOHdLRo0eVk5OjlStXKjg4uKLDAgAAqNTIwQAAQGnYzdQ2Jycnvfnmm3rmmWdkMpnUv39/NW3atKLDAgAAqNTIwQAAQGkYzGazuaKDAAAAAAAAgP2zm6ltAAAAAAAAsG8UkgAAAAAAAGAVu1kjCSjMiRMn9NJLLykjI0MGg0GPPPKInnzySWVmZmrcuHFKTU1Vo0aNFBMTozp16lR0uADKwKVLl/T4448rJydHJpNJ3bt3V2RkpI4eParx48crMzNTfn5+mjlzppydnSs6XAColPguBqqmK2vleXt7a968eVzzKBQjkmDXHB0dNXHiRK1atUqLFy/Wl19+qQMHDig2NlZBQUFKTExUUFCQYmNjKzpUAGXE2dlZCxYs0DfffKP4+Hht2rRJe/bs0axZszRs2DCtXbtWbm5uWrp0aUWHCgCVFt/FQNW0cOFCNWnSxPKYax6FoZAEu+bl5SU/Pz9JUu3atXXHHXfIaDQqOTlZ4eHhkqTw8HAlJSVVYJQAypLBYFCtWrUkSXl5ecrLy5PBYNDWrVvVvXt3SVK/fv2UnJxckWECQKXGdzFQ9aSlpWnDhg0aMGCAJMlsNnPNo1AUknDTOHbsmH755Re1bNlSGRkZ8vLykiR5enoqIyOjgqMDUJZMJpP69u2r9u3bq3379vL19ZWbm5ucnC7PyPbx8ZHRaKzgKAGgcuO7GKhaoqOjFRUVJQeHy2WC06dPc82jUBSScFM4f/68IiMj9eqrr6p27doFnjMYDDIYDBUUGQBbcHR0VEJCgjZu3Kh9+/bp4MGDFR0SAFQ5fBcDVcf69evl4eGh++67r6JDwU2AxbZh93JzcxUZGamwsDB169ZNklSvXj2lp6fLy8tL6enp8vDwqOAoAdiCm5ubAgMDtWfPHmVlZSkvL09OTk5KS0uTt7d3RYcHAFUC38VA5bdr1y6tW7dOKSkpunTpks6dO6dp06ZxzaNQjEiCXTObzXrttdd0xx13KCIiwrI9ODhY8fHxkqT4+HiFhIRUUIQAytqpU6eUlZUlSbp48aI2b96sJk2aKDAwUGvWrJEkxcXFKTg4uCLDBIBKje9ioGqZMGGCUlJStG7dOr377rtq166d3nnnHa55FMpgNpvNFR0EUJQdO3bo8ccf11133WWZqzt+/Hi1aNFCY8eO1YkTJ9SwYUPFxMTI3d29YoMFUCZ+/fVXTZw4USaTSWazWT169NCYMWN09OhRjRs3TmfOnNE999yjWbNmcftZALARvouBqmvbtm3617/+pXnz5nHNo1AUkgAAAAAAAGAVprYBAAAAAADAKhSSAAAAAAAAYBUKSQAAAAAAALAKhSQAAAAAAABYhUISAAAAAAAArEIhCUCZSUpKUrNmzfTHH3+UabsJCQkKCwtTaGio+vTpo9dee01ZWVllegwAAICbFTkYgPJEIQlAmVmxYoVat26tlStXllmbKSkpWrBggT799FOtXLlScXFx8vf3119//XXNviaTqcyOCwAAcLMgBwNQngxms9lc0UEAuPmdP39ePXr00MKFCzVq1CitWbNGkpSfn68pU6Zo69atatCggZycnNS/f3/16NFDP/30k2bMmKHs7GzVrVtX06dPl5eXV4F2Bw8erMjISLVr167Q4wYHB6tnz57avHmznnnmGZnNZs2bN09ms1mdOnVSVFSUJMnf31+7d++WJK1evVobNmzQjBkzNHHiRDk7O+unn37S+fPnNXHiRHXu3NmGZwoAAKDskIMBKG+MSAJQJpKTk/Xggw+qcePGqlu3rn766SdJUmJiolJTU7Vq1SrNnDlTe/bskSTl5ubq7bff1vvvv69ly5apf//+mj179jXtHjhwQH5+fsUe293dXXFxcWrTpo1mzZqlBQsWKD4+Xj/++KOSkpJKjD01NVVLly7VvHnzNGnSJF26dKn0JwAAAKACkIMBKG8UkgCUiZUrVyo0NFSS1KtXL8vQ6p07d6pHjx5ycHCQp6enAgMDJUl//vmn9u/fr4iICPXt21cff/yxjEZjscf47bff1LdvX3Xp0kWrVq2ybO/Vq5ck6ccff1Tbtm3l4eEhJycnhYWF6Ycffigx9p49e8rBwUG33367fH19dfDgwes6BwAAAOWNHAxAeXOq6AAA3PwyMzO1detW7d+/XwaDQSaTSQaDQS+99FKRrzGbzWratKkWL15cbNt33nmnfv75Z7Vr107NmjVTQkKCpkyZoosXL1r2cXFxKVW8f+/tMhgMxT4GAACwR+RgACoCI5IA3LA1a9aob9++Wr9+vdatW6eNGzfqlltu0Y4dO3T//fcrMTFR+fn5+uuvv7R9+3ZJUuPGjXXq1CnLnPnc3Fz9/vvv17Q9cuRIzZw5U2lpaZZtVycwV2vRooV++OEHnTp1SiaTSStXrlRAQIAkqX79+vrjjz+Un59/zVDr1atXKz8/X0eOHNHRo0fVuHHjMjkvAAAAtkQOBqAiMCIJwA1bsWKFhg8fXmBbt27dtGLFCk2aNElbtmxRr1691KBBA917771ydXWVs7Oz3n//fb399ts6e/asTCaTnnzySTVt2rRAO506ddKpU6c0fPhwmUwmubm5qWnTpnrggQeuicPLy0sTJkzQk08+aVnosUuXLpKkCRMmaOTIkfLw8NB9992n7Oxsy+saNGigAQMG6Pz583rrrbdUvXp1G5wlAACAskUOBqAicNc2ADZ3/vx51apVS6dPn9bAgQP11VdfydPTs6LDkiRNnDhRDz30kHr06FHRoQAAAJQpcjAAtsCIJAA2N2rUKGVlZSk3N1fPPfec3SQwAAAAlRk5GABbYEQSAAAAAAAArMJi2wAAAAAAALAKhSQAAAAAAABYhUISAAAAAAAArEIhCQAAAAAAAFahkAQAAAAAAACrUEgCAAAAAACAVf4fKC/9TMe7y7sAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 1440x360 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "missing_flower_preference['Age Group'] = df.Age//10 * 10\n",
    "missing_color_preference['Age Group'] = df.Age//10 * 10\n",
    "\n",
    "fig, axes = plt.subplots(1,2, figsize=(20,5))\n",
    "sns.countplot(x=\"Age Group\", ax=axes[0], palette='tab10', data=missing_flower_preference)\n",
    "axes[0].set_title(\"Distribution of MISSING Flower Preference by Age \")\n",
    "axes[0].set_ylabel('Number of Persons')\n",
    "\n",
    "sns.countplot(x=\"Age Group\", ax=axes[1], palette='tab10', data=missing_color_preference)\n",
    "axes[1].set_title(\"Distribution of MISSING Color Preference by Age\")\n",
    "axes[1].set_ylabel('Number of Persons')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dca94f6e-35e2-4c4b-9b36-4d94b9767dfa",
   "metadata": {},
   "source": [
    "### Biasing Trends"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cc68f52e-5551-4f78-9cf2-eb016640d657",
   "metadata": {},
   "source": [
    "Understanding bias based on a synthetic dataset of US name/age data, adapted from CleanData.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "e8f8c6bd-9e38-4cb1-b2d9-2fe0739bfcc8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Age</th>\n",
       "      <th>Birth_Month</th>\n",
       "      <th>Name</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Home</th>\n",
       "      <th>Age Group</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>17</td>\n",
       "      <td>June</td>\n",
       "      <td>Matthew</td>\n",
       "      <td>M</td>\n",
       "      <td>Hawaii</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5</td>\n",
       "      <td>September</td>\n",
       "      <td>Emma</td>\n",
       "      <td>F</td>\n",
       "      <td>West Virginia</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4</td>\n",
       "      <td>January</td>\n",
       "      <td>Liam</td>\n",
       "      <td>M</td>\n",
       "      <td>Alaska</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>96</td>\n",
       "      <td>March</td>\n",
       "      <td>William</td>\n",
       "      <td>M</td>\n",
       "      <td>Arkansas</td>\n",
       "      <td>90</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7</td>\n",
       "      <td>March</td>\n",
       "      <td>William</td>\n",
       "      <td>M</td>\n",
       "      <td>Hawaii</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6337</th>\n",
       "      <td>88</td>\n",
       "      <td>July</td>\n",
       "      <td>Dorothy</td>\n",
       "      <td>F</td>\n",
       "      <td>Massachusetts</td>\n",
       "      <td>80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6338</th>\n",
       "      <td>29</td>\n",
       "      <td>August</td>\n",
       "      <td>Jessica</td>\n",
       "      <td>F</td>\n",
       "      <td>Massachusetts</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6339</th>\n",
       "      <td>51</td>\n",
       "      <td>April</td>\n",
       "      <td>Michael</td>\n",
       "      <td>M</td>\n",
       "      <td>Wyoming</td>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6340</th>\n",
       "      <td>29</td>\n",
       "      <td>May</td>\n",
       "      <td>Christopher</td>\n",
       "      <td>M</td>\n",
       "      <td>North Carolina</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6341</th>\n",
       "      <td>62</td>\n",
       "      <td>November</td>\n",
       "      <td>James</td>\n",
       "      <td>M</td>\n",
       "      <td>Texas</td>\n",
       "      <td>60</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6342 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Age Birth_Month         Name Gender            Home  Age Group\n",
       "0      17        June      Matthew      M          Hawaii         10\n",
       "1       5   September         Emma      F   West Virginia          0\n",
       "2       4     January         Liam      M          Alaska          0\n",
       "3      96       March      William      M        Arkansas         90\n",
       "4       7       March      William      M          Hawaii          0\n",
       "...   ...         ...          ...    ...             ...        ...\n",
       "6337   88        July      Dorothy      F   Massachusetts         80\n",
       "6338   29      August      Jessica      F   Massachusetts         20\n",
       "6339   51       April      Michael      M         Wyoming         50\n",
       "6340   29         May  Christopher      M  North Carolina         20\n",
       "6341   62    November        James      M           Texas         60\n",
       "\n",
       "[6342 rows x 6 columns]"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "names = pd.read_parquet(os.path.join(data_dir,'usa_names_states.parq'))\n",
    "names['Age Group'] = names.Age//10 * 10\n",
    "names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "e92cf3a5-bbdd-42b4-ad5c-e97ac55dd06d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Age Group', ylabel='count'>"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Distribution of name frequency by age')"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Number of Persons')"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x324 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# trends in top five first names \n",
    "fig, axis = plt.subplots(figsize=(12, 4.5))\n",
    "somenames = ['Michael', 'James', 'Mary', 'Ashley']\n",
    "popular = names[names.Name.isin(somenames)]\n",
    "sns.countplot(x=\"Age Group\", hue=\"Name\", \n",
    "              ax=axis, palette='tab10', data=popular)\n",
    "axis.set_title(\"Distribution of name frequency by age\")\n",
    "axis.set_ylabel('Number of Persons')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "d53c169f-f1fd-4f44-a4ea-8426db40d2d3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Age Group', ylabel='count'>"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Distribution of birth month frequency by age')"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Number of Persons')"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x324 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# trends in birth month\n",
    "fig, axis = plt.subplots(figsize=(12, 4.5))\n",
    "months = ['January', 'February', 'March', 'April']\n",
    "popular = names[names.Birth_Month.isin(months)]\n",
    "sns.countplot(x=\"Age Group\", hue=\"Birth_Month\", \n",
    "              ax=axis, palette='tab10', data=popular)\n",
    "axis.set_title(\"Distribution of birth month frequency by age\")\n",
    "axis.set_ylabel('Number of Persons')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "7711828b-a139-46f4-9abf-f5a135096862",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Birth_Month</th>\n",
       "      <th>January</th>\n",
       "      <th>February</th>\n",
       "      <th>March</th>\n",
       "      <th>April</th>\n",
       "      <th>May</th>\n",
       "      <th>June</th>\n",
       "      <th>July</th>\n",
       "      <th>August</th>\n",
       "      <th>September</th>\n",
       "      <th>October</th>\n",
       "      <th>November</th>\n",
       "      <th>December</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Age Group</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>20</td>\n",
       "      <td>67</td>\n",
       "      <td>59</td>\n",
       "      <td>76</td>\n",
       "      <td>66</td>\n",
       "      <td>77</td>\n",
       "      <td>71</td>\n",
       "      <td>65</td>\n",
       "      <td>67</td>\n",
       "      <td>67</td>\n",
       "      <td>56</td>\n",
       "      <td>63</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>37</td>\n",
       "      <td>72</td>\n",
       "      <td>71</td>\n",
       "      <td>78</td>\n",
       "      <td>70</td>\n",
       "      <td>73</td>\n",
       "      <td>82</td>\n",
       "      <td>81</td>\n",
       "      <td>83</td>\n",
       "      <td>79</td>\n",
       "      <td>70</td>\n",
       "      <td>79</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>52</td>\n",
       "      <td>60</td>\n",
       "      <td>76</td>\n",
       "      <td>72</td>\n",
       "      <td>65</td>\n",
       "      <td>65</td>\n",
       "      <td>71</td>\n",
       "      <td>66</td>\n",
       "      <td>68</td>\n",
       "      <td>75</td>\n",
       "      <td>76</td>\n",
       "      <td>71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>54</td>\n",
       "      <td>56</td>\n",
       "      <td>66</td>\n",
       "      <td>64</td>\n",
       "      <td>73</td>\n",
       "      <td>58</td>\n",
       "      <td>87</td>\n",
       "      <td>82</td>\n",
       "      <td>66</td>\n",
       "      <td>65</td>\n",
       "      <td>57</td>\n",
       "      <td>58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40</th>\n",
       "      <td>56</td>\n",
       "      <td>62</td>\n",
       "      <td>48</td>\n",
       "      <td>49</td>\n",
       "      <td>45</td>\n",
       "      <td>50</td>\n",
       "      <td>58</td>\n",
       "      <td>55</td>\n",
       "      <td>56</td>\n",
       "      <td>66</td>\n",
       "      <td>68</td>\n",
       "      <td>60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50</th>\n",
       "      <td>56</td>\n",
       "      <td>43</td>\n",
       "      <td>62</td>\n",
       "      <td>55</td>\n",
       "      <td>53</td>\n",
       "      <td>43</td>\n",
       "      <td>58</td>\n",
       "      <td>48</td>\n",
       "      <td>53</td>\n",
       "      <td>58</td>\n",
       "      <td>52</td>\n",
       "      <td>46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <td>66</td>\n",
       "      <td>47</td>\n",
       "      <td>41</td>\n",
       "      <td>43</td>\n",
       "      <td>54</td>\n",
       "      <td>34</td>\n",
       "      <td>41</td>\n",
       "      <td>51</td>\n",
       "      <td>50</td>\n",
       "      <td>32</td>\n",
       "      <td>52</td>\n",
       "      <td>37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>70</th>\n",
       "      <td>57</td>\n",
       "      <td>43</td>\n",
       "      <td>39</td>\n",
       "      <td>33</td>\n",
       "      <td>39</td>\n",
       "      <td>36</td>\n",
       "      <td>45</td>\n",
       "      <td>34</td>\n",
       "      <td>38</td>\n",
       "      <td>30</td>\n",
       "      <td>37</td>\n",
       "      <td>37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>80</th>\n",
       "      <td>57</td>\n",
       "      <td>39</td>\n",
       "      <td>28</td>\n",
       "      <td>21</td>\n",
       "      <td>31</td>\n",
       "      <td>37</td>\n",
       "      <td>23</td>\n",
       "      <td>28</td>\n",
       "      <td>27</td>\n",
       "      <td>31</td>\n",
       "      <td>34</td>\n",
       "      <td>37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>90</th>\n",
       "      <td>55</td>\n",
       "      <td>17</td>\n",
       "      <td>31</td>\n",
       "      <td>24</td>\n",
       "      <td>21</td>\n",
       "      <td>23</td>\n",
       "      <td>30</td>\n",
       "      <td>29</td>\n",
       "      <td>33</td>\n",
       "      <td>25</td>\n",
       "      <td>28</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>100</th>\n",
       "      <td>10</td>\n",
       "      <td>7</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>6</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>7</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Birth_Month  January  February  March  April  May  June  July  August  \\\n",
       "Age Group                                                               \n",
       "0                 20        67     59     76   66    77    71      65   \n",
       "10                37        72     71     78   70    73    82      81   \n",
       "20                52        60     76     72   65    65    71      66   \n",
       "30                54        56     66     64   73    58    87      82   \n",
       "40                56        62     48     49   45    50    58      55   \n",
       "50                56        43     62     55   53    43    58      48   \n",
       "60                66        47     41     43   54    34    41      51   \n",
       "70                57        43     39     33   39    36    45      34   \n",
       "80                57        39     28     21   31    37    23      28   \n",
       "90                55        17     31     24   21    23    30      29   \n",
       "100               10         7      4      2    6     2     4       6   \n",
       "\n",
       "Birth_Month  September  October  November  December  \n",
       "Age Group                                            \n",
       "0                   67       67        56        63  \n",
       "10                  83       79        70        79  \n",
       "20                  68       75        76        71  \n",
       "30                  66       65        57        58  \n",
       "40                  56       66        68        60  \n",
       "50                  53       58        52        46  \n",
       "60                  50       32        52        37  \n",
       "70                  38       30        37        37  \n",
       "80                  27       31        34        37  \n",
       "90                  33       25        28        20  \n",
       "100                  5        5         7         7  "
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "month_names = np.array(\"\"\"\n",
    "    January February March April May\n",
    "    June July August September October\n",
    "    November December\"\"\".split())\n",
    "\n",
    "by_month = (names\n",
    "    .groupby('Age Group')\n",
    "    .Birth_Month\n",
    "    .value_counts()\n",
    "    .unstack())\n",
    "\n",
    "by_month = by_month[month_names]\n",
    "by_month"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "b1f34db0-86d7-4256-b3bf-7b85b38f64f5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Age Group\n",
      "0      0.289808\n",
      "10     0.172563\n",
      "20     0.061524\n",
      "30     0.138908\n",
      "40     0.077120\n",
      "50     0.059772\n",
      "60     0.169321\n",
      "70     0.104118\n",
      "80     0.227215\n",
      "90     0.284632\n",
      "100    0.079604\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "print(by_month.var(axis=1) / by_month.sum(axis=1))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e123ef31-98fa-4db0-ad1f-5d9ec9b099e9",
   "metadata": {},
   "source": [
    "### Compare distributions to baselines"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "fa2398a0-94f1-4cf4-b23b-87fc09d844cb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>State</th>\n",
       "      <th>Population_2019</th>\n",
       "      <th>Population_2010</th>\n",
       "      <th>House_Seats</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>California</td>\n",
       "      <td>39512223</td>\n",
       "      <td>37254523</td>\n",
       "      <td>53.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Texas</td>\n",
       "      <td>28995881</td>\n",
       "      <td>25145561</td>\n",
       "      <td>36.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Florida</td>\n",
       "      <td>21477737</td>\n",
       "      <td>18801310</td>\n",
       "      <td>27.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>New_York</td>\n",
       "      <td>19453561</td>\n",
       "      <td>75459</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Pennsylvania</td>\n",
       "      <td>12801989</td>\n",
       "      <td>12702379</td>\n",
       "      <td>18.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>51</th>\n",
       "      <td>Wyoming</td>\n",
       "      <td>578759</td>\n",
       "      <td>563626</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>52</th>\n",
       "      <td>Guam</td>\n",
       "      <td>165718</td>\n",
       "      <td>159358</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53</th>\n",
       "      <td>U.S._Virgin_Islands</td>\n",
       "      <td>104914</td>\n",
       "      <td>106405</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>54</th>\n",
       "      <td>American_Samoa</td>\n",
       "      <td>55641</td>\n",
       "      <td>55519</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>55</th>\n",
       "      <td>Northern_Mariana_Islands</td>\n",
       "      <td>55194</td>\n",
       "      <td>53883</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>56 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                       State  Population_2019  Population_2010  House_Seats\n",
       "0                 California         39512223         37254523         53.0\n",
       "1                      Texas         28995881         25145561         36.0\n",
       "2                    Florida         21477737         18801310         27.0\n",
       "3                   New_York         19453561            75459          NaN\n",
       "4               Pennsylvania         12801989         12702379         18.0\n",
       "..                       ...              ...              ...          ...\n",
       "51                   Wyoming           578759           563626          1.0\n",
       "52                      Guam           165718           159358          1.0\n",
       "53       U.S._Virgin_Islands           104914           106405          1.0\n",
       "54            American_Samoa            55641            55519          1.0\n",
       "55  Northern_Mariana_Islands            55194            53883          1.0\n",
       "\n",
       "[56 rows x 4 columns]"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "states = pd.read_csv(os.path.join(data_dir,'state-population.csv'), delimiter='|')\n",
    "states"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "094bf077-53c8-48ad-810b-afcba9c017cf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:title={'center':'Distribution of sample by home state'}, xlabel='Home State', ylabel='Number of Occurrences'>"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAtQAAAErCAYAAAD+ARShAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAACi20lEQVR4nOydd1gU1/f/3wuIolhRUBG7xkQsCGJLQImNYkMRTcDeUOyiAooFu36tWGOPXVEQsBsxibGLMWo0dhAUVETpZZnfH/xmPrvszO7MwlL0vJ4nT2T27uzduzN3zj33nPeRMQzDgCAIgiAIgiAIrdAr7g4QBEEQBEEQRGmGDGqCIAiCIAiCKABkUBMEQRAEQRBEASCDmiAIgiAIgiAKABnUBEEQBEEQBFEAyKAmCIIgCIIgiAJABjVBEDojICAAGzduLJRzxcXFwcrKCnK5HADg6emJo0ePFsq5AWDUqFE4ceJEoZ1PLGvWrEG7du3QqVOnIv9ssXzzzTd49eqV5PcdP34cgwcPLpQ+FPbvTRAEUZgYFHcHCIIonTg4OOD9+/fQ19eHvr4+GjdujD59+sDd3R16enlr9YULF4o+16JFi9CxY0fBNrVr10ZUVFSh9H3Dhg149eoVVq1axR3bvn17oZxbCnFxcdi1axcuXboEExOTIv98QnfwXWPquH79Onx8fPD777/ruGcEQegCMqgJgtCaLVu2oGPHjkhOTsaNGzewePFi3Lt3D0uXLi3Uz8nJyYGBwZc3XcXFxaFKlSpkTBMEQZRyKOSDIIgCU7FiRfz4449Yu3YtTpw4gf/++w8AMHv2bKxZswYAkJiYiLFjx8LGxga2trb46aefkJubCx8fH8TFxWHcuHGwsrLCL7/8gtevX+Obb77B0aNH0blzZwwdOpQ7lpOTw31udHQ0BgwYgDZt2sDLywtJSUkA8rx9dnZ2Sn10cHDAX3/9hd9//x1bt27F6dOnYWVlhd69ewNQDinIzc3Fpk2b0KVLF3To0AEzZ85EcnIyAHD9OHHiBDp37ox27dph8+bNgmOTnJyMmTNnon379ujSpQs2bdqE3Nxc/PXXXxgxYgQSEhJgZWWF2bNnq7xXaMwAYNu2bejatSusrKzg5OSE8+fPc+87fvw4Bg0ahCVLlsDGxgY//vgj7ty5g+PHj8Pe3h4dOnRQCm+ZPXs2AgICMHz4cFhZWcHDwwOxsbG83ycrKwvLly9H586d0bFjRwQEBCAjI0Pw+zMMg4ULF8La2ho9e/bE1atXAQCnT5+Gq6urUttdu3bBy8tL8FyxsbEYNGgQrKysMGLECCQmJnKvXbx4Ec7OzrCxsYGnpyeePXvGvebg4IDt27ejV69eaN26Nfz8/PD+/XuMGjUKVlZWGDZsGD59+sS1v3v3LgYNGgQbGxv07t0b169fF+zTtm3b8MMPP8DKygo9evTA1atXBa+x4OBgODo6wsrKCj/++CMOHToEAEhLS8Po0aO5a8HKygrx8fHIzc3lfud27dph8uTJ3DVOEEQJgyEIgtCCLl26MFeuXFE5bm9vz+zfv59hGIaZNWsWs3r1aoZhGGbVqlXM3LlzmaysLCYrK4u5efMmk5uby3uumJgYpmnTpoyPjw+TmprKpKenc8eys7MZhmEYDw8P5vvvv2ceP37MpKamMt7e3sz06dMZhmGYa9euMT/88INgf9evX8+1ZfHw8GCOHDnCMAzDHD16lOnatSsTHR3NpKSkMBMmTGBmzJih1Dd/f38mPT2d+ffff5nmzZszT58+5R0nHx8fZty4cUxycjITExPDdO/enfscvn4qom7MTp06xbx9+5aRy+VMREQE06pVKyY+Pp5hGIYJDg5mvv32W+bYsWNMTk4Os3r1asbe3p6ZP38+k5mZyfzxxx9M69atmZSUFO53at26NXPjxg0mMzOTCQwMZAYNGsT1o2nTpszLly8ZhmGYxYsXM2PHjmU+fvzIJCcnM2PHjmVWrVrF23+2H7t27WKysrKYiIgIpk2bNszHjx+ZzMxMpm3btkrj1qdPH+bMmTO85/Lw8GB+/PFH5vnz50x6ejrj4eHBrFy5kmEYhnn+/DnTqlUr5s8//2SysrKYbdu2MV27dmUyMzMZhsn77d3c3Jh3794xb9++Zdq3b8/07duXefDgAZORkcF4enoyGzZsYBiGYd6+fcvY2toykZGRjFwuZ/7880/G1taW+fDhg0qfnj17xtjZ2TFv375lGCbv2nj16hXDMPzX2KVLl5hXr14xubm5zPXr15mWLVsy9+/fZxiG/1rYvXs34+bmxrx584bJzMxk5s6dy0ydOpV3fAiCKF7IQ00QRKFiamqq5O1jMTAwwLt37xAXF4cyZcrAxsYGMplM7bkmTpyI8uXLo1y5cryv9+nTB02bNkX58uUxefJknDlzhktaLAhhYWEYNmwYLCwsUKFCBUybNg2nTp1S8o57e3ujXLlyaNasGZo1a4ZHjx6pnEcul+PUqVOYPn06jI2NUadOHQwfPhwnT54U1Q91Y+bo6AgzMzPo6enByckJ9erVw71797j31qlTB/3794e+vj6cnJzw5s0bTJgwAYaGhvj+++9haGiI6Ohorn3nzp3Rtm1bGBoaYurUqbh79y7evHmj1B+GYXDkyBH4+fmhSpUqMDY2xtixYxERESH4HapVq4ahQ4eiTJkycHJyQoMGDRAZGQlDQ0M4OjpyY/HkyRPExsaiS5cugudydXVFgwYNUK5cOfTs2RP//vsvAODUqVOwt7dHp06dUKZMGYwcORIZGRlKMfceHh6oXr06zMzMYGNjg5YtW+K7775D2bJl0a1bNzx8+BAAEBoaCjs7O9jb20NPTw+dOnWCpaUlLl++rNIffX19ZGVl4dmzZ8jOzkadOnVQt25dwf537twZdevWhUwmg62tLTp16oRbt24Jtj906BCmTp2KmjVrwtDQEN7e3jh79qzSdUgQRMngywtKJAiiWImPj0flypVVjo8cORJBQUEYMWIEAMDd3R1jxoxRe66aNWuqfb1WrVrcv2vXro3s7Gx8/PhRi14rk5CQAHNzc+5vc3Nz5OTk4MOHD9yx6tWrc/82MjJCWlqaynk+fvyI7Oxs1K5dW6mf8fHxovqhbsxCQkKwa9cuLjQjLS1N6bsrxmWzCxLFPpctWxapqanc34pjXaFCBVSuXBkJCQlKY5yYmIj09HSlUA2GYbgwFD7MzMyUFk61a9dGQkICAKBfv36YNm0apkyZgtDQUDg6OsLQ0FDwXDVq1OD+rTjmCQkJSmOsp6eHWrVqKY1z/u+u+He5cuW4c8XFxeHMmTO4dOkS93pOTg7atWun0p969erBz88PGzZswNOnT/H9999j9uzZMDMz4+3/5cuXsXHjRrx8+RK5ubnIyMhA06ZNBb9vXFwcJkyYwCX5st/tw4cPgp9BEETxQAY1QRCFxr179xAfHw9ra2uV14yNjTF79mzMnj0b//33H4YOHYoWLVqgQ4cOgufT5MFW9KC+efMGZcqUQdWqVWFkZKQU1yuXy5XibTWd19TUVCmGOC4uDgYGBjAxMcHbt2/VvleRqlWrokyZMoiLi0Pjxo25foo1hoTGrG7dupgzZw52794NKysr6Ovro0+fPqL7xYfi90pNTcWnT59gamqq8n3KlSuHiIgI0d8hPj4eDMNwY/7mzRs4ODgAAFq3bo0yZcrg1q1bCA8PF62IkR9TU1Mubh/IM/KljLMitWrVQp8+fbBo0SJR7Xv16oVevXohJSUFAQEBWLVqFVauXKlyjWVlZWHSpElYvnw5fvzxR5QpUwbjx48HwzAA+K/JmjVrYsmSJbz3E0EQJQsK+SAIosCkpKTg0qVLmDZtGnr37o1vvvlGpc2lS5fw6tUrMAyDihUrQl9fnzMiqlevjpiYGMmfe/LkSTx9+hTp6elYt24devToAX19fTRo0ACZmZmIjIxEdnY2Nm/ejKysLO59JiYmiI2NFfSsuri4YM+ePYiJiUFqairWrFkDR0dHyUoj+vr66NmzJ9asWYOUlBTExsZi165dXJKaJoTGLD09HTKZDNWqVQOQl+z25MkTSX3Lz+XLl3Hr1i1kZWVh3bp1aNWqlZJ3Gsjzjrq5uWHJkiWctz4+Ph5//PGH4HkTExOxd+9eZGdn4/Tp03j27Bns7e251/v27YuFCxfCwMAANjY2WvXd0dERly9fxtWrV5GdnY2dO3fC0NAQVlZWks/Vu3dvXLp0CX/88QfkcjkyMzNx/fp13oXU8+fPcfXqVWRlZcHQ0BBly5blvMn5r7GsrCxkZWWhWrVqMDAwwOXLl3HlyhXuXCYmJkhKSuKSXwFg8ODBWLt2Lbe4S0xMxIULFyR/J4IgdA95qAmC0Jpx48ZBX18fenp6aNy4MYYPH45Bgwbxtn316hUCAwORmJiISpUqYfDgwWjfvj0AYMyYMVi0aBFWrlwJLy8v9OjRQ9Tn9+nTB7Nnz8bz589ha2uL+fPnA8hTHZk3bx7mzJkDuVyOUaNGKYU09OzZEydPnkS7du1Qp04dlYIu/fv3R3x8PDw8PJCZmYnvv/8ec+fO1WKEgLlz5yIwMBBdu3ZF2bJl4ebmhv79+4t6r7oxGzFiBAYNGgSZTIa+ffuiTZs2WvWPxcXFBRs3bsTdu3fx3XffYeXKlbztfHx8sHHjRgwcOBAfP36EmZkZBg8ejB9++IG3fcuWLfHq1Su0b98e1atXx/r161G1alXu9T59+mDdunUYP3681n1v2LAhVq5cicDAQMTHx+Pbb7/Fli1b1IaPCFGrVi1s2rQJK1euxPTp06Gnp4eWLVty15YiWVlZ+L//+z88e/YMZcqUgZWVFae9zneNzZkzB1OmTEFWVha6dOnCeeoBoFGjRnB2dkbXrl0hl8sRERGBIUOGgGEYTg3GxMQETk5O6Nq1q9ZjRRCEbpAx7H4TQRAE8VXCxv1OnTq1yD87IyODk/GrX79+kX8+QRBEYUAhHwRBEESxcfDgQbRo0YKMaYIgSjUU8kEQBEEUCw4ODmAYBhs3bizurhAEQRQICvkgCIIgCIIgiAJAIR8EQRAEQRAEUQDIoCYIgiAIgiCIAlCqY6hzc3Mhl6tGrOjry3iPC0HtqT211037ktQXak/tqf3X074k9YXafznty5TRF3xPqTao5XIGSUmq5X6rVCnPe1wIak/tqb1u2pekvlB7ak/tv572Jakv1P7LaV+jRkXB91DIB0EQBEEQBEEUADKoCYIgCIIgCKIAkEFNEARBEARBEAWADGqCIAiCIAiCKABkUBMEQRAEQRBEASCDmiAIgiAIgiAKQKmWzfuaMa5kBKOy//v5WCmX9MwcpHxOL65uEQRBEARBfHWQQV1KMSprgPqzI1SOv1zmjJRi6A9BEARBEMTXCoV8EARBEARBEEQBIIOaIAiCIAiCIAoAGdQEQRAEQRAEUQDIoCYIgiAIgiCIAkAGNUEQBEEQBEEUAJ2pfPj6+iIyMhImJiYIDw8HAEyZMgUvXrwAACQnJ6NixYoIDQ3F69ev4eTkhAYNGgAAWrVqhYULF+qqawRBEARBEARRaOjMoHZ1dYWHhwdmzZrFHVu7di3372XLlsHY2Jj7u27duggNDdVVdwiCIAiCIAhCJ+gs5KNt27aoXLky72sMw+D06dNwcXHR1ccTBEEQBEEQRJFQLDHUt27dgomJCerXr88de/36Nfr27QsPDw/cunWrOLpFEARBEARBEJKRMQzD6Orkr1+/xrhx47gYapZ58+ahXr16GDFiBAAgKysLqampqFq1Ku7fv48JEyYgIiJCKSSEj9zcXMjlqt3X19eDXJ4rup+lsX2ZMvqClRKzs+VF3h9qT+1Lel+oPbWn9l9P+5LUF2r/5bQvU0Zf8D1FXno8JycH58+fx/Hjx7ljhoaGMDQ0BABYWlqibt26ePHiBVq0aKH2XHI5g6SkNJXjVaqU5z0uRGlsX6NGRcHXNL23JPSf2n8d7UtSX6g9taf2X0/7ktQXav/ltFdnexV5yMdff/2Fhg0bombNmtyxxMREyOV5XtWYmBi8fPkSFhYWRd01giAIgiAIgpCMzjzU06ZNw40bN/Dx40fY2dlh4sSJcHNzw6lTp+Ds7KzU9ubNm1i/fj0MDAygp6eHBQsWoEqVKrrqGkEQBEEQBEEUGjozqFevXs17fNmyZSrHevTogR49euiqKwRBEARBEAShMzSGfJw+fRopKSkAgE2bNsHb2xsPHjzQeccIgiAIgiAIojSg0aDetGkTjI2NcevWLVy9ehUDBgzA/Pnzi6BrBEEQBEEQBFHy0WhQ6+vnSYRcvnwZAwcOROfOnZGdna3zjhEEQRAEQRBEaUCjQW1mZoaAgACcOnUK9vb2yMrKQm6ueC0/giAIgiAIgviS0WhQr127Ft9//z127NiBSpUqISkpCTNnziyKvhEEQRAEQRBEiUejyoeRkRGqVauG27dvo379+jAwMEC9evWKom8EQRAEQShgXMkIRmX/9+hmC02kZ+Yg5XN6cXWLIL56NBrUQUFBuH//Pl68eIH+/fsjOzsbPj4+OHToUFH0jyAIgiAKjdJukBqVNUD92REqx18uc0ZKMfSHIIg8NBrU58+fR0hICPr16wcgL6Y6NTVV5x0jCIIgiMKGDFKCIHSBxhjqMmXKQCaTQSaTAQDS0sTXQicIgiAIgiCILx2NHmpHR0cEBATg8+fPOHLkCIKDgzFw4MCi6BtBEARBEARBlHg0GtQjR47ElStXUKFCBbx48QKTJk1Cp06diqJvBEEQBEEQBFHi0WhQx8TEwMbGhjOiMzIy8Pr1a9SpU0fnnSMIgihqSnvSGkEQBFH0aDSoJ0+erKTooaenh8mTJyM4OFjt+3x9fREZGQkTExOEh4cDADZs2IAjR46gWrVqAIBp06bB3t4eALB161YcO3YMenp6mDNnDn744QetvxRBEIS2fG1Ja7SA+LKh35cgigaNBrVcLoehoSH3t6GhoajS466urvDw8MCsWbOUjg8bNgwjR45UOvb06VNEREQgIiIC8fHxGD58OM6ePcuVPScIgiB0w9e2gPjaoN+XIIoGjSof1apVw8WLF7m/L1y4gKpVq2o8cdu2bVG5cmVRnbh48SKcnZ1haGgICwsL1KtXD/fu3RP1XoIgCIIgCIIoTjR6qBcsWIAZM2YgMDAQDMOgVq1aWL58udYfuH//foSEhMDS0hKzZ89G5cqVER8fj1atWnFtzMzMEB8fr/VnEARBEARBEERRodGgrlu3Lo4cOcIVc6lQoYLWHzZ48GCMHz8eMpkM69atw7Jly7B06VKtz6evL0OVKuV5juvxHhc+T+lunx9N7y1p/af2X277ktQXbdrn50u/t/JD37do+6Pr/kttX9K+79c09+iivRxAuTL/C6Vl4+kzsuXQFGBbEvpfktsDIgzqrKwsnD17FrGxscjJyeGOe3t7S/ogAKhevTr3bzc3N4wbNw5Ankf67du33Gvx8fEwMzPTeD65nEFSkmqhmSpVyvMeF6I0tmdvBD40vbck9J/afx3tS1JfxLb/2u4t+r7/ozR8X6n9L+3fV9v2JakvJaV9jRoVBePp371LLvL+lMb26u4njTHUXl5euHjxIvT19VG+fHnuP21ISEjg/n3hwgU0adIEAODg4ICIiAhkZWUhJiYGL1++RMuWLbX6DIIgCIIgCIIoSjR6qOPj47Fjxw7JJ542bRpu3LiBjx8/ws7ODhMnTsSNGzfw6NEjAIC5uTkWLlwIAGjSpAkcHR3h5OQEfX19BAQEkMIHQRAEQRAEUSrQaFBbWVnh8ePH+OabbySdePXq1SrH3NzcBNt7eXnBy8tL0mcQBEEQBEEQRHGj0aC+ffs2Tpw4AXNzcyU96rCwMJ12jCAIgiAIgiBKAxoN6l9++aUo+kEQBPFVQJXrCIIgvjw0GtTm5ua4desWXr16hf79+yMxMZGT0CMIgiCkQZXrCIIgvjw0qnwEBQVh+/bt2LZtGwAgOzsbPj4+Ou8YQXxJGFcyQo0aFVGjRkWUKaPP/du4klFxd40gCIIgiAKi0UN9/vx5hISEoF+/fgDyNKPJQ00Q0iCvJEEQBIU8EV8uGg3qMmXKQCaTQSaTAQDS0sQLYxMEQWiCHrBfNvT7EoqUJOcCXZtEYaLRoHZ0dERAQAA+f/6MI0eOIDg4GAMHDiyKvhEE8RVQkh6wROFDvy9RUqFrkyhM1BrUDMPAyckJz58/R4UKFfDixQtMmjQJnTp1Kqr+EQRBEARBEESJRq1BLZPJMGbMGISFhZERTRAEQRAEQRA8aFT5+O6773Dv3r2i6AtBEESpgxRcCIIgCI0x1H///TfCwsJQu3ZtGBn97wFBlRIJgiAoDpMgCIIQEUMdGBiI2rVrF1V/CIIgCIIgCKJUoTGGeuHChVp5o319fREZGQkTExOEh4cDAJYvX45Lly6hTJkyqFu3LpYuXYpKlSrh9evXcHJyQoMGDQAArVq1wsKFC7X4OkRhQXJCBEEQBEEQ4tAY8sHGULds2VLSiV1dXeHh4YFZs2Zxxzp16oTp06fDwMAAK1euxNatW7mqi3Xr1kVoaKjE7hO6graxCYIgCIIgxKGzGOq2bdvi9evXSse+//577t+tW7fGmTNnpPaXIAiCIAiCINRS1DvtGg3qHTt2FPqHAkBwcDAcHR25v1+/fo2+ffvC2NgYU6ZMgY2NjcZz6OvLUKVKeZ7jerzHhc9TutvnR9N7S9r5v7b2+fmSx7O0j43U/ui6fUn7viXt/KW9PyXt+ixp/f+a5p7SPPYlpX2ZMvqCO+0GOpjbNBrUbMnxwmTz5s3Q19dH7969AQCmpqa4dOkSqlativv372PChAmIiIiAsbGx2vPI5QySklRLoVepUp73uBClsT270uJD03tLwvm/tvZf63iWxrGR2h9dt1ekJHzfknb+0t4fqe3pevty5x5dt6fv+z+0/b7qzqnRoB47diz378zMTLx+/RoNGjRARISq1S+G48ePIzIyErt37+aMdUNDQxgaGgIALC0tUbduXbx48QItWrTQ6jMIgiAIgiBKEyQGULrRaFDnj5V+8OABDhw4oNWH/f7779i+fTv27dunFI+dmJiIypUrQ19fHzExMXj58iUsLCy0+gyC+BqhiZggCKJ0Q2IApRuNBnV+mjdvLqpy4rRp03Djxg18/PgRdnZ2mDhxIrZt24asrCwMHz4cwP/k8W7evIn169fDwMAAenp6WLBgAapUqSL5yxDE1wpNxARBEMSXTEl3HGk0qHft2sX9Ozc3Fw8fPoSpqanGE69evVrlmJubG2/bHj16oEePHhrPSRAEQRAEQXx9lHTHkUaDOjU1lfu3vr4+7O3tS6TxW9JXLgRBEARBEMSXiUaD2tvbuyj6UWBK+sqF+LKgBRxBEARBaM+X9hzVaFAPHz4c69atQ6VKlQAAnz59wrRp03SmT00QpQFawJUevrRJmyCI4oHmksLlS3uOajSoExMTOWMaACpXrowPHz7otFMEQRCFxZc2aRMEUTzQXEKoQ09TA319fcTFxXF/x8bG6qTYC0EQBEEQBEGURjR6qKdMmYKffvoJbdu2BcMwuH37NhYuXFgUfSMIooRAW50EQRAEIYxGg9rOzg7Hjx/H33//DQDw8/NDtWrVdN4xgiBKDrTVSRAEQRDCaDSoz58/j/bt26NLly4AgM+fP+PChQvo2rWrzjtXmiGPHlGSoeuTIEoGdC8SxJeBRoM6KCgI3bp14/6uVKkSgoKCyKDWgFSPHk2qRFFCHmeCKBnQvUgQXwYaDerc3FyVY3K5XCed+Zr52iZVWkAQBEEQmuB7VtBzgiiJaDSoLS0tsXTpUvz8888AgP3796N58+Y675iuIYOueNH1AoJ+X4IgCN2j67mW71nxpTqaiNKNRoN67ty52LRpE6ZMmQIA6NSpEwICAkSd3NfXF5GRkTAxMUF4eDgAICkpCVOnTkVsbCzMzc2xdu1aVK5cGQzDYPHixbh8+TLKlSuHZcuW6dRw/9o8wl8b9PsSBEHoHpprv1zIMSUNjQZ1+fLl4eXlBS8vL1SoUEHSyV1dXeHh4YFZs2Zxx7Zt24YOHTpgzJgx2LZtG7Zt2wYfHx/8/vvvePnyJc6dO4e///4b8+fPx9GjR6V/I4IgCIIgCKJA0GJJGmoLu+zfvx+dO3eGg4MDHBwc0KVLF+zfv1/0ydu2bYvKlSsrHbt48SL69u0LAOjbty8uXLigdFwmk6F169b4/PkzEhISJH4dgiBKAsaVjFCjRkWUKaOPGjUqokaNijCuZFTc3SIIgiAInSDood60aROioqLw66+/wsLCAgAQExODxYsX49OnTxg/frxWH/jhwweYmpoCAGrUqMGVMY+Pj0fNmjW5djVr1kR8fDzXliCI0gPFPRJfK7RNThBfJ4IGdWhoKE6ePImyZctyxywsLLB27Vr06dNHa4NaEZlMVqAy5vr6MlSpUl5jOzFtpLTX19eTfE5d9kdqe133n85fun6vomxPY1Ow9lK/b2m/V0rj9y1TRl9wm9ygFFxvcgDlyuhzf7MLgoxsOfRVWuu+P9q2LWlzQ0m4Ngty/tLeH6nttem/oEEtk8mUjGmWcuXKFcgINjExQUJCAkxNTZGQkMBVXTQzM8Pbt2+5dm/fvoWZmZnac8nlDJKS0gD876bng22jiNT2ilSpUl5jG133p6T1X9fnz+/10dPLm9qFvD4lrf+lvT+F1Z7GRvffV2r7kjb+Us9f0vpT0q4fbdoLLQjevUsulv6Ibavr50RJu3Z0ff7S3h9d9F/dOQUNajMzM1y9ehUdOnRQOn716lXUqFFDbUfU4eDggJCQEIwZMwYhISH48ccfueP79u2Ds7Mz/v77b1SsWJHCPQgOSo4gCIIg1EHPCaIgFDRcS9CgnjNnDsaPHw9ra2tOvu7+/fu4c+cONm3aJKpz06ZNw40bN/Dx40fY2dlh4sSJGDNmDKZMmYJjx46hdu3aWLt2LQDA3t4ely9fRrdu3WBkZIQlS5aI+gyCIAjiy4FikAmCKA4KuiATNKibNGmC8PBwhIWF4enTpwAAGxsbLFy4kDcUhI/Vq1fzHt+zZ4/KMZlMhnnz5ok6L0EQBPFlQl5GgiBKI2p1qMuWLYsBAwYUVV8IgiAIgiAIotShsbALQRAEUXxQCARBEETJhwxqgiCIEgyFQKhH1wsOWtAQBCEGQYN66NCh2LNnD1auXAkfH5+i7FOJhCZVgiCIkjcX6nrBQQsagiDEIGhQv3v3Dnfu3MFvv/0GZ2dnMAyj9Dqr/PG1QJMqQRAEzYUEQRB8CBrUkyZNwqZNm/D27VssXbpU6TWZTIa9e/fqvHMEQRAEQRAEUdIRNKh79uyJnj17YuPGjZgwYUJR9okgCIIgCIIoRZS0cLCiRmNS4oQJE3Dx4kXcunULAGBra4suXbrovGMEQRB8fO2TtiZofAiiZPC13YtfeziYRoP6//7v/3Dv3j306tULALB3715ERUVh2rRpOu8cQRBEfr72SVsTND4EUTKge/HrQqNBHRkZidDQUOjp6QEA+vXrh759+5JBTRAEQRAEQRAQqUP9+fNnVKlSBQCQnJysy/4QOuJr23oiCIIgCIIoKjQa1GPHjkW/fv3Qrl07MAyDmzdvYsaMGUXRN6IQoa0ngiAIgiAI3aDRoHZxcYGtrS3++ecfAMCMGTNQo0YNrT/w+fPnmDp1Kvd3TEwMJk2ahOTkZBw5cgTVqlUDAEybNg329vZafw5BEARBEARBFAWiQj5MTU3x448/FsoHNmzYEKGhoQAAuVwOOzs7dOvWDcePH8ewYcMwcuTIQvkcgiAIgiAIgigKRBnUuuLq1auwsLCAubl5cXaDKAQoRpsgCIIgig567pYsitWgjoiIgIuLC/f3/v37ERISAktLS8yePRuVK1dW+359fRmqVCmv8XPEtKH2BWtfpoy+YIy2QSnovyL6+nqSz/k19acg7UtSX6g9taf2pbd9SepLcbX/kp67X0J7tQa1XC6Hs7Mzzpw5I+mDxZCVlYXffvsN06dPBwAMHjwY48ePh0wmw7p167Bs2TKVkueq/WOQlJQG4H8rMz7YNopQe2ovRJUq5TW2+dr6U1jtS1JfqD21p/alt31J6gu1/3raq2ujJ/gKAH19fTRo0ABxcXHqmmnF77//jubNm6N69eoAgOrVq0NfXx96enpwc3PjkiAJgiAIgiAIoiSjMeTj8+fPcHZ2RsuWLWFkZMQd37JlS4E+OCIiAs7OztzfCQkJMDU1BQBcuHABTZo0KdD5CYIgCIIgCKIo0GhQT548udA/NC0tDX/99RcWLlzIHVu5ciUePXoEADA3N1d6jSC+NijZhCAIgiBKDxoNaltbW8TGxuLVq1fo2LEj0tPTIZfLC/Sh5cuXx/Xr15WOrVy5skDnJIgvCSrEQxAEQRClB7Ux1ABw5MgRTJo0CQEBAQCA+Ph4TJgwQecdIwiCIAiCIIjSgEaDev/+/Th48CCMjY0BAPXr10diYqLOO0YQBEEQBEEQpQGNBrWhoSEMDQ25v3NycnTaIYIgCIIgCIIoTWiMoW7bti22bNmCjIwMXLlyBQcOHICDg0NR9I0gigxKAiQIgiAIQls0GtQzZszAsWPH0LRpUxw+fBj29vZwc3Mrir4RRJFBSYAEQRAEQWiLRoNaT08Pffv2RcuWLSGTydCgQQPIZLKi6BtBEARBEARBlHg0GtSRkZGYN28e6tatC4Zh8Pr1ayxYsAD29vZF0T+CIAiCIAiCKNFoNKiXLVuGvXv3ol69egCA6OhojBkzhgxqgiAIgiAIgoAIlY8KFSpwxjQAWFhYoEKFCjrtFEEQBEEQBEGUFgQ91OfOnQMAWFpaYvTo0XB0dIRMJsOZM2fQokWLIusgQRAEQRAEQZRkBA3qS5cucf+uXr06bt68CQCoVq0aMjMzdd8zgiAIgiAIgigFCBrUS5cu1ekHOzg4oEKFCtDT04O+vj6OHz+OpKQkTJ06FbGxsTA3N8fatWtRuXJlnfaDIAiCIAiCIAqCxqTEmJgY7Nu3D7GxsUpVErds2VLgD9+zZw+qVavG/b1t2zZ06NABY8aMwbZt27Bt2zb4+PgU+HMIgiAIgiAIQldoNKgnTJiAAQMGoEuXLtDT05jDWCAuXryIX3/9FQDQt29feHp6kkFNEARBEARBlGg0GtRly5bFkCFDdPLhI0eOhEwmg7u7O9zd3fHhwweYmpoCAGrUqIEPHz7o5HMJgiAIgiAIorDQaFAPGTIEQUFB6NSpEwwNDbnjzZs3L9AHHzx4EGZmZvjw4QOGDx+Ohg0bKr0uk8k0VmTU15ehSpXyGj9LTBtqT+2pve7bl6S+UHtqT+1Lb/uS1BdqT+0BEQb1f//9h9DQUFy7do0zcGUyGfbu3SupM/kxMzMDAJiYmKBbt264d+8eTExMkJCQAFNTUyQkJCjFV/MhlzNISkoDANSoUVGwHdtGEWpP7al90bcvSX2h9tSe2pfe9iWpL9T+62mvro1Gg/rMmTO4cOGCkne6oKSlpSE3NxfGxsZIS0vDlStXMH78eDg4OCAkJARjxoxBSEgIfvzxx0L7TIIgCIIgCILQBRoN6iZNmiA5ORkmJiaF9qEfPnzAhAkTAAByuRwuLi6ws7NDixYtMGXKFBw7dgy1a9fG2rVrC+0zCYIgCIIgCEIXaDSok5OT4ejoiBYtWqBMmTLc8YLI5llYWODkyZMqx6tWrYo9e/ZofV6CIAiCIAiCKGo0GtQTJ04sin4QBEEQBEEQRKlEo0Fta2tbFP0gCIIgCIIgiFKJRoPaysqKU/fIzs5GTk4OjIyMcOfOHZ13jiAIgiAIgiBKOhoN6qioKO7fDMPg4sWLuHv3ri77RBAEQRAEQRClBkm1xGUyGbp27Yo///xTV/0hCIIgCIIgiFKFRg/1uXPnuH/n5ubi/v37KFu2rE47RRAEQRAEQRClBY0G9aVLl7h/6+vrw9zcHJs2bdJppwiCIAiCIAiitKDRoF66dGlR9IMgCIIgCIIgSiWCBnVQUJDgm2QyGVfpkCAIgiAIgiC+ZgQN6vLly6scS0tLQ3BwMJKSksigJgiCIAiCIAioMahHjBjB/TslJQV79+7F8ePH4eTkpPQaQRAEQRAEQXzNqI2hTkpKwq5duxAWFoZ+/frhxIkTqFy5clH1jSAIgiAIgiBKPIIG9fLly3H+/HkMHDgQYWFhqFChQqF84Js3bzBz5kx8+PABMpkMAwcOxNChQ7FhwwYcOXIE1apVAwBMmzYN9vb2hfKZBEEQBEEQBKErBA3qXbt2wdDQEJs3b8aWLVu44wzDQCaTaV16XF9fH7Nnz0bz5s2RkpKC/v37o1OnTgCAYcOGYeTIkVqdlyAIgiAIgiCKA0GD+tGjRzr5QFNTU5iamgIAjI2N0bBhQ8THx+vkswiCIAiCIAhC12jUodYlr1+/xr///otWrVrhzp072L9/P0JCQmBpaYnZs2drjNfW15ehShVVNZL8iGlD7ak9tdd9+5LUF2pP7al96W1fkvpC7ak9UIwGdWpqKiZNmgQ/Pz8YGxtj8ODBGD9+PGQyGdatW4dly5ZpLCojlzNISkoDANSoUVGwHdtGEWpP7al90bcvSX2h9tSe2pfe9iWpL9T+62mvro2e4Cs6JDs7G5MmTUKvXr3QvXt3AED16tWhr68PPT09uLm54Z9//imOrhEEQRAEQRCEJIrcoGYYBv7+/mjYsCGGDx/OHU9ISOD+feHCBTRp0qSou0YQBEEQBEEQkinykI/bt28jNDQUTZs2RZ8+fQDkSeSFh4dziZDm5uZYuHBhUXeNIAiCIAiCICRT5Aa1jY0NHj9+rHKcNKcJgiAIgiCI0kixxFATBEEQBEEQxJcCGdQEQRAEQRAEUQDIoCYIgiAIgiCIAkAGNUEQBEEQBEEUADKoCYIgCIIgCKIAkEFNEARBEARBEAWADGqCIAiCIAiCKABkUBMEQRAEQRBEASCDmiAIgiAIgiAKABnUBEEQBEEQBFEAyKAmCIIgCIIgiAJQ4gzq33//HT169EC3bt2wbdu24u4OQRAEQRAEQailRBnUcrkcCxcuxPbt2xEREYHw8HA8ffq0uLtFEARBEARBEIKUKIP63r17qFevHiwsLGBoaAhnZ2dcvHixuLtFEARBEARBEIKUKIM6Pj4eNWvW5P42MzNDfHx8MfaIIAiCIAiCINQjYxiGKe5OsJw5cwZ//PEHFi9eDAAICQnBvXv3EBAQUMw9IwiCIAiCIAh+SpSH2szMDG/fvuX+jo+Ph5mZWTH2iCAIgiAIgiDUU6IM6hYtWuDly5eIiYlBVlYWIiIi4ODgUNzdIgiCIAiCIAhBDIq7A4oYGBggICAAo0aNglwuR//+/dGkSZPi7hZBEARBEARBCFKiYqgJgiAIgiAIorRRokI+CIIgCIIgCKK0QQY1QRAEQRAEQRQAMqgJgiAIgiAIogCUqKREgiAIgpBCbGwsXr16hY4dOyIjIwM5OTkwNjYutPNnZWXh5cuXAIAGDRqgTJkyatsaGhoqHUtKSkKVKlUE3/Pp0ye8evUKmZmZ3LG2bdsWqM9fElLGXyq6Hvtbt27h1atX6N+/PxITE5GamgoLC4tCOz9RsviiDOoPHz4o3Ri1a9culPPevXsXgYGBeP78ObKzsyGXy2FkZIQ7d+4UyvkV+fTpE968eYNmzZoV+rmlsGfPHgwdOlTjMRaGYXDy5EnExMTA29sbcXFxeP/+PVq2bKnSNjExEb/88guePn2q9Hvt3btXbZ90PfmlpKQgJyeH+1vdQ1AbpDwYoqOjUbNmTRgaGuL69et4/Pgx+vbti0qVKgm+R+r46Go8P378iKpVqxb4PEJIuda0QZuxj4+PR2xsLORyOXfsSzKKdu3apfb14cOHq31dV9fmkSNHcPjwYXz69AkXLlzA27dvMW/ePOzZs4f3vK6urujfvz9cXFxQuXJltX0GgOvXr2P27NkwNzcHwzB48+YNli9fLth3b29vbNy4kbu3ExISMG7cOBw/fpy3/dGjR7F37168ffsWzZo1w99//43WrVurnQv/++8/PH36FFlZWdyxvn37CrZ/9OgRbt26BQCwsbEp9meLFMSMf69evdSeIywsjPe4rsc+KCgI9+/fx4sXL9C/f39kZ2fDx8cHhw4d4m2/YsUKjB8/HmXLlsWoUaPw+PFj+Pr6ok+fPkrtAgMDIZPJBPs4Z84cwdekMHToUJX7iO+YIrp8Rr98+RKrV69WsRsuXrwo+J6inpe/CIP64sWLWL58ORISElCtWjXExcWhUaNGiIiI4G0v1UBeuHAh1qxZg8mTJyM4OBghISGcYcRHZmYmjh07hidPnij98EuXLuVt7+npic2bNyMnJweurq4wMTFBmzZt4OvrK/gZUi+u5ORkbNiwgZtYbW1tMWHCBFSsWJG3fUhIiIrxfOLECUGDev78+dDT08O1a9fg7e2NChUqYOLEiQgODlZpO2PGDDg6OiIyMhILFizAiRMnUK1aNcHvCkif/KRMfIcOHcKGDRtQtmxZ7phMJuMdy8WLF8Pf3x/jxo3jPdeWLVt4j0t9MLNj9+rVKwQEBMDBwQHTp0/HL7/8wtte6vhIbS92sgcAd3d3NGvWDP3794ednZ3ayZ8lMjJS5X7x9vbmbSv2WtP2wSN17FeuXInTp0+jUaNG0NfX544L/bZiF5RSr7XQ0FD06dNH0PgVMnrFzFepqam87xWDLq/N/fv34+jRoxg4cCAAoH79+khMTBTsy5o1a3D8+HEMGDAAlpaWcHV1xffffy94nSxfvhw7duxAw4YNAQAvXrzA9OnTBQ3krl27YsqUKVi/fj3evHkDLy8vzJo1S7A/e/fuxbFjxzBw4ED8+uuvePbsGdasWSPYPigoCNevX8ezZ89gb2+P33//HdbW1oJz2549e3D06FF069YNAODj44OBAwfC09OTt71UZ0diYiKOHDmC2NhYJWeE0LMOkPb8FTP+7H2wf/9+AODmJCFDWvE76XLsz58/j5CQEPTr1w9AXuE6dffRlStXMHPmTJw/fx7m5uYICgrCzz//rDLHWlpaqv1e6rh9+zaCgoIQFxeHnJwcMAyj8qzLzMxEeno6Pn78iE+fPoEVgktJSUF8fLzguaXe5+fOncOqVavw4cMHMAzD9UXIDvP19cWkSZOwZMkS7N27F8ePH0dubq5gf6TOy1ZWVirzQMWKFWFpaYnZs2eL2ln4IgzqdevW4fDhwxg+fDhCQkJw7do1nDx5UrC9VAMZAOrVqwe5XA59fX30798fffv2xfTp03nb+vj4oGHDhvjzzz8xYcIEhIWFcRMCH8nJyTA2NsbRo0fRt29fTJo0SeOqW+rF5efnhyZNmmDdunUA8h6+vr6+CAoKUmoXHh6O8PBwvH79WulBnpqaqtajc+/ePZw4cYKbXCpXrozs7GzetklJSXBzc8PevXtha2sLW1tb9O/fX+33lTL5SZ34du7cibCwMI1GPfC/yXrEiBEa2yoi9cGsp6cHAwMDnD9/Hh4eHvD09FTrhZL6cJDaXuxkDwBnz57FX3/9heDgYCxatAiOjo7o168fGjRowHvugIAAZGRk4Pr163Bzc8PZs2fRokULwb6IvdbYB8+dO3fw9OlTODk5AQDOnDmDRo0aCZ5f6thfuHABZ86cUdnqF0LsglLqtZaeng5AuvErZr4SWtyIQZfXpqGhodK4Kxp1fNSrVw9Tp07F5MmTcenSJfj5+UFfXx+urq4YMmSIyq5Udna20lg0aNBAcF4DgIEDByI7OxsTJkxAbGwsFixYgDZt2gi2NzQ05BbyWVlZaNSoEV68eCHY/uzZswgNDUXfvn2xdOlSvH//Hj4+PoLtjx07hiNHjqB8+fIAgNGjR8Pd3V3QoJbq7Bg/fjysra3RoUMHJaNFHVKev2LG39zcHADw119/ISQkhDv+zTffoF+/fpgxYwbvuXU99mXKlIFMJuOMtLS0NMG2ADgvamRkJHr27Cno7GINdEVyc3ORlpamMdTJ398fvr6+sLS0hJ4efwrdoUOHsGfPHiQkJMDV1ZUzqI2NjeHh4SF4bqn3+cqVK7Flyxa1c7EimZmZ6NChA4C833zixIlwdXXF5MmTedtLnZeHDh2KmjVrwsXFBQAQERGB6OhoNG/eHH5+fvj11181nuOLMKgNDAxQtWpV5ObmIjc3F+3bt8eSJUvUvkeKgWxkZISsrCx8++23WLFiBUxNTdUar9HR0Vi/fj0uXryIfv36wcXFBT///LNge7lcjoSEBJw+fRpTpkwR9Z2lXlzR0dHYsGED97e3tzevMWRlZYUaNWrg48ePSg/yChUq4JtvvhHsj4GBAeRyOTd5JCYmCt6wBgZ5l52pqSkiIyNhamqKT58+qf2+UiY/qROfhYUFjIyM1H4+C2uk2draimrPIvXBbGBggPDwcISEhGDz5s0A1BsLUh8OUtuLneyBPO9+p06d0KlTJ1y7dg0+Pj44cOAAmjVrhunTp8PKykqpfVRUFMLCwtCrVy94e3tj+PDhGD16tOD5xV5r7IPn4MGDOHDgAHfdDRo0SO39KHXsLSwskJ2dLXriFrugVLzWsrKy8Pz5c8hkMjRo0ID3swYNGgS5XA5jY2MMGzZMVF8AafOVlJ0KFl1em23btsWWLVuQkZGBK1eu4MCBAxqr6z569AjHjx/H5cuX0aNHD/Tq1Qu3b9/G0KFDERoaqtTW0tIS/v7+6N27N4A8ryefh1BxV4BhGMTFxXFeur///ltwd6BmzZr4/PkzunbtiuHDh6NSpUpqQxXLli3LLfhSUlJgYmKCN2/eqP2+ioauJqNXqrMjPT1d7dwqhNjnr9jxB/LG/fbt27C2tgaQt5BW95zW9dg7OjoiICAAnz9/xpEjRxAcHMztpPDRuXNn9OzZE+XKlcP8+fORmJiotGuan+nTp2PBggXQ09PDgAEDkJKSgiFDhmDUqFGC76lYsSLs7e0FXwfyDMuhQ4fi119/FVx48SH1PjcxMRFtTLPnz83NRb169bBv3z6NHn+p8/Jvv/2m5Ih1d3dHnz594OPjI7jznJ8vwqCuVKkSUlNT0bZtW8yYMQPVqlXjVuR8SDWQV6xYAYZhEBAQgN27d+PNmzdKxml+2Ad3pUqV8N9//6F69er48OGDYPvx48dj5MiRsLa2RsuWLRETE4P69eur/c5SL65y5crh1q1bsLGxAZC39VOuXDmVdubm5jA3N8fhw4fVfn5+PD09MWHCBHz48AFr1qzBmTNnBBcHXl5eSE5OxqxZsxAYGIjU1FS14S2AtMlP6sQ3ffp0DBo0CK1atVK6+fhCAiZPnox169YJ7iAIbTNKeTAAeVumhw4dwrhx42BhYYGYmBjuvXxIfThIbS9lsv/48SNOnjyJ0NBQVK9eHXPnzoWDgwP+/fdfTJ48Gb/99ptSe/Y6NDIyQnx8PKpWrYp3794J9kXKtQbkxfWlpKRw3se0tDS1CzipY29kZIS+ffuiQ4cOGq8fQPqCMjIyEvPmzUPdunXBMAxev36NBQsW8D4Y9fX1ER4eLsmgljJfSdmpYNHltenj44OjR4+iadOmOHz4MOzt7eHm5iZ4bldXV1SsWBEDBgzAjBkzuN+rVatWvFvNCxYswP79+znvlI2NDX766SeVdvnn3u7du/Mez8/GjRsB5IUZtWvXDsnJyfjhhx8E21taWuLz589wc3ODq6srypcvr7JAzf993dzcuJCPCxcuqDWQpV6bnTt3xuXLlzUaaYpIef6KHX8gL0TKz88PKSkpYBgGlSpVUutY0/XYjxw5EleuXEGFChXw4sULTJo0CZ06dRJsP2PGDIwaNQoVK1aEvr4+jIyMsGnTJsH2T58+hbGxMU6ePAk7OztMnz4drq6uvAb1gwcPAADt2rXD8uXL0b17d6W5qnnz5irv8fT0xJ07d1RikIV266Te55aWlpgyZQq6du2q1Bf23smPn58f0tPTMWfOHKxbtw7Xrl3D8uXLBc8vdV42MjLCqVOn0LNnTwB5O5nsM05M2CLwhVRKTEtLQ9myZcEwDMLCwpCcnIxevXoJJkbFxsaievXqyM7Oxu7du5GcnIyff/4ZdevWFfwMKQllR48eRffu3TnvTVpaGiZNmoTBgwcX6Hsqcu/ePTRq1AjJyclYt24dkpOTMWrUKLRu3Zq3/b///otZs2Zxk03lypWxbNkywQQVxXii7Oxs5OTkCMa55ebm4u7du6hcuTKuXbsGhmHQoUMHSatPKdy4cYOb/PhWn/Pnz8e0adMQERGBXbt2oXz58vj2228F4/oGDBgAa2trNG3aVMnTybe1lpCQAFNTU8TGxvKei91+zE9WVhb279+P27dvA/jfg0Hs6lkKmsZH2/ZJSUncZJ+eno6UlBTUqFFDpV2PHj3Qu3dv9O/fHzVr1lR6bdu2bRgzZozSsY0bN8LT0xNXr17FwoULIZPJMGDAALVG8rNnz0Rfa8HBwQgKCkK7du3AMAxu3ryJiRMn8v6+gPSE3BMnTvAeFzr/pUuXYGNjgzdv3nALSm9vb0HPas+ePbF161bUq1cPQJ5HecyYMThz5gxv+yVLliAnJwdOTk5KOy98D01A2nzl4uKC8PBw+Pv7o0ePHrCzs0Pv3r3Vhtgpwl5rdnZ2otQa1F2bcrkczs7OguPAR0xMjCSVBfbZwnp25XI5srKyeHe05HI5Vq1apTZmmg+5XI73798rGS1iEupfv36NlJQUjUmGDx48UJp3vvvuO8G2fNfmhAkT8OOPP/K2t7KyQnp6OsqUKcMZ4+riYIG856+JiQlycnK45+9PP/3EXd+KSBl/luTkZABQu4vGouuxV1SgSU9P53aQhJCS++Ps7IyQkBBMnz4dHh4esLW1FbwX1XmaZTIZb5yzj48PYmJi0KxZM278ZTKZqKRHMc8UISeauvh7KUidl2NiYrB48WJERUVBJpOhdevW8PX1hZmZGe7fv885I9XxRRjULGJVGvhW1AcPHhQ0eKUmlElFahJjQUhJSQEASbJSDMPg4sWLuHv3rmA8Wt++fZXi1/j45ZdfMHr0aMFkMb4bNSkpSe05NSlxiJn4xPS9qNDWAw5IezisXbsWbdu2hZWVldrdHEXETvaHDx+Gu7u70rFVq1YJXjuKZGVlITMzU+PDUOqD8N27d/j7778B5Hkj+RYCLP369VOZjAvzGlHcllZ3jKV///5KCZcMw2DAgAG8Cb8A/8NT6KEplVWrVuHChQsoV64cjh49iuTkZIwdOxZHjx4VfM+6deuUQtHkcjlmzpyJ//u//1Nqp8297uXlhblz54pWdHr//j1Wr16NhIQEbN++HU+fPkVUVJSgV3vgwIHYtWsXKlSoACDP4zxy5EhBpQZ3d3dJu3u//vorgoKCUL16daXFvNB9LlZ5ISUlBcbGxoJjWtgKRrpCyvhnZWXh7NmzKgmSQvH/uhp7lvwKNC9fvlSrQCOU+7N+/Xre9nv37sUvv/yCZs2aYdu2bYiLi+PC6woDR0dHnDp1SqN3VtfXmrZCAMXBFxHyoajSIJPJeDNXFdm8eTMMDQ25GOTt27fj2rVrgga11IQyqTe2lCRGqRdXQeWugLyHcdeuXREUFCRoFHXo0AFnz55F9+7dBW9A1osoJUvZ1dWV+03fvHnDSZd9/vwZtWrVUgofePbsGRo1asRtbyny4MEDQQ+dnZ0dDh8+jC5duiitptVNBFKVYvJnV7Pkv0b9/f0BSJ8kpD4cLCwsEB4ejkWLFqFChQqwsbGBjY0NunbtytteSqLnhQsXYGRkxIVJLFiwQGmhyIeUrUWp3xXI20WpVq0a5HI5Xr58iZcvX6osiLVNyJWquLNo0SIVg53vGIulpSVGjx4NR0dHyGQynDlzBi1atMC5c+cAqG6RikmeUUTKfCV1WxoA3r59i61bt2Ls2LHIysrC5MmTeb2kUu51ls+fP8PZ2RktW7ZU8loK3T+zZ8+Gq6sr93r9+vUxdepUQYM6MzOTM+aAvFwSNvmTj2bNmmHcuHHo2bOn0kJVaBt77969OHPmjEaZSanKC9OnT8fWrVu5MWXR9GyMiYnBvn37VK4FdfPRxYsXldSjunTpwttOG2eBlPH38vJCxYoV0bx5c1E7c7oaexapCjRSc3+GDBmCIUOGcH+bm5uLWjSLVVRq0qQJ3r17B1NTU7Xny3+tKfpo1V1rb9++RWBgIPfMtLGxgb+/v8quptTkbG2dUtoo1uTnizCopag0AMCmTZswbtw4lClTBn/88QeeP3+u9qEgNaFM6o0tJSlI6sXFxvC9ePEC//zzD7etfOnSJbVKCuzDGsgzRu7fv682QeLQoUPYtWsXDAwMYGhoyCuBw342u+UixlvOPkTnzJmDbt26cTsLly9fVrlRd+/ejcDAQCxbtkzlPOo8dOHh4QCArVu3KrVXp28pVSlGTHY1AG7yMjc3x/v37/HPP/8AAFq2bAkTExPB94l9OLD0798f/fv3x7t373D69Gns3LkThw8fRlRUFG97KZP9hg0b4OXlBT09Pfzxxx+oWLGi2lhGoa1FIYNa6ndl5ZMaN26sNPb5DWptE3LFKu5ERUUhKioKiYmJSgvdlJQUpYVEfrKyslC9enXcvHkTAFCtWjVkZmbi0qVLAFSNtfzKPSxCC3ox85XifMCHkMEI5IWgzJgxA1u3bsX169dhZ2fHG+Mt5V5nEUrCFuLjx49wcnLCtm3bAOTFDKu7H42MjJQW4/fv3+fNPWHJyspC1apVcf36daXjQuNTs2ZNUaEJisoLilvWQsoL7FzGtwhRx4QJEzBgwAB06dJF7biwrFq1Cv/88w9nvOzduxd37tzhTTDUxlkgZfzj4+OxY8cO0efW1dizSFWgEZv7UxAnmRRFpY8fP3KLVcXwrPy/n7bXmq+vL1xcXDjlsZMnT8LX11fl+0kVAtDWKaWNYk1+vgiDWopKA5D3QNq8eTOGDRsGS0tLrF+/Xu22htSEMqk3tpSkIKkXF/sQ/fnnn3H8+HHOePX29sbYsWMF38c+rIG8RCdzc3O1iw4hQ4yPf/75B35+fkhNTQXDMJzBpW5M//77byxatIj7297eHqtWrVJqExgYCEC6h07qRMAiRSlGTHa1IqdOncLKlStha2sLhmEQGBiImTNncgkT+RH7cGDx9/fHs2fPYGJiAhsbG6xfv15tbKWYyV5xy2/RokWYMGEC2rRpA29vb7XV4u7fvy9qa5FF6ncVK5/EJuTa2Nio3F8rV64UXECIVdzJzs5GWloa5HK5UrKasbGx4LYuID30S9EzmpmZicjISLWynWLmK8X5gA8+g1Fxp2jIkCEICAhAmzZt0LZtW7U7RmLudRapajvly5fHx48fuWvt7t27aq8lPz8/TJ48GaampmAYBu/fv1crBSb1t7KwsICnpyc6d+6sdH3mN4q0VV4ApBW3KFu2rJLXUxOXL19GaGgoZ3z369dPcB5UdBaIRcr4W1lZ4fHjx2oXv4roeuylKtCITXosiCa8FEWliRMnSj6/lGstMTFRKUHW1dVVbdEYMRrawP+us6pVq6JcuXLQ09PDixcv8Pz5c9jZ2QmeX1vFGkW+CINarEoDm2jH/hDZ2dl4/fo1zpw5ozaRQkqmMfs5Um5sd3d3fPr0CVOmTIGXlxeXFKQOsRcXy/v375XGxtDQEO/fvxc8vzbx22KrJPn5+WHevHlckP+tW7fg6+urdsve1NQUmzZtUlrUCG1F8XnTKlasiKZNmwp6eaVWHxObqa5NdjWQt7o+duwY19/ExEQMGzZM0KAW+3BgSUpKglwuR6VKlVC5cmVUrVqVW9jxIWayV9zyY/8fGRmJyMhItdem2K1Fbb+rVPmkv/76S+XY77//LjjZilXcYWXI+vXrB3Nzc66N4pY2H2yyzN27d7lkGT8/P8Hkuvy7VyNHjsTIkSMFzy9mvtJmPsi/U1SpUiU8ffoUy5YtU7tjJOZeHzx4MA4ePKhSjEFTcYjZs2fDy8sL0dHRGDRoED5+/Mh5yPho2bIlTp8+zcl/aUpIF7uNzVK7dm3Url0b2dnZanc9Wdzd3bF3716lEAt3d3fBPkktbjFkyBAEBQWhU6dOouYpIC/shl0sswmB6pBS0EPK+N++fRsnTpyAubm5Ut+Fniu6HvsZM2bg2LFjohVo5s+fDyDv2v7hhx8Ec38KogkvRVHJ1tZW0i6p1GutSpUqCA0N5XSfw8PD1YZZit3lZfHw8MD+/fvx+fNnjBw5EpaWljh16pRK7gaLNoo1+fkikhKlqDQUBU5OToiOjhZ9Y2tDz549eS8uoW3wzZs34/Tp00rySY6OjoKx2LNmzYK/vz8Xx/jp0ycsW7ZM8MEqpUoSX4IXXyKYIklJSQgKClIqoevt7c17A44ZMwZ3795Fu3btAORlHDdv3hyvX7/G+PHjVQxlqckgAL9SDF+mujbZ1UBeOV3F6yU3Nxd9+vQRvIakbvOzPHv2DH/88Qf27NkDuVyO33//XW17QHyGu1g8PT3x6NEjjVuLLFK/68SJE/Ho0SON8kkHDhzAwYMHER0draT4k5qaijZt2gh6SaUq7vz333+YOXMmJ0dWtWpVLFu2DE2bNuVtP3DgQPz0009KBQf27dunNhFQkU+fPmHAgAE4f/487+tFMV9JQcq9rg05OTl48eIFGIYRNNCuXr2KDh06CIa6CIVwDB8+HC4uLlxo3smTJxEWFqZxm14s/v7+yMnJ4eawkydPQk9PD4sXL+Zt36NHD4SFhYleTP7f//0fQkNDUbduXW6hoilc7v/+7/+UFHRmzJjBFVHio1u3bhoLemgz/lKVl6QidewVSUpK4p6NQhw9elTJ4JbL5di8eXOBDOj8SFFUyr9LeuvWLbW7pFKvtdjYWAQGBnKOAisrK8ydOxe1atXibe/m5iZ6zgP+Z1P8+uuvyMjIwOjRo9GnTx8VrXkWVrHG0NAQBgYGGhfnfHwRHuqcnByNOsaK3L59G99++y3Kly+P0NBQPHz4EEOHDhXMFL906RLWrVun4g0WGmihEsVC7NmzB/3790eFChUwZ84cPHz4ENOnT8f3338v+B6pIQReXl744YcfOPmkpUuXqt3if/z4MWdMA3nV6P7991/B9mKqJLHe2rZt2yIgIADOzs6QyWQ4deqUxq3bKlWqiJLrAfImolOnTqF69eoA8rzzs2bNwpEjR+Dh4aFiUEtNBgHy4t5NTExgbGysdsKTGn7C8v3332PkyJFwdnYGkDe5qduukjrpXrp0Cbdu3cKtW7fw+fNntG/fXlBlAlC+Z27fvo2HDx9iyJAhvA+r/fv3o1evXkqLsfDwcMG8AKlbi1K/q4ODg8ZiH0DeIsbOzg6rV69W2rKuUKGCWmOuZcuWXDsxntyAgADMnj0b7du3B5CnIhQQECCoHJGenq50zfbp00dtiIZiMk5ubi4SExMxYcIEwfZS5yupSJ3fpNzrgDTFl9OnT+OHH35AkyZNsGnTJjx8+BBeXl4qHtibN2+iQ4cOgqEuQga12G1sbZUL/vnnHyVZtA4dOqjVSJe6O3PmzBlcuHBBdHsXFxfY2tpyXswZM2aoVdABxBX00Gb82bnow4cPapOgi2rsPT09sXnzZuTk5MDV1RUmJiawsrKCn58fb/tr167h3LlzWLx4MT59+oTZs2dLDmnSxOjRo2FoaIgePXqgS5cuyMzMFMyN0maXVMq19vbtW5Wxvn37tqBBLXWXl2EYLsSFXfSoqzciJWxViC/CoJaq0jB//nycPHkSjx49wq5du+Dm5oaZM2di3759vO2XLFmCDRs24JtvvhEV52lubo5Hjx4peVjUrUyDg4MxdOhQ/PHHH0hKSsKKFSswc+ZMtQa11IsLyNu2r1WrFjfZxMXFCT54cnNz8enTJ07dgA0REEJMlaT8W8CKnkahcdVm8nvz5g1nTAPg4n2rVKnCG9agTfWxkJAQzJ8/H5UrV4a1tTXatm0La2trtWoQYrOrgbwdgrNnz3KLNnd3d253gY/ExET88ssvKkoTQp6lP/74AzY2NhgyZAjMzMzUfleA/56ZNWsW7z1z5MgRJeO5cuXKOHr0qKBBLfahoe2DUOxOVcWKFVGxYkWsXr0at27dwqtXr9C/f38kJiaq1S/m60/FihVhaWmJQYMGqTyw0tLSOGMayLuX1ZUltrOzw7Zt2+Dk5MQtQO3t7bmY9fzznOI4GBgYwMTERG04j1hDRFukzm9SrmWpii+bNm2Co6Mjbt26hatXr2LkyJGYP3++iueLDbmTGuoidhtbanI5i76+vtIOSkxMDG8CFStNKrW4RZMmTZCcnKx2a18R1knChrQkJCQgPT0dtWvXFrzmxBT00Gb8L168iOXLlyMhIQHVqlVDXFwcGjVqhIiICKV2uh57luTkZBgbG+Po0aPo27cvJk2aJKg8AeTtDpw6dQq9evVC+fLlsWrVKrVODm1wd3fndoLZpEmh3WGGYZSugypVqkBdQIPUa02q2hEre3r//n3umLrdE39/f2zduhVdu3ZFkyZNEBMTw+1aK6JOHQxQb1Pl54swqKWqNBgYGEAmk+HChQv4+eef4ebmhmPHjgmev2bNmmjatKnopKk9e/bg6NGjnAHk4+ODgQMHCm7/sxfp5cuX0bdvXzRp0kTthQtIv7jyTzZv3rxBw4YNVSYblhEjRsDd3R09e/YEwzA4e/asoCEDiKuSpI23VpvJz9bWFmPHjuVW0mfPnoWtrS3S0tJ4E5CkVsACwFVoio+Px9mzZ7Fw4UIkJCTg4cOHvO2lZFez9OjRAz169BDzlTFjxgw4OjoiMjISCxYswIkTJ9Sq3gQEBHDxcQ8fPtQYHyflnsnNzeV2cYA8D6K6GEWxEoTaPgilytoFBQXh/v37ePHiBfr374/s7Gz4+PgIepDr1KnDZcQDebsJFSpUwMuXLzFnzhysXLlSqb2FhQU2btyoFBagrtjI6dOnAUDl8yMiInjnOakLerGGCIvUfAOp85uUa1mq4gtrAF2+fBkDBw5E586dsXbtWsH2Pj4+CAgI4OaN2NhY+Pn5qXid582bBx8fHyxZsgSBgYFYunQpt43NZxRKTS5nmTlzJoYMGQILCwuuxDmfgg57/kaNGsHW1hYymQz6+vpqFUqAPCPQ0dERLVq0EBV+tWDBAjx8+JALV/rvv/84o3z+/Pm8i6bU1FQYGRnhypUrSsfze53lcjk+ffrE/fZZWVk4ceIEdu/ezd0Tiqxbtw6HDx/G8OHDERISgmvXrvEWOdH12Cv2PyEhAadPn1ZbpIrl5cuX2Lt3L3r06IFnz54hNDQU3333naDgghS5y3fv3iE+Ph4ZGRlKhmNKSoqgDCHfLqm6SpJidwK1VTuSaj+0bdtWKX7bwsKC17jXVh2Mjy/CoJaq0lChQgVs3boVYWFh2LdvH3Jzc9VK2vj4+GD06NGwtbUVlQR17NgxHDlyhMu2Hz16NNzd3QUNaktLS4wYMQKvX7/G9OnTkZKSojboXi6X48cff5RUXljsZMPSt29fWFpa4tq1awDyjIzGjRsLtpdSxvXz588ICQlRyQbmu9gtLS0hl8tx+PBhwWSC/MyfPx9nz57lwlv69u2LHj16QCaT8d6UYpNBFAkNDcXt27fx33//oUqVKvj555/VVlKSkl0NSEvcAfJ2ENzc3LB3714u+U1dieHTp09jxYoVolVEpNwz33//PaZMmYJBgwYByDME1U3EYiUItX0QipW1Yzl//jxCQkI4z7ZQkiFLVFSUUpEVBwcHrhgL+zBShN3xYkNdbGxs1D6Ypc5vUhf0UuYGKXrkLFLnNynXslTFFzMzMwQEBODKlSsYPXo0srKy1F4L1tbWcHNzg6+vL6eGwlcJ0cLCAq6urpg4caIouS51nkpA2MNep04dnDt3Ds+fPwcANGzYEI8ePVJp5+LigjVr1iA4OJgrSBYXFwdXV1dMmzZN8HOlhl+Zmppi8eLFaNKkCYC8ctjr16+Hj48PvL29eQ1qMV7niIgIBAQEwMjICPXr18e4cePg5+eHFi1aCOYyGBgYoGrVqsjNzUVubi7at2/Pe1/peuxZxo8fj5EjR8La2hotW7ZETEwM6tevL9h+3LhxCAgIQMeOHcEwDHbt2oUBAwYILmylyPP++eefOH78ON6+fatUrrtChQqC14PUXVKxO4FS1Y5CQ0PRp08fwTwEITvsxYsX2Llzp8qCI7+BrK06GB9fhEENSPOarFmzBuHh4Vi8eDFq1KiBuLg4tVnwa9euRfny5ZGZmSkqGxiA0laQJk3DxYsX499//+Xk/z5+/Kj2Aauvr4/w8HBJBrXYyUax6lH16tW5rUsAaqXPFCvvaTJ4xowZg1atWqkkkQqhr6+PuLg4ZGVlaZw4FMsRi/Xusvq++Y+pq4S5ZMkS1K1bF4MGDUK7du1Qp04dtZ8hJbsayMuY1pS4owi7vWpqaorIyEiYmppySW98bN68WVJ8nJR7hvXmHjx4EADQsWNHtdntgDQJQqkeZ7GydixlypSBTCbjPOzqwjHY1xXDp+Li4rj38CW8Va5cmVs8yuVypKen82qxa5sYJ3VBL3ZuALTLN5A6v4m5ltmHq1TFl7Vr1+KPP/7AiBEjUKlSJSQkJGDmzJmCfRk0aBAaN26MoUOHomrVqjhx4gRvjPCoUaPQq1cvLF26FMHBwRg0aJDS3Jb/t9K2utvkyZOxefNmbsF/8+ZNLFy4UMUIXLlyJdLS0nDx4kXu2kpJScHy5cuxYsUKTqs3P1KVHV6+fMkZ0wDQuHFjPH/+XO2Oi5jKwJs3b8bx48dRr149PHjwAO7u7li/fr1aD2ilSpWQmpqKtm3bYsaMGahWrRpvFVhdjz2Lo6MjHB0dub8tLCywYcMGwfMfO3aM+61kMhlGjBghWCQHkCbP+/HjR3Tp0oU7n0wmQ9WqVWFtba32t+rRowc6derEGaR8NoDUQir51Y40wXrQpcoFTp48GYMGDYKbm5soO0MulyMyMlLF0Sem+B3LF2FQS/Wa1KhRQ2mQateurdbDkpCQwIWViMHV1RVubm5KihrqvIV6enqoXr06nj59qnbLQ5E2bdpg4cKFcHJyUtoSEor3ETvZaFthS0rlvczMTElJpOz5Bw8eDAcHB6V+57/Y9fX10aBBA7Xx4flRnJQyMzNx7949NG/eXO1Wz/Xr1/HkyRPcvHkTa9aswatXr9CgQQOV7X2Wzp07c/I97NgOGDBA8PxiEncU8fLyQnJyMmbNmoXAwECkpqaqHWOp8XFS7hk9PT389NNPaqUlFRErQcgi1eMsVtaOxdHREQEBAfj8+TOOHDmC4OBgrtoZH7Nnz8ZPP/3EPZhev36NefPmIS0tjXeMpk+fjgULFkBPTw8DBgxASkoKhgwZglGjRim10zYxDpC2oBc7NwDa5Rvo6emhTp06ePnypagYbTHXMvv7SZE+k8vl6NevH86cOcMdMzU1VSvXGBISgs2bN2P58uV4/PgxxowZg6VLl/LuYJmZmaFz585Ys2YNLl26pNagVjQkpBiw8+fPx/jx47F161Y8ePAA//d//8cVqVEkMjISZ8+eVZrDjY2NMX/+fDg6Ogoa1FL17xs3box58+YphQU0atQIWVlZgjHUYioDlylThlNMat68OerXr68xnGDTpk0oW7YsJ8GanJzMm4yr67FnWbFiBcaPH4+yZcti1KhRePz4MXx9fblQr/xkZGRgyZIlnKH89OlTREVFoUGDBrztpcjz8jkFYmNjsWXLFkycOJF3J01sBWptC6mwnmFF+HJP2J1OqcnoBgYGop9BQN4OQdmyZUU7+vj4ImTzevXqxXlNTp48yXlNhLYI+GI2WfUCPlasWIGOHTuqTRLMz4MHD7jz2djYqFXUENJvVHeB8nmb1MX7pKWloVy5csjNzeUmm169eomOPRSLYuW9T58+8WbO7t69G+XLl1fxKqlTUpAilfbzzz9zccFiyhHn582bN9y2vBApKSm4ffs2bt68iVu3buHjx49o3bq10naaEFlZWcjMzFS7Vb1o0SK8f/9ebeJOQVi+fDn+++8/pQfhN998I+htlBKC4uDgwJtvILQYi42NhYmJCXJyctRKELK4urri+PHjStKC7DE+pMraAcCVK1fw559/AsgLYenUqZNgWyDvN2W3ghs0aKC2qigr3XTy5ElO8cLV1bXQZOp27dqFEydOoFu3bmAYhqvAKrSjxTc39O7dm/d+nD9/PqZNm4aIiAjs2rUL5cuXx7fffqt2G1+KpCaQt1situqtIrm5uUhLS1NbedXLywtz584VvdgeP348AgMDOUPr3r17mDt3ror01pMnTzB//nyYmprC19dXtKa6VGkyIC/EKCAgAGXLlsW2bdt4x6pHjx44e/Ys7/vVvda7d2/s2rVLZedKKAQoIyMDBw4c4J51bdq0wU8//YSyZcsiPT2dV2OdlU1l79/s7Gz8/PPPOHLkCNfGzs5OaQG/a9cupb+leA2F0NXYs7D3+fnz53Hp0iX4+vri559/FhzLUaNGwdXVFVu2bMHJkyeRk5ODfv36Cc4LhSF3mZSUhOHDh/MmAnbv3h2HDh3S6l4Uw6JFi1RyT4yNjSGTyZCSkqLinFIs9sRibGwMS0tLXsfdhg0bUK1aNXTr1k2UnZFfqlYbvggPtVSvidSy0QcPHsTOnTtF6xP6+fnB09NTqeKUYsxkfsRWclNESryPXC7H2LFj8euvv0JPT09UrNPQoUNVEm/4jrFIqbxXpkwZrFixQsnA1VTqmzWcxRTDkFqOOD81a9bEs2fP1LYZPHgwrK2tYW1tDQ8PD8HCDdqWbBabuPPLL79g9OjRXFZ/foQyrKXGx0kJQVGMJ87KysLp06fVhp8oeozEeCGkepylytqxKhydOnXC8+fP8eLFC2RnZ6uEbwiFZERHRwMQ/m1zcnKQnZ2NCxcuwMPDgwsxEUKq7Nzw4cNha2srWiJz48aN8PHxUZobhCpDapNvIEZSU5HBgwfD3Nwcjo6O6N69u1rlHLHefpbPnz9z5ZTFLLbZ6rDp6ekwMjJCy5YtebVwJ02aBH9/f0lOF/ZzxYRe5U8Iz8jIQMWKFTkJtvz9b9SoEUJCQlR2SEJDQwU9noD0naty5crhp59+QufOnVW8zEJztJjKwAMHDlS6p/P/rUj+gm2K30Xdc1pXY8/C7jZHRkaiZ8+egg6UnJwcGBgY4OPHj3BycuK83gYGBmo9pYUhd6nu95VagTp/kSXgfx7n2bNnq4SWSM09yczMxPPnz7nf59y5c6hTpw4ePXqE69evq+y6sIsExR1odXaGnZ0d/vzzT8n3sCJfhEGtjUqDlJhNqfqEf/75J+7fv48RI0ZwE9pvv/0maFBL1W8E8rKxg4KCuPhfW1tbTJgwgfem1dfXh56eHpKTkzUm8GRmZiI9PR0fP37Ep0+fuJstJSUF8fHxgu+TUnlv586dOHfunKSVL18xjOXLlyvF77FIjQNUNEZzc3Px8OFDtQYIIN4LwG7Xf/jwAVFRUUraw1ZWVoJGl1i5KNbAVVe2XQgpKiJSQlDy73oMGzaMN2ZZauwdi5+fH9LT0zFnzhysW7cO165d490ZUKdKAwg/CBUrbI0aNUqwwpa2IRnu7u5wcHBAs2bN0LZtW8TGxqr1qkqVnYuOjkaTJk3QvHlzXLt2Dbdu3UKdOnWUdOUVkVoZMn95YU35BmIkNRU5e/Ys7t27h4iICGzZsgWNGzeGk5MT71b506dPYWxsjJMnT8LOzo7z9gsZ1FIX21FRUfD390daWhoiIyPx6NEjHDp0iFtYsISGhkqav1nEGrBSlW3mzZsHb29vBAcHc2GA9+/fR0ZGBpdAzodU/fuLFy9ixYoVyM7Oxm+//YZ///0X69atU7sbyFYGnjx5MlcZOP/vImV7X1v9YF2NPUvnzp3Rs2dPlCtXDvPnz0diYiLvzpWbmxtOnDiB8uXL4+PHj9yz6O7du7zPazbPSVOFVTFcu3ZNcF4QW4GaZejQoahZs6ZSAaro6Gg0b94cfn5+Kk5Aqbknjx8/xsGDB7ld/MGDB+Pnn3/GgQMHeJ8hUpO5W7duDW9vb+Tm5n7dhV2kek2kxmwC4stqA3nGx969e+Hj44O///4b/v7+harfCOQZFU2aNOHK5oaGhsLX11cwNKJ8+fLo1asXOnbsqBQfmf8zDh06hD179iAhIQGurq5cv42NjeHh4SHYH3aSZivvDRkyRLDyXr169SStfAH+Yhhz587llTKTGgfIGqOstJSLiwvatGmjtj9itXJZw3jEiBGIiIjgtoITEhJ4Y5ylepzZuEKxGdZ8XgRAszdHjHYsi6IsU25uLu7fv8+rCKJt7J1Yj7O2D0KGYWBkZIRjx45h8ODBXIWt/GirVTxkyBCl3Stzc3O18fpSZecmTpyI4OBgvHr1CvPmzYODgwOmT5+u4tFiK0PGxMQoPZDYypB8SC0vDIiT1MxPy5Yt0bJlS4wdOxbLli3D7NmzeX8Dqd5+W1tbxMbG4tWrV+jYsSPS09PV5q0sWbIEO3bsgJeXFwCgWbNmnByhItoY04B4A1aqso2ZmRmOHj2Kq1ev4unTpwAAe3t7LjlXCKk7Vxs3bsSxY8e4EMRvv/1WsGIhi6urK/T19WFra6t2V1Iq0dHRqFmzJgwNDXH9+nU8fvwYffv2FTQYdTX2LDNmzMCoUaNQsWJFTrKQ3fFQhL2XZ8+eDS8vL0RHR2PQoEH4+PEj93xXJH+ek+JcIOSB5TM4P336BFNTU8EwxYCAALRv3150TPFvv/2mFM7i7u6OPn36wMfHh3eOl5p78unTJyXp2/T0dCQlJUFfX5/3/svOzsbBgwdFl4pfunQpDh06JLreCB9fhEEN5Ln/b9++DZlMBmtra7UG9YoVK5Cbm4uAgADs3r0bb968URsvKzUGkGEYVKxYEVu2bMGGDRvg6emJ5ORkwfOL1W9UJDo6WqnP3t7egskOQJ7hIyb+dujQoRg6dCh+/fVXtWWz8yOl8h67gGjXrp3oBYSUYhhit/IuXLiA+Ph4ruDIgAEDkJiYCJlMBh8fH7WxdFJ1n9+8eaMUV1m9enXExcWptJPqcZbqhdXWmyM2BAVQLuBjYGCAOnXq8Gr9suNRtWpVlCtXDnp6enjx4gWeP3/O+2CT+l3ZB+Fvv/2Gzp07i040kVphS4oeLJCXCLV69WokJCRg+/btXPKRkBKKVNk5Nvzt3Llz8PDwgKenJ+8DSpvKkNqEp0mR1ATyPHDnz59HREQEYmJi0LVrV8GSw1K9/UeOHMHhw4fx6dMn7v6fN2+eYCgbAJXKbdomLOWHYRgMGTIE//zzDxeeo8mAFavZztKhQweNRnR+pOxcGRgYSJItBIAff/wRP/zwA5ycnNC+fXutjZf8KC4kAwICBBeSQNGMfXp6Og4cOIA3b94gMDAQCQkJePHihYpyh6Iec7du3WBvbw+GYWBoaIirV6+q2DJsvQ0pHtj8c6NMJkOVKlUEk48B6RWojYyMcOrUKe65eebMGc4jz/cb29vbK8kQKuae8OV7jBo1Cn369FEqcz9u3DikpaXxXuPz589HTk4OBg8eDCBP73/+/PmCpeJr1aolqd4IH1+EQT1//nxER0dzK81Dhw7hr7/+wrx583jbS43ZlBoDqGgcT5w4Ec2bN8fu3bsF24v1LipSrlw53Lp1i9M+vn37tlrR/n79+iErK4uLFW/QoIHgSg3Ie2h8/vxZdPloKZX3unbtyptEoA4pxTDEbuVt375d6XfMzs7G8ePHkZaWBl9fX7UGtVTd5w4dOqh4Qzp27KjSTqrHmfXCnjt3Du/fv+dK4UZERIiudiYGKV7YJUuWqPw2MTExgu0VQyxGjhwpGGJx9+5d1KpVC87OzmjVqpXG4kcsp06dwpIlS9C9e3f0799fY+iKn5+fqApbLFL0YIE8zwybfAQA9evXx9SpUwUN6vyyc0lJSRpl58LDwxEaGorNmzcDAO8OgWJlSMXy3WlpaUhLS+P1IksNT1OUsQTEeft69+6Nrl27YsKECRpD96R6+/fv34+jR49yqi3169dHYmKiYPtatWrhzp07kMlkyM7Oxt69e9VeP1evXoWVlZXGAipAnpExZswYhIWFiU42lpr/IxWp+veNGzdGWFgY5HI5Xr58iV9//VXjb3b69GlcunQJ+/fvh5+fH7p06QInJye1Ov5iYBeS58+fV7uQBIpm7H19fdG8eXPOiWFmZobJkyerGNS5ubm88eEZGRlq+8NX2a9ixYq8VSrFyNPlR2oF6lWrVmHx4sVYsGABZDIZWrdujZUrVyIjIwNz587lfc/9+/e58DFW05vvN8vNzUWjRo1w6NAh3Lt3DwAwdepUztbg04aXWiqeleC0s7MTJcHJxxdhUF+7dg2nT5/mVhb9+vXjDWpXJ+guk8kEs2+lxgCyW8EsmjzQUnV1gbwKVTNnzkRKSgqAvAQPvko/LNevX8fs2bM5kf83b95g+fLlglu1UstHBwQECH52frRZQOQvhmFtbS1oVIit8JSdna3kfbK2tkaVKlVQpUoVwepRLFJ1nwMCAnDu3Dlu+0nIG6KtF3bZsmVKKhcODg5wdXVVey4piNGOZZk0aZJK1vjkyZMFVTjEhlhcuXIFV65cQUREBMLDw2Fvbw8XFxfeOHpFVq1ahZSUFISHh8PX1xcymQyurq5wdnbm9WayCyQWoQpbLFL0YAFITj6KiorCt99+i/LlyyM0NBQPHz5UMiLzw25djhs3DhYWFoiJiVH7INm3bx82bNggqny31PA0bWQsL168CJlMpvEeBPLGcuPGjdzuZJs2bTBhwgRB9SK23DKLuoJeADiPVnx8POzs7NCpUye1c11ISAjmz5+PypUrw9raGm3btoW1tbVgYuV3332He/fucWFMYpCS/yMVqfr3c+fOxZYtW2BoaMglyo4fP17te4yMjODk5AQnJyd8+vQJixcvhqenJ/7991+VtsnJydiwYYPStr1QrhC7kGSlDgH1v6+uxz46Ohpr167lCrMYGRnxOgFq1KghWRIO0K5KpRSkVKCWy+U4cOCAYPge32LJx8cHMTExaNasGRc+JpPJeA1qPT09LFy4ECEhIaKdcVJLxdepUwd16tQRJcEpxBdhUNerVw9xcXHcKuzNmze8klt8PzbDMHj79q3SRZMfsTGAgwcPxsGDB1XiVDWt8qXo6u7ZswdDhw5FamoqTp48yRnU6rY5gTyZtB07dnCZ2C9evMD06dMFjRxdlY8GpMuqAcrFMDQxa9YsLgQIEDZeP3/+rPS34oNSndcKkK77DIgLu9E27jc9PR0xMTGcZzgmJkaUQSIWMdqxz549w9OnT5GcnKykfJGSkqJWf1hsiIW+vj7s7OxgZ2eHrKwshIeHw9PTE97e3mrj+4G8+6NHjx7IyMjA3r17cf78eezYsQOenp4qoU2enp6816eQ51OKHiwA0clHLPPnz8fJkyfx6NEj7Nq1C25ubpg1axb27dvH275x48bcvfLp0yekpqZizJgxguffs2eP6PLd2oSnSVXWuHv3rqhEQACYNm0apyoE5C0Cpk6dKrgj2LZtW2zZsgUZGRm4cuUKDhw4oPb7VKtWTXSFVgBcPGp8fDzOnj2LhQsXIiEhAQ8fPuRt//fffyMsLAy1a9dWGhuhhFxt8n+kICX5WC6XY8yYMfj1118xdepUSZ9z48YNnDp1Cn/88QcsLS0Fy79LyRWSupDU9dgbGhoiIyODu8+jo6N5d3a0VS7WpkqlWHJzczFjxgw4OTmJaq+vry8oOyzE/fv3cerUKdEhFh06dMDZs2fRvXt3Ue+RWipeipKYEKVah5r15qWkpOCff/7hVprsqlOdtNzDhw8RFhaGs2fPwtzcHD169ND4UAbyJgI2BlDbRJT8SNHVZbUt+/Xrx6sdKQSfxqI63cXly5cjLi5OqXx0rVq1MHv2bMHvwLcdxrd6//jxI/dvRVk1vgx8bZUa+BKP8i86pk+fjnbt2qkU7Th06BBu3LiB1atXq/1sMWibBCiV33//HQEBAUqTx4IFC9TGqkpBjHbshQsXcPHiRfz2229KRkqFChXg5OQkmOh248YN7Ny5E23atMGYMWMQExODPXv28C6gsrKyEBkZifDwcMTGxsLBwQEDBgxQG2Z04cIFnDhxAtHR0ejTpw/69esHExMTpKenw9nZWSUW8f79+9y/MzMzce7cOejr66tU1GN3vORyOV69eoU6deqI0oN98OABAgMD8eTJEzRp0oRLPhLK+2Dv9aCgIJiZmcHNzU3t/e/p6YnNmzcjJycHrq6uMDExQZs2bQQXfJ6enti1a5egKk9BuXHjBu9xofAPNzc3rF+/Hl5eXggJCQGQV0qbr7gW33F181pubi6OHTumpDHu5uamco/yad4qIrS4Dw0Nxe3bt/Hff/+hSpUqsLa2ho2NjWAYhFACn9AWfWxsLKpXr47s7GxRmu1iYRfAN27ckKR/P3ToUAQFBUmKo3ZwcMC3334LR0dHlUJd+WGfd5qOaYOux/7KlSvYvHkznj59ik6dOiEqKgpLly5VCR9TV4FYHXzXPnusMMZInbY/H/PmzUN8fDx69uyp9JsKXTuTJk3CnDlzRGu2W1lZIT09HQYGBjA0NBT1DFWsD9CwYUO1NpsUJTEhSrWHWqo378WLF9x2cdWqVeHk5ASGYQQNb/bHY2ONnz9/jocPH6J27dqCP0z+mEExSNHVbdSoEbp3746EhATeEBahB4mlpSX8/f25FXtYWJjaxDddlo8WK6sGaOexFZt45Ofnx3lbWWmpBw8eICsrS1BaSkh9gyX/g1ZqEqC6sCRA+Pe1s7NTSvDQNHlIRYx2LBsbHxUVpTGOUhGxIRYzZ87EkydPYGdnB29vb26rUxMXLlzAsGHDVMKbjIyMeBNU8t8X1tbWvFUttS1h3Lx5c+zbtw8vXrwAwzAa8xkqVKiArVu3IiwsDPv27UNubq7arezk5GQYGxvj6NGj6Nu3LyZNmqT2upJSvlub8DRbW1u8e/cO9+7dg0wmQ4sWLXjLdysiNhGwU6dOiIiI4Eo8nzlzRq1nTk9PDwMHDlRb+RLIW1Q3adIEjo6OMDU1Fe1FXLJkCerWrYtBgwahXbt2qFOnjtr2rPH24cMHUVUkzc3Nud0zbcIEhFCUfhSbfAyIV49S5OTJkxp3VFnE5AppO2fqeuw7deqE7777Dn///TcYhoG/vz9v4ro2xjSQZwtIrVIphY4dO2LHjh0q1ZiF+puVlYWqVavi+vXrSseFrh22qEvLli2V5j+heVXqs3T//v3o1asX56j49OmTxrBVsUpiQpRqg1qqnI2joyNsbGywdetWblWpLllw1KhRWLx4MerXr49Xr15h0KBB6NWrFy5duoR79+5hxowZKu/RJmaQT1d3xYoVvG1Xr16Nd+/eYeTIkVycmBgWLFiA/fv3c4sHGxsbtWU59fT04Orqivbt26ts7fMhZTtMrKwakBfXJHYcWcQmHpmYmODQoUOSpKUUjS11xXq0RVsjDRCf4KENrHbslClTBLVjWerVq4ctW7aoqF7kj7devHgx/P39BXch8o/FyZMnYWRkxCU/sajzVMjlcsTGxgrmCvD91klJSdy/c3Nz8eDBA16VHvaBfPfuXTRu3JgzElJSUvDs2TO1iUD37t3jfis2HEDot1qzZg3Cw8OxePFi1KhRA3FxcRg5cqTgueVyORISEnD69GlMmTJFsB2LlPLdUsu+A3kqSRs3bkT79u3BMAwWLVqE8ePH8y5SAGmJgEeOHMGePXs4zezc3FwYGRnh0KFDSteEOqPL0NAQdevWxdixY7mH7x9//IEzZ87g1KlTMDAwgJOTE3r06CEowcZy/fp1PHnyBDdv3sSaNWvw6tUrNGjQQKXqG8vFixexfPlyJCQkoFq1aoiLi0OjRo24uFsWhmEQFBSEffv2ccmC+vr68PDwKBTDWqr0I8sPP/yAjh07cpKj6pIxpTojAHG5QtrOmUUx9llZWahUqRLkcjmePXuGZ8+eqZWYlMLy5ctx4MABzlHUpk0bzJo1CwYGBmoTc8Vy6tQpAHnPUxZ1hVGkXkNin53Pnj1Do0aNeJMwAXDOsPxIzQOToiQmRKk2qFnExu8GBQUhIiICQ4YMwQ8//ABnZ2e1nofPnz+jfv36APKq7jg7O2Pu3LnIyspC//79eQ1q9n35YwZlMpmgAaynp4cKFSoo6eoKFYsA8pIYhBIohTA0NMTw4cNFZ6xKFeyXIkWYX1bN3NxcMIZuwoQJ3Nb2xIkT1cobskhNPJIiLaWYULlnzx6tEizVoU02NiAtwUMKb968Qa1atbjdibZt23ITqtA1On78eFhbW6NDhw5qk0DYxEOxuxDsIkEKUooasSjqu7Kyf0JSS0BejLNi+EX58uVVjiki9beqUaOG0n1bu3Zttb/r+PHjMXLkSFhbW6Nly5aIiYnh5jE+pMQOZmZmcveKubk5Jk6cKLi7xLJ9+3acOHGC25n6+PEjBg0aJGhQS0kEFOu1Umd0yeVy/Pfff5g9ezYXYlK1alUMHjwYgwcPxtu3bxEREQEnJyfMmDFD7dinpKQgLi4OcXFxiI2NRXJystqE03Xr1uHw4cMYPnw4QkJCcO3aNd65fffu3bhz5w6OHTumlCcxf/587N69W7CsvFTEJh/n5ORg9erVCA4O5hLd4+Li4OrqimnTpvGeW5viUxUqVFDJFcqvGKTtnKnrsWc12xs3bqx0DRSGQS2XyzF69Gj8+uuvvPNnYRR9ESvLp221XrEO0d27dyMwMJBXdEEmkwkuHqTmgUlREhPiizCoxcrZsFvSaWlpuHjxIvbs2YPExETMmzcP3bp1U7tVeO3aNa76lqGhodqVtuLDhWEY3Lp1i1vt8TF37lwsX76c28KOiIjA7t27VeR12HNLqS6n7XaYVMF+KVKEUsqmKy541EmvKSI18UhbCks/VRFtY66lJniIZfjw4di+fbvK1nVwcDA2b97Me42mp6cLVtlThH3Aals4QSxSt6WlVtjKX/JYT09P7SJO7G+lbZKzo6MjFwIB5D0o1C1EpcQOSi37zp5P8QFfoUIFtQmQUhMBHz16pFS5EVDdZtZkdNWtW5c3cfDBgwcIDw/HX3/9BTs7O41G4eDBg2FtbQ1ra2t4eHigZs2aatsbGBigatWqyM3NRW5uLtq3b8+bOBUaGoqdO3cqhQxYWFhg5cqVGDFiRKEZ1GKSj4E8B0pqaiouXryotDOzfPlyrFixQqUMNPA/Z4SUBF5WMUgxRESdYpAUdD322mi2i0UbR4FU0tPTsWvXLk5H++XLl7w62ocOHYKVlRWaN28u6vkjdV5jnTlS7AYgLz9iypQpSnlg6nKKFJXE2Hom6pIY+fgiDGpAmpwN+4Dt1asXPn36hDNnzuCXX35RMai/+eYbLF++HGZmZoiOjkanTp0AqKpD5MfW1lYl6ZH9UflYv349Jk2ahFWrVuH27dsICQnBzp07edtKrS6n7XaYWMF+KQY7K14vBJ/3XPGGE2sszpgxA8eOHUPTpk1x+PBhdO7cWWP8d0lB28IrTZo0wbt370QneIjF19cXI0eOxNatWzkv59atWxEeHi6oMtG5c2dcvnwZ9vb2oj5DG9UXKYgtaqTInTt3VIw0Ic+khYUF9u7dyxUQOHDggFrPhtjfis1fEHtNaOspkhI7KLbsO/C/+71u3boYOHAgfvzxR27LmM+gEqryCuTd+xMmTFA57uvri8ePH6NJkyZKXkCpvzegLHe6bt06XL58GQ0bNoSzszOmT58uKi6Vne/S09NFVYOtVKkSUlNT0bZtW8yYMQPVqlXjTdLLycnhjb+tVq2axh04KURHR2P9+vW4ePEi+vXrBxcXF94t8sjISJw9e1bpOjM2Nsb8+fPh6OjIa1CzLFiwAFlZWejXrx969+7N+5zRVjFICroee6ma7VLRJn5dCmJ1tD09PbFy5Uq8e/cOPXv2hIuLC7777jvB80qd1wICApCWlgYnJyf06tVLtAqNj48PDh8+LDoP7O3btwUeuy/CoC6IlFDlypXh7u4Od3d3ldcWLVqEvXv34vXr19i5cyc3QT59+pR3m0Vq0iOLhYUFVq9ejQkTJqBWrVrYuXOnYCwa+xAWu82l2O79+/f4559/AOSV9lVX+EOsYL8Ug12TJ4uPR48eoU2bNmAYBpmZmZxSBN9qVrHy4cCBA3HkyBEkJibiwYMHqFixotpCLWJRXFVnZGSo7U9RIjXBQyz29vYwNDTE6NGjsXHjRhw9ehT//PMP9u3bJ6itu3fvXmzduhVlypRBmTJlNI5NcHAw929F1ZfCQmpYjtSQjAULFmDRokXYvHkzZDIZOnTogMDAQMHzS/2txJZUllplk0VK7KDYsu/A/+73unXrclqwQF6lPD74jJm0tDQEBwcjKSmJ16D++++/1e7+acvmzZtRp04dPH78GI8fP1ZR/BHa2YuKihIt+QcAmzZtQrly5eDr64uwsDAkJyfzfk91SavqXpOKmORjIO9+4Fu06evra3R8HDhwAC9fvkRwcDBcXV3RsmVL9OvXT8mh9eLFC0RGRiI5OVkptKxChQpq762MjAzExcWJyvvR9dhL1WyXijaOAimI1dEeNmwYhg0bhtjYWERERMDPzw8ZGRlwcXGBi4uL2nAzxYJSLPlzpkJCQvD8+XOcOnUKEydOhIGBAVxcXODk5KQ26VdPT48L20pKSsLbt2/VhiCyCz1XV1f06tVLK89/qZbNY4mNjYWJiQlycnIKVUpIKs2aNYONjQ0WL17MffaPP/4o6GnL791NTEyEsbExd/PxTdrahgScOnUKK1euhK2tLReGMnPmTEEjMz09HVu2bMGff/4JhmHwww8/YPz48VyBGz4UpeoyMjKQk5MjOpu7MBg0aBDWrFnDKQT06dMHe/bs4SofqisvXNqRKk0mlVu3bnGV69atW6f2OigMpEo2qUOqMoWjo6NOwmdYpP5Wffr0QXBwMGJjYzFmzBg4ODjg6dOnvCWVtWHChAn47rvvlGIHHzx4oKR0IzWBlA+xXlsgzxPJVqh1dHTEiBEjeB0Afn5+GDFiBBo3bizqvGIrGaoLbwOEHRpiJf9evXqF9+/fw9raWun4rVu3YGpqqrQAAfJC7vjGjmEYZGVlCSZsSeXo0aPo3r07Hj9+DF9fX6SlpWHSpEnc7gvL+PHj0b17d5VFZmhoKE6fPi3qepDL5bhw4QIWLVoEY2NjMAyDadOmcUaiXC7HL7/8olE6leW3337D8uXLNeb9FNXYC+VQFHbeja4YNGgQdu/ejcGDB3Oyo9OmTcOxY8c0vvfhw4fw8/PD48ePeQv2AHkhHEFBQaIKSiny6NEjRERE4PTp06hevbqgCgeffKiVlRX8/PwEz/3ixQscP34cZ86cQcuWLeHq6spFJojhi/BQSy0lriukJj1q4z3UNiRgy5YtOHbsGPdQSkxMxLBhwwQNaiMjI0ydOlW0YH9+qbq3b9/yStUBeVsrgYGBnPFvY2MDf39/jfGGmihI5cPSjq7ikNkFHMMwyM7OxrVr19ChQwe1CziGYXDy5Em8fv0aEyZMwJs3b/Du3TvBimRSVF+0QaoyhdiQDF0n47CILamsrWa7mCqkUhNIFZHitU1KSsKuXbsQFhbGaW0L7YQAeWE47u7uqF69uigNcLGVDLVNdAPESf4tWbKEN3mvYsWKWLJkicpvJWSUFDbslritra3akKt58+bB29sbwcHBnMrC/fv3kZGRISg5yvLo0SMcP34cly9fRseOHbFlyxY0b94c8fHxGDRoEGdQ6+vr48KFC6IN6qCgIFF5P0U19roynKXmUUllwYIFcHZ2hre3N0aNGoU3b95g+vTpnI62EDk5Ofj9998RERGBa9euwdbWVq09tnfvXtEFpVhyc3Px4cMHvH//Hunp6Wp32aXKhwJAgwYNMGXKFFhaWmLRokV4+PChykJPHaXaoNa2lLiukJr0aG5urpVutSL5NTSFJOYYhlG6+KpUqaLW2H/x4gV27typIn0mlFErVqoOyDNwXFxcuOpXJ0+ehK+vr8YYa00UpPJhaUXXhWO0WcDNnz8fenp6uHbtGiZMmIDy5ctjwYIFSqEdikhRfdEGscoU7IM7NTVVVEiGtiEW586dw6pVq/DhwwdOhkvdbyW2pPLdu3dRq1YtODs7o1WrVqK1k8VUIbW0tIRcLsfhw4clJQwCeQbMjh074OXlBSBvJ48tJa3I8uXLcf78eQwcOBBhYWGilAr8/f2xYsUKNG3aVK2ahuJnAOIrGUpFrOTf+/fveePIv/nmG43ecV0gNb/FzMwMR48elSQ5yrJo0SIMGDAA06ZNU9opYGN0FWnTpg0WLlyoooXMJ5UmNu+nqMb+9u3bCAoKQlxcHHJycrj7vKC5Iey9WtBwPiHq16/PxUR37NgRHTp0QPPmzQV1tK9cuYLw8HD8/vvvaNGiBZydnREYGKi2YA+QV4FabFjFrVu3EB4ejgsXLuCbb76Bk5MT/Pz81L5fqnyo2IWeOkq1Qa1tKXFdIzbpEdBOtxoQr6HJ8v3332PkyJFKIvB2dnaC5588eTIGDRoENzc3UQ8qKVJ1iYmJ6N+/P/e3q6troYRjtGzZEkeOHOGtfCjkHS3taLtjoUvu3buHEydOcF7UypUrq5Urkpq9LRWxyhRSva+scoxUT9TKlSuxZcsW0ck1YksqX7lyBVeuXOHyOOzt7eHi4iJY6UuqR1tfXx9xcXHIysqSnGglxmu7a9cuGBoaYvPmzUqfrW7BUa1aNcGYbD7yVzL8+eefuaIhhYFYyT8+XXOWjIyMQuuPWLTJbwGkSY6yKCYzf/r0CW/evOH0v/PvvLDeYdb5AghLpYnN+ymqsff394evry8sLS1FPUPFMnToUC4+OX94SmGdf+jQoVxM9KlTpxAWFgYXFxc4OzujQYMGSu23bt2KXr16Yfbs2Wp3k1jYxZvYglL29vaoXbs2nJ2dMXHiRLVeaUXEyofu3r0bbdq0wdKlS+Hu7i5qoSdEqTaoFbfl+EqJFxYvXrzAjh07uJUmixjxdHVJjyxSdasB8RqabLzYrFmzcO7cOdy+fRsA0Lp1a96HMouBgYHawi/5kSJVV6VKFYSGhsLFxQUAEB4ernW1KEW0qXxIFD4GBgaQy+Wc5zwxMVHtAyU5ORlBQUG4efMmgLzt5gkTJhSaHJRYZQo2FCMmJgampqZcnHhGRgbev3+v0l7bEAsTExPRxjSQZyiwXqlPnz4hNTUVY8aMUWmnr68POzs72NnZISsrC+Hh4fD09IS3tzc8PDxU2mvj0bawsMDgwYNVSkar07cX67XVRmf822+/xfTp09GlSxdRpbKlVjIUG3PNIlbyz9LSknfxf/ToUcFCFbqE3ZrnK4MtVq5ULHyxrW3atIGvr69KWymL7blz52LLli0wNDTEtGnTuLyf/BTV2FesWFG00pEUVq9ejYiICIwYMQJVqlSBi4sLHB0dYWZmVqifY25ujjFjxmDMmDFcTPTGjRtVQmCkFpFhF29iC0odOHBAqxAssfKh8fHxWLJkCZ49e4Zjx47h+fPnsLKygpWVFXcviK3nUKqTEvlUNXbu3Km2KIo29O7dG4MGDVJZaWojVM+HYpKSom61kLcZ+F/SVu/evRESEgI9PT307t1bxageO3Yspk2bprLF9fjxY6xZs0bwob9hwwZUq1YN3bp1U3pQCRm+ubm5OHbsGP78808AeR5xNzc33nCE2NhYBAYG4u7du5DJZLCyssKcOXMkV0QUQnEbsnHjxpI9KETBOHnyJE6dOoWHDx+iX79+OHPmDKZMmaI0uSkyceJENGnShPP0hoaG4tGjR2pl1HSJq6srDh06xF33WVlZGDx4sErISvv27dUapEKx0osWLcL79+/RtWtXUUagFAMkKysLkZGRCA8PR2xsLBwcHDBgwADeh61cLuc82o8fP9bo0QaEpe3UxUomJiZi8eLFuHr1KhiGQadOneDv7y8pdlIIvjEA1FdtYysZ3r59W2Mlw1mzZuHu3bsaY66lSv69f/8e3t7eKFOmjFIMcnZ2NoKCgjSWZtcVgwYNwvbt27lk8mfPnmHy5MkqSZUFoW/fvggJCcHRo0fx5s0bLraVL/b3/fv3WL16NRISErB9+3Y8ffoUUVFRBZJBLaqxX7VqFeRyObp37650nxem0X737l2cOnUK586dg4WFBXr16qWyUNAWvphoZ2dndO3atVDOr0hubi7S0tIKRcRA29yWrKws3L9/H1FRUbh79y6ioqJQqVIlSSpCpdpDLbWUuLZI9dZKRapuNSBeQ1PbeDE2Q3nHjh3cMXXxX3p6elwMOV+clSLm5uY6i/8CtNuGJAoOW1Wxd+/eaN68Oa5duwaGYbBp0yZER0cLvi86OlrJc+Dt7c0lwRUEbT3Icrlc6QFoaGjI60GRGmLBkpqaCiMjI1y5ckXpuJBBLTa5ZubMmXjy5Ans7Ozg7e3NFYoSQqpHG9Au6VtqoRYpSC13LLWSodiYa6mSf6w6wbVr1/DkyRMA4mKQpcbfS2XcuHEYN24ctm7dihcvXmDWrFlYtWpVoZybRUps6+zZs+Hq6srdq/Xr18fUqVOVDGqp93lRjf3ff/8NIM9YZ1FX2U8bWrdujdatW+PHH3/E0qVLsXDhwgIb1NrGREtl+vTpWLBgAfT09DBgwACkpKRgyJAhXAE9bcnKysK9e/fQrFkzTrZVDJmZmUhJSUFycjKSk5NhamoqugARS6k2qKWqamhLly5dsH//ftHeWrFoo1vNhnDk19CMjY3lXXlpGy8mtlocwzAICgrCvn37uLHX09ODh4eHysN3+fLlqFevnspi4dChQ3j9+rVgKXeidKBYVbFRo0bctv6xY8ewZcsW3qqKAFCuXDncunWLi2W9ffu26C12dWibpFetWjVcvHiRi829cOECrzdVG4MUkG4EijVATp48CSMjIy5+lEXdgz+/R9vT0xPdunUT/IzExET88ssvKhKEfEaCNoVapCK2VDaL1EqGYmOuFePvWcm/48ePw8nJSW1sfvv27ZU0wDUhNf5eKp07d0ZOTg5GjhyJ1NRUBAUFqcTMFhSxsa1Anma7k5MTtm3bBiDPuZV/AcSO77lz5/D+/XsulDEiIkJtvK2ux17XuSH37t1DREQEzp07hzp16sDd3b1Qai1IjYnWlqdPn8LY2BgnT56EnZ0dpk+fDldXV0GD+vbt2ypSh3zHUlJSuBCOb775Bm3atFEJ4VBk7ty5ePLkCSpUqIBWrVrBysoKw4cP1+q7l2qDuiClxKUg1VsrFm087KzkD7ta1NPTQ79+/QRDOAoSLyamWtzu3btx584dHDt2jKsOFxMTg/nz52P37t1KZVmvX7+OmTNnqnzOwIED0bt3bzKoSzl8VRW3bduGsLAwwaqKQJ5M08yZM5GSkgIgb/dFUflDW7T1IC9YsAAzZsxAYGAgGIZBrVq1BKsBSjFItd2KFGuASI1BlurRBvKqkDo6OiIyMhILFizAiRMnBHektCnUIhWxpbJZpFYylBJzLVXyTxukxt+LRfGaZBgGycnJsLCwwP79+wEUXjESQHxsK5B3DX38+JHr2927d1VyK9jQqmXLlilp1zs4OMDV1bXQ+i117HURrgLkxVCfOnUKlStXhrOzMw4ePFhgyVlFCtODro6cnBxkZ2fjwoUL8PDwQJkyZdRq/y9atEhF25vv2KxZswAoh3AcP34cc+fO5Q3hYBOt69evDzMzM9SsWVOlaJZYSrVBzSJFVUMbxHprpaKNh11qCIefnx+8vb2VEvUU48WEEFstLjQ0FDt37lR6qFpYWGDlypUYMWKEkkGdlZXFe8Po6enpZGeBKFq0qaoI5MmonTx5kjOojY2NsXv3bi7zX1u09SDXrVsXR44c4ZJnhOTbpBqk2srsSTFApKCNRzspKQlubm7Yu3cvbG1tYWtrq6TYo4i2XlspiC2VzSK1kuH169e5mOs1a9YIxlxrI/knBbb8tqWlJaZMmSI6/l4s7DWZkZEBuVyOBg0aQF9fv1B2ivKTmJiII0eOqEiy8u0qzJ49G15eXoiOjsagQYPw8eNHJcUPRdLT0xETE6Pk2CmM+gPajr2YcBVtMDQ0xPbt29VWICwNuLu7w8HBAc2aNUPbtm0RGxvLG0MdFRWFqKgoJCYmKsk7pqSkKDn78iM2hGPHjh1gGAZPnjxBVFQUdu3axe1ItW7dGpMmTRL9nb4Ig1oRMaoa2vDff//h6dOnyMrK4o6JzfwUQhsPu9QQDm3jxe7fvy+qWlxOTg6vh6patWoq0nlly5bFy5cvVSaCly9f6rzyHlE0dOjQAUuXLoWnpyesrKywZ88e0b+t4mSaf3dDW6SGNLBERkaqhBHkD2GSapBKldnT1qMtFm1UNdjS1KampoiMjISpqanaMvG69tqKLZXNIlYTm0VszLU2kn9SUEy0lxJ/LxYXFxesWbMGwcHBXHJ4XFwcXF1deYugFITx48fD2toaHTp0UFsKGshL4Nu3bx9evHgBhmHQoEEDwXLfvr6+8PT0hIWFBRiGQVxcHBYuXFjg/kod+5ycHBgYGIgKV9GG4ixeV5gMGTIEQ4YM4f42Nzfn9Y5nZ2cjLS0NcrlcSd7R2NgY69evV2mvTQiHTCZD06ZNUalSJVSsWBHGxsaIjIzEvXv3vm6DWhcEBQXh+vXrePbsGezt7fH777/D2tq6wAY1ixQPu7YhHFLjxcRWixOa3PhemzRpEkaPHg0vLy8lb/m2bdvUlgMlSgfaVFUUojB2LLQJaQDyCgJlZGTg+vXrcHNzw9mzZ9GiRQuVdlINUqnJU9p6tHWJl5cXkpOTMWvWLAQGBiI1NVVQaUPXXlsgz8v16dMnTJ48GV5eXlypbHWI0cRmERtzrc3iBBCf6MZ6b4XiSAvKypUrOccOu7BNSUnB8uXLsWLFCvj7+xf4M1jS09Ph4+Mjqi1bvp2FTQble/ba2dnh3LlzeP78OQCgYcOGavXSdTX2bm5uOHHihKhwla8dMY4LdiesX79+nHyeOlUQqSEce/fu5bzgBgYGXLz1gAEDRD8zWEq1bF5R0atXL4SGhqJv3744efIk3r9/Dx8fnwJX9tOGopL88fT0xKNHjzRWi/v22295YxEZhkFWVpZSWWkgz9O/Y8cOzlvepEkTjBgxQnI2LfFl07lzZ0RGRhboHM2aNVPSdWfRZOCzEl7s/1NTUzF69GgcOHCgQP3RVmavtNKsWTMYGhpCX19f0vjrkkmTJmHYsGEIDAzEkSNHsHfvXty/fx9r1qxR+z6xMddS6datm6REN9bLr+mYVLp3746zZ8+q7ITI5XI4OjpyYQ+FwZo1a9CmTRtRGs2BgYHcvzMzM3H16lU0b96c1zOZnZ2NgwcPcjsOtra2cHd3F3T66GrsWVnABw8eIDAwEE+ePEGTJk24cJWChrJ9KQg5LpYsWcLbXooqiGIIR1RUlNoQjqVLl3KJi5ociJogD7UIypYtCz09PRgYGCAlJQUmJiZ48+ZNsfRF2xAOqUycOFFUu/wi75po2rSpYIIX8XWhrmy6osdCW7T1GrJxo0ZGRoiPj0fVqlXx7t27AvdH15UMdcmiRYvUvs4XfqLt+ItBaqlsFrGVDFmkxlxLRWyim7ZxpGKRyWS892L+xVBhsHfvXmzduhWGhoYwMDBQu8CaO3eu0t+fP3/G1KlTec87f/585OTkYPDgwQDyQrLY35sPXY29Yrtu3brB3t4eDMPA0NAQV69eJYP6/xMVFcU5Lry9vTF8+HCMHj1asL0UVRApIRxCO2zaQAa1CCwtLfH582e4ubnB1dUV5cuX5y1pWpRIDeGQiq2tLd6/f49//vkHQF5Zb7ElPwlCDCWxbDqQ5x3//PkzRo4cCVdXV8hkMgwYMKDA5y2KSoa64tChQ2jSpAkcHR1hampa7EnEirGUhw4d0qjbzyJVE1tqzLVYpCa6SY0jlUqjRo0QEhLCm3Re2LJ5BbnvjYyM8Pr1a97X/vnnH6XCZh06dOCtBqzrsc/NzeUt5V4UJeULY7eiqGBza8Q6LsSqghRmCIdUyKAWAeuNGDx4MH744QekpKR88avMU6dOYeXKlbC1tQXDMAgMDMTMmTMLReeSIEoyrJxbjx490KVLF2RmZhZa7KOUJEltZf90wR9//IEzZ87g1KlTMDAwgJOTE3r06KG1vFRBUYyzvHDhgsZErYJoYkuJuRaL1EQ3W1tbWFtb4/HjxzpJSps3bx68vb0RHBysFEqYkZGBjRs3FvrnxcfHq0iytm3bVqWd4i4NwzB4+vSpYMVVfX19REdHo27dugDyVD74kh61Gfv8MbzqqFGjRrElDpYGY3r37t1o06YNHBwc8PnzZ4waNUqU40KsKkhsbCx69uwJX1/fAodwSIViqEVw/vx5tG/fnnuofv78GTdu3NBJCc6SQu/evbFr1y7OK52YmIhhw4aplDaXwsqVK+Hj44PTp08LTooEUdycPn0aP/zwA4yNjbFp0yY8fPgQ48ePx3fffVeg8yomSTo7O0vylrAe7RUrVmiU/dM1b9++RUREBHbt2oUZM2YUWnK2tojxyu3cuVPlmKImtpDXVNuYa7GILVbB4u7ujsOHDxfKZ/Nx9epVPH36FADQuHFjnVScXblyJU6fPo1GjRopGbx8IUw3btzg/q2vrw9zc3PBxNCrV6/C19dXSeVjyZIlgju5Usfe09NT0COqCBtDXVR8/PgRt27dQq1atUpUArMQy5cvR1RUlFLhldatW8PKyoq3gJY6WEWVkgIZ1CLo06cPQkNDlY4V9U1T1LAJWSy5ubno06eP0jFtznny5Em4urqWipU08XXCXvu3bt3CunXrMHLkSE5XuyBokySZ36Pt4OCAAQMGwMzMrEB90ZYHDx4gPDwcf/31F5o3b44RI0agcePGxdIXFqnb3Kwm9rFjx+Do6IgRI0YIhrMlJiZi8eLFuHr1KhiGQadOneDv7y/5wS+l7+q+z7x58xAfH4+ePXsqFc4pqGxeUdKjRw+EhYWpVeDIzMzEwYMHER0djaZNm2LAgAGiDKesrCzRKh9Sx16xhHhmZibOnTsHfX19lWJlSUlJBa6irI6xY8di+vTpaNq0KRISEuDq6gpLS0tER0dj4MCBhSI3WhQoFl65e/cuoqKieAuvsOiqUE5hUnJM+xJMbm6uyrHCSAQpyXz//fcYOXIknJ2dAeSFgNjZ2RX4nG3btkVaWhratGnDGRLFmfVPEPlhvWaXL1/GwIED0blzZ6xdu7bA5y2KSoa6Yt26dbh8+TIaNmwIZ2dnTJ8+vVg9Q7169eL+HR0drfQ3AN6Fvzaa2FJjrsWibZJhVlYWqlatiuvXrysdL00GtYWFBbKzs9Uau7NmzYKBgQFsbGzw+++/4+nTp6J01+/fv8+FkrD3W/4dFG3HPr/319ramjdEQZfGNAC8fv2amwuOHz+Ojh07YsWKFUhJScHgwYNLjUEttvAKi64K5RQmZFCLwNLSEkuXLuUqcO3fv19j2e7SyqtXr/D+/XvMmjUL586d43Q2W7duzZvgIYVZs2Zh1qxZ8PLywubNmwujuwRR6JiZmSEgIABXrlzB6NGjkZWVxbuo1jXaVDLUFZs3b0adOnXw+PFjPH78GKtXr1Z6vSA7V9ogVeFEqiZ2QWKuxaBtkiFfNcHShpGREfr27YsOHTooGdWKBvOzZ8+4a2rAgAGijCax1X21HfukpCTu37m5uXjw4IHaQmu6QnEhe/XqVa4mhbGxcaHE9+sabQqvANBZoZzChAxqEcydOxebNm3ClClTAECj1FJpZsmSJVxlrO7du3Oej8ePH2PJkiWFItW1efNmJQWRVq1a8VZbJIjiYO3atfjjjz8wYsQIVKpUCQkJCSrbukWBLmXnpHLx4sXi7oISYpLDFJFayVAxnIJFMea6oAa1tkmGb9++RWBgINdfGxsb+Pv7C8YVl0QcHBy4qqFCKBqNYndCxFb3lZpkyMImzjEMAwMDA9SpU0dQkk+X1KpVC7/++itq1qyJhw8f4ocffgCQpyKSvzpxSURq4RWW0lAoh2KoCSX69++P4OBg3tfyx1Vry+nTp7FixQpOQeTWrVukIEKUGKKjo1GzZk0YGhri+vXrePz4Mfr27VtsihZE8SIl5loqUpMMhw8fDhcXF/Tp0wdA3i5GWFhYsRQZKwgZGRmIi4tDw4YNeV9XLBjG6tKXK1dO7e7MpEmTMGfOHNHKDmKTDEsaHz58wLp16/Du3Tv8/PPPXEXla9eu4cGDBxg5cmQx91AzUgqvsNy/fx+LFi0q0YVyyKBWw+LFi+Hv7y9YYKEoCysUFd27dxesitWtWzecP3++wJ+hCwURgigs+vTpg+DgYMTGxmLMmDFwcHDA06dP8csvvxR314giJH/M9ZAhQzRuS0tFapIhX4I837GSzG+//Ybly5cjOzsbv/32G/7991+sW7dO6+cp+3xOTU0VVd2XRWySIYvUSoyEZt6+fYs7d+7gzp07iIyMRFJSkorOOyuzx6osvXjxAgzDoEGDBiVu7CnkQw2sF2DEiBHF3JOiw9LSEkeOHOHisliOHj1aaHHjDMMoeXiqVKlS7IUiCIKFrYp67tw5eHh4wNPTs9il4Qh+rl69CisrK666ZWEhNeZaW6QmGVapUgWhoaFwcXEBAISHh+s8Ca6wCQoKwrFjx+Dp6QkgzxstVKxFDNo+n8UmGbJIrcRYHBw+fBju7u7F3Q21SC28Eh8fjyVLluD58+do2rSpUpnwknbtk0GtBktLS8jlchw+fFgnmd4lET8/P3h7eyMsLExJ4D87O1ttoo4UdKEgQhCFhYGBAcLDwxEaGsolz5aG2MSvkZCQEMyfPx+VK1eGtbU12rZtC2tr6wJ7kqXGXGuL1CTDJUuWIDAwEEuXLoVMJoOVlVWpS1Q0MDBQiX0tSHlzW1tb3uO5ubkIDw8XfJ/UJEOxlRiLk9LgmJJaeGXWrFkAlGX2jh8/jrlz56qV2SsOyKDWgL6+PhdEr07m50uhevXqOHToEK5du4YnT54AAOzt7QtV4D+/goi7u7tgtTiCKGqWLl2KQ4cOYdy4cbCwsEBMTEyJe3CWJDZs2ICJEycWy2cvX74cQJ4X6+zZs1i4cCESEhLw8OHDAp23qBJCpSYZmpubl/pQw8aNGyMsLAxyuZxTsLGystL6fCkpKdi/fz/i4+Ph4OCATp06Yf/+/di5cye++eYbwXtXapKh2EqMxcmgQYOKuwsa8fX11ep9UmX2igOKoRbBzJkz8ezZMzg4OCjFuQ0fPrwYe0UQBFH8/PbbbxpVG3RFaGgobt++zSU1WVtbw8bGpkAGWlEiNslQ1zJ+RUl6ejq2bNmCP//8E0DejuX48eNRtmxZrc7n5eWFypUro3Xr1rh69SoSExPBMAz8/f3x7bffFlq/pVZi1BX5rw2ZTMZd+xYWFkXal6Igv8xeq1at0Lp160LPZygMyEMtgrp166Ju3bpgGEZJt5IgiC+Ply9fYvXq1Xj69CkyMzO54yVNOq6kUFzGNJAXAlG3bl0MGjQI7dq1Q506dYqtL9qQmJiI/v37c3+7urpiz549Ku10LeNXFOSvfnj48OFCKQ70+vVrLjTLzc0N33//PSIjIzUa6FKTDDt06IBz586JrsSoK/hskNevX2PLli2YOHEiF0r5paCtzF5xQB5qCaSnp3NSPgRBfJkMHjwYkyZN4nTXjx8/jtzcXEyePLm4u1ZslGQP6ZMnT3Dz5k3cvn0br169QoMGDbBy5cpi648Uhg4dCldXV6Ukw+PHj/Ma1Sy6lPHTJVOmTFGqfmhubg5/f/8Cnzd/uXCxpej9/f2Rk5PDJRyfPHkSenp6KmEf9+7dQ61atVCjRg0AeXH7Z8+ehbm5Oby9vUtMYlxSUhKGDx8u6ruXNrSR2SsOSlaZmRJKVFQUnJyc4OjoCCAvvm7+/PnF26lSDN/DQt0DhCCKkszMTC5nwNzcHBMnTsTly5eLuVfFS/ny5VX+k8lkCA4Oxvbt24utXykpKYiLi0NcXBxiY2ORnJxc4qqnqWPJkiU4ffo0OnXqhO+//x5nz54VTDJMSkrCmjVr0Lt3b8jlcpw4cQI+Pj6lwpgG8qofrlq1CoMGDcL69etV5NG05dGjR2jTpg2n/vD48WPu323atBF83z///IPly5ejQ4cO6NChA5YuXcoVG1Nk3rx5nNf65s2bWLVqFfr27QtjY+MSVeDtS1bLkslkaNq0Kezt7WFnZ4c2bdogOjq6xGmGU8iHCJYsWYIdO3bAy8sLANCsWbNCmwy+RkJCQjB06FClYydOnFA5RhDFgaGhIXJzc1GvXj3s27cPZmZmX32ol6I0GeshDQ4OhpOTU7HKig4ePBjW1tawtraGh4dHqaoYCIhPMiwqGT9dok31QzH8+++/Wr1PbJKhXC7nvNCnTp2Cu7s7evTogR49enCx7yWBa9euldhQiIIgVWavOCGDWiS1atVS+rs0eUFKCuHh4QgPD8fr16+ViuWkpqaWyAQD4uvEz88P6enpmDNnDtatW4dr165xahJfM/kLnZw4caLY71u2cmtpC8eTGkJTVDJ+uoT1JAP/q37Ypk2bYvsOM2fOxJAhQ1SSDPOTm5uLnJwcGBgY4OrVqwgMDORek8vlRdllAHkVi/Pz6dMnmJqafpHzlFSZveKEDGoR1KpVC3fu3IFMJkN2djb27t2LRo0aFXe3Sh1WVlaoUaMGPn78qOTVqlChQomTvyG+Xlq2bAkg77osbRq/uqKkekijoqLg7++PtLQ0REZG4tGjRzh06FCJD8mTmmRYVDJ+ukRbT7KuEJtk6OzsDA8PD1StWhXlypWDjY0NAODVq1cwNjYu0j4DqpUfWZUPvmvqS0Bbmb3igJISRZCYmIjFixfj6tWrYBgGnTp1gr+/P6pWrVrcXSuVpKWloVy5ctDT08OLFy/w/Plz2NnZlbgyosTXheKuCR+lXf+3IDRr1gyGhobQ19dXKsJR3B5SNzc3rF+/Hl5eXggJCQEAuLi4qC3oUdIorUmGpRVtkgzv3r2Ld+/eoVOnTpzh+uLFC6SlpRVaBWGi9EMeahFUq1btq6mUWBR4eHhg//79+Pz5M0aOHAlLS0ucOnWKxpgoVu7evYtatWrB2dkZrVq1+mITfLShJHtIS2s4XkkMofkamDdvHqflzCYZzp07F//++y8CAgKwfv16lfe0bt1a5ViDBg103VWilEEGtQhiYmKwb98+xMbGKpUg/po9VgWBYRgYGRnh2LFjGDx4MEaPHl2ikjuIr5MrV67gypUriIiIQHh4OOzt7eHi4oImTZoUd9cIAUprOF5JDaH5GigtSYZE6YMMahFMmDABAwYMwP9r7+5Cmv7bOI5/tkGGQpgUQplBJHpgpCVGqAMryQdsGT1TJnkUDKKiEkUK0Qx6gFASI7QwsCzENdcDIUhIVEh2IC1IEkmliIwyJaa5+yD+u/Ovda/W3TZ7v478bd/td20H8mFc3+ubnp4eNL9+BDK3262uri7Z7XbPzM+JiQk/V4W/nclkktlsltlslsvlUmtrq3bv3i2r1apdu3b5uzxM4/jx46qoqNCbN29kNpuVkpISUKPMvmcmbDIMVoG2yRAzB4HaCyEhIcrPz/d3GTNGcXGxamtrtW7dOsXExOjVq1datWqVv8sC5HK51N7ertbWVg0MDGj37t3KyMjwd1n4jmBtxwvkFpqZLtA2GWLmYFOiF+x2u/r6+pSSkjJpFzCbEYCZ48iRI3rx4oXMZrNycnICbsYp/iuQT25E4GOTIf4fCNReOHPmjGw2m6Kjoz073A0GQ8Cd0hPoKioqVFJS8t1pCvSkw5/i4uI8s4wDaZIFpqqrq5vy2Ldj57q6uvxQFYC/GYHaCxkZGXI4HNPOqIT3uru7FR8fr8ePH0/7fHJy8h+uCECwY+wcgEBAD7UXYmJiNDw8zD9pH8XHx0v6GpyHhoYkfe2BBICfxdg5AIGEQO2F4eFhZWVladmyZZMOH6FF4edVVVXpypUrcrvdcrvdMplM2rVrl6xWq79LAxAkGDsHINDQ8uEFWhR+j/r6et2/f19lZWVatGiRpK8zvo8fP660tDQVFBT4t0AAQSFQT24E8PciUP+Czs5OORwOHTt2zN+lBJWNGzeqrq5uSpvH0NCQ9u7d6zk6GAAAIJjQ8uGlZ8+eyW636+7du1q4cKHWr1/v75KCzvj4+LQ90xEREZNOoAQAAAgmBOof6O3t9RxDPHfuXGVnZ8vtdquhocHfpQWlb/vPf+Y5AACAQEag/oGsrCwlJSWptrZWixcvliRdunTJv0UFsefPn2vFihVTHne73XK5XH6oCAAAwHcE6h+orq6Ww+FQfn6+0tLSlJOTI1rOf53T6fR3CQAAAL8dmxK9MDo6qra2NjkcDj18+FAWi0UZGRlKTU31d2kAAADwMwL1T/rw4YPu3LmjW7du6fLly/4uBwAAAH5GoAYAAAB8YPR3AQAAAEAwI1ADAAAAPiBQA4CfJSYmTrpubm5WWVnZH7v/06dPtWXLFlksFmVlZamqqkqS9OjRI6+O8fZ2HQDMVIzNA4C/3NGjR3Xu3DnFxcXpy5cv6u3tlSQ9fvxYoaGh086P/5a36wBgpiJQA0AA6+/vV3Fxsd6/f6+IiAhVVlZqwYIFKioqUkhIiJxOp969e6cTJ06opaVFT58+1fLly3Xy5ElJUkdHh6qqquRyubRo0SJVVlYqLCxs0j2GhoY0f/58SZLJZNLSpUvV39+vq1evymg06ubNmyotLdXHjx9VU1OjsbExhYeH6/Tp0/r8+fOUdUuWLNGxY8c0ODgoSSouLtbKlSv/7BcHAH8QgRoA/Ozz58+yWCye6w8fPmjNmjWSpPLycuXl5SkvL083btxQeXm5zp8/L0n6+PGjrl27pra2Nu3bt0+NjY2KiYnR5s2b5XQ6FRkZqZqaGtXX1ys0NFQXLlxQfX29rFbrpPvv2bNHmZmZSk5OVlpamvLy8hQVFaXt27crNDRUhYWFnrqamppkMBh0/fp1Xbx4UUVFRVPWHTp0SHv27FFSUpIGBwdVWFio27dv/4mvEgD8gkANAH42e/Zs2Ww2z3Vzc7O6u7slSV1dXZ6eZovFolOnTnnWpaeny2AwKDY2VvPmzVNsbKwkaenSpRoYGNDr16/V09OjHTt2SJLGxsaUkJAw5f5Wq1UbNmxQR0eHWltb5XA41NDQMGXd69evdeDAAb19+1Yul0tRUVHTfp4HDx6op6fHc/3p0yeNjIxM+WUcAGYKAjUABKlZs2ZJkgwGg+dvSTIajRofH5fRaFRKSorOnj37P98rOjpaO3fu1NatW7V69Wq9f/9+ypry8nIVFBRo7dq1evTokaqrq6d9r4mJCTU1NSkkJOQXPxkABBemfABAAEtMTJTD4ZAk2e12JSUlef3ahIQEPXnyRH19fZKk0dFRz4bDb7W3t+ufM776+vpkNBo1Z84chYWFaWRkxLNueHhYkZGRkqSWlhbP4/9el5qaOukXbqfT6XXNABCMCNQAEMBKS0vV3Nys3Nxc2Ww2lZSUeP3afzYxHjx4ULm5udq2bZtevnw5ZZ3NZlNmZqYsFosOHz6s06dPy2QyKT09Xffu3ZPFYlFnZ6esVqv279+vTZs2KTw83PP6f68rKSlRd3e3cnNzlZ2drcbGxt/xVQBAwOLocQAAAMAH/EINAAAA+IBADQAAAPiAQA0AAAD4gEANAAAA+IBADQAAAPiAQA0AAAD4gEANAAAA+IBADQAAAPjgPwiY689HrMFhAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 864x216 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "(names\n",
    "    .Home\n",
    "    .value_counts()\n",
    "    .sort_index()\n",
    "    .plot(kind='bar', figsize=(12, 3), \n",
    "          title=\"Distribution of sample by home state\",\n",
    "          xlabel='Home State',\n",
    "          ylabel='Number of Occurrences')\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "3fbf89eb-f164-4f12-92fd-05e2648f7d05",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:title={'center':'2019 Population of U.S. states and territories'}, xlabel='State', ylabel='Population'>"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x216 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "(states\n",
    "    .sort_values('State')\n",
    "    [['State', 'Population_2019']]\n",
    "    .set_index('State')\n",
    "    .plot(kind='bar', figsize=(12, 3),\n",
    "          title=\"2019 Population of U.S. states and territories\",\n",
    "          xlabel='State',\n",
    "          ylabel='Population')\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "209d9254-4998-4c11-a3c3-4a64e085d98b",
   "metadata": {},
   "source": [
    "### Class Imbalance"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a178e527-3caa-4a2d-b6fe-4a39b05eb67c",
   "metadata": {},
   "source": [
    "Example: Apache server logs (adapted from CleanData)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "473113fa-0c2c-49a6-9f00-714ae69632d0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  10280 200\n",
      "      2 206\n",
      "    398 301\n",
      "   1680 304\n",
      "    181 403\n",
      "    901 404\n",
      "      9 500\n"
     ]
    }
   ],
   "source": [
    "%%bash\n",
    "zcat ../data/gnosis/*.log.gz | \n",
    "    cut -d' ' -f9 | \n",
    "    sort | \n",
    "    uniq -c"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "ba83982c-cbd5-4bf4-b2f4-fa2da2a42ead",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "162.158.238.207 - - [30/Mar/2020:00:00:00 -0400]\n",
      "\"GET /TPiP/024.code HTTP/1.1\" 200 75\n"
     ]
    }
   ],
   "source": [
    "%%bash\n",
    "zcat ../data/gnosis/20200330.log.gz | head -1 | fmt -w50"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "424cac03-e272-4cab-bbda-40adb34f1375",
   "metadata": {},
   "outputs": [],
   "source": [
    "def apache_log_to_df(fname):\n",
    "    # Read one log file.  Treat is as a space separated file\n",
    "    # There is no explicit header, so we assign columns\n",
    "    cols = ['ip_address', 'ident', 'userid', 'timestamp', \n",
    "            'tz', 'request', 'status', 'size']\n",
    "    df = pd.read_csv(fname, sep=' ', header=None, names=cols)\n",
    "    \n",
    "    # The first pass gets something workable, but refine it\n",
    "    # Datetime has superfluous '[', but fmt matches that\n",
    "    fmt = \"[%d/%b/%Y:%H:%M:%S\"\n",
    "    df['timestamp'] = pd.to_datetime(df.timestamp, format=fmt)\n",
    "    \n",
    "    # Convert timezone to an integer\n",
    "    # Not general, I know these logs use integral timezone\n",
    "    # E.g. India Standard Time (GMT+5:30) would break this\n",
    "    df['tz'] = df.tz.str[:3].astype(int)\n",
    "    \n",
    "    # Break up the quoted request into sub-components\n",
    "    df[['method', 'resource', 'protocol']] = (\n",
    "                df.request.str.split(' ', expand=True))\n",
    "    \n",
    "    # Break the IP address into each quad\n",
    "    df[['quad1', 'quad2', 'quad3', 'quad4']] = (\n",
    "                df.ip_address.str.split('.', expand=True))\n",
    "    \n",
    "    # Pandas lets us pull components from datetime\n",
    "    df['hour'] = df.timestamp.dt.hour\n",
    "    df['minute'] = df.timestamp.dt.minute\n",
    "    \n",
    "    # Split resource into the path/directory vs. actual page\n",
    "    df[['path', 'page']] = (\n",
    "                df.resource.str.rsplit('/', n=1, expand=True))\n",
    "    # Only care about some fields for current purposes\n",
    "    cols = ['hour', 'minute', \n",
    "            'quad1', 'quad2', 'quad3', 'quad4', \n",
    "            'method', 'path', 'page', 'status']\n",
    "    return df[cols]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "2471463a-b3d5-4f0c-aca2-24e0dbcc7ffb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>hour</th>\n",
       "      <th>minute</th>\n",
       "      <th>quad1</th>\n",
       "      <th>quad2</th>\n",
       "      <th>method</th>\n",
       "      <th>path</th>\n",
       "      <th>page</th>\n",
       "      <th>status</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>108</td>\n",
       "      <td>162</td>\n",
       "      <td>GET</td>\n",
       "      <td>/download/gnosis/xml/pickle/ext</td>\n",
       "      <td></td>\n",
       "      <td>200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>162</td>\n",
       "      <td>158</td>\n",
       "      <td>GET</td>\n",
       "      <td>/download/relax</td>\n",
       "      <td>rnc2rng</td>\n",
       "      <td>200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>10</td>\n",
       "      <td>162</td>\n",
       "      <td>158</td>\n",
       "      <td>GET</td>\n",
       "      <td>/publish</td>\n",
       "      <td>rss.xml</td>\n",
       "      <td>403</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>10</td>\n",
       "      <td>162</td>\n",
       "      <td>158</td>\n",
       "      <td>GET</td>\n",
       "      <td>/publish/programming</td>\n",
       "      <td>charming_python_6.html</td>\n",
       "      <td>200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>172</td>\n",
       "      <td>69</td>\n",
       "      <td>GET</td>\n",
       "      <td>/download/gnosis/xml/pickle/doc</td>\n",
       "      <td>THANKS_TO</td>\n",
       "      <td>200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13446</th>\n",
       "      <td>23</td>\n",
       "      <td>45</td>\n",
       "      <td>108</td>\n",
       "      <td>162</td>\n",
       "      <td>GET</td>\n",
       "      <td>/TPiP</td>\n",
       "      <td>036.code</td>\n",
       "      <td>304</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13447</th>\n",
       "      <td>23</td>\n",
       "      <td>47</td>\n",
       "      <td>172</td>\n",
       "      <td>69</td>\n",
       "      <td>GET</td>\n",
       "      <td>/download/relax</td>\n",
       "      <td>regextest.rnc</td>\n",
       "      <td>200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13448</th>\n",
       "      <td>23</td>\n",
       "      <td>52</td>\n",
       "      <td>172</td>\n",
       "      <td>69</td>\n",
       "      <td>GET</td>\n",
       "      <td>/juvenilia</td>\n",
       "      <td>The%20rivers%20flow.pdf</td>\n",
       "      <td>200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13449</th>\n",
       "      <td>23</td>\n",
       "      <td>57</td>\n",
       "      <td>172</td>\n",
       "      <td>69</td>\n",
       "      <td>GET</td>\n",
       "      <td>/TPiP</td>\n",
       "      <td>214.code</td>\n",
       "      <td>200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13450</th>\n",
       "      <td>23</td>\n",
       "      <td>58</td>\n",
       "      <td>172</td>\n",
       "      <td>68</td>\n",
       "      <td>GET</td>\n",
       "      <td>/publish/programming</td>\n",
       "      <td>charming_python_6.html</td>\n",
       "      <td>200</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>13451 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       hour  minute quad1 quad2 method                             path  \\\n",
       "0         0       1   108   162    GET  /download/gnosis/xml/pickle/ext   \n",
       "1         0       4   162   158    GET                  /download/relax   \n",
       "2         0      10   162   158    GET                         /publish   \n",
       "3         0      10   162   158    GET             /publish/programming   \n",
       "4         0      12   172    69    GET  /download/gnosis/xml/pickle/doc   \n",
       "...     ...     ...   ...   ...    ...                              ...   \n",
       "13446    23      45   108   162    GET                            /TPiP   \n",
       "13447    23      47   172    69    GET                  /download/relax   \n",
       "13448    23      52   172    69    GET                       /juvenilia   \n",
       "13449    23      57   172    69    GET                            /TPiP   \n",
       "13450    23      58   172    68    GET             /publish/programming   \n",
       "\n",
       "                          page  status  \n",
       "0                                  200  \n",
       "1                      rnc2rng     200  \n",
       "2                      rss.xml     403  \n",
       "3       charming_python_6.html     200  \n",
       "4                    THANKS_TO     200  \n",
       "...                        ...     ...  \n",
       "13446                 036.code     304  \n",
       "13447            regextest.rnc     200  \n",
       "13448  The%20rivers%20flow.pdf     200  \n",
       "13449                 214.code     200  \n",
       "13450   charming_python_6.html     200  \n",
       "\n",
       "[13451 rows x 8 columns]"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reqs = pd.concat(map(apache_log_to_df, \n",
    "                 glob.glob('../data/gnosis/*.log.gz')))\n",
    "# Each file has index from 0, so dups occur in raw version\n",
    "reqs = reqs.reset_index().drop('index', axis=1)\n",
    "# The /16 subnetwork is too random for this purpose\n",
    "reqs.drop(['quad3', 'quad4'], axis=1, inplace=True)\n",
    "reqs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "f01fb9cd-d664-48f1-ae0a-8b206570f824",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'hour distibution')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'hour')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Amount')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'minute distibution')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'minute')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Amount')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'quad1 distibution')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'quad1')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Amount')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'quad2 distibution')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'quad2')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Amount')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'method distibution')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'method')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Amount')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'status distibution')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'status')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Amount')"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x648 with 6 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axes = plt.subplots(3, 2, figsize=(12, 9))\n",
    "\n",
    "# Which factors should we analyze for class balance?\n",
    "factors = ['hour', 'minute', 'quad1', 'quad2', 'method', 'status']\n",
    "\n",
    "# Loop through the axis subplots and the factors\n",
    "for col, ax in zip(factors, axes.flatten()):\n",
    "    # Minute is categorical but too many so quantize\n",
    "    if col == 'minute':\n",
    "        data = (reqs[col] // 5 * 5).value_counts()\n",
    "    else:\n",
    "        data = reqs[col].value_counts()\n",
    "    # sort x-axis\n",
    "    data = data.sort_index()\n",
    "    data.plot(kind='bar', ax=ax)\n",
    "    ax.set_title(f\"{col} distibution\")\n",
    "    ax.set_xlabel(col)\n",
    "    ax.set_ylabel(\"Amount\")\n",
    "\n",
    "# Matplotlib trick to improve spacing of subplots\n",
    "fig.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "236baa38-ab61-4405-b751-fa2dcd4d3d32",
   "metadata": {},
   "source": [
    "### Normalization and Scaling"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5498afe7-588a-4a86-bc4d-726683d1e979",
   "metadata": {},
   "source": [
    "Example based on synthetic data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "e5d37397-88b2-49cf-a725-d5a7b458f78a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Synthetic data to illustrate scaling\n",
    "def make_unscaled_features(N=200, j1=1/50, j2=1/10):\n",
    "    \"\"\"Create DataFrame of synthetic data\n",
    "    \n",
    "    Feature_1 will be:\n",
    "      * positively correlated with Target\n",
    "      * numerically small values\n",
    "    Feature_2 will be:\n",
    "      * negatively correlatged with Target\n",
    "      * numerically large values\n",
    "    \n",
    "    N  - number of rows to geneate\n",
    "    j1 - the relative scale of random jitter for F1\n",
    "    j2 - the relative scale of random jitter for F2\n",
    "    \"\"\"\n",
    "    assert j2 > j1\n",
    "    # Repeatable randomness\n",
    "    np.random.seed(1)\n",
    "    \n",
    "    # Target points range from 10 to 20\n",
    "    target = np.linspace(10, 20, N)\n",
    "    \n",
    "    # Feature_1 is roughly 1/100th size of Target\n",
    "    feat1 = target / 100\n",
    "    feat1 += np.random.normal(\n",
    "        loc=0, scale=np.max(feat1)*j1, size=N) \n",
    "\n",
    "    # Feature_2 is around 20,000\n",
    "    feat2 = np.linspace(21_000, 19_000, N)\n",
    "    feat2 += np.random.normal(\n",
    "        loc=0, scale=np.max(feat2)*j2, size=N)\n",
    "\n",
    "    df = pd.DataFrame({'Feature_1': feat1, \n",
    "                       'Feature_2': feat2, \n",
    "                       'Target': target})\n",
    "    return (df.sample(frac=1)\n",
    "              .reset_index()\n",
    "              .drop('index', axis=1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "a37a9e62-31c8-49cb-9fd4-d352e9a62f51",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Feature_1</th>\n",
       "      <th>Feature_2</th>\n",
       "      <th>Target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.112999</td>\n",
       "      <td>19247.756104</td>\n",
       "      <td>11.407035</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.204178</td>\n",
       "      <td>23432.270613</td>\n",
       "      <td>20.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.173678</td>\n",
       "      <td>19179.445753</td>\n",
       "      <td>17.336683</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.161411</td>\n",
       "      <td>17579.625264</td>\n",
       "      <td>16.633166</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.192209</td>\n",
       "      <td>19255.160726</td>\n",
       "      <td>19.095477</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>195</th>\n",
       "      <td>0.110874</td>\n",
       "      <td>20213.848541</td>\n",
       "      <td>10.502513</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>196</th>\n",
       "      <td>0.137692</td>\n",
       "      <td>20934.654450</td>\n",
       "      <td>13.316583</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>197</th>\n",
       "      <td>0.184393</td>\n",
       "      <td>18855.241195</td>\n",
       "      <td>18.241206</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>198</th>\n",
       "      <td>0.177846</td>\n",
       "      <td>19760.314890</td>\n",
       "      <td>17.839196</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>199</th>\n",
       "      <td>0.145229</td>\n",
       "      <td>20497.722353</td>\n",
       "      <td>14.371859</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>200 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Feature_1     Feature_2     Target\n",
       "0     0.112999  19247.756104  11.407035\n",
       "1     0.204178  23432.270613  20.000000\n",
       "2     0.173678  19179.445753  17.336683\n",
       "3     0.161411  17579.625264  16.633166\n",
       "4     0.192209  19255.160726  19.095477\n",
       "..         ...           ...        ...\n",
       "195   0.110874  20213.848541  10.502513\n",
       "196   0.137692  20934.654450  13.316583\n",
       "197   0.184393  18855.241195  18.241206\n",
       "198   0.177846  19760.314890  17.839196\n",
       "199   0.145229  20497.722353  14.371859\n",
       "\n",
       "[200 rows x 3 columns]"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "unscaled = make_unscaled_features()\n",
    "unscaled"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "03e0098b-8e40-45df-b306-9eb906ad355c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Feature_1</th>\n",
       "      <th>Feature_2</th>\n",
       "      <th>Target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Feature_1</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.272963</td>\n",
       "      <td>0.992514</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Feature_2</th>\n",
       "      <td>-0.272963</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.269406</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Target</th>\n",
       "      <td>0.992514</td>\n",
       "      <td>-0.269406</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Feature_1  Feature_2    Target\n",
       "Feature_1   1.000000  -0.272963  0.992514\n",
       "Feature_2  -0.272963   1.000000 -0.269406\n",
       "Target      0.992514  -0.269406  1.000000"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# univariate correlation with target?\n",
    "unscaled.corr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "102faf5b-9260-4f7b-88fc-e3d44f96823a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x288 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_univariate_trends(df, Target='Target'):\n",
    "    df = df.sort_values(Target)\n",
    "    target = df[Target]\n",
    "    X = df.drop(Target, axis=1)\n",
    "    n_feat = len(X.columns)\n",
    "    fig, axes = plt.subplots(n_feat, 1,\n",
    "                             figsize=(10, n_feat*2))\n",
    "    for ax, col in zip(axes, X.columns):\n",
    "        ax.plot(target, X[col])\n",
    "        ax.set_title(f\"{col} as a function of {Target}\")\n",
    "        ax.set_xlabel(f\"{Target}\")\n",
    "        ax.set_ylabel(f\"{col}\")\n",
    "        \n",
    "    fig.tight_layout()\n",
    "    \n",
    "plot_univariate_trends(unscaled)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e0fb6c0d-b4a3-40ac-a8e9-fba71d38e656",
   "metadata": {},
   "source": [
    "#### Applying a ML Model on unscaled vs. scaled data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "id": "8aa9492f-6655-4951-95b7-3db642225921",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.027756186064182953"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = unscaled.drop('Target', axis=1)\n",
    "y = unscaled['Target']\n",
    "\n",
    "X_train, X_test, y_train, y_test = (\n",
    "    train_test_split(X, y, random_state=1))\n",
    "\n",
    "knn = KNeighborsRegressor()\n",
    "knn.fit(X_train, y_train).score(X_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "id": "accc963b-a11d-44b4-91ce-e7f0297ca7c0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9743878175626131"
      ]
     },
     "execution_count": 129,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# use MinMaxScaler\n",
    "X_scaled = MinMaxScaler().fit_transform(X)\n",
    "\n",
    "X_train, X_test, y_train, y_test = (\n",
    "    train_test_split(X_scaled, y, random_state=1))\n",
    "\n",
    "knn2 = KNeighborsRegressor()\n",
    "knn2.fit(X_train, y_train).score(X_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 160,
   "id": "6b0d615c-e8b1-4542-8eb6-7e410ddbfaca",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([ 1.,  5.,  2.,  8.,  6., 12.,  5.,  6.,  7.,  7.,  9.,  4.,  8.,\n",
       "        10.,  7.,  7., 10.,  7.,  4.,  7., 10.,  5., 10.,  6.,  7.,  6.,\n",
       "         6.,  8.,  4.,  6.]),\n",
       " array([0.09330641, 0.09700212, 0.10069783, 0.10439354, 0.10808926,\n",
       "        0.11178497, 0.11548068, 0.11917639, 0.1228721 , 0.12656782,\n",
       "        0.13026353, 0.13395924, 0.13765495, 0.14135066, 0.14504638,\n",
       "        0.14874209, 0.1524378 , 0.15613351, 0.15982922, 0.16352494,\n",
       "        0.16722065, 0.17091636, 0.17461207, 0.17830778, 0.1820035 ,\n",
       "        0.18569921, 0.18939492, 0.19309063, 0.19678634, 0.20048206,\n",
       "        0.20417777]),\n",
       " <BarContainer object of 30 artists>)"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Value Distribution of Feature_1 before Scaling')"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'Feature_1')"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Values')"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "(array([ 1.,  0.,  2.,  2.,  4.,  1.,  1.,  0.,  8.,  4., 13., 21., 11.,\n",
       "        15., 14., 13., 19., 15.,  9.,  9., 12.,  6.,  4.,  3.,  3.,  4.,\n",
       "         2.,  2.,  0.,  2.]),\n",
       " array([13478.28565813, 13902.97851262, 14327.67136711, 14752.36422159,\n",
       "        15177.05707608, 15601.74993057, 16026.44278506, 16451.13563954,\n",
       "        16875.82849403, 17300.52134852, 17725.21420301, 18149.9070575 ,\n",
       "        18574.59991198, 18999.29276647, 19423.98562096, 19848.67847545,\n",
       "        20273.37132994, 20698.06418442, 21122.75703891, 21547.4498934 ,\n",
       "        21972.14274789, 22396.83560237, 22821.52845686, 23246.22131135,\n",
       "        23670.91416584, 24095.60702033, 24520.29987481, 24944.9927293 ,\n",
       "        25369.68558379, 25794.37843828, 26219.07129277]),\n",
       " <BarContainer object of 30 artists>)"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Value Distribution of Feature_2 before Scaling')"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'Feature_2')"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Values')"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "(array([ 1.,  5.,  2.,  8.,  6., 12.,  5.,  6.,  7.,  7.,  9.,  4.,  8.,\n",
       "        10.,  7.,  7., 10.,  7.,  4.,  7., 10.,  5., 10.,  6.,  7.,  6.,\n",
       "         6.,  8.,  4.,  6.]),\n",
       " array([0.        , 0.03333333, 0.06666667, 0.1       , 0.13333333,\n",
       "        0.16666667, 0.2       , 0.23333333, 0.26666667, 0.3       ,\n",
       "        0.33333333, 0.36666667, 0.4       , 0.43333333, 0.46666667,\n",
       "        0.5       , 0.53333333, 0.56666667, 0.6       , 0.63333333,\n",
       "        0.66666667, 0.7       , 0.73333333, 0.76666667, 0.8       ,\n",
       "        0.83333333, 0.86666667, 0.9       , 0.93333333, 0.96666667,\n",
       "        1.        ]),\n",
       " <BarContainer object of 30 artists>)"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Value Distribution of Feature_1 after Scaling')"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'Feature_1')"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Values')"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "(array([ 1.,  0.,  2.,  2.,  4.,  1.,  1.,  0.,  8.,  4., 13., 21., 11.,\n",
       "        15., 14., 13., 19., 15.,  9.,  9., 12.,  6.,  4.,  3.,  3.,  4.,\n",
       "         2.,  2.,  0.,  2.]),\n",
       " array([0.        , 0.03333333, 0.06666667, 0.1       , 0.13333333,\n",
       "        0.16666667, 0.2       , 0.23333333, 0.26666667, 0.3       ,\n",
       "        0.33333333, 0.36666667, 0.4       , 0.43333333, 0.46666667,\n",
       "        0.5       , 0.53333333, 0.56666667, 0.6       , 0.63333333,\n",
       "        0.66666667, 0.7       , 0.73333333, 0.76666667, 0.8       ,\n",
       "        0.83333333, 0.86666667, 0.9       , 0.93333333, 0.96666667,\n",
       "        1.        ]),\n",
       " <BarContainer object of 30 artists>)"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Value Distribution of Feature_2 after Scaling')"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'Feature_2')"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Values')"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x1080 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# inspect changes in distribution before and after scaling \n",
    "X_scaled = pd.DataFrame(X_scaled)\n",
    "X_scaled.columns={\"Feature_1\", \"Feature_2\"}\n",
    "fig, axes = plt.subplots(2,2, figsize=(20,15))\n",
    "\n",
    "axes[0,0].hist(X['Feature_1'], bins=30)\n",
    "axes[0,0].set_title(\"Value Distribution of Feature_1 before Scaling\")\n",
    "axes[0,0].set_xlabel(\"Feature_1\")\n",
    "axes[0,0].set_ylabel(\"Values\")\n",
    "\n",
    "axes[0,1].hist(X['Feature_2'], bins=30)\n",
    "axes[0,1].set_title(\"Value Distribution of Feature_2 before Scaling\")\n",
    "axes[0,1].set_xlabel(\"Feature_2\")\n",
    "axes[0,1].set_ylabel(\"Values\")\n",
    "\n",
    "axes[1,0].hist(X_scaled['Feature_1'], bins=30)\n",
    "axes[1,0].set_title(\"Value Distribution of Feature_1 after Scaling\")\n",
    "axes[1,0].set_xlabel(\"Feature_1\")\n",
    "axes[1,0].set_ylabel(\"Values\")\n",
    "\n",
    "axes[1,1].hist(X_scaled['Feature_2'], bins=30)\n",
    "axes[1,1].set_title(\"Value Distribution of Feature_2 after Scaling\")\n",
    "axes[1,1].set_xlabel(\"Feature_2\")\n",
    "axes[1,1].set_ylabel(\"Values\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "dataeng_kernel",
   "language": "python",
   "name": "dataeng_kernel"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}