demo_V4 .ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\tomma\\AppData\\Local\\Temp\\ipykernel_11616\\119758007.py:8: DtypeWarning: Columns (8,12,13,14,15,16,50,51,52,53,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  df = pd.read_csv('dataset/survey_results_public.csv', sep=',')\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 98855 entries, 0 to 98854\n",
      "Columns: 129 entries, Respondent to SurveyEasy\n",
      "dtypes: float64(41), int64(1), object(87)\n",
      "memory usage: 97.3+ MB\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "None"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>Respondent</th>\n",
       "      <th>AssessJob1</th>\n",
       "      <th>AssessJob2</th>\n",
       "      <th>AssessJob3</th>\n",
       "      <th>AssessJob4</th>\n",
       "      <th>AssessJob5</th>\n",
       "      <th>AssessJob6</th>\n",
       "      <th>AssessJob7</th>\n",
       "      <th>AssessJob8</th>\n",
       "      <th>AssessJob9</th>\n",
       "      <th>...</th>\n",
       "      <th>JobEmailPriorities6</th>\n",
       "      <th>JobEmailPriorities7</th>\n",
       "      <th>ConvertedSalary</th>\n",
       "      <th>AdsPriorities1</th>\n",
       "      <th>AdsPriorities2</th>\n",
       "      <th>AdsPriorities3</th>\n",
       "      <th>AdsPriorities4</th>\n",
       "      <th>AdsPriorities5</th>\n",
       "      <th>AdsPriorities6</th>\n",
       "      <th>AdsPriorities7</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>98855.000000</td>\n",
       "      <td>66985.000000</td>\n",
       "      <td>66985.000000</td>\n",
       "      <td>66985.000000</td>\n",
       "      <td>66985.000000</td>\n",
       "      <td>66985.000000</td>\n",
       "      <td>66985.000000</td>\n",
       "      <td>66985.000000</td>\n",
       "      <td>66985.000000</td>\n",
       "      <td>66985.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>46213.00000</td>\n",
       "      <td>46213.000000</td>\n",
       "      <td>4.770200e+04</td>\n",
       "      <td>60479.000000</td>\n",
       "      <td>60479.000000</td>\n",
       "      <td>60479.000000</td>\n",
       "      <td>60479.000000</td>\n",
       "      <td>60479.000000</td>\n",
       "      <td>60479.000000</td>\n",
       "      <td>60479.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>50822.971635</td>\n",
       "      <td>6.397089</td>\n",
       "      <td>6.673524</td>\n",
       "      <td>5.906875</td>\n",
       "      <td>4.065791</td>\n",
       "      <td>3.953243</td>\n",
       "      <td>4.407196</td>\n",
       "      <td>5.673181</td>\n",
       "      <td>4.225200</td>\n",
       "      <td>7.640009</td>\n",
       "      <td>...</td>\n",
       "      <td>4.97425</td>\n",
       "      <td>4.836388</td>\n",
       "      <td>9.578086e+04</td>\n",
       "      <td>2.726880</td>\n",
       "      <td>3.805784</td>\n",
       "      <td>3.340945</td>\n",
       "      <td>3.782470</td>\n",
       "      <td>4.383604</td>\n",
       "      <td>5.138809</td>\n",
       "      <td>4.821459</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>29321.650410</td>\n",
       "      <td>2.788428</td>\n",
       "      <td>2.531202</td>\n",
       "      <td>2.642734</td>\n",
       "      <td>2.541196</td>\n",
       "      <td>2.520499</td>\n",
       "      <td>2.502069</td>\n",
       "      <td>2.923998</td>\n",
       "      <td>2.507411</td>\n",
       "      <td>2.407457</td>\n",
       "      <td>...</td>\n",
       "      <td>1.86063</td>\n",
       "      <td>1.659844</td>\n",
       "      <td>2.023482e+05</td>\n",
       "      <td>1.881078</td>\n",
       "      <td>1.821323</td>\n",
       "      <td>1.673485</td>\n",
       "      <td>1.844864</td>\n",
       "      <td>1.931746</td>\n",
       "      <td>1.853249</td>\n",
       "      <td>1.874895</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.00000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>25443.500000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>4.00000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>2.384400e+04</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>50823.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>5.00000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>5.507500e+04</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>5.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>76219.500000</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>7.00000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>9.300000e+04</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>7.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>101592.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>7.00000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>2.000000e+06</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>7.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 42 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          Respondent    AssessJob1    AssessJob2    AssessJob3    AssessJob4  \\\n",
       "count   98855.000000  66985.000000  66985.000000  66985.000000  66985.000000   \n",
       "mean    50822.971635      6.397089      6.673524      5.906875      4.065791   \n",
       "std     29321.650410      2.788428      2.531202      2.642734      2.541196   \n",
       "min         1.000000      1.000000      1.000000      1.000000      1.000000   \n",
       "25%     25443.500000      4.000000      5.000000      4.000000      2.000000   \n",
       "50%     50823.000000      7.000000      7.000000      6.000000      4.000000   \n",
       "75%     76219.500000      9.000000      9.000000      8.000000      6.000000   \n",
       "max    101592.000000     10.000000     10.000000     10.000000     10.000000   \n",
       "\n",
       "         AssessJob5    AssessJob6    AssessJob7    AssessJob8    AssessJob9  \\\n",
       "count  66985.000000  66985.000000  66985.000000  66985.000000  66985.000000   \n",
       "mean       3.953243      4.407196      5.673181      4.225200      7.640009   \n",
       "std        2.520499      2.502069      2.923998      2.507411      2.407457   \n",
       "min        1.000000      1.000000      1.000000      1.000000      1.000000   \n",
       "25%        2.000000      2.000000      3.000000      2.000000      6.000000   \n",
       "50%        3.000000      4.000000      6.000000      4.000000      8.000000   \n",
       "75%        6.000000      6.000000      8.000000      6.000000     10.000000   \n",
       "max       10.000000     10.000000     10.000000     10.000000     10.000000   \n",
       "\n",
       "       ...  JobEmailPriorities6  JobEmailPriorities7  ConvertedSalary  \\\n",
       "count  ...          46213.00000         46213.000000     4.770200e+04   \n",
       "mean   ...              4.97425             4.836388     9.578086e+04   \n",
       "std    ...              1.86063             1.659844     2.023482e+05   \n",
       "min    ...              1.00000             1.000000     0.000000e+00   \n",
       "25%    ...              4.00000             4.000000     2.384400e+04   \n",
       "50%    ...              5.00000             5.000000     5.507500e+04   \n",
       "75%    ...              7.00000             6.000000     9.300000e+04   \n",
       "max    ...              7.00000             7.000000     2.000000e+06   \n",
       "\n",
       "       AdsPriorities1  AdsPriorities2  AdsPriorities3  AdsPriorities4  \\\n",
       "count    60479.000000    60479.000000    60479.000000    60479.000000   \n",
       "mean         2.726880        3.805784        3.340945        3.782470   \n",
       "std          1.881078        1.821323        1.673485        1.844864   \n",
       "min          1.000000        1.000000        1.000000        1.000000   \n",
       "25%          1.000000        2.000000        2.000000        2.000000   \n",
       "50%          2.000000        4.000000        3.000000        4.000000   \n",
       "75%          4.000000        5.000000        5.000000        5.000000   \n",
       "max          7.000000        7.000000        7.000000        7.000000   \n",
       "\n",
       "       AdsPriorities5  AdsPriorities6  AdsPriorities7  \n",
       "count    60479.000000    60479.000000    60479.000000  \n",
       "mean         4.383604        5.138809        4.821459  \n",
       "std          1.931746        1.853249        1.874895  \n",
       "min          1.000000        1.000000        1.000000  \n",
       "25%          3.000000        4.000000        3.000000  \n",
       "50%          5.000000        6.000000        5.000000  \n",
       "75%          6.000000        7.000000        7.000000  \n",
       "max          7.000000        7.000000        7.000000  \n",
       "\n",
       "[8 rows x 42 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from matplotlib import pyplot as plt\n",
    "import seaborn as sns\n",
    "from scipy.stats import chi2_contingency\n",
    "import numpy as np\n",
    "from IPython.display import display\n",
    "\n",
    "df = pd.read_csv('dataset/survey_results_public.csv', sep=',')\n",
    "display(df.info())\n",
    "display(df.describe())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>Hobby</th>\n",
       "      <th>OpenSource</th>\n",
       "      <th>Country</th>\n",
       "      <th>Employment</th>\n",
       "      <th>FormalEducation</th>\n",
       "      <th>UndergradMajor</th>\n",
       "      <th>JobSatisfaction</th>\n",
       "      <th>ConvertedSalary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>Employed full-time</td>\n",
       "      <td>Bachelor’s degree (BA, BS, B.Eng., etc.)</td>\n",
       "      <td>A natural science (ex. biology, chemistry, phy...</td>\n",
       "      <td>Moderately dissatisfied</td>\n",
       "      <td>70841.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>South Africa</td>\n",
       "      <td>Employed full-time</td>\n",
       "      <td>Some college/university study without earning ...</td>\n",
       "      <td>Computer science, computer engineering, or sof...</td>\n",
       "      <td>Slightly satisfied</td>\n",
       "      <td>21426.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>Employed full-time</td>\n",
       "      <td>Bachelor’s degree (BA, BS, B.Eng., etc.)</td>\n",
       "      <td>Computer science, computer engineering, or sof...</td>\n",
       "      <td>Moderately satisfied</td>\n",
       "      <td>41671.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>United States</td>\n",
       "      <td>Employed full-time</td>\n",
       "      <td>Some college/university study without earning ...</td>\n",
       "      <td>Computer science, computer engineering, or sof...</td>\n",
       "      <td>Slightly satisfied</td>\n",
       "      <td>120000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>United States</td>\n",
       "      <td>Employed full-time</td>\n",
       "      <td>Some college/university study without earning ...</td>\n",
       "      <td>Fine arts or performing arts (ex. graphic desi...</td>\n",
       "      <td>Moderately satisfied</td>\n",
       "      <td>250000.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Hobby OpenSource         Country          Employment  \\\n",
       "1   Yes        Yes  United Kingdom  Employed full-time   \n",
       "4   Yes         No    South Africa  Employed full-time   \n",
       "5   Yes         No  United Kingdom  Employed full-time   \n",
       "6   Yes        Yes   United States  Employed full-time   \n",
       "8   Yes        Yes   United States  Employed full-time   \n",
       "\n",
       "                                     FormalEducation  \\\n",
       "1           Bachelor’s degree (BA, BS, B.Eng., etc.)   \n",
       "4  Some college/university study without earning ...   \n",
       "5           Bachelor’s degree (BA, BS, B.Eng., etc.)   \n",
       "6  Some college/university study without earning ...   \n",
       "8  Some college/university study without earning ...   \n",
       "\n",
       "                                      UndergradMajor          JobSatisfaction  \\\n",
       "1  A natural science (ex. biology, chemistry, phy...  Moderately dissatisfied   \n",
       "4  Computer science, computer engineering, or sof...       Slightly satisfied   \n",
       "5  Computer science, computer engineering, or sof...     Moderately satisfied   \n",
       "6  Computer science, computer engineering, or sof...       Slightly satisfied   \n",
       "8  Fine arts or performing arts (ex. graphic desi...     Moderately satisfied   \n",
       "\n",
       "   ConvertedSalary  \n",
       "1          70841.0  \n",
       "4          21426.0  \n",
       "5          41671.0  \n",
       "6         120000.0  \n",
       "8         250000.0  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "columns=['Hobby','OpenSource','Country','Employment',\\\n",
    "    'FormalEducation','UndergradMajor','JobSatisfaction','ConvertedSalary']\n",
    "\n",
    "data=df.get(columns).dropna()\n",
    "data.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "js_dict = {\n",
    "    'Extremely dissatisfied':0,\n",
    "    'Moderately dissatisfied':1,\n",
    "    'Slightly dissatisfied':2,\n",
    "    'Neither satisfied nor dissatisfied':3,\n",
    "    'Slightly satisfied':4,\n",
    "    'Moderately satisfied':5,\n",
    "    'Extremely satisfied':6,\n",
    "}\n",
    "\n",
    "data['JobSatisfaction']=data['JobSatisfaction'].map(js_dict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = data.replace('Bachelor’s degree (BA, BS, B.Eng., etc.)',\"Bachelor\")\n",
    "data = data.replace('Master’s degree (MA, MS, M.Eng., MBA, etc.)',\"Master\")\n",
    "data = data.replace('Other doctoral degree (Ph.D, Ed.D., etc.)',\"Ph.D\")\n",
    "data = data[data['FormalEducation'].isin(['Bachelor','Master','Ph.D'])]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "countries=data.groupby('Country').size().sort_values()[-3:].index.tolist()\n",
    "data = data[data['Country'].isin(countries)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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></th>\n",
       "      <th>Country</th>\n",
       "      <th>Employment</th>\n",
       "      <th>FormalEducation</th>\n",
       "      <th>Hobby</th>\n",
       "      <th>OpenSource</th>\n",
       "      <th>UndergradMajor</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ConvertedSalary</th>\n",
       "      <th>JobSatisfaction</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 rowspan=\"7\" valign=\"top\">0-250.000</th>\n",
       "      <th>0</th>\n",
       "      <td>494</td>\n",
       "      <td>494</td>\n",
       "      <td>494</td>\n",
       "      <td>494</td>\n",
       "      <td>494</td>\n",
       "      <td>494</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1371</td>\n",
       "      <td>1371</td>\n",
       "      <td>1371</td>\n",
       "      <td>1371</td>\n",
       "      <td>1371</td>\n",
       "      <td>1371</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1547</td>\n",
       "      <td>1547</td>\n",
       "      <td>1547</td>\n",
       "      <td>1547</td>\n",
       "      <td>1547</td>\n",
       "      <td>1547</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>858</td>\n",
       "      <td>858</td>\n",
       "      <td>858</td>\n",
       "      <td>858</td>\n",
       "      <td>858</td>\n",
       "      <td>858</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2014</td>\n",
       "      <td>2014</td>\n",
       "      <td>2014</td>\n",
       "      <td>2014</td>\n",
       "      <td>2014</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5587</td>\n",
       "      <td>5587</td>\n",
       "      <td>5587</td>\n",
       "      <td>5587</td>\n",
       "      <td>5587</td>\n",
       "      <td>5587</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2976</td>\n",
       "      <td>2976</td>\n",
       "      <td>2976</td>\n",
       "      <td>2976</td>\n",
       "      <td>2976</td>\n",
       "      <td>2976</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"7\" valign=\"top\">1.000.000+</th>\n",
       "      <th>0</th>\n",
       "      <td>14</td>\n",
       "      <td>14</td>\n",
       "      <td>14</td>\n",
       "      <td>14</td>\n",
       "      <td>14</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>30</td>\n",
       "      <td>30</td>\n",
       "      <td>30</td>\n",
       "      <td>30</td>\n",
       "      <td>30</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>24</td>\n",
       "      <td>24</td>\n",
       "      <td>24</td>\n",
       "      <td>24</td>\n",
       "      <td>24</td>\n",
       "      <td>24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>19</td>\n",
       "      <td>19</td>\n",
       "      <td>19</td>\n",
       "      <td>19</td>\n",
       "      <td>19</td>\n",
       "      <td>19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>32</td>\n",
       "      <td>32</td>\n",
       "      <td>32</td>\n",
       "      <td>32</td>\n",
       "      <td>32</td>\n",
       "      <td>32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>96</td>\n",
       "      <td>96</td>\n",
       "      <td>96</td>\n",
       "      <td>96</td>\n",
       "      <td>96</td>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>68</td>\n",
       "      <td>68</td>\n",
       "      <td>68</td>\n",
       "      <td>68</td>\n",
       "      <td>68</td>\n",
       "      <td>68</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"7\" valign=\"top\">250.000-1.000.000</th>\n",
       "      <th>0</th>\n",
       "      <td>18</td>\n",
       "      <td>18</td>\n",
       "      <td>18</td>\n",
       "      <td>18</td>\n",
       "      <td>18</td>\n",
       "      <td>18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>60</td>\n",
       "      <td>60</td>\n",
       "      <td>60</td>\n",
       "      <td>60</td>\n",
       "      <td>60</td>\n",
       "      <td>60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>53</td>\n",
       "      <td>53</td>\n",
       "      <td>53</td>\n",
       "      <td>53</td>\n",
       "      <td>53</td>\n",
       "      <td>53</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>29</td>\n",
       "      <td>29</td>\n",
       "      <td>29</td>\n",
       "      <td>29</td>\n",
       "      <td>29</td>\n",
       "      <td>29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>51</td>\n",
       "      <td>51</td>\n",
       "      <td>51</td>\n",
       "      <td>51</td>\n",
       "      <td>51</td>\n",
       "      <td>51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>190</td>\n",
       "      <td>190</td>\n",
       "      <td>190</td>\n",
       "      <td>190</td>\n",
       "      <td>190</td>\n",
       "      <td>190</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>128</td>\n",
       "      <td>128</td>\n",
       "      <td>128</td>\n",
       "      <td>128</td>\n",
       "      <td>128</td>\n",
       "      <td>128</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                   Country  Employment  FormalEducation  \\\n",
       "ConvertedSalary   JobSatisfaction                                         \n",
       "0-250.000         0                    494         494              494   \n",
       "                  1                   1371        1371             1371   \n",
       "                  2                   1547        1547             1547   \n",
       "                  3                    858         858              858   \n",
       "                  4                   2014        2014             2014   \n",
       "                  5                   5587        5587             5587   \n",
       "                  6                   2976        2976             2976   \n",
       "1.000.000+        0                     14          14               14   \n",
       "                  1                     30          30               30   \n",
       "                  2                     24          24               24   \n",
       "                  3                     19          19               19   \n",
       "                  4                     32          32               32   \n",
       "                  5                     96          96               96   \n",
       "                  6                     68          68               68   \n",
       "250.000-1.000.000 0                     18          18               18   \n",
       "                  1                     60          60               60   \n",
       "                  2                     53          53               53   \n",
       "                  3                     29          29               29   \n",
       "                  4                     51          51               51   \n",
       "                  5                    190         190              190   \n",
       "                  6                    128         128              128   \n",
       "\n",
       "                                   Hobby  OpenSource  UndergradMajor  \n",
       "ConvertedSalary   JobSatisfaction                                     \n",
       "0-250.000         0                  494         494             494  \n",
       "                  1                 1371        1371            1371  \n",
       "                  2                 1547        1547            1547  \n",
       "                  3                  858         858             858  \n",
       "                  4                 2014        2014            2014  \n",
       "                  5                 5587        5587            5587  \n",
       "                  6                 2976        2976            2976  \n",
       "1.000.000+        0                   14          14              14  \n",
       "                  1                   30          30              30  \n",
       "                  2                   24          24              24  \n",
       "                  3                   19          19              19  \n",
       "                  4                   32          32              32  \n",
       "                  5                   96          96              96  \n",
       "                  6                   68          68              68  \n",
       "250.000-1.000.000 0                   18          18              18  \n",
       "                  1                   60          60              60  \n",
       "                  2                   53          53              53  \n",
       "                  3                   29          29              29  \n",
       "                  4                   51          51              51  \n",
       "                  5                  190         190             190  \n",
       "                  6                  128         128             128  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,8))\n",
    "data.ConvertedSalary=data.ConvertedSalary.map(lambda x: '0-250.000' if x<=250000 else '250.000-1.000.000' if x<=1000000 else '1.000.000+')\n",
    "data.ConvertedSalary.hist()\n",
    "pd.pivot_table(data,index=['ConvertedSalary','JobSatisfaction'],aggfunc='count')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "stem=['A natural science (ex. biology, chemistry, physics)',\n",
    " 'Computer science, computer engineering, or software engineering',\n",
    " 'Web development or web design',\n",
    " 'Another engineering discipline (ex. civil, electrical, mechanical)',\n",
    " 'Mathematics or statistics',\n",
    " 'Information systems, information technology, or system administration',\n",
    "]\n",
    "\n",
    "not_stem=[ 'A social science (ex. anthropology, psychology, political science)',\n",
    " 'A humanities discipline (ex. literature, history, philosophy)',\n",
    " 'A business discipline (ex. accounting, finance, marketing)',\n",
    " 'Fine arts or performing arts (ex. graphic design, music, studio art)',\n",
    " 'A health science (ex. nursing, pharmacy, radiology)',\n",
    "]\n",
    "\n",
    "data=data[data['UndergradMajor'].isin(stem+not_stem)]\n",
    "data.UndergradMajor=data.UndergradMajor.map(lambda x: 'STEM' if x in stem else 'NOT_STEM')\n",
    "#'I never declared a major' WHERE DO THEY GO? \n",
    "\n",
    "#Just Delete them <------\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>Hobby</th>\n",
       "      <th>OpenSource</th>\n",
       "      <th>Country</th>\n",
       "      <th>Employment</th>\n",
       "      <th>FormalEducation</th>\n",
       "      <th>UndergradMajor</th>\n",
       "      <th>JobSatisfaction</th>\n",
       "      <th>ConvertedSalary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>Employed full-time</td>\n",
       "      <td>Bachelor</td>\n",
       "      <td>STEM</td>\n",
       "      <td>1</td>\n",
       "      <td>0-250.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>Employed full-time</td>\n",
       "      <td>Bachelor</td>\n",
       "      <td>STEM</td>\n",
       "      <td>5</td>\n",
       "      <td>0-250.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>Employed full-time</td>\n",
       "      <td>Bachelor</td>\n",
       "      <td>STEM</td>\n",
       "      <td>4</td>\n",
       "      <td>0-250.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>India</td>\n",
       "      <td>Employed full-time</td>\n",
       "      <td>Master</td>\n",
       "      <td>STEM</td>\n",
       "      <td>5</td>\n",
       "      <td>0-250.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>United States</td>\n",
       "      <td>Employed full-time</td>\n",
       "      <td>Bachelor</td>\n",
       "      <td>NOT_STEM</td>\n",
       "      <td>5</td>\n",
       "      <td>250.000-1.000.000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Hobby OpenSource         Country          Employment FormalEducation  \\\n",
       "1    Yes        Yes  United Kingdom  Employed full-time        Bachelor   \n",
       "5    Yes         No  United Kingdom  Employed full-time        Bachelor   \n",
       "22    No         No  United Kingdom  Employed full-time        Bachelor   \n",
       "24   Yes         No           India  Employed full-time          Master   \n",
       "27    No         No   United States  Employed full-time        Bachelor   \n",
       "\n",
       "   UndergradMajor  JobSatisfaction    ConvertedSalary  \n",
       "1            STEM                1          0-250.000  \n",
       "5            STEM                5          0-250.000  \n",
       "22           STEM                4          0-250.000  \n",
       "24           STEM                5          0-250.000  \n",
       "27       NOT_STEM                5  250.000-1.000.000  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Hobby ['Yes' 'No']\n",
      "OpenSource ['Yes' 'No']\n",
      "Country ['United Kingdom' 'India' 'United States']\n",
      "Employment ['Employed full-time' 'Employed part-time'\n",
      " 'Independent contractor, freelancer, or self-employed']\n",
      "FormalEducation ['Bachelor' 'Master' 'Ph.D']\n",
      "UndergradMajor ['STEM' 'NOT_STEM']\n",
      "JobSatisfaction [1 5 4 0 6 2 3]\n",
      "ConvertedSalary ['0-250.000' '250.000-1.000.000' '1.000.000+']\n"
     ]
    }
   ],
   "source": [
    "display(data.head())\n",
    "for col in data.columns: \n",
    "    print(col,data[col].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "def chi2_contingency_mat(data,alpha=None):\n",
    "    s=data.columns.size\n",
    "    a = 0\n",
    "    b = 0\n",
    "    mat=np.zeros((s,s))\n",
    "    for i in data.columns:\n",
    "        for j in data.columns:\n",
    "            contigency_pct = pd.crosstab(data[i], data[j])\n",
    "            c, p, dof, expected = chi2_contingency(contigency_pct)\n",
    "            mat[a][b]=p\n",
    "            b=b+1\n",
    "        a = a+1\n",
    "        b=0\n",
    "    if alpha:\n",
    "        mat[mat>=alpha]=1\n",
    "        mat[mat<alpha]=0\n",
    "    return mat\n",
    "\n",
    "def chi2_contingency_dict(data,alpha=None):\n",
    "    s=data.columns.size\n",
    "    a = 0\n",
    "    b = 0\n",
    "    mat={}\n",
    "    for i in data.columns:\n",
    "        mat[i] = {}\n",
    "\n",
    "    \n",
    "    for i in data.columns:\n",
    "        for j in data.columns:\n",
    "            contigency_pct = pd.crosstab(data[i], data[j])\n",
    "            c, p, dof, expected = chi2_contingency(contigency_pct)\n",
    "            mat[i][j]=p\n",
    "    # if alpha:\n",
    "    #     mat[mat>=alpha]=1\n",
    "    #     mat[mat<alpha]=0\n",
    "    return mat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Hobby',\n",
       " 'OpenSource',\n",
       " 'Country',\n",
       " 'Employment',\n",
       " 'FormalEducation',\n",
       " 'UndergradMajor',\n",
       " 'JobSatisfaction',\n",
       " 'ConvertedSalary']"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(data.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "chi2Mat=chi2_contingency_mat(data,5e-7)\n",
    "labels = list(data.columns)\n",
    "plt.figure(figsize=(10,8))\n",
    "sns.heatmap(chi2Mat,annot=True, xticklabels=labels, yticklabels=labels,cmap=\"YlGnBu\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Figure size 720x576 with 0 Axes>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 720x576 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "chi2Mat=chi2_contingency_dict(data,5e-7)\n",
    "plt.figure(figsize=(10,8))\n",
    "# sns.heatmap(chi2Mat,annot=True)\n",
    "# print(chi2Mat)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "data = data.drop('Employment', axis=1)\n",
    "chi2Mat=chi2_contingency_mat(data,5e-3)\n",
    "labels = list(data.columns)\n",
    "plt.figure(figsize=(10,8))\n",
    "sns.heatmap(chi2Mat,annot=True, xticklabels=labels, yticklabels=labels,cmap=\"YlGnBu\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## GRAPH PLOTTING"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "def compute_graph_table(data, chi2Mat):\n",
    "\n",
    "    graph_table = pd.DataFrame()\n",
    "\n",
    "\n",
    "    source = []\n",
    "    target=[]\n",
    "\n",
    "    a=1\n",
    "    for i in range(data.columns.size):\n",
    "        for j in range(a, data.columns.size):\n",
    "            if chi2Mat[i][j]==0:\n",
    "                source.append(data.columns[i])\n",
    "                target.append(data.columns[j])\n",
    "        a=a+1\n",
    "\n",
    "    type=['Unidirected' for i in range(len(source))]\n",
    "    weight=[None for i in range(len(source))]\n",
    "    graph_table['Source']=source\n",
    "    graph_table['Target']=target\n",
    "    graph_table['Type']=type\n",
    "    graph_table['weight']=weight\n",
    "    return graph_table\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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>Source</th>\n",
       "      <th>Target</th>\n",
       "      <th>Type</th>\n",
       "      <th>weight</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Hobby</td>\n",
       "      <td>OpenSource</td>\n",
       "      <td>Unidirected</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>OpenSource</td>\n",
       "      <td>Country</td>\n",
       "      <td>Unidirected</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>OpenSource</td>\n",
       "      <td>FormalEducation</td>\n",
       "      <td>Unidirected</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>OpenSource</td>\n",
       "      <td>JobSatisfaction</td>\n",
       "      <td>Unidirected</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Country</td>\n",
       "      <td>FormalEducation</td>\n",
       "      <td>Unidirected</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Country</td>\n",
       "      <td>UndergradMajor</td>\n",
       "      <td>Unidirected</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Country</td>\n",
       "      <td>JobSatisfaction</td>\n",
       "      <td>Unidirected</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Country</td>\n",
       "      <td>ConvertedSalary</td>\n",
       "      <td>Unidirected</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>FormalEducation</td>\n",
       "      <td>JobSatisfaction</td>\n",
       "      <td>Unidirected</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>FormalEducation</td>\n",
       "      <td>ConvertedSalary</td>\n",
       "      <td>Unidirected</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>UndergradMajor</td>\n",
       "      <td>JobSatisfaction</td>\n",
       "      <td>Unidirected</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Source           Target         Type weight\n",
       "0             Hobby       OpenSource  Unidirected   None\n",
       "1        OpenSource          Country  Unidirected   None\n",
       "2        OpenSource  FormalEducation  Unidirected   None\n",
       "3        OpenSource  JobSatisfaction  Unidirected   None\n",
       "4           Country  FormalEducation  Unidirected   None\n",
       "5           Country   UndergradMajor  Unidirected   None\n",
       "6           Country  JobSatisfaction  Unidirected   None\n",
       "7           Country  ConvertedSalary  Unidirected   None\n",
       "8   FormalEducation  JobSatisfaction  Unidirected   None\n",
       "9   FormalEducation  ConvertedSalary  Unidirected   None\n",
       "10   UndergradMajor  JobSatisfaction  Unidirected   None"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "graph_table = compute_graph_table(data, chi2Mat)\n",
    "graph_table"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import networkx as nx\n",
    "\n",
    "G = nx.from_pandas_edgelist(graph_table, source='Source', target='Target',create_using=nx.DiGraph())\n",
    "# net = Network(notebook=True, directed=True)\n",
    "# net.from_nx(G)\n",
    "# net.show('nx.html')\n",
    "pos={'Hobby':(0.5,10),\n",
    "     'JobSatisfaction':(2,7),\n",
    "     'OpenSource':(0.5,7),\n",
    "     'FormalEducation':(0.5,3),\n",
    "     'Country':(2,3),\n",
    "     'ConvertedSalary':(1.25,1),\n",
    "     'UndergradMajor':(3,5)\n",
    " }\n",
    "plt.figure(figsize=(10,8))\n",
    "\n",
    "nx.draw(G, arrows=True, with_labels=True, node_size=7000, arrowsize=20, pos=pos, font_size=10, font_color='white')\n",
    "# print(G.edges())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Markov Blanket Plotting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAt4AAAJOCAYAAACA8gAcAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAACcmklEQVR4nOzdeVxUVeMG8OcOMwMzgOKCCqailoIIuEBJKIqmZZKWG1qpabmUqGGopaUtrpULalL65lKUqam5pKW4h2g6kiiL4gYu5IKKMDAwzNzfH/OT3AWEuTPD8/18/LwJM3Me6O3ycObccwRRFEUQEREREVGFkkkdgIiIiIioMmDxJiIiIiIyAxZvIiIiIiIzYPEmIiIiIjIDFm8iIiIiIjNg8SYiIiIiMgMWbyIiIiIiM2DxJiIiIiIyAxZvIiIiIiIzYPEmIiIiIjIDFm8iIiIiIjNg8SYiIiIiMgMWbyIiIiIiM5BLHUAqoijiUs4lXLh1AZm5mcjMyURmbia0ei0KDYWQy+Swt7OHq9oV7s7ucHN2g7uzOzxcPKC0U0odn4iIiIisTKUp3tm6bOw6twvx5+OxN2Mvjl85jiJjEezt7CFChN6gR35R/n3PU9opYW9nD5kgg0E0oKCoAB4uHgisF4h29duhg0cHPF39aQm+IiIiIiKyJoIoiqLUISpK+s10bDixAT8f+xkJ/ybAwc4BuYW5MMJYLq+vVqghiiJqqGugb7O+6NWsF9o81QYygSt4iIiIiOhuNle8DUYDfk/7HbPiZuFI5hEIEB44k13e7AQ7qBQqOCmcMDZwLIa0HIIa6hoVPi4RERERWQebKd55+jwsOLgAX+//GgWGAuQU5kiWRSVXQYSI7k27Y2rIVDxT4xnJshARERGRZbD64q036PF9wveYuGMiCgwFyNPnSR2pmJ1gB4WdAv28+2F6p+lwc3aTOhIRERERScSqi/e209swZMMQ3NTdhFavlTrOQyntlLAT7BDRJgJTOkzhrihERERElZBVFu9bBbcw8veRWJe6zqJmuB9HrVCjjlMdrOmzBq3cWkkdh4iIiIjMyOqKd+yZWPRf2x+5hbnQFemkjlMmKrkKo58bjakdp0IuqzQ7OhIRERFValZTvEVRxKy4Wfh8z+dm2aWkoqkVavjV9sPm1zejuqq61HGIiIiIqIJZRfHWFenw5ro38cepPyx6LXdpKe2UqKmqie0Dt6OZazOp4xARERFRBbL44n09/zraL2+P09dP28RM970ECFAr1NjQbwM6NeokdRwiIiIiqiAWXbyvaq8i8PtAZGRnQG/USx2nQqkVaqzpswYvP/Oy1FGIiIiIqAJYbPHOysvCs/97Fuezz9t86b5NJVfht36/oUvjLlJHISIiIqJyZpHFO0+fh4AlAUjLSqs0pfs2tUKNHQN3oM1TbaSOQkRERETlSCZ1gHuJoojX176OszfOVrrSDZh+6Xj5p5dx8dZFqaMQERERUTmyuOI9de9UxJ6JtckbKUsqpzAHnX/sjHx95f0eEBEREdkaiyreW9K2YMZfM2xqy8CyKDIW4dzNcxi4fqDUUYiIiIionFhM8b6efx1vrHujUs903ym/KB9bTm3Br8m/Sh2FiIiIiMqBxRTvoZuGIk+fJ3UMi5Knz8M7G9/BVe1VqaMQERER0ROyiOK98cRG/HHqDxQaCqWOYnHyi/IxZMMQqWMQERER0ROSvHjrinR4e+PbnO1+iEJDIXad24Xtp7dLHYWIiIiInoDkxXvBwQXcveMxtHotRm0dBaNolDoKEREREZWRpMU7W5eNz/d+Xul3MSmJC7cuYG3yWqljEBEREVEZSVq8Z8XNgsFokDKC1dDqtXj/z/f5/SIiIiKyUpIVb12RDgv+XsDtA0shpyAHW9K2SB2DiIiIiMpAsuK9JmmNVENbrZzCHMyKmyV1DCIiIiIqA8mK96y4WcgtzJVqeKulydTg1PVTUscgIiIiolKSpHgnXk7E2ZtnpRja6hmMBnxz6BupYxARERFRKUlSvH9N/hV6g16Koa2e3qjHquOrpI5BRERERKUkSfFeeXwl9EYW77LKLsjGiWsnpI5BRERERKVg9uJ94dYFnM8+b+5hbYrBaMBvqb9JHYOIiIiISsHsxXtr2lbIZXJzD2tTCgwF+CXpF6ljEBEREVEpmL1470nfw5Mqy0HK1RQepkNERERkRcxevA9cOGDuIW2Swk6Bk1knpY5BRERERCVk1uKtK9IhIzvDnEPaNE2mRuoIRERERFRCZi3eyVeT4SB3MOeQNiu3MBcHLx6UOgYRERERlZBZi/f57PMQBMGcQ9o0nmBJREREZD3MWrwzczPNenBOzkc5d/19kN8gLOi64JHPWdZjGXp59brv4yV5rrldvHVR6ghEREREVEJmLd4Xb11EflG+OYe0aZe1l6WOQEREREQlZNbifS77nDmHe6QGVRtgx8AdODriKGIHxKJelXrFn3uh0Qs4NPQQToSfQLdnuhV/vF6Vetg1aBdOhp/E5PaTAQCfdfgMY54bU/yYqR2nYvRzo83yNdzIv2GWcYiIiIjoyZn1JJvcwlxzDgeVXIWE4QnFf6+uqo6NJzYCABZ0XYAVR1fgh6M/YHCLwZjfdT5eW/UaAMDDxQPPLnkWjas3xq5Bu/D0/KcBAM/WfRbNo5sjT5+HQ0MP4feTv2NpwlKsC1uHqINRECCgn3c/PPu/Z83y9RUZi8wyDhERERE9ObMW7yKDeYtiflE+Wn7Xsvjvg/wGwd/dHwAQWC8QPVf3BAD8mPgjvuz8ZfHjViethggRp66fwpkbZ+BZ0xMAsP3MdlzPvw4AWJeyDm3rt0XUwShk5WWhRZ0WqO1YGwn/JhQ/pqKJEGEUjZAJZt+OnYiIiIhKyazF21p2NBEhPvDvovjgj/8v4X94q8VbqONYB0sTlpon5P8TYB3fUyIiIqLKzqxTpUo7pTmHe6T95/ejX/N+AIA3fN7AvvR9xZ/r06wPBAhoVK0RGlVrhBPXTgAAOjfujGoO1eAgd8Crnq8iLiMOALA+ZT1eavwSAuoG4M/Tf5rta5AJMqv5ZYaIiIiosjPrjLer2tWcwz3SqK2jsKzHMox7fhyuaq9i8IbBxZ/LyM7A30P/RhX7KhixeQQKDAUAgL8v/o21fdfiqSpPIeZYTPHJkXqjHrvO7cJN3U0YRaPZvga1Qm22sYiIiIjoyQjivesnKtCXcV9i0s5JNndToAABR4YfQZ81fcx6qI1HVQ+cff+s2cYjIiIiorIz61ITNyc3mzsy3qumF06NPoUdZ3eY/SRJN2c3s45HRERERGVn1qUmbs5usBPszDlkhUu5loLG8xtLMvade48TERERkWUz64x3kxpNUGgoNOeQNkshU8C3tq/UMYiIiIiohMxavOtVqQc7mW3NeEtFrVAjoG6A1DGIiIiIqITMWrwFQUDzWs3NOaTNyi/KR2u31lLHICIiIqISMvuRh8H1gyEz/7A2p4p9FdRQ15A6BhERERGVkNkbcMeGHeFk72TuYW1O+wbtpY5ARERERKVg9uLdwaMDb7B8Qs5K5+JTN4mIiIjIOpi9eNvL7dHBo4O5h7UpBYYCvNj4RaljEBEREVEpSLLYun/z/nBScrlJWbV2aw1ne2epYxARERFRKUhSvHs07WFzx8abi5PSCSP8R0gdg4iIiIhKSZLiXdWhKvo062Nzp1iaS1/vvlJHICIiIqJSkmxfv7GBY2Evt5dqeKukkCnwTqt34CB3kDoKEREREZWSZMW7RZ0WaFytsVTDWyU7mR1GPTtK6hhEREREVAaSnmTzZecv4ahwlDKC1ZALcrz8zMtoVK2R1FGIiIiIqAwkLd4vNn4RXq5eUkawGnI7Ob7u/LXUMYiIiIiojCQt3oIgYEHXBVAr1FLGsHhKOyUG+g5Ew2oNpY5CRERERGUkafEGgDZPtUGIRwgUMoXUUSyW0k6JLzp+IXUMIiIiInoCkhdvAPhf9/9xp46HcFQ4Yn7X+ajlWEvqKERERET0BCyieNdxqoNvQ7/ljZb3kMvkCKgbgLf83pI6ChERERE9IYso3oDpGPm29dtCaaeUOorFcJA7IOa1GAiCIHUUIiIiInpCFlO8BUHATz1/QnVVdQhg0VQr1Pi558+oW6Wu1FGIiIiIqBxYTPEGgBrqGtg+YHul3+XEUeGID4M+xCtNX5E6ChERERGVE4sq3gDQvFZz/NzrZ6jkKqmjSMJB7oAXGr2Aj4M/ljoKEREREZUjiyveANC9aXd80fGLSjfzbW9nj+aupl88uK6biIiIyLZYZPEGgA8CP8BHbT+qNOXbQe6ApjWbYuegnZXmayYiIiKqTCy2eAPAx8EfY3LwZJsvog5yB3i7euOvwX/B2d5Z6jhEREREVAEEURRFqUM8ztKEpQjfEo78onypo5Q7R4Uj2nu0x5o+a2z+FwwiIiKiyswqijcA7D+/H91+7oacghwYRIPUccqFSq5C5POR+KzDZ1zTTURERGTjrKZ4A8D57PPoEtMFGdkZyNPnSR2nzOwEOzjIHfDjaz/iNa/XpI5DRERERGZgVcUbAAoNhfh096eYd2CeVS49cVQ4onmt5vil9y/wcPGQOg4RERERmYnVFe/bEjIT0GdNH/yb+y+0eq3UcR5LIVNAaafEl52/xLv+73JpCREREVElY7XFGzDNfkcfisbk3ZOhN+gtcgZcJshgb2ePHk174MvOX6Je1XpSRyIiIiIiCVh18b4tpyAHs+JmYe6BuRBF0SIKuJ1gB3u5PYLqBWHui3PhXctb6khEREREJCGbKN63ZeVlYWnCUsyJn4NcfS5yC3PNnkGtUMMoGtGnWR+MDRyLFnVamD0DEREREVkemyretxlFI7ad3oa58XOxJ30P7OX2yCnIgYiK+VIdFY4oMhahgUsDjAwYiUF+g1DVoWqFjEVERERE1skmi/ed8vX52HVuF1YlrcLvJ39HbmEu7OX2yCvMQ5FYVKbXdFI6QRRFFBmL8GzdZ/Gm75sIbRIKd2f3ck5PRERERLbC5ov3va5or0BzSYNDlw4h7nwczmefxxXtFdzU3YSdzA52gh30hXoolAqIEFFoKISjwhE11DXg5uSGVm6tEPhUIFq7t0aTGk0gE2RSf0lEREREZAUqXfF+GFEUcVN3E7oiHUJeCMHC+Qvh29wX1RyqQWGnkDoeEREREVk5udQBLIUgCKimqgYAUOYrUUtVC7Uca0mcioiIiIhsBddJEBERERGZAYs3EREREZEZsHgTEREREZkBizcRERERkRmweBMRERERmQGLNxERERGRGbB4ExERERGZAYs3EREREZEZsHgTEREREZkBizcRERERkRmweBMRERERmQGLNxERERGRGbB4ExERERGZAYs3EREREZEZsHgTEREREZkBizcRERERkRmweBMRERERmQGLNxERERGRGbB4ExERERGZAYs3EREREZEZsHgTEREREZkBizcRERERkRmweBMRERERmQGLNxERERGRGbB4ExERERGZAYs3EREREZEZsHgTEREREZkBizcRERERkRmweBMRERERmQGLNxERERGRGbB4ExERERGZAYs3EREREZEZsHgTEREREZkBizcRERERkRmweBMRERERmQGLNxERERGRGbB4ExERERGZAYs3EREREZEZsHgTEREREZkBizcRERERkRmweBMRERERmQGLNxERERGRGbB4ExERERGZAYs3EREREZEZsHgTEREREZkBizcRERERkRmweBMRERERmQGLNxERERGRGbB4ExERERGZAYs3EREREZEZsHgTEREREZkBizcRERERkRmweBMRERERmQGLNxERERGRGbB4ExERERGZAYs3EREREZEZsHgTEREREZkBizcRERERkRmweBMRERERmQGLNxERERGRGbB4ExERERGZAYs3EREREZEZsHgTEREREZmBIIqiKHUIqXXt2hV//vln8d9FUYQgCMV/VyqVuHDhAmrWrClFPCIiIiKyAZzxBvDaa69BrVZDFEXc/j3k9j+LoggfHx+WbiIiIiJ6IpzxBlBYWIinnnoKV69eve9zjo6O+P3339G+fXsJkhERERGRreCMN0xLSaZOnQpHR8f7Pufl5cXSTURERERPjDPe/+9Bs96c7SYiIiKi8sIZ7//3oFlvznYTERERUXnhjPcd7pz1VqlU2Lp1K4s3EREREZULznjf4fasNwA0atSIpZuIiIiIyg1nvO+h1+tRrVo1LF++HL1795Y6DhERERHZiMpZvG/dAhISgMRE4Nw54OxZ4Px54MoVoKAAosEAQSYD5HKgWjWgbl3AwwNo2BBo2hRo3RqoVw+445AdIiIqm9zCXCRkJuDo5aNIv5mOMzfPICM7A1e1V1FgKIDBaIAgCJALcrioXFDXuS4aujSEh4sHmtZsitZurVG/av27Dj4jIrJElaN4X78ObN0KrF0LHDwIXL0KqFRAYSGg05X8deRyQK0G9HrAzg7w9QVCQ4FXXwU8PVnEiYhK4KbuJrambcXalLU4cOEArmivQKVQodBQCF1Rya/JdoIdHJWO0Bv0kAky+NTyQWiTULzq+SqauTZjEScii2O7xTsrC/jxR+CHH4CkJECpBHJzy38ce3tTCa9SBejdG3j7baBFi/Ifh4jIit3Iv4EfE3/Ej0d/ROKVRNjb2SOnMKfcx7G3s4edzA5OSif09uqNt1u9jVZurcp9HCKisrC94v3338Ds2cCGDYBMBuTnm29sOztTEW/cGJgwwVTE7e3NNz4RkYXRXNJgdvxsrE9dDxlkyCvKM9vYMkEGB7kDPKp6YELbCejr3RcOcgezjU9EdC/bKd67dgFjxgBnzpjKttEobR4nJ9PSk08+AUaNAhx4sSeiymNv+l6M3joaadfToCvSwShKe012UjpBgICJ7SZizHNjoFKoJM1DRJWT9RfvI0dMxfaff4A8882klJijo6l0f/klMGiQaVaciMhGJV5OxOito3Ho0iHk6S3vmqxWqOEgd8DMTjMxuOVgyGVyqSMRUSVivcU7J8dUuFevNt0gaelfhqMj4O5uyss14ERkY3ILcxHxZwR+SvwJuiIdRFj2NdlR4YhajrWwps8atHZvLXUcIqokrLN4x8YCr79uKt+l2ZVEaoJgmv0eOxaYPNl0wycRkZXbfW43+v/aHzcLbpZqVxJLoJKrEP5sOL4I+QL2ct6TQ0QVy7qKd2EhMHIk8PPPlrmspKTUatPe4Fu2AE8/LXUaIqIy0Rv0eP+P97Hsn2XILzLjjezlTK1Qo7ZjbWx9Yyua1mwqdRwismHWU7yvXgVeeglITbXu0n2bTGZafrJuHfDCC1KnISIqlay8LHT7uRuOXTlmkWu5S0uAAEelI9b0WYOXnn5J6jhEZKNkUgcokaNHgebNgWPHbKN0A6ZdV3JygO7dgblzLX+NOhHR/zt+5TiaRzdHwr8JNlG6AUCEiNzCXPRc1ROz4mbBWuakiMi6WP6M9549QLdugFYrdZKKo1YDgwcDCxbw9EsismhxGXF46aeXoC3UWvwNlGXlqHDE6z6v49vQbyETrGN+ioisg2UX7x07TDPCtjLL/ShqtemG0cWLWb6JyCLtObcH3X7uBq3ehidC/p9aoUZvr95Y9uoylm8iKjeWezXZu7fylG7A9HWuXGm6edSCfxciospp//n9ePnnlytF6QaAPH0efk35FcM3DeeyEyIqN5ZZvFNSTMtLKkvpvk2rBX74AZg5U+okRETF0rLS8FLMSzaznruk8vR5+Pn4z/hsz2dSRyEiG2F5S01u3DDdSJmZWXlnflUqYO1aoGtXqZMQUSWXrcuGb7QvLuRckPzYd6mo5Cqs7LUSPTx7SB2FiKycZc14FxUBoaHAtWuVt3QDQH4+0LevaetEIiKJGIwGvLbqNVzWXq60pRsA8ovy8ca6N3D8ynGpoxCRlbOs4j1xIvDPP6aDcio7rRZ48UVTCSciksCnuz/FwYsHUWAokDqK5PL0eXjxxxehLawca9yJqGJYTvE+fBhYuLDyret+GFE0HRo0YYLUSYioEvrn338wO352pVvX/TAiRNzQ3cDYbWOljkJEVswy1ngXFACensC5c1InsTwqlWlbxcBAqZMQUSWhN+jRbFEznL5+2mb36i4rlVyFP978A8ENgqWOQkRWyDJmvD/5BLhyReoUlun2em+dTuokRFRJfLH3C1zKucTS/QD5Rfno92s/vhNARGUiffHOyOASk8e5ccP0PSIiqmCXci7h6/1fs1g+QnZBNuYdmCd1DCKyQtIvNenf37R1nl4vaQyL5+wMXLgAVKkidRIismFv/fYWVh5fiUIDb3J/FEeFI85HnEc1VTWpoxCRFZF2xjs5GdiwgaW7JIqKgBkzpE5BRDYsLSsNq5JWsXSXgEE04Iu9X0gdg4isjLQz3qGhwNatgLHy7g9bKioVcPEiUI0zLERU/nqt6oUNJzbAIBqkjmIVVHIV0t9Ph6ujq9RRiMhKSDfjfekSEBvL0l0aggAsWyZ1CiKyQVe0V/B72u8s3aW05MgSqSMQkRWRrnhHR0s2tNXKywNmz+YvK0RU7hZrFkMQBKljWJX8onzMOzAPBiN/WSGikpGmeOv1pl06CngaWqndugXs3Cl1CiKyIQajAVEHo6Ar4ralpaUr0uGPU39IHYOIrIQ0xXv7dsDAGYIyyc3l1oJEVK52nduFgiJOhJRFTmEOFvy9QOoYRGQlpCneq1ebCiSVzfbt3AmGiMrNmuQ10Oq1UsewWnvS9/AXFyIqEfMXb6PRtIWgBZxUb7XkcuCvv6ROQUQ2QBRFrEtZB6PIe0fKSmmnxO5zu6WOQURWwPzF+8gR057UVHZaLfDrr1KnICIbcOzKMeTr86WOYdVyCnKwOnm11DGIyAqYv3hv3w4U8nCGJ2IwAJs3S52CiGxA7JlYFBk5GfIkRIjYmrZV6hhEZAXMX7z37GHxLg+XLplmvomInsCe9D0oMHB98pO6lncN2bpsqWMQkYWTZqkJPTm1Gjh6VOoURGTlDl86LHUEm6BWqJHwb4LUMYjIwpm3eGdlAdmcESgXhYWARiN1CiKyYjkFObiqvSp1DJugK9JBc4nXZCJ6NPMW7+RkQKUy65A2S6cDDnOmiojKLuVaClQKXpPLQ4GhAH9f+lvqGERk4cxbvC9d4nHn5Sk9XeoERGTFLuVckjqCTcm4mSF1BCKycOYt3pmZZTsmvm5d4LffgJMngVOngHnzAIWifLM1aQLs2gUkJJhm5r/7rnxfvyJc4g9NInqwl156CUFBQYiPj3/oYy7lXILe8ODDuHI+ynno89o3aI9N/Tc98HODWwxG4ohEHB1xFMfePYbuTbs/MmePpj3gVdOr+O+fdfgMnRp2eujja6pr4sDbB3Bk2BG0rd/2ka99L7/afuj6dNfiv7/S5BVMCJpQqtd4lMzczHJ7LSKyTeYt3ufPl21Hk3XrTMW7SRPTHycnYNq08s02fz4wdy7QsiXQrBmwoJyOAJZV4Lf42rWKe20ismr//vsv9u/fjxdeeOGhBfzirYvQFenKbcy6znUxqd0ktF3WFn7f+qHN/9og8XLiI5/zqueraObarPjvU3ZPwY6zOx76+E4NO+HYlWNotbgV/soo3UFiLeq0wMvPvFz8900nN2FW3KxSvcajZOVnldtrEZFtMn/xLq2OHU3rmZcvN/3daAQiIoAhQ4B33zUV8l27TLPhkyf/97w33gAOHjTNYH/77X8FOCcHmDoV+OcfID4eqFXL9HE3N+DChf+ef/y46X/t7YGlS4HERNOOLB06mD4+aNDd5XzTJqB9+//G+Ppr0xiBgcCAAaYdSP75B/jhB9NjatY0HYLz99+mP88/X/rvza1bpX8OEVUqeXl5Dy3gF25dgIhHnyL8ZecvcezdY0gckYi+3n2LP17Fvgo299+M1JGpiO4WDQECajnWQk5hDnILcwEAWr0W526eAwC80+od/P3O3/hn+D/4tc+vUMlVCHwqEN2bdsdXnb9CwvAENKrWCMt6LEMvr14AgBmdZiDpvSQcHXEUX3X+Cn61/fBl5y/Ro2kPJAxPgIPcAYu6LcKhoYdw/N3j+LTDp8X5/N39ETckDv8M/wcH3zmIKvZV8HnI5wjzDkPC8AT09e6LQX6DsKCr6TreoGoD7Bi4A0dHHEXsgFjUq1IPALCsxzJEvRSFuCFxOD36dHG2B8ktzOUJoET0SHKzjlaWZSbe3vfv3pGTA2RkmI5Of/ZZoHlzIC8POHQI+P130/7WYWFAUJDplMxvvjEV8R9/NM2WHzgAfPwxMGsWMHSoafZ87lxg505g/35g2zZg2TLTDiwjR5qOt/f1BZo2NX2uSZNHZ3ZyMpX+yEjT7PnHH5uKdVYWUK2a6TFRUaYx4+KAevWAP/80PbY0DAbkabWAIJTueURk84z33E9zZwH38fHBzJkzHzvb3dOrJ1rUbgG/b/1QU10Th4Yewt70vQCAZ+s+i2bfNEN6djr+eOMP9PTqifWp63E59zLOjjmLHWd2YF3qOmw+aTrsa13KOvzvyP8AAF+EfIG3W72NhX8vxMYTG7H55GasTVl719jVVdXxmudr8PzGEwBQ1b4qsguyMXnXZPi7+2PU1lEAgEk7JuGG7gZkggw7Bu6ATy0fpF5LxareqxD2axgOXzoMZ6Uz8vR59z13kN+g4vEWdF2AFUdX4IejP2Bwi8GY33U+Xlv1GgDAzckNbZe2hWdNT2zsv/G+rLfJBBmKjEVQ2ikf/y+IiCol8xZvg6H8X3P7duD6ddM/r1sHtG1rKtutW5uKOGDaSeXKFdM/FxT8d+qjRgN07mz65+XLTeX3pZeAHj2A4cMBPz/T692e2T5xwnRD4+OKd1ERsPb/L8wdOwJr1phKNwDcuGH63xdeuLtoV6kCODqW+lAc15o1IbJ4E9E9dLoHl+q8vDwcPHgQISEhCPk25JGv0bZ+W6w8vhJG0Ygr2ivYc24PAtwDcKvgFv6++DfO3jwLAFh5fCXa1m+LtSlr8dJPLyHAPQCdGnXC3BfnorVba3y25zM0r9UcU0OmwsXBBU5KJ/x5+s9Hjp2ty4auSIfvu3+PzSc3Fxf4e/X17othrYdBLpPDzckNzVybQYSIzJzM4j3Kcwofvl79tsB6gei5uicA4MfEH/Fl5y+LP/fbid8gQkTKtRTUdqz90NcQIMBgNAB2jx2OiCop8xZveRmGS04Geve++2POzkD9+qaCK97zNqkommaAV6wAJk68//X0d9xIZDDcnSkz0zTTvWwZcOyYaSb9YYqK7l6/7eDw3z/rdI/fvUUmA9q0Kdu7ALcJArT5+WV/PhHZrBYtWuDoPYdsyWQyKJVKvPTSS5g+fTo+S/oM+Ldsry/ec+29c8nKoUuHcOjSIWw/vR3LeizDZ3s+w/Iey/HqqleReDkRg/wGoYNHh0e+vkE04Nn/PYtODTuhd7PeCH82HJ1+uPumSw8XD0Q+H4mAJQG4qbuJZT2WwUHu8JBXLLuCov+u08IjJjqMohFymXl/rBKRdTHvGm+HMlwQd+wwndI4YIDp7zIZMHu2aYY6L880Y12tmum1X33VtHRjxw5TWXd1NT2nWjVTUX+UF1/8r4TXrg3UqAFcvAjs22dapgIAzzxjep0TJ4Bz54AWLUwl/6mnTEteHmTnTqBPH6B69f+yAKYlK6NG/fc4P7/SfV8AwI7TKkT0eDKZDA4ODujevTuOHDmC9evXw8vL67EldV/6PoR5h0EmyFBTXRPBDYLx90XTXtXP1n0WHi4eECAgzDsMf2X8BTcnN7Ss07L4+S3qtEB6tmnbU2d7Z2TmZEIuk+MNnzeKH5NTmANne+f7xnZUOKKqfVVsPbUVEX9GwK/2/dfIKvZVoC3UIluXjVqOtYp3LDlx7QTcnN3g7+4PAHBSOsFOsDONpbx/LADYf34/+jXvBwB4w+cN7Evf98jvzcPYyXhdJqKHM++v5vXqle15r70GLFoEfPKJqXhv2WKaze7f33Rj4tq1pvIbE/PfevCPPzaVW5nMNMs9cqRpXfjDdOliWnd9++3ZceOAy5dN40ZHm26uLCoC3nrLtDNLXBxw9qxpRj4lxXTj5YMkJ5vWkO/ZY5phT0gABg8GRo82rT0/etRU+PfuNd0sWhpVqpTu8URUqQiCAHt7++IZbi8vr7s+X69KPQgQ7rvB0k6wQ0FRAdanrkdgvUAcHXEUoihifOx4XNZehmdNTxy6dAgLuy7E09Wfxq5zu7A+ZT3qVa2Hr7t8DXdnd+iKdLiqvYoRv48AAHyy6xMcfOcgruZdxcGLB4sL8C/Hf8GSV5Zg9LOj0XvNf+9uOts7Y0O/DXCQO0CAgLHbxt739SVeTkTCvwlIDU/F+ezziDsfBwDQG/UI+zUMC7ougEquQn5RPl744QXsOrsLHwZ9iIThCZjx14y7XmvU1lFY1mMZxj0/Dle1VzF4w+BSf7+dlE6QCeadzyIi6yKI975fWJHmzwfGj3+y5RV3GjQI8Pe/e+a4MmnaFEhNlToFEVmgvn37Qq/XP7Bw3/bt4W8x9s+xyC+6e8mab21fLHllCZ7733PmiGozGro0xJkxZ6SOQUQWzLwz3m5upu35yqt4V3bu7lInICILtXr16sc+xt3ZHQo7xV3Fe3jr4Rj93Gi8/8f7FZjONrk5uUkdgYgsnHmLd9265ft6K1aY/lRWDRtKnYCIrFhd5/uvyd9pvsN3Gis4udcCNXBpIHUEIrJw5l2M5u0NcBeO8qFSmZbZEBGVkZerF/L0eVLHsAkOcgc8V5dLc4jo0cxbvKtWNe0WQk9OoTDtVU5EVEZqhZrLI8qJ0k6J1u68JhPRo5n/9muWxfKRl2c6TZOI6Ak8W/chW6FSqeTp89CiTgupYxCRhTN/8Q4JMd1gSU+mfv2y7YtORHSH9g3aQyVXSR3D6rk5ucFJ6SR1DCKycOYv3p07l+0ES/qPnZ3pWHsioifUuXHnR57GSI8nE2R4pckrUscgIitg/uLt42O6MZDKTq0GevWSOgUR2YCmNZqiqn1VqWNYNSelE3o36/34BxJRpWf+4i0IQM+ephMlqezatJE6ARHZAEEQ0LtZb9gJPOq8rIqMRWhbv63UMYjICkjTfvv2BRwdJRna6gkC8PLLpuUmRETloE+zPlAp+E5kWXVu1BkKO4XUMYjICkhTvDt04I2BZaVWA6NGSZ2CiGxIUP0gVLGvInUMq+SkdMLo50ZLHYOIrIQ0xdvODnj/fa71LotatYDnn5c6BRHZEJkgwweBH0AtV0sdxepUta+KEI8QqWMQkZUQRFEUJRn56lWgXj2goECS4a2SoyPw9dfAiBFSJyEiG3Mj/wbc57hDV6STOorVUCvU6KrsinO/nIOLiwvy8vKQm5sLrVaLvLw86HQ66HQ66PV6/PHHH3jhhRekjkxEEpOueANAWBiwbh1QVCRZBKvi5ARkZpr+l4ionA1YPwCrjq+C3qiXOopVUCvUWOCxAG+/8fYjH6dSqXD58mU4OzubKRkRWSpptxaZMcN09Dk9nloNfPQRSzcRVZhpHadBLuM5CyWhkqsQGRiJIa8PwXfffQeHh9y3pFAo8M4777B0ExEAqYt3o0bAm2/yJMuSsLc3rYsnIqog9avWx9st34a9Ha/Jj6O0U2Jc0DgAwLBhwzBo0CCo1Q9eIz927FhzRiMiCyb9ZtpffME9vR+jUKnE0X79IPJmVCKqIKIo4tatWxhQfwDsZNyu9FEcFY74POTzu46IX7hwIVq0aAGlUnnXY1UqFbp27YrFixcjPz/f3FGJyMJIu8b7tmnTTMtOtFqpk1geQUBe3bp4Vq1Gg6efxrx58/DMM89InYqIrNCOHTuwfv16ZGZm4urVq8jKysLNmzdx69Yt5OXlQRRFiKKIkTEjsTx9ObR6XpMfpKFLQ6SGp0Jpd3fJvnHjBnx8fHDp0iWIogi1Wo2dO3ciLy8Pc+fOxYEDBzB8+HCMHDkSderUkSg9EUnJMqaaJ0wAGjQwHQ5Dd3NwgHrzZhw5dgwhISEIDAzExIkToeUvKURUSv/88w++/fZbrFu3Dvv27UNycjIuXbqE3NxcGI1GCIKAV155BVH9o/B09achEyzjR4QlUclVWNNnzX2lGwCqVauGHTt2wPH/D4h7+umn8dxzzyEkJAQbN27Evn37kJWVBS8vLwwePBiJiYnmjk9EErOMq6pcDqxZw0N17qVWAx98APj5QalUIjIyEomJicjIyICXlxdWrVoFS3jDgoisw6hRo+Du7v7Qz1epUgUrVqyAncwOq/us5lrve6jlaoQ/G47W7q0f+pimTZti9erVEAQBU6ZMue9zixYtwqlTp9CkSRN07doVL7zwArZs2QKj0VjR8YnIAljGUpPbpk83/eFsrumQoWeeARITH7jzy759+xAeHo7q1atjwYIFaN68uQQhicjabN++Ha+++iry8vLu+rijoyOWL1+O3r17F39s9v7ZmLx7MvL0efe+TKUjE2Ro6NIQSe8lwV7++F9IkpOT4enpCdkj7mEqLCzEqlWrMGfOHOh0OkRERGDAgAFQ8X4eIptlGTPet334IRAczJlvwLRt4J9/PnS7xXbt2kGj0aB3797o2LEjIiIikJ2dbeaQRGRNRFHE9evXi5eV3CaXyxEUFIRevXrd9fixgWPRpVEXqOQsgk5KJ2wbsK1EpRsAmjVr9sjSDQBKpRIDBgzAkSNHsGjRImzevBkNGjTAJ598gn///bc8YhORhbGs4i2TmZacPPWUaca3slKpgM2bgfr1H/kwuVyOkSNHIikpCVqtFp6enli+fDnfsiSi+xw/fhwdO3bE9OnTsWLFirv2nba3t8eyZcvuKuMAIAgCfu71Mxq4NKjU+3ur5Cr8FvYbGlVrVCGvLwgC14ETVRKWVbwB07HosbFAZT1sQK0G5s0D2rYt8VNcXV2xePFibNy4EdHR0QgKCoJGo6m4jERkNbKzsxEREYGQkBD06tULGo0Gffv2RWRkJFQqFRwdHTF79uyHrv1WKVTYPmA7nJWV85qsVqgxq/MshDQMMct4XAdOZNssa433nRISgPbtgZwcqZOYj1oNjB8P3HNDTmkYjUasWLECEydORPfu3TFt2jTUrFmzHEMSkTUwGo344Ycf8NFHHyE0NBTTp0+Hq6tr8ed1Oh08PDxQv359HDx48L7Z7nsdu3wMbZe1xa2CWxUd3WKoFWq8/9z7mNZpmmQZuA6cyLZYbvEGgEOHgI4dgdxcqZNUPLUaGDPGdHNpObh58yamTJmClStX4tNPP8Xw4cNhV5mX7xBVIhqNBuHh4TAajVi4cCECAgIe+LiTJ0/CxcUFtWrVKtHrHsk8gpAVIZWifKsVarzr/y6+6vzVY38pMQdRFLF7927uB05k5Sy7eAPAkSNASIipfNvq22xqtenG0k8+KfeXPnbsGEaNGoXs7GwsXLgQQUFB5T4GEVmGa9euYdKkSdiwYQOmT5+Ot95667E3+JVW4uVEtF/eHjkFOTCIhnJ9bUuhVqgR0SYCX4R8YRGl+14nTpxAVFQUVq5ciVdffRURERHw9fWVOhYRlYDlrfG+V6tWpvJdv75t7naiVgPffVchpRsAfHx8sGvXLkyYMAFhYWEYOHAgMjMzK2QsIpKGwWDAokWL0KxZMzg4OCA1NRVDhgwp99INAL61fZEwPAEeLh5wkNveNVklV2HhywsxteNUiyzdANeBE1kzy5/xvi0nB+jZE9i/H8izgT1l5XKgShXgjz+Ah7wNXN5yc3Mxbdo0LFmyBB999BFGjx4NxUO2KyQi6xAXF4fw8HBUqVIFCxYsMNvMZ25hLvqu6Ys96XtsYp9vuUwOZ6UztryxBW2eaiN1nFLhOnAi62E9xRswLTX55BNg7lwgP1/qNGXn6Ag0awZs2AC4uZl9+JMnT2LMmDFIT0/H/Pnz8cILL5g9AxE9mczMTEyYMAE7d+7EV199hX79+pl9htYoGvHFni8wK24WdEU6iLCeHyd3clQ4okmNJtjUfxPqVqkrdZwy4zpwIstn+UtN7iSTAdOmAfv2AQ0bmpZpWBM7O1Pm6dOBAwckKd0A0KRJE2zZsgUzZ87EsGHD0Lt3b6Snp0uShYhKR6/XY/bs2fDx8YG7uztSU1PRv39/SZZFyAQZpnSYgvi34/F09aehVljXNVkmyKCSq/B5yOc4POywVZdugPuBE1kD6yret7VuDaSkACNHmg6bkVvBwQ6OjoC/P3DsGDB6tOmXCAkJgoDu3bsjKSkJvr6+aNWqFaZOnQqdTidpLiJ6uNjYWPj5+WH79u2Ii4vDzJkz4eTkJHUs+NXxQ9J7SYhoEwGVXGUVh+04KhzRsk5LHB1xFGMDx0ImWOePw4fhOnAiy2RdS00e5MwZIDLStFZapwMs7ctxdARq1QLmzwe6dQMs9Gadc+fO4YMPPsA///yDefPmITQ01GJvLCKqbNLT0/HBBx9Ao9Fg3rx56N69u8X+95l+Mx3jt4/HppObUGAogFG0rJLnqHBEDXUNzH9pPro3tdzvY3njOnAiy2D9xfu2o0eBiAggPh4wGAC9Xto8Tk6mP19+Cbz+ummZiRXYtm0bRo8ejcaNG2PevHl45plnpI5EVGnpdDp8/fXXmDt3LsaMGYNx48ZZTVE6fuU4Iv6IwF/n/4JRNKLQUChpHielE9QKNWZ2momBfgNhJ7OOa3J54zpwImnZzntrfn7Azp2mpRzvvmsqveY+dt7e3rTlYceOwK+/AhcvAgMGWE3pBoAuXbogMTERISEhCAwMxMSJE6HVaqWORVSpiKKITZs2wdvbG0eOHIFGo8HkyZOtpnQDQPNazbF94HYkv5eMkQEj4ax0Nvux80o7JRzkDujQoANW9V6FS2MvYXDLwZW2dANcB04kNduZ8b5Xfj6wbh3w00/Arl2AUlkxh/A4OZlm159+Gujf31S069cv3zEkcunSJYwfPx579+7FV199hb59+1aat2WJpJKWlob3338fp0+fxvz589GlSxepI5ULXZEOv6X+hpjEGOw8uxMKOwVyC3PLfSmKo8IRRcYiNKrWCP2b98ebvm+iYbWG5TqGrcnKysLixYuxcOFCeHl5YezYsXjppZcqZB94osrOdov3nQoKgD17TNv37dsHnDhhKuKCYFoXXpJlKTKZaTZbLjftI16njmn/7W7dgNBQoHbtiv86JLJv3z6Eh4ejevXqWLBgAZo3by51JCKbo9VqMW3aNCxevBgTJkzAmDFjoFQqpY5VIQoNhdibvhcbUjdgb8ZenLh2AnKZHDJBBl2RDnrj46/JAgSoFKYbOfP1+ajlWAv+7v4IbRKK0CahqOPEpROlxXXgRBWvchTvexkMpvJ99KhpOci5c6Y/ly4BBQVIP30aderWhb1aDbi6mmawGzUC3N0BT0+gRQvTTHclUlRUhO+++w6fffYZ3njjDXz66aeoWrWq1LGIrJ4oili9ejXGjRuH4OBgfPnll3B3d5c6llkZjAaczDqJo5eP4sKtC8jIzsDZG2dxMeciCgwF0BfpYWdnB7lMjprqmmhQtQEaujSEu7M7PGt6okWdFnC2N/PSQhvGdeBEFadyFu/H8PX1RUxMjNlOgLMmV69exaRJk7Bp0ybMmDEDAwcO5NuRRGV0/PhxjBo1CtevX8eCBQsQHBwsdSSLU1hYiCpVqmDu3Ll49913pY5T6Zw4cQJRUVFYuXIlXn31VURERPBnI9ETYGOiUnF1dcXixYuxceNGREdHIygoCBqNRupYRFYlOzsbERERCAkJQa9evaDRaFi6H2Lp0qUoKCjAjBkzwHki8+N+4ETli8WbyiQgIADx8fEYNmwYQkNDMXz4cFy7dk3qWEQWzWg0Yvny5fD09ERubi6Sk5MRHh4OuTUcAiaBwsJCfPLJJwCAa9euYdOmTRInqrxq1KiBjz76CGfPnsWgQYMwadIkeHt7Y/HixcjPz5c6HpHVYPGmMpPJZBg8eDBSUlLg4OCAZs2aYdGiRTAYDFJHI7I4Go0GQUFBiI6OxsaNG7FkyRK4urpKHcuiLV26tLjU5efnIzIykrPeElMqlRgwYACOHDmCRYsWYfPmzWjQoAE++eQT/Pvvv1LHI7J4LN70xFxcXBAVFYUdO3Zg9erV8Pf3R1xcnNSxiCzCtWvXMHz4cHTr1g1Dhw5FfHw8AgICpI5l8W7Pdt95jkBmZiZnvS0E9wMnKhsWbyo3Pj4+2LVrFyZMmICwsDAMHDgQmZmZUscikoTBYMCiRYvQrFkzODg4IDU1FUOGDOHNyCV052z3bbm5uZz1tkBcB05UcvwJQOVKEAT069cPqampqFu3Lnx8fDB79mzoS7JXOpGNiIuLg7+/P1atWoXY2FhERUXBxcVF6lhW40Gz3bdx1ttycR040eOxeFOFcHJywowZM7B//37ExsbCz88PsbGxUsciqlCZmZkYOHAgwsLCMH78eOzevZtbr5XB0qVLH1i6Ac56WwOuAyd6OBZvqlBNmjTBli1bMHPmTAwbNgy9e/dGenq61LGIypVer8fs2bPh4+MDd3d3pKamon///hAEQepoVumvv/6CnZ0dnJyc4OTkBJlMBrVaXfz3Gzdu4PLly1LHpMfgOnCi+7F4U4UTBAHdu3dHUlISfH190apVK0ydOhU6nU7qaERP7PY7Otu3b0dcXBxmzpwJp0p2sm15i4mJQU5OTvGfli1bYs+ePcV/v3r1Kk9RtDJcB05kwuJNZqNSqTB58mRoNBokJCTA29sbmzZt4lvGZJXS09PRu3dvDB06FDNmzMDWrVvRtGlTqWMRWTSuA6fKjsWbzM7DwwNr165FdHQ0xo0bh9DQUKSlpUkdi6hEdDodpk6dilatWsHX1xfJycno0aMHl5UQlQLXgVNlxeJNkunSpQsSExMREhKCwMBATJw48aE3VBFJTRRFbNq0Cd7e3jhy5Ag0Gg0mT54MlUoldTQiq8V14FTZsHiTpJRKJSIjI5GYmIiMjAx4eXlh1apVXH5CFiUtLQ2hoaEYN24coqOjsW7dOnh4eEgdi8imcB04VQYs3mQR3N3dERMTg59++gnTp09Hx44dcfz4caljUSWn1WoxceJEBAYGokOHDkhMTESXLl2kjkVk07gOnGwZizdZlHbt2kGj0aB3797o2LEjIiIikJ2dLXUsqmREUcSqVavg5eWFjIwMJCYmYty4cVAqlVJHI6o0uA6cbBGLN1kcuVyOkSNHIikpCVqtFp6enli+fDnfaiSzOH78ODp27Ijp06cjJiYGMTExcHd3lzoWUaXFdeBkS1i8yWK5urpi8eLF2LhxI6KjoxEUFASNRiN1LLJR2dnZiIiIQEhICHr16gWNRoPg4GCpYxHRHbgOnKwdizdZvICAAMTHx2PYsGEIDQ3F8OHDce3aNaljkY0wGo1Yvnw5PD09kZubi+TkZISHh0Mul0sdjYgeguvAyVqxeJNVkMlkGDx4MFJSUuDg4IBmzZph0aJFMBgMUkcjK6bRaBAUFITo6Ghs3LgRS5Ysgaurq9SxiKiEuA6crA2LN1kVFxcXREVFYceOHVi9ejX8/f0RFxcndSyyMteuXcPw4cPRrVs3DB06FPHx8QgICJA6FhGVEdeBW458fT5u5N/AVe1VZOVlIVuXDaPIZUC38b1Usko+Pj7YtWsXVq1ahbCwMHTs2BGzZs2Cm5ub1NHIghkMBnz33Xf49NNP0b9/f6SmpsLFxUXqWERUjm6vA//iiy+wePFidO3aFV5eXhg7dixeeuklyGScc3xS2bpsJPybgMOXDmP/+f04d/McLudexnXddegNeshlcgiCAFEUYRSNMIpGVLGvAle1K9yruKNlnZZ4ru5zaO3eGo2rNa5UJ/8KIk8quY+vry9iYmLg6+srdRQqgdzcXEybNg1LlizBRx99hNGjR0OhUEgdiyxMXFwcwsPDUaVKFSxYsID/fVsRf39/fPvtt/D395c6ClmhwsJCrFq1CnPmzIFOp0NERAQGDBjAU2dLQW/Q46+Mv/Br8q/47cRvuKq9CpVCBV2RDoWGwlK/ngABTkonGEQDRFFEm6fa4A2fNxDaJBS1nWpXwFdgOVi8H4DF2zqdPHkSY8aMQXp6OubPn48XXnhB6khkATIzMzFhwgTs3LkTX331Ffr161epZldsAYs3lQdRFLF7927MnTsXBw4cwPDhwzFy5EjUqVNH6mgWSRRFxJ2Pw7wD87D11FbIZXJoC7UwiBVzb5WjwhF6ox6NqzXGewHvYaDfQFSxr1IhY0mJ77eQzWjSpAm2bNmCmTNnYtiwYejduzfS09OljkUS0ev1mD17Nnx8fODu7o7U1FT079+fpZuokuI68JLJLcxF9KFoNJrfCC/FvIR1KeuQp8/DrYJbFVa6AUCr16LQUIiUayn4MPZD1Pm6Dgb/NhjHLh+rsDGlwOJNNkUQBHTv3h1JSUnw9fVFq1atMHXqVOh0OqmjkRnFxsbCz88P27dvR1xcHGbOnAknJyepYxGRheB+4PfTFenw1f6v4DbbDeO2j8O5m+eg1WshwvwLI7R6LfKL8hFzLAbP/e85vBjzIlKuppg9R0Vg8SabpFKpMHnyZGg0GiQkJMDb2xubNm0CV1bZtvT0dPTu3RtDhw7FjBkzsHXrVjRt2lTqWERkobgfOGAwGrA0YSmemvMUPtv9GXILc6HVa6WOBQAoMhYhvygfsWdi0Xpxa7y+9nWczz4vdawnwuJNNs3DwwNr165FdHQ0xo0bh9DQUKSlpUkdi8qZTqfD1KlT0apVK/j6+iI5ORk9evTgshIiKpHKuh/4iWsn0Hpxa4zeOhpZ+VkWU7jvZRSNyC/Kx6/Jv8LrGy8sOrTIaifSWLypUujSpQsSExMREhKCwMBATJw4EVqtZV5gqOREUcSmTZvg7e2NI0eOQKPRYPLkydytgIjKpLKsAzcYDZgVNwstv2uJY1eOWWzhvpfeqIdWr8X47eMR+H0gzt08J3WkUmPxpkpDqVQiMjISiYmJyMjIgJeXF1atWmW1vzVXdmlpaQgNDcW4ceMQHR2NdevWwcPDQ+pYRGQjbHUd+FXtVbT5vg2+2PMF8ovyrfJwG61ei8OXDqP5ouZYm7xW6jilwuJNlY67uztiYmLw008/Yfr06ejYsSOOHz8udSwqIa1Wi4kTJyIwMBAdOnRAYmIiunTpInUsIrJRtrQO/Oi/R9E8ujmO/nvUama5H8YgGqDVazHwt4H4eOfHVvMLBIs3VVrt2rWDRqNB79690bFjR0RERCA7O1vqWPQQoihi1apV8PLyQkZGBhITEzFu3DgolUqpoxFRJXDnOvDo6GirWwe+NnktgpYG4Yr2CvRGvdRxyk2ePg/zDsxD6M+h0BZa/i8TLN5UqcnlcowcORJJSUnQarXw9PTE8uXLrfptRFt0/PhxdOzYEdOnT0dMTAxiYmLg7u4udSwiqoQEQUCHDh2wceNG/PXXX7h+/brFrwNfrFmMgb8NtPpZ7ofR6rXYdW4X2i5ri1sFt6SO80gs3kQAXF1dsXjxYmzcuBHR0dEICgqCRqOROlall52djYiICISEhKBXr17QaDQIDg6WOhYREQDTwW3ffPONRa8DX3RoESL+jECePk/qKBVKV6RDytUUBC0NsujyzeJNdIeAgADEx8dj2LBhCA0NxfDhw3Ht2jWpY1U6RqMRy5cvh6enJ3Jzc5GcnIzw8HDI5XKpoxER3cdS14EvS1iGyG2RNl+6byswFCAtKw3tl7e32GUnLN5E95DJZBg8eDBSUlLg4OCAZs2aYdGiRTAYKu6oXPqPRqNBUFAQoqOjsXHjRixZsgSurq5SxyIieixLWge+6+wujNwyEvlF1nUD6JMqMBQg9Woq+v7a1yJ3LWPxJnoIFxcXREVFYceOHVi9ejX8/f0RFxcndSyblZWVhREjRqBbt24YOnQo4uPjERAQIHUsIqJSk3od+JkbZ/DqqlcrXem+TWfQYfe53Ziye4rUUe7D4k30GD4+Pti1axcmTJiAsLAwDBw4EJmZmVLHshkGgwHR0dHw8vKCvb09UlNTMWTIEMhkvDwRkfUz9zrwnIIcvPDDC8gtzC3317Ymefo8fL3/a6xPWS91lLvwJxtRCQiCgH79+iE1NRV169aFj48PZs+eDb3edrZkkkJcXBz8/f3xyy+/IDY2FlFRUXBxcZE6FhFRuTPXOvChm4YiMyfTava1rkj5RfkYsH4AMrIzpI5SjMWbqBScnJwwY8YM7N+/H7GxsfDz80NsbKzUsaxOZmYmBg4ciLCwMIwfPx67d++Gr6+v1LGIiCpcRa4D//3k79h0chN0Bl05pbV+BYYC9F/b32LWe7N4E5VBkyZNsGXLFsycORPDhg1D7969kZ6eLnUsi6fX6zFnzhz4+PjA3d0dqamp6N+/PwRBkDoaEZFZlfc68Bv5NzBg/YBKs4NJSRUZi3D036NYrFksdRQALN5EZSYIArp3746kpCT4+vqiVatWmDp1KnQ6zjQ8yO13CLZt24a4uDjMnDkTTk5OUsciIpJceawDH7V1FEv3Q2j1Wnyw7QNcyrkkdRQWb6InpVKpMHnyZGg0GiQkJMDb2xubNm2ymLe1pJaRkYE+ffpg6NChmDFjBrZu3YqmTZtKHYuIyOKUdR348SvHsTZlLQoMBWZMa10KDYWYuGOi1DFYvInKi4eHB9auXYvo6GiMGzcOoaGhSEtLkzqWZHQ6HaZOnYqWLVvCx8cHycnJ6NGjB5eVEBE9RmnXgb//x/soNBRKkNR66I16rE5ajZNZJyXNweJNVM66dOmCxMREhISEIDAwEBMnToRWa5knaFWUzZs3w9vbG0eOHIFGo8HkyZOhUqmkjkVEZFVKsg48LiMO8RfiuYtJCRQaCjH2z7GSZmDxJqoASqUSkZGRSExMREZGBry8vLBq1SqbX36SlpaGbt26ITIyEtHR0Vi3bh08PDykjkVEZPUetg58+K/Duba7hAyiATvP7kTK1RTJMrB4E1Ugd3d3xMTE4KeffsL06dPRsWNHHD9+XOpY5U6r1WLSpEkIDAxEhw4dkJiYiC5dukgdi4jI5ty5DrzrG12ReitV6khWRW/QI+pglGTjs3gTmUG7du2g0WjQu3dvdOzYEREREcjOzpY61hMTRRGrV6+Gl5cX0tPTkZiYiHHjxkGpVEodjYjIpimVSmTUyYDMjlWuNIrEIvyY+CO0hdIsAeW/LSIzkcvlGDlyJJKSkqDVauHp6Ynly5dXyJHB5pCUlIROnTph2rRpiImJQUxMDNzd3aWORURUKeTr87E0YSn0Rp6gXFoCBMQkxkgyNos3kZm5urpi8eLF2LhxI6KjoxEUFASNRiN1rBLLzs5GREQEQkJC0LNnT2g0GgQHB0sdi4ioUvnz9J/cJaqMtHotvtN8J8nYLN5EEgkICEB8fDyGDRuG0NBQDB8+HNeuXZM61kMZjUasWLECnp6eyM3NRVJSEsLDwyGXy6WORkRU6fxy/BfkFOZIHcNqJV1NQlZeltnHZfEmkpBMJsPgwYORkpICBwcHNGvWDIsWLYLBYJA62l00Gg2CgoKwaNEibNy4EUuWLIGrq6vUsYiIKiWD0YAtaVukjmHVlHZKbD211ezjsngTWQAXFxdERUVhx44dWL16Nfz9/REXFyd1LGRlZWHEiBHo1q0bhg4divj4eAQEBEgdi4ioUjt48aDUEaxebmEufj72s9nHZfEmsiA+Pj7YtWsXJkyYgLCwMAwcOBCZmZlmz2EwGBAdHQ0vLy/Y29sjNTUVQ4YMgUzGSwYRkdT2nNsDXZFO6hhWL+58nNnP1+BPUSILIwgC+vXrh9TUVNStWxc+Pj6YPXs29Hrz3LkeFxcHf39//PLLL4iNjUVUVBRcXFzMMjYRET3e7vTd3M2kHBQaCnEx56JZx2TxJrJQTk5OmDFjBvbv34/Y2Fj4+fkhNja2wsbLzMzEwIEDERYWhvHjx2P37t3w9fWtsPGIiKhsjmQekTqCTVDaKaG5ZN5dxVi8iSxckyZNsGXLFsycORPDhg1D7969kZ6eXm6vr9frMWfOHPj4+MDd3R2pqano378/t6kiIrJA1/Ov45bultQxbEJuYS7+vvi3Wcdk8SayAoIgoHv37khKSoKvry9atWqFqVOnQqd7sjV+t2fSt23bhri4OMycORNOTk7llJqIiMrbyayTcFA4SB3DJhhFIxL+TTDrmCzeRFZEpVJh8uTJ0Gg0SEhIgLe3NzZt2lTqm0MyMjLQp08fDB06FDNmzMDWrVvRtGnTCkpNRETl5VLOJakj2JQLty6YdTwWbyIr5OHhgbVr1yI6Ohrjxo1DaGgo0tLSHvs8nU6HqVOnomXLlvDx8UFycjJ69OjBZSVERFYiMycThYZCAECDqg1w7N1jd31+Svsp+CDwgxK/3q5Bu9DarXW5ZiytZT2WoZdXr+I86e/fvZxyfdh65Hz0+MOC4oaUfhveK9orpX7Ok2DxJrJiXbp0QWJiIkJCQhAYGIiJEydCq9U+8LGbN2+Gt7c3jhw5Ao1Gg8mTJ0OlUpk5MRERPYkLty5IupWgTChZdbQT7Mo8xk3dTQTVCwIAVLWvCjcntxI9L2hpUInHuJ3vhu6GWbcU5FnPRFZOqVQiMjISr7/+OsaPHw8vLy989dVX6Nu3LwRBQFpaGt5//32cPn0a0dHR6NKli9SRiYiojP7N/bdEj9s1aBcOXjyIEI8QuDi44O2Nb+OvjL/gIHfAsh7L4FfbD6nXUqGS/zcB07lRZ3zW4TPYy+1x+vppDN4wGFq9FmfHnMWqpFXo3Kgzvoz7ErcKbmHOi3OgLdQi7nwcGlVrhFdWvoIp7aegcbXGaFStETKyM/DRjo/w42s/wlHpCAAI3xKO+AvxAIAFXRegc6POOH/rfPEM/m2/HP8F/Zr3Q9z5OPT06ol1qevgXcsbAOCocMSGfhtQTVUNCpkCH+/6GBtPbAQA5HyUA+cZzgCALzt/ia5Pd4Uoipi6bypWJ61G+wbt8UXIF7ihuwHPmp5ourApioxFKDQUwl5u/2T/YkqIxZvIRri7uyMmJgb79u1DeHg4vvnmG3h6emLdunWYMGEC1q9fD6VSKXVMIiJ6AqXZv1suk+O5/z2Hrk93xZT2U9D5x8541/9d5Onz0GxRM/jU8sGR4aatCWuoauDj4I/xwo8vIE+fh/FB4zE2cCy+2PsFACArLwutF7eGvZ090kalIXh5MM7dPIefe959+mMz12Zou6wtdEU6qOQqdP6xMwoMBXi6+tNY2WslApYE4DXP19C0RlM0W9QMtR1rI3lkMpYmLC1+jR1nd2DJK0sgE2To17wfhm0ahk+CPwEA6Ip0eG3Va8gpzEENVQ0ceOdAcfG+radXT7So3QJ+3/qhpromDg09hL3pewEArdxaoXl0c5y7eQ6AaQbfIBpK9y/hCbB4E9mYtm3b4sMPP8TIkSPx999/Y8CAARg2bBhLNxGRDbizJIp48BKJ2x9fl7IOAKDJ1MDDxQMAENwgGPMPzgcAHLtyDImXEwEAbZ5qg2auzYrXSSvtlMWz0wCwKmkVAMCzpifO3DhTXFxXHl+JYa2HFT9u48mNxUthFHYKLOy6EC3qtIBBNKBJjSbFGVYeXwmjaERmbiZ2nt1599doNOCvjL/Qr3k/qOQqpGf/t+ZbEARM7zQdwQ2CYRSNqOtcF7Uda+Oy9nLxY9rWb1v8+le0V7Dn3B4EuAfgVsEt/H3x7+LsACBAgMHI4k1EZZCUlIRRo0YhKysLv/32G7y8vDBp0iR4enpixowZGDhwII99JyKyYgqZovifs/KyUM2h2l2fr66qjrM3zwIACooKAJiKrFz26MonCAK2n96O19e9/sDPawsffP/Qox4X0SYCl7WX4fetH2SCDLqPS742/Zfjv2B92Hp8uufTuz7+hs8bcFW7ovXi1igyFuHsmLNwkJd8e0Wt/u6vwygaobBTPOTR5Y8/gYlsQHZ2NiIiIhASEoKePXtCo9EgODgYrq6uWLx4MTZu3Ijo6GgEBQVBozHvKV1ERFR+nJT/nbWg1WuRmZuJEI8QAEA1h2p46emX8FfGXw99/t70vXjdx1SuvV294VvbdELxgQsHEFQ/CI2rNQYAqBVqPFP9mfuefyLrBBpVa4QGVRsAAMK8wx46VlWHqsjMzYQIEQP8BhSX/73pexHmHQaZIEMdpzrF+e+0L2MfZvw1AyuPrbzvNa/kXUGRsQgdPDoUz+Tf9dz0fcWvX1NdE8ENgh96UI5RNN71y0xF44w3kRUzGo348ccf8eGHHyI0NBRJSUlwdXW973EBAQGIj4/HihUrEBoaiu7du2PatGmoWbOmBKmJiKis6letD7kgR5FYBAAYuH4gvnn5G8x5cQ4A4LM9n+HMjTMPfX704Wgs67EMye8lI+VaSvGR6dfyruGt397Cyl4ri280/Hjnx0i7fvdWtboiHd7b8h7+ePMPaAu1OHTp0EPHWnRoEdb2XYuBvgPxx+k/kFuYCwBYn7oeHRt2RPJ7ycjIzrhrScudZsfPvu9jPyX+hE39NyFxRCIOXzqMlKspxZ+7vTvJ+tT1CKwXiKMjjkIURYyPHY/L2svwrOl53+s52zvDTlb2HVhKSxDNuYeKlfD19UVMTAx8fX2ljkL0UBqNBuHh4TAajVi4cCECAgJK9LybN29iypQpWLlyJT799FMMHz4cdnbmu+gQlZa/vz++/fZb+Pv7Sx2FSHI/HP0BI7eMLC6xUnBUOBYv2fjm5W+Qdj0N8w7MkywPYFpic2TYEXhEeZTqeY2qNcLp0acrJtQDcKkJkZXJysrCiBEj0K1bNwwdOhTx8fElLt0A4OLigqioKOzYsQOrV6+Gv78/4uJKf+gAERGZn5uT2xPtkV0ehrYeioThCUh6LwlV7aviu8PfSZrHzckN8W/H4+v4r8v0XHPiUhMiK2EwGLB48WJMmTIF/fv3R2pqKlxcXMr8ej4+Pti1axdWrVqFsLAwdOzYEbNmzYKbm3kvQkREVHL1qtYz6y4cDzLvwDzJZ7jvlJmbiaYLm5bpuY2rNy7nNI/GGW8iKxAXFwd/f3/88ssviI2NRVRU1BOV7tsEQUC/fv2QmpqKunXrwsfHB7Nnz4ZeX/J9YomIyHyeqf4MCo2Fj38gPZZKrkLgU4FmHZPFm8iCZWZmYuDAgQgLC8P48eOxe/fuCrn3wMnJCTNmzMD+/fsRGxsLPz8/xMbGlvs4RET0ZOxkdg/cbYRKTyFToLVba7OOyeJNZIH0ej3mzJkDHx8fuLu7IzU1Ff3794cgCBU6bpMmTbBlyxbMnDkTw4YNQ+/evZGenv74JxIRkdm0rd9W6gg2Ia8oDz61fcw6Jos3kYW5PeO8bds2xMXFYebMmXBycnr8E8uJIAjo3r07kpKS4Ovri1atWmHq1KnQ6Up+8AEREVWctvXb3rWfN5VNQ5eGpTp8pzyweBNZiIyMDPTp0wdDhw7FjBkzsHXrVjRtWrabRcqDSqXC5MmTodFokJCQAG9vb2zevFmyPEREZPJi4xehN/BenCehkCnQu1lvs4/L4k0kMZ1Oh6lTp6Jly5bw8fFBcnIyevToUeHLSkrKw8MDa9euRXR0NCIjI9GtWzekpaU9/olERFQhXB1d8UwNrvN+EvZye/T06mn2cVm8iSS0efNmeHt748iRI9BoNJg8eTJUKpXUsR6oS5cuSExMREhICAIDAzFp0iRotVqpYxERVUqvN38d9nb2UsewWnaCHVq5tTL7uCzeRBJIS0tDt27dEBkZiejoaKxbtw4eHh5Sx3ospVKJyMhIJCYmIj09HV5eXli9ejV4AC4RkXn1atYLMoE1rizsBDv09OopyfeP/8aIzEir1WLSpEkIDAxEhw4dkJiYiC5dukgdq9Tc3d0RExODn376CdOmTUOnTp2QlJQkdSwiokqjSY0maObaTOoYVslebo/Rz42WZGwWbyIzEEURq1evhpeXF9LT05GYmIhx48ZBqVRKHe2JtGvXDhqNBr169UJISAgiIiKQnZ0tdSwiIqt3+vRpHDt2DGfPnsXVq1eRl5d337uLE4ImcHeTMmhcrTFa1Gkhydg8Mp6ogiUlJWHUqFHIyspCTEwMgoODpY5UruRyOUaOHIm+ffti0qRJ8PLywowZMzBgwADIZPzdnoioLEJCQnD16lXI5XIUFRWhqKgIBoMBSqUS9vb2EEURTlWcYBduJ3VUq+KkdMKEoAmSjc+fikQVJDs7GxEREQgJCUHPnj2h0WhsrnTfydXVFYsXL8aGDRuwaNEiBAUFQaPRSB2LiMgqDRs2DACQm5sLnU6HoqIiiKKIgoIC3Lp1C1qtFq92fxURbSKglqslTms9pNpG8DYWb6JyZjQasWLFCnh6eiI3NxdJSUkIDw+HXF453mAKCAhAfHw8hg0bhtDQUIwYMQJZWVlSxyIisirvvffeQz/n4OCAXr164ZtvvsEHz38AhZ3CjMmsl6PCEbNemAV7uXS7wbB4E5UjjUaDoKAgLFq0CBs3bsSSJUvg6uoqdSyzk8lkGDx4MFJSUmBvbw8vLy9ER0fDYDBIHY2IyCpUrVoVzz///H0fl8vleOaZZ/DDDz9AEAQ4KZ3wecjncFQ4SpDSulRTVcPgloMlzcDiTVQOsrKyMGLECHTr1g1Dhw5FfHw8AgICpI4lORcXF0RFRWHHjh1YtWoV/P39ERcXJ3UsIiKLlZubiwULFqBJkya4du0aFIq7Z7OrVq2Kbdu2wcHhv6POR/iP4E2Wj+GocMS8F+dBLpP23WcWb6InYDAYEB0dDS8vL9jb2yM1NRVDhgzhTYX38PHxwa5duzBhwgSEhYVh4MCByMzMlDoWEZHFOH/+PCZMmAAPDw/s3bsXMTExOHr0KNq2bVv8GLVajW3btqFOnTp3PVdpp8TSHkuhVnCt94PIZXK0qNNCkpMq78V2QFRGcXFx8Pf3xy+//ILY2FhERUXBxcVF6lgWSxAE9OvXD6mpqahbty58fX0xZ84c6PV6qaMREUnm8OHDeP311+Hn54fCwkIcOnQIa9asQWBgIABg8uTJUKvVUKvV+P7779Gq1YNPW3z5mZfxSpNXeJrlA9jb2ePnXj9DEASpo7B4E5VWZmYmBg4ciLCwMIwfPx67d++Gr6+v1LGshpOTE2bMmIG4uDhs374dfn5+iI2NlToWEZHZGAwGrF+/HsHBwejVqxf8/f1x9uxZzJ07Fw0bNrzrse3bt0ejRo0wevRo9OvX75Gv+23ot3BUcq33nRwVjpjz4hzUr1pf6igAuI83UYnp9XosWLAA06dPxzvvvIPU1FQ4OXFNXVk1adIEW7ZswaZNmzBs2DC0bt0as2fPRv36lnFxJCIqb7m5uVi2bBnmzZsHV1dXjB07Fj179nzkrleCICAhIaFEO2O5OLjgl16/oMcvPZBflF+e0a2SvZ092jzVBkNbDZU6SjHOeBOVQGxsLPz8/LBt2zbExcVh5syZLN3lQBAEdO/eHUlJSfDx8UGrVq0wdepU6HQ6qaMREZWbB63fPnDgAPr27VuiQl2a7Wg7N+6MT4I/qfS7nMgEGWo71cbavmstYonJbSzeRI+QkZGBPn36YOjQoZgxYwa2bt2Kpk2bSh3L5qhUKkyePBmHDx9GQkICvL29sXnzZqljERE9kcet364oH7b9EC89/RJUclWFjmPJHBWOiB0Qi6oOVaWOchcWb6IH0Ol0mDp1Klq2bAkfHx8kJyejR48eFvVbsy3y8PDA2rVrER0djcjISHTr1g1paWlSxyIiKrHSrN+uKIIgIKZnDJ6u/jSUdkqzjGlJVHIV1vZdi2dqPCN1lPuweBPdY/PmzfD29saRI0eg0WgwefJkqFSVd9ZACl26dEFiYiJCQkIQGBiISZMmQavVSh2LiOih7tx/e9asWQgPD8fp06cxduxYVK1q/llXB7kD9ry1Bw2qNoBCVnlOtlTJVVjx6gp0btxZ6igPxOJN9P/S0tLQrVs3REZGIjo6GuvWrYOHh4fUsSotpVKJyMhIJCYmIj09HV5eXli9ejVEUZQ6GhFRsSddv12RqqmqYf/b++Hh4lEpZr5VchWW9liKPt59pI7yUCzeVOlptVpMmjQJgYGB6NChAxITE9GlSxepY9H/c3d3R0xMDH766SdMmzYNnTp1QlJSktSxiKiSk2r9dmnVVNfEwXcOwrOmp02v+VYr1Pip50/o1/zRWy5KjcWbKi1RFLF69Wp4eXkhPT0diYmJGDduHJRK258VsEbt2rWDRqNBr169EBISgoiICGRnZ0sdi4gqEUtYv10W1VTVcPCdgwhtEmpzu50oZApUV1XHnrf24DWv16SO81gs3lQpJSUloVOnTpg2bRpiYmIQExMDd3d3qWPRY8jlcowcORJJSUnQarXw8vLCihUrYDQapY5GRDbM0tZvl4WD3AGreq/C5PaTbWbmWyVXwbOmJ46/exz+7v5SxykRFm+qVLKzsxEREYGQkBD07NkTGo0GwcHBUseiUnJ1dcXixYuxYcMGLFq0CEFBQdBoNFLHIiIbY8nrt8tCEASMDxqPTf03oaa6JhzsHKSOVGYquQqD/Abh76F/w83ZTeo4JcbiTZWC0WjEihUr4OnpidzcXCQlJSE8PNwqL5z0n4CAAMTHx2PYsGEIDQ3FiBEjkJWVJXUsIrJy1rJ+u6w6NeqEU6NOoXez3lAr1FLHKRWVXAU3Jzf8+eafiA6NhoPcun55YPEmm6fRaBAUFIRFixZh48aNWLJkCVxdXaWOReVEJpNh8ODBSElJgb29Pby8vBAdHQ2DwSB1NCKyIta6frusqjpUxY89f8T6sPVwd3a3+LXfckEOB7kDhrQcglOjT6Fdg3ZSRyoTFm+yWVlZWRgxYgS6deuGoUOHIj4+HgEBAVLHogri4uKCqKgo7NixA6tWrYK/vz/i4uKkjkVEFs4W1m8/iS6Nu+DcmHP4qstXcHFwsbgZcJkgg0quQg/PHkh+LxkLX15ocRlLg8WbbI7BYEB0dDS8vLxgb2+P1NRUDBkyBDIZ/+9eGfj4+GDXrl2YMGECwsLCMHDgQGRmZkodi4gsjK2t334SCjsF3vV/FxfHXsSkdpNQXVUdzkpnSTM5yB1gb2ePlxq/hAPvHMCvfX9Fw2rW/84DmwjZlLi4OPj7++OXX35BbGwsoqKi4OLiInUsMjNBENCvXz+kpqaibt268PX1xZw5c6DX66WORkQSs/X1209CrVBjYruJuBx5GT+89gPaPNUGDnIHs62jlgkyOCudUc2hGsY9Pw5nxpzB72/8Dt/avmYZ3xxYvMkmZGZmYuDAgQgLC8P48eOxe/du+Prazn+oVDZOTk6YMWMG4uLisH37dvj5+SE2NlbqWERkZpVt/faTksvkeNXzVcS/HY/k95IxveN0tHZrDaWdEs5KZwgQym0sB7kDHBWOqKmuiXdavYO1fdficuRlfB7yOdydbW+b38r1XgrZHL1ejwULFmD69Ol45513kJqaCicnJ6ljkYVp0qQJtmzZgk2bNmHYsGFo3bo1Zs+ejfr160sdjYgqUG5uLpYtW4Z58+bB1dUVY8eORc+ePSvdUpIn0bBaQ0QERiAiMAI38m8g9kws9l/Yj33p+5B8NRmCIEAhU0AURRQYClBgKLjvNewEOzjIHSCXyWEUjcgvyoebkxuerfssghsEo32D9vCt7QtBKL9Cb6n4/zyyWrGxsRg9ejTq16+PuLg4NG3aVOpIZMEEQUD37t3RuXNnfPXVV2jVqhXef/99REZGwsHBurajIqJHO3/+PBYuXIjvv/8eISEhiImJ4VKSclBNVQ19vPugj3cfAIBRNCL9Zjou5lzEpZxLyMzJxMWci8jT56HAUAC5IIfSTonaTrXh5uQGd2d3uDm7oXG1xnBUWvYuKhWFxZusTkZGBj744AMcPnwY8+bNQ/fu3SvFb8lUPlQqFSZPnoyBAwfigw8+gLe3N6KiohAaGip1NCJ6QocPH8acOXPwxx9/YNCgQTh06BCXklQgmSBDw2oNbeKmR3PhGm+yGjqdDlOnTkXLli3h4+OD5ORk9OjRg6WbysTDwwNr165FdHQ0IiMj0a1bN6SlpUkdi4hKieu3yZqweJNV2Lx5M7y9vXHkyBFoNBpMnjwZKpVK6lhkA7p06YLExESEhIQgMDAQkyZNglarlToWET1GZd9/m6wTizdZtLS0NHTr1g2RkZGIjo7GunXr4OHhIXUssjFKpRKRkZFITExEeno6vLy8sHr1aoiiKHU0IroH998ma8biTRZJq9Vi0qRJCAwMRIcOHZCYmIguXbpIHYtsnLu7O2JiYvDTTz9h2rRp6NSpE5KSkqSORUTg/ttkG1i8yaKIoojVq1fDy8sL6enpSExMxLhx46BUKqWORpVIu3btoNFo0KtXL4SEhCAiIgLZ2dlSxyKqdLh+m2wNizdZjKSkJHTq1AnTpk1DTEwMYmJi4O5ue5vnk3WQy+UYOXIkkpKSoNVq4eXlhRUrVsBoNEodjcjmcf022SoWb5JcdnY2IiIiEBISgp49e0Kj0SA4OFjqWEQAAFdXVyxevBgbNmzAokWLEBQUBI1GI3UsIpvE9dtk61i8STJGoxErVqyAp6cncnNzkZSUhPDwcF5cySIFBAQgPj4ew4YNQ2hoKEaMGIGsrCypYxHZBK7fpsqCxZskodFoEBQUhEWLFmHjxo1YsmQJXF1dpY5F9EgymQyDBw9GSkoK7O3t4eXlhejoaBgMBqmjEVkdrt+myojFm8wqKysLI0aMQLdu3TB06FDEx8cjICBA6lhEpeLi4oKoqCjs2LEDq1atgr+/P+Li4qSORWQV7ly/PXPmTK7fpkqF7+kDiI2NRWpqavHfr127hpUrV2Lv3r0AAHt7ewwaNIg7azwBg8GAxYsXY8qUKejfvz9SU1Ph4uIidSyiJ+Lj44Ndu3Zh1apVCAsLQ8eOHTFr1iy4ublJHY3I4pw/fx4LFizA999/j44dOyImJoZLSajSYfEGsHDhQvz++++ws7MDABQWFmLOnDkQBAGiKEIQBPTr14/Fu4zi4uIQHh6OKlWqIDY2Fr6+vlJHIio3t68PoaGhmDZtGnx9ffHRRx9h1KhRUCgUUscjktyhQ4cwd+5c/PHHHxg0aBAOHz7MpSRUaXGpCYDPP/8cCoUCBQUFKCgogCiKKCwsREFBAQRBQHh4OJydnaWOaXUyMzMxcOBAhIWFYfz48di9ezdLN9ksJycnzJgxA3Fxcdi+fTv8/PwQGxsrdSwiSdxev92uXTv07t2b67eJ/h+LNwBfX1+0b98eMtn93w6ZTIYPP/xQglTWS6/XY86cOfDx8YG7uztSU1PRv39/CIIgdTSiCtekSRNs2bIFM2fOxLBhw9CnTx9kZGRIHYvILO7df3vUqFFcv010Bxbv/zdr1izY29vf9TF7e3u89957qFmzpkSprE9sbCz8/Pywbds2xMXFYebMmXBycpI6FpFZCYKA7t27IykpCT4+PmjVqhWmTp0KnU4ndTSiCnH+/HmMHz8eDRo04P7bRI/A4v3/HjTrzdnuksvIyECfPn0wdOhQzJgxA1u3bkXTpk2ljkUkKZVKhcmTJ+Pw4cNISEiAt7c3Nm/eLHUsonJz6NCh4v239Xo9Dh8+zP23iR6BxfsOd856K5VKznaXgE6nw9SpU9GyZUv4+PggOTkZPXr04LISojt4eHhg7dq1iI6ORmRkJLp164a0tDSpYxGVCddvE5Udi/cdbs96A5ztLonNmzfD29sbR44cgUajweTJk6FSqaSORWSxunTpgsTERISEhCAwMBCTJk2CVquVOhZRiXD9NtGTY/G+x6xZswAAffv25Wz3Q6SlpaFbt26IjIxEdHQ01q1bBw8PD6ljEVkFpVKJyMhIJCYmIj09HV5eXli9ejVEUZQ6GtEDcf02Ufmp9P/FiKKI7IJsZOZk4t/cf6FT6dA5vDM6vd4J205vQw1VDbg7u6OWYy3YyeykjisprVaL6dOn47vvvsOECROwfv167m1OVEbu7u6IiYnBvn37EB4ejm+//RYLFiyAt7e31NEkJYoibhXcwqWcS7isvQxdkQ43a91E3JU4XD99HTVUNeDm7IZajrUgl1X6H2EVivtvE5U/QaxE0yxZeVnQZGpw+NJh7D63G4mXE5GVnwUZZLCX20Mm3P8GgAgReoMeBYYCOCud0ahaI7Sr3w5tnmoDf3d/PF39aZtfzyyKItasWYPIyEgEBwfjyy+/hLu7u9SxiGxGUVERvvvuO3z22Wd444038Omnn1aKt+6v51+H5pLpmrwnfQ+OXj6KrLwsAICD3KH4mlxQUAClUmk61OyOa7KT0gmNXBqhXQPTNbm1W2s8U+OZB17LqWQMBgM2btyIOXPmICMjA2PGjMHbb79dKf7/SGQONl28RVHEsSvHsCF1A34+/jPO3DgDlVyFPH0e9EZ9mV9XgAAnpRMMogH2dvbo0bQH+nr3RUjDEDjIHcrxK5BeUlISRo0ahaysLCxYsADBwcFSRyKyWVevXsWkSZOwefNmzJgxAwMGDHjg+QLWShRFJF9Nxm+pv+Hn4z/j1PVT5XpNNopGKGQKdG/aHX29+6Jjw45QKXjfSUnk5uZi2bJlmDdvHlxdXTF27Fj07NmTS0mIyplNFu+r2qtYcmQJ5h+cj9zCXOiNehQaCitsPAECnO2dUWgoxGuer+GDwA/Q2r11hY1nDtnZ2fj000/x008/YfLkyRgxYgQvwERmcujQIYSHh0Mmk2HhwoVo3dq6ryfX8q7h+yPfY97BebhVcAsGowEFhoIKG+/2NbmgqADdm3ZH5PORCHAPsPl3J8vi/PnzWLBgAb7//nt07NgRY8eO5VaARBXIpor3oYuHMPOvmdhyagsECMgvyjd7Bpkgg4PcAQ2qNsCEoAl43ed1KOwUZs9RVkajET/++CM+/PBDhIaGYvr06XB1dZU6FlGlYzQasWLFCkycOBE9evTAtGnTUKNGDaljlYrmkgYz42Zi88nNkl+Tn6ryFCYETcCbvm9Cacd7U+5dvz169Giu3yYyA5so3slXk/H+H+8j7nwc8vX5EGEZX5KT0gnOSmfMfXEu+nj3sfh1hxqNBuHh4TAajVi4cCECAgKkjkRU6d28eRNTpkzBypUr8dlnn2HYsGGws7PsG71PXDuB9/98H3vO7UGBoQBG0Sh1JACAo8IRTkonzHlxDvo172fx1+TyxvXbRNKz6uKdmZOJsX+OxYYTGyzq4n4vJ4UT3Ku449tu3yKkYYjUce6TlZWFSZMm4bfffsP06dPx1ltv2dS6UiJbcOzYMYwaNQrZ2dlYuHAhgoKCpI50nyvaK4jcFok1yWugN+hhEA1SR3ogR4Uj6jjVQXS3aHRu3FnqOBWO67eJLIdVFm9RFPHTsZ/w3u/vQVeke6KbcsxJrVCjT7M+WNB1AZztnaWOA4PBgMWLF2PKlCno378/PvvsM7i4uEgdi4geQhRFrFq1CpGRkejYsSNmzZoFNzc3qWNBFEWsTlqNYZuHIV+fb1XX5B5NeyC6WzSqOtjerC/XbxNZHqub1szMyUSXH7tgxOYRyCnMsZoLPADk6fOwKmkVGs9vjNgzsZJmiYuLg7+/P3755RfExsYiKiqKpZvIwgmCgH79+iE1NRV169aFr68v5syZA71euuvgFe0VdPu5G97e+DZuFdyyumvy+tT1aDy/Mf449YfUccrNoUOH8Prrr8PPzw96vR6HDx/GmjVrWLqJLIBVzXjHZcQh9OdQaPVaq7q4P4hKrkJEmwh80fELs64zzMzMxIQJE7Bz50589dVX6NevH+/0J7JSJ0+exJgxY5Ceno758+fjhRdeMOv4By8cRNefukJbqEWhseJ2jjIHtUKN9wLew6wXZlnl2m+u3yayDlZTvBdrFuP9P96X5K74iqJWqBHcIBhr+qyBk9KpQsfS6/VYsGABpk+fjnfeeQcff/wxnJwqdkwiqniiKGLTpk14//330bp1a8yePRv169ev8HGX/7McI38fibyivAofy1zUCjWer/c81vZdiyr2VaSOUyJcv01kXSz+13qjaMTwzcMR8WeETZVuwPQ25+5zu9Hi2xY4n32+wsaJjY2Fn58ftm3bhri4OMycOZOlm8hGCIKA7t27IykpCT4+PmjVqhWmTp0KnU5XIeMZRSPG/DEGI7fYVukGTNfkvzL+gm+0L87dPCd1nEc6f/48xo8fjwYNGmDv3r2IiYnBgQMH0LdvX5ZuIgtm0cW7yFiEsF/DEJMYgzy9bV3gb9MV6XDu5jn4L/HH2Rtny/W1MzIy0KdPHwwdOhQzZszA1q1b0bRp03Idg4gsg0qlwuTJk3H48GEkJCTA29sbmzdvLtcxDEYDBq4fiO+PfG/T1+Tzt84jYEkATl0/JXWc+3D9NpF1s9jibTAaELYmDFvSttjsBf42g2jAtbxrePZ/z5bLLItOp8PUqVPRsmVL+Pj4IDk5GT169OBabqJKwMPDA2vXrkV0dDQiIyPRrVs3pKWlPfCxY8aMweLFi0v0ukbRiDfXv4n1qeuh1WvLM7LFMYpGXM+/juf+9xxOXz8tdRwYDAasX78e7dq1Q+/eveHv74+zZ89i7ty5PPSGyMpY5BpvURQx6LdBWJuy1uZL951kggy1HGvhyLAjcHMu2xZhmzdvxpgxY+Dn54c5c+bAw8OjfEMSkdUoLCzE/PnzMXPmTAwfPhwTJ06Eo6MjANPMaXBwMGQyGZKSkh55rRBFEUM3DcXK4ysr3TW5hqoGjgw/gqeqPGX28bl+m8j2WOSM95f7v8S6lHWV6gIPmGZZsvKy0CWmC3RFpVufmZaWhm7duiEyMhLR0dFYt24dSzdRJadUKhEZGYnExESkp6fDy8sLq1evhsFgwFtvvQWdToeCggK8+eabeNQcTNTBqEpXuoH/Zr47/9gZ+Xrz3WPE9dtEtsviivfWtK34bPdnNv9W5sPojXqcvn4ag34b9MgfhLdptVpMmjQJgYGB6NChAxITE9GlSxczJCUia+Hu7o6YmBj89NNPmDZtGry9vXH2rOmeEoPBgH/++Qc//PDDA5+748wOTNwxsdKV7tsMogHnbp7D62tfL9E1+Ulw/TaR7bOopSYnrp2A/2J/5OpzpY4iObVCjU87fIpxz4974OdFUcSaNWsQGRmJ4OBgfPnll3B3dzdzSiKyNteuXUO9evXu2/XE2dkZp06dQq1atYo/dvr6abT8riVyCnPMHdPiqBVqfNj2Q3wS/Em5vi733yaqXCymeBcZi+Ab7YvUa6kQYRGRJKeSq7D/7f1oUafFXR9PSkrCqFGjkJWVhQULFiA4OFiagERkdYYPH44VK1agoKDgro8rFAp07doVGzZsAGC6wb3V4lY4fuU4jKJRiqgWRyVXYe/gvfB393/i1+L6baLKyWKWmszYNwPp2eks3XfQFenQZ00f6A2mUzqzs7MRERGBkJAQ9OzZExqNhqWbiEosMTERP/74432lGzAdsrVt2zZs2rQJAPB1/Nc4ff00S/cd8ovy0WdNHxQU3f/9Kymu3yaq3CyieB+/chwz/ppRadcQPowIEZdyLuHT3Z9ixYoV8PT0RG5uLpKSkhAeHs6LNBGVyu3SrVarUaVKFVStWhXOzs5QqVQQBAE6nQ59+vTBgbQDlfpem0e5or2Cj3d9XOrncf02EQEWsNREFEW0+LYFjl05xtnuh7Az2qHZvmb4ftb3CAgIkDoOEVkpURSRl5eHrKwsXL9+HdevXy/+56ysLGRkZCD+QDwMQwxIuZnC2e6HUMlV+Hvo32heq/kjH8f120R0L8mnTDec2IDTN06zdD+KHfDU20+xdBPRExEEAY6OjnB0dET9+vUf+JgtaVvQd01flu5HKDAU4P0/3kfswNgHfp7rt4noYSRdalJkLMKYrWP4duZjGEQD9qTvwaGLh6SOQkQ2zCgaMWrrKF6TH8MoGhF/IR5xGXF3fZzrt4nocSQt3j8c/QHX869LGcFq5OvzEb41XOoYRGTDVh5biSu5V6SOYRXy9HkI3xoOURS5fpuISkyyNd6iKKLe3Hq4mHNRiuGtklqhxp639pTLVlZERHcSRRGN5jfCuZvnpI5iNVR2Kjxz4BncPHaT67eJqEQke+9r59mdyC7Ilmp4q6Qr0mFO/Bz83OtnqaMQkY2JOx+Hq9qrUsewKjqDDvYd7XH6t9NcSkJEJSLZUpOv9n+F3EKeUFkaRtGI9anrcSP/htRRiMjGfBX3Fbd0LSURIo7lH8P1Ai6ZJKKSkaR4X8q5hD3n9kgxtNWTCTIsTVgqdQwisiFXtFew7fQ27i5VBgIELNEskToGEVkJSYr3upR1EARBiqGtXp4+D8v+WSZ1DCKyIRtSN0Ams4jz1KxOflE+lh9dLnUMIrISklxpYxJjkF+UL8XQNuHU9VO4nHtZ6hhEZCNijsVwmckTOJ99HhduXZA6BhFZAbMX71sFt5Dwb4K5h7UpCjsFfk/7XeoYRGQDtIVaHLxwUOoYVs1OZodNJzZJHYOIrIDZi/e209tgb2dv7mFtSm5hLn469pPUMYjIBuw4u4PX5CeUp8/jNZmISsTsxXv3ud3czaQcHLp4CBJtwU5ENmRv+l7k6nlNflJHMo/wmkxEj2X24v1Xxl+8c74c6I16rikkoie2N30vjKJR6hhWTxAEnLlxRuoYRGThzFq8jaIRqddSzTmkzVLaKaHJ1Egdg4ismCiKSLqaJHUMmyAX5LwmE9FjmbV4p2WlQS7j6V7lIbcwF39f/FvqGERkxdKz06WOYDNyCnN4kyoRPZZZi/eZG2dYvMuJUTQi5WqK1DGIyIqduXEGCplC6hg2QYSI5KvJUscgIgtn1uKdmZuJImMRij4pQsLwhOI/Dao2MFuGs2POooaqBgDcl2NC0IT7Ht++QXts6l++20S1b9AegU8FFv99eOvhGOA7oNSvc/7W+Ud+Pjc3FzExMSgqKir1axOR7cvMyYRBNFTY69d2rI2VvVbi1KhTODz0MH5//Xc8U/2Zcnv9e6+lUruQw/tuiOjRzDr9nJmTifyifOQX5aPldy1L/Xw7wa5cf0iUNceT6uDRAbmFuYi/EA8A+E7zXZle57L2wYfo5ObmYv78+Zg5cyZyc3MRGBiIxo0blzkvEdmmzNxMFBQVVNjrrw9bjxVHV6D/2v4AAN/avqjtVBtp19PK5fXvvZbeqbx/XpTEFe0Vs45HRNbHrMX77M2zD7173q+2H74N/RZqhRqnr5/GkI1DcFN3E7sG7cI///6DtvXbYuXxlXilyStI+DcB7eq3g6PCEQN/G4iP2n4En1o+WJW0Cp/s+gSA6YJfr0o9OMgdEHUwCkuOLClxzhcbv4h5L81Dnj4Pf2X8VfzxKe2nILcwF7PjZwMAjr17DKE/hyI9Ox0DfAcg8vlIiKKIxMuJGPjbQIQ2CcXH7T6G0k6JrPwsvLHuDajkKozwHwGD0YA3fd/EqK2j0Klhp+LXfdT34eDFgwjxCIGLgwve3vg2NJfuvpHnzsJtMBiQl5cHJyen0v5rIqJK4tzNc9Ab9RXy2iEeIdAb9XdNLCReTgQAfNn5S3R9uitEUcTUfVOxOmk12jdoj8jnI/HKylcAAAu6LsDhS4ex4ugKnB1zFiuOrsArTV6BQqZAnzV9oCvS3Xctfbvl29AV6dCyTkvEnY/DK01ewfNLn8e1vGsQIODkqJMI/D4Q1/KuVcjXfCP/BkRRhCAIFfL6RGT9zFq8r+dfBwCo5CokDDedXnn2xln0XN0TP7z2A0ZtHYW96XvxWYfPMKX9FET8GQHAtINHwJIAAMArTV5BoaEQAUsCMPq50djQbwNaL26N6/nXcXr0acw9MBfX869jyIYhuKG7AQe5Aw4NPYS1KWuLx7/tzhwAMOOvGdiQugFLXlmCjj90xKnrp7Cq96rHfl3NXJvh4+CP8fz3zyMrPwvVHKoBMG2d2Ob7NgCAt1u+jfFB4xG5LRLfHv72rgLfqWGn4td61PdBLpPjuf89h65Pd8WU9lPwYsyLAB5cuImIHufea2J5al6r+QN3+ejp1RMtareA37d+qKmuiUNDD2Fv+t7Hvt61vGtovbg13vV/F5HPR2LopqH3XUvfbvk2nqryFJ5f+jyMohHZBdl4w+cNRB2MwguNXsDRf49WWOkGTNu8GkUj7AS7ChuDiKybWYt3kdG01vjeJR5V7KvAxcGl+OK74ugKrOmzpvjzq5LuLr8bT2wEABy7fAxJV5Lwb+6/AEw3CtWrUg/X869j9HOj8ZrnawCAelXq4Znqz+DgxbvvOH/QUhO/2n44e/MsTl0/BQCISYzBsNbDHvl1dWzYEWuS1yArPwsAcEN3AwDwVJWnsKr3Krg5uUFpp8TZm2cf+TqP+z6sS1kHANBkauDh4gGjaMSw4cPww4ofYDQaodffP3NVWFiIb7/9FjVq1Hjk2ERU+RzTHzP7mLffvTSKRlzRXsGec3sQ4B6AWwW3Hvm8O69/Pb16PvRxa5LXFL+zujRhKTb024Cog1EY0nIIlv2zrPy+kAeQCTIUGYtgJ2PxJqIHM2vxLuupXtpC7V1/v70m0SgaUWD4b32iUTRCLpOjfYP2eKHRCwj8PhD5RfnYNWgXHOQOZQ/+/4qMRZAJ/92P+rjXXNB1AebEz8Gmk5vQvkF7fNrh0yca//bXbTAaineHuX79OgwGw0O/t6Io4tatW7Cz4w8CIrqbXqkHKujSkHQ1Cb2b9S7x4x93fX3Q9e9B7vx5ceHWBVzOvYwQjxA8W/dZvLHujRLnKQsBAg+II6JHMmvxVtg9eNuqWwW3cCP/BtrWb4u/Mv7CAN8B2JO+p8zjVHWoihv5N5BflI+mNZqizVNtSvzc1Gup8HDxQKNqjXDmxhn0b96/+HPnbp5DaJNQAEDLOi3R0KUhAGDn2Z1YH7Yec+Ln4Hr+dVRzqIYbuhuoal8VF3MuAgAG+Q0qfp2cwhxUsa9y39il/T7IBBl+XfMrrl27hpkzZyI6OhpGoxE6na74Mfb29hg/fjxvriSi+2SszcCJ4ycq5LV3nt2J6R2nY2irocX32PjU8sFN3U2EeYdhxdEVqK6qjuAGwRi3fRwUdgo0c20GpZ0SKrkKnRp2uusemwd52LX0Tv9L+B9iesbgx8QfK/yETqNo5PaMRPRIZi3eVe2rPvRzg34bVHxT4ZkbZzB4w+Ayj/PHqT8wovUIJL+XjBNZJ3DgwoEHPu7eNd5/nPoDH+34CMM2DcPvr/+OPH0e9mXsg7O9MwBgbcpaDPQbiOPvHsfBiwdxMuskACD5ajKm7ZuGPW/tgcFoQMK/CRi8YTA+3fMp1vRZgxv5N7Dz3E40rGYq6ptObMKvfX9Fj6Y9MGrrqDJ/H5R2SgBAzZo18fXXX+PDDz98aAEnIrqXi4NLhb7+a6tew7yX5mFC0AToinQ4d/Mc3v/zfTgpnXB0xFGIoojxseOLd2hanbQax989jrM3zyLh34THvPqjr6W3bTyxEct6LMOyhIpdZgIAdjK7u2btiYjuJYhlXf9RBp/v+Ryf7f4MRlTsrENl4e7sjotjL9738TtnwHU6HU6ePMkZbyK6z5dxX2LSzknF99/YotZurTH3xbkIXh5c4WO5ql1xZRy3FCSihzPrr+Z1nevCQfHka63JpLZj7Qd+/PYMeHp6OubNm4d69eqZORkRWQM3J7dyuf/FUk0ImoC1fdfiox0fmWW8Wo61zDIOEVkvsy41cXN24/q3clSv6qMLdc2aNTFq1IPffiUicnd2t+mt72bFzcKsuFlmG69ulbpmG4uIrJNZZ7w9XDzMfpKYrZJBBs8anlLHICIr5uHiYdPLTMxJgACvml5SxyAiC2fW4t20RlMUGgrNOaTNcrJ3wrN1n5U6BhFZsUbVGlX4Th+VhZPSCc/VfU7qGERk4cxavO1kdnim+jPmHNJm6Q16tHZvLXUMIrJigsBZ2vJiFI28JhPRY5l936O29duae0ibJBNkaFC1gdQxiMjKtWvQDgIEqWNYPYNowNPVn5Y6BhFZOLMX7w4eHeCsdDb3sDanlVsrCAJ/WBLRkwluEMxrcjnwq+3HPbyJ6LHMfpV4sfGLdx3zTqWnVqjxhk/FHn1MRJVD50adoTPwsK0noZKr8LrP61LHICIrYPbiXU1VDc1rNTf3sDbFYDQUH11PRPQknO2d0dqNa5OfhAgR3Zt2lzoGEVkBSd4Xe8PnDZs+tKGiNajagPvFElG5edP3TagVaqljWK06jnXg4eIhdQwisgKSFO9eXr2kGNYmqOQqDGoxSOoYRGRDXvV8FUYjtxUsCwe5Awb4DZA6BhFZCUmKdwOXBmjzVBsphrZ6IkS80+odqWMQkQ1xd3ZHe4/2UsewWiP8R0gdgYishGS3YI9/fjyclE5SDW+VBAjo+nRX1HKsJXUUIrIx454fx2tyKQkQEOIRAndnd6mjEJGVkKx4v/j0i1xTWEpqhRqRz0dKHYOIbFDHhh1R1b6q1DGsiqPSEeOeHyd1DCKyIpIVb5kgwyfBn8BR4ShVBKvTuHpjBD4VKHUMIrJBgiDg0w6f8ppcCvWq1EMHjw5SxyAiKyLpbv/DWw+Hsz0PbigJtUKNb17+hofmEFGFeavFW6iuqi51DKvgqHDEwpcX8ppMRKUiafFW2Ckwp8scOCm4rvBRZIIMAe4BaFu/rdRRiMiGyWVyzHtpHme9H0OAAN/avujYsKPUUYjIykh+vm1Y8zC4ObtJHcOiCQYBuvU6pKSkSB2FiGxYXl4eElYmQPevDgI4k/swKrkKC7oukDoGEVkhyYu3TJBhZa+VUMlVUkexSCq5Cu899x5e7/Q6goODERkZiVu3bkkdi4hsiCiKWLduHZo1a4a0k2n4fcjvPOTsIVRyFQb6DURrd572SUSlJ3nxBoDW7q0R/mw41HLucnKvmuqa+LLLlxg9ejSOHz+O69evw8vLCzExMRBFUep4RGTlUlJS0KVLF0yePBnLli3DL7/8ghdbvIgPAj/gzlMP4OLggtkvzpY6BhFZKUG0kPZWUFQAr2+8cPbmWamjWAyVXIWdg3bed9jQgQMHEB4eDgcHByxcuBAtWrSQJiARWa1bt27hiy++wPLly/Hxxx/jvffeg0KhKP683qCH9yJvnLp+CiIs4seE5FRyFf5880+0a9BO6ihEZKUsYsYbAOzl9vit32+cYfl/jgpHfBD4wQNP+GzTpg0OHjyIQYMG4cUXX8TIkSNx/fp1CVISkbURRRExMTHw8vJCVlYWjh8/jjFjxtxVugHTze+8Jv9HrVBj5LMjWbqJ6IlYTPEGAN/avljx6opKf6F3kDsguEEwPgv57KGPsbOzw9ChQ5GSkgJBEODl5YXFixfDYDCYMSkRWZN//vkHwcHBmDdvHtauXYulS5eidu3aD318M9dm+LnXz5X+Hhx7O3sEPhWIWS/MkjoKEVk5iyreANC7WW+MeW5Mpd3Oyk6ww1NVnsKaPmsgEx7/r6d69epYuHAh/vzzT/zwww947rnncODAATMkJSJrcf36dYwcORIvvvgiBgwYgIMHD6JNm/vfTXuQ7k2748O2H1baCRGZIEMdpzpYF7auRNdkIqJHsciryNSOU9GpYadKd6EXIKCqQ1VsH7AdjsrS/eLRokUL7Nu3D++//z569eqFwYMH4/LlyxWUlIisgcFgwJIlS+Dl5QXAdCPlsGHDYGdnV6rX+ST4E7z8zMuV7gZ4AQKq2lfFjoE7UMW+itRxiMgGWGTxlgky/Nr3VwTVC6o0b3HeLt1xQ+Lg4eJRttcQBLz55ptISUlBzZo10bx5c0RFRUGv15dvWCKyeAcOHMBzzz2HFStW4M8//8Q333yD6tXLdiqlIAhY2WslQhqGVKoJEWd7Z+wbvA+NqzeWOgoR2QiL2dXkQQoNhei+sjv2pe9DXlGe1HEqjEyQoaq9qXR7uXqV2+umpKRg9OjRyMzMxIIFCxASElJur01Eluny5cv46KOP8Oeff2LWrFl44403yu1Yc71Bj16re2HH2R3I09vuNfn2TPfewXvhU9tH6jhEZEMscsb7NqWdEpv6b0Jo01CbnWWxt7NHHac6OPjOwXIt3QDg5eWFbdu24fPPP8fgwYPRr18/XLhwoVzHICLLUFRUhKioKDRv3hzVq1dHSkoK3nzzzXIr3YBpp5N1YevQy6uXzd6Ho5QpUcuxFuLfiWfpJqJyZ9HFGzBd6H/p9QumtJ9ic8tO1Ao1Wru3xvF3j+OZGs9UyBiCIKBnz55ITk5G06ZN0aJFC8yYMQMFBQUVMh4Rmd/u3bvRsmVLbN68GXv37sXXX3+NKlUqZk2yXCbHildXYGrHqTZ5TW7h1gJJ7yXBs6an1HGIyAZZ9FKTe/1x6g/0WdMH+fp8GETr3jZPrVDjLb+3ENU1CnKZ3GzjnjlzBhEREUhOTkZUVBRefvlls41NROXrwoULiIyMRHx8PObMmYOePXuW6wz348SeiUXPVT2RX5SPImOR2catCGqFGq/7vI5FLy+Cwk7x+CcQEZWBVRVvADh74yzCfg1D8tVkaPVaqeOUmtJOCZVche+7f49ezXpJlmPr1q0YM2YMPD09MXfuXDRuzJuHiKxFQUEB5s6di6+//hrvvfcePvzwQ6jV0izHS7+Zjv5r+yPxcqJ1XpNlSjgoHLA4dDHCmodJHYeIbJzFLzW5V8NqDXHgnQOY3mk61Ao17ITSbYslJbVCjZeefgmnRp+StHQDQNeuXXHs2DE8//zzeO655zB58mTk5dnuzVJEtmLr1q3w8fFBfHw8/v77b3z++eeSlW4AaODSAHFD4vB1l6/hqHC0qmuyo8IRnRp1QtqoNJZuIjILq5vxvtOZG2fw3u/vYW/6XuQX5Usd56EcFY6o6lAV37z8DV71fFXqOPe5cOECxo0bh/3790vydjURPZ41LBNLv5mOkVtGYufZndAV6SDCMn+8OCoc4WzvjAVdF6CXVy9e74jIbKy6eN928MJBhG8NR8rVFIt6q1OtUMPezh7TO03H2y3ftvh1g7t378aoUaNQp04dzJ8/v/jQDSKSTl5eHmbOnIlFixbhgw8+wNixY2Fvby91rEc6fOkwRm0dhWOXj1nWNVmuhtJOiamdpmJoq6FQ2imljkRElYxNFG8AEEURO87uwLS903DgwgEYYUShoVCSLE5KJ1Sxr4Jxz4/DsNbDrGorxKKiIixatAhffPEFBg0ahMmTJ1fY7ghE9HCi+H/t3Xt0VOW5x/HfkAvJhIsELMYFXkDFYGgjYBNBUdRKoWJ7wNJiaDFlyakQIGK8sAg5LmIrCAqRxNMDpxCOIB4IUCsVkBZBqgmUlgAhQWyhXBTigQETMsmQSeb88TYG5ZpJMnsu309XFsmePXuexLWmvzx59vt6tHbtWk2dOlXJycmaM2eOunfvbnVZTbL50Gb9etuv9dHRj1TvsfY9uX1ke029e6qe6v9Uk3cGBoCWEjTB+3z/PPNP5e7I1cK/LpQkOWudrb4KSvvI9nLVuTT4psF6dsCzeuDmBwL6z5etuQkHgMsLts2vjnx5RHk78vSbv/5GHo/Hp+/J995wr54f+Lwe7PGg2tgC7rYmAEEmKIN3A3e9W4VHC7WmbI1Wla6So9qh8DbhOnvubLNnD+3hdoW1CVOdp04P3fyQRvcZre/f8n1dE3VNyxTvJ4qKipSWlqaoqCjl5uYqMTHR6pKAoFVRUaHs7Gzl5+crMzNTEyZMUESEf4+oNUVdfZ2KjhVpzf41WrlvpU45TymiTYTO1p5Vvae+Wde2R9gVbgtXbX2tHrz5QY3uM1pDbxmqTtGdWqh6AGi+oA7e33To9CHt/Hynio4V6cMjH2r/yf1y1joVHR6t8Dbh8sgjj8cjjzyyNfzPZlO9p/6rG4Vu7Hijkrsl654b7lG/uH5KvC7R72e3m6uurk6LFy9WZmamHnvsMWVnZys2NtbqsoCg4fF4tHz5cj3//PMaMmSIXn75ZXXt2tXqslrd4TOH9ZfP/6Ltn23Xh//8UGUnzX06V/Oe7Kpzqd5Trxs63ND4nny9eU9mdhuAvwqp4H0xNe4anTh7Qscrj6u8qlw17hq5690Ks4UpvE24Ots7K65dnK5vf706tO0Q0uMWDodDWVlZWrVqlbKzszVu3DiFhQXO0mGAPyouLtakSZNUXV2t3NxcJScnW12SpVxul3lPPntcJ86ekMvtUm197QXvyXHt49SxbceQfk8GEHhCPnij6YqLi5WWlqaamhqCAuAlh8OhGTNmqKCggF9kASBEcKcJmiwxMVHbtm1Tenq6Ro4cqdTUVJWXl1tdFhAQ6urqtGjRoq+W6ywrK9P48eMJ3QAQAgje8IrNZtOYMWNUVlamLl26KCEhQTk5OaqtrbW6NMBvFRUVKSkpSUuXLtXGjRuVl5fH/RIAEEIYNUGLCLblz4CWxPKcAACJjjdaSHx8vN5//33NnDlTqamp+ulPf6pjx45ZXRZgKbfbrZycHCUkJCg2NlZlZWUaM2YMoRsAQhTBGy3GZrNpxIgRKi0tVa9evZSYmKiXX35ZLpfL6tIAn9uyZYvuvPNOrVu3Th9++KHmzp3LLrAAEOIYNUGrOXjwoJ5++mmVlpYqJydHw4YNs7okoNUdO3ZMGRkZKiws1GuvvaYRI0bQ4QYASKLjjVbUo0cPvfPOO3r99deVnp6uRx99VP/4xz+sLgtoFS6XS7NmzVJiYqJuu+02lZWVaeTIkYRuAMBXCN5odUOHDtXevXs1YMAAJSUlKSsrS06n0+qygBazfv169enTR4WFhdqxY4dmzpwpu91udVkAAD/DqAl86tixY3r22WdVWFioV199lT/DI6AxTgUAaAo63vCpbt26acWKFcrPz9eLL76ohx9+WGVlZVaXBTSJ0+lUVlaWvvvd7yo5OVklJSWEbgDAFRG8YYn7779fu3bt0vDhwzVo0CBlZGSooqLC6rKAy/J4PFqzZo169+6tAwcOaNeuXZo2bZratm1rdWkAgABA8IZlwsPDNXnyZJWUlMjhcCg+Pl7Lli0T00/wR2VlZXr44YeVlZWlJUuW6O2331b37t2tLgsAEECY8YbfKCoqUlpamqKiopSbm6vExESrSwJUUVGh7Oxs5efnKzMzUxMmTFBERITVZQEAAhAdb/iN5ORkbd++XWPHjtWQIUM0ceJEORwOq8tCiPJ4PFq2bJni4+N16tQplZSUaMqUKYRuAIDXCN7wK2FhYXryySdVVlYmm82m+Ph4LVy4UHV1dVaXhhBSXFysQYMGaf78+Vq9erUWL16srl27Wl0WACDAMWoCv1ZcXKy0tDTV1NQoNzdXycnJVpeEIOZwODRjxgwVFBQoOztb48aNU1hYmNVlAQCCBB1v+LXExERt27ZN6enpGjlypFJTU1VeXm51WQgydXV1WrRokeLj4yWZGynHjx9P6AYAtCiCN/yezWbTmDFjVFZWpi5duighIUE5OTmqra21ujQEgaKiIiUlJWnp0qXauHGj8vLyFBsba3VZAIAgxKgJAk5ZWZkmT56s48ePa8GCBRo8eLDVJSEAlZeXa9q0adq4caNmz56tlJQUdlEFALQqgjcCksfj0dq1azV16lQlJydr7ty56tatm9VlWaK2VvrsM+nzz6Xjx82/Z85I585JHo8UESFFR0txcebj+uulbt2kDh2srtwabrdbeXl5eumllzR27FhlZWWpQ6j+MAAAPkXwRkBzOp2aPXu28vLy9Mwzz2jq1KlBv4vggQPStm3SRx9JH38sHTwoRUZK4eEmaLtcjaG7QXi4FBUlhYVJ9fVSTY3UqZPUt690331ScrI0YIC5TjDbsmWLJk2apOuuu06vv/76VzPdAAD4AsEbQeHgwYN6+umnVVpaqpycHA0bNszqklpMXZ1UWCitXi2tWiU5HFKbNlJVVctcPzLShPLaWunBB6XRo6WhQ00wDxbHjh1TRkaGCgsL9dprr2nEiBGMlQAAfI7gjaCyfv16TZkyRbfffrvmzZunnj17Wl2S1774Qlq0SJo/33SxnU4Twltb+/YmhA8fLmVkSHfdJQVqRnW5XJo3b57mzp2rCRMm6IUXXpDdbre6LABAiGJVEwSVoUOHau/evRowYICSkpKUlZUlp9NpdVlNsm+fNGKEdOON0ksvSSdPSpWVvgndknmtmhrTYR88WOrVS1q+3Hev31LWr1+vPn36qLCwUDt27NDMmTMJ3QAAS9HxRtAKtPGCw4el556Tfv97M6NdX291RY1iYqRvfUtasEAaNsy/O+DBPHYEAAhsBG8EvQ8++ECTJk1SXFycX95Q53RKL7xgxkrcbvPhr2JipFtvlf7nf6Q+fayu5uucTqdmzZqlvLw8ZWRkhMSNtgCAwMKoCYLe4MGDtWvXLj3yyCMaNGiQMjIyVFFRYXVZkszqJLfcIv33f5vxDn8O3ZK5oXP3bikpSXrxRTMLbjWPx6M1a9aod+/e+uSTT1RcXKxp06YRugEAfoeON0KKv2yaUl0tPf206RxXV/v85VuE3S51725mwe+4w5oa2EwJABBICN4ISUVFRUpLS1NUVJRyc3OVmJjos9f+7DPp4YelQ4cCN3Q3sNnM5jxvvmluCPWViooKZWdnKz8/X9OnT9fEiRMVERHhuwIAAPACoyYIScnJydq+fbt+/vOfa8iQIZo4caIcDkerv+727WY2+sCBwA/dktmkx+mUfvYzKTOz9W8I9Xg8WrZsmeLj43Xy5EmVlJQoPT2d0A0ACAgEb4SssLAwjR8/XmVlZZKk+Ph4LVy4UHWttG7eypXSAw9Ip0/7/yx3Uzmd0rx50g9/aFZkaQ3FxcUaNGiQ5s2bp4KCAi1ZskRdu3ZtnRcDAKAVMGoC/EtxcbHS0tJUU1Oj3NxcJScnX/Lc2traJnVZly6VnnoqOLrclxMdbbaff+89sxvm1Wj4RScsLOyijzscDs2YMUMFBQXKzs7WuHHjLnkuAAD+jI438C+JiYnatm2b0tPTNWLECKWmpqq8vPyC87Zu3aprr71WR48evarrvvlmaIRuyXyPRUVmre+r7Xw/+uijSklJueB4XV2dFi1apPj4eHk8HpWWlmr8+PGEbgBAwCJ4A+ex2WwaM2aM9u/fr86dOyshIUE5OTmq/de6eW63W0888YQqKys1duxYXekPRu++K/37v4dG6G7QEL5HjrzyzPfq1au1ZcsWvfvuu/r444+/Ol5UVKSkpCTl5+drw4YNeuONN9S5c+dWrhwAgNbFqAlwGd9crq64uFgzZsxQVVWV7Ha7Fi1apMcff/yiz923z6x3XVXl46L9REyMlJ5utr2/mNOnT6tHjx46c+aMJOnWW2/Vli1blJmZqQ0bNmj27NkaM2aMX+82CgBAUxC8gSto2KBlypQpOnHixNduvuzQoYMOHjx4QTf21CkpIUEqLzcrf4Sq6Ghp2bKLLzWYkpKi1atXy+VySZIiIyMVERGhX/7yl8rKylKHDh18XC0AAK2L4A1cpVGjRmn16tWqP29+IjIyUsOHD1dBQcFXx+rqpHvukf72t9Zb4SOQ2O1mGcWEhMZjmzdv1vDhw+V0Or92bkxMjA4fPsxYCQAgKDHjDVyF7du3a926dV8L3ZJ07tw5rV+/XuvXr//q2Pz50t69hO4G1dXSY481bi/vdDqVkpJyQeiWzAx9RkaGjysEAMA36HgDV1BfX6877rhD+/fvv+Q5sbGxOnz4sI4fb6fvfCe0bqa8Gna79Oyz0osvShMnTtTChQvlvsRi5hERESoqKlLfvn19WyQAAK0s3OoCAH/35ZdfKjIyUtdee60qKyvlcrkUGRmpyMhI2Ww2uVwuORwO/ehHI3Xq1Eb9a2QZ53E6pVdekeLiPtYbb7yhsLAwtW/fXjabTW63Wy6XSzabTe3atVOHDh104MABgjcAIOjQ8QaayO126/Tp03I4HHI4HDp16pQ+/fRT7d7dTwUFg0J2FZMrsdmk22+v0Q9+kKXk5CR17txZsbGxio2NVefOnRUdHW11iQAAtCqCN9ACqqul7t3Naia4tJgY6e23pUcesboSAAB8j5srgRawYAFz3VejqkqaPNms/AIAQKgheAPNVFEhZWebOWZc2RdfSCtWWF0FAAC+R/AGmmnp0itvjY5GVVVmdROG3AAAoYYZb6AZPB7pxhulo0etriSwxMRIf/yjlJxsdSUAAPgOHW+gGbZulU6ftrqKwFNdLb36qtVVAADgW3S8gWZ49FFp3TrGJrwRFSV9/rnUqZPVlQAA4Bt0vAEvuVzSpk2Ebm9FREjvvWd1FQAA+A7BG/DSli1SZKTVVQSuykrprbesrgIAAN8heANeWrnShEd474MPpHPnrK4CAADfIHgDXvr97xkzaa6ICOmjj6yuAgAA3yB4A1744gu63S2hpkbavt3qKgAA8A2CN+CFv/5VatvW6ioC37lzZlYeAIBQQPAGvLBjB1vEt5S//c3qCgAA8A2CN+CFP/9ZcrutriI4nDljPgAACHYEb8ALR45YXUHwiIqSjh2zugoAAFofwRvwwv/9n/m3a1dpxQrp73+Xdu6U/vAH6dZbfV/P2LFSXFzTnnPjjdLevebz6Ghp2TJpzx5zbNs2KSbm8s8/dEjq3Nm7es/Xpo10/HjzrwMAgL8Lt7oAINDU10sVFebztWulpUul0aPN19/+tgnjn37qu3ratJGeeEIqKfE+wE6ZIpWXm/ol6bbbpNraFitRkqmzvv7C4243wRsAEBroeANNdOqUFB4uDR5swul//VfjY3v2mPnvV14xneM9e6RRo8xj991nNoxZtUoqKzMdZkkaMsRsxtPgvvukd981n3/ve9LHH5tVVFaubOxCHzokzZpljo8eLfXvLy1fLu3aZUY3+vY1q4Xs3Clt2CBdd515Xt++UnGx+Zg4sfE14+Kkzz5r/PrAgcaNbdauNdcpKZGefPLiP5NLnVNZKc2da15v+nRzXoOHHpLWrDFLChK8AQChgOANNJHTaYJ3QoIJvt80YoSUmCh95zsmXM6Z0xh877xTSk+XeveWevSQBg6U/vhHKSlJstvNOT/5ifT222aMIzPTXKNfPxNsp05tfJ1Tp8zx5cvNYykp5vput7RggfTYYyaQL14s/epX5jlLlkiTJpn6zrd4sfT88ybkZ2dLt9zS+NgvfmGu07+/NHmyFBt74fd8qXPatTPrdCcmmuvefrvUpYt5LDXVvG5dnVRd3bT/BgAABCKCN9BEbrdks1368XvuMXPf9fVmo52tW6W77jKP7dhhOssej+kC33STCZ4bNkjDh0thYdIPfiC9846UnGwC+kcfmU722LFmLrvB//7vxV+/Vy/zS8GmTeZ5mZlSt25Sx47SNdeY+W1JevPNxufs3m1+EZgzx4Tmv/zFhGTJBOniYqmoSOre/eIz7Jc6x+2WVq9uPO/NN6UxY0wtd98trV9vjrtcl/55AgAQLJjxBpqoIXTv22e6yk1xfsCsqzOdc8l0uNPSJIfDdK/PnjWvs2mT9PjjF79WVdWl69u3Txow4OvHO3a8fG1VVWYUZO1a80vDsGFmXv2hh0xIrq42ozJRUV9/3n33Xfqcmpqvz3UvWWLGaGpqzMhNXZ053oYWAAAgBPB/d0ATRUSYMLl5s9m98vyZ5j59zJrUP/mJCZNdukiDBplO9+Vs3Wrmr5980oRwyXSPBw6UevY0X9vtl14xpbJSat/efP7JJ9K115qOuWTCfe/e0pdfmtoGDjTHU1Ianz9ggOmGN3x/vXtLhw+bsH76tAnUvXo1XvN8V3NOg+PHpc8/N134JUsaj0dGXu6nAwBAcCB4A010zTWNNx7+27+Zbu/f/25uLHz5Zemtt8xNlbt3m3D+3HNmxZDLqa+X1q2Thg41/0rSyZNmtZIVK8y1Cgsbxz++KT9f+s1vzGhJWJjpxM+e3XgjZUP3OzVVyssz550/LtOzpwn/e/aYx3buNCMiGzaY4F5aam7mLCq68LWv5pzzLV8uHT0q7d9vvm7bVurU6fLPAQAgGNg8Ho/H6iKAQNO2bWP4RtMsWGDC/eLF5uv27aXf/lb68Y+trQsAgNZGxxvwwsVW9sCV7dxp1gpvWEpRMiM5Td38BwCAQMTNlYAXunaVTpywuorA07//hcfcboI3ACA00PEGvBAfb3UFwePcObMEIQAAwY7gDXjh3nul6GirqwgON93EqiYAgNBA8Aa80K+fWXYPzffN9cYBAAhWBG/AC9/+ttk6Hs1jtzeuKw4AQLAjeANeiI42m8Wg+e691+oKAADwDYI34KXHHzfrecN7HTvyCwwAIHQQvAEv/ehHZpdIeKdhh83zd9AEACCYEbwBL8XHm10X4R273QRvAABCBcEb8JLNJj3xBEvheSsykhsrAQChheANNMPEiYxKeCMqSpoyhVEdAEBoIXgDzdC9O6tyeMPjkcaPt7oKAAB8i+ANNNNzz0nt2lldReBo00YaMkTq2tXqSgAA8C2bx+PxWF0EEMg8HikhQSottbqSwBAdLW3fLvXpY3UlAAD4Fh1voJlsNik316zSgcsLD5eGDSN0AwBCEx1voIUMHCgVFpoOOC4uKsr8ZeDmm62uBAAA36PjDbSQvDwTLHFx0dHSL35B6AYAhC6CN9BCEhOlp55i5ORSOnaUXnnF6ioAALAOoyZAC3K5pF69pMOHra7Ev9jt0h/+IN1/v9WVAABgHTreQAtq21ZatcqMVcCIipJSUgjdAAAQvIEWdtddUlaWFBNjdSXWCw+XbrpJmj/f6koAALAeoyZAK/B4pFGjzHhFdbXV1VinUydpzx6pWzerKwEAwHoEb6CV1NRI/ftLn3wiud1WV+N70dHSn/4k3X231ZUAAOAfGDUBWklUlLRpk/Stb0lhYVZX41vR0dJvf0voBgDgfARvoBXFxZlNdbp0CZ3wHR1tdvIcPdrqSgAA8C8Eb6CV3XCDtGOH1LWrudkwmEVHS//5n2ajHAAA8HXMeAM+cvy49L3vSQcPBucNl3a79NZb0g9/aHUlAAD4J4I34EM1NdLPfia9957kdFpdTcuIjDSrl2zaJPXpY3U1AAD4L0ZNAB+KipJWrjTrfAfDJjsxMVJiolRSQugGAOBK6HgDFtmxQ/rxj6WTJwOv+92mjdml8z/+Q8rICJ0bRwEAaA6CN2Chmhpp+nRzQ2JNjdl4x9/FxEg9e5rOfa9eVlcDAEDgIHgDfmDXLiktTdq9W6qqsrqai7PbTZd71ixp3Di63AAANBXBG/AjmzdLkyZJR45IZ89aXY1ht5vRkunTpSlTgmM2HQAAKxC8AT/j8Ujvvy/NmSP9+c/m63PnfF9Hu3ZSx45mhjs11XwOAAC8R/AG/NiRI1JenpSfbzrgdXWSy9U6r2WzSe3bm5D/wAPSM89Igweb4wAAoPkI3kAA8Hik0lLpd78zm9QcOGBGQGprvd+MJzzcXMPlMt3t4cOlUaNM2I6KatHyAQCACN5AQKqulvbskXbulLZtM6H8iy8kh8M8HhnZ2Kn2eEyn/Nw5qUMHqUsXs439vfdKd90l9esnXXeddd8LAAChguANBBGPR6qslE6fltxuqb5eiogwN0R26cJKJAAAWIngDQAAAPgAW8YDAAAAPkDwBgAAAHyA4A0AAAD4AMEbAAAA8AGCNwAAAOADBG8AAADABwjeAAAAgA8QvAEAAAAfIHgDAAAAPkDwBgAAAHyA4A0AAAD4AMEbAAAA8AGCNwAAAOAD/w9HKFEj7HjpbwAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 720x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Function to extract the Markov Blanket of a Node from the Graph\n",
    "def get_mb(graph, node):\n",
    "    mb = set()\n",
    "    parents = [i for i in graph.predecessors(node)]\n",
    "    mb.update(parents)\n",
    "    sons = [i for i in graph.successors(node)]\n",
    "    mb.update(sons)\n",
    "    sons_parents=[]\n",
    "    for s in sons:\n",
    "        sons_parents.extend([i for i in graph.predecessors(s) if i != node])\n",
    "\n",
    "    mb.update(sons_parents)\n",
    "    return mb\n",
    "\n",
    "#Markov Blanket Plotting Function\n",
    "def plot_mb(G, mb, node):\n",
    "    pos={'Hobby':(0.5,10),\n",
    "     'JobSatisfaction':(2,7),\n",
    "     'OpenSource':(0.5,7),\n",
    "     'FormalEducation':(0.5,3),\n",
    "     'Country':(2,3),\n",
    "     'ConvertedSalary':(1.25,1),\n",
    "     'UndergradMajor':(3,5)\n",
    "    }\n",
    "    plt.figure(figsize=(10,8))\n",
    "    color_map=[]\n",
    "    for n in G:\n",
    "        if n in mb:\n",
    "            color_map.append('green')\n",
    "        elif n == node:\n",
    "            color_map.append('red')\n",
    "        else: \n",
    "            color_map.append('blue')  \n",
    "    nx.draw(G, arrows=True,node_color=color_map, with_labels=True, node_size=7000, arrowsize=20, pos=pos, font_size=10, font_color='white')\n",
    "\n",
    "mb=get_mb(G, 'OpenSource')\n",
    "plot_mb(G, mb, 'OpenSource')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## PGMPY"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Function that computes the Graph Edges using the Upper triangular part of the $chi^2$ matrix as an adjacency Table."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('Hobby', 'OpenSource'),\n",
       " ('OpenSource', 'Country'),\n",
       " ('OpenSource', 'FormalEducation'),\n",
       " ('OpenSource', 'JobSatisfaction'),\n",
       " ('Country', 'FormalEducation'),\n",
       " ('Country', 'UndergradMajor'),\n",
       " ('Country', 'JobSatisfaction'),\n",
       " ('Country', 'ConvertedSalary'),\n",
       " ('FormalEducation', 'JobSatisfaction'),\n",
       " ('FormalEducation', 'ConvertedSalary'),\n",
       " ('UndergradMajor', 'JobSatisfaction')]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def getEdges(mat,names=[]):\n",
    "    result=[]\n",
    "    l,_=mat.shape\n",
    "    for i in range(l): \n",
    "        for j in range(i+1,l):\n",
    "            if mat[i,j]==0:\n",
    "                if len(names)>0:\n",
    "                    result.append((names[i],names[j]))\n",
    "                else: result.append((i,j))\n",
    "    return result    \n",
    "edges=getEdges(chi2Mat,names=data.columns)\n",
    "edges"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+------------+----------+\n",
      "| Hobby(No)  | 0.199923 |\n",
      "+------------+----------+\n",
      "| Hobby(Yes) | 0.800077 |\n",
      "+------------+----------+\n",
      "+-----------------+--------------------+---------------------+\n",
      "| Hobby           | Hobby(No)          | Hobby(Yes)          |\n",
      "+-----------------+--------------------+---------------------+\n",
      "| OpenSource(No)  | 0.7966101694915254 | 0.49800223749400674 |\n",
      "+-----------------+--------------------+---------------------+\n",
      "| OpenSource(Yes) | 0.2033898305084746 | 0.5019977625059933  |\n",
      "+-----------------+--------------------+---------------------+\n",
      "+-------------------------+---------------------+---------------------+\n",
      "| OpenSource              | OpenSource(No)      | OpenSource(Yes)     |\n",
      "+-------------------------+---------------------+---------------------+\n",
      "| Country(India)          | 0.20440215522182736 | 0.24486845909222318 |\n",
      "+-------------------------+---------------------+---------------------+\n",
      "| Country(United Kingdom) | 0.17872291642783447 | 0.16536571263370917 |\n",
      "+-------------------------+---------------------+---------------------+\n",
      "| Country(United States)  | 0.6168749283503382  | 0.5897658282740676  |\n",
      "+-------------------------+---------------------+---------------------+\n",
      "+---------------------------+-----+------------------------+\n",
      "| Country                   | ... | Country(United States) |\n",
      "+---------------------------+-----+------------------------+\n",
      "| OpenSource                | ... | OpenSource(Yes)        |\n",
      "+---------------------------+-----+------------------------+\n",
      "| FormalEducation(Bachelor) | ... | 0.7134803921568628     |\n",
      "+---------------------------+-----+------------------------+\n",
      "| FormalEducation(Master)   | ... | 0.24215686274509804    |\n",
      "+---------------------------+-----+------------------------+\n",
      "| FormalEducation(Ph.D)     | ... | 0.04436274509803922    |\n",
      "+---------------------------+-----+------------------------+\n",
      "+--------------------+-----+------------------------+\n",
      "| Country            | ... | Country(United States) |\n",
      "+--------------------+-----+------------------------+\n",
      "| FormalEducation    | ... | FormalEducation(Ph.D)  |\n",
      "+--------------------+-----+------------------------+\n",
      "| OpenSource         | ... | OpenSource(Yes)        |\n",
      "+--------------------+-----+------------------------+\n",
      "| UndergradMajor     | ... | UndergradMajor(STEM)   |\n",
      "+--------------------+-----+------------------------+\n",
      "| JobSatisfaction(0) | ... | 0.05806451612903226    |\n",
      "+--------------------+-----+------------------------+\n",
      "| JobSatisfaction(1) | ... | 0.05806451612903226    |\n",
      "+--------------------+-----+------------------------+\n",
      "| JobSatisfaction(2) | ... | 0.08387096774193549    |\n",
      "+--------------------+-----+------------------------+\n",
      "| JobSatisfaction(3) | ... | 0.025806451612903226   |\n",
      "+--------------------+-----+------------------------+\n",
      "| JobSatisfaction(4) | ... | 0.08387096774193549    |\n",
      "+--------------------+-----+------------------------+\n",
      "| JobSatisfaction(5) | ... | 0.3741935483870968     |\n",
      "+--------------------+-----+------------------------+\n",
      "| JobSatisfaction(6) | ... | 0.3161290322580645     |\n",
      "+--------------------+-----+------------------------+\n",
      "+--------------------------+-----+------------------------+\n",
      "| Country                  | ... | Country(United States) |\n",
      "+--------------------------+-----+------------------------+\n",
      "| UndergradMajor(NOT_STEM) | ... | 0.15759433463693057    |\n",
      "+--------------------------+-----+------------------------+\n",
      "| UndergradMajor(STEM)     | ... | 0.8424056653630695     |\n",
      "+--------------------------+-----+------------------------+\n",
      "+-----+------------------------+\n",
      "| ... | Country(United States) |\n",
      "+-----+------------------------+\n",
      "| ... | FormalEducation(Ph.D)  |\n",
      "+-----+------------------------+\n",
      "| ... | 0.9244712990936556     |\n",
      "+-----+------------------------+\n",
      "| ... | 0.027190332326283987   |\n",
      "+-----+------------------------+\n",
      "| ... | 0.04833836858006042    |\n",
      "+-----+------------------------+\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from pgmpy.models import BayesianNetwork\n",
    "from pgmpy.estimators import ParameterEstimator, MaximumLikelihoodEstimator\n",
    "\n",
    "model= BayesianNetwork(edges)\n",
    "# pe = ParameterEstimator(model, data)\n",
    "model.fit(data, estimator=MaximumLikelihoodEstimator)\n",
    "for cpd in model.get_cpds():\n",
    "    print(cpd)\n",
    "\n",
    "model.get_independencies()\n",
    "\n",
    "plot_mb(G, model.get_markov_blanket('JobSatisfaction'), 'JobSatisfaction')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Markov Blanket Notes\n",
    "\"What the Markov Blanket says, is that all information about a random variable in a Bayesian network is contained within this set of nodes (parents, children, and parents of children). That is, if we observe ALL OF THESE variables, then our node is independent of all other nodes within the network.\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_mb(G, model.get_markov_blanket('ConvertedSalary'), 'ConvertedSalary')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As we can see asking the BN the probability of having a certain Converted Salary given its Markov Blanket is the same as adding evidence to other nodes that aren't part of it.\n",
    "This means that Converted Salary is independent to other nodes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Finding Elimination Order: : : 0it [00:00, ?it/s]\n",
      "0it [00:00, ?it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+------------------------------------+------------------------+\n",
      "| ConvertedSalary                    |   phi(ConvertedSalary) |\n",
      "+====================================+========================+\n",
      "| ConvertedSalary(0-250.000)         |                 0.9836 |\n",
      "+------------------------------------+------------------------+\n",
      "| ConvertedSalary(1.000.000+)        |                 0.0008 |\n",
      "+------------------------------------+------------------------+\n",
      "| ConvertedSalary(250.000-1.000.000) |                 0.0156 |\n",
      "+------------------------------------+------------------------+\n",
      "P(ConvertedSalary | Country=India, FormalEducation=Bachelor)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Finding Elimination Order: : : 0it [00:00, ?it/s]\n",
      "0it [00:00, ?it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+------------------------------------+------------------------+\n",
      "| ConvertedSalary                    |   phi(ConvertedSalary) |\n",
      "+====================================+========================+\n",
      "| ConvertedSalary(0-250.000)         |                 0.9836 |\n",
      "+------------------------------------+------------------------+\n",
      "| ConvertedSalary(1.000.000+)        |                 0.0008 |\n",
      "+------------------------------------+------------------------+\n",
      "| ConvertedSalary(250.000-1.000.000) |                 0.0156 |\n",
      "+------------------------------------+------------------------+\n",
      "P(ConvertedSalary | Country=India, FormalEducation=Bachelor, OpenSource=Yes)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "from pgmpy.inference import VariableElimination\n",
    "inference = VariableElimination(model)\n",
    "\n",
    "pSalary1 = inference.query(['ConvertedSalary'],{'Country':'India','FormalEducation':'Bachelor'})\n",
    "print(pSalary1)\n",
    "print(\"P(ConvertedSalary | Country=India, FormalEducation=Bachelor)\")\n",
    "pSalary2 = inference.query(['ConvertedSalary'],{'Country':'India','FormalEducation':'Bachelor','OpenSource':'Yes'})\n",
    "print(pSalary2)\n",
    "print(\"P(ConvertedSalary | Country=India, FormalEducation=Bachelor, OpenSource=Yes)\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Now switch to sampling methods\n",
    "from pgmpy.factors.discrete import State\n",
    "from pgmpy.sampling import BayesianModelSampling\n",
    "\n",
    "def run_experiment(model,sample_size,evidence,p_exact):\n",
    "    # Sample\n",
    "    def prob_LW(samples,variable):\n",
    "        result={}\n",
    "        values=samples[variable].unique()\n",
    "        for value in values:\n",
    "            result[value]=round(np.sum(samples[samples[variable]==value]['_weight'])/np.sum(samples['_weight']),2)\n",
    "        return result\n",
    "\n",
    "    def prob_RS(samples,variable):\n",
    "        result={}\n",
    "        values=samples[variable].unique()\n",
    "        tot=len(samples[variable])\n",
    "        for value in values:\n",
    "            result[value]=len(samples[samples[variable]==value])/tot\n",
    "        return result\n",
    "\n",
    "    def relative_error(exact_value,approx_value):\n",
    "        return np.absolute((exact_value-approx_value)/exact_value)\n",
    "\n",
    "    def absolute_error(exact_value,approx_value):\n",
    "\n",
    "        return np.absolute(exact_value-approx_value)\n",
    "\n",
    "    evidence2 = [State(key,val) for key,val in evidence.items()]\n",
    "    inference_sampling=BayesianModelSampling(model)\n",
    "    samples_LW = inference_sampling.likelihood_weighted_sample(evidence = evidence2, size=sample_size)\n",
    "    samples_RS = inference_sampling.rejection_sample(evidence=evidence2, size=sample_size)\n",
    "    \n",
    "    # # Statistics  \n",
    "    variables=[str(node) for node in model.nodes if str(node) not in evidence.keys()]\n",
    "    p_LW={}\n",
    "    p_RS={}\n",
    "    absolute_error_LW={}\n",
    "    absolute_error_RS={}\n",
    "    \n",
    "    for variable in variables:\n",
    "\n",
    "        p_LW[variable]=prob_LW(samples_LW,variable)\n",
    "        p_RS[variable]=prob_RS(samples_RS,variable)\n",
    "        \n",
    "        values=samples_LW[variable].unique()\n",
    "        # exec('absolute_error_LW[variable]={value:absolute_error(p_exact[variable].get_value(%s=value),p_LW[variable][value]) for value in values}'%variable,locals())\n",
    "        absolute_error_LW[variable]={value:absolute_error(p_exact[variable].get_value(**{variable:value}),p_LW[variable][value]) for value in values}\n",
    "        \n",
    "        values=samples_RS[variable].unique()\n",
    "        # exec('absolute_error_RS[variable]={value:absolute_error(p_exact[variable].get_value(%s=value),p_RS[variable][value]) for value in values}'%variable,locals())\n",
    "        absolute_error_RS[variable]={value:absolute_error(p_exact[variable].get_value(**{variable:value}),p_RS[variable][value]) for value in values}\n",
    "\n",
    "    # Return results\n",
    "    return p_exact,p_LW,p_RS,absolute_error_LW,absolute_error_RS\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 160,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Finding Elimination Order: : 100%|██████████| 1/1 [00:00<00:00, 125.20it/s]\n",
      "Eliminating: OpenSource: 100%|██████████| 1/1 [00:00<00:00, 123.85it/s]\n",
      "Finding Elimination Order: : 100%|██████████| 1/1 [00:00<00:00, 124.99it/s]\n",
      "Eliminating: Hobby: 100%|██████████| 1/1 [00:00<?, ?it/s]\n",
      "Finding Elimination Order: : 100%|██████████| 3/3 [00:00<?, ?it/s]\n",
      "Eliminating: OpenSource: 100%|██████████| 3/3 [00:00<00:00, 375.02it/s]\n",
      "Finding Elimination Order: : : 0it [00:00, ?it/s]\n",
      "0it [00:00, ?it/s]\n",
      "Finding Elimination Order: : : 0it [00:00, ?it/s]\n",
      "0it [00:00, ?it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 176.10it/s]\n",
      "  0%|          | 0/10 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "  0%|          | 0/10 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 10/10 [00:00<00:00, 37.66it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 143.07it/s]\n",
      "  0%|          | 0/16 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 31%|███▏      | 5/16 [00:00<00:00, 37.83it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 16/16 [00:00<00:00, 60.81it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 139.55it/s]\n",
      "  0%|          | 0/26 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 23%|██▎       | 6/26 [00:00<00:00, 34.01it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 26/26 [00:00<00:00, 86.25it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 111.93it/s]\n",
      "  0%|          | 0/42 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 29%|██▊       | 12/42 [00:00<00:00, 85.71it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 42/42 [00:00<00:00, 160.01it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 149.82it/s]\n",
      "  0%|          | 0/69 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 30%|███       | 21/69 [00:00<00:00, 156.46it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 69/69 [00:00<00:00, 283.46it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 159.44it/s]\n",
      "  0%|          | 0/112 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 25%|██▌       | 28/112 [00:00<00:00, 211.51it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 112/112 [00:00<00:00, 488.96it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 115.44it/s]\n",
      "  0%|          | 0/183 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 27%|██▋       | 49/183 [00:00<00:00, 340.26it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 183/183 [00:00<00:00, 733.01it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 136.37it/s]\n",
      "  0%|          | 0/297 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 297/297 [00:00<00:00, 1467.61it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 132.35it/s]\n",
      "  0%|          | 0/483 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 27%|██▋       | 132/483 [00:00<00:00, 1257.70it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 483/483 [00:00<00:00, 2308.18it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 129.70it/s]\n",
      "  0%|          | 0/784 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 24%|██▍       | 188/784 [00:00<00:00, 1544.52it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 784/784 [00:00<00:00, 3189.71it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 112.94it/s]\n",
      "  0%|          | 0/1274 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 24%|██▍       | 307/1274 [00:00<00:00, 2743.55it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 1274/1274 [00:00<00:00, 5092.39it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 119.33it/s]\n",
      "  0%|          | 0/2069 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 28%|██▊       | 571/2069 [00:00<00:00, 4950.67it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 2069/2069 [00:00<00:00, 7955.20it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 96.48it/s]\n",
      "  0%|          | 0/3359 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 24%|██▍       | 809/3359 [00:00<00:00, 6487.43it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 3359/3359 [00:00<00:00, 10582.78it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 74.95it/s]\n",
      "  0%|          | 0/5455 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 24%|██▍       | 1315/5455 [00:00<00:00, 9078.03it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 5455/5455 [00:00<00:00, 12478.89it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 53.80it/s]\n",
      "  0%|          | 0/8858 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 25%|██▍       | 2176/8858 [00:00<00:00, 15098.76it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 8858/8858 [00:00<00:00, 15204.32it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 43.17it/s]\n",
      "  0%|          | 0/14384 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 25%|██▌       | 3653/14384 [00:00<00:00, 18663.15it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 14384/14384 [00:00<00:00, 17903.17it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 32.58it/s]\n",
      "  0%|          | 0/23357 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 25%|██▍       | 5778/23357 [00:00<00:00, 23224.58it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 23357/23357 [00:01<00:00, 20333.38it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 21.59it/s]\n",
      "  0%|          | 0/37926 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 25%|██▍       | 9433/37926 [00:00<00:01, 25827.67it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 37926/37926 [00:01<00:00, 19558.09it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00, 13.10it/s]\n",
      "  0%|          | 0/61584 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 25%|██▍       | 15179/61584 [00:00<00:01, 26613.89it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 61584/61584 [00:03<00:00, 20409.12it/s]\n",
      "Generating for node: JobSatisfaction: 100%|██████████| 7/7 [00:00<00:00,  8.47it/s]\n",
      "  0%|          | 0/100000 [00:00<?, ?it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      " 25%|██▍       | 24713/100000 [00:00<00:02, 26159.81it/s]C:\\Users\\tomma\\Documents\\Uni\\Magistrale\\pyvenvs\\FAIKR_venv\\lib\\site-packages\\pgmpy\\sampling\\Sampling.py:227: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
      "  sampled = sampled.append(_sampled).iloc[:size, :]\n",
      "100%|██████████| 100000/100000 [00:05<00:00, 19582.32it/s]\n"
     ]
    }
   ],
   "source": [
    "evidence = {'Country':'India','FormalEducation':'Bachelor'}\n",
    "\n",
    "starting_size_=1 # from 10 sample points\n",
    "final_size=5     # to 10^5 sample points\n",
    "experiments=20 # 8 experiments\n",
    "result=[]\n",
    "inference_exact=VariableElimination(model)\n",
    "\n",
    "variables=[str(node) for node in model.nodes if str(node) not in evidence.keys()]\n",
    "p_exact={variable:inference_exact.query([variable],evidence) for variable in variables}\n",
    "\n",
    "for size in np.logspace(starting_size_, final_size, num=experiments, dtype='<i8'):\n",
    "    p_exact,p_LW,p_RS,absolute_error_LW,absolute_error_RS=run_experiment(model,size,evidence,p_exact)\n",
    "    result.append({\n",
    "        'sample_size':size,\n",
    "        'p_exact':p_exact,\n",
    "        'p_LW':p_LW,\n",
    "        'p_RS':p_RS,\n",
    "        'e_LW':absolute_error_LW,\n",
    "        'e_RS':absolute_error_RS\n",
    "    })"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 161,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1440x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1440x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_prob(results,p_exact,evidence,**variables):\n",
    "\n",
    "    sample_size=[r['sample_size'] for r in results]\n",
    "    \n",
    "    for var,val in variables.items():\n",
    "        p_LW=[r['p_LW'][var][val] for r in results]\n",
    "        p_RS=[r['p_RS'][var][val] for r in results]\n",
    "        p=p_exact[var].get_value(**{var:val})\n",
    "\n",
    "        plt.figure(figsize=(20,5))\n",
    "        plt.subplot()\n",
    "        plt.ylim(0,1)\n",
    "        plt.title('P({}={}|{}'.format(var,val,','.join([str(k)+\"=\"+str(v) for k,v in evidence.items()])))\n",
    "        LWCplot, = plt.semilogx(sample_size,p_LW,'b',label=\"Likelihood Weighting\")\n",
    "        RSCplot, = plt.semilogx(sample_size,p_RS,'g',label=\"Rejection Sampling\")\n",
    "        VECplot, = plt.semilogx(sample_size,p*np.ones(len(results)),'r',label=\"reference value\")\n",
    "        plt.legend(handles=[LWCplot,RSCplot,VECplot])\n",
    "        plt.show()\n",
    "plot_prob(result,p_exact,evidence,OpenSource='Yes',Hobby='Yes')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1440x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1440x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_error(results,p_exact,evidence,**variables):\n",
    "    # evidence=p_exact['Hobby'].get_evidence()\n",
    "    # print(evidence)\n",
    "    sample_size=[r['sample_size'] for r in results]\n",
    "    \n",
    "    for var,val in variables.items():\n",
    "        e_LW=[r['e_LW'][var][val] for r in results]\n",
    "        e_RS=[r['e_RS'][var][val] for r in results]\n",
    "\n",
    "        plt.figure(figsize=(20,5))\n",
    "        plt.subplot()\n",
    "        plt.ylim(0,np.max(e_LW+e_RS)+0.1*np.max(e_LW+e_RS))\n",
    "        plt.title('Absolute error on P({}={}|{}'.format(var,val,','.join([str(k)+\"=\"+str(v) for k,v in evidence.items()])))\n",
    "        LWCplot, = plt.semilogx(sample_size,e_LW,'b',label=\"Likelihood Weighting\")\n",
    "        RSCplot, = plt.semilogx(sample_size,e_RS,'g',label=\"Rejection Sampling\")\n",
    "        plt.legend(handles=[LWCplot,RSCplot])\n",
    "        plt.show()\n",
    "        \n",
    "plot_error(result,p_exact,evidence,OpenSource='Yes',Hobby='Yes')"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "c23b91227a54c2af61c5e03a530e77c3a20e29d5fbc858ef43b726817a78fb0f"
  },
  "kernelspec": {
   "display_name": "Python 3.10.2 ('FAIKR_venv')",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.2"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}