Logistic-Regression-Assignment.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "I decided to treat this as a classification problem by creating a new binary\n",
    "variable affair (did the woman have at least one affair?) and trying to\n",
    "predict the classification for each woman.\n",
    "Dataset\n",
    "\n",
    "The dataset I chose is the affairs dataset that comes with Statsmodels. It\n",
    "was derived from a survey of women in 1974 by Redbook magazine, in\n",
    "which married women were asked about their participation in extramarital\n",
    "affairs. More information about the study is available in a 1978 paper from\n",
    "the Journal of Political Economy.\n",
    "\n",
    "Description of Variables\n",
    "\n",
    "The dataset contains 6366 observations of 9 variables:\n",
    "    \n",
    "* rate_marriage: woman's rating of her marriage (1 = very poor, 5 =very good)\n",
    "* age: woman's age\n",
    "* yrs_married: number of years married\n",
    "* children: number of children\n",
    "* religious: woman's rating of how religious she is (1 = not religious, 4 = strongly religious)\n",
    "* educ: level of education (9 = grade school, 12 = high school, 14 =some college, 16 = college graduate, 17 = some graduate school, 20= advanced degree)\n",
    "* occupation: woman's occupation (1 = student, 2 = farming/semi-skilled/unskilled, 3 = \"white collar\", 4 =teacher/nurse/writer/technician/skilled, 5 = managerial/business, 6 =professional with advanced degree)\n",
    "* occupation_husb: husband's occupation (same coding as above)\n",
    "* affairs: time spent in extra-marital affairs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "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>rate_marriage</th>\n",
       "      <th>age</th>\n",
       "      <th>yrs_married</th>\n",
       "      <th>children</th>\n",
       "      <th>religious</th>\n",
       "      <th>educ</th>\n",
       "      <th>occupation</th>\n",
       "      <th>occupation_husb</th>\n",
       "      <th>affairs</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>17.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.111111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3.0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3.230769</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.400000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.0</td>\n",
       "      <td>37.0</td>\n",
       "      <td>16.5</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.727273</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.666666</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6361</th>\n",
       "      <td>5.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>17.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6362</th>\n",
       "      <td>4.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6363</th>\n",
       "      <td>5.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6364</th>\n",
       "      <td>5.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6365</th>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6366 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      rate_marriage   age  yrs_married  children  religious  educ  occupation  \\\n",
       "0               3.0  32.0          9.0       3.0        3.0  17.0         2.0   \n",
       "1               3.0  27.0         13.0       3.0        1.0  14.0         3.0   \n",
       "2               4.0  22.0          2.5       0.0        1.0  16.0         3.0   \n",
       "3               4.0  37.0         16.5       4.0        3.0  16.0         5.0   \n",
       "4               5.0  27.0          9.0       1.0        1.0  14.0         3.0   \n",
       "...             ...   ...          ...       ...        ...   ...         ...   \n",
       "6361            5.0  32.0         13.0       2.0        3.0  17.0         4.0   \n",
       "6362            4.0  32.0         13.0       1.0        1.0  16.0         5.0   \n",
       "6363            5.0  22.0          2.5       0.0        2.0  14.0         3.0   \n",
       "6364            5.0  32.0          6.0       1.0        3.0  14.0         3.0   \n",
       "6365            4.0  22.0          2.5       0.0        2.0  16.0         2.0   \n",
       "\n",
       "      occupation_husb   affairs  \n",
       "0                 5.0  0.111111  \n",
       "1                 4.0  3.230769  \n",
       "2                 5.0  1.400000  \n",
       "3                 5.0  0.727273  \n",
       "4                 4.0  4.666666  \n",
       "...               ...       ...  \n",
       "6361              3.0  0.000000  \n",
       "6362              5.0  0.000000  \n",
       "6363              1.0  0.000000  \n",
       "6364              4.0  0.000000  \n",
       "6365              4.0  0.000000  \n",
       "\n",
       "[6366 rows x 9 columns]"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import statsmodels.api as sm\n",
    "import matplotlib.pyplot as plt\n",
    "from patsy import dmatrices\n",
    "from sklearn.linear_model import LogisticRegression \n",
    "from sklearn.model_selection import train_test_split \n",
    "from sklearn import metrics \n",
    "from sklearn.model_selection import cross_val_score \n",
    "dta = sm.datasets.fair.load_pandas().data\n",
    "dta"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "dta['affair'] = (dta.affairs > 0).astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>rate_marriage</th>\n",
       "      <th>age</th>\n",
       "      <th>yrs_married</th>\n",
       "      <th>children</th>\n",
       "      <th>religious</th>\n",
       "      <th>educ</th>\n",
       "      <th>occupation</th>\n",
       "      <th>occupation_husb</th>\n",
       "      <th>affairs</th>\n",
       "      <th>affair</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>17.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.111111</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3.0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3.230769</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.400000</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.0</td>\n",
       "      <td>37.0</td>\n",
       "      <td>16.5</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.727273</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.666666</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   rate_marriage   age  yrs_married  children  religious  educ  occupation  \\\n",
       "0            3.0  32.0          9.0       3.0        3.0  17.0         2.0   \n",
       "1            3.0  27.0         13.0       3.0        1.0  14.0         3.0   \n",
       "2            4.0  22.0          2.5       0.0        1.0  16.0         3.0   \n",
       "3            4.0  37.0         16.5       4.0        3.0  16.0         5.0   \n",
       "4            5.0  27.0          9.0       1.0        1.0  14.0         3.0   \n",
       "\n",
       "   occupation_husb   affairs  affair  \n",
       "0              5.0  0.111111       1  \n",
       "1              4.0  3.230769       1  \n",
       "2              5.0  1.400000       1  \n",
       "3              5.0  0.727273       1  \n",
       "4              4.0  4.666666       1  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dta.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    4313\n",
       "1    2053\n",
       "Name: affair, dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dta['affair'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 6366 entries, 0 to 6365\n",
      "Data columns (total 10 columns):\n",
      " #   Column           Non-Null Count  Dtype  \n",
      "---  ------           --------------  -----  \n",
      " 0   rate_marriage    6366 non-null   float64\n",
      " 1   age              6366 non-null   float64\n",
      " 2   yrs_married      6366 non-null   float64\n",
      " 3   children         6366 non-null   float64\n",
      " 4   religious        6366 non-null   float64\n",
      " 5   educ             6366 non-null   float64\n",
      " 6   occupation       6366 non-null   float64\n",
      " 7   occupation_husb  6366 non-null   float64\n",
      " 8   affairs          6366 non-null   float64\n",
      " 9   affair           6366 non-null   int32  \n",
      "dtypes: float64(9), int32(1)\n",
      "memory usage: 472.6 KB\n"
     ]
    }
   ],
   "source": [
    "dta.info()"
   ]
  },
  {
   "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>rate_marriage</th>\n",
       "      <th>age</th>\n",
       "      <th>yrs_married</th>\n",
       "      <th>children</th>\n",
       "      <th>religious</th>\n",
       "      <th>educ</th>\n",
       "      <th>occupation</th>\n",
       "      <th>occupation_husb</th>\n",
       "      <th>affairs</th>\n",
       "      <th>affair</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>6366.000000</td>\n",
       "      <td>6366.000000</td>\n",
       "      <td>6366.000000</td>\n",
       "      <td>6366.000000</td>\n",
       "      <td>6366.000000</td>\n",
       "      <td>6366.000000</td>\n",
       "      <td>6366.000000</td>\n",
       "      <td>6366.000000</td>\n",
       "      <td>6366.000000</td>\n",
       "      <td>6366.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>4.109645</td>\n",
       "      <td>29.082862</td>\n",
       "      <td>9.009425</td>\n",
       "      <td>1.396874</td>\n",
       "      <td>2.426170</td>\n",
       "      <td>14.209865</td>\n",
       "      <td>3.424128</td>\n",
       "      <td>3.850141</td>\n",
       "      <td>0.705374</td>\n",
       "      <td>0.322495</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.961430</td>\n",
       "      <td>6.847882</td>\n",
       "      <td>7.280120</td>\n",
       "      <td>1.433471</td>\n",
       "      <td>0.878369</td>\n",
       "      <td>2.178003</td>\n",
       "      <td>0.942399</td>\n",
       "      <td>1.346435</td>\n",
       "      <td>2.203374</td>\n",
       "      <td>0.467468</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>17.500000</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>4.000000</td>\n",
       "      <td>22.000000</td>\n",
       "      <td>2.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>12.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>4.000000</td>\n",
       "      <td>27.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>14.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>5.000000</td>\n",
       "      <td>32.000000</td>\n",
       "      <td>16.500000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>16.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>0.484848</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>5.000000</td>\n",
       "      <td>42.000000</td>\n",
       "      <td>23.000000</td>\n",
       "      <td>5.500000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>57.599991</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       rate_marriage          age  yrs_married     children    religious  \\\n",
       "count    6366.000000  6366.000000  6366.000000  6366.000000  6366.000000   \n",
       "mean        4.109645    29.082862     9.009425     1.396874     2.426170   \n",
       "std         0.961430     6.847882     7.280120     1.433471     0.878369   \n",
       "min         1.000000    17.500000     0.500000     0.000000     1.000000   \n",
       "25%         4.000000    22.000000     2.500000     0.000000     2.000000   \n",
       "50%         4.000000    27.000000     6.000000     1.000000     2.000000   \n",
       "75%         5.000000    32.000000    16.500000     2.000000     3.000000   \n",
       "max         5.000000    42.000000    23.000000     5.500000     4.000000   \n",
       "\n",
       "              educ   occupation  occupation_husb      affairs       affair  \n",
       "count  6366.000000  6366.000000      6366.000000  6366.000000  6366.000000  \n",
       "mean     14.209865     3.424128         3.850141     0.705374     0.322495  \n",
       "std       2.178003     0.942399         1.346435     2.203374     0.467468  \n",
       "min       9.000000     1.000000         1.000000     0.000000     0.000000  \n",
       "25%      12.000000     3.000000         3.000000     0.000000     0.000000  \n",
       "50%      14.000000     3.000000         4.000000     0.000000     0.000000  \n",
       "75%      16.000000     4.000000         5.000000     0.484848     1.000000  \n",
       "max      20.000000     6.000000         6.000000    57.599991     1.000000  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dta.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Frequency')"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# barplot of marriage rating grouped by affair (True or False)\n",
    "pd.crosstab(dta.rate_marriage, dta.affair.astype(bool)).plot(kind='bar')\n",
    "plt.title('Marriage Rating Distribution by Affair Status')\n",
    "plt.xlabel('Marriage Rating')\n",
    "plt.ylabel('Frequency')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Frequency')"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAEjCAYAAADDry0IAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/d3fzzAAAACXBIWXMAAAsTAAALEwEAmpwYAAAnlUlEQVR4nO3debxVdb3/8ddbQBExBQQH0A4540R2HMpbaWhSDuAtL5gpmsnNa2X3pxWaJd3kZtloXTVzHlLRUrlaqZDgzVBExBxwoEA5AoI44Mign98f63twe9jnrH3O2cMZ3s/HYz/22t81fdY+++zP/q7vd32XIgIzM7OWbFDrAMzMrONzsjAzs1xOFmZmlsvJwszMcjlZmJlZLicLMzPL5WTRRUmqkxSSelZ5v8dKuqua+2yy/9clfahM2zpL0qVpuqzvp6TtUqw9yrG9JtsOSTuUe7tF9iNJV0h6WdKsVHaKpBfSsQ3IWX/d+2sdn5NFJyJpoaS30j9i4+PXNYxnvS/QiLguIj5dgX0dKOndguNukDRZ0j6Fy0VE34j4ZwnbasjbZ0T8d0R8ub2xp30ulHRwwbafS7G+U47tV1J6v0LSt5rM+hfgEGBIROwrqRfwM+DT6dhWtLTdtry/KcEsKPgM3Fgwb7qkkrcnaaKka1uz/+7MyaLzOSL9IzY+vlrrgKpocUT0BTYF9geeBP5P0ohy76jaNbIObhzwUnou9EFgYUS8kV5vCfQGHm/vDou9/5LGAccBB6fPQT0wrb37shJFhB+d5AEsJPtHKTavB/AT4EXgn8CpQAA9i60LTASuLXj9L8DfgFeARcAJqfww4GFgZSqfWLDOc2kfr6fHR4ETgL8WLPMx4EHg1fT8sYJ504EfAPcBrwF3AVs0c3wHAg1Fyn8NzC54HcAOafqzwBNp288DZwCbAG8B7xbEvU16P24Grk3H+uXC9wioS9seDywGlgCnF+z3SuDcYvEC16T9vZX2962C7TX+fbYBppB9Kc8HTm7yt5oMXJ2O5XGgvoXPSQBfT5+DF4HzyX4YbpS2v0fBsoNSXAOb2VaftM+xwOrG/QInAW8D76Rjuh54o+Dz8Je03C/T52Yl8BDw8WKfwYL34ySyz9W9zfytf9FMnJNSLG+n/f+6pf0DI9PxrEnLP5L3f0KWCK8FVpD9nzwIbFnr74VqPVyz6DpOBg4HPkz2i+vzpa4oaTvgT8CvgIHAcGBumv0GcDywOVniOEXS6DTvE+l588hqOTObbLc/cAdwATCA7BTFHU3OZX8BOJHsS2tDsi/01vgDsLekTYrMuwz494jYFNid7AvsDeAzpFpKeixOy48iSxibA9c1s7+DgB2BTwMTCk8tNScijiP7AmysFf64yGLXAw1kSePzwH83qTEdCdyQYptC9sXZkqPIPgd7p+P6UkSsStv4YsFyxwBTI2J5M9v5HNmX6U3AnWSfBSLiMuArwMx0TMcAu6V1No+IT6XpB8k+T/2B3wE3SerdQtyfBHYFDi0y737geEnflFRf2N4TEd8B/g/4ary/xl10/xHxZ+C/gRvT8nu1EFOjccBmwLZkn+evkCXabsHJovO5VdIrBY+TU/m/kf3qWhQRLwE/bMU2jyX7wrg+ItZExIqImAsQEdMj4tGIeDci/k72pfbJErd7GPBMRFwTEWsj4nqyU0dHFCxzRUQ8HRFvkf16Ht6KuCH7lS+yL9Gm1gDDJH0gIl6OiDk525oZEbemY23uS+D7EfFGRDwKXEH2ZdsukrYlq9l9OyLeTu/9pWSnXBr9NSL+GFkbxzVA3pfbjyLipYh4DvhFQZxXAV+Q1Pi/f1zaXnPGkX2hvkP2ZXtMapsoSURcmz5PayPip2S1m51bWGVien/Xe/8j4lrga2SJZAawTNKEMu+/JWvIksQOEfFORDwUESvbuK1Ox8mi8xkdEZsXPH6byrchq243erYV29wW+EexGZL2k3SPpOWSXiX7NbVFidvdpkgczwKDC14vLZh+E+hb4rYbDSY7ffFKkXmfIzsV9aykGZI+mrOtRTnzmy7zLNkxttc2wEsR8VqTbbf0PvXOaVcpGmdEPEBWW/ykpF2AHchqKutJSewg3qtl3UZ2KuawvAMq2MbpkuZJelXSK2S/zFv6/LT4N4isA8XBZD8OvgL8l6RitZC27r8l15DVrm6QtFjSj1uTODs7J4uuYwnZl36j7ZrMf4Ps/HOjrQqmFwHbN7Pd35F9mWwbEZsBF5P9kofsS7oli8kaQQttR9Z+UC5HAXPivUbWdSLiwYgYRXaK61aymgs0H3cpQzA3fY8bT2G19P7mbXsx0F/Spk223Z73qbk4IatdfJGsVnFzRLzdzDaOI/uO+F9JS8naQHqTTkXlkfRx4Ntktd5+EbE5WduVWlitpGGwUw34JuDvZKcY11u3hP0X21ezf8e0z+9HxDCytrjDKfG96AqcLLqOycDXJQ2R1A9oWj2fC4yV1EtS0zaN64CDJf2bpJ6SBkganuZtSvar921J+5K1MTRaTtZw29x1DX8EdpL0hbTdMcAw4PZ2HGdj//7Bks4ha4g+q8gyGyq75mOziFhD1sDZ2E31BWCApM3asPvvSuojaTeytpbGrptzgc9K6i9pK+AbTdZ7gWbep4hYRNa54IeSekvak6yht7l2k1J8U1K/VDs4rSBOyH4hH0WWMK5uYRvHA98nOzXY+PgccFjeNRTJpsBass9JT0nfAz7QqqMoIOkESYdJ2lTSBpI+Q9ZO8kBapOl7nLf/F4C6glNy0ML/iaSDJO2R2kpWkp2W6vBdn8vFyaLz+V+9/zqLW1L5b8mqyI8Ac8gafgt9l6z28DLZF8DvGmek89qfBU4n6y0zl/fOif8HWVX/NeB7vPfrnIh4k6wXyn2p/WT/wh1G1s/+8LTdFWS9gA6PiBfbeOzbSGrswfQgsAdwYEQ0dxHgccBCSSvJTll8McX1JFnbyz9T3K05lTSDrLfSNOAnBfu+huy9X0jWq+vGJuv9EDg77a9YI/4xZD2CFgO3AOdExN2tiKup28h6/8wl62RwWeOMiGgg+4wEWaPwetLfsg74n4hYWvCYQnb8pbTV3EnWceJpslNhb1Paqb7mrCT7YfAc2WnHHwOnRMRf0/xfAp9XdpHgBSXs/6b0vEJSY3tWs/8nZLWMm1Mc88g+C93mOg1F+OZHZt2NpMvJeoSdXetYrHPwhUdm3YykOuBfybpZm5XEp6HMuhFJPwAeA86PiAW1jsc6D5+GMjOzXK5ZmJlZLicLMzPL1WUbuLfYYouoq6urdRhmZp3KQw899GJEDGxa3mWTRV1dHbNnz651GGZmnYqkokMF+TSUmZnlcrIwM7NcThZmZpary7ZZmJmVas2aNTQ0NPD2280NwNv19O7dmyFDhtCrV2mjrDtZmFm319DQwKabbkpdXR1SSyOodw0RwYoVK2hoaGDo0KElrePTUGbW7b399tsMGDCgWyQKAEkMGDCgVTUpJwszM+g2iaJRa4/XycLMrMJuuukmdt11Vw466CAAjjnmGPbcc09+/vOfN7vOxRdfzNVXt3Rvqupym4V1GXUT7mjTegvPK/mW0mZtctlll3HhhRdy0EEHsXTpUv72t7/x7LNFr31b5ytf+UrR8rVr19KzZ/W/up0szMzKaPTo0SxatIi3336b0047jaVLl/LXv/6VBQsWcOSRR3LnnXeybNkyhg8fzq9+9SuefPJJLrnkElavXs0OO+zANddcQ58+fZg4cSJ9+/bljDPO4MADD+RjH/sY9913H0ceeSSnn3561Y/LycLMrIwuv/xy+vfvz1tvvcU+++zDjBkz+Mtf/sJPfvIT6uvrOfXUUzn88MOZO3cuAMOGDePkk08G4Oyzz+ayyy7ja1/72nrbfeWVV5gxY0Y1D+V9nCzMzMroggsu4JZbbgFg0aJFPPPMMy0u/9hjj3H22Wfzyiuv8Prrr3PooYcWXW7MmDFlj7U1nCzMzMpk+vTpTJ06lZkzZ9KnTx8OPPDA3O6pJ5xwArfeeit77bUXV155JdOnTy+63CabbFKBiEvn3lBmZmXy6quv0q9fP/r06cOTTz7J/fffn7vOa6+9xtZbb82aNWu47rrrqhBl21QsWUi6XNIySY8VmXeGpJC0RUHZmZLmS3pK0qEF5R+R9Giad4G6W2doM+s0Ro4cydq1a9lzzz357ne/y/7775+7zg9+8AP2228/DjnkEHbZZZcqRNk2FbsHt6RPAK8DV0fE7gXl2wKXArsAH4mIFyUNA64H9gW2AaYCO0XEO5JmAacB9wN/BC6IiD/l7b++vj58P4vuxV1nra3mzZvHrrvuWuswqq7YcUt6KCLqmy5bsZpFRNwLvFRk1s+BbwGFWWoUcENErIqIBcB8YF9JWwMfiIiZkWW1q4HRlYrZzMyKq2qbhaQjgecj4pEmswYDiwpeN6SywWm6abmZmVVR1XpDSeoDfAf4dLHZRcqihfLm9jEeGA+w3XbbtSFKMzMrppo1i+2BocAjkhYCQ4A5krYiqzFsW7DsEGBxKh9SpLyoiLgkIuojon7gwPXuN25mZm1UtWQREY9GxKCIqIuIOrJEsHdELAWmAGMlbSRpKLAjMCsilgCvSdo/9YI6HritWjGbmVmmkl1nrwdmAjtLapB0UnPLRsTjwGTgCeDPwKkR8U6afQpZ76n5wD+A3J5QZmZWXhVrs4iIY3Lm1zV5PQmYVGS52cDuTcvNzLqSHj16sMcee6x7feutt1JXV1d02b59+/L6669XKbKMh/swM2uirdfsNKeUa3k23njjdYMLdkROFt2IL1oz6zxef/11Ro0axcsvv8yaNWs499xzGTVq1PuWWbJkCWPGjGHlypWsXbuWiy66iI9//OPcddddnHPOOaxatYrtt9+eK664gr59+7YrHo8NZWbWAbz11lsMHz6c4cOHc9RRR9G7d29uueUW5syZwz333MPpp59O0xE3fve733HooYcyd+5cHnnkEYYPH86LL77Iueeey9SpU5kzZw719fX87Gc/a3d8rlmYmXUATU9DrVmzhrPOOot7772XDTbYgOeff54XXniBrbbaat0y++yzD1/60pdYs2YNo0ePZvjw4cyYMYMnnniCAw44AIDVq1fz0Y9+tN3xOVmYmXVA1113HcuXL+ehhx6iV69e1NXVrTfc+Sc+8Qnuvfde7rjjDo477ji++c1v0q9fPw455BCuv/76ssbj01BmZh3Qq6++yqBBg+jVqxf33HNP0Xt2P/vsswwaNIiTTz6Zk046iTlz5rD//vtz3333MX/+fADefPNNnn766XbH45qFmVkHdOyxx3LEEUdQX1/P8OHDiw5fPn36dM4//3x69epF3759ufrqqxk4cCBXXnklxxxzDKtWrQLg3HPPZaeddmpXPE4WZmZN1KIHYNPrJrbYYgtmzpzZ4rLjxo1j3Lhx683/1Kc+xYMPPljW+HwayszMcjlZmJlZLicLMzPL5WRhZma5nCzMzCyXk4WZmeVy11kzsxpbsWIFI0aMAGDp0qX06NGDxrt9zpo1iw033LCW4QFOFmZm65u4WZm392qLswcMGLBuXKiJEyfSt29fzjjjjHXz165dS8+etf26drIwM+uATjjhBPr378/DDz/M3nvvzaabbvq+JLL77rtz++23U1dXx7XXXssFF1zA6tWr2W+//bjwwgvp0aNHWeNxm4WZWQf19NNPM3XqVH760582u8y8efO48cYbue+++5g7dy49evTguuuuK3ssrlmYmXVQRx99dG4NYdq0aTz00EPss88+QHZfjEGDBpU9loolC0mXA4cDyyJi91R2PnAEsBr4B3BiRLyS5p0JnAS8A3w9Iu5M5R8BrgQ2Bv4InBZN7wBiZtYFbbLJJuume/bsybvvvrvudeNw5RHBuHHj+OEPf1jRWCp5GupKYGSTsruB3SNiT+Bp4EwAScOAscBuaZ0LJTWm04uA8cCO6dF0m2ZmXV5dXR1z5swBYM6cOSxYsACAESNGcPPNN7Ns2TIAXnrppaLDmbdXxZJFRNwLvNSk7K6IWJte3g8MSdOjgBsiYlVELADmA/tK2hr4QETMTLWJq4HRlYrZzKyj+tznPsdLL73E8OHDueiii9YNOT5s2DDOPfdcPv3pT7PnnntyyCGHsGTJkrLvv5ZtFl8CbkzTg8mSR6OGVLYmTTctNzOrnJyurhXd9cSJRcs33nhj7rrrrqLzxowZw5gxYyoYVY16Q0n6DrAWaGyyV5HFooXy5rY7XtJsSbOXL1/e/kDNzAyoQbKQNI6s4fvYgobqBmDbgsWGAItT+ZAi5UVFxCURUR8R9Y1XP5qZWftVNVlIGgl8GzgyIt4smDUFGCtpI0lDyRqyZ0XEEuA1SftLEnA8cFs1YzYzs8p2nb0eOBDYQlIDcA5Z76eNgLuz737uj4ivRMTjkiYDT5Cdnjo1It5JmzqF97rO/ik9zMzKKiJI30vdQmuvQKhYsoiIY4oUX9bC8pOASUXKZwO7lzE0M7P36d27NytWrGDAgAHdImFEBCtWrKB3794lr+MruM2s2xsyZAgNDQ10p44xvXv3ZsiQIfkLJk4WZtbt9erVi6FDh9Y6jA7NAwmamVkuJwszM8vlZGFmZrmcLMzMLJeThZmZ5XKyMDOzXE4WZmaWy8nCzMxyOVmYmVkuJwszM8vlZGFmZrmcLMzMLJeThZmZ5XKyMDOzXE4WZmaWy8nCzMxyOVmYmVkuJwszM8tVsWQh6XJJyyQ9VlDWX9Ldkp5Jz/0K5p0pab6kpyQdWlD+EUmPpnkXqDvcTd3MrIOpZM3iSmBkk7IJwLSI2BGYll4jaRgwFtgtrXOhpB5pnYuA8cCO6dF0m2ZmVmEVSxYRcS/wUpPiUcBVafoqYHRB+Q0RsSoiFgDzgX0lbQ18ICJmRkQAVxesY2ZmVVLtNostI2IJQHoelMoHA4sKlmtIZYPTdNPyoiSNlzRb0uzly5eXNXAzs+6sozRwF2uHiBbKi4qISyKiPiLqBw4cWLbgzMy6u2onixfSqSXS87JU3gBsW7DcEGBxKh9SpNzMzKqo2sliCjAuTY8DbisoHytpI0lDyRqyZ6VTVa9J2j/1gjq+YB0zM6uSnpXasKTrgQOBLSQ1AOcA5wGTJZ0EPAccDRARj0uaDDwBrAVOjYh30qZOIetZtTHwp/QwM7MqqliyiIhjmpk1opnlJwGTipTPBnYvY2hmZtZKHaWB28zMOjAnCzMzy+VkYWZmuUpKFpLcZmBm1o2VWrO4WNIsSf8hafNKBmRmZh1PSckiIv4FOJbswrnZkn4n6ZCKRmZmZh1GyW0WEfEMcDbwbeCTwAWSnpT0r5UKzszMOoZS2yz2lPRzYB7wKeCIiNg1Tf+8gvGZmVkHUOpFeb8GfgucFRFvNRZGxGJJZ1ckMjMz6zBKTRafBd5qHIJD0gZA74h4MyKuqVh0ZmbWIZTaZjGVbGymRn1SmZmZdQOlJoveEfF644s03acyIZmZWUdTarJ4Q9LejS8kfQR4q4XlzcysCym1zeIbwE2SGm88tDUwpiIRmZlZh1NSsoiIByXtAuxMdqvTJyNiTUUjMzOzDqM197PYB6hL63xYEhFxdUWiMjOzDqWkZCHpGmB7YC7QeAe7AJwszKqkbsIdbVpv4XmHlTkS645KrVnUA8MiIioZjJmZdUyl9oZ6DNiqkoGYmVnHVWqy2AJ4QtKdkqY0Ptq6U0n/KelxSY9Jul5Sb0n9Jd0t6Zn03K9g+TMlzZf0lKRD27pfMzNrm1JPQ00s1w4lDQa+TnZa6y1Jk4GxwDBgWkScJ2kCMAH4tqRhaf5uwDbAVEk7NQ49YmZmlVfq/SxmAAuBXmn6QWBOO/bbE9hYUk+yK8EXA6OAq9L8q4DRaXoUcENErIqIBcB8YN927NvMzFqp1N5QJwPjgf5kvaIGAxcDI1q7w4h4XtJPgOfIrgK/KyLukrRlRCxJyyyRNCitMhi4v2ATDanMrDwmbtbG9V4tbxxmHVipbRanAgcAK2HdjZAGtbhGM1JbxChgKNlppU0kfbGlVYqUFe2VJWm8pNmSZi9fvrwt4ZmZWRGlJotVEbG68UU6fdTWbrQHAwsiYnm6CvwPwMeAFyRtnba/NbAsLd9AdjvXRkPITlutJyIuiYj6iKgfOHBgG8MzM7OmSk0WMySdRdbOcAhwE/C/bdznc8D+kvpIEtmprHnAFGBcWmYccFuangKMlbSRpKHAjsCsNu7bzMzaoNTeUBOAk4BHgX8H/ghc2pYdRsQDkm4mayBfCzwMXAL0BSZLOoksoRydln889Zh6Ii1/qntCmZlVV6kDCb5LdlvV35ZjpxFxDnBOk+JVNNNgHhGTgEnl2LeZmbVeqb2hFlCkjSIiPlT2iMzMrMNpzdhQjXqTnSLqX/5wzMysIyr1orwVBY/nI+IXwKcqG5qZmXUUpZ6G2rvg5QZkNY1NKxKRmZl1OKWehvppwfRasqE//q3s0ZiZWYdUam+ogyodiJmZdVylnob6fy3Nj4iflScc65A8dpJZt9ea3lD7kF1NDXAEcC+wqBJBmZlZx1JqstgC2DsiXgOQNBG4KSK+XKnAzMys4yh1bKjtgNUFr1cDdWWPxszMOqRSaxbXALMk3UJ2JfdRwNUVi8rMzDqUUntDTZL0J+DjqejEiHi4cmGZmVlHUuppKMhuf7oyIn4JNKThws3MrBsoKVlIOgf4NnBmKuoFXFupoMzMrGMptWZxFHAk8AZARCzGw32YmXUbpSaL1RERpGHKJW1SuZDMzKyjKTVZTJb0G2BzSScDUynTjZDMzKzjy+0Nle6TfSOwC7AS2Bn4XkTcXeHYzMysg8hNFhERkm6NiI8AThBmZt1Qqaeh7pe0T7l2KmlzSTdLelLSPEkfldRf0t2SnknP/QqWP1PSfElPSTq0XHGYmVlpSk0WB5EljH9I+rukRyX9vR37/SXw54jYBdgLmAdMAKZFxI7AtPQaScOAscBuwEjgQkk92rFvMzNrpRZPQ0naLiKeAz5Trh1K+gDwCeAEgIhYDayWNAo4MC12FTCd7NqOUcANEbEKWCBpPrAvMLNcMZmZWcvyaha3AkTEs8DPIuLZwkcb9/khYDlwhaSHJV2auuJuGRFL0v6WAIPS8oN5/1DoDanMzMyqJC9ZqGD6Q2XaZ09gb+CiiPgw2YV+E0qMoVEUXVAaL2m2pNnLly9vf6RmZgbkJ4toZro9GoCGiHggvb6ZLHm8IGlrgPS8rGD5bQvWHwIsLhpsxCURUR8R9QMHDixTuGZmlpcs9pK0UtJrwJ5peqWk1yStbMsOI2IpsEjSzqloBPAE2V34xqWyccBtaXoKMFbSRmnwwh2BWW3Zt5mZtU2LDdwRUaleR18DrpO0IfBP4ESyxDVZ0knAc8DRKYbHJU0mSyhrgVMj4p0KxWVmZkWUevOjsoqIuWT39W5qRDPLTwImVTImMzNrXmvuZ2FmZt2Uk4WZmeVysjAzs1xOFmZmlsvJwszMcjlZmJlZLicLMzPL5WRhZma5nCzMzCyXk4WZmeVysjAzs1xOFmZmlsvJwszMcjlZmJlZLicLMzPL5WRhZma5nCzMzCyXk4WZmeVysjAzs1w1SxaSekh6WNLt6XV/SXdLeiY99ytY9kxJ8yU9JenQWsVsZtZd1bJmcRowr+D1BGBaROwITEuvkTQMGAvsBowELpTUo8qxmpl1azVJFpKGAIcBlxYUjwKuStNXAaMLym+IiFURsQCYD+xbpVDNzIza1Sx+AXwLeLegbMuIWAKQngel8sHAooLlGlKZmZlVSdWThaTDgWUR8VCpqxQpi2a2PV7SbEmzly9f3uYYzczs/WpRszgAOFLSQuAG4FOSrgVekLQ1QHpelpZvALYtWH8IsLjYhiPikoioj4j6gQMHVip+M7Nup+rJIiLOjIghEVFH1nD9l4j4IjAFGJcWGwfclqanAGMlbSRpKLAjMKvKYZuZdWs9ax1AgfOAyZJOAp4DjgaIiMclTQaeANYCp0bEO7UL08ys+6lpsoiI6cD0NL0CGNHMcpOASVULzMyqrm7CHW1ab+F5h5U5EivGV3CbmVkuJwszM8vlZGFmZrmcLMzMLJeThZmZ5XKyMDOzXE4WZmaWy8nCzMxyOVmYmVkuJwszM8vlZGFmZrmcLMzMLJeThZmZ5epIQ5SbWSVM3KyN671a3jisU3PNwszMcjlZmJlZLicLMzPL5TYLM7Mq6Ox3AnTNwszMclU9WUjaVtI9kuZJelzSaam8v6S7JT2TnvsVrHOmpPmSnpJ0aLVjNjPr7mpRs1gLnB4RuwL7A6dKGgZMAKZFxI7AtPSaNG8ssBswErhQUo8axG1m1m1VPVlExJKImJOmXwPmAYOBUcBVabGrgNFpehRwQ0SsiogFwHxg36oGbWbWzdW0zUJSHfBh4AFgy4hYAllCAQalxQYDiwpWa0hlZmZWJTVLFpL6Ar8HvhERK1tatEhZNLPN8ZJmS5q9fPnycoRpZmbUKFlI6kWWKK6LiD+k4hckbZ3mbw0sS+UNwLYFqw8BFhfbbkRcEhH1EVE/cODAygRvZtYN1aI3lIDLgHkR8bOCWVOAcWl6HHBbQflYSRtJGgrsCMyqVrxmZlabi/IOAI4DHpU0N5WdBZwHTJZ0EvAccDRARDwuaTLwBFlPqlMj4p2qR21m1o1VPVlExF8p3g4BMKKZdSYBkyoWlJmZtchXcJuZWS4nCzMzy+VkYWZmuZwszMwsl4coN7POzbeNrQrXLMzMLJeThZmZ5XKyMDOzXE4WZmaWy8nCzMxyOVmYmVkud501M+vIOkjXYNcszMwsl5OFmZnlcrIwM7NcThZmZpbLycLMzHI5WZiZWS4nCzMzy+VkYWZmuTrNRXmSRgK/BHoAl0bEeZXYT92EO9q03sLeX2jbDj2mvpl1Ap2iZiGpB/A/wGeAYcAxkobVNiozs+6jUyQLYF9gfkT8MyJWAzcAo2ock5lZt6GIqHUMuSR9HhgZEV9Or48D9ouIrzZZbjwwPr3cGXiqimFuAbxYxf1VU1c+NvDxdXY+vvL6YEQMbFrYWdosVKRsvSwXEZcAl1Q+nPVJmh0R9bXYd6V15WMDH19n5+Orjs5yGqoB2Lbg9RBgcY1iMTPrdjpLsngQ2FHSUEkbAmOBKTWOycys2+gUp6EiYq2krwJ3knWdvTwiHq9xWE3V5PRXlXTlYwMfX2fn46uCTtHAbWZmtdVZTkOZmVkNOVmYmVkuJwszM8vlZGFmZrk6RW+ojkjSlsBgsosDF0fECzUOycw6OUm7kA1ltO67BZgSEfNqGhjuDdVqkoYDFwObAc+n4iHAK8B/RMSc2kRWXh35Q9teXfnYwMfXWUn6NnAM2dh3Dal4CNl1ZTdUaqTtUjlZtJKkucC/R8QDTcr3B34TEXvVJLAy6ugf2vboyscGPr7OfHySngZ2i4g1Tco3BB6PiB1rE1mKw8midSQ909wfTdL8iNih2jGVW0f/0LZHVz428PF15uOT9CRwaEQ826T8g8BdEbFzbSLLuM2i9f4k6Q7gamBRKtsWOB74c82iKq93gW2AZ5uUb53mdWZd+djAx9eZfQOYJukZ3vtu2Q7YAfhqcytVi5NFK0XE1yV9hvfOmYqsOvw/EfHHmgZXPt+gA39o2+kbdN1jAx9fpxURf5a0E9n9ewq/Wx6MiHdqGhw+DWXNkLQBHfRD215d+djAx2eV4WRRRpLGp3tqmJmVjaTbI+LwWsbgi/LKq9hNmroUSbfXOoZK6crHBj6+Tu7kWgfgmkUbSNoeOIqsYXst8AxwfUS8WtPAqkDS1hGxpNZxVEJXPjbw8Vn7uGbRSpK+TnZRXm9gH2BjsqQxU9KBtYusOrriP6OkQdA1jw1A0gDousfXqLMfn6TNJJ0n6UlJK9JjXirbvNbxOVm03snAyIg4FzgYGBYR3wFGAj+vaWRlIukDkn4o6RpJX2gy78JaxVUOkvo3eQwAZknqJ6l/reNrr/TFskWarpf0T+ABSc9K+mSNw2s3SXMknZ1q913NZOBl4MCIGBARA4CDUtlNNY0MJ4u2auxyvBGwKUBEPAf0qllE5XUFWfvL74Gxkn4vaaM0b//ahVUWLwIPFTxmk/WqmZOmO7vDIuLFNH0+MCZdKHoI8NPahVU2/YDNgXskzZL0n5K2qXFM5VIXET+KiKWNBRGxNCJ+RNY9uKacLFrvUuBBSZcAM4FfA0gaCLxUy8DKaPuImBARt0bEkWRfpH9pPJ3RyX0LeAo4MiKGRsRQoCFNf6jGsZVDL0mNP2Y2jogHASLiabIfN53dyxFxRkRsB5wO7AjMkXSPpPE1jq29npX0rTRIKZANWJqGOFnUwnpV4QbuNpC0G7Ar8FhEPFnreMpN0jyyIRXeLSgbR/ZF2zciPliz4MpA0hCyU4aLgHOAR7pIokDS14AjgPOAT5D9Cv8DMAL4UEQcV7vo2k/SnIjYu0lZD7Ka05iIOLE2kbWfpH7ABLILfrckGyTxBWAK8KOIqOmPUScLW4+kH5ONRTO1SflI4FedefydQpKOAL5DVv3fqtbxlEvqaHEKsBPZKdNFwK3A5RGxtmaBlYGkGyJibK3jqJQ0ou4Q4P6IeL2gfGRE1HQ4IScLaxVJJ0bEFbWOo1wkbUx22u2xrnZsTfn4OrbU0/JUYB4wHDgtIm5L89arUVWbk4W1iqTn0vniLqcrHxv4+Do6SY8CH42I1yXVATcD10TELyU9HBEfrmV8HkjQ1iPp783NIjuX2ml15WMDH181Y6mAHo2nniJiYTqdeHMaorzmo0M4WVgxWwKHkvXvLiTgb9UPp6y68rGBj68zWyppeETMBUg1jMOBy4E9ahoZThZW3O1kvZ7mNp0haXrVoymvrnxs4OPrzI4nGz5ondQh4XhJv6lNSO9xm4WZmeXyRXlmZpbLycLMzHI5WZi1gaQTJP26zNscLWlYwev/knRwOfdh1lZOFmYdx2hgXbKIiO81vYrerFacLMyKkPTFNKrpXEm/kdRD0omSnpY0AzigYNkrJX2+4HXhMA3fkvSopEcknZfKTpb0YCr7vaQ+kj4GHAmcn/a5feF2JY2Q9HDa1uWNowBLWijp+2no7kfTcBFmZedkYdaEpF2BMcABETEceAf4IvB9siRxCAU1gBa28xmy2sJ+EbEX8OM06w8RsU8qmwecFBF/Ixsw7psRMTwi/lGwnd7AlWQD5e1B1uX9lIJdvZiGgrgIOKOtx23WEicLs/WNAD5CNhT93PT6P4HpEbE8IlYDN5awnYOBKyLiTYCCUUN3l/R/aXiHY4HdcrazM7AgDTMOcBXZiLKN/pCeHwLqSojLrNWcLMzWJ+Cq9At/eETsDEwkGzK6mLWk/yVJAjYs2E6xda4EvppqCd8nu0VvXjwtWZWe38EX2lqFOFmYrW8a8Hmle3On260+DBwoaYCkXsDRBcsvJKuJQHYvgsY7Jt4FfElSn4LtQHZ3xSVpO8cWbOe1NK+pJ4E6STuk18cBM9p+eGat52Rh1kREPAGcDdyVBq67G9iarHYxE5hKdvfARr8FPilpFrAf8Ebazp/J2iFmp9NZje0J3wUeSNstvHnWDcA3U0P2untMR8TbwInATenU1bvAxWU8ZLNcHu7DzMxyuWZhZma5nCzMzCyXk4WZmeVysjAzs1xOFmZmlsvJwszMcjlZmJlZLicLMzPL9f8BVp1oRD3EP8gAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.crosstab(dta.educ, dta.affair.astype(bool)).plot(kind='bar')\n",
    "plt.title('Education Distribution by Affair Status')\n",
    "plt.xlabel('education')\n",
    "plt.ylabel('Frequency')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Percentage')"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "affair_yrs_married = pd.crosstab(dta.yrs_married, dta.affair.astype(bool))\n",
    "affair_yrs_married.div(affair_yrs_married.sum(1).astype(float), axis=0).plot(kind='bar', stacked=True)\n",
    "plt.title('Affair Percentage by Years Married')\n",
    "plt.xlabel('Years Married')\n",
    "plt.ylabel('Percentage')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "y, X = dmatrices('affair ~ rate_marriage + age + yrs_married + children +religious + educ +C(occupation) + C(occupation_husb)',dta, return_type=\"dataframe\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>Intercept</th>\n",
       "      <th>C(occupation)[T.2.0]</th>\n",
       "      <th>C(occupation)[T.3.0]</th>\n",
       "      <th>C(occupation)[T.4.0]</th>\n",
       "      <th>C(occupation)[T.5.0]</th>\n",
       "      <th>C(occupation)[T.6.0]</th>\n",
       "      <th>C(occupation_husb)[T.2.0]</th>\n",
       "      <th>C(occupation_husb)[T.3.0]</th>\n",
       "      <th>C(occupation_husb)[T.4.0]</th>\n",
       "      <th>C(occupation_husb)[T.5.0]</th>\n",
       "      <th>C(occupation_husb)[T.6.0]</th>\n",
       "      <th>rate_marriage</th>\n",
       "      <th>age</th>\n",
       "      <th>yrs_married</th>\n",
       "      <th>children</th>\n",
       "      <th>religious</th>\n",
       "      <th>educ</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>17.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>14.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>16.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>37.0</td>\n",
       "      <td>16.5</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>16.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>14.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6361</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>17.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6362</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>16.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6363</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>14.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6364</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>14.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6365</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>16.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6366 rows × 17 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Intercept  C(occupation)[T.2.0]  C(occupation)[T.3.0]  \\\n",
       "0           1.0                   1.0                   0.0   \n",
       "1           1.0                   0.0                   1.0   \n",
       "2           1.0                   0.0                   1.0   \n",
       "3           1.0                   0.0                   0.0   \n",
       "4           1.0                   0.0                   1.0   \n",
       "...         ...                   ...                   ...   \n",
       "6361        1.0                   0.0                   0.0   \n",
       "6362        1.0                   0.0                   0.0   \n",
       "6363        1.0                   0.0                   1.0   \n",
       "6364        1.0                   0.0                   1.0   \n",
       "6365        1.0                   1.0                   0.0   \n",
       "\n",
       "      C(occupation)[T.4.0]  C(occupation)[T.5.0]  C(occupation)[T.6.0]  \\\n",
       "0                      0.0                   0.0                   0.0   \n",
       "1                      0.0                   0.0                   0.0   \n",
       "2                      0.0                   0.0                   0.0   \n",
       "3                      0.0                   1.0                   0.0   \n",
       "4                      0.0                   0.0                   0.0   \n",
       "...                    ...                   ...                   ...   \n",
       "6361                   1.0                   0.0                   0.0   \n",
       "6362                   0.0                   1.0                   0.0   \n",
       "6363                   0.0                   0.0                   0.0   \n",
       "6364                   0.0                   0.0                   0.0   \n",
       "6365                   0.0                   0.0                   0.0   \n",
       "\n",
       "      C(occupation_husb)[T.2.0]  C(occupation_husb)[T.3.0]  \\\n",
       "0                           0.0                        0.0   \n",
       "1                           0.0                        0.0   \n",
       "2                           0.0                        0.0   \n",
       "3                           0.0                        0.0   \n",
       "4                           0.0                        0.0   \n",
       "...                         ...                        ...   \n",
       "6361                        0.0                        1.0   \n",
       "6362                        0.0                        0.0   \n",
       "6363                        0.0                        0.0   \n",
       "6364                        0.0                        0.0   \n",
       "6365                        0.0                        0.0   \n",
       "\n",
       "      C(occupation_husb)[T.4.0]  C(occupation_husb)[T.5.0]  \\\n",
       "0                           0.0                        1.0   \n",
       "1                           1.0                        0.0   \n",
       "2                           0.0                        1.0   \n",
       "3                           0.0                        1.0   \n",
       "4                           1.0                        0.0   \n",
       "...                         ...                        ...   \n",
       "6361                        0.0                        0.0   \n",
       "6362                        0.0                        1.0   \n",
       "6363                        0.0                        0.0   \n",
       "6364                        1.0                        0.0   \n",
       "6365                        1.0                        0.0   \n",
       "\n",
       "      C(occupation_husb)[T.6.0]  rate_marriage   age  yrs_married  children  \\\n",
       "0                           0.0            3.0  32.0          9.0       3.0   \n",
       "1                           0.0            3.0  27.0         13.0       3.0   \n",
       "2                           0.0            4.0  22.0          2.5       0.0   \n",
       "3                           0.0            4.0  37.0         16.5       4.0   \n",
       "4                           0.0            5.0  27.0          9.0       1.0   \n",
       "...                         ...            ...   ...          ...       ...   \n",
       "6361                        0.0            5.0  32.0         13.0       2.0   \n",
       "6362                        0.0            4.0  32.0         13.0       1.0   \n",
       "6363                        0.0            5.0  22.0          2.5       0.0   \n",
       "6364                        0.0            5.0  32.0          6.0       1.0   \n",
       "6365                        0.0            4.0  22.0          2.5       0.0   \n",
       "\n",
       "      religious  educ  \n",
       "0           3.0  17.0  \n",
       "1           1.0  14.0  \n",
       "2           1.0  16.0  \n",
       "3           3.0  16.0  \n",
       "4           1.0  14.0  \n",
       "...         ...   ...  \n",
       "6361        3.0  17.0  \n",
       "6362        1.0  16.0  \n",
       "6363        2.0  14.0  \n",
       "6364        3.0  14.0  \n",
       "6365        2.0  16.0  \n",
       "\n",
       "[6366 rows x 17 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = X.rename(columns =\n",
    "{'C(occupation)[T.2.0]':'occ_2',\n",
    "\n",
    "'C(occupation)[T.3.0]':'occ_3',\n",
    "'C(occupation)[T.4.0]':'occ_4',\n",
    "'C(occupation)[T.5.0]':'occ_5',\n",
    "'C(occupation)[T.6.0]':'occ_6',\n",
    "'C(occupation_husb)[T.2.0]':'occ_husb_2',\n",
    "'C(occupation_husb)[T.3.0]':'occ_husb_3',\n",
    "'C(occupation_husb)[T.4.0]':'occ_husb_4',\n",
    "'C(occupation_husb)[T.5.0]':'occ_husb_5',\n",
    "'C(occupation_husb)[T.6.0]':'occ_husb_6'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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>Intercept</th>\n",
       "      <th>occ_2</th>\n",
       "      <th>occ_3</th>\n",
       "      <th>occ_4</th>\n",
       "      <th>occ_5</th>\n",
       "      <th>occ_6</th>\n",
       "      <th>occ_husb_2</th>\n",
       "      <th>occ_husb_3</th>\n",
       "      <th>occ_husb_4</th>\n",
       "      <th>occ_husb_5</th>\n",
       "      <th>occ_husb_6</th>\n",
       "      <th>rate_marriage</th>\n",
       "      <th>age</th>\n",
       "      <th>yrs_married</th>\n",
       "      <th>children</th>\n",
       "      <th>religious</th>\n",
       "      <th>educ</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>17.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>14.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>16.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>37.0</td>\n",
       "      <td>16.5</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>16.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>14.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6361</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>17.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6362</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>16.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6363</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>14.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6364</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>14.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6365</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>16.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6366 rows × 17 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Intercept  occ_2  occ_3  occ_4  occ_5  occ_6  occ_husb_2  occ_husb_3  \\\n",
       "0           1.0    1.0    0.0    0.0    0.0    0.0         0.0         0.0   \n",
       "1           1.0    0.0    1.0    0.0    0.0    0.0         0.0         0.0   \n",
       "2           1.0    0.0    1.0    0.0    0.0    0.0         0.0         0.0   \n",
       "3           1.0    0.0    0.0    0.0    1.0    0.0         0.0         0.0   \n",
       "4           1.0    0.0    1.0    0.0    0.0    0.0         0.0         0.0   \n",
       "...         ...    ...    ...    ...    ...    ...         ...         ...   \n",
       "6361        1.0    0.0    0.0    1.0    0.0    0.0         0.0         1.0   \n",
       "6362        1.0    0.0    0.0    0.0    1.0    0.0         0.0         0.0   \n",
       "6363        1.0    0.0    1.0    0.0    0.0    0.0         0.0         0.0   \n",
       "6364        1.0    0.0    1.0    0.0    0.0    0.0         0.0         0.0   \n",
       "6365        1.0    1.0    0.0    0.0    0.0    0.0         0.0         0.0   \n",
       "\n",
       "      occ_husb_4  occ_husb_5  occ_husb_6  rate_marriage   age  yrs_married  \\\n",
       "0            0.0         1.0         0.0            3.0  32.0          9.0   \n",
       "1            1.0         0.0         0.0            3.0  27.0         13.0   \n",
       "2            0.0         1.0         0.0            4.0  22.0          2.5   \n",
       "3            0.0         1.0         0.0            4.0  37.0         16.5   \n",
       "4            1.0         0.0         0.0            5.0  27.0          9.0   \n",
       "...          ...         ...         ...            ...   ...          ...   \n",
       "6361         0.0         0.0         0.0            5.0  32.0         13.0   \n",
       "6362         0.0         1.0         0.0            4.0  32.0         13.0   \n",
       "6363         0.0         0.0         0.0            5.0  22.0          2.5   \n",
       "6364         1.0         0.0         0.0            5.0  32.0          6.0   \n",
       "6365         1.0         0.0         0.0            4.0  22.0          2.5   \n",
       "\n",
       "      children  religious  educ  \n",
       "0          3.0        3.0  17.0  \n",
       "1          3.0        1.0  14.0  \n",
       "2          0.0        1.0  16.0  \n",
       "3          4.0        3.0  16.0  \n",
       "4          1.0        1.0  14.0  \n",
       "...        ...        ...   ...  \n",
       "6361       2.0        3.0  17.0  \n",
       "6362       1.0        1.0  16.0  \n",
       "6363       0.0        2.0  14.0  \n",
       "6364       1.0        3.0  14.0  \n",
       "6365       0.0        2.0  16.0  \n",
       "\n",
       "[6366 rows x 17 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "xtrain, xtest, ytrain, ytest = train_test_split(X, y, test_size=0.2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\bhatt\\Desktop\\ml\\env\\lib\\site-packages\\sklearn\\utils\\validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
      "  return f(**kwargs)\n",
      "C:\\Users\\bhatt\\Desktop\\ml\\env\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0.7488226059654631"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = LogisticRegression()\n",
    "model.fit(xtrain, ytrain)\n",
    "model.score(xtest, ytest)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}