Predicting_Negative_Positive_Emotions.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# **Predicting Changes in Positive and Negative Emotions from Coronavirus-related Variables**\n",
    "Lindsay Warrenburg  \n",
    "lindsay.a.warrenburg@gmail.com  \n",
    "Final version: December 22, 2020\n",
    "\n",
    "### This script describes Step 1 of investigating individual differences in lockdown situations and music-related behaviors.\n",
    "\n",
    "- A series of linear regression analyses was conducted to examine the degree to which the pandemic and lockdown measures influenced emotions\n",
    "- Changes in *Negative Emotions* and *Positive Emotions* are the dependent variables\n",
    "- Three different sets of predictors were used: (1) Contact with the COVID-19 Virus, (2) Work Situation due to the Pandemic, and (3) Living Situation during the Pandemic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np, pandas as pd, os, sys, seaborn as sns, warnings, matplotlib.pyplot as plt, statsmodels.api as sm\n",
    "from statsmodels.stats.outliers_influence import variance_inflation_factor\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.max_rows', None)\n",
    "%matplotlib inline\n",
    "plt.rcParams['figure.figsize'] = (14,4)\n",
    "warnings.filterwarnings(action='ignore')\n",
    "%run Coronavirus_Music_Functions.ipynb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5113, 240)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_data = pd.read_csv('factors_all_data.csv') \n",
    "all_data.rename(columns={'Demographics_General_Gender': 'Gender'}, inplace=True)\n",
    "all_data.columns = all_data.columns.str.replace(r'^.*_', '', regex=True)\n",
    "all_data.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Pre-processing\n",
    "\n",
    "### Impute missing values in the emotion variables with the median value for that variable, with regard to that person's country"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "neg_emotions = ['Depressed','Stressed','Anxious','Negative Valence','Lonely']\n",
    "pos_emotions = ['Positive Valence','Arousal','General Health']\n",
    "all_emotions = neg_emotions + pos_emotions\n",
    "\n",
    "normalize_column = 'Country'\n",
    "\n",
    "for i, column in enumerate(all_emotions):\n",
    "    all_data[column] = all_data.groupby(normalize_column, sort = False)[column].apply(lambda x: x.fillna(x.median()))\n",
    "    \n",
    "all_data.reset_index(inplace = True, drop = True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Create lists of corona-virus related variables that we will use as the regression predictors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "living = [c for c in all_data.columns if c.startswith('Living Situation') and 'No Response' not in c]\n",
    "work = [c for c in all_data.columns if c.startswith('Ways Work Affected') and 'No Response' not in c]\n",
    "covid = [c for c in all_data.columns if c.startswith('Infected with COVID') and 'No Response' not in c]\n",
    "\n",
    "col_list = living + work + covid\n",
    "\n",
    "all_X = all_data.loc[:,col_list]\n",
    "all_X.reset_index(inplace = True, drop = True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# **Changes in Negative Emotions**\n",
    "\n",
    "The DV is the average of the variables referring to changes in the negative emotions during the coronavirus crisis:\n",
    "- Depression\n",
    "- Stress\n",
    "- Anxiety\n",
    "- Negative Valence\n",
    "- Loneliness"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# create average score of all negative emotions\n",
    "y = (all_data.loc[:,neg_emotions]).mean(skipna=True,axis=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Contact with the COVID-19 Virus"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkoAAAIDCAYAAAD7dDE9AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAABa6UlEQVR4nO3dd5xcdb3/8dc7AZQaei+hRJAaaYJgAQEFC6AoIHIBC+pVQb16xQ7+vIoXFesVIgqoSFFEUFGiKCDSa0JVBBQEpYiAgCjJ+/fH+Q6ZLDO7s5vdPWc27yeP88ic72mfmYSdz36rbBMRERERzzSp7gAiIiIimiqJUkREREQXSZQiIiIiukiiFBEREdFFEqWIiIiILpIoRURERHSxSN0BxISWuSciIppDdQfQj1KjFBEREdFFEqWIiIiILpIoRURERHSRRCkiIiKiiyRKEREREV0kUYqIiIjoIolSRERERBdJlCIiIiK6SKIUERER0UUSpYiIiIgukihFREREdJFEKSIiIqKLJEoRERERXSRRioiIiOgiiVJEREREF0mUIiIiIrpIohQRERHRRRKliIiIiC6SKI2QpH8McmxvSZa00QI+42BJX+3hvGMk3SjpmBE848NjFVdERES/S6I0NvYHLgb2G6fnvQ3Y0vYHRnDtsBOliIiIhUUSpVEmaSlgB+DNtCVKkl4i6UJJZ0j6naSjJR0g6QpJsyWtP8R9T5L0ZUmXSLpd0j6l/BxgSeBySftKWknSmZKuLNsOrbgknVieNUvSayUdDSwu6TpJp5Tz3lhiuk7S8ZIml/JDStwXlvcXEREx4SVRGn17AT+3/Tvgb5K2bDu2BXA4sBlwIPAc29sCJwDv7uHeqwE7Aq8Ejgaw/WrgCdvTbZ8OfAk41vY2wGvLvQE+BjxsezPbmwO/sn1E27UHSHousC+wg+3pwBzgAEmrAUdRJUi7Aht3C1DSoZKuknTVjBkzenhLERERzbVI3QFMQPsDXyyvTyv715T9K23fCyDpD8DMUj4b2KmHe//I9lzgJkmrdDlnF2BjSa39ZSQtXcqfruGy/VCHa18KbAVcWa5fHLgPeD5wge37S+ynA8/p9HDbM4BWhuQe3lNERERjJVEaRZJWAHYGNpVkYDJgSf9dTnmy7fS5bftz6e3vov16dTlnErC97ScGxCaGTlwEnGz7QwOu3auHayMiIiacNL2Nrn2Ab9tex/ZU22sBd1A1l42XmcC7WjuSpncpX668/LekRcvr84F9JK1czlle0jrA5cBLJK1Qzn3d2L6FiIiIZkiiNLr2B84aUHYm8IZxjOEwYOvSYfsm4O2l/FPAcpJukHQ985r6ZgCzJJ1i+ybgo8BMSbOAXwCrlebCI4FLgV8yrykxIiJiQpOdFpUYM/nHFRHRHN26bMQgUqMUERER0UUSpYiIiIgukihFREREdJFEKSIiIqKLJEoRERERXSRRioiIiOgiiVJEREREF0mUIiIiIrpIohQRERHRRRKliIiIiC6SKEVERER0kUQpIiIiooskShERERFdJFGKiIiI6CKJUkREREQXSZQiIiIiukiiFBEREdHFInUHEBPbI/fcW3cIPVtm9dXqDiEiIhomNUoRERERXSRRioiIiOgiiVJEREREF0mUIiIiIrpIohQRERHRRRKliIiIiC6SKEVERER0kUQpIiIiooskShERERFdJFGKiIiI6CKJUkREREQXSZQiIiIiukiiFBEREdFFEqWIiIiILpIoRURERHSRRCkiIiKiiyRKEREREV00MlGS9I9Bju0tyZI2WsBnHFzu89IO995nQe7d4/MvGeX7fUnSnyV1/DuV9BJJPxnNZ0ZEREx0jUyUhrA/cDGw3yjca3a5X8t+wPWjcF8kLTLYcdsvGI3nlGdNAvYG7gJeNFr3jYiIWNj1VaIkaSlgB+DNtCVKpbbkQklnSPqdpKMlHSDpCkmzJa3f5Za/AbaVtGi59wbAdW33famka8s9viXpWaX8TkkrltdbS7qgvD5S0gxJM4Fvl/1vSbpA0u2SDmu79z/aYr9A0g8k3SLpFEkqx/YoZRdL+vIgNUI7ATcAX2f+xK+Xz3T/8v5ukPTZUjZZ0kmlbLak95bywyTdJGmWpNOG85yIiIh+1FeJErAX8HPbvwP+JmnLtmNbAIcDmwEHAs+xvS1wAvDuLvcz8EvgZcCewDmtA5KeDZwE7Gt7M2AR4B09xLgVsKftN5T9jcr9twU+IWnRDtc8D3gPsDGwHrBDef7xwO62dwRWGuSZ+wOnAmcBr+zyjGeQtDrwWWBnYDqwjaS9yus1bG9a3vuJ5ZIjgOfZ3hx4ey/PiIiI6FWpXLhP0g1djqtUHNxWfmnfsu3YyyXdWo4dMVox9VuitD/Qqsk4jflrT660fa/tJ4E/ADNL+Wxg6iD3PI2qdmo/qmSjZUPgjpKUAZxMb81a59h+om3/p7aftP0AcB+wSodrrrB9t+25VDVaU6kSrNtt31HOObXDdUhaDNgD+JHtR4DLgd16iBNgG+AC2/fbfgo4heo93g6sJ+krkl4OPFLOnwWcIumNwFNd4jlU0lWSrpoxY0aPYURERABVBcXLBzm+OzCtbIdStaQgaTLwtXJ8Y2B/SRuPRkCD9qNpEkkrUNV8bCrJwGTAkv67nPJk2+lz2/bnMsj7tH2FpE2BJ2z/rrR6AajbNVRJQivJfPaAY48N2G+Pa06XWDqdM9jz270cmALMLrEvATwO/LSHazs+w/ZDkragqgl7J/B64E3AK6gSqVcDH5O0SUmw2q+dAbQyJD9yz709vo2IiFjY2b5I0tRBTtkT+LZtA5dJWlbSalQVDLfZvh2gdA/ZE7hpQWPqpxqlfag+nHVsT7W9FnAHsOMo3PtDwIcHlN0CTJW0Qdk/ELiwvL6TqokN4LWj8PxObqGq1Zla9vftct7+wFvKZzIVWBfYTdISPTzjcuDFklYs2fj+wIWl/9Uk22cCHwO2LB3G17L9a+C/gWWBpUb21iIiIkZkDaqBSy13l7Ju5Qusb2qUqL7Ejx5QdibwBuD0Bbmx7Z91KPunpEOA75cRbFcCx5XDRwHflPRhqmRj1Nl+QtJ/Aj+X9ABwxcBzSjL0MuBtbdc9Juli4FU883N5qaS72/ZfR5Uk/pqqdulc22eX2qQT26Ya+BBVDd53JU0p5x5r+++j8FYjIqKP/X7Hl7nXc5/z25lvo2oya5lRWiJ61aklxIOULzBVtVfRRJKWsv2PMgrua8DvbR9bd1zD0FdNb8usvlrdIUREjKVeu3QMy+9fuHvPicS03/xsyBhKS8pPbG/a4djxVH1rTy37twIvoWp6O9L2y0r5hwBsf6bX2Lrpp6a3hdFbJV0H3EjVD+n4esOJiIgYQOp9W3DnAP9RRr9tBzxs+16qVp9pktYtg5z2o20k+4Lop6a3hU6pPeqnGqSIiFjYTBq9iipJp1LVEK1Yuop8AlgUwPZxwLlUI71voxq4dEg59pSkdwHnUXUV+ZbtG0cjpiRKERERMWJdVs4aEduDTppcRru9s8uxc6kSqVGVRCkiIiJGbvLE7sWTRCkiIiJGblISpYiIiIjORqeTdmMlUYqIiIgRUxKliIiIiC7S9BYRERHRRTpzR0RERHQxitMDNFESpYiIiBgxjeKEk02URCkiIiJGLp25IyIiIrpI01tEREREF2l6i4iIiOhMkyfXHcKYSqIUERERI5c+ShEjt8zqq9UdQkREjKVMOBkRERHRRWqUIkbuoRtuqjuEni236cY8fMeddYfRsynrTq07hIiIJEoRERER3ShNbxERERFdTPC13ib2u4uIiIixpUm9b73cTnq5pFsl3SbpiA7HPyDpurLdIGmOpOXLsTslzS7HrhqNt5capYiIiBi5UZxwUtJk4GvArsDdwJWSzrH9dIdX28cAx5TzXwW81/bf2m6zk+0HRium1ChFRETEyEm9b0PbFrjN9u22/wWcBuw5yPn7A6eOwrvoKolSREREjJg0qeetB2sAd7Xt313KOjxXSwAvB85sKzYwU9LVkg4d4VuaT5reIiIiYuSG0Zm7JC/tCcwM2zPaT+lwmbvc7lXAbwc0u+1g+x5JKwO/kHSL7Yt6DrCDJEoRERExcsOYHqAkRTMGOeVuYK22/TWBe7qcux8Dmt1s31P+vE/SWVRNeQuUKKXpLSIiIkZudPsoXQlMk7SupMWokqFznvlITQFeDJzdVrakpKVbr4HdgBsW9O2lRikiIiJGTKM46s32U5LeBZwHTAa+ZftGSW8vx48rp+4NzLT9WNvlqwBnqUrIFgG+Z/vnCxpTEqWIiIgYuR7nR+qV7XOBcweUHTdg/yTgpAFltwNbjGowJFGKiIiIBZG13iIiIiK6mDy57gjGVBKliIiIGLHR7KPUREmUIiIiYuTS9BYRERHRxTDmUepHSZQiIiJi5CZ4jdKQaaCkf/RSLulgSV8drcA6PO8lkh6WdK2kmyV9YpjXryTp8nL9C0chnq0lfXlB79PhvndKWrFD+VKSjpf0B0k3SrpI0vNH+IyDJa0+wmunSnrDSK6NiIiJR5Mn97z1o36rL/uN7ecBWwNvlLRV+0FJg9WQvRS4xfbzbP9mQQOxfZXtwxb0PsNwAvA3YJrtTYCDgWckVD06GBhRogRMBZIoRUREZXRn5m6cMUmUJL2qrfbml5JWkTSp1JYs23bebeXYSpLOlHRl2XYY7P5lJs6rgfUlHSlphqSZwLclrSPpfEmzyp9rS5oO/C+wh6TrJC0uaTdJl0q6RtL3JS1VYjpa0k3l+s+VstdJukHS9ZIuKmUvkfST8np5ST8q11wmafNSfqSkb0m6QNLtkp5OrMr5V5faoUFXOJa0PvB84KO255bP4HbbPy3H31fiu0HSe0rZ1FLz9o3yjJnlfe9DlWie0vZZfLx87jeUz1LlHhuUv7/ry+e0PnA08MJy7XuH/tcQERET2iT1vvWhBUmUFi9fltdJug74ZNuxi4HtSu3PacB/ly/4s6mmHac0G91p+6/Al4BjbW8DvJaq9qQrSSsA2wE3lqKtgD1tvwH4KvBt25sDpwBftn0d8HHgdNvTgSWBjwK72N4SuAp4n6TlS3yblOs/Ve7/ceBltrcAXt0hpKOAa8s1Hwa+3XZsI+BlVAvzfULSoqX8Tba3okpaDivvqZtNgOtsz+nwWWwFHEKVSG0HvFXS88rhacDXSg3U34HX2v5Beb8H2J5u+wngq7a3sb0psDjwynL9KeX6LYAXAPcCR1DV7E23fewgMUdExMJAk3rf+tCCRP1E+bKcXpKPj7cdWxM4T9Js4ANUX/QApwP7ltf7lX2AXYCvloTrHGAZlYXtBnihpGuBmcDRtluJ0jnlCx9ge+B75fV3gB073Gc7YGPgt+WZBwHrAI8A/wROkPQa4PFy/m+BkyS9lWrtmYF2LM/C9q+AFVQt2AfwU9tP2n4AuI9qLRqokqPrgcuoVkqe1uG+vdgROMv2Y7b/AfwQaPXBuqMkiVDVwE3tco+dSg3gbGBnYJPy+a9h+6zyvv5p+/Eu1z9N0qGSrpJ01YwZgy0QHRERE8IEr1Eaq1FvXwG+YPscSS8BjizllwIbSFoJ2It5NTaTgO3bkp1ufmP7lR3KH+tQ1uIOZQJ+YXv/ZxyQtqXqz7Qf8C5gZ9tvLzVgrwCuK015A+/X7blPtpXNARYpn8kuVO/5cUkXAM8e5D3cCGwhaVKr6W2IZ7cMfPbiA0+Q9Gzg/4Ctbd8l6cgSy4j+RdueAbQyJD90w00juU1ERPSLPu171KuxqgebAvy5vD6oVWjbwFnAF4CbbT9YDs2kSkoA6JCIDMclVEkOwAFUzYADXQbsIGmD8rwlJD2n9FOaUhbkew8wvRxf3/bltj8OPEBVA9TuovIsShL0gO1HBolxCvBQSZI2oqrh6sr2H6iay45q6z80TdKe5dl7lfewJFXT4VCd1R8FWjV2rQTtgfL+9ynPfAS4W9Je5XnPkrTEgGsjImIhl1FvI3Mk8H1Jv6FKLNqdDryRec1uAIcBW5fO0DcBb1+AZx8GHCJpFnAgcPjAE2zfTzXy69Ry3mVUfYmWBn5Syi4EWp2Vj5E0W9INVInJ9QNueWQrfqrOzgcxuJ9T1SzNAv5fef5Q3gKsCtxWmsi+Adxj+xqqFZSvAC4HTrB97RD3Ogk4rjQ7PlnuNRv4EXBl23kHUjURzqJKQFcFZgFPlQ7e6cwdEbGwm+Cj3lRV8kSMib5qeltu0415+I476w6jZ1PWnVp3CBHRX8YkU/nzZ7/YcyKxxgff03fZUmbmjoiIiJHr05qiXiVRioiIiBFTn45m61USpYiIiBi5Pp0fqVcT+91FRETE2Jo8qfetB5JeLulWVat3HNHheGvt19ak1x/v9dqRSI1SREREjNwo1ihJmgx8DdgVuBu4UtI5tgeODHrGvIrDuHZYUqMUERERI6ZJ6nnrwbbAbWU9039RLYO2Z4+hLMi1XSVRioiIiJEb3XmU1gDuatu/u5QNtH2Zz+9nklrLpPV67bCk6S0iIiJGblLvdS6SDgUObSuaUZa+evqUDpcNnKfpGmAd2/+QtAfVZMnTerx22JIoRURExMgNY2mSAeuBdnI38y8TtiZwz4B7PNL2+lxJ/ydpxV6uHYk0vUVERMSIjXIfpSuBaZLWlbQY1dqt58z3PGnVtnVPt6XKZR7s5dqRSI1SREREjNwojnqz/ZSkdwHnAZOBb9m+UdLby/HjqBZvf4ekp4AngP1crcfW8doFjSmJUkRERIzcKC9hYvtc4NwBZce1vf4q8NVer11QSZQiIiJi5LKESUREREQXE3wJkyRKERERMWLqcWmSfpVEKSIiIkZuGPMo9aMkSjGmltt047pDGJYp606tO4SIiP4yyp25myaJUkRERIxcEqWIkXtg5q/qDqFnK+62Mw//8U91h9GzKeusDcBDs26oOZLeLbf5pnWHEBGjTGl6i4iIiOgiNUoRERERXQxjrbd+lEQpIiIiRi4TTkZERER0pjS9RURERHSRmbkjIiIiukjTW0REREQX6cwdERER0UX6KEVERER0pjS9RURERHSRztwRERERXaRGKSIiIqKLCd5HaWLXl0VERMSY0uTJPW893U96uaRbJd0m6YgOxw+QNKtsl0jaou3YnZJmS7pO0lWj8f5SoxQREREjN4o1SpImA18DdgXuBq6UdI7tm9pOuwN4se2HJO0OzACe33Z8J9sPjFZMSZQiIiJi5CaNauPUtsBttm8HkHQasCfwdKJk+5K28y8D1hzNAAZK01tERESMnNTzJulQSVe1bYcOuNsawF1t+3eXsm7eDPysbd/ATElXd7j3iPRVoiTpH72WS3q7pP9YwOctK+lBlRX/JG0vyZLWLPtTJP1N0iRJ55bzl5X0n233eImkn/TwrO0kXV7aVW+WdOSCxB4RETEuJqnnzfYM21u3bTMG3K1TO547PVbSTlSJ0gfbinewvSWwO/BOSS9a4Le3oDdoKtvH2f72At7j78BfgOeWohcA15Y/AbYDLrc91/Ye5fxlgf9k+E4GDrU9HdgUOGPEgUdERIwTaVLPWw/uBtZq218TuOeZz9TmwAnAnrYfbJXbvqf8eR9wFlVT3gKZsImSpCMlvV/ScyVd0VY+VdKs8norSReWKrrzJK3W4Va/ZV5i9ALg2AH7l5R73SlpReBoYP1SM3RMOW8pST+QdIukU1o1VAOsDNwLYHtOq+OapOUl/aj07r+s/ONovb+TJc0sz36NpP8tvf1/LmnRwd6jpOnlfrMknSVpuVJ+gaTPSrpC0u8kvbCUT5Z0jKQryzVvG/7fSkRETDiTJ/W+De1KYJqkdSUtBuwHnNN+gqS1gR8CB9r+XVv5kpKWbr0GdgNuWNC3N2ETpRbbNwOLSVqvFO0LnFESia8A+9jeCvgW8D8dbnEJ8xKj9YDvA1uX/RdQJVLtjgD+YHu67Q+UsucB7wE2LvfYocNzjgVuLUnL2yQ9u5QfBVxre3Pgw0B7Ldn6wCuoOrp9F/i17c2AJ4BXDPEevw18sNx3NvCJtvsuYnvbEnOr/M3Aw7a3AbYB3ipp3Q7vIyIiFiaa1Ps2BNtPAe8CzgNuBs6wfWPpTvP2ctrHgRWA/xswDcAqwMWSrgeuAH5q++cL+vYWllFvZwCvp6rt2bdsG1I1cf2iVPBMptToDPBb4IiSFNxp+5+qLAVsRfWXMZQrbN8NIOk6YCpwcfsJtj8p6RSqDPgNwP7AS4AdgdeWc34laQVJU8plP7P9b0mzS/ytfxCzyzM6vsdy/bK2Lyznn0yVALb8sPx5dbkPJa7NJe1T9qcA06iGaT6tdJ47FOD444/nNVM36OHjiYiIvjXKM3PbPhc4d0DZcW2v3wK8pcN1twNbDCxfUAtLonQ68H1JPwRs+/eSNgNutL39YBeWc5cDXgVcWoqvBg4B7rDdsYP5AE+2vZ5Dl8/d9h+Ar0v6BnC/pBUYvGPbk+W6uZL+bbtVPrc8Q3R4j22J1lDxtscq4N22zxvswtIxr9U5zw/M/NUQj4qIiH7WuTfJxDHhm97g6QRkDvAxqqQJ4FZgJUnbA0haVNImXW5xKXA48xKlS6mapS7pcO6jwNLDjVHSK9r6Lk0r8f4duAg4oJzzEuAB24/0eNuO79H2w8BDrf5HwIHAhd1uUpwHvKOt79NzShtwREQszCZN6n3rQxOlRmkJSXe37X+hwzmnA8cA6wLY/ldpRvpyqWFZBPgicGOHa38L7AG02kEvpepr9IxEyfaDkn4r6QaquR1+2uN7OBA4VtLjwFPAAbbnlGkCTiwd0B8HDurxfkO9x4OA4yQtAdxOVUM2mBOomuGuKQnd/cBevcYSERETVJ8mQL3SvNaaiFHXV01vK+62Mw//8U91h9GzKeusDcBDsxZ4UMe4WW7zTesOIWJhNiZtZA/dcFPPicRym27cd+10E6VGKSIiImow0fsoJVGKiIiIkRvlUW9Nk0QpIiIiRq63Gbf7VhKliIiIGLnUKEVERER0MWly3RGMqSRKERERMWJKjVJEREREFxn1FhEREdHFBJ9wMolSREREjFxqlCIiIiI60+R05o6IiIjoLDVKEREREV1k1FtEREREF5mZOyIiIqKLCV6jNLHTwIiIiBhTknreerzfyyXdKuk2SUd0OC5JXy7HZ0nastdrRyKJUkRERIzc5Mm9b0OQNBn4GrA7sDGwv6SNB5y2OzCtbIcCXx/GtcOWRCkiIiJGTup9G9q2wG22b7f9L+A0YM8B5+wJfNuVy4BlJa3W47XDlj5KMaZW3G3nukMYlinrrF13CMO23Oab1h1CRCzMhjEzt6RDqWqBWmbYntG2vwZwV9v+3cDzB9ym0zlr9HjtsCVRijF145331B1CzzaZunrfxQtwzW13DXFmc2y5wVpA//27iIjuPIx5lEpSNGOQUzrdzD2e08u1w5ZEKSIiIkZsztxRvd3dwFpt+2sCA3+z6nbOYj1cO2zpoxQREREj5mH814MrgWmS1pW0GLAfcM6Ac84B/qOMftsOeNj2vT1eO2ypUYqIiIgRmzN3gVu3nmb7KUnvAs4DJgPfsn2jpLeX48cB5wJ7ALcBjwOHDHbtgsaURCkiIiJGzB69RKnc71yqZKi97Li21wbe2eu1CyqJUkRERIzY3FFOlJomiVJERESM2ATPk5IoRURExMiNdtNb0yRRioiIiBEbzc7cTZREKSIiIkYsNUoRERERXaQzd0REREQXEztNSqIUERERCyA1ShERERFdpI9SRERERBcZ9RYRERHRRWqUIiIiIrqY4HlSEqWIiIgYuYnemXtS3QHE2JFkSZ9v23+/pCNrDCkiIiYY2z1v/SiJ0sT2JPAaSSvWHUhERExMc9371o+SKE1sTwEzgPcOPCBpHUnnS5pV/ly7lJ8k6cuSLpF0u6R92q75gKQryzVHjd/biIiIpprruT1v/SiJ0sT3NeAASVMGlH8V+LbtzYFTgC+3HVsN2BF4JXA0gKTdgGnAtsB0YCtJLxrb0CMioulSoxR9zfYjwLeBwwYc2h74Xnn9HarEqOVHtufavglYpZTtVrZrgWuAjagSp/lIOlTSVZKumjFjxui9kYiIaKSJ3kcpo94WDl+kSm5OHOSc9n/BT7a9Vtufn7F9/GAPsj2DqrkPwDfeec/wIo2IiL4yXgmQpOWB04GpwJ3A620/NOCctagqB1YF5gIzbH+pHDsSeCtwfzn9w7bPHeq5qVFaCNj+G3AG8Oa24kuA/crrA4CLh7jNecCbJC0FIGkNSSuPdqwREdFf5to9bwvoCOB829OA88v+QE8B/2X7ucB2wDslbdx2/Fjb08s2ZJIESZQWJp8H2ke/HQYcImkWcCBw+GAX255J1VR3qaTZwA+Apcco1oiI6BNz5rrnbQHtCZxcXp8M7DXwBNv32r6mvH4UuBlYY0Eemqa3Ccz2Um2v/wos0bZ/J7Bzh2sOHuQeXwK+NAahRkREnxrHvker2L63PPPeoVo1JE0Fngdc3lb8Lkn/AVxFVfP0UKdr26VGKSIiIkbM7n1rH/BTtkPb7yXpl5Ju6LDtOZyYSjeRM4H3lEFNAF8H1qcauX0vVUvLkFKjFBERESM2nL5HAwb8dDq+S7djkv4qabVSm7QacF+X8xalSpJOsf3Dtnv/te2cbwA/6SXm1ChFRETEiHkY/y2gc4CDyuuDgLMHniBJwDeBm21/YcCx1dp29wZu6OWhSZQiIiJixIbT9LaAjgZ2lfR7YFfmTYi8uqTWCLYdqAYo7SzpurLtUY79r6TZZRDTTnRYtaKTNL1FRETEiM2ZOz5Lk9h+EHhph/J7gD3K64uZN//fwPMOHMlzkyhFRETEiPXr0iS9SqIUERERI9avS5P0KolSREREjFgSpYiIiIgu0vQWERER0UVqlCIiIiK6mJNEKSIiIqKz1ChFREREdDGcJUz6URKliIiIGLEJniclUYqIiIiRS9NbRERERBfjtYRJXTTRM8GoVf5xRUQ0R8c10BbUGRdf3/PP+tfvuMWYxDCWUqMUERERIzbRK1ySKMWYuu9vf687hJ6tvPyy3P/Qw3WH0bOVlpsCwF8efKjmSHq36grLAfTd53zrXX+pO4yebbjWqnWHEAuZJEoRERERXUzsHkpJlCIiImIBpEYpIiIioos5E3xV3CRKERERMWKpUYqIiIjoYryWMJG0PHA6MBW4E3i97WeMZpF0J/AoMAd4yvbWw7l+oEmjEXxEREQsnOzetwV0BHC+7WnA+WW/m51sT28lSSO4/mlJlCIiImLEbPe8LaA9gZPL65OBvcbj+jS9RURExIiNY2fuVWzfC2D7XkkrdznPwExJBo63PWOY188niVJERESM2HD6KEk6FDi0rWhGWyKDpF8CnWZN/cgwQtrB9j0lEfqFpFtsXzSM6+eTRCkiIiJGbDiJUkmKZgxyfJduxyT9VdJqpTZoNeC+Lve4p/x5n6SzgG2Bi4Cerh8ofZQiIiJixMaxj9I5wEHl9UHA2QNPkLSkpKVbr4HdgBt6vb6TJEoRERExYuM46u1oYFdJvwd2LftIWl3SueWcVYCLJV0PXAH81PbPB7t+KGl6i4iIiBEbr3mUbD8IvLRD+T3AHuX17cAWw7l+KEmUIiIiYsTGK1GqSxKliIiIGLEkShERERFdZK23iIiIiC4meo3SQjfqTdIcSddJukHS9yUtMczrj5F0o6RjRvj8qZIs6d1tZV+VdPAQ1x0safUO5V8r7+cmSU+U19dJ2meI+y0h6RRJs8tncbGkpUbyniIiYuE1jqPearEw1ig9YXs6gKRTgLcDX2gdlDTZ9pxBrn8bsJLtJ3t5mKRFbD81oPg+4HBJx9v+V49xH0w1F8Q97YW231meMxX4Seu99eBw4K+2NyvXbwj8u8drIyIigInf9LbQ1SgN8BtgA0kvkfRrSd8DZkuaXGqOrpQ0S9LbACSdAywJXC5pX0krSTqznHelpB3KeUdKmiFpJvDtDs+9n2rl4oMGHpA0XdJl5blnSVqu1A5tDZxSaosWH+xNSVpe0o/KPS6TtHmH01YD/tzasX1rK/kr115das4OLWVvlnRs2zPeKukLz7hrREQsVObMdc9bP1poEyVJiwC7A7NL0bbAR2xvDLwZeNj2NsA2wFslrWv71ZQaKdunA18Cji3nvRY4oe0RWwF72n5DlxCOBv5L0uQB5d8GPmh78xLbJ2z/ALgKOKA8+4kh3t5RwLXlHh+mc7L2LeCDki6V9ClJ09qOvcn2VlTJ2WGSVgBOA14tadFyziHAiQNvKulQSVdJumrGjK6z1EdExAQxjjNz12JhbHpbXNJ15fVvgG8CLwCusH1HKd8N2Lytn88UYBpwB/PbBdhYUmt/mdbU6cA5gyU0tu+QdAXwdCIlaQqwrO0LS9HJwPeH+f4AdqRK3LD9K0krSJpi++G2518nab3yXncBrpS0ve2bqZKjvcupawHTbF8m6VfAKyXdDCxqezYDDFjHx/f97e8jCD8iIvrFRO/MvTAmSk/3UWopic5j7UXAu22fN8S9JgHbD0yIOtyvm08DP6BarG80qUPZM/4l2/4H8EPgh5LmAntIWoUqcdre9uOSLgCeXS45gaqG6hY61CZFRMTCZ2KnSQtx09sQzgPe0WpmkvScsrjeQDOBd7V2JE0fzkNs3wLcBLyy7D8MPCTpheWUA4FW7dKjwNLPuElnFwEHlJheAjxg+5H2EyTtIGm58noxYGPgj1S1Zw+VJGkjYLu2eC+nqmF6A3DqcN5rRERMTHPtnrd+tDDWKPXiBGAqcI2q6qH7gb06nHcY8DVJs6g+y4uoRtENx/8A17btHwQcV6YtuJ2qLxDASaX8CTrUYg1wJHBiietxOnQaB9YHvl7e3yTgp8CZwGLA28u1twKXDbjuDGC67Yd6focRETFhze3TTtq9Ur92rop6SPoJVQf283s4va/6KK28/LLc/9DDQ5/YECstNwWAvzzYPznrqissB9B3n/Otd/2l7jB6tuFaq9YdQjRXp24ZC+yj35vZcyLxqTfsNiYxjKU0vUVPJC0r6XdUfbx6SZIiImIhkFFvEYDtvwPPqTuOiIholj7Nf3qWRCkiIiJGrF87afcqiVJERESMWL82qfUqiVJERESM2JwJniilM3dERESM2Hh15i7rmP5C0u/Ln8t1OGfDsiZqa3tE0nvKsSMl/bnt2B69PDeJUkRERIzYXPe+LaAjgPNtT6NaWP6IgSeUBd6nlxU4tqKaS/CstlOObR23fW4vD02iFBERESM2jtMD7Em1Birlz72GOP+lwB9s/3FBHppEKSIiIkZsHJcwWcX2vQDlz5WHOH8/nrnc1rskzZL0rU5Nd50kUYqIiIgRG06NkqRDJV3Vth3afi9Jv5R0Q4dtz+HEVNYwfTXw/bbir1Mt3zUduBf4fC/3yqi3iIiIGLE5w+h8ZHsGMGOQ47t0Oybpr5JWs32vpNWA+wZ51O7ANbb/2nbvp19L+gbwk15iTo1SREREjNg49lE6h3mLvB8EnD3IufszoNmtJFctewM39PLQJEoRERExYnbv2wI6GthV0u+BXcs+klaX9PQINklLlOM/HHD9/0qaLWkWsBPw3l4emqa3iIiIGLHxWsLE9oNUI9kGlt8D7NG2/ziwQofzDhzJc5MoRURExIiZiT0zdxKliIiIGLHhdObuR0mUYkytvPyydYcwLCstN6XuEIZt1RV6mgqkUfrtc95wrVXrDiGisbIobkREREQXE7xCKYlSjK1HH3ig7hB6tvSKK/L3G2+uO4yeLbvJcwF4+O67a46kd1PWXBOAR+65t+ZIerfM6qsx85pb6g6jZ7ttuREAd9/3YM2R9G7NlZ/R7zb6SGqUIiIiIrpIohQRERHRRZreIiIiIrqYM3du3SGMqSRKERERMWITvEIpiVJERESMXPooRURERHQxXkuY1CWJUkRERIzYBM+TkihFRETEyKXpLSIiIqKLjHqLiIiI6CLzKEVERER0kaa3iIiIiC6SKEVERER0MdGb3ibVHUBERET0r7me2/O2ICS9TtKNkuZK2nqQ814u6VZJt0k6oq18eUm/kPT78udyvTw3iVJERESM2Fz3vi2gG4DXABd1O0HSZOBrwO7AxsD+kjYuh48Azrc9DTi/7A8piVJERESMmO2etwV8zs22bx3itG2B22zfbvtfwGnAnuXYnsDJ5fXJwF69PLeWREnSR0r12SxJ10l6fh1xLAhJB0v66iDHz5Z06Sg8Z1FJR5eqwhskXSFp93LsTkkrLugzOjzzI+Xv5TpJc9peHzbaz4qIiP421+55GwdrAHe17d9dygBWsX0vQPlz5V5uOO6duSVtD7wS2NL2k+WLfrHxjmMsSVoW2BL4h6R1bd+xALf7f8BqwKbl81oFePEohNmV7f8B/gdA0j9sTx/L50VERP/61ZFvVq/nSjoUOLStaIbtGW3Hfwms2uHSj9g+u5dHdChboAytjhql1YAHbD8JYPsB2/cASHqppGslzZb0LUnPKuV3Svq0pEslXSVpS0nnSfqDpLe3bizpA5KuLDVVR7WVv6/Uxtwg6T2lbKqkmyV9o9RuzZS0eDm2vqSfS7pa0m8kbTTM9/ha4MdUVX77tcVxkqSvS/q1pNslvbi8z5slnTTwJpKWAN4KvLvt8/qr7TM6nNvpPS4p6aeSri/l+5byrSRdWN7feZJWG+oNSXq2pBPL3821knYa5mcSERELOdszbG/dts0YcHwX25t22HpJkqCqQVqrbX9N4J7y+q+t77vy53293LCORGkmsJak30n6P0kvhuqLGDgJ2Nf2ZlS1Xe9ou+4u29sDvynn7QNsB3yyXL8bMI2qfXI6sJWkF0naCjgEeH45/62SnlfuOQ34mu1NgL9TJTgAM6iSk62A9wP/N8z3uD9watn2H3BsOWBn4L1UydSxwCbAZpKmDzh3A+BPth8Z7GGDvMeXA/fY3sL2psDPJS0KfAXYp7y/b1Fqj4bwToDyd7M/cHL5O4uIiGiKK4FpktaVtBhVZcU55dg5wEHl9UFAT8nXuCdKtv8BbEVV9XY/cLqkg4ENgTts/66cejLworZLW290NnC57Udt3w/8szR17Va2a4FrgI2oEqEdgbNsP1ae/UPgheVed9i+rry+GpgqaSngBcD3JV0HHE9VC9aT0jS2AXBxeS9PSdq07ZQfu+rRNhv4q+3ZtucCNwJTe33OAN3e42xgF0mflfRC2w9Tfc6bAr8o7++jVBl3L8/4DoDtW4A/As8ZeJKkQ0ut31UzZswYeDgiImJEJO0t6W5ge+Cnks4r5atLOhfA9lPAu4DzgJuBM2zfWG5xNLCrpN8Du5b9IdUy4aTtOcAFwAWSZlNldtcNcdmT5c+5ba9b+4tQtUt+xvbx7Re1mqGGuCfAHGBxquTx7wvQL2dfqlqjOyQBLEOV0X50wDO7vY92twFrS1ra9qODPLNj+7Dt35Xapj2Az0iaCZwF3Fhq54ajpzboUo3aypD86AMPDPMxERERz2T7LKrvsIHl91B9z7X2zwXO7XDeg8BLh/vcca9RkrShpGltRdOpaiduoarR2aCUHwhcOIxbnwe8qdQIIWkNSStTzbewl6QlJC0J7E3VfNdRaea6Q9Lryn0kaYthxLE/8HLbU21Ppao922/wS7rG8jjwTeDLpQoRSatJeuOAUzu+R0mrA4/b/i7wOaoO5rcCK6nqVN8aVbdJD+FcBBxQrnkOsHa5V0RExIRVR43SUsBXSnPZU1S1Jofa/qekQ6iavBahamc8rteb2p4p6bnApaUm5x/AG21fUzpKX1FOPcH2tZKmDnK7A4CvS/oosChVp+zrh4qh3HNt4LK2uO6Q9IhGPgXCR4FPATdJ+ifwGPDx9hMGeY8vA46RNBf4N/AO2/+StA9V8jWF6t/AF6ma/gbzf8BxpQbwKeDgVgfziIiIiUoTfTG7qFVfNb0tveKK/P3Gm+sOo2fLbvJcAB6+++6aI+ndlDWr7nCP3HNvzZH0bpnVV2PmNbfUHUbPdtuyGqR7930P1hxJ79ZceYW6Q1hY9DyMP+bJzNwRERERXSRRioiIiOgiiVJEREREF0mUIiIiIrpIohQRERHRRRKliIiIiC6SKEVERER0kUQpIiIiooskShERERFdJFGKiIiI6CKJUkREREQXSZQiIiIiukiiFBEREdFFEqWIiIiILpIoRURERHSRRCkiIiKiiyRKEREREV3Idt0xxMSVf1wREc2hugPoR4vUHUBMbH+/7fa6Q+jZshusx8N/uqvuMHo2Ze21gP77jAEevv2OmiPp3ZT11uXWu/5Sdxg923CtVQG494GHao6kd6utuBxAX/7/FxNfmt4iIiIiukiiFBEREdFFEqWIiIiILpIoRURERHSRRCkiIiKiiyRKEREREV0kUYqIiIjoIolSRERERBdJlCIiIiK6SKIUERER0UUSpYiIiIgukihFREREdJFEKSIiIqKLJEoRERERXSRRioiIiOgiiVJEREREF0mUIiIiIrpodKIkyZI+37b/fklHltdHSvqzpOvatmXLsW0lXSDp95KukfRTSZsNuPf1kk4trw9pu8e/JM0ur4+WdLCkr0p6iaRLB9xjEUl/lbSapJMk3dF2n0s6vJ+XSHp4QMy7tL3X7wy49/2SftJWtpekWZJuKTHuVcq/Vu51k6Qn2u69T4lrn3LeYpK+KOkP5bM5W9KaPX7eG5bP9DpJN0uaMdy/z4iIiH6zSN0BDOFJ4DWSPmP7gQ7Hj7X9ufYCSasAZwBvsH1JKdsRWB+YXfafS5UkvkjSkrZPBE4sx+4Edmo9T9LB5dYXAWtKmmr7zlK2C3CD7XslAXzA9g+GeE+/sf3KDuWPAZtKWtz2E8CuwJ/b3tcWwOeAXW3fIWld4BeSbrf9znLOVOAntqe3Xdf+rE8DSwPPsT1H0iHADyU937YZ/PP+MtXnfXa572ZERERMcI2uUQKeAmYA7x3GNe8CTm4lSQC2L7b9o7Zz3gB8B5gJvLqXm9qeC3wf2LeteD/g1GHENpSfAa8or/cfcO/3A5+2fUeJ5w7gM8AHermxpCWAQ4D32p5T7nEiVXK0czltsM97NeDu1o7t2b29pYiIiP7V9EQJ4GvAAZKmdDj23rZmpl+Xsk2Aa4a4577A6VSJyP7DiOVUquQISc8C9gDObDt+TFs8p3S5xwsHNL2t33bsNGA/Sc8GNgcubzu2CXD1gHtdVcp7sQHwJ9uPDHGPbp/3scCvJP1M0ntbzZwRERETWeMTpfLF/m3gsA6Hj7U9vWw7dbpe0uWlT82Xyv42wP22/wicD2wpabkeY7kSWErShsDuwGW2H2o75QNt8RzQ5Ta/aTtnuu0/tN1/FjCVKnk7d+BbAdxDWTfdzp2vvNvnXWqfnktVq/YS4LKSLM5/M+lQSVdJumrGjHRjioiI/tb4RKn4IvBmYMkezr0R2LK1Y/v5wMeAVg3J/sBGpS/SH4BlgNcOI5bTqGqVRrvZreUcqr5IA+99I7D1gLItgZt6vO9twDqSlu7hHl+kw+dt+x7b37K9J1Uz3aYDH2J7hu2tbW996KGH9hhaREREM/VFomT7b1QdtN/cw+lfAw6W9IK2siUAJE0CXgdsbnuq7anAngy/+e2NVP16zhnGdb36FvDJDn2APgd8qHTYbnXc/jDweXpg+zHgZOALkiaXe/wH1WfzqwHnPuPzlvRySYuW16sCK9DW2TwiImIi6otEqfg8sOKAsvcO6O8z1fZfqPogfUbSbWWY/j7AV4EXAX+23f4FfxGwsaTVegnC9k3A48CvSvLR7pgB8SzW4RYD+yjtM+D+d9v+UofnXgd8EPixpFuAHwP/Xcp79SHgn8DvJP2eKmncu4x4G2jg570bcIOk64HzqJoZ/zKMZ0dERPQddf6OjBgV/vttt9cdQ8+W3WA9Hv7TXXWH0bMpa68FQL99xgAP335HzZH0bsp663LrXf3zO8GGa60KwL0PPDTEmc2x2opVN9F+/P+vz6juAPpRP9UoRURERIyrJEoRERERXSRRioiIiOgiiVJEREREF0mUIiIiIrpIohQRERHRRRKliIiIiC6SKEVERER0kUQpIiIiooskShERERFdJFGKiIiI6CKJUkREREQXSZQiIiIiukiiFBEREdFFEqWIiIiILpIoRURERHQh23XHEBNX/nFFRDSH6g6gH6VGKcaSxmKT9Laxundi7t+Y+y3efoy53+JNzM/YYgSSKEU/OrTuAEYgMY+9fosX+i/mfosXEnMsoCRKEREREV0kUYqIiIjoIolS9KMZdQcwAol57PVbvNB/MfdbvJCYYwFl1FtEREREF6lRioiIiOgiiVJEREREF0mUIsaYpEmSlqk7jqFIOryXsiaRtI6kXcrrxSUtXXdME4mkz0napO44hkvSYpI2LduidcfTK0mLSnqepJXrjiXmSR+laCxJX2GQ2b1tHzaO4QyLpO8BbwfmAFcDU4Av2D6m1sAGIeka21sOKLvW9vPqimkwkt5KNd/M8rbXlzQNOM72S2sObUiSdgSm2T5R0krAUrbvqDuugSS9BTgEWAQ4ETjV9sP1RjU4SS8BTgbupJpkcS3gINsX1RdVZ5KOA75i+0ZJU4BLqX5mLA+83/aptQYYQGqUotmuokoyng1sCfy+bNOpfpg02ca2HwH2As4F1gYOrDWiLiTtL+nHwLqSzmnbfg08WHd8g3gnsAPwCIDt3wON/01c0ieADwIfKkWLAt+tL6LubJ9gewfgP4CpwCxJ35O0U72RDerzwG62X2z7RcDLgGNrjqmbF9q+sbw+BPid7c2ArYD/ri+saLdI3QFEdGP7ZABJBwM72f532T8OmFljaL1YtFT57wV81fa/JTW1+vYS4F5gRaovmZZHgVm1RNSbJ23/S6pWZpC0CP2xvuDewPOAawBs39PkJkNJk4GNyvYAcD3wPklvs71frcF1tqjtW1s7tn/X4Oa3f7W93hX4PoDtv7T+XUf9kihFP1gdWBr4W9lfqpQ12fFUVf/XAxdJWodS89E0tv8I/FHSAcA9tv8JVZ8fYE2q99FEF0r6MLC4pF2B/wR+XHNMvfiXbbcSZ0lL1h1QN5K+ALwaOB/4tO0ryqHPSrq1+5XjT9K7bH8VuErSN4HvlEMHUNVMN9HfJb0S+DNV7eib4emkf/E6A4t50kcpGk/SIcCRwK9L0YuBI1s1Tv1C0iK2n6o7jm4kXQW8wPa/yv5iwG9tb1NvZJ1JmkT1xbIbVV+U84AT3PAfapLeD0yjqkH4DPAm4Hu2v1JrYB1IehNwmu3HOxyb0qT+Sq0+dpKeBbyLKvEQcBHwf7afrDXADiQ9B/gysCrwRdsnlfKXUTUf/leN4UWRRCn6gqRVgeeX3ctt/6XOeIZSRoudSNV8dQJVU8sRthvbZCjpOtvTB5Rdb3uLmkKasEoN2NMJnu1f1BxSV5KWo0rsnt0qa2jH6GcMRogYDWl6i8ZT1Vi/C7Ce7U9KWlvStm3NAE30JttfKr8ZrkTVUfNEmt236n5Jr7Z9DoCkPan6pDSSpB2oahrXofpZJsC216szrl6UxKixyVFLGfV2OFUT7HXAdlQjs3auMaxuNpfUqXm79e+icVN0SPr4IIdt+/+NWzDRVRKl6Af/B8yl+uH8SapamjOBRjYJFa2emHsAJ9q+Xs3vnfl24BRJX6WK/y6q0U5N9U3gvVT9T5o+CvJpkl4DfJZqhJ5o8Bc5VZK0DXCZ7Z0kbQQcVXNM3cxu6lQWg3isQ9kSwFuAFYAkSg2QRCn6wfNL34NrAWw/VPrPNNnVkmYC6wIfKqOa5tYc06Bs/wHYTtJSVM3yj9Yd0xAetv2zuoMYgf8FXmX75roD6cE/bf9TEpKeZfsWSRvWHdREYfvpUablZ8ThVH3WTmP+EahRoyRK0Q/+XYYot0YJrUTDkw6qTsbTgdttPy5pBarmt0aT9ApgE+DZrQow25+sNajufi3pGOCHwNMddW1fU19IPflrnyRJAHdLWhb4EfALSQ8B99QaUXffrzuAkZC0PPA+qtF5JwNb2n6o3qiiXTpzR+OVYev7Uk06eTKwD/Ax22fUGtgQJL0aeFHZvdB2o4eul/mplgB2ouqAvg9whe031xpYF2VCzIFsu4n9Z54m6UtUo5x+xPwJ3g/riqkXkl5MNcP8z1sjI2PBlET/NcAM4Gu2/1FzSNFBEqXoC6VvxEup+nOc3/TfyCUdTdW345RStD9wle0Pdb+qXpJm2d687c+lgB/a3q3u2CYSSSd2KLbtN417MF1IWgL4d9skrxtS9bf7Y9MTun4iaS5VsvwU80+W2uR+awudJErReJK+Y/vAocqaRNIsYLrtuWV/MnCt7c3rjaw7SZfbfr6ky6h+y30QuMH2tJpD66isjfUJ2mrtgE82aW6ffiXpIuDNtn8vaQPgCqqkf2PgSttH1BpgxDjKWm/RD+ZbvbwkHVvVFMtwLNv2ekpdQQzDT0p/lGOolte4k6pTaVN9i2oE5OvL9gjVFAyNJmlNSWdJuk/SXyWdKWnNuuMaYLmydh7AQVSL4b4b2B14RX1hDU3SKpK+KelnZX9jSY1sPm6RtJOkd0l6p6pFfaNB0pk7GkvSh4DWEhWt+VFEtT7SjNoC681ngGtLPxpR1Xo0ttmt+N8ye/GZkn5CNcHgP2uOaTDr235t2/5Rkq6rK5hhOBH4HvC6sv/GUrZrbRE9U3tTw85UyTNlbb2mD6Q4ierz/EjZ/x1wOtV0Eo0iaQ2qwQj/pJrmQsDry/JBe9v+c53xRSVNb9F4kj7T5L493UhajaqfkoDLgXVsX15vVN11mtm4ybMdS7oU+IDti8v+DsDnbG9fb2SD6zID+jPK6iTpu8BfqNYgOwJYt4zeXJZqYEJjZ2uXdKXtbSRd25pXqWmfb4uks4CzW0uXtJX/B/Ba23vWEljMJzVK0Q+uaF9XqvywfontH9Ua1RBs3wuc09qXdAWwdn0RdVaWh1mDqubuecybLHMZqlFwTfUO4OTSVwngIeDg+sLp2QOS3gicWvb3p+oP1iRvpZrTZyrVmmOttd42Bj5XV1A9eqxMx9GaTmQ7oKn91ja2vffAQtvflvSRThfE+EuNUjRel9/An/5tsV9Iusv2WnXHMZCkg6gSjK2Bq9oOPQqc1PRRTpKWAbDdafmKxpG0NvBVYHuqL/NLgMNt/7HWwCYISVsCXwE2BW6gWkJoH9uzag2sA0m32d6gQ/kk4HedjsX4S6IUjdcarj6gbLbtzeqKaSQk/cl242qUWiS91vaZdcfRK0mrAJ8GVre9u6SNge1tN64vSowvSYsAG1LVjt7amuagaSQdCywFvMf2Y6VsSeBYqlnRD6szvqgkUYrGk/Qt4O/A16h+A3831aicg2sMqyNJP2b+jrBPHwJ2tr3kOIfUM0nPAl5L1dzydLN8U2fmLqOaTgQ+YnuL8uV4bVMT6CyAOj4kvY5qUsxHJX2UaqLaTzVxxnZJi1IN/DgYaNUork01se6HM7FnMyRRisYrv2F9DNilFM0E/qf1G1iTlNmLu7J94XjFMlySfk7Vl2O+RWbb16Nqkn7qtAsg6b86FC9JtdzNCraXGueQelbWIXM/zBzdNmHqjlRJyOeoko7n1xxaV2WU2wZUv1Dd1tYnLBognbmj8UpCdISkpZr+g7rJiVAP1rT98rqDGIZ+6rTbbQHUQ2jwAqiSNgO+DSxf7ep+4CDbN9Qb2aBaSf4rgK/bPlvSkTXG05Wk13Qo3kDz1llsdP/AhUUSpWg8SS+gWntsKWBtSVsAb7P9n/VGNuFcImkz27PrDqRH76MaVbi+pN9SOu3WG9Lg1H8LoB4PvM/2rwHKZIgzgBfUGNNQ/izpeKoa6M+WJuWmTq78qkGOmWqOpahZmt6i8SRdTvUFeE5bE8sNtjetN7KJRdJNVNX/d1CtP9Vab6rJy670Radd6M8FUCVdP3DOpE5lTaJqnbqXA7PLEiyrAZvZnllzaM8g6TWpNWq+JErReG1rkLX3RWn0D+uBJD0beJXt79cdSzeS1ulU3tRh62Upm1fwzM7nX6grpsGojxZAbX2BlwkRrwG+Uw69Edja9l61BdeDUuv8wrL7G9vX1xlPN02e0DXmaWp1ZES7u0rzmyUtJun9wM11BzUUSZMl7S7p21QjWvatO6bBlIRoWarmgFcByzY1SSp+TDVaaAVg6batkWxPsr247aVtL9O2Ld2kJKn4aPnzTVRNmj8EziqvD6krqF5IOpxqAd+Vy/ZdSe+uN6roZ6lRisaTtCLwJao+B6Ia9Xa47abNZgyApBcBb6Cq7bgC2AFYr+kjWcoXzFuZ1y9ib2CG7a/UF1V3nebXitHRzzUdkmZRzafVPi/RpU38tyLpceC2TodoeLP3wiSduaOxJH3W9geBnWwfUHc8vZB0N/An4OtU65A9KumOpidJxZuB57d9wXwWuJRqluMm+pmk3ZrY92QC2KgkHB01/AtctE1vUV6ry7l1u4PBO3RHAyRRiibbo0wY9yGgsX17BjgT2IuqmW2OpLPpPAFlE/XTFwzAZcBZZbmHf9PAvj59rJ+/wE8ELi/9q6D6/7Gps7X/q+HN20ESpWi2nwMPAEtKeoTyRUiDvxBtHy7pPcBOVIudHgMsI+n1wLkNH+nUT18wUM09tD3V6KZ+SUb7Rd9+gdv+gqQLgB2pflYcYvvaeqPq6rd1BxBDSx+laDxJZ9ves+44RqIsUfByqqRpN9sr1hzSoMqCoq0vmIsa/AWDpPOA3W3PrTuWiUbSV22/q+44hqPMUdWV7b+NVyzDIWlT4L+Bjal+EbwJ+HwTF/FdWCVRihgnkha3/UTdcQwkaRtgRds/G1D+auDPtq+uJ7LBSToJWA/4GdWwe6C50wPE2JJ0B/NqnGFek3erBnq9WgIbhKQ9qZZY+QxwFVWsW1F1N3i/7bNrDC+KJErReGWa/89SDfUVDW5660elmeJg23cOKN+AatTbznXENRRJn+hUbvuo8Y4lYiQkXQ/s2eH/vanA2f00V9xElkQpGk/SbVSTNTZ+7qR+JGm27c26HGv8xJ79tGBrv5H0LNtPDlXWBJJeBixt+wcDyt8A3G/7F/VE1p2km2xvPNxjMb4y4WT0g78mSRpTiw9ybMlxi2KYJG0q6VrgBuBGSVdL2qTuuCaYS3ssa4KjgE6LUv8K+OQ4x9Krf0tae2BhmSX/qRriiQ4y6i36wVWSTgd+xPx9URq7RpKkH/PMaQEepuqHcLztf45/VF39UtL/AB9tHz0m6SiqL5mmmsEzF2z9Bs1esLUvSFoVWANYXNLzmNfvZxlgidoCG9wStu8fWGj7L2XSySb6BNX/f58Grqb6mbENcATwwToDi3mSKEU/WAZ4HNitrazpK2vfTrXcw6llf1/gr8BzqL7MD6wprk7+CzgBuE3SdaVsC6qk7i11BdWDJVtJEoDtCxr8hdhvXka1PMyaQHvn+EeBD9cRUA+eLWkR2/PVxJSRp4PVmtbG9o9KJ/T/At5NlZDeCLy+qevTLYzSRyliDEi6yPaLOpVJutF245qIJK0HtOK60fbtdcYzlH5dsLWfSHqt7TPrjqMXko4GVgHeNWD5ki8DD5RZ/iOGLTVK0ViSvsIgs1rbPmwcwxmulSStbftPAKUfQmsOpX/VF1Z3JTFqdHI0wJuo+qX8kDLvEw1fsLUPnS/pC0Ar6b8Q+KTth2uMqZuPAp8C/iipNVnm2lSTpn6stqgGIemcwY7bfvV4xRLdpUYpGkvSQYMdt33yeMUyXJL2AI4D/kD1Jb4u8J/ABcBbbX+xtuAmIEnLAX/PDN2jS9KZVJ3lW/+vHQhsYfs19UU1OEmLAxuU3duaOHdZi6T7gbuomugvZ8CSQbY7dU6PcZZEKWKMSHoWsBHVD79bGtaBu29J+jhwhu1bymf8M6o+VXOAN9j+Za0BTiCSrrM9faiyGBlJk4FdqWbu3xz4KXCq7RtrDSzmk+kBIsbOVlR9fjYHXi/pP2qOpyNJyw+21R1fB/sCt5bXB1H9HFsZeDHw6bqCmqCekLRja0fSDkBja2j6je05tn9u+yBgO+A24AJJ7645tGiTPkoRY0DSd4D1geuoajqg6m/17bpiGkRrWLI6HDPVMiFN8q+2JraXUf0GPge4WVJ+po2udwAnS5pC9e/jb1Sj4WKUlFrRV1DVKk2l6nze5BG9C500vUWMAUk3Axunz8zok3QZ1bQFf6WqWdrK9h3l2C22N6ozvolI0jIAth+pO5ZeSNqcKul4OnFu4rxrkk4GNqVqPj7N9g01hxQd5LevaDxJ61LNMTKV+X/wNXlEyA3AqsC9dQcyHKVT9DTg2a0y2xfVF1FHhwM/oJqn6ti2JGkP4No6A5soujUTS1Wlo+0m1owCIOlbVM3dNwJzS3FT5107EHiMan61w1qfL1nPslFSoxSNVxaO/CYwm3k/+Bo9IkTSr4HpwBXMP5t4Y5M7SW+hSkLWpGoy3A64tKmL4sbYKVNzPKMYeBWwhu3G/pKdNdJitDX2H3tEm3/a/nLdQQzTkXUHMAKHUy2fcJntnSRtRDVPUSxkbD/dmVhVNccBVEtqXAb8T11x9ehSSRvbvqnuQIYiaWfbvyqv123Vjpb91zSxuXBhlBqlaLyy+vc0YCbz185cU1tQE5CkK21vU5Yxeb7tJzMUfOFVOsYfTLW8xuXAZ2zfOuhFDSDpRcCPgb9Q/bxoNWNtXmtgHUi6xvaWA1932o/6pEYp+sFmVG35OzN/n4PGNQlJutj2jpIeZf5Zxfuhz8HdkpalWnz4F5IeAu6pNaKohaR3UtUwng+83PYfh7ikSb5F9fNivqb6hlKX1532oyapUYrGk3QLsLntRi79MRFJejEwBfh5kz93SS/gmZ38G9vRuF9ImgvcB9xP54S/cbUzLZJ+1S/96lKj1B9SoxT94HpgWaof3H2jzLq7CvN/if+pvoiG1hZzq6/EqkAjY+6zuar6zbp1B7AAbpH0Parmt/am+ib291mvrPemttcwb9mjaIDUKEXjSbqAarjvlfTPCLJ3A5+gmuvn6ebChv8m3lcxZ66q6ETSiR2KbftN4x7MEErNbVdNHtm7MEmiFI3X7YdJk3+ISLqNqkP0g3XH0qt+i1nS94HDbPfVXFUx/iRtY/vKuuOI/pSmt2i8gQlRWW/qDUBjEyWqFcEfrjuIYeqLmCX9mKqJbWngJkl9M1dVjB9JGwP7US0N8jCwdb0RRb9KohR9QdJ0quTo9VT9Z86sNaCh3U61uOVPmf9L/Av1hTSkfon5c3UHsDAo/dVOtv3GumPplaR1qBKj/YGngHWArW3fWWdc0d+SKEVjSXoO834jfBA4naq5eKdaA+vNn8q2WNn6QV/E3KphlPRZ2x9sPybpszS7prFv2J4jaSVJizV55GOLpEuoRmqeBuxj+/eS7ujXJEnSIrafqjuOSKIUzXYL8BvgVbZvA5D03npDGlr5TXxaP/0mDmD7KABJS1e7/kfNIQ1lV6rZotvt3qEsRu5O4LdlNNZjrcIG1jJCNZXBmlSjNlcCfs/8Uxs0TmvetfL6O7YPbDt8BZDpARpgUt0BRAzitVSz6/5a0jckvZQ+mITN9hxgJUmNrZXpRNKmkq6lWtD3RklXS9qk7rgGkvQOSbOBDSXNatvuAGbVHd8Ecw/wE6rviqXbtsaxvSfV5LTXAEeVfw/LSdq23sgGtWTb64H/rzX+Z93CIqPeovEkLQnsRdUEtzNwMnCW7Zl1xjUYScdT/TbYD7+JA083XXzE9q/L/kuAT9t+QZ1xDSRpCrAc8BngiLZDj9r+Wz1RTWySlrT92NBnNoeklYF9qX5urGV7rZpDeoZMONkf0vQWjVd+QJ8CnCJpeeB1VF+QjU2UqH4Tv4d5v4n3gyVbSRKA7QtKkto0tn1nWWZjPpKWT7I0eiRtD3wTWApYW9IWwNts/2e9kQ3N9n3AV4CvlE7eTbSspL2pfk4sK+k1pVxU/a2iAVKjFBEASDqLqtniO6XojVQjhvaqLagOJP3E9itL04qZv4nCtterKbQJR9LlwD7AObafV8pusL1pvZFNDF0mx3ya7UPGK5boLjVKEWNA0q/p0JG04WtQvQk4CvghVfJxEdC4H9S2X1n+zBIP48D2XdJ83WXmdDs3hu0I23+tO4gYXBKliLHx/rbXz6bqmN7oob62HwIOqzuOoUh6ELgMuAT4LXCF7cfrjWrCuqssPOwyOOEw4OaaY5pIri8DE04FzrTd+AlfF0ZpeosYJ5IutD3o2k51kPRF2+9pm/F6Pk2b6VrSMsB2wAvKthXVZJmXAL+1fUaN4U0oklYEvgTsQlXLOBM4vInL3Ej6CoNMB2C7cb8ElKlEdqGaL24P4FKqpOkc20/UGVvMk0QpGkvSo3T+wSeqvijLjHNIPSudzlsmUX2Zf9n2hjWF1JWkrWxf3Y9r6sHToyIPAd4DrGt7cr0R9b/WZJ6SXmf7+3XH0wtJBw123PbJ4xXLSJQau92pkqadgPNtH1BvVAFJlCLGxICOxk9RLbvySdsX1xpYjyQtRzWkunHzEklanXm1SduU4qupmuMutf3HumKbKEpz0JbA5RmiPn4kTaOazuCNwGOtDvRRr/RRihgD/djRWNIFwKupfi5cB9xfmgvfV2dcHdxNNTrvWKrOsI1fXqMP/Rx4AFhS0iOUWlz6oDa330ham3nzPS1JtQTLnrbTF6whUqMUMQYkLQq8A3hRKboAON72v2sLagiSrrX9PElvoapN+oSkWbY3rzu2dmVun+2papTWpVpm49KyXWX7ye5Xx3BIOrvMeB1joEzyugbwA+BU21fVHFJ0kEQpYgxIOgFYlGoWcYADgTm231JfVIMrzS27UcX8EdtXNjFRGkjSVOBVwOHAmrafXW9EE0uZrHGa7V9KWhxYxPajdcc1EZR+gRc5X8SNlqa3iLGxje0t2vZ/Jen62qLpzSeB84CLS5K0HtXCoo0jaSPm9VPagWpJk0uB4+qMa6KR9FbgUGB5YH2qRWePA15aZ1yDkfQc4OvAKrY3lbQ58Grbn6o5tE72AV47YJ6qpzVxpN7CKDVKEWNA0jXA62z/oeyvB/wgHWMXnKQHgHuppgNoTQlwW71RTUySrgO2perU3ZqZe7btzWoNbBCSLgQ+QNXU3ejZxPt9pN7CIjVKEWPjA8CvJd1O1QF2HRo4y3U7Sf8LfAp4gqoz7xbAe2x/t9bAnmn9TMw3bp60/a9WjYekRRhkrqKGWML2FQNqaZo62euGtj9cdxAxuEl1BxAxEdk+H5hGNZPxYVQ/EH89+FW12832I8ArqUaWPYcq4WuUJEnj6kJJHwYWl7Qr8H3gxzXHNJQHJK1PSegk7UNVA9lEL687gBhaapQiRlHb6t8DrS8J2z8c14CGZ9Hy5x5UI3D+1q3vRCw0Pgi8BZgNvA04Fzih1oiG9k5gBrCRpD9TzWH2xnpD6mpymbOs4/9otv82zvFEB+mjFDGKJM2lmoPoulZR22HbftN4x9QrSUcDe1E1vW0LLAv8xPbzawwraiJpEjCriX17elFmbJ/U5BF6kp4E/kznRMm21xvnkKKDJEoRo0jS3lSTx20AnE1VM9M3HY3Lb7eP2J5TvmiWtv2XuuPqRNIqwKeB1W3vLmljYHvb36w5tAlD0inAh2z/qe5YeiXpWVSLUE+lrdXE9ifriqmb1txldccRg0sfpYhRZPss2/sBLwb+AHxe0sXd1lFrEklLUDVbfL0UrQ5sXV9EQzqJajqD1cv+76jWe4vRsxpwo6TzJZ3T2uoOaghnA3tSdeB+rG3rK+UXgWiA9FGKGBv/BB4GHgHWBvphEsQTqdZMe0HZv5uq8+5PaotocCvaPkPShwBsPyVpTt1BTTBH1R3ACKxpu186SX+pfUfSFKrasDcAz6WatTtqlkQpYhRJ2olqzaZtgV8CX+qjZQnWt72vpP0BbD+hZvfmfkzSCswb3bQdVXIaC0jSs4G3UzUhzwa+abupQ+wHukTSZrZn1x3IUGyfVGY7fzVVcrQlsDRVX8GLagwt2qSPUsQoKp25ZwEXU32Bz/c/WJNn2i3rTr2UagLHLcsQ61Ntb1tzaB1J2gr4MrApcAOwErCP7Vm1BjYBSDod+DfwG2B34I+2D683qt5IuokqwbsDeJJ5C/k2bime0gfsRcBMqsVwfwXc1o+Lak9kqVGKGF2NnlRyCJ+gmmhyrfIDfAfg4FojGoTtq0vfrw2pvgxvbfKiw31m49bs25K+CVxRczzDsXvdAQzDpsBDwM3ALWUQRWovGiY1ShELOUk72P5tGS20FLAdVeJxme0H6o2uu7J23unA6a2lYmJ0SLqmfbmdgftNJ2kL4IVl9ze2G7vOYlm38A1Uo2XvAzYCNmvqaNOFURKliIWcpKttb9WHX4brUH257AvMpUqazuinoexNVTrFt0aKCVgceJx5zVjL1BXbUCQdDrwVaE3uujcww/ZX6ouqN5K2pkqa9gHutv2CIS6JcZBEKWIhJ+kyqqr/PaiSjfk0uV9Vi6RpwMeAA2xPrjueqI+kWVTzaT1W9pcELm1iH6VuyiCKF9m+sO5YIn2UIqJa220XYGeq6QH6hqSpwOupapXmAP9da0DRBKL6t9Ayhy5LhNRN0iZUo03PKfvHAlPK4a/WFljMJ4lSxBiQtC7wbp45O/Cr64qpm9IP6TRJNze5L8dAki6nWp/u+8DrbN9ec0jRDCcCl0s6q+zvBTR1tvajgc+07b+MqmZ0CeDjVLFHzdL0FjEGSkfjb1LNQTO3Vd7kqnRJawJfoRrtZqopDg63fXetgXUhaSPbt9QdRzSPpC2BHalqki6yfW3NIXUk6SrbW7ftX2Z7u/L6Yts71hddtKRGKWJs/NP2l+sOYphOBL4HvK7sv7GU7VpbRB1IeqPt7wJ7SNpj4HHbX6ghrGiWJYBHbZ8oaSVJ69q+o+6gOli6faeVJBUrj3Ms0UUSpYix8SVJn6CaSO7JVqHta+oLaUgr2z6xbf8kSe+pK5hBLFn+XLrDsVSRL+TK/3dbU82vdSJV8+x3qWpKm+YeSc+3fXl7YZll/p6aYooBkihFjI3NgAOpOki3mt5c9pvqfklvBE4t+/sDD9YYT0e2jy9/PmMdsoYmdjG+9gaeB1wDYPseSZ2S6ib4IHC6pJMo8QJbAQdRDVCIBkgfpYgxIOkWYHPb/6o7ll5JWptqpM32VEndJVR9lP5Ya2DDIOlPtteuO46oj6QrbG/bmhes6dMDSFoZeBewSSm6Efia7b/WF1W0S41SxNi4HliWaqbdxpM0Gfh0E0flDVMjh4HHuDpD0vHAspLeCrwJ+EbNMXUkaRnb91GNcBt4bO1MntoMSZQixsYqwC2SrmT+PkqNTETKGlMrSVqsn2rBOkgV+ULO9uck7Qo8QtVP6eO2f1FzWN1cAGwJIOl82y9tO/aj1rGoVxKliLHxiboDGIE7gd9KOod5y1c0bhSZpEfpnBC1ltqIhZztX5R5thYBkLS87b/VHFYn7TWgyw9yLGqURCliDAycL0nSDlRrODV2HiWqUTb3AJPoPKKsEWw3Nraon6S3AZ8EnqAaSCGqxHq9OuPqwl1ed9qPmiRRihgjkqZTJUevB+4Azqw1oEFIeh5VJ9Ibbd9cdzwRC+D9wCZlxvmmW1nS+6iSudZryv5K9YUV7ZIoRYwiSc8B9mPe0PrTqUaX7lRrYIOQ9HGqySWvBv5X0mdsN7Lza0QP/gA8XncQPfoG82pv218DnDD+4UQnmR4gYhRJmgv8Bniz7dtK2e22m1jtD4CkG4FtbD8uaQXg57a3qTuuiJEotaMnApcz/0CKw2oLKvpaapQiRtdrqWqUfi3p58BpNL9T5j9tPw5g+0FJk+oOKGIBHA/8igHrLDZRqc3txrb/37gFE12lRiliDJRJ7vaiaoLbGTgZOMv2zDrj6kTS34GLWrvAC9v2GzelwRCj3mx7mXEOKRpE0iW2X1B3HL2Q9F8dipcE3gysYHupcQ4pOkiiFDHGJC1PtdDsvrYbt4SJpBcPdnzgCL6IJpP0P8AfgR8zf9NbE6cHeFpZZuVwqiTpDODzZTLKqFkSpYiImDAk3dGh2E3tJ1h+kXofcABVzfOXbD9Ub1TRLn2UIiJiwrC9bt0x9ErSMcBrgBnAZrb/UXNI0UFqlCIiYsKQtCjwDuBFpegC4Hjb/64tqC7KKNkngaeYv99d+ts1SBKliJiPpCVtPzb0mRHNI+kEYFGqZiyAA4E5tt9SX1TRz5IoRYyifh6RJekFVJPcLWV7bUlbAG+z/Z81hxbRM0nX295iqLKIXqWPUsQo6vN1yI4FXgacA2D7ekkvGvySiMaZI2l9238AkLQeMKfmmKKPJVGKiKfZvkuab37MfMFEv/kA1YSvt1PV5K4DHFJvSNHPkihFRMtdpfnNkhYDDgOyQG70FdvnS5oGbEiVKN1i+8khLovoKksVRETL24F3AmsAdwPTy35E40naRtKqACUxmg58EjimzFUUMSLpzB0RAEhayfb9dccRMRKSrgF2sf230rfuNODdVAnTc23vU2d80b9SoxQRLZdIminpzZKWrTuYiGGa3LZMyb7ADNtn2v4YsEGNcUWfS6IUEQDYngZ8FNgEuEbSTyS9seawIno1WVKr3+1LgV+1HUt/3BixJEoR8TTbV9h+H7At8DfmTdoX0XSnAhdKOht4AvgNgKQNgIfrDCz6W/ooRQQAkpYB9gb2A9YHzgLOsH11rYFF9EjSdsBqwMzW7PKSnkM1ieo1tQYXfSuJUkQAT6+6/iOq5OjSmsOJiGiEJEoRAYAkOT8QIiLmkw5uEdGyoqT/purM/exWoe2d6wspIqJe6cwdES2nALcA6wJHAXcCV9YZUERE3dL0FhEASLra9laSZtnevJRdaPvFdccWEVGXNL1FRMu/y5/3SnoFcA+wZo3xRETULolSRLR8StIU4L+ArwDLAO+tN6SIiHql6S0iIiKii9QoRSzkJH0F6Pobk+3DxjGciIhGSaIUEVe1vT4K+ERdgURENE2a3iLiaZKutf28uuOIiGiKzKMUEe3ym1NERJskShERERFdpOktYiEn6VHm1SQtATzeOgTY9jK1BBYR0QBJlCIiIiK6SNNbRERERBdJlCIiIiK6SKIUERER0UUSpYiIiIguMjN3xEJuwKi3+Q6RUW8RsZDLqLeIiIiILtL0FhEREdFFEqWIiIiILpIoRURERHSRRCkiIiKiiyRKEREREV0kUYqIiIjo4v8DoaJQ/WH2FdcAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 576x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# correlations\n",
    "data = all_X.loc[:,covid]\n",
    "data.columns = data.columns.str.replace(r'^.*-', '', regex=True)\n",
    "data['NEGATIVE EMOTIONS'] = y\n",
    "corr = data.corr()\n",
    "fig, ax = plt.subplots(figsize=(8, 8))\n",
    "cmap = sns.diverging_palette(230, 10, as_cmap=True)\n",
    "mask = np.triu(np.ones_like(corr))\n",
    "sns.heatmap(corr, cmap = cmap, fmt = '.2g', vmax = 1.0, vmin = -1.0, center = 0, square = True, \\\n",
    "            mask = mask, linewidths = 0.7, cbar_kws = {\"shrink\": 0.5}, annot = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>            <td>y</td>        <th>  R-squared:         </th> <td>   0.046</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.044</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   34.94</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Date:</th>             <td>Tue, 22 Dec 2020</td> <th>  Prob (F-statistic):</th> <td>5.91e-48</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Time:</th>                 <td>07:57:11</td>     <th>  Log-Likelihood:    </th> <td> -8089.8</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>      <td>  5113</td>      <th>  AIC:               </th> <td>1.620e+04</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Residuals:</th>          <td>  5105</td>      <th>  BIC:               </th> <td>1.625e+04</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Model:</th>              <td>     7</td>      <th>                     </th>     <td> </td>    \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>    \n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "               <td></td>                  <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>const</th>                       <td>    4.4259</td> <td>    0.027</td> <td>  163.862</td> <td> 0.000</td> <td>    4.373</td> <td>    4.479</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>I Am Infected</th>               <td>    0.4204</td> <td>    0.091</td> <td>    4.609</td> <td> 0.000</td> <td>    0.242</td> <td>    0.599</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>I Am Mourning A Loss</th>        <td>    0.2982</td> <td>    0.089</td> <td>    3.345</td> <td> 0.001</td> <td>    0.123</td> <td>    0.473</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>I Have Professional Contact</th> <td>    0.3584</td> <td>    0.075</td> <td>    4.806</td> <td> 0.000</td> <td>    0.212</td> <td>    0.505</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>I Live With Someone</th>         <td>    0.3625</td> <td>    0.095</td> <td>    3.817</td> <td> 0.000</td> <td>    0.176</td> <td>    0.549</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>None</th>                        <td>   -0.2314</td> <td>    0.037</td> <td>   -6.201</td> <td> 0.000</td> <td>   -0.305</td> <td>   -0.158</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prefer Not To Say</th>           <td>   -0.3549</td> <td>    0.090</td> <td>   -3.960</td> <td> 0.000</td> <td>   -0.531</td> <td>   -0.179</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Someone I Am Close To</th>       <td>    0.1291</td> <td>    0.052</td> <td>    2.484</td> <td> 0.013</td> <td>    0.027</td> <td>    0.231</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "  <th>Omnibus:</th>       <td>257.832</td> <th>  Durbin-Watson:     </th> <td>   1.928</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(Omnibus):</th> <td> 0.000</td>  <th>  Jarque-Bera (JB):  </th> <td> 327.685</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Skew:</th>          <td>-0.507</td>  <th>  Prob(JB):          </th> <td>6.98e-72</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Kurtosis:</th>      <td> 3.715</td>  <th>  Cond. No.          </th> <td>    7.06</td>\n",
       "</tr>\n",
       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                      y   R-squared:                       0.046\n",
       "Model:                            OLS   Adj. R-squared:                  0.044\n",
       "Method:                 Least Squares   F-statistic:                     34.94\n",
       "Date:                Tue, 22 Dec 2020   Prob (F-statistic):           5.91e-48\n",
       "Time:                        07:57:11   Log-Likelihood:                -8089.8\n",
       "No. Observations:                5113   AIC:                         1.620e+04\n",
       "Df Residuals:                    5105   BIC:                         1.625e+04\n",
       "Df Model:                           7                                         \n",
       "Covariance Type:            nonrobust                                         \n",
       "===============================================================================================\n",
       "                                  coef    std err          t      P>|t|      [0.025      0.975]\n",
       "-----------------------------------------------------------------------------------------------\n",
       "const                           4.4259      0.027    163.862      0.000       4.373       4.479\n",
       "I Am Infected                   0.4204      0.091      4.609      0.000       0.242       0.599\n",
       "I Am Mourning A Loss            0.2982      0.089      3.345      0.001       0.123       0.473\n",
       "I Have Professional Contact     0.3584      0.075      4.806      0.000       0.212       0.505\n",
       "I Live With Someone             0.3625      0.095      3.817      0.000       0.176       0.549\n",
       "None                           -0.2314      0.037     -6.201      0.000      -0.305      -0.158\n",
       "Prefer Not To Say              -0.3549      0.090     -3.960      0.000      -0.531      -0.179\n",
       "Someone I Am Close To           0.1291      0.052      2.484      0.013       0.027       0.231\n",
       "==============================================================================\n",
       "Omnibus:                      257.832   Durbin-Watson:                   1.928\n",
       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              327.685\n",
       "Skew:                          -0.507   Prob(JB):                     6.98e-72\n",
       "Kurtosis:                       3.715   Cond. No.                         7.06\n",
       "==============================================================================\n",
       "\n",
       "Notes:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "\"\"\""
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# regression\n",
    "X = all_X.loc[:,covid]\n",
    "X.columns = X.columns.str.replace(r'^.*-', '', regex=True)\n",
    "X = sm.add_constant(X)\n",
    "\n",
    "model = sm.OLS(y, X)\n",
    "results = model.fit()\n",
    "results.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Work Situation due to the Pandemic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# correlations\n",
    "data = all_X.loc[:,work]\n",
    "data.columns = data.columns.str.replace(r'^.*-', '', regex=True)\n",
    "data['NEGATIVE EMOTIONS'] = y\n",
    "corr = data.corr()\n",
    "fig, ax = plt.subplots(figsize=(8, 8))\n",
    "cmap = sns.diverging_palette(230, 10, as_cmap=True)\n",
    "mask = np.triu(np.ones_like(corr))\n",
    "sns.heatmap(corr, cmap = cmap, fmt = '.2g', vmax = 1.0, vmin = -1.0, center = 0, square = True, \\\n",
    "            mask = mask, linewidths = 0.7, cbar_kws = {\"shrink\": 0.5}, annot = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>            <td>y</td>        <th>  R-squared:         </th> <td>   0.031</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.030</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   20.59</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Date:</th>             <td>Tue, 22 Dec 2020</td> <th>  Prob (F-statistic):</th> <td>5.41e-31</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Time:</th>                 <td>07:57:11</td>     <th>  Log-Likelihood:    </th> <td> -8128.2</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>      <td>  5113</td>      <th>  AIC:               </th> <td>1.627e+04</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Residuals:</th>          <td>  5104</td>      <th>  BIC:               </th> <td>1.633e+04</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Model:</th>              <td>     8</td>      <th>                     </th>     <td> </td>    \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>    \n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "            <td></td>              <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>const</th>                <td>    4.1616</td> <td>    0.040</td> <td>  102.782</td> <td> 0.000</td> <td>    4.082</td> <td>    4.241</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Homeschool Children</th>  <td>    0.0624</td> <td>    0.058</td> <td>    1.078</td> <td> 0.281</td> <td>   -0.051</td> <td>    0.176</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Job At Risk</th>          <td>    0.3548</td> <td>    0.070</td> <td>    5.062</td> <td> 0.000</td> <td>    0.217</td> <td>    0.492</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Lost Job</th>             <td>    0.3767</td> <td>    0.064</td> <td>    5.920</td> <td> 0.000</td> <td>    0.252</td> <td>    0.501</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Lower Income</th>         <td>    0.2733</td> <td>    0.048</td> <td>    5.737</td> <td> 0.000</td> <td>    0.180</td> <td>    0.367</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Now Work From Home</th>   <td>    0.2215</td> <td>    0.045</td> <td>    4.911</td> <td> 0.000</td> <td>    0.133</td> <td>    0.310</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Reduced Hours</th>        <td>    0.1502</td> <td>    0.050</td> <td>    2.981</td> <td> 0.003</td> <td>    0.051</td> <td>    0.249</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Still Go To Work</th>     <td>    0.0710</td> <td>    0.049</td> <td>    1.460</td> <td> 0.144</td> <td>   -0.024</td> <td>    0.166</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Still Work From Home</th> <td>    0.1422</td> <td>    0.049</td> <td>    2.922</td> <td> 0.003</td> <td>    0.047</td> <td>    0.238</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "  <th>Omnibus:</th>       <td>241.327</td> <th>  Durbin-Watson:     </th> <td>   1.921</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(Omnibus):</th> <td> 0.000</td>  <th>  Jarque-Bera (JB):  </th> <td> 303.769</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Skew:</th>          <td>-0.488</td>  <th>  Prob(JB):          </th> <td>1.09e-66</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Kurtosis:</th>      <td> 3.689</td>  <th>  Cond. No.          </th> <td>    5.91</td>\n",
       "</tr>\n",
       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                      y   R-squared:                       0.031\n",
       "Model:                            OLS   Adj. R-squared:                  0.030\n",
       "Method:                 Least Squares   F-statistic:                     20.59\n",
       "Date:                Tue, 22 Dec 2020   Prob (F-statistic):           5.41e-31\n",
       "Time:                        07:57:11   Log-Likelihood:                -8128.2\n",
       "No. Observations:                5113   AIC:                         1.627e+04\n",
       "Df Residuals:                    5104   BIC:                         1.633e+04\n",
       "Df Model:                           8                                         \n",
       "Covariance Type:            nonrobust                                         \n",
       "========================================================================================\n",
       "                           coef    std err          t      P>|t|      [0.025      0.975]\n",
       "----------------------------------------------------------------------------------------\n",
       "const                    4.1616      0.040    102.782      0.000       4.082       4.241\n",
       "Homeschool Children      0.0624      0.058      1.078      0.281      -0.051       0.176\n",
       "Job At Risk              0.3548      0.070      5.062      0.000       0.217       0.492\n",
       "Lost Job                 0.3767      0.064      5.920      0.000       0.252       0.501\n",
       "Lower Income             0.2733      0.048      5.737      0.000       0.180       0.367\n",
       "Now Work From Home       0.2215      0.045      4.911      0.000       0.133       0.310\n",
       "Reduced Hours            0.1502      0.050      2.981      0.003       0.051       0.249\n",
       "Still Go To Work         0.0710      0.049      1.460      0.144      -0.024       0.166\n",
       "Still Work From Home     0.1422      0.049      2.922      0.003       0.047       0.238\n",
       "==============================================================================\n",
       "Omnibus:                      241.327   Durbin-Watson:                   1.921\n",
       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              303.769\n",
       "Skew:                          -0.488   Prob(JB):                     1.09e-66\n",
       "Kurtosis:                       3.689   Cond. No.                         5.91\n",
       "==============================================================================\n",
       "\n",
       "Notes:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "\"\"\""
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# regression\n",
    "X = all_X.loc[:,work]\n",
    "X.columns = X.columns.str.replace(r'^.*-', '', regex=True)\n",
    "X = sm.add_constant(X)\n",
    "\n",
    "model = sm.OLS(y, X)\n",
    "results = model.fit()\n",
    "results.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Living Situation during the Pandemic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# correlations\n",
    "data = all_X.loc[:,living]\n",
    "data.columns = data.columns.str.replace(r'^.*-', '', regex=True)\n",
    "data['NEGATIVE EMOTIONS'] = y\n",
    "corr = data.corr()\n",
    "fig, ax = plt.subplots(figsize=(8, 8))\n",
    "cmap = sns.diverging_palette(230, 10, as_cmap=True)\n",
    "mask = np.triu(np.ones_like(corr))\n",
    "sns.heatmap(corr, cmap = cmap, fmt = '.2g', vmax = 1.0, vmin = -1.0, center = 0, square = True, \\\n",
    "            mask = mask, linewidths = 0.7, cbar_kws = {\"shrink\": 0.5}, annot = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>            <td>y</td>        <th>  R-squared:         </th> <td>   0.018</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.016</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   9.340</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Date:</th>             <td>Tue, 22 Dec 2020</td> <th>  Prob (F-statistic):</th> <td>1.61e-15</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Time:</th>                 <td>07:57:11</td>     <th>  Log-Likelihood:    </th> <td> -8163.1</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>      <td>  5113</td>      <th>  AIC:               </th> <td>1.635e+04</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Residuals:</th>          <td>  5102</td>      <th>  BIC:               </th> <td>1.642e+04</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Model:</th>              <td>    10</td>      <th>                     </th>     <td> </td>    \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>    \n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "     <td></td>        <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>const</th>   <td>    4.2284</td> <td>    0.050</td> <td>   83.734</td> <td> 0.000</td> <td>    4.129</td> <td>    4.327</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Alone</th>   <td>    0.1726</td> <td>    0.064</td> <td>    2.695</td> <td> 0.007</td> <td>    0.047</td> <td>    0.298</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Child</th>   <td>    0.2322</td> <td>    0.039</td> <td>    5.930</td> <td> 0.000</td> <td>    0.155</td> <td>    0.309</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Elderly</th> <td>   -0.1182</td> <td>    0.132</td> <td>   -0.898</td> <td> 0.369</td> <td>   -0.376</td> <td>    0.140</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Friend</th>  <td>    0.6204</td> <td>    0.132</td> <td>    4.703</td> <td> 0.000</td> <td>    0.362</td> <td>    0.879</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Other</th>   <td>    0.0524</td> <td>    0.126</td> <td>    0.416</td> <td> 0.678</td> <td>   -0.195</td> <td>    0.300</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Parent</th>  <td>    0.2042</td> <td>    0.054</td> <td>    3.775</td> <td> 0.000</td> <td>    0.098</td> <td>    0.310</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Partner</th> <td>    0.0048</td> <td>    0.050</td> <td>    0.096</td> <td> 0.924</td> <td>   -0.093</td> <td>    0.103</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Pet</th>     <td>   -0.0124</td> <td>    0.042</td> <td>   -0.295</td> <td> 0.768</td> <td>   -0.095</td> <td>    0.070</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Shared</th>  <td>    0.5020</td> <td>    0.121</td> <td>    4.159</td> <td> 0.000</td> <td>    0.265</td> <td>    0.739</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>SibCous</th> <td>    0.2208</td> <td>    0.088</td> <td>    2.501</td> <td> 0.012</td> <td>    0.048</td> <td>    0.394</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "  <th>Omnibus:</th>       <td>193.161</td> <th>  Durbin-Watson:     </th> <td>   1.902</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(Omnibus):</th> <td> 0.000</td>  <th>  Jarque-Bera (JB):  </th> <td> 233.791</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Skew:</th>          <td>-0.433</td>  <th>  Prob(JB):          </th> <td>1.71e-51</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Kurtosis:</th>      <td> 3.589</td>  <th>  Cond. No.          </th> <td>    10.6</td>\n",
       "</tr>\n",
       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                      y   R-squared:                       0.018\n",
       "Model:                            OLS   Adj. R-squared:                  0.016\n",
       "Method:                 Least Squares   F-statistic:                     9.340\n",
       "Date:                Tue, 22 Dec 2020   Prob (F-statistic):           1.61e-15\n",
       "Time:                        07:57:11   Log-Likelihood:                -8163.1\n",
       "No. Observations:                5113   AIC:                         1.635e+04\n",
       "Df Residuals:                    5102   BIC:                         1.642e+04\n",
       "Df Model:                          10                                         \n",
       "Covariance Type:            nonrobust                                         \n",
       "==============================================================================\n",
       "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
       "------------------------------------------------------------------------------\n",
       "const          4.2284      0.050     83.734      0.000       4.129       4.327\n",
       "Alone          0.1726      0.064      2.695      0.007       0.047       0.298\n",
       "Child          0.2322      0.039      5.930      0.000       0.155       0.309\n",
       "Elderly       -0.1182      0.132     -0.898      0.369      -0.376       0.140\n",
       "Friend         0.6204      0.132      4.703      0.000       0.362       0.879\n",
       "Other          0.0524      0.126      0.416      0.678      -0.195       0.300\n",
       "Parent         0.2042      0.054      3.775      0.000       0.098       0.310\n",
       "Partner        0.0048      0.050      0.096      0.924      -0.093       0.103\n",
       "Pet           -0.0124      0.042     -0.295      0.768      -0.095       0.070\n",
       "Shared         0.5020      0.121      4.159      0.000       0.265       0.739\n",
       "SibCous        0.2208      0.088      2.501      0.012       0.048       0.394\n",
       "==============================================================================\n",
       "Omnibus:                      193.161   Durbin-Watson:                   1.902\n",
       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              233.791\n",
       "Skew:                          -0.433   Prob(JB):                     1.71e-51\n",
       "Kurtosis:                       3.589   Cond. No.                         10.6\n",
       "==============================================================================\n",
       "\n",
       "Notes:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "\"\"\""
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# regression\n",
    "X = all_X.loc[:,living]\n",
    "X.columns = X.columns.str.replace(r'^.*-', '', regex=True)\n",
    "X = sm.add_constant(X)\n",
    "\n",
    "model = sm.OLS(y, X)\n",
    "results = model.fit()\n",
    "results.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# **Changes in Positive Emotions**\n",
    "\n",
    "The DV is the average of the variables referring to changes in the positive emotions/general wellbeing during the coronavirus crisis:\n",
    "- Positive Valence\n",
    "- Energetic Arousal\n",
    "- General Health"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "y = (all_data.loc[:,pos_emotions]).mean(skipna=True,axis=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Contact with the COVID-19 Virus"
   ]
  },
  {
   "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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\n",
      "text/plain": [
       "<Figure size 576x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# correlations\n",
    "data = all_X.loc[:,covid]\n",
    "data.columns = data.columns.str.replace(r'^.*-', '', regex=True)\n",
    "data['POSITIVE EMOTIONS'] = y\n",
    "corr = data.corr()\n",
    "fig, ax = plt.subplots(figsize=(8, 8))\n",
    "cmap = sns.diverging_palette(230, 10, as_cmap=True)\n",
    "mask = np.triu(np.ones_like(corr))\n",
    "sns.heatmap(corr, cmap = cmap, fmt = '.2g', vmax = 1.0, vmin = -1.0, center = 0, square = True, \\\n",
    "            mask = mask, linewidths = 0.7, cbar_kws = {\"shrink\": 0.5}, annot = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>            <td>y</td>        <th>  R-squared:         </th> <td>   0.067</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.066</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   52.43</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Date:</th>             <td>Tue, 22 Dec 2020</td> <th>  Prob (F-statistic):</th> <td>1.30e-72</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Time:</th>                 <td>07:57:12</td>     <th>  Log-Likelihood:    </th> <td> -7506.8</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>      <td>  5113</td>      <th>  AIC:               </th> <td>1.503e+04</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Residuals:</th>          <td>  5105</td>      <th>  BIC:               </th> <td>1.508e+04</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Model:</th>              <td>     7</td>      <th>                     </th>     <td> </td>    \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>    \n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "               <td></td>                  <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>const</th>                       <td>    3.9000</td> <td>    0.024</td> <td>  161.831</td> <td> 0.000</td> <td>    3.853</td> <td>    3.947</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>I Am Infected</th>               <td>    0.4435</td> <td>    0.081</td> <td>    5.449</td> <td> 0.000</td> <td>    0.284</td> <td>    0.603</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>I Am Mourning A Loss</th>        <td>    0.2496</td> <td>    0.080</td> <td>    3.137</td> <td> 0.002</td> <td>    0.094</td> <td>    0.406</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>I Have Professional Contact</th> <td>    0.2803</td> <td>    0.067</td> <td>    4.213</td> <td> 0.000</td> <td>    0.150</td> <td>    0.411</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>I Live With Someone</th>         <td>    0.6388</td> <td>    0.085</td> <td>    7.539</td> <td> 0.000</td> <td>    0.473</td> <td>    0.805</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>None</th>                        <td>   -0.3348</td> <td>    0.033</td> <td>  -10.055</td> <td> 0.000</td> <td>   -0.400</td> <td>   -0.270</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prefer Not To Say</th>           <td>   -0.1358</td> <td>    0.080</td> <td>   -1.698</td> <td> 0.090</td> <td>   -0.293</td> <td>    0.021</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Someone I Am Close To</th>       <td>   -0.2514</td> <td>    0.046</td> <td>   -5.420</td> <td> 0.000</td> <td>   -0.342</td> <td>   -0.160</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "  <th>Omnibus:</th>       <td>72.504</td> <th>  Durbin-Watson:     </th> <td>   1.734</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(Omnibus):</th> <td> 0.000</td> <th>  Jarque-Bera (JB):  </th> <td> 122.373</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Skew:</th>          <td> 0.101</td> <th>  Prob(JB):          </th> <td>2.67e-27</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Kurtosis:</th>      <td> 3.730</td> <th>  Cond. No.          </th> <td>    7.06</td>\n",
       "</tr>\n",
       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                      y   R-squared:                       0.067\n",
       "Model:                            OLS   Adj. R-squared:                  0.066\n",
       "Method:                 Least Squares   F-statistic:                     52.43\n",
       "Date:                Tue, 22 Dec 2020   Prob (F-statistic):           1.30e-72\n",
       "Time:                        07:57:12   Log-Likelihood:                -7506.8\n",
       "No. Observations:                5113   AIC:                         1.503e+04\n",
       "Df Residuals:                    5105   BIC:                         1.508e+04\n",
       "Df Model:                           7                                         \n",
       "Covariance Type:            nonrobust                                         \n",
       "===============================================================================================\n",
       "                                  coef    std err          t      P>|t|      [0.025      0.975]\n",
       "-----------------------------------------------------------------------------------------------\n",
       "const                           3.9000      0.024    161.831      0.000       3.853       3.947\n",
       "I Am Infected                   0.4435      0.081      5.449      0.000       0.284       0.603\n",
       "I Am Mourning A Loss            0.2496      0.080      3.137      0.002       0.094       0.406\n",
       "I Have Professional Contact     0.2803      0.067      4.213      0.000       0.150       0.411\n",
       "I Live With Someone             0.6388      0.085      7.539      0.000       0.473       0.805\n",
       "None                           -0.3348      0.033    -10.055      0.000      -0.400      -0.270\n",
       "Prefer Not To Say              -0.1358      0.080     -1.698      0.090      -0.293       0.021\n",
       "Someone I Am Close To          -0.2514      0.046     -5.420      0.000      -0.342      -0.160\n",
       "==============================================================================\n",
       "Omnibus:                       72.504   Durbin-Watson:                   1.734\n",
       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              122.373\n",
       "Skew:                           0.101   Prob(JB):                     2.67e-27\n",
       "Kurtosis:                       3.730   Cond. No.                         7.06\n",
       "==============================================================================\n",
       "\n",
       "Notes:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "\"\"\""
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# regression\n",
    "X = all_X.loc[:,covid]\n",
    "X.columns = X.columns.str.replace(r'^.*-', '', regex=True)\n",
    "X = sm.add_constant(X)\n",
    "\n",
    "model = sm.OLS(y, X)\n",
    "results = model.fit()\n",
    "results.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Work Situation due to the Pandemic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# correlations\n",
    "data = all_X.loc[:,work]\n",
    "data.columns = data.columns.str.replace(r'^.*-', '', regex=True)\n",
    "data['POSITIVE EMOTIONS'] = y\n",
    "corr = data.corr()\n",
    "fig, ax = plt.subplots(figsize=(8, 8))\n",
    "cmap = sns.diverging_palette(230, 10, as_cmap=True)\n",
    "mask = np.triu(np.ones_like(corr))\n",
    "sns.heatmap(corr, cmap = cmap, fmt = '.2g', vmax = 1.0, vmin = -1.0, center = 0, square = True, \\\n",
    "            mask = mask, linewidths = 0.7, cbar_kws = {\"shrink\": 0.5}, annot = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>            <td>y</td>        <th>  R-squared:         </th> <td>   0.059</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.057</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   39.70</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Date:</th>             <td>Tue, 22 Dec 2020</td> <th>  Prob (F-statistic):</th> <td>6.96e-62</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Time:</th>                 <td>07:57:12</td>     <th>  Log-Likelihood:    </th> <td> -7530.0</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>      <td>  5113</td>      <th>  AIC:               </th> <td>1.508e+04</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Residuals:</th>          <td>  5104</td>      <th>  BIC:               </th> <td>1.514e+04</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Model:</th>              <td>     8</td>      <th>                     </th>     <td> </td>    \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>    \n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "            <td></td>              <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>const</th>                <td>    3.3097</td> <td>    0.036</td> <td>   91.889</td> <td> 0.000</td> <td>    3.239</td> <td>    3.380</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Homeschool Children</th>  <td>    0.0920</td> <td>    0.051</td> <td>    1.788</td> <td> 0.074</td> <td>   -0.009</td> <td>    0.193</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Job At Risk</th>          <td>    0.1094</td> <td>    0.062</td> <td>    1.754</td> <td> 0.079</td> <td>   -0.013</td> <td>    0.232</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Lost Job</th>             <td>    0.3968</td> <td>    0.057</td> <td>    7.011</td> <td> 0.000</td> <td>    0.286</td> <td>    0.508</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Lower Income</th>         <td>    0.1133</td> <td>    0.042</td> <td>    2.673</td> <td> 0.008</td> <td>    0.030</td> <td>    0.196</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Now Work From Home</th>   <td>    0.5147</td> <td>    0.040</td> <td>   12.829</td> <td> 0.000</td> <td>    0.436</td> <td>    0.593</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Reduced Hours</th>        <td>    0.4747</td> <td>    0.045</td> <td>   10.591</td> <td> 0.000</td> <td>    0.387</td> <td>    0.563</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Still Go To Work</th>     <td>    0.4369</td> <td>    0.043</td> <td>   10.097</td> <td> 0.000</td> <td>    0.352</td> <td>    0.522</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Still Work From Home</th> <td>    0.4938</td> <td>    0.043</td> <td>   11.408</td> <td> 0.000</td> <td>    0.409</td> <td>    0.579</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "  <th>Omnibus:</th>       <td>117.723</td> <th>  Durbin-Watson:     </th> <td>   1.713</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(Omnibus):</th> <td> 0.000</td>  <th>  Jarque-Bera (JB):  </th> <td> 173.811</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Skew:</th>          <td> 0.247</td>  <th>  Prob(JB):          </th> <td>1.81e-38</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Kurtosis:</th>      <td> 3.757</td>  <th>  Cond. No.          </th> <td>    5.91</td>\n",
       "</tr>\n",
       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                      y   R-squared:                       0.059\n",
       "Model:                            OLS   Adj. R-squared:                  0.057\n",
       "Method:                 Least Squares   F-statistic:                     39.70\n",
       "Date:                Tue, 22 Dec 2020   Prob (F-statistic):           6.96e-62\n",
       "Time:                        07:57:12   Log-Likelihood:                -7530.0\n",
       "No. Observations:                5113   AIC:                         1.508e+04\n",
       "Df Residuals:                    5104   BIC:                         1.514e+04\n",
       "Df Model:                           8                                         \n",
       "Covariance Type:            nonrobust                                         \n",
       "========================================================================================\n",
       "                           coef    std err          t      P>|t|      [0.025      0.975]\n",
       "----------------------------------------------------------------------------------------\n",
       "const                    3.3097      0.036     91.889      0.000       3.239       3.380\n",
       "Homeschool Children      0.0920      0.051      1.788      0.074      -0.009       0.193\n",
       "Job At Risk              0.1094      0.062      1.754      0.079      -0.013       0.232\n",
       "Lost Job                 0.3968      0.057      7.011      0.000       0.286       0.508\n",
       "Lower Income             0.1133      0.042      2.673      0.008       0.030       0.196\n",
       "Now Work From Home       0.5147      0.040     12.829      0.000       0.436       0.593\n",
       "Reduced Hours            0.4747      0.045     10.591      0.000       0.387       0.563\n",
       "Still Go To Work         0.4369      0.043     10.097      0.000       0.352       0.522\n",
       "Still Work From Home     0.4938      0.043     11.408      0.000       0.409       0.579\n",
       "==============================================================================\n",
       "Omnibus:                      117.723   Durbin-Watson:                   1.713\n",
       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              173.811\n",
       "Skew:                           0.247   Prob(JB):                     1.81e-38\n",
       "Kurtosis:                       3.757   Cond. No.                         5.91\n",
       "==============================================================================\n",
       "\n",
       "Notes:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "\"\"\""
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# regression\n",
    "X = all_X.loc[:,work]\n",
    "X.columns = X.columns.str.replace(r'^.*-', '', regex=True)\n",
    "X = sm.add_constant(X)\n",
    "\n",
    "model = sm.OLS(y, X)\n",
    "results = model.fit()\n",
    "results.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Living Situation during the Pandemic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# correlations\n",
    "data = all_X.loc[:,living]\n",
    "data.columns = data.columns.str.replace(r'^.*-', '', regex=True)\n",
    "data['POSITIVE EMOTIONS'] = y\n",
    "corr = data.corr()\n",
    "fig, ax = plt.subplots(figsize=(8, 8))\n",
    "cmap = sns.diverging_palette(230, 10, as_cmap=True)\n",
    "mask = np.triu(np.ones_like(corr))\n",
    "sns.heatmap(corr, cmap = cmap, fmt = '.2g', vmax = 1.0, vmin = -1.0, center = 0, square = True, \\\n",
    "            mask = mask, linewidths = 0.7, cbar_kws = {\"shrink\": 0.5}, annot = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>            <td>y</td>        <th>  R-squared:         </th> <td>   0.034</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.033</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   18.21</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Date:</th>             <td>Tue, 22 Dec 2020</td> <th>  Prob (F-statistic):</th> <td>3.65e-33</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Time:</th>                 <td>07:57:13</td>     <th>  Log-Likelihood:    </th> <td> -7594.6</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>      <td>  5113</td>      <th>  AIC:               </th> <td>1.521e+04</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Residuals:</th>          <td>  5102</td>      <th>  BIC:               </th> <td>1.528e+04</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Model:</th>              <td>    10</td>      <th>                     </th>     <td> </td>    \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>    \n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "     <td></td>        <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>const</th>   <td>    3.4412</td> <td>    0.045</td> <td>   76.158</td> <td> 0.000</td> <td>    3.353</td> <td>    3.530</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Alone</th>   <td>    0.2289</td> <td>    0.057</td> <td>    3.993</td> <td> 0.000</td> <td>    0.117</td> <td>    0.341</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Child</th>   <td>    0.3170</td> <td>    0.035</td> <td>    9.045</td> <td> 0.000</td> <td>    0.248</td> <td>    0.386</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Elderly</th> <td>    0.4024</td> <td>    0.118</td> <td>    3.418</td> <td> 0.001</td> <td>    0.172</td> <td>    0.633</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Friend</th>  <td>    0.4171</td> <td>    0.118</td> <td>    3.533</td> <td> 0.000</td> <td>    0.186</td> <td>    0.648</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Other</th>   <td>   -0.0084</td> <td>    0.113</td> <td>   -0.075</td> <td> 0.940</td> <td>   -0.230</td> <td>    0.213</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Parent</th>  <td>    0.3712</td> <td>    0.048</td> <td>    7.669</td> <td> 0.000</td> <td>    0.276</td> <td>    0.466</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Partner</th> <td>    0.2664</td> <td>    0.045</td> <td>    5.947</td> <td> 0.000</td> <td>    0.179</td> <td>    0.354</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Pet</th>     <td>   -0.1012</td> <td>    0.038</td> <td>   -2.693</td> <td> 0.007</td> <td>   -0.175</td> <td>   -0.028</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Shared</th>  <td>   -0.1080</td> <td>    0.108</td> <td>   -1.000</td> <td> 0.318</td> <td>   -0.320</td> <td>    0.104</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>SibCous</th> <td>   -0.0233</td> <td>    0.079</td> <td>   -0.295</td> <td> 0.768</td> <td>   -0.178</td> <td>    0.132</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "  <th>Omnibus:</th>       <td>153.088</td> <th>  Durbin-Watson:     </th> <td>   1.685</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(Omnibus):</th> <td> 0.000</td>  <th>  Jarque-Bera (JB):  </th> <td> 216.431</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Skew:</th>          <td> 0.318</td>  <th>  Prob(JB):          </th> <td>1.01e-47</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Kurtosis:</th>      <td> 3.781</td>  <th>  Cond. No.          </th> <td>    10.6</td>\n",
       "</tr>\n",
       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                      y   R-squared:                       0.034\n",
       "Model:                            OLS   Adj. R-squared:                  0.033\n",
       "Method:                 Least Squares   F-statistic:                     18.21\n",
       "Date:                Tue, 22 Dec 2020   Prob (F-statistic):           3.65e-33\n",
       "Time:                        07:57:13   Log-Likelihood:                -7594.6\n",
       "No. Observations:                5113   AIC:                         1.521e+04\n",
       "Df Residuals:                    5102   BIC:                         1.528e+04\n",
       "Df Model:                          10                                         \n",
       "Covariance Type:            nonrobust                                         \n",
       "==============================================================================\n",
       "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
       "------------------------------------------------------------------------------\n",
       "const          3.4412      0.045     76.158      0.000       3.353       3.530\n",
       "Alone          0.2289      0.057      3.993      0.000       0.117       0.341\n",
       "Child          0.3170      0.035      9.045      0.000       0.248       0.386\n",
       "Elderly        0.4024      0.118      3.418      0.001       0.172       0.633\n",
       "Friend         0.4171      0.118      3.533      0.000       0.186       0.648\n",
       "Other         -0.0084      0.113     -0.075      0.940      -0.230       0.213\n",
       "Parent         0.3712      0.048      7.669      0.000       0.276       0.466\n",
       "Partner        0.2664      0.045      5.947      0.000       0.179       0.354\n",
       "Pet           -0.1012      0.038     -2.693      0.007      -0.175      -0.028\n",
       "Shared        -0.1080      0.108     -1.000      0.318      -0.320       0.104\n",
       "SibCous       -0.0233      0.079     -0.295      0.768      -0.178       0.132\n",
       "==============================================================================\n",
       "Omnibus:                      153.088   Durbin-Watson:                   1.685\n",
       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              216.431\n",
       "Skew:                           0.318   Prob(JB):                     1.01e-47\n",
       "Kurtosis:                       3.781   Cond. No.                         10.6\n",
       "==============================================================================\n",
       "\n",
       "Notes:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "\"\"\""
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# regression\n",
    "X = all_X.loc[:,living]\n",
    "X.columns = X.columns.str.replace(r'^.*-', '', regex=True)\n",
    "X = sm.add_constant(X)\n",
    "\n",
    "model = sm.OLS(y, X)\n",
    "results = model.fit()\n",
    "results.summary()"
   ]
  }
 ],
 "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": "3.8.10"
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}