COVID_Research_Project.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "fa131238",
   "metadata": {},
   "source": [
    "# COVID Data: Correlations with Distress Levels"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "43c660a9",
   "metadata": {},
   "source": [
    "Run the following cell:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "082e4561",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import os\n",
    "import plotly.io as pio\n",
    "pio.renderers.default= 'iframe'\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "import numpy as np\n",
    "import plotly.figure_factory as ff\n",
    "import matplotlib.pyplot as plt\n",
    "from scipy import stats\n",
    "from sklearn.linear_model import LinearRegression"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b5ff80b4",
   "metadata": {},
   "source": [
    "Run the following line in conda Powershell prompt:"
   ]
  },
  {
   "cell_type": "raw",
   "id": "b0586ce8",
   "metadata": {},
   "source": [
    "conda install -c conda-forge pyreadstat"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7ceec490",
   "metadata": {},
   "source": [
    "Visit https://healthpolicy.ucla.edu/chis/data/Pages/public-use-data.aspx and create an account. Click on the data files link, and scroll to the bottom of the page. Download the adult SPSS file from the 2020 CHIS column.\n",
    "\n",
    "Get the absolute directory and paste it between the quotation marks.\n",
    "\n",
    "(more info: https://stackoverflow.com/questions/5265702/how-to-get-full-path-of-a-file)\n",
    "\n",
    "Run the following code. If it doesn't run, make sure you downloaded the SPSS file, unzipped the file, obtained the file's absolute directory, and pasted it correctly."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "4df81bf9",
   "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>AA5C</th>\n",
       "      <th>AA5G</th>\n",
       "      <th>AB1</th>\n",
       "      <th>AB112</th>\n",
       "      <th>AB17</th>\n",
       "      <th>AB18</th>\n",
       "      <th>AB22V2</th>\n",
       "      <th>AB23_P1</th>\n",
       "      <th>AB24</th>\n",
       "      <th>AB25</th>\n",
       "      <th>...</th>\n",
       "      <th>USUAL_TP</th>\n",
       "      <th>VOTE_ENG2</th>\n",
       "      <th>VOTE_RSNNO</th>\n",
       "      <th>WEIGHK_P</th>\n",
       "      <th>WGHTK_P</th>\n",
       "      <th>WGHTP_P</th>\n",
       "      <th>WHOBMI</th>\n",
       "      <th>WORK2</th>\n",
       "      <th>WRKST_P1</th>\n",
       "      <th>YRUS_P1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>GOOD</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>...</td>\n",
       "      <td>DOC OFFICE/HMO/KAISER</td>\n",
       "      <td>SOMETIMES ENGAGED</td>\n",
       "      <td>VOTING DOESN’T MAKE A DIFFERENCE</td>\n",
       "      <td>71.67</td>\n",
       "      <td>71.67</td>\n",
       "      <td>158.0</td>\n",
       "      <td>23.0 - 27.49 (INCREASED RISK)</td>\n",
       "      <td>NONE</td>\n",
       "      <td>FULL-TIME EMPLOYMENT (21+ HRS/WEEK)</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>VERY GOOD</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>...</td>\n",
       "      <td>DOC OFFICE/HMO/KAISER</td>\n",
       "      <td>SOMETIMES ENGAGED</td>\n",
       "      <td>TOO BUSY OR FORGOT</td>\n",
       "      <td>72.57</td>\n",
       "      <td>72.57</td>\n",
       "      <td>160.0</td>\n",
       "      <td>23.0 - 27.49 (INCREASED RISK)</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>UNEMPLOYED, NOT LOOKING FOR WORK</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>VERY GOOD</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>...</td>\n",
       "      <td>DOC OFFICE/HMO/KAISER</td>\n",
       "      <td>ALWAYS ENGAGED</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>77.11</td>\n",
       "      <td>77.11</td>\n",
       "      <td>170.0</td>\n",
       "      <td>27.5 OR HIGHER (HIGHER HIGH RISK)</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>UNEMPLOYED, NOT LOOKING FOR WORK</td>\n",
       "      <td>15-19 YEARS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>GOOD</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>YES</td>\n",
       "      <td>NO</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>...</td>\n",
       "      <td>DOC OFFICE/HMO/KAISER</td>\n",
       "      <td>ALWAYS ENGAGED</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>49.90</td>\n",
       "      <td>49.90</td>\n",
       "      <td>110.0</td>\n",
       "      <td>18.5 - 22.99 (ACCEPTABLE RISK)</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>UNEMPLOYED, NOT LOOKING FOR WORK</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>YES</td>\n",
       "      <td>FAIR</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>...</td>\n",
       "      <td>DOC OFFICE/HMO/KAISER</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>104.33</td>\n",
       "      <td>104.33</td>\n",
       "      <td>230.0</td>\n",
       "      <td>27.5 OR HIGHER (HIGHER HIGH RISK)</td>\n",
       "      <td>MODERATE</td>\n",
       "      <td>FULL-TIME EMPLOYMENT (21+ HRS/WEEK)</td>\n",
       "      <td>15-19 YEARS</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21944</th>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>VERY GOOD</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>...</td>\n",
       "      <td>COMMUN/GOV CLIN, COMMUN HOSP</td>\n",
       "      <td>SOMETIMES ENGAGED</td>\n",
       "      <td>DON’T KNOW ENOUGH ABOUT CANDIDATES/ISSUES</td>\n",
       "      <td>65.77</td>\n",
       "      <td>65.77</td>\n",
       "      <td>145.0</td>\n",
       "      <td>23.0 - 27.49 (INCREASED RISK)</td>\n",
       "      <td>MODERATE</td>\n",
       "      <td>FULL-TIME EMPLOYMENT (21+ HRS/WEEK)</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21945</th>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>EXCELLENT</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>...</td>\n",
       "      <td>DOC OFFICE/HMO/KAISER</td>\n",
       "      <td>ALWAYS ENGAGED</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>61.69</td>\n",
       "      <td>61.69</td>\n",
       "      <td>136.0</td>\n",
       "      <td>23.0 - 27.49 (INCREASED RISK)</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>FULL-TIME EMPLOYMENT (21+ HRS/WEEK)</td>\n",
       "      <td>15-19 YEARS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21946</th>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>VERY GOOD</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>YES</td>\n",
       "      <td>YES</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>...</td>\n",
       "      <td>DOC OFFICE/HMO/KAISER</td>\n",
       "      <td>ALWAYS ENGAGED</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>88.45</td>\n",
       "      <td>88.45</td>\n",
       "      <td>195.0</td>\n",
       "      <td>27.5 OR HIGHER (HIGHER HIGH RISK)</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>FULL-TIME EMPLOYMENT (21+ HRS/WEEK)</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21947</th>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>GOOD</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>...</td>\n",
       "      <td>COMMUN/GOV CLIN, COMMUN HOSP</td>\n",
       "      <td>NEVER ENGAGED</td>\n",
       "      <td>DON'T LIKE OR CARE ABOUT POLITICS</td>\n",
       "      <td>65.77</td>\n",
       "      <td>65.77</td>\n",
       "      <td>145.0</td>\n",
       "      <td>18.5 - 22.99 (ACCEPTABLE RISK)</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>UNEMPLOYED, NOT LOOKING FOR WORK</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21948</th>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>YES</td>\n",
       "      <td>VERY GOOD</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>NO</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>...</td>\n",
       "      <td>COMMUN/GOV CLIN, COMMUN HOSP</td>\n",
       "      <td>ALWAYS ENGAGED</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>63.50</td>\n",
       "      <td>63.50</td>\n",
       "      <td>140.0</td>\n",
       "      <td>23.0 - 27.49 (INCREASED RISK)</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "      <td>UNEMPLOYED, NOT LOOKING FOR WORK</td>\n",
       "      <td>INAPPLICABLE</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>21949 rows × 604 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "               AA5C          AA5G        AB1         AB112 AB17          AB18  \\\n",
       "0      INAPPLICABLE  INAPPLICABLE       GOOD  INAPPLICABLE   NO  INAPPLICABLE   \n",
       "1      INAPPLICABLE  INAPPLICABLE  VERY GOOD  INAPPLICABLE   NO  INAPPLICABLE   \n",
       "2      INAPPLICABLE  INAPPLICABLE  VERY GOOD  INAPPLICABLE   NO  INAPPLICABLE   \n",
       "3      INAPPLICABLE  INAPPLICABLE       GOOD  INAPPLICABLE  YES            NO   \n",
       "4      INAPPLICABLE           YES       FAIR  INAPPLICABLE   NO  INAPPLICABLE   \n",
       "...             ...           ...        ...           ...  ...           ...   \n",
       "21944  INAPPLICABLE  INAPPLICABLE  VERY GOOD  INAPPLICABLE   NO  INAPPLICABLE   \n",
       "21945  INAPPLICABLE  INAPPLICABLE  EXCELLENT  INAPPLICABLE   NO  INAPPLICABLE   \n",
       "21946  INAPPLICABLE  INAPPLICABLE  VERY GOOD  INAPPLICABLE  YES           YES   \n",
       "21947  INAPPLICABLE  INAPPLICABLE       GOOD  INAPPLICABLE   NO  INAPPLICABLE   \n",
       "21948  INAPPLICABLE           YES  VERY GOOD  INAPPLICABLE   NO  INAPPLICABLE   \n",
       "\n",
       "      AB22V2       AB23_P1          AB24          AB25  ...  \\\n",
       "0         NO  INAPPLICABLE  INAPPLICABLE  INAPPLICABLE  ...   \n",
       "1         NO  INAPPLICABLE  INAPPLICABLE  INAPPLICABLE  ...   \n",
       "2         NO  INAPPLICABLE  INAPPLICABLE  INAPPLICABLE  ...   \n",
       "3         NO  INAPPLICABLE  INAPPLICABLE  INAPPLICABLE  ...   \n",
       "4         NO  INAPPLICABLE  INAPPLICABLE  INAPPLICABLE  ...   \n",
       "...      ...           ...           ...           ...  ...   \n",
       "21944     NO  INAPPLICABLE  INAPPLICABLE  INAPPLICABLE  ...   \n",
       "21945     NO  INAPPLICABLE  INAPPLICABLE  INAPPLICABLE  ...   \n",
       "21946     NO  INAPPLICABLE  INAPPLICABLE  INAPPLICABLE  ...   \n",
       "21947     NO  INAPPLICABLE  INAPPLICABLE  INAPPLICABLE  ...   \n",
       "21948     NO  INAPPLICABLE  INAPPLICABLE  INAPPLICABLE  ...   \n",
       "\n",
       "                           USUAL_TP          VOTE_ENG2  \\\n",
       "0             DOC OFFICE/HMO/KAISER  SOMETIMES ENGAGED   \n",
       "1             DOC OFFICE/HMO/KAISER  SOMETIMES ENGAGED   \n",
       "2             DOC OFFICE/HMO/KAISER     ALWAYS ENGAGED   \n",
       "3             DOC OFFICE/HMO/KAISER     ALWAYS ENGAGED   \n",
       "4             DOC OFFICE/HMO/KAISER       INAPPLICABLE   \n",
       "...                             ...                ...   \n",
       "21944  COMMUN/GOV CLIN, COMMUN HOSP  SOMETIMES ENGAGED   \n",
       "21945         DOC OFFICE/HMO/KAISER     ALWAYS ENGAGED   \n",
       "21946         DOC OFFICE/HMO/KAISER     ALWAYS ENGAGED   \n",
       "21947  COMMUN/GOV CLIN, COMMUN HOSP      NEVER ENGAGED   \n",
       "21948  COMMUN/GOV CLIN, COMMUN HOSP     ALWAYS ENGAGED   \n",
       "\n",
       "                                      VOTE_RSNNO WEIGHK_P WGHTK_P WGHTP_P  \\\n",
       "0               VOTING DOESN’T MAKE A DIFFERENCE    71.67   71.67   158.0   \n",
       "1                             TOO BUSY OR FORGOT    72.57   72.57   160.0   \n",
       "2                                   INAPPLICABLE    77.11   77.11   170.0   \n",
       "3                                   INAPPLICABLE    49.90   49.90   110.0   \n",
       "4                                   INAPPLICABLE   104.33  104.33   230.0   \n",
       "...                                          ...      ...     ...     ...   \n",
       "21944  DON’T KNOW ENOUGH ABOUT CANDIDATES/ISSUES    65.77   65.77   145.0   \n",
       "21945                               INAPPLICABLE    61.69   61.69   136.0   \n",
       "21946                               INAPPLICABLE    88.45   88.45   195.0   \n",
       "21947          DON'T LIKE OR CARE ABOUT POLITICS    65.77   65.77   145.0   \n",
       "21948                               INAPPLICABLE    63.50   63.50   140.0   \n",
       "\n",
       "                                  WHOBMI         WORK2  \\\n",
       "0          23.0 - 27.49 (INCREASED RISK)          NONE   \n",
       "1          23.0 - 27.49 (INCREASED RISK)  INAPPLICABLE   \n",
       "2      27.5 OR HIGHER (HIGHER HIGH RISK)  INAPPLICABLE   \n",
       "3         18.5 - 22.99 (ACCEPTABLE RISK)  INAPPLICABLE   \n",
       "4      27.5 OR HIGHER (HIGHER HIGH RISK)      MODERATE   \n",
       "...                                  ...           ...   \n",
       "21944      23.0 - 27.49 (INCREASED RISK)      MODERATE   \n",
       "21945      23.0 - 27.49 (INCREASED RISK)  INAPPLICABLE   \n",
       "21946  27.5 OR HIGHER (HIGHER HIGH RISK)  INAPPLICABLE   \n",
       "21947     18.5 - 22.99 (ACCEPTABLE RISK)  INAPPLICABLE   \n",
       "21948      23.0 - 27.49 (INCREASED RISK)  INAPPLICABLE   \n",
       "\n",
       "                                  WRKST_P1       YRUS_P1  \n",
       "0      FULL-TIME EMPLOYMENT (21+ HRS/WEEK)  INAPPLICABLE  \n",
       "1         UNEMPLOYED, NOT LOOKING FOR WORK  INAPPLICABLE  \n",
       "2         UNEMPLOYED, NOT LOOKING FOR WORK   15-19 YEARS  \n",
       "3         UNEMPLOYED, NOT LOOKING FOR WORK  INAPPLICABLE  \n",
       "4      FULL-TIME EMPLOYMENT (21+ HRS/WEEK)   15-19 YEARS  \n",
       "...                                    ...           ...  \n",
       "21944  FULL-TIME EMPLOYMENT (21+ HRS/WEEK)  INAPPLICABLE  \n",
       "21945  FULL-TIME EMPLOYMENT (21+ HRS/WEEK)   15-19 YEARS  \n",
       "21946  FULL-TIME EMPLOYMENT (21+ HRS/WEEK)  INAPPLICABLE  \n",
       "21947     UNEMPLOYED, NOT LOOKING FOR WORK  INAPPLICABLE  \n",
       "21948     UNEMPLOYED, NOT LOOKING FOR WORK  INAPPLICABLE  \n",
       "\n",
       "[21949 rows x 604 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# dataframe from https://healthpolicy.ucla.edu/chis/data/Pages/public-use-data.aspx\n",
    "\n",
    "adult_df = pd.read_spss(r\"C:\\Users\\ryvo1\\Downloads\\ADULT_SPSS_PUF_2020\\SPSS\\ADULT.sav\")\n",
    "adult_df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6f98087a",
   "metadata": {},
   "source": [
    "What do these column names mean?\n",
    "\n",
    "Download the adult SAS file from the 2020 CHIS column. Unzip it and open ADULT_LABEL.SAS.\n",
    "\n",
    "Open the three label files in jupyterlab (or at least that's what I'm using), and we see the data categories associated with the labels.\n",
    "\n",
    "#### ADULT_LABEL.SAS should look like this:"
   ]
  },
  {
   "attachments": {
    "image.png": {
     "image/png": "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"
    }
   },
   "cell_type": "markdown",
   "id": "1cf1952a",
   "metadata": {},
   "source": [
    "![image.png](attachment:image.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b11be15d",
   "metadata": {},
   "source": [
    "### Representing the data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "add1704c",
   "metadata": {},
   "source": [
    "We want to find correlations between one of these columns in adult_df and the DISTRESS levels of a patient (given by 'DISTRESS', which is another column in adult_df).\n",
    "\n",
    "For example, for categorical variables like \"CV1\" (Ever had or thought had COVID-19, where respondents answer yes/no), we start by getting the proportions of respondents who said \"YES\" to possessing the COVID-related trait to all respondents. Then, we aggregate each patient's answer with their distress levels. Distress levels are reported by patient on a scale of 0-24. \n",
    "\n",
    "Informally, below is a neat plotly histogram which shows the counts of COVID havers per distress level. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "619b989b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<iframe\n",
       "    scrolling=\"no\"\n",
       "    width=\"620px\"\n",
       "    height=\"620\"\n",
       "    src=\"iframe_figures/figure_3.html\"\n",
       "    frameborder=\"0\"\n",
       "    allowfullscreen\n",
       "></iframe>\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# CV1           =  \"EVER HAD OR THOUGHT HAD COVID-19\"\n",
    "# DISTRESS      =  \"SERIOUS PSYCHOLOGICAL DISTRESS\"\n",
    "\n",
    "fig = px.histogram(adult_df, \n",
    "x = \"CV1\", \n",
    "color = \"DISTRESS\", \n",
    "width = 600,\n",
    "height = 600)\n",
    "\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bafa9d85",
   "metadata": {},
   "source": [
    "We want to see how 'DISTRESS' is affected by possessing the COVID related trait. Here is another histogram, showing how CV1 affects distress levels."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "60496468",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<iframe\n",
       "    scrolling=\"no\"\n",
       "    width=\"620px\"\n",
       "    height=\"620\"\n",
       "    src=\"iframe_figures/figure_4.html\"\n",
       "    frameborder=\"0\"\n",
       "    allowfullscreen\n",
       "></iframe>\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = px.histogram(adult_df, \n",
    "x = \"DISTRESS\", \n",
    "color = \"CV1\", \n",
    "width = 600,\n",
    "height = 600,\n",
    "marginal = \"box\", # or violin, rug\n",
    "hover_data = adult_df.columns)\n",
    "\n",
    "fig.update_layout(barmode='overlay')\n",
    "\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7196163c",
   "metadata": {},
   "source": [
    "People who respond \"YES\" to CV1 (so they do have/ think they've had COVID) tend to have higher DISTRESS levels, as the box-and-whisker shows that their median DISTRESS levels and interquartile range are placed higher than those for the people who responded \"NO\" to CV1."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "73c978a8",
   "metadata": {},
   "source": [
    "##### Now, let's make a more specific model of how distress levels change for each instance of CV1 (thinks they had COVID, doesn't think they had COVID):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "19e9e1f7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>AA5C</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DISTRESS</th>\n",
       "      <th>CV1</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">0.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>4161</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>324</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">1.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>2504</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>233</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">2.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>2798</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>264</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">3.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>2125</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>231</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">4.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>1733</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>212</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">5.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>1238</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>202</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">6.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>1148</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>161</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">7.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>789</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>150</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">8.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>657</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>124</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">9.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>532</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">10.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>426</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>78</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">11.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>325</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">12.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>327</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>62</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">13.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>209</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">14.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>166</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">15.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>110</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">16.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>84</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">17.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">18.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>68</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">19.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">20.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">21.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">22.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">23.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">24.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">PROXY SKIPPED</th>\n",
       "      <th>NO</th>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   AA5C\n",
       "DISTRESS      CV1      \n",
       "0.0           NO   4161\n",
       "              YES   324\n",
       "1.0           NO   2504\n",
       "              YES   233\n",
       "2.0           NO   2798\n",
       "              YES   264\n",
       "3.0           NO   2125\n",
       "              YES   231\n",
       "4.0           NO   1733\n",
       "              YES   212\n",
       "5.0           NO   1238\n",
       "              YES   202\n",
       "6.0           NO   1148\n",
       "              YES   161\n",
       "7.0           NO    789\n",
       "              YES   150\n",
       "8.0           NO    657\n",
       "              YES   124\n",
       "9.0           NO    532\n",
       "              YES   100\n",
       "10.0          NO    426\n",
       "              YES    78\n",
       "11.0          NO    325\n",
       "              YES    64\n",
       "12.0          NO    327\n",
       "              YES    62\n",
       "13.0          NO    209\n",
       "              YES    39\n",
       "14.0          NO    166\n",
       "              YES    26\n",
       "15.0          NO    110\n",
       "              YES    25\n",
       "16.0          NO     84\n",
       "              YES    19\n",
       "17.0          NO     70\n",
       "              YES    14\n",
       "18.0          NO     68\n",
       "              YES    18\n",
       "19.0          NO     33\n",
       "              YES     7\n",
       "20.0          NO     16\n",
       "              YES     4\n",
       "21.0          NO     23\n",
       "              YES     6\n",
       "22.0          NO      2\n",
       "              YES     2\n",
       "23.0          NO      5\n",
       "              YES     2\n",
       "24.0          NO     23\n",
       "              YES     5\n",
       "PROXY SKIPPED NO      4\n",
       "              YES     1"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "work = adult_df.groupby(['DISTRESS', 'CV1']).count()\n",
    "work[['AA5C']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "25393ff1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>AA5C</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DISTRESS</th>\n",
       "      <th>CV1</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">0.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.927759</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.072241</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">1.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.914870</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.085130</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">2.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.913782</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.086218</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">3.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.901952</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.098048</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">4.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.891003</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.108997</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">5.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.859722</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.140278</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">6.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.877005</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.122995</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">7.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.840256</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.159744</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">8.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.841229</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.158771</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">9.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.841772</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.158228</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">10.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.845238</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.154762</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">11.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.835476</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.164524</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">12.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.840617</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.159383</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">13.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.842742</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.157258</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">14.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.864583</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.135417</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">15.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.814815</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.185185</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">16.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.815534</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.184466</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">17.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.833333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.166667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">18.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.790698</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.209302</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">19.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.825000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.175000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">20.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.800000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.200000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">21.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.793103</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.206897</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">22.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">23.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.714286</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.285714</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">24.0</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.821429</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.178571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">PROXY SKIPPED</th>\n",
       "      <th>NO</th>\n",
       "      <td>0.800000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YES</th>\n",
       "      <td>0.200000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                       AA5C\n",
       "DISTRESS      CV1          \n",
       "0.0           NO   0.927759\n",
       "              YES  0.072241\n",
       "1.0           NO   0.914870\n",
       "              YES  0.085130\n",
       "2.0           NO   0.913782\n",
       "              YES  0.086218\n",
       "3.0           NO   0.901952\n",
       "              YES  0.098048\n",
       "4.0           NO   0.891003\n",
       "              YES  0.108997\n",
       "5.0           NO   0.859722\n",
       "              YES  0.140278\n",
       "6.0           NO   0.877005\n",
       "              YES  0.122995\n",
       "7.0           NO   0.840256\n",
       "              YES  0.159744\n",
       "8.0           NO   0.841229\n",
       "              YES  0.158771\n",
       "9.0           NO   0.841772\n",
       "              YES  0.158228\n",
       "10.0          NO   0.845238\n",
       "              YES  0.154762\n",
       "11.0          NO   0.835476\n",
       "              YES  0.164524\n",
       "12.0          NO   0.840617\n",
       "              YES  0.159383\n",
       "13.0          NO   0.842742\n",
       "              YES  0.157258\n",
       "14.0          NO   0.864583\n",
       "              YES  0.135417\n",
       "15.0          NO   0.814815\n",
       "              YES  0.185185\n",
       "16.0          NO   0.815534\n",
       "              YES  0.184466\n",
       "17.0          NO   0.833333\n",
       "              YES  0.166667\n",
       "18.0          NO   0.790698\n",
       "              YES  0.209302\n",
       "19.0          NO   0.825000\n",
       "              YES  0.175000\n",
       "20.0          NO   0.800000\n",
       "              YES  0.200000\n",
       "21.0          NO   0.793103\n",
       "              YES  0.206897\n",
       "22.0          NO   0.500000\n",
       "              YES  0.500000\n",
       "23.0          NO   0.714286\n",
       "              YES  0.285714\n",
       "24.0          NO   0.821429\n",
       "              YES  0.178571\n",
       "PROXY SKIPPED NO   0.800000\n",
       "              YES  0.200000"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "work.reset_index()\n",
    "lol = work.groupby(['DISTRESS']).sum()\n",
    "lol[['AA5C']]\n",
    "\n",
    "wow = work / lol\n",
    "wow[['AA5C']]\n",
    "\n",
    "# proportions:"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5d1eafbf",
   "metadata": {},
   "source": [
    "# Variables to measure:"
   ]
  },
  {
   "cell_type": "raw",
   "id": "f6a068da",
   "metadata": {},
   "source": [
    "I wanted to measure \n",
    "\n",
    "DISTRESS      =  \"SERIOUS PSYCHOLOGICAL DISTRESS\"\n",
    "\n",
    "against:\n",
    "\n",
    "CV7_1         =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: LOST JOB\"\n",
    "CV7_10        =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: NONE OF THESE\"\n",
    "CV7_11        =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: INCREASED MENTAL HEALTH CHALLENGES\"\n",
    "CV7_2         =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: REDUCED JOB HOURS OR INCOME\"\n",
    "CV7_3         =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: WORKING FROM HOME\"\n",
    "CV7_4         =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: CONTINUED WORK AS AN ESSENTIAL WORKER\"\n",
    "CV7_5         =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: CHILDCARE DIFFICULTIES\"\n",
    "CV7_6         =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: DIFFICULTIES PAYING RENT/MORTGAGE\"\n",
    "CV7_7         =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: DIFFICULTIES PAYING FOR BASIC NECESSITIES\"\n",
    "CV7_8         =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: TREATED UNFAIRLY DUE TO RACE/ETHNICITY\"\n",
    "CV7_9         =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: OTHER\"\n",
    "CV8_1         =  \"INCREASE IN HH DURING COVID STAY-AT-HOME ORDER: INTERPERSONAL CONFLICT\"\n",
    "CV8_2         =  \"INCREASE IN HH DURING COVID STAY-AT-HOME ORDER: SNAPPING/YELLING\"\n",
    "CV8_4         =  \"INCREASE IN HH DURING COVID STAY-AT-HOME ORDER: NONE OF THESE\"\n",
    "\n",
    "and see which factor is the most/least impactful. To do this, we will be doing..."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "59212a06",
   "metadata": {},
   "source": [
    "# Linear Regression"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5d2c4118",
   "metadata": {},
   "source": [
    "using Linear Regression from scikit learn.\n",
    "\n",
    "WANT: X = 'DISTRESS' values (0, 1, ..., 24), Y = proportion of 'YES' for a variable (like CV1) to all respondents per distress level."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4d86e8a2",
   "metadata": {},
   "source": [
    "### Getting 'DISTRESS' values:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "9b738c02",
   "metadata": {},
   "outputs": [],
   "source": [
    "woah = adult_df[\"DISTRESS\"].sort_values()\n",
    "sick = woah.unique()\n",
    "sick\n",
    "\n",
    "# Prepares 'DISTRESS' to be graphed later\n",
    "bang = sick\n",
    "bang = bang.reshape(-1,1)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5a540b7b",
   "metadata": {},
   "source": [
    "### Getting values for comparison (Doing 'CV1' for example):"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "834ce61d",
   "metadata": {},
   "source": [
    "First, get total values per distress value ('YES' + 'NO'):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "af815c65",
   "metadata": {},
   "outputs": [],
   "source": [
    "work = adult_df.groupby(['DISTRESS', 'CV1']).count()\n",
    "totals = work.groupby(['DISTRESS']).sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2c73dedc",
   "metadata": {},
   "source": [
    "Now, get each 'YES' count per 'DISTRESS' (324, 233, ...):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "11f70c8a",
   "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>AA5C</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DISTRESS</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0.0</th>\n",
       "      <td>4485</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1.0</th>\n",
       "      <td>2737</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2.0</th>\n",
       "      <td>3062</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3.0</th>\n",
       "      <td>2356</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4.0</th>\n",
       "      <td>1945</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5.0</th>\n",
       "      <td>1440</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6.0</th>\n",
       "      <td>1309</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7.0</th>\n",
       "      <td>939</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8.0</th>\n",
       "      <td>781</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9.0</th>\n",
       "      <td>632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10.0</th>\n",
       "      <td>504</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11.0</th>\n",
       "      <td>389</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12.0</th>\n",
       "      <td>389</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13.0</th>\n",
       "      <td>248</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14.0</th>\n",
       "      <td>192</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15.0</th>\n",
       "      <td>135</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16.0</th>\n",
       "      <td>103</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17.0</th>\n",
       "      <td>84</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18.0</th>\n",
       "      <td>86</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19.0</th>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20.0</th>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21.0</th>\n",
       "      <td>29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22.0</th>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23.0</th>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24.0</th>\n",
       "      <td>28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PROXY SKIPPED</th>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               AA5C\n",
       "DISTRESS           \n",
       "0.0            4485\n",
       "1.0            2737\n",
       "2.0            3062\n",
       "3.0            2356\n",
       "4.0            1945\n",
       "5.0            1440\n",
       "6.0            1309\n",
       "7.0             939\n",
       "8.0             781\n",
       "9.0             632\n",
       "10.0            504\n",
       "11.0            389\n",
       "12.0            389\n",
       "13.0            248\n",
       "14.0            192\n",
       "15.0            135\n",
       "16.0            103\n",
       "17.0             84\n",
       "18.0             86\n",
       "19.0             40\n",
       "20.0             20\n",
       "21.0             29\n",
       "22.0              4\n",
       "23.0              7\n",
       "24.0             28\n",
       "PROXY SKIPPED     5"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "work = adult_df.groupby(['DISTRESS', 'CV1']).count()\n",
    "totals = work.groupby(['DISTRESS']).sum()\n",
    "totals[['AA5C']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "fb128e10",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1     0.072241\n",
       "3     0.085130\n",
       "5     0.086218\n",
       "7     0.098048\n",
       "9     0.108997\n",
       "11    0.140278\n",
       "13    0.122995\n",
       "15    0.159744\n",
       "17    0.158771\n",
       "19    0.158228\n",
       "21    0.154762\n",
       "23    0.164524\n",
       "25    0.159383\n",
       "27    0.157258\n",
       "29    0.135417\n",
       "31    0.185185\n",
       "33    0.184466\n",
       "35    0.166667\n",
       "37    0.209302\n",
       "39    0.175000\n",
       "41    0.200000\n",
       "43    0.206897\n",
       "45    0.500000\n",
       "47    0.285714\n",
       "49    0.178571\n",
       "51    0.200000\n",
       "Name: AA5C, dtype: float64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "props = work / totals\n",
    "props = props.reset_index()\n",
    "finalprops = props[props['CV1'] == \"YES\"]['AA5C']\n",
    "finalprops"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9c0efdd4",
   "metadata": {},
   "source": [
    "##### Linear Regression part:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "b7e98318",
   "metadata": {},
   "outputs": [],
   "source": [
    "bing = finalprops.values\n",
    "bing = bing.reshape(-1,1)\n",
    "bang = sick\n",
    "bang = bang.reshape(-1,1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "71f2be94",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.0722408 ],\n",
       "       [0.0851297 ],\n",
       "       [0.08621816],\n",
       "       [0.09804754],\n",
       "       [0.10899743],\n",
       "       [0.14027778],\n",
       "       [0.12299465],\n",
       "       [0.15974441],\n",
       "       [0.15877081],\n",
       "       [0.15822785],\n",
       "       [0.1547619 ],\n",
       "       [0.16452442],\n",
       "       [0.15938303],\n",
       "       [0.15725806],\n",
       "       [0.13541667],\n",
       "       [0.18518519],\n",
       "       [0.18446602],\n",
       "       [0.16666667],\n",
       "       [0.20930233],\n",
       "       [0.175     ],\n",
       "       [0.2       ],\n",
       "       [0.20689655],\n",
       "       [0.5       ],\n",
       "       [0.28571429],\n",
       "       [0.17857143],\n",
       "       [0.2       ]])"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "ad9b934f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[[0.0], [1.0], [2.0], [3.0], [4.0], ..., [21.0], [22.0], [23.0], [24.0], ['PROXY SKIPPED']]\n",
       "Length: 26\n",
       "Categories (26, object): [0.0, 1.0, 2.0, 3.0, ..., 22.0, 23.0, 24.0, 'PROXY SKIPPED']"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bang"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9f30fc05",
   "metadata": {},
   "source": [
    "We don't really care about 'PROXY SKIPPED' and its value bing[25], so we'll remove them both to work with the data:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "ad691430",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = np.delete(bing, 25)\n",
    "Y = np.delete(bang, 25)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "6b3b2f87",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.0722408 , 0.0851297 , 0.08621816, 0.09804754, 0.10899743,\n",
       "       0.14027778, 0.12299465, 0.15974441, 0.15877081, 0.15822785,\n",
       "       0.1547619 , 0.16452442, 0.15938303, 0.15725806, 0.13541667,\n",
       "       0.18518519, 0.18446602, 0.16666667, 0.20930233, 0.175     ,\n",
       "       0.2       , 0.20689655, 0.5       , 0.28571429, 0.17857143])"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "21398f72",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0,\n",
       "       13.0, 14.0, 15.0, 16.0, 17.0, 18.0, 19.0, 20.0, 21.0, 22.0, 23.0,\n",
       "       24.0], dtype=object)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "389bff3b",
   "metadata": {},
   "source": [
    "Finally, we gotta shape it so it works with LinearRegression().fit:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "d6d55fcc",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = X.reshape(-1,1)\n",
    "Y = Y.reshape(-1,1)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cc387fb5",
   "metadata": {},
   "source": [
    "Now it is ready."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "99885b8a",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = LinearRegression().fit(Y, X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "7c45a83c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.00789314]])"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.coef_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "6a6fb31b",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_pred = model.predict(Y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "8190ef69",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[0.00789314]]\n",
      "intercept: [0.0754341]\n"
     ]
    }
   ],
   "source": [
    "print('slope:', model.coef_)\n",
    "print('intercept:', model.intercept_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "58321933",
   "metadata": {},
   "outputs": [
    {
     "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": [
    "plt.scatter(Y, X)\n",
    "plt.plot(Y, x_pred, color='black')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "65e9ee3b",
   "metadata": {},
   "source": [
    "Now, we do the same for the rest of our variables:"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "42fdc61a",
   "metadata": {},
   "source": [
    "### CV7_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "8dbf6dac",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[0.00841025]]\n",
      "intercept: [0.03548043]\n"
     ]
    },
    {
     "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": [
    "a = adult_df.groupby(['DISTRESS', 'CV7_1']).count()\n",
    "atotals = a.groupby(['DISTRESS']).sum()\n",
    "aprops = a / atotals\n",
    "aprops = aprops.reset_index()\n",
    "aprops\n",
    "afinalprops = aprops[aprops['CV7_1'] == \"YES\"]['AA5C']\n",
    "afinalprops\n",
    "bing1 = afinalprops.values\n",
    "bing1 = bing1.reshape(-1,1)\n",
    "X1 = np.delete(bing1, 25)\n",
    "X1 = X1.reshape(-1,1)\n",
    "model1 = LinearRegression().fit(Y, X1)\n",
    "model1.coef_\n",
    "x1_pred = model1.predict(Y)\n",
    "print('slope:', model1.coef_)\n",
    "print('intercept:', model1.intercept_)\n",
    "plt.scatter(Y, X1)\n",
    "plt.plot(Y, x1_pred, color='red')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "871f745f",
   "metadata": {},
   "source": [
    "### CV7_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "ca04bb71",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[0.00948629]]\n",
      "intercept: [0.11119345]\n"
     ]
    },
    {
     "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": [
    "b = adult_df.groupby(['DISTRESS', 'CV7_2']).count()\n",
    "btotals = b.groupby(['DISTRESS']).sum()\n",
    "bprops = b / btotals\n",
    "bprops = bprops.reset_index()\n",
    "bprops\n",
    "bfinalprops = bprops[bprops['CV7_2'] == \"YES\"]['AA5C']\n",
    "bfinalprops\n",
    "bing2 = bfinalprops.values\n",
    "bing2 = bing2.reshape(-1,1)\n",
    "X2 = np.delete(bing2, 25)\n",
    "X2 = X2.reshape(-1,1)\n",
    "model2 = LinearRegression().fit(Y, X2)\n",
    "model2.coef_\n",
    "x2_pred = model2.predict(Y)\n",
    "print('slope:', model2.coef_)\n",
    "print('intercept:', model2.intercept_)\n",
    "plt.scatter(Y, X2)\n",
    "plt.plot(Y, x2_pred, color='orange')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0b1ff6ef",
   "metadata": {},
   "source": [
    "### CV7_3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "9db782f8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[0.00474906]]\n",
      "intercept: [0.22433384]\n"
     ]
    },
    {
     "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": [
    "c = adult_df.groupby(['DISTRESS', 'CV7_3']).count()\n",
    "ctotals = c.groupby(['DISTRESS']).sum()\n",
    "cprops = c / ctotals\n",
    "cprops = cprops.reset_index()\n",
    "cprops\n",
    "cfinalprops = cprops[cprops['CV7_3'] == \"YES\"]['AA5C']\n",
    "cfinalprops\n",
    "bing3 = cfinalprops.values\n",
    "bing3 = bing3.reshape(-1,1)\n",
    "X3 = np.delete(bing3, 25)\n",
    "X3 = X3.reshape(-1,1)\n",
    "model3 = LinearRegression().fit(Y, X3)\n",
    "model3.coef_\n",
    "x3_pred = model3.predict(Y)\n",
    "print('slope:', model3.coef_)\n",
    "print('intercept:', model3.intercept_)\n",
    "plt.scatter(Y, X3)\n",
    "plt.plot(Y, x3_pred, color='yellow')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "77bade4f",
   "metadata": {},
   "source": [
    "### CV7_4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "42f8524e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[0.00274451]]\n",
      "intercept: [0.14540029]\n"
     ]
    },
    {
     "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": [
    "d = adult_df.groupby(['DISTRESS', 'CV7_4']).count()\n",
    "dtotals = d.groupby(['DISTRESS']).sum()\n",
    "dprops = d / dtotals\n",
    "dprops = dprops.reset_index()\n",
    "dprops\n",
    "dfinalprops = dprops[dprops['CV7_4'] == \"YES\"]['AA5C']\n",
    "dfinalprops\n",
    "bing4 = dfinalprops.values\n",
    "bing4 = bing4.reshape(-1,1)\n",
    "X4 = np.delete(bing4, 25)\n",
    "X4 = X4.reshape(-1,1)\n",
    "model4 = LinearRegression().fit(Y, X4)\n",
    "model4.coef_\n",
    "x4_pred = model4.predict(Y)\n",
    "print('slope:', model4.coef_)\n",
    "print('intercept:', model4.intercept_)\n",
    "plt.scatter(Y, X4)\n",
    "plt.plot(Y, x4_pred, color='green')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "91668242",
   "metadata": {},
   "source": [
    "### CV7_5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "f3494412",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[0.00045818]]\n",
      "intercept: [0.02465135]\n"
     ]
    },
    {
     "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": [
    "e = adult_df.groupby(['DISTRESS', 'CV7_5']).count()\n",
    "etotals = e.groupby(['DISTRESS']).sum()\n",
    "eprops = e / etotals\n",
    "eprops = eprops.reset_index()\n",
    "eprops\n",
    "efinalprops = eprops[eprops['CV7_5'] == \"YES\"]['AA5C']\n",
    "efinalprops\n",
    "bing5 = efinalprops.values\n",
    "bing5 = bing5.reshape(-1,1)\n",
    "X5 = np.delete(bing5, 25)\n",
    "X5 = X5.reshape(-1,1)\n",
    "model5 = LinearRegression().fit(Y, X5)\n",
    "model5.coef_\n",
    "x5_pred = model5.predict(Y)\n",
    "print('slope:', model5.coef_)\n",
    "print('intercept:', model5.intercept_)\n",
    "plt.scatter(Y, X5)\n",
    "plt.plot(Y, x5_pred, color='blue')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2f3ce0c1",
   "metadata": {},
   "source": [
    "### CV7_6"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "b22491b9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[0.00944908]]\n",
      "intercept: [0.01617633]\n"
     ]
    },
    {
     "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": [
    "f = adult_df.groupby(['DISTRESS', 'CV7_6']).count()\n",
    "ftotals = f.groupby(['DISTRESS']).sum()\n",
    "fprops = f / ftotals\n",
    "fprops = fprops.reset_index()\n",
    "fprops\n",
    "ffinalprops = fprops[fprops['CV7_6'] == \"YES\"]['AA5C']\n",
    "ffinalprops\n",
    "bing6 = ffinalprops.values\n",
    "bing6 = bing6.reshape(-1,1)\n",
    "X6 = np.delete(bing6, 25)\n",
    "X6 = X6.reshape(-1,1)\n",
    "model6 = LinearRegression().fit(Y, X6)\n",
    "model6.coef_\n",
    "x6_pred = model6.predict(Y)\n",
    "print('slope:', model6.coef_)\n",
    "print('intercept:', model6.intercept_)\n",
    "plt.scatter(Y, X6)\n",
    "plt.plot(Y, x6_pred, color='purple')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0f098680",
   "metadata": {},
   "source": [
    "### CV7_7"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "571f8882",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[0.01521413]]\n",
      "intercept: [-0.01092046]\n"
     ]
    },
    {
     "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": [
    "g = adult_df.groupby(['DISTRESS', 'CV7_7']).count()\n",
    "gtotals = g.groupby(['DISTRESS']).sum()\n",
    "gprops = g / gtotals\n",
    "gprops = gprops.reset_index()\n",
    "gprops\n",
    "gfinalprops = gprops[gprops['CV7_7'] == \"YES\"]['AA5C']\n",
    "gfinalprops\n",
    "bing7 = gfinalprops.values\n",
    "bing7 = bing7.reshape(-1,1)\n",
    "X7 = np.delete(bing7, 25)\n",
    "X7 = X7.reshape(-1,1)\n",
    "model7 = LinearRegression().fit(Y, X7)\n",
    "model7.coef_\n",
    "x7_pred = model7.predict(Y)\n",
    "print('slope:', model7.coef_)\n",
    "print('intercept:', model7.intercept_)\n",
    "plt.scatter(Y, X7)\n",
    "plt.plot(Y, x7_pred, color='pink')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b5028c1a",
   "metadata": {},
   "source": [
    "### CV7_8"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "ad3da448",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[0.00415819]]\n",
      "intercept: [-0.00908834]\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAD4CAYAAADrRI2NAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAAAX/0lEQVR4nO3de3BcZ3nH8e9jSU5EGkaJb8SyFSmMEdjxRc5KmRIKJCTxhYBNGCCBYYAycULiBobGk6SdAdoOk7ShLZlpIHVTc+mUhg7YrkshDuUyUCBoZRswtmNHtpNYkrF8ky8TxRf56R+7clbrlXR2vff395nJSHv2nN33sOSrk3fPnjV3R0REwjGh1AMQEZHiUvhFRAKj8IuIBEbhFxEJjMIvIhKY2lIPIJPJkyd7c3NzqYchIlIxNm3adMjdp0RZtyzD39zcTFdXV6mHISJSMczspajraqpHRCQwCr+ISGAUfhGRwCj8IiKBUfhFRAIT6aweM1sMPA7UAE+5+6Np938EeDB58yTwKXf/bfK+F4ETwBBw1t1j+Rm6iEjhrd/Sy2Mbd9I3MMj0hnpWLWpleVtjqYd1UcYNv5nVAE8AtwA9QNzMNrj79pTV9gLvcPejZrYEWA1cn3L/je5+KI/jFhEpuPVbenl47VYGzwwB0DswyMNrtwJUdPyjTPV0AN3uvsfdTwNPA8tSV3D3X7r70eTN54AZ+R2miEjxPbZx5/noDxs8M8RjG3eWaET5ESX8jcC+lNs9yWWj+STwg5TbDjxrZpvMbMVoG5nZCjPrMrOugwcPRhiWiEhh9Q0MZrW8UkQJv2VYlvHbW8zsRhLhfzBl8Q3uvhBYAtxnZm/PtK27r3b3mLvHpkyJ9KljEZGCmt5Qn9XyShEl/D3AzJTbM4C+9JXMbB7wFLDM3Q8PL3f3vuTPfmAdiakjEZGyt2pRK/V1NSOW1dfVsGpRa4lGlB9Rwh8HZplZi5lNBO4ANqSuYGZNwFrgo+6+K2X5ZWZ2+fDvwK3A7/M1eBGRQlre1sgjt8+lsaEeAxob6nnk9rkV/cYuRDirx93PmtlKYCOJ0znXuPs2M7snef+TwOeAScBXzAxeO21zGrAuuawW+Ja7P1OQPRERKYDlbY0VH/p0Vo5fth6LxVxX5xQRic7MNkX9nJQ+uSsiEhiFX0QkMAq/iEhgFH4RkcAo/CIigVH4RUQCo/CLiARG4RcRCYzCLyISGIVfRCQwCr+ISGAUfhGRwCj8IiKBUfhFRAKj8IuIBEbhFxEJjMIvIhIYhV9EJDAKv4hIYBR+EZHAKPwiIoFR+EVEAqPwi4gERuEXEQmMwi8iEhiFX0QkMAq/iEhgFH4RkcAo/CIigYkUfjNbbGY7zazbzB7KcP9HzOx3yX9+aWbzo24rIiLFNW74zawGeAJYAswG7jSz2Wmr7QXe4e7zgL8BVmexrYiIFFGUI/4OoNvd97j7aeBpYFnqCu7+S3c/mrz5HDAj6rYiIlJcUcLfCOxLud2TXDaaTwI/yHZbM1thZl1m1nXw4MEIwxIRkVxECb9lWOYZVzS7kUT4H8x2W3df7e4xd49NmTIlwrBERCQXtRHW6QFmptyeAfSlr2Rm84CngCXufjibbUVEpHiiHPHHgVlm1mJmE4E7gA2pK5hZE7AW+Ki778pmWxERKa5xj/jd/ayZrQQ2AjXAGnffZmb3JO9/EvgcMAn4ipkBnE1O22TctkD7IiIiEZh7xin3korFYt7V1VXqYYiIVAwz2+TusSjr6pO7IiKBUfhFRAKj8IuIBEbhFxEJjMIvIhIYhV9EJDAKv4hIYBR+EZHAKPwiIoFR+EVEAqPwi4gERuEXEQmMwi8iEhiFX0QkMAq/iEhgFH4RkcAo/CIigVH4RUQCo/CLiARG4RcRCYzCLyISGIVfRCQwCr+ISGAUfhGRwCj8IiKBUfhFRAKj8IuIBEbhFxEJjMIvIhKYSOE3s8VmttPMus3soQz3v9nMfmVmp8zsgbT7XjSzrWb2GzPrytfARUQkN7XjrWBmNcATwC1ADxA3sw3uvj1ltSPA/cDyUR7mRnc/dJFjFRGRPIhyxN8BdLv7Hnc/DTwNLEtdwd373T0OnCnAGEVEJI+ihL8R2Jdyuye5LCoHnjWzTWa2IpvBiYhI/o071QNYhmWexXPc4O59ZjYV+KGZPe/uP7vgSRJ/FFYANDU1ZfHwIiKSjShH/D3AzJTbM4C+qE/g7n3Jn/3AOhJTR5nWW+3uMXePTZkyJerDi4hIlqKEPw7MMrMWM5sI3AFsiPLgZnaZmV0+/DtwK/D7XAcrIiIXb9ypHnc/a2YrgY1ADbDG3beZ2T3J+580szcAXcDrgXNm9hlgNjAZWGdmw8/1LXd/piB7IiIikUSZ48fdvw98P23Zkym//4HEFFC648D8ixmgiIjklz65KyISGIVfRCQwCr+ISGAUfhGRwCj8IiKBUfhFRAKj8IuIBEbhFxEJjMIvIhIYhV9EJDAKv4hIYBR+EZHAKPwiIoFR+EVEAqPwi4gERuEXEQmMwi8iEhiFX0QkMAq/iEhgFH4RkcAo/CIigVH4RUQCo/CLiARG4RcRCUxtqQcgIhK69Vt6eWzjTvoGBpneUM+qRa0sb2ss2PMp/CIiJbR+Sy8Pr93K4JkhAHoHBnl47VaAgsVfUz0iIiX02Mad56M/bPDMEI9t3Fmw59QRv4gEo9hTKlH0DQxmtTwfdMQvIkEYnlLpHRjEeW1KZf2W3pKOa3pDfVbL80HhF5EglGJKJYpVi1qpr6sZsay+roZVi1oL9pyRwm9mi81sp5l1m9lDGe5/s5n9ysxOmdkD2WwrIlIMpZhSiWJ5WyOP3D6XxoZ6DGhsqOeR2+eW9qweM6sBngBuAXqAuJltcPftKasdAe4HluewrYhIwU1vqKc3Q+QLOaUS1fK2xqK+1xDliL8D6Hb3Pe5+GngaWJa6grv3u3scOJPttiIixVCKKZVyFSX8jcC+lNs9yWVRRN7WzFaYWZeZdR08eDDiw4uIRFOKKZVyFeV0TsuwzCM+fuRt3X01sBogFotFfXwRkciKPaVSrqIc8fcAM1NuzwD6Ij7+xWwrIiIFECX8cWCWmbWY2UTgDmBDxMe/mG1FRKQAxp3qcfezZrYS2AjUAGvcfZuZ3ZO8/0kzewPQBbweOGdmnwFmu/vxTNsWaF9ERCQCcy+/6fRYLOZdXV2lHoaISFGdHRyktj6300vNbJO7x6Ksq2v1iIiUyKuHD9Pf1cWBzk7643GGTp/mvc88U/DnVfhFRIokPfTHdu8GoPZ1r2PKddcxrb2dc0NDTKipGeeRLo7CLyJSIOOFvmXZMqa2t3Pl7NlMqC1ejhV+ERlTOV7KuFyVa+jTKfwiMqpSfDtUJRkz9AsXlk3o05XPSESk7Ix1KeMQwz9u6N/7XqZ2dHDlW97ChLq6Eo92dAq/iIyqXC9lXCzVEvp0Cr+IjKqcL2VcCOdDH48nQt/dDUBtfX1ijr5CQ59O4ReRUa1a1Dpijh+q61LG44b+Pe+pitCnU/hFZFTD8/jVclbPq0eO0B+PBxf6dAq/iIypki9lrNBnpvCLSNVQ6KNR+EWkYo0Z+oULab7tNqZ1dCTOow849OkUfhGpGAp9fij8IlK2Rgt9TX09U9raaL7tNqbGYky69lqFPgsKv4iUjVePHKG/q+t87I+98AKQFvr2dibNmaPQXwSFX0RKZtzQv/vdCn0BKPwiUjTjhn7pUqZ2dCj0Babwi0jB6Ii+PCn8IpI3Cn1lUPhFJGevHj3KweTVKzV1UzkUfhGJ7Hzok6dXDuzaBVx4RH/l7NnUTJxY4tHKaBR+ERnVqYGB165e2dl5QejnL12q0FcghV9Ezhsz9AsWMP/Tn06Efs4chb6CKfwiARv3iH7JEoW+Cin8IgFR6AUUfpGqptBLJgq/SBVR6CUKhV+kgin0kotI4TezxcDjQA3wlLs/mna/Je9fCrwCfNzdNyfvexE4AQwBZ909lrfRiwRm1NBfeilTFi5MhD4W48prr6240K/f0pvVd/tmu768Ztzwm1kN8ARwC9ADxM1sg7tvT1ltCTAr+c/1wFeTP4fd6O6H8jZqkUCMGfq2Nubdfz/T2tsrMvSp1m/p5eG1Wxk8MwRA78AgD6/dCpAx5tmuLyNFOeLvALrdfQ+AmT0NLANSw78M+Ka7O/CcmTWY2VXuvj/vIxapYqcGBujftIn+5CUQBnbtAveqC326xzbuPB/xYYNnhnhs486MIc92fRkpSvgbgX0pt3sYeTQ/2jqNwH7AgWfNzIF/dvfVmZ7EzFYAKwCampoiDV6k0o0V+skLFjBv5crEVwlWWejT9Q0MFnS5jBQl/JZhmWexzg3u3mdmU4Efmtnz7v6zC1ZO/EFYDRCLxdIfX6QqRAn91PZ2Js2dW9WhTze9oZ7eDNGe3lCfl/VlpCjh7wFmptyeAfRFXcfdh3/2m9k6ElNHF4RfpBop9NGsWtQ6Ys4eoL6uhlWLWvOyvowUJfxxYJaZtQC9wB3Ah9PW2QCsTM7/Xw8cc/f9ZnYZMMHdTyR/vxX46/wNX6S8jBr6Sy5R6McwPC8f9SydbNeXkSzxfuw4K5ktBb5M4nTONe7+RTO7B8Ddn0yezvlPwGISp3N+wt27zOwaYF3yYWqBb7n7F8d7vlgs5l1dXbnsj8i48nka4Jihb2tjWnu7Qi9FYWabop4uHyn8xabwS6GknwYIiSmCR26fGyn+Cr2Uq2zCr0/uSlCyPQ1QUzdSjRR+Ccp4pwGeGhjg4ObNHOjspD8e5+jOnSOO6BV6qQYKvwQl/TTAS0+/QsuRvcw98RI/eP8ahT5PdDmF8qbwS1AeeNt0vv6179HY3801h3bzhuP7mYBD3UQmLmxj7n33Ma2jQ6G/CLqcQvlT+KWqnT52jP5Nm85/Ofjg88/zIXfO1tTxUkMT8flLeft7bmL5+29S6PNEl1Mofwq/VLzUaYWWeufexldpObw7MUf//PMj3ozVEX3h6XIK5U/hl4q27v+e5+tf+x7z+7tZfmg3Vx3fz2mcnXUTmRbA1E05zqXrcgrlT+GXipI+dfPKjuf5EM6ZCbW8fGUzP2q9hb2TrmGo+U38/C8X5e15yzGwuc6lF3pfdDmF8qfwS1lJj9IDb5tO++m+86FPn7r5Uest7Jn0RvY1zGSo5rX/O9uJs3kdUzm+WZnLXHox9kWXUyh/Cr+UjfVbevmrp3/NtAPdLDm8h5ZDu3nl3/bzM0afo//coz8u+LRCub5ZmctcerH2ZXlbo0JfxhR+KanTx48npm46O3npez/mz4/0MmF46uaKq/lR680cv3o23/7bj2ecoy/GtEK5vlmZy1x6ue6LFJfCL0U1HPr+eJwD8ThHd+wAdyZMnMjxy2fy29ab2TPpjfQ0zORsTR2Q+LKH0d6YLca0Qq5vVpbjXLreeBVQ+KXAxgr9lAULmHvvveenbt7+j7/IKUqFnlbIJbDlOpeuN14FFH7Js7FCP3n+fK791KeY1tHB5HnzqLnkkhHblmuUcglsrm+8ZvtfCNn+0dMbrwK6LHOwcolMpm2WvvHyMUM/raODqe3tGUOfr3GVo5aH/ueC7yeFxLTV3kfffcHyi71ctIguyyxjymUaYngbf+UkrYf30rJtN7v/ey/fOdY7IvRz7703q9Cnq5azQbKdSy/XM4ekOin8AcomMsNTN7984rv8ad8urjrWd/6sm31XNNE5dzEPf/ZDOYe+WmU7baWzbaSYFP4AjRWZ0ebo5yRD/+M33czeSdew74omztbUYcCX29szPl61TNvkItu5dJ1tI8Wk8FeBbAObGplLzwzSfHgvLYd30zrwIt9564MZp24+8OwRXs7wadjRwlSun3Ytpmymrcr1jW2pTgp/hcs2sKePH+ezU4/y0+d+RFN/9/mpm7MTapnYOoc5d7434xz9Z2szv/k4Wpg0Z50dnW0jxaTwl6FsjuDHC+zpEyc4mHJRs6M7duDnzvHHtXX0Trqan057F8euns2H77yV913fMuqYsg2T5qyzVy1vbEv5U/jLTLZH8OkhveTMIM1H9nLNtj0888Enz4d+Ql0dkxcsYM499zCtvZ1J8+ZRe+mlWY0tmzBpzlqkfCn8ZSbbKZLm18HEvTtoObybaw7tYfqxxLVuhibUUntd20WF/mJozlqkfCn8WcjXh57G2ma8KZLTJ05wcPPmxFk3nZ3ctX0H+DnOTqhhX0MTP3nTu+idNou7P7GUm6+/JvedvUiasxYpX1Xzyd1sA5vL+tl+sjKXbW5Iu8xwYurmReadfJl32R8umLqZ2t7OCw0tPL53AvtODimwIoHK5pO7VRH+bAObjyAPa2yo5xcP3ZS3bdb9YhdrvvY9GvtfGDF1Q20dU9sSoS/F1I2IlLfgLtmQ7bx4Lqca5nKWSpRt0qduXt2xgzvPnWNoQi0vXdFE17zF/MltN7Hs/Tcp9CKSF1UR/myjnEvEczlLJdM2l5wZ5LpTfWz50pc40Nk5cupm/nzm3H134oh+/nyFXkQKoirCn22Uc4l4LmeprFrUyue/HecNB7ovOOtmp0IvIiUSKfxmthh4HKgBnnL3R9Put+T9S4FXgI+7++Yo2+ZDtlHOJeJRz1I5c/Ik/Zs309/ZyaXxOA9u237+rJsDk1uY+L6P8I733KTQi1SpSrhG1bhv7ppZDbALuAXoAeLAne6+PWWdpcCfkQj/9cDj7n59lG0zKcezekaTGvoD8ThHt28fMXVz/s1YhV6k6pXyexXy/eZuB9Dt7nuSD/40sAxIjfcy4Jue+CvynJk1mNlVQHOEbfMil28iKkToNXUjEq5KuUZVlPA3AvtSbveQOKofb53GiNsCYGYrgBUATU1NEYZVHKOGvraWSfPnM2fFisRFzebPp7ZelyMQCVmlXKMqSvgtw7L0+aHR1omybWKh+2pgNSSmeiKMqyAUehHJVaVcoypK+HuAmSm3ZwB9EdeZGGHbklLoRSRfKuUaVVHCHwdmmVkL0AvcAXw4bZ0NwMrkHP71wDF3329mByNsW1QKvYgUSqVco2rc8Lv7WTNbCWwkcUrmGnffZmb3JO9/Evg+iTN6ukmczvmJsbYtyJ6MYrzQz77rLqZ1dCj0IpIXlfC9ClVxrZ5UZ06e5OCWLRzo7KQ/HufI9u340ND50E9rb9cRvYhUneCu1QMwdOoU//uxj10Q+jl33aXQi4ikqJrw11xyCZc3N3PVDTco9CIiY6ia8AO89dG8Xw1CRKTqTCj1AEREpLgUfhGRwCj8IiKBUfhFRAKj8IuIBEbhFxEJjMIvIhIYhV9EJDBlea2e5FU9X8px88nAoTwOp5KEvO8Q9v5r38M1vP9Xu/uUKBuUZfgvhpl1Rb1QUbUJed8h7P3Xvoe575Db/muqR0QkMAq/iEhgqjH8q0s9gBIKed8h7P3Xvocr6/2vujl+EREZWzUe8YuIyBgUfhGRwFRN+M1ssZntNLNuM3uo1OMpNjN70cy2mtlvzCy3LyyuEGa2xsz6zez3KcuuNLMfmtkLyZ9XlHKMhTTK/n/BzHqTr/9vzGxpKcdYKGY208x+YmY7zGybmX06ubzqX/8x9j3r174q5vjNrAbYBdwC9ABx4E53317SgRWRmb0IxNy96j/IYmZvB04C33T3a5PL/g444u6PJv/wX+HuD5ZynIUyyv5/ATjp7l8q5dgKzcyuAq5y981mdjmwCVgOfJwqf/3H2PcPkuVrXy1H/B1At7vvcffTwNPAshKPSQrE3X8GHElbvAz4RvL3b5D4F6IqjbL/QXD3/e6+Ofn7CWAH0EgAr/8Y+561agl/I7Av5XYPOf4PUsEceNbMNpnZilIPpgSmuft+SPwLAkwt8XhKYaWZ/S45FVR1Ux3pzKwZaAN+TWCvf9q+Q5avfbWE3zIsq/w5rOzc4O4LgSXAfcnpAAnHV4E3AguA/cDfl3Q0BWZmfwR8F/iMux8v9XiKKcO+Z/3aV0v4e4CZKbdnAH0lGktJuHtf8mc/sI7E9FdIDiTnQIfnQvtLPJ6icvcD7j7k7ueAf6GKX38zqyMRvn9397XJxUG8/pn2PZfXvlrCHwdmmVmLmU0E7gA2lHhMRWNmlyXf7MHMLgNuBX4/9lZVZwPwseTvHwP+q4RjKbrh6CW9jyp9/c3MgH8Fdrj7P6TcVfWv/2j7nstrXxVn9QAkT2H6MlADrHH3L5Z2RMVjZteQOMoHqAW+Vc37b2b/AbyTxOVoDwCfB9YD/wk0AS8DH3D3qnwDdJT9fyeJ/9R34EXg7uE572piZm8Dfg5sBc4lF/8Fibnuqn79x9j3O8nyta+a8IuISDTVMtUjIiIRKfwiIoFR+EVEAqPwi4gERuEXEQmMwi8iEhiFX0QkMP8PSJw6kHW/thwAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "h = adult_df.groupby(['DISTRESS', 'CV7_8']).count()\n",
    "htotals = h.groupby(['DISTRESS']).sum()\n",
    "hprops = h / htotals\n",
    "hprops = hprops.reset_index()\n",
    "hprops\n",
    "hfinalprops = hprops[hprops['CV7_8'] == \"YES\"]['AA5C']\n",
    "hfinalprops\n",
    "bing8 = hfinalprops.values\n",
    "bing8 = bing8.reshape(-1,1)\n",
    "X8 = np.delete(bing8, 25)\n",
    "X8 = X8.reshape(-1,1)\n",
    "model8 = LinearRegression().fit(Y, X8)\n",
    "model8.coef_\n",
    "x8_pred = model8.predict(Y)\n",
    "print('slope:', model8.coef_)\n",
    "print('intercept:', model8.intercept_)\n",
    "plt.scatter(Y, X8)\n",
    "plt.plot(Y, x8_pred, color='brown')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a7bfeb95",
   "metadata": {},
   "source": [
    "### CV7_9"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "0356d624",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[0.00142768]]\n",
      "intercept: [0.01781202]\n"
     ]
    },
    {
     "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": [
    "i = adult_df.groupby(['DISTRESS', 'CV7_9']).count()\n",
    "itotals = i.groupby(['DISTRESS']).sum()\n",
    "iprops = i / itotals\n",
    "iprops = iprops.reset_index()\n",
    "iprops\n",
    "ifinalprops = iprops[iprops['CV7_9'] == \"YES\"]['AA5C']\n",
    "ifinalprops\n",
    "bing9 = ifinalprops.values\n",
    "bing9 = bing9.reshape(-1,1)\n",
    "X9 = np.delete(bing9, 25)\n",
    "X9 = X9.reshape(-1,1)\n",
    "model9 = LinearRegression().fit(Y, X9)\n",
    "model9.coef_\n",
    "x9_pred = model9.predict(Y)\n",
    "print('slope:', model9.coef_)\n",
    "print('intercept:', model9.intercept_)\n",
    "plt.scatter(Y, X9)\n",
    "plt.plot(Y, x9_pred, color='cyan')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1a1e4573",
   "metadata": {},
   "source": [
    "### CV7_10        =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: NONE OF THESE\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "52984e89",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[-0.01409242]]\n",
      "intercept: [0.47161348]\n"
     ]
    },
    {
     "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": [
    "j = adult_df.groupby(['DISTRESS', 'CV7_10']).count()\n",
    "jtotals = j.groupby(['DISTRESS']).sum()\n",
    "jprops = j / jtotals\n",
    "jprops = jprops.reset_index()\n",
    "jprops\n",
    "jfinalprops = jprops[jprops['CV7_10'] == \"YES\"]['AA5C']\n",
    "jfinalprops\n",
    "bing10 = jfinalprops.values\n",
    "bing10 = bing10.reshape(-1,1)\n",
    "X10 = np.delete(bing10, 25)\n",
    "X10 = X10.reshape(-1,1)\n",
    "model10 = LinearRegression().fit(Y, X10)\n",
    "model10.coef_\n",
    "x10_pred = model10.predict(Y)\n",
    "print('slope:', model10.coef_)\n",
    "print('intercept:', model10.intercept_)\n",
    "plt.scatter(Y, X10)\n",
    "plt.plot(Y, x10_pred, color='magenta')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "548373c4",
   "metadata": {},
   "source": [
    "### CV7_11        =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: INCREASED MENTAL HEALTH CHALLENGES\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "cd4a5c02",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[0.00034318]]\n",
      "intercept: [0.00788963]\n"
     ]
    },
    {
     "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": [
    "k = adult_df.groupby(['DISTRESS', 'CV7_11']).count()\n",
    "ktotals = k.groupby(['DISTRESS']).sum()\n",
    "kprops = k / ktotals\n",
    "kprops = kprops.reset_index()\n",
    "kprops\n",
    "kfinalprops = kprops[kprops['CV7_11'] == \"YES\"]['AA5C']\n",
    "kfinalprops\n",
    "bing11 = kfinalprops.values\n",
    "bing11 = bing11.reshape(-1,1)\n",
    "X11 = np.delete(bing11, 25)\n",
    "X11 = X11.reshape(-1,1)\n",
    "model11 = LinearRegression().fit(Y, X11)\n",
    "model11.coef_\n",
    "x11_pred = model11.predict(Y)\n",
    "print('slope:', model11.coef_)\n",
    "print('intercept:', model11.intercept_)\n",
    "plt.scatter(Y, X11)\n",
    "plt.plot(Y, x11_pred, color='gray')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd5e821b",
   "metadata": {},
   "source": [
    "### CV8_1         =  \"INCREASE IN HH DURING COVID STAY-AT-HOME ORDER: INTERPERSONAL CONFLICT\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "387bf5ef",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[0.00934817]]\n",
      "intercept: [0.1003169]\n"
     ]
    },
    {
     "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": [
    "l = adult_df.groupby(['DISTRESS', 'CV8_1']).count()\n",
    "ltotals = l.groupby(['DISTRESS']).sum()\n",
    "lprops = l / ltotals\n",
    "lprops = lprops.reset_index()\n",
    "lprops\n",
    "lfinalprops = lprops[lprops['CV8_1'] == \"YES\"]['AA5C']\n",
    "lfinalprops\n",
    "bing12 = lfinalprops.values\n",
    "bing12 = bing12.reshape(-1,1)\n",
    "X12 = np.delete(bing12, 25)\n",
    "X12 = X12.reshape(-1,1)\n",
    "model12 = LinearRegression().fit(Y, X12)\n",
    "model12.coef_\n",
    "x12_pred = model12.predict(Y)\n",
    "print('slope:', model12.coef_)\n",
    "print('intercept:', model12.intercept_)\n",
    "plt.scatter(Y, X12)\n",
    "plt.plot(Y, x12_pred, color='lime')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d8630f03",
   "metadata": {},
   "source": [
    "### CV8_2         =  \"INCREASE IN HH DURING COVID STAY-AT-HOME ORDER: SNAPPING/YELLING\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "a0600036",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[0.01522962]]\n",
      "intercept: [0.07062213]\n"
     ]
    },
    {
     "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": [
    "m = adult_df.groupby(['DISTRESS', 'CV8_2']).count()\n",
    "mtotals = m.groupby(['DISTRESS']).sum()\n",
    "mprops = m / mtotals\n",
    "mprops = mprops.reset_index()\n",
    "mprops\n",
    "mfinalprops = mprops[mprops['CV8_2'] == \"YES\"]['AA5C']\n",
    "mfinalprops\n",
    "bing13 = mfinalprops.values\n",
    "bing13 = bing13.reshape(-1,1)\n",
    "X13 = np.delete(bing13, 25)\n",
    "X13 = X13.reshape(-1,1)\n",
    "model13 = LinearRegression().fit(Y, X13)\n",
    "model13.coef_\n",
    "x13_pred = model13.predict(Y)\n",
    "print('slope:', model13.coef_)\n",
    "print('intercept:', model13.intercept_)\n",
    "plt.scatter(Y, X13)\n",
    "plt.plot(Y, x13_pred, color='gold')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1b42142e",
   "metadata": {},
   "source": [
    "### CV8_4         =  \"INCREASE IN HH DURING COVID STAY-AT-HOME ORDER: NONE OF THESE\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "f9731369",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[-0.0140446]]\n",
      "intercept: [0.67883064]\n"
     ]
    },
    {
     "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": [
    "n = adult_df.groupby(['DISTRESS', 'CV8_4']).count()\n",
    "ntotals = n.groupby(['DISTRESS']).sum()\n",
    "nprops = n / ntotals\n",
    "nprops = nprops.reset_index()\n",
    "nprops\n",
    "nfinalprops = nprops[nprops['CV8_4'] == \"YES\"]['AA5C']\n",
    "nfinalprops\n",
    "bing14 = nfinalprops.values\n",
    "bing14 = bing14.reshape(-1,1)\n",
    "X14 = np.delete(bing14, 25)\n",
    "X14 = X14.reshape(-1,1)\n",
    "model14 = LinearRegression().fit(Y, X14)\n",
    "model14.coef_\n",
    "x14_pred = model14.predict(Y)\n",
    "print('slope:', model14.coef_)\n",
    "print('intercept:', model14.intercept_)\n",
    "plt.scatter(Y, X14)\n",
    "plt.plot(Y, x14_pred, color='navy')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1fe54048",
   "metadata": {},
   "source": [
    "### CV9           =  \"WOULD GET COVID-19 VACCINE IF AVAILABLE\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "af540f45",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope: [[-0.00263771]]\n",
      "intercept: [0.82929893]\n"
     ]
    },
    {
     "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": [
    "o = adult_df.groupby(['DISTRESS', 'CV9']).count()\n",
    "ototals = o.groupby(['DISTRESS']).sum()\n",
    "oprops = o / ototals\n",
    "oprops = oprops.reset_index()\n",
    "oprops\n",
    "ofinalprops = oprops[oprops['CV9'] == \"YES\"]['AA5C']\n",
    "ofinalprops\n",
    "bing15 = ofinalprops.values\n",
    "bing15 = bing15.reshape(-1,1)\n",
    "X15 = np.delete(bing15, 25)\n",
    "X15 = X15.reshape(-1,1)\n",
    "model15 = LinearRegression().fit(Y, X15)\n",
    "model15.coef_\n",
    "x15_pred = model15.predict(Y)\n",
    "print('slope:', model15.coef_)\n",
    "print('intercept:', model15.intercept_)\n",
    "plt.scatter(Y, X15)\n",
    "plt.plot(Y, x15_pred, color='salmon')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "a361e112",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "slope1: [[0.00841025]]\n",
      "slope2: [[0.00948629]]\n",
      "slope3: [[0.00474906]]\n",
      "slope4: [[0.00274451]]\n",
      "slope5: [[0.00045818]]\n",
      "slope6: [[0.00944908]]\n",
      "slope7: [[0.01521413]]\n",
      "slope8: [[0.00415819]]\n",
      "slope9: [[0.00142768]]\n",
      "slope10: [[-0.01409242]]\n",
      "slope11: [[0.00034318]]\n",
      "slope12: [[0.00934817]]\n",
      "slope13: [[0.01522962]]\n",
      "slope14: [[-0.0140446]]\n",
      "slope15: [[-0.00263771]]\n"
     ]
    }
   ],
   "source": [
    "print('slope1:', model1.coef_)\n",
    "print('slope2:', model2.coef_)\n",
    "print('slope3:', model3.coef_)\n",
    "print('slope4:', model4.coef_)\n",
    "print('slope5:', model5.coef_)\n",
    "print('slope6:', model6.coef_)\n",
    "print('slope7:', model7.coef_)\n",
    "print('slope8:', model8.coef_)\n",
    "print('slope9:', model9.coef_)\n",
    "print('slope10:', model10.coef_)\n",
    "print('slope11:', model11.coef_)\n",
    "print('slope12:', model12.coef_)\n",
    "print('slope13:', model13.coef_)\n",
    "print('slope14:', model14.coef_)\n",
    "print('slope15:', model15.coef_)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8177db74",
   "metadata": {},
   "source": [
    "So it seems slope13 is the steepest, so that variable is the most impactful (followed closely by slope7's variable)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b24e54b7",
   "metadata": {},
   "source": [
    "##### CV8_2         =  \"INCREASE IN HH DURING COVID STAY-AT-HOME ORDER: SNAPPING/YELLING\" causes the greatest increase in distress levels out of any of these variables.\n",
    "\n",
    "##### CV7_10        =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: NONE OF THESE\" causes the greatest decrease in distress levels out of any of these variables."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "90d21ff1",
   "metadata": {},
   "source": [
    "# Verifying our results"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2a8f35f3",
   "metadata": {},
   "source": [
    "### For ### CV8_2         =  \"INCREASE IN HH DURING COVID STAY-AT-HOME ORDER: SNAPPING/YELLING\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "853832b5",
   "metadata": {},
   "source": [
    "We compare:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "a0475f0e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.03522854],\n",
       "       [0.05882353],\n",
       "       [0.08458524],\n",
       "       [0.11247878],\n",
       "       [0.12750643],\n",
       "       [0.14305556],\n",
       "       [0.16195569],\n",
       "       [0.20660277],\n",
       "       [0.184379  ],\n",
       "       [0.21202532],\n",
       "       [0.24603175],\n",
       "       [0.25449871],\n",
       "       [0.27506427],\n",
       "       [0.27822581],\n",
       "       [0.28125   ],\n",
       "       [0.28888889],\n",
       "       [0.33009709],\n",
       "       [0.4047619 ],\n",
       "       [0.3255814 ],\n",
       "       [0.35      ],\n",
       "       [0.45      ],\n",
       "       [0.34482759],\n",
       "       [0.5       ],\n",
       "       [0.42857143],\n",
       "       [0.25      ]])"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X13"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "24664a11",
   "metadata": {},
   "source": [
    "to:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "a112d23e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.07062213],\n",
       "       [0.08585175],\n",
       "       [0.10108137],\n",
       "       [0.116311  ],\n",
       "       [0.13154062],\n",
       "       [0.14677024],\n",
       "       [0.16199986],\n",
       "       [0.17722948],\n",
       "       [0.1924591 ],\n",
       "       [0.20768872],\n",
       "       [0.22291834],\n",
       "       [0.23814797],\n",
       "       [0.25337759],\n",
       "       [0.26860721],\n",
       "       [0.28383683],\n",
       "       [0.29906645],\n",
       "       [0.31429607],\n",
       "       [0.32952569],\n",
       "       [0.34475531],\n",
       "       [0.35998494],\n",
       "       [0.37521456],\n",
       "       [0.39044418],\n",
       "       [0.4056738 ],\n",
       "       [0.42090342],\n",
       "       [0.43613304]])"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x13_pred"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4729811b",
   "metadata": {},
   "source": [
    "Now, we find the correlation coefficient to ensure that our trendlines reflect strong, reliable correlations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "b1472a66",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SpearmanrResult(correlation=0.916923076923077, pvalue=1.1878653188790997e-10)"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "stats.spearmanr(X13, Y)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "277d0002",
   "metadata": {},
   "source": [
    "The correlation is high (close to 1), and the pvalue is very low (almost 0) so we can be assured that this result is trustworthy."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "74b9ba9e",
   "metadata": {},
   "source": [
    "We can also conduct a chi-squared test with the null hypothesis that our observed and expected values deviate too much for a strong enough correlation to exist."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "f26daa80",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Power_divergenceResult(statistic=array([0.18173187]), pvalue=array([9.54971411e-05]))"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "stats.chisquare(X13, x13_pred, ddof=23.9999) # using the actual degree of freedom (24) bugs it out and produces a NaN value"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b9d3c35d",
   "metadata": {},
   "source": [
    "Since our chi-squared test statistic is low with the appropriate degree of freedom,\n",
    "\n",
    "and the p-value is almost 0, \n",
    "\n",
    "we have very good evidence to reject the null hypothesis and we know our results are significant.\n",
    "\n",
    "This will ring similarly for our other tests:"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "60756a04",
   "metadata": {},
   "source": [
    "### CV7_10        =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: NONE OF THESE\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "1b8e1972",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SpearmanrResult(correlation=-0.8707692307692307, pvalue=1.5135913785692422e-08)"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "stats.spearmanr(X10, Y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "784dd386",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Power_divergenceResult(statistic=array([0.52681296]), pvalue=array([5.01936942e-05]))"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "stats.chisquare(X10, x10_pred, ddof=23.9999)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "493c07b5",
   "metadata": {},
   "source": [
    "# CONCLUSION"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3ebb57d1",
   "metadata": {},
   "source": [
    "In this walkthrough, we have:\n",
    "\n",
    "- Prepared COVID data in our dataframe adult_df\n",
    "\n",
    "- Represented the data with multiple visualizations in plotly\n",
    "\n",
    "- Manipulated adult_df to isolate column variables: aggregating, cleaning, finding proportions and counts, etc.\n",
    "\n",
    "- Performed Linear Regression tests to find variables that correlated with a change \"DISTRESS\" in distress values\n",
    "\n",
    "- Verified our findings using scipy statistical tests (spearmanr, chisquare)\n",
    "\n",
    "### Therefore, we can confidently state that among other findings, \n",
    "\n",
    "##### CV8_2         =  \"INCREASE IN HH DURING COVID STAY-AT-HOME ORDER: SNAPPING/YELLING\" causes the greatest increase in distress levels out of any of these variables,\n",
    "\n",
    "so increased snapping/yelling at one's home due to COVID STAY-AT-HOME Order is most likely to raise distress levels out of all surveyed variables, while\n",
    "\n",
    "##### CV7_10        =  \"EVER EXPERIENCED DUE TO COVID-19 OUTBREAK: NONE OF THESE\" causes the greatest decrease in distress levels out of any of these variables,\n",
    "\n",
    "so respondents who didn't experience any COVID-related troubles listed in the survey were increasingly unlikely to report higher distress levels."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "ea1684b6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<iframe\n",
       "    scrolling=\"no\"\n",
       "    width=\"620px\"\n",
       "    height=\"620\"\n",
       "    src=\"iframe_figures/figure_45.html\"\n",
       "    frameborder=\"0\"\n",
       "    allowfullscreen\n",
       "></iframe>\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = px.histogram(adult_df, \n",
    "x = \"DISTRESS\", \n",
    "color = \"CV8_2\", \n",
    "width = 600,\n",
    "height = 600,\n",
    "marginal = \"box\", # or violin, rug\n",
    "hover_data = adult_df.columns,\n",
    "barmode='overlay')\n",
    "\n",
    "fig.update_layout(barmode='overlay')\n",
    "\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "4d04cae9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<iframe\n",
       "    scrolling=\"no\"\n",
       "    width=\"620px\"\n",
       "    height=\"620\"\n",
       "    src=\"iframe_figures/figure_46.html\"\n",
       "    frameborder=\"0\"\n",
       "    allowfullscreen\n",
       "></iframe>\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = px.histogram(adult_df, \n",
    "x = \"DISTRESS\", \n",
    "color = \"CV7_10\", \n",
    "width = 600,\n",
    "height = 600,\n",
    "marginal = \"box\", # or violin, rug\n",
    "hover_data = adult_df.columns,\n",
    "barmode='overlay')\n",
    "\n",
    "fig.update_layout(barmode='overlay')\n",
    "\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4b025b92",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:PIC16B] *",
   "language": "python",
   "name": "conda-env-PIC16B-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}