Machine_Learning_Model.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Random Forest Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import dependencies\n",
    "import pandas as pd\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.preprocessing import StandardScaler,OneHotEncoder\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
    "from sqlalchemy import create_engine"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Load data from SQLite database"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>22</th>\n",
       "      <th>23</th>\n",
       "      <th>24</th>\n",
       "      <th>25</th>\n",
       "      <th>26</th>\n",
       "      <th>27</th>\n",
       "      <th>28</th>\n",
       "      <th>29</th>\n",
       "      <th>30</th>\n",
       "      <th>31</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Somewhat easy</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>1</td>\n",
       "      <td>Yes, they all did</td>\n",
       "      <td>...</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "      <td>Rarely</td>\n",
       "      <td>Sometimes</td>\n",
       "      <td>Male</td>\n",
       "      <td>United States of America</td>\n",
       "      <td>United States of America</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Neither easy nor difficult</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Maybe</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>1</td>\n",
       "      <td>I don't know</td>\n",
       "      <td>...</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "      <td>Sometimes</td>\n",
       "      <td>Sometimes</td>\n",
       "      <td>Female</td>\n",
       "      <td>United States of America</td>\n",
       "      <td>United States of America</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Yes</td>\n",
       "      <td>I am not sure</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Somewhat easy</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "      <td>No, none did</td>\n",
       "      <td>...</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>1</td>\n",
       "      <td>Not applicable to me</td>\n",
       "      <td>Often</td>\n",
       "      <td>Male</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>United Kingdom</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>I don't know</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Somewhat easy</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>1</td>\n",
       "      <td>Some did</td>\n",
       "      <td>...</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Not applicable to me</td>\n",
       "      <td>Not applicable to me</td>\n",
       "      <td>Male</td>\n",
       "      <td>United States of America</td>\n",
       "      <td>United States of America</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Very easy</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>I don't know</td>\n",
       "      <td>No</td>\n",
       "      <td>1</td>\n",
       "      <td>Some did</td>\n",
       "      <td>...</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "      <td>Sometimes</td>\n",
       "      <td>Often</td>\n",
       "      <td>Female</td>\n",
       "      <td>United States of America</td>\n",
       "      <td>United States of America</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 32 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "              0              1    2                           3    4      5   \n",
       "0            No            Yes  Yes               Somewhat easy   No     No  \\\n",
       "1           Yes            Yes   No  Neither easy nor difficult  Yes  Maybe   \n",
       "2           Yes  I am not sure  Yes               Somewhat easy  Yes    Yes   \n",
       "3  I don't know             No   No               Somewhat easy   No     No   \n",
       "4           Yes            Yes  Yes                   Very easy   No     No   \n",
       "\n",
       "              6    7  8                  9  ...   22   23   24   25 26   \n",
       "0           Yes   No  1  Yes, they all did  ...  Yes  Yes  Yes  Yes  1  \\\n",
       "1            No   No  1       I don't know  ...  Yes  Yes  Yes  Yes  1   \n",
       "2            No  Yes  1       No, none did  ...   No   No  Yes   No  1   \n",
       "3           Yes   No  1           Some did  ...   No   No   No   No  0   \n",
       "4  I don't know   No  1           Some did  ...  Yes  Yes  Yes  Yes  1   \n",
       "\n",
       "                     27                    28      29   \n",
       "0                Rarely             Sometimes    Male  \\\n",
       "1             Sometimes             Sometimes  Female   \n",
       "2  Not applicable to me                 Often    Male   \n",
       "3  Not applicable to me  Not applicable to me    Male   \n",
       "4             Sometimes                 Often  Female   \n",
       "\n",
       "                         30                        31  \n",
       "0  United States of America  United States of America  \n",
       "1  United States of America  United States of America  \n",
       "2            United Kingdom            United Kingdom  \n",
       "3  United States of America  United States of America  \n",
       "4  United States of America  United States of America  \n",
       "\n",
       "[5 rows x 32 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# load data back into a dataframe from the database\n",
    "#cnx = create_engine('sqlite:///mental_health.db').connect()\n",
    "mental_df = pd.read_sql_table('pre_encoded_survey', 'sqlite:///mental_health.db').drop(columns=['index'])\n",
    "mental_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     object\n",
       "1     object\n",
       "2     object\n",
       "3     object\n",
       "4     object\n",
       "5     object\n",
       "6     object\n",
       "7     object\n",
       "8      int64\n",
       "9     object\n",
       "10    object\n",
       "11    object\n",
       "12    object\n",
       "13    object\n",
       "14    object\n",
       "15    object\n",
       "16    object\n",
       "17    object\n",
       "18    object\n",
       "19    object\n",
       "20    object\n",
       "21    object\n",
       "22    object\n",
       "23    object\n",
       "24    object\n",
       "25    object\n",
       "26     int64\n",
       "27    object\n",
       "28    object\n",
       "29    object\n",
       "30    object\n",
       "31    object\n",
       "dtype: object"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mental_df.dtypes"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     4\n",
       "1     3\n",
       "2     3\n",
       "3     6\n",
       "4     3\n",
       "5     3\n",
       "6     3\n",
       "7     2\n",
       "9     4\n",
       "10    4\n",
       "11    4\n",
       "12    4\n",
       "13    4\n",
       "14    4\n",
       "15    4\n",
       "16    3\n",
       "17    3\n",
       "18    5\n",
       "19    5\n",
       "20    6\n",
       "21    4\n",
       "22    3\n",
       "23    3\n",
       "24    3\n",
       "25    2\n",
       "27    5\n",
       "28    5\n",
       "29    3\n",
       "30    7\n",
       "31    8\n",
       "dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Generate our categorical variable list\n",
    "mental_cat = mental_df.dtypes[mental_df.dtypes == \"object\"].index.tolist()\n",
    "\n",
    "# Check the number of unique values in each column\n",
    "mental_df[mental_cat].nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\Admin\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:868: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "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>0_I don't know</th>\n",
       "      <th>0_No</th>\n",
       "      <th>0_Not eligible for coverage / N/A</th>\n",
       "      <th>0_Yes</th>\n",
       "      <th>1_I am not sure</th>\n",
       "      <th>1_No</th>\n",
       "      <th>1_Yes</th>\n",
       "      <th>2_I don't know</th>\n",
       "      <th>2_No</th>\n",
       "      <th>2_Yes</th>\n",
       "      <th>...</th>\n",
       "      <th>30_United Kingdom</th>\n",
       "      <th>30_United States of America</th>\n",
       "      <th>31_Australia</th>\n",
       "      <th>31_Canada</th>\n",
       "      <th>31_Germany</th>\n",
       "      <th>31_Netherlands</th>\n",
       "      <th>31_Other</th>\n",
       "      <th>31_Sweden</th>\n",
       "      <th>31_United Kingdom</th>\n",
       "      <th>31_United States of America</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 120 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   0_I don't know  0_No  0_Not eligible for coverage / N/A  0_Yes   \n",
       "0             0.0   1.0                                0.0    0.0  \\\n",
       "1             0.0   0.0                                0.0    1.0   \n",
       "2             0.0   0.0                                0.0    1.0   \n",
       "3             1.0   0.0                                0.0    0.0   \n",
       "4             0.0   0.0                                0.0    1.0   \n",
       "\n",
       "   1_I am not sure  1_No  1_Yes  2_I don't know  2_No  2_Yes  ...   \n",
       "0              0.0   0.0    1.0             0.0   0.0    1.0  ...  \\\n",
       "1              0.0   0.0    1.0             0.0   1.0    0.0  ...   \n",
       "2              1.0   0.0    0.0             0.0   0.0    1.0  ...   \n",
       "3              0.0   1.0    0.0             0.0   1.0    0.0  ...   \n",
       "4              0.0   0.0    1.0             0.0   0.0    1.0  ...   \n",
       "\n",
       "   30_United Kingdom  30_United States of America  31_Australia  31_Canada   \n",
       "0                0.0                          1.0           0.0        0.0  \\\n",
       "1                0.0                          1.0           0.0        0.0   \n",
       "2                1.0                          0.0           0.0        0.0   \n",
       "3                0.0                          1.0           0.0        0.0   \n",
       "4                0.0                          1.0           0.0        0.0   \n",
       "\n",
       "   31_Germany  31_Netherlands  31_Other  31_Sweden  31_United Kingdom   \n",
       "0         0.0             0.0       0.0        0.0                0.0  \\\n",
       "1         0.0             0.0       0.0        0.0                0.0   \n",
       "2         0.0             0.0       0.0        0.0                1.0   \n",
       "3         0.0             0.0       0.0        0.0                0.0   \n",
       "4         0.0             0.0       0.0        0.0                0.0   \n",
       "\n",
       "   31_United States of America  \n",
       "0                          1.0  \n",
       "1                          1.0  \n",
       "2                          0.0  \n",
       "3                          1.0  \n",
       "4                          1.0  \n",
       "\n",
       "[5 rows x 120 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Create a OneHotEncoder instance\n",
    "enc = OneHotEncoder(sparse=False)\n",
    "\n",
    "# Fit and transform the OneHotEncoder using the categorical variable list\n",
    "encode_df = pd.DataFrame(enc.fit_transform(mental_df[mental_cat]))\n",
    "\n",
    "# Add the encoded variable names to the DataFrame\n",
    "encode_df.columns = enc.get_feature_names_out(mental_cat)\n",
    "encode_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The Column Header : [\"0_I don't know\", '0_No', '0_Not eligible for coverage / N/A', '0_Yes', '1_I am not sure', '1_No', '1_Yes', \"2_I don't know\", '2_No', '2_Yes', \"3_I don't know\", '3_Neither easy nor difficult', '3_Somewhat difficult', '3_Somewhat easy', '3_Very difficult', '3_Very easy', '4_Maybe', '4_No', '4_Yes', '5_Maybe', '5_No', '5_Yes', \"6_I don't know\", '6_No', '6_Yes', '7_No', '7_Yes', \"9_I don't know\", '9_No, none did', '9_Some did', '9_Yes, they all did', '10_I was aware of some', '10_N/A (not currently aware)', '10_No, I only became aware later', '10_Yes, I was aware of all of them', \"11_I don't know\", '11_None did', '11_Some did', '11_Yes, they all did', \"12_I don't know\", '12_No', '12_Sometimes', '12_Yes, always', \"13_I don't know\", '13_None of them', '13_Some of them', '13_Yes, all of them', \"14_I don't know\", '14_No, at none of my previous employers', '14_Some of my previous employers', '14_Yes, at all of my previous employers', \"15_I don't know\", '15_None did', '15_Some did', '15_Yes, they all did', '16_None of them', '16_Some of them', '16_Yes, all of them', '17_Maybe', '17_No', '17_Yes', '18_Maybe', \"18_No, I don't think it would\", '18_No, it has not', '18_Yes, I think it would', '18_Yes, it has', '19_Maybe', \"19_No, I don't think they would\", '19_No, they do not', '19_Yes, I think they would', '19_Yes, they do', '20_Neutral', '20_Not applicable to me (I do not have a mental illness)', '20_Not open at all', '20_Somewhat not open', '20_Somewhat open', '20_Very open', '21_Maybe/Not sure', '21_No', '21_Yes, I experienced', '21_Yes, I observed', \"22_I don't know\", '22_No', '22_Yes', '23_Maybe', '23_No', '23_Yes', '24_Maybe', '24_No', '24_Yes', '25_No', '25_Yes', '27_Never', '27_Not applicable to me', '27_Often', '27_Rarely', '27_Sometimes', '28_Never', '28_Not applicable to me', '28_Often', '28_Rarely', '28_Sometimes', '29_Female', '29_Male', '29_Other', '30_Australia', '30_Canada', '30_Germany', '30_Netherlands', '30_Other', '30_United Kingdom', '30_United States of America', '31_Australia', '31_Canada', '31_Germany', '31_Netherlands', '31_Other', '31_Sweden', '31_United Kingdom', '31_United States of America']\n"
     ]
    }
   ],
   "source": [
    "column_headers = list(encode_df.columns.values)\n",
    "print(\"The Column Header :\", column_headers)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>8</th>\n",
       "      <th>26</th>\n",
       "      <th>0_I don't know</th>\n",
       "      <th>0_No</th>\n",
       "      <th>0_Not eligible for coverage / N/A</th>\n",
       "      <th>0_Yes</th>\n",
       "      <th>1_I am not sure</th>\n",
       "      <th>1_No</th>\n",
       "      <th>1_Yes</th>\n",
       "      <th>2_I don't know</th>\n",
       "      <th>...</th>\n",
       "      <th>30_United Kingdom</th>\n",
       "      <th>30_United States of America</th>\n",
       "      <th>31_Australia</th>\n",
       "      <th>31_Canada</th>\n",
       "      <th>31_Germany</th>\n",
       "      <th>31_Netherlands</th>\n",
       "      <th>31_Other</th>\n",
       "      <th>31_Sweden</th>\n",
       "      <th>31_United Kingdom</th>\n",
       "      <th>31_United States of America</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 122 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   8  26  0_I don't know  0_No  0_Not eligible for coverage / N/A  0_Yes   \n",
       "0  1   1             0.0   1.0                                0.0    0.0  \\\n",
       "1  1   1             0.0   0.0                                0.0    1.0   \n",
       "2  1   1             0.0   0.0                                0.0    1.0   \n",
       "3  1   0             1.0   0.0                                0.0    0.0   \n",
       "4  1   1             0.0   0.0                                0.0    1.0   \n",
       "\n",
       "   1_I am not sure  1_No  1_Yes  2_I don't know  ...  30_United Kingdom   \n",
       "0              0.0   0.0    1.0             0.0  ...                0.0  \\\n",
       "1              0.0   0.0    1.0             0.0  ...                0.0   \n",
       "2              1.0   0.0    0.0             0.0  ...                1.0   \n",
       "3              0.0   1.0    0.0             0.0  ...                0.0   \n",
       "4              0.0   0.0    1.0             0.0  ...                0.0   \n",
       "\n",
       "   30_United States of America  31_Australia  31_Canada  31_Germany   \n",
       "0                          1.0           0.0        0.0         0.0  \\\n",
       "1                          1.0           0.0        0.0         0.0   \n",
       "2                          0.0           0.0        0.0         0.0   \n",
       "3                          1.0           0.0        0.0         0.0   \n",
       "4                          1.0           0.0        0.0         0.0   \n",
       "\n",
       "   31_Netherlands  31_Other  31_Sweden  31_United Kingdom   \n",
       "0             0.0       0.0        0.0                0.0  \\\n",
       "1             0.0       0.0        0.0                0.0   \n",
       "2             0.0       0.0        0.0                1.0   \n",
       "3             0.0       0.0        0.0                0.0   \n",
       "4             0.0       0.0        0.0                0.0   \n",
       "\n",
       "   31_United States of America  \n",
       "0                          1.0  \n",
       "1                          1.0  \n",
       "2                          0.0  \n",
       "3                          1.0  \n",
       "4                          1.0  \n",
       "\n",
       "[5 rows x 122 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Merge one-hot encoded features and drop the originals\n",
    "mental_df = mental_df.merge(encode_df,left_index=True, right_index=True)\n",
    "mental_df = mental_df.drop(mental_cat,axis=1)\n",
    "mental_df.head()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Send encoded dataframe to database to be used in model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create the engine\n",
    "engine = create_engine(\"sqlite:///mental_health.db\", echo=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "861"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Use pandas to_sql to write records stored in a dataframe to a SQL database\n",
    "\n",
    "# Write dataframe of all survey questions to a sqlite table\n",
    "mental_df.to_sql('encoded_survey', con=engine, if_exists='replace')\n",
    "#engine.execute(\"SELECT * FROM encoded_survey\").fetchall()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>8</th>\n",
       "      <th>26</th>\n",
       "      <th>0_I don't know</th>\n",
       "      <th>0_No</th>\n",
       "      <th>0_Not eligible for coverage / N/A</th>\n",
       "      <th>0_Yes</th>\n",
       "      <th>1_I am not sure</th>\n",
       "      <th>1_No</th>\n",
       "      <th>1_Yes</th>\n",
       "      <th>2_I don't know</th>\n",
       "      <th>...</th>\n",
       "      <th>30_United Kingdom</th>\n",
       "      <th>30_United States of America</th>\n",
       "      <th>31_Australia</th>\n",
       "      <th>31_Canada</th>\n",
       "      <th>31_Germany</th>\n",
       "      <th>31_Netherlands</th>\n",
       "      <th>31_Other</th>\n",
       "      <th>31_Sweden</th>\n",
       "      <th>31_United Kingdom</th>\n",
       "      <th>31_United States of America</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>856</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>857</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>858</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>859</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>860</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>861 rows × 122 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     8  26  0_I don't know  0_No  0_Not eligible for coverage / N/A  0_Yes   \n",
       "0    1   1             0.0   1.0                                0.0    0.0  \\\n",
       "1    1   1             0.0   0.0                                0.0    1.0   \n",
       "2    1   1             0.0   0.0                                0.0    1.0   \n",
       "3    1   0             1.0   0.0                                0.0    0.0   \n",
       "4    1   1             0.0   0.0                                0.0    1.0   \n",
       "..  ..  ..             ...   ...                                ...    ...   \n",
       "856  1   0             0.0   0.0                                0.0    1.0   \n",
       "857  1   1             1.0   0.0                                0.0    0.0   \n",
       "858  1   1             0.0   0.0                                0.0    1.0   \n",
       "859  1   1             0.0   0.0                                0.0    1.0   \n",
       "860  1   0             1.0   0.0                                0.0    0.0   \n",
       "\n",
       "     1_I am not sure  1_No  1_Yes  2_I don't know  ...  30_United Kingdom   \n",
       "0                0.0   0.0    1.0             0.0  ...                0.0  \\\n",
       "1                0.0   0.0    1.0             0.0  ...                0.0   \n",
       "2                1.0   0.0    0.0             0.0  ...                1.0   \n",
       "3                0.0   1.0    0.0             0.0  ...                0.0   \n",
       "4                0.0   0.0    1.0             0.0  ...                0.0   \n",
       "..               ...   ...    ...             ...  ...                ...   \n",
       "856              1.0   0.0    0.0             0.0  ...                0.0   \n",
       "857              1.0   0.0    0.0             1.0  ...                0.0   \n",
       "858              0.0   1.0    0.0             0.0  ...                0.0   \n",
       "859              0.0   0.0    1.0             0.0  ...                0.0   \n",
       "860              1.0   0.0    0.0             0.0  ...                0.0   \n",
       "\n",
       "     30_United States of America  31_Australia  31_Canada  31_Germany   \n",
       "0                            1.0           0.0        0.0         0.0  \\\n",
       "1                            1.0           0.0        0.0         0.0   \n",
       "2                            0.0           0.0        0.0         0.0   \n",
       "3                            1.0           0.0        0.0         0.0   \n",
       "4                            1.0           0.0        0.0         0.0   \n",
       "..                           ...           ...        ...         ...   \n",
       "856                          0.0           0.0        1.0         0.0   \n",
       "857                          0.0           0.0        1.0         0.0   \n",
       "858                          1.0           0.0        0.0         0.0   \n",
       "859                          1.0           0.0        0.0         0.0   \n",
       "860                          1.0           0.0        0.0         0.0   \n",
       "\n",
       "     31_Netherlands  31_Other  31_Sweden  31_United Kingdom   \n",
       "0               0.0       0.0        0.0                0.0  \\\n",
       "1               0.0       0.0        0.0                0.0   \n",
       "2               0.0       0.0        0.0                1.0   \n",
       "3               0.0       0.0        0.0                0.0   \n",
       "4               0.0       0.0        0.0                0.0   \n",
       "..              ...       ...        ...                ...   \n",
       "856             0.0       0.0        0.0                0.0   \n",
       "857             0.0       0.0        0.0                0.0   \n",
       "858             0.0       0.0        0.0                0.0   \n",
       "859             0.0       0.0        0.0                0.0   \n",
       "860             0.0       0.0        0.0                0.0   \n",
       "\n",
       "     31_United States of America  \n",
       "0                            1.0  \n",
       "1                            1.0  \n",
       "2                            0.0  \n",
       "3                            1.0  \n",
       "4                            1.0  \n",
       "..                           ...  \n",
       "856                          0.0  \n",
       "857                          0.0  \n",
       "858                          1.0  \n",
       "859                          1.0  \n",
       "860                          1.0  \n",
       "\n",
       "[861 rows x 122 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# load data back into a dataframe from the database\n",
    "#cnx=create_engine('sqlite:///mental_health.db').connect()\n",
    "mental_df = pd.read_sql_table('encoded_survey','sqlite:///mental_health.db' ).drop(columns=['index'])\n",
    "mental_df"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>Question</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Does your employer provide mental health benef...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Do you know the options for mental health care...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Does your employer offer resources to learn mo...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>If a mental health issue prompted you to reque...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Do you think that discussing a mental health d...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Do you think that discussing a physical health...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Do you feel that your employer takes mental he...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Have you heard of or observed negative consequ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Do you have previous employers?</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Have your previous employers provided mental h...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Were you aware of the options for mental healt...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Did your previous employers ever formally disc...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Was your anonymity protected if you chose to t...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Do you think that discussing a mental health d...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Would you have been willing to discuss a menta...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Did you feel that your previous employers took...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Did you hear of or observe negative consequenc...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>Would you bring up a mental health issue with ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Do you feel that being identified as a person ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>Do you think that team members/co-workers woul...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>How willing would you be to share with friends...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>Have you observed or experienced an unsupporti...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>Do you have a family history of mental illness?</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>Have you had a mental health disorder in the p...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>Do you currently have a mental health disorder?</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>Have you been diagnosed with a mental health c...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>Have you ever sought treatment for a mental he...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>If you have a mental health issue, do you feel...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>If you have a mental health issue, do you feel...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>What is your gender?</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>What country do you live in?</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>What country do you work in?</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                             Question\n",
       "0   Does your employer provide mental health benef...\n",
       "1   Do you know the options for mental health care...\n",
       "2   Does your employer offer resources to learn mo...\n",
       "3   If a mental health issue prompted you to reque...\n",
       "4   Do you think that discussing a mental health d...\n",
       "5   Do you think that discussing a physical health...\n",
       "6   Do you feel that your employer takes mental he...\n",
       "7   Have you heard of or observed negative consequ...\n",
       "8                     Do you have previous employers?\n",
       "9   Have your previous employers provided mental h...\n",
       "10  Were you aware of the options for mental healt...\n",
       "11  Did your previous employers ever formally disc...\n",
       "12  Was your anonymity protected if you chose to t...\n",
       "13  Do you think that discussing a mental health d...\n",
       "14  Would you have been willing to discuss a menta...\n",
       "15  Did you feel that your previous employers took...\n",
       "16  Did you hear of or observe negative consequenc...\n",
       "17  Would you bring up a mental health issue with ...\n",
       "18  Do you feel that being identified as a person ...\n",
       "19  Do you think that team members/co-workers woul...\n",
       "20  How willing would you be to share with friends...\n",
       "21  Have you observed or experienced an unsupporti...\n",
       "22    Do you have a family history of mental illness?\n",
       "23  Have you had a mental health disorder in the p...\n",
       "24    Do you currently have a mental health disorder?\n",
       "25  Have you been diagnosed with a mental health c...\n",
       "26  Have you ever sought treatment for a mental he...\n",
       "27  If you have a mental health issue, do you feel...\n",
       "28  If you have a mental health issue, do you feel...\n",
       "29                               What is your gender?\n",
       "30                       What country do you live in?\n",
       "31                       What country do you work in?"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# load data back into a dataframe from the database\n",
    "#cnx=create_engine('sqlite:///mental_health.db').connect()\n",
    "questions_df = pd.read_sql_table('pre_encoded_questions', 'sqlite:///mental_health.db').drop(columns=['index'])\n",
    "questions_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define the target set.\n",
    "y = mental_df[\"25_Yes\"]\n",
    "\n",
    "# Define the features set.\n",
    "X = mental_df.drop(columns=[\"25_Yes\",\"25_No\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Splitting into Train and Test sets.\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=78)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a random forest classifier.\n",
    "rf_model = RandomForestClassifier(n_estimators=128, random_state=78)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Fitting the model\n",
    "rf_model = rf_model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0., 1., 1., 1., 1., 0., 1., 0., 1., 1., 1., 0., 0., 1., 1., 0., 1.,\n",
       "       1., 1., 1., 1., 1., 0., 0., 1., 0., 1., 1., 0., 1., 1., 0., 1., 1.,\n",
       "       1., 0., 0., 1., 1., 0., 1., 1., 0., 0., 0., 1., 0., 1., 0., 1., 1.,\n",
       "       1., 0., 1., 0., 1., 1., 1., 0., 1., 0., 1., 1., 0., 1., 0., 1., 1.,\n",
       "       0., 0., 0., 0., 0., 1., 0., 1., 1., 1., 1., 1., 1., 0., 1., 1., 1.,\n",
       "       0., 1., 0., 1., 1., 1., 1., 1., 0., 0., 1., 1., 1., 0., 1., 1., 1.,\n",
       "       0., 0., 0., 1., 1., 0., 0., 1., 1., 1., 1., 1., 1., 0., 1., 1., 1.,\n",
       "       0., 1., 0., 1., 0., 0., 1., 1., 0., 0., 1., 1., 0., 1., 1., 1., 0.,\n",
       "       1., 1., 0., 1., 0., 0., 1., 0., 1., 1., 1., 0., 1., 1., 0., 1., 0.,\n",
       "       0., 0., 1., 1., 0., 1., 1., 0., 0., 0., 1., 1., 1., 1., 1., 0., 1.,\n",
       "       0., 1., 1., 0., 0., 1., 1., 0., 1., 1., 1., 0., 0., 1., 0., 0., 1.,\n",
       "       0., 1., 1., 0., 1., 1., 1., 0., 1., 0., 0., 1., 1., 1., 1., 1., 1.,\n",
       "       1., 1., 1., 1., 1., 0., 0., 1., 1., 0., 1., 0.])"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Making predictions using the testing data.\n",
    "predictions = rf_model.predict(X_test)\n",
    "predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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>Predicted 0</th>\n",
       "      <th>Predicted 1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Actual 0</th>\n",
       "      <td>75</td>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Actual 1</th>\n",
       "      <td>7</td>\n",
       "      <td>111</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Predicted 0  Predicted 1\n",
       "Actual 0           75           23\n",
       "Actual 1            7          111"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Calculating the confusion matrix.\n",
    "cm = confusion_matrix(y_test, predictions)\n",
    "\n",
    "# Create a DataFrame from the confusion matrix.\n",
    "cm_df = pd.DataFrame(\n",
    "cm, index=[\"Actual 0\", \"Actual 1\"], columns=[\"Predicted 0\", \"Predicted 1\"])\n",
    "\n",
    "cm_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8283582089552238\n"
     ]
    }
   ],
   "source": [
    "# Calculating the accuracy score.\n",
    "import sklearn\n",
    "\n",
    "\n",
    "acc_score = accuracy_score(y_test, predictions)\n",
    "pres = sklearn.metrics.precision_score(y_test, predictions)\n",
    "print(pres)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Create a Confusion Matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Confusion Matrix\n"
     ]
    },
    {
     "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>Predicted 0</th>\n",
       "      <th>Predicted 1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Actual 0</th>\n",
       "      <td>75</td>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Actual 1</th>\n",
       "      <td>7</td>\n",
       "      <td>111</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Predicted 0  Predicted 1\n",
       "Actual 0           75           23\n",
       "Actual 1            7          111"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy Score : 0.8611111111111112\n",
      "Classification Report\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "         0.0       0.91      0.77      0.83        98\n",
      "         1.0       0.83      0.94      0.88       118\n",
      "\n",
      "    accuracy                           0.86       216\n",
      "   macro avg       0.87      0.85      0.86       216\n",
      "weighted avg       0.87      0.86      0.86       216\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Displaying results\n",
    "print(\"Confusion Matrix\")\n",
    "display(cm_df)\n",
    "print(f\"Accuracy Score : {acc_score}\")\n",
    "print(\"Classification Report\")\n",
    "print(classification_report(y_test, predictions))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.00000000e+00, 1.10419050e-01, 5.67529724e-03, 1.65687097e-03,\n",
       "       3.34889219e-03, 4.77398577e-03, 2.86263014e-03, 6.59232613e-03,\n",
       "       6.87360840e-03, 4.75727324e-03, 4.52849706e-03, 4.32812773e-03,\n",
       "       3.84626568e-03, 2.44265684e-03, 4.74462438e-03, 3.93220193e-03,\n",
       "       1.96594474e-03, 2.45223494e-03, 4.32743555e-03, 4.14851247e-03,\n",
       "       2.76312046e-03, 3.94917584e-03, 3.04315937e-03, 2.26892999e-03,\n",
       "       4.42000131e-03, 3.18407639e-03, 3.68580684e-03, 2.50538604e-03,\n",
       "       1.92557573e-03, 4.96987345e-03, 4.02072982e-03, 7.53026483e-03,\n",
       "       2.36400258e-03, 5.49362358e-03, 6.82871236e-03, 2.98918112e-03,\n",
       "       1.99578370e-03, 1.32254134e-03, 3.64470239e-03, 4.60907129e-03,\n",
       "       8.87053686e-04, 4.09469487e-03, 1.66981912e-03, 3.11731938e-03,\n",
       "       2.70249597e-03, 3.47603523e-03, 2.49857420e-03, 4.73271396e-03,\n",
       "       5.25853416e-03, 1.09213371e-03, 3.55670457e-03, 3.82392394e-03,\n",
       "       1.48931802e-03, 5.92142403e-03, 4.83229807e-03, 5.52944146e-03,\n",
       "       8.67261202e-04, 4.24373462e-03, 3.63790159e-03, 1.33819673e-03,\n",
       "       3.52337157e-03, 4.70457136e-03, 2.27761535e-03, 5.09720601e-03,\n",
       "       1.48013486e-03, 9.74735092e-04, 3.56826688e-03, 1.87431654e-03,\n",
       "       4.61220633e-03, 3.39251757e-03, 2.15908157e-03, 3.97732359e-03,\n",
       "       1.09691524e-03, 2.35067212e-03, 2.62899355e-03, 1.40045065e-03,\n",
       "       3.66390993e-03, 4.88522724e-03, 3.25369720e-03, 4.20801536e-03,\n",
       "       3.92040223e-03, 6.09875180e-03, 3.34012519e-03, 4.31860930e-03,\n",
       "       2.08773044e-02, 1.87398806e-02, 1.58858884e-02, 6.01976677e-02,\n",
       "       1.20248058e-01, 1.38676462e-02, 3.68153955e-02, 8.94888194e-02,\n",
       "       3.26145254e-03, 7.24086890e-02, 1.30968184e-03, 1.52994812e-02,\n",
       "       9.31987753e-03, 2.03765295e-04, 4.37201858e-02, 2.91200630e-02,\n",
       "       4.50932783e-03, 9.23245175e-03, 4.69447728e-03, 4.55127772e-03,\n",
       "       8.88642181e-04, 1.26947644e-04, 1.75915960e-03, 1.15920860e-03,\n",
       "       9.82574596e-04, 2.25969427e-03, 1.62972450e-03, 3.59269743e-03,\n",
       "       9.19225625e-05, 1.22621938e-03, 5.51998884e-04, 1.04972430e-03,\n",
       "       2.70030468e-03, 1.36094931e-03, 1.88350257e-03, 4.21848984e-03])"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Calculate feature importance in the Random Forest model.\n",
    "importances = rf_model.feature_importances_\n",
    "importances"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[(0.12024805797660318, '23_Yes'),\n",
       " (0.11041904981287384, '26'),\n",
       " (0.08948881936577566, '24_Yes'),\n",
       " (0.07240868904721894, '27_Not applicable to me'),\n",
       " (0.060197667718725555, '23_No'),\n",
       " (0.043720185842798506, '28_Not applicable to me'),\n",
       " (0.036815395479663025, '24_No'),\n",
       " (0.02912006295329515, '28_Often'),\n",
       " (0.020877304353417295, '22_No'),\n",
       " (0.01873988058843284, '22_Yes'),\n",
       " (0.01588588843548007, '23_Maybe'),\n",
       " (0.015299481191566024, '27_Rarely'),\n",
       " (0.013867646180869025, '24_Maybe'),\n",
       " (0.009319877532035678, '27_Sometimes'),\n",
       " (0.009232451751315603, '28_Sometimes'),\n",
       " (0.007530264833722061, '9_Some did'),\n",
       " (0.006873608396547313, '1_Yes'),\n",
       " (0.006828712358086473, '10_N/A (not currently aware)'),\n",
       " (0.006592326132076189, '1_No'),\n",
       " (0.006098751799722544, '21_Yes, I experienced'),\n",
       " (0.0059214240286992025, \"15_I don't know\"),\n",
       " (0.005675297236103962, \"0_I don't know\"),\n",
       " (0.005529441456887535, '15_Some did'),\n",
       " (0.005493623584711995, '10_I was aware of some'),\n",
       " (0.005258534156281813, '13_Yes, all of them'),\n",
       " (0.00509720601394967, '18_Maybe'),\n",
       " (0.004969873449539534, \"9_I don't know\"),\n",
       " (0.004885227235971476, '20_Somewhat open'),\n",
       " (0.004832298069130747, '15_None did'),\n",
       " (0.004773985774505891, '0_Yes'),\n",
       " (0.004757273239359274, \"2_I don't know\"),\n",
       " (0.00474462438256302, '3_Somewhat difficult'),\n",
       " (0.004732713963944044, '13_Some of them'),\n",
       " (0.004704571362841303, '17_No'),\n",
       " (0.004694477283394608, '29_Female'),\n",
       " (0.004612206328236454, '19_Maybe'),\n",
       " (0.004609071289895478, '11_Some did'),\n",
       " (0.004551277722747784, '29_Male'),\n",
       " (0.004528497064968191, '2_No'),\n",
       " (0.0045093278315437215, '28_Rarely'),\n",
       " (0.004420001312399554, \"6_I don't know\"),\n",
       " (0.004328127729206886, '2_Yes'),\n",
       " (0.0043274355527788, '4_Maybe'),\n",
       " (0.004318609295670676, \"22_I don't know\"),\n",
       " (0.0042437346194589935, '16_None of them'),\n",
       " (0.004218489837384891, '31_United States of America'),\n",
       " (0.0042080153579229194, '21_Maybe/Not sure'),\n",
       " (0.004148512474691333, '4_No'),\n",
       " (0.00409469487040336, \"12_I don't know\"),\n",
       " (0.004020729815157015, '9_No, none did'),\n",
       " (0.0039773235860317375, '19_Yes, I think they would'),\n",
       " (0.00394917583696326, '5_Maybe'),\n",
       " (0.003932201934965467, '3_Somewhat easy'),\n",
       " (0.003920402225205477, '21_No'),\n",
       " (0.0038462656779453546, \"3_I don't know\"),\n",
       " (0.003823923943166018, '14_Some of my previous employers'),\n",
       " (0.0036858068386194246, '6_Yes'),\n",
       " (0.003663909929799883, '20_Somewhat not open'),\n",
       " (0.0036447023906744334, '11_None did'),\n",
       " (0.0036379015871988584, '16_Some of them'),\n",
       " (0.0035926974332522034, '30_United States of America'),\n",
       " (0.003568266882616158, '18_Yes, I think it would'),\n",
       " (0.003556704572037552, '14_No, at none of my previous employers'),\n",
       " (0.003523371567202977, '17_Maybe'),\n",
       " (0.0034760352302814048, \"13_I don't know\"),\n",
       " (0.003392517573674982, \"19_No, I don't think they would\"),\n",
       " (0.0033488921897075617, '0_Not eligible for coverage / N/A'),\n",
       " (0.0033401251894899205, '21_Yes, I observed'),\n",
       " (0.0032614525361438166, '27_Never'),\n",
       " (0.003253697203449811, '20_Very open'),\n",
       " (0.0031840763922629405, '6_No'),\n",
       " (0.003117319384988977, '12_Sometimes'),\n",
       " (0.0030431593725536847, '5_No'),\n",
       " (0.0029891811172830535, '10_No, I only became aware later'),\n",
       " (0.0028626301448683522, '1_I am not sure'),\n",
       " (0.002763120459132322, '4_Yes'),\n",
       " (0.002702495970587231, '12_Yes, always'),\n",
       " (0.002700304681168638, '31_Other'),\n",
       " (0.002628993547790125,\n",
       "  '20_Not applicable to me (I do not have a mental illness)'),\n",
       " (0.002505386040665268, '7_No'),\n",
       " (0.0024985742000502107, '13_None of them'),\n",
       " (0.002452234941148902, '3_Very easy'),\n",
       " (0.0024426568448041933, '3_Neither easy nor difficult'),\n",
       " (0.0023640025809882367, '9_Yes, they all did'),\n",
       " (0.0023506721234228807, '20_Neutral'),\n",
       " (0.0022776153452677907, '17_Yes'),\n",
       " (0.0022689299937348546, '5_Yes'),\n",
       " (0.002259694271194966, '30_Other'),\n",
       " (0.002159081569693065, '19_No, they do not'),\n",
       " (0.0019957837019981273, '10_Yes, I was aware of all of them'),\n",
       " (0.0019659447362507976, '3_Very difficult'),\n",
       " (0.0019255757266982484, '7_Yes'),\n",
       " (0.00188350257440474, '31_United Kingdom'),\n",
       " (0.0018743165419644787, '18_Yes, it has'),\n",
       " (0.0017591596042759532, '30_Canada'),\n",
       " (0.0016698191172917118, '12_No'),\n",
       " (0.001656870971835973, '0_No'),\n",
       " (0.0016297244960730773, '30_United Kingdom'),\n",
       " (0.001489318016517049, '14_Yes, at all of my previous employers'),\n",
       " (0.001480134864856029, \"18_No, I don't think it would\"),\n",
       " (0.0014004506514670345, '20_Not open at all'),\n",
       " (0.0013609493093240032, '31_Sweden'),\n",
       " (0.001338196729098717, '16_Yes, all of them'),\n",
       " (0.001322541340796772, \"11_I don't know\"),\n",
       " (0.0013096818449635716, '27_Often'),\n",
       " (0.0012262193801065905, '31_Canada'),\n",
       " (0.0011592086038048545, '30_Germany'),\n",
       " (0.0010969152409325876, '19_Yes, they do'),\n",
       " (0.0010921337064618492, \"14_I don't know\"),\n",
       " (0.001049724298985151, '31_Netherlands'),\n",
       " (0.000982574595740978, '30_Netherlands'),\n",
       " (0.0009747350916809387, '18_No, it has not'),\n",
       " (0.0008886421807399982, '29_Other'),\n",
       " (0.0008870536861229455, '11_Yes, they all did'),\n",
       " (0.0008672612024514066, '15_Yes, they all did'),\n",
       " (0.0005519988836541869, '31_Germany'),\n",
       " (0.0002037652947386564, '28_Never'),\n",
       " (0.00012694764367634752, '30_Australia'),\n",
       " (9.192256248014986e-05, '31_Australia'),\n",
       " (0.0, '8')]"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# We can sort the features by their importance.\n",
    "sorted(zip(rf_model.feature_importances_, X.columns), reverse=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test score: 86.11 %\n"
     ]
    }
   ],
   "source": [
    "# save our model to use later\n",
    "import pickle\n",
    "\n",
    "# Save to file in the current working directory\n",
    "pkl_filename = \"pickle_model.pkl\"\n",
    "with open(pkl_filename, 'wb') as file:\n",
    "    pickle.dump(rf_model, file)\n",
    "\n",
    "# Load from file\n",
    "with open(pkl_filename, 'rb') as file:\n",
    "    pickle_model = pickle.load(file)\n",
    "    \n",
    "# Calculate the accuracy score and predict target values\n",
    "score = pickle_model.score(X_test, y_test)\n",
    "print(\"Test score: {0:.2f} %\".format(100 * score))\n",
    "Ypredict = pickle_model.predict(X_test)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Our model’s accuracy score is 86.11, meaning that it accurately predicts if an individual has a mental health disorder 86.11% of the time, based off how they answer survey questions (assuming they answer honestly). Since this model is not making a prediction that has high consequences, it is merely for the interest of an individual working in tech and wanting to know their likelihood of having (or developing) a mental health disorder, or for the interest of a tech company and wanting to know if offering certain mental health services would be of benefit to their employees, an accuracy of 86.11% is sufficient."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}