4b_ex_1_solution.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Stroke Thromobolysis Dataset: Logistic Regression Exercise (Solution)\n",
    "\n",
    "The data loaded in this exercise is for seven acute stroke units, and whether a patient receives clost-busting treatment for stroke.  There are lots of features, and a description of the features can be found in the file stroke_data_feature_descriptions.csv.\n",
    "\n",
    "Train a Logistic Regression model to try to predict whether or not a stroke patient receives clot-busting treatment.  Use the prompts below to write each section of code.\n",
    "\n",
    "What do you conclude are the most important features for predicting whether a patient receives clot busting treatment?  Can you improve accuracy by changing the size of your train / test split?  If you have time, perhaps consider dropping some features from your data based on your outputs (in the same way you dropped passengerID in the Titanic example).  Don't forget you'll need to rerun all subsequent cells if you make changes like that."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Clotbuster given</th>\n",
       "      <th>Hosp_1</th>\n",
       "      <th>Hosp_2</th>\n",
       "      <th>Hosp_3</th>\n",
       "      <th>Hosp_4</th>\n",
       "      <th>Hosp_5</th>\n",
       "      <th>Hosp_6</th>\n",
       "      <th>Hosp_7</th>\n",
       "      <th>Male</th>\n",
       "      <th>Age</th>\n",
       "      <th>...</th>\n",
       "      <th>S2NihssArrivalFacialPalsy</th>\n",
       "      <th>S2NihssArrivalMotorArmLeft</th>\n",
       "      <th>S2NihssArrivalMotorArmRight</th>\n",
       "      <th>S2NihssArrivalMotorLegLeft</th>\n",
       "      <th>S2NihssArrivalMotorLegRight</th>\n",
       "      <th>S2NihssArrivalLimbAtaxia</th>\n",
       "      <th>S2NihssArrivalSensory</th>\n",
       "      <th>S2NihssArrivalBestLanguage</th>\n",
       "      <th>S2NihssArrivalDysarthria</th>\n",
       "      <th>S2NihssArrivalExtinctionInattention</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>63.0</td>\n",
       "      <td>...</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</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>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>85.0</td>\n",
       "      <td>...</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>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\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",
       "      <td>91.0</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>1.0</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>3</th>\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",
       "      <td>90.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</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>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>...</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 51 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Clotbuster given  Hosp_1  Hosp_2  Hosp_3  Hosp_4  Hosp_5  Hosp_6  Hosp_7  \\\n",
       "0               1.0     0.0     1.0     0.0     0.0     0.0     0.0     0.0   \n",
       "1               1.0     0.0     1.0     0.0     0.0     0.0     0.0     0.0   \n",
       "2               0.0     0.0     1.0     0.0     0.0     0.0     0.0     0.0   \n",
       "3               0.0     0.0     1.0     0.0     0.0     0.0     0.0     0.0   \n",
       "4               1.0     0.0     1.0     0.0     0.0     0.0     0.0     0.0   \n",
       "\n",
       "   Male   Age  ...  S2NihssArrivalFacialPalsy  S2NihssArrivalMotorArmLeft  \\\n",
       "0   0.0  63.0  ...                        3.0                         4.0   \n",
       "1   0.0  85.0  ...                        0.0                         0.0   \n",
       "2   0.0  91.0  ...                        0.0                         1.0   \n",
       "3   0.0  90.0  ...                        1.0                         1.0   \n",
       "4   0.0  69.0  ...                        2.0                         0.0   \n",
       "\n",
       "   S2NihssArrivalMotorArmRight  S2NihssArrivalMotorLegLeft  \\\n",
       "0                          0.0                         4.0   \n",
       "1                          0.0                         0.0   \n",
       "2                          0.0                         0.0   \n",
       "3                          0.0                         1.0   \n",
       "4                          4.0                         1.0   \n",
       "\n",
       "   S2NihssArrivalMotorLegRight  S2NihssArrivalLimbAtaxia  \\\n",
       "0                          0.0                       0.0   \n",
       "1                          0.0                       0.0   \n",
       "2                          0.0                       1.0   \n",
       "3                          0.0                       0.0   \n",
       "4                          4.0                       0.0   \n",
       "\n",
       "   S2NihssArrivalSensory  S2NihssArrivalBestLanguage  \\\n",
       "0                    0.0                         0.0   \n",
       "1                    0.0                         2.0   \n",
       "2                    0.0                         0.0   \n",
       "3                    1.0                         0.0   \n",
       "4                    1.0                         2.0   \n",
       "\n",
       "   S2NihssArrivalDysarthria  S2NihssArrivalExtinctionInattention  \n",
       "0                       1.0                                  1.0  \n",
       "1                       1.0                                  0.0  \n",
       "2                       0.0                                  0.0  \n",
       "3                       1.0                                  0.0  \n",
       "4                       2.0                                  1.0  \n",
       "\n",
       "[5 rows x 51 columns]"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "# Import machine learning methods\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "# Download data\n",
    "# (not required if running locally and have previously downloaded data)\n",
    "\n",
    "download_required = True\n",
    "\n",
    "if download_required:\n",
    "\n",
    "    # Download processed data:\n",
    "    address = 'https://raw.githubusercontent.com/MichaelAllen1966/' + \\\n",
    "                '2004_titanic/master/jupyter_notebooks/data/hsma_stroke.csv'\n",
    "    data = pd.read_csv(address)\n",
    "\n",
    "    # Create a data subfolder if one does not already exist\n",
    "    import os\n",
    "    data_directory ='./data/'\n",
    "    if not os.path.exists(data_directory):\n",
    "        os.makedirs(data_directory)\n",
    "\n",
    "    # Save data to data subfolder\n",
    "    data.to_csv(data_directory + 'hsma_stroke.csv', index=False)\n",
    "\n",
    "# Load data\n",
    "data = pd.read_csv('data/hsma_stroke.csv')\n",
    "# Make all data 'float' type\n",
    "data = data.astype(float)\n",
    "# Show data\n",
    "data.head()"
   ]
  },
  {
   "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>Clotbuster given</th>\n",
       "      <th>Hosp_1</th>\n",
       "      <th>Hosp_2</th>\n",
       "      <th>Hosp_3</th>\n",
       "      <th>Hosp_4</th>\n",
       "      <th>Hosp_5</th>\n",
       "      <th>Hosp_6</th>\n",
       "      <th>Hosp_7</th>\n",
       "      <th>Male</th>\n",
       "      <th>Age</th>\n",
       "      <th>...</th>\n",
       "      <th>S2NihssArrivalFacialPalsy</th>\n",
       "      <th>S2NihssArrivalMotorArmLeft</th>\n",
       "      <th>S2NihssArrivalMotorArmRight</th>\n",
       "      <th>S2NihssArrivalMotorLegLeft</th>\n",
       "      <th>S2NihssArrivalMotorLegRight</th>\n",
       "      <th>S2NihssArrivalLimbAtaxia</th>\n",
       "      <th>S2NihssArrivalSensory</th>\n",
       "      <th>S2NihssArrivalBestLanguage</th>\n",
       "      <th>S2NihssArrivalDysarthria</th>\n",
       "      <th>S2NihssArrivalExtinctionInattention</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "      <td>1862.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.403330</td>\n",
       "      <td>0.159506</td>\n",
       "      <td>0.142320</td>\n",
       "      <td>0.154672</td>\n",
       "      <td>0.165414</td>\n",
       "      <td>0.055854</td>\n",
       "      <td>0.113319</td>\n",
       "      <td>0.208915</td>\n",
       "      <td>0.515575</td>\n",
       "      <td>74.553706</td>\n",
       "      <td>...</td>\n",
       "      <td>1.114930</td>\n",
       "      <td>1.002148</td>\n",
       "      <td>0.963480</td>\n",
       "      <td>0.963480</td>\n",
       "      <td>0.910849</td>\n",
       "      <td>0.216971</td>\n",
       "      <td>0.610097</td>\n",
       "      <td>0.944146</td>\n",
       "      <td>0.739527</td>\n",
       "      <td>0.566595</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.490698</td>\n",
       "      <td>0.366246</td>\n",
       "      <td>0.349472</td>\n",
       "      <td>0.361689</td>\n",
       "      <td>0.371653</td>\n",
       "      <td>0.229701</td>\n",
       "      <td>0.317068</td>\n",
       "      <td>0.406643</td>\n",
       "      <td>0.499892</td>\n",
       "      <td>12.280576</td>\n",
       "      <td>...</td>\n",
       "      <td>0.930527</td>\n",
       "      <td>1.479211</td>\n",
       "      <td>1.441594</td>\n",
       "      <td>1.406501</td>\n",
       "      <td>1.380606</td>\n",
       "      <td>0.522643</td>\n",
       "      <td>0.771932</td>\n",
       "      <td>1.121379</td>\n",
       "      <td>0.731083</td>\n",
       "      <td>0.794000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>40.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>67.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>76.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>83.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 51 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Clotbuster given       Hosp_1       Hosp_2       Hosp_3       Hosp_4  \\\n",
       "count       1862.000000  1862.000000  1862.000000  1862.000000  1862.000000   \n",
       "mean           0.403330     0.159506     0.142320     0.154672     0.165414   \n",
       "std            0.490698     0.366246     0.349472     0.361689     0.371653   \n",
       "min            0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%            0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "50%            0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "75%            1.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "max            1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "            Hosp_5       Hosp_6       Hosp_7         Male          Age  ...  \\\n",
       "count  1862.000000  1862.000000  1862.000000  1862.000000  1862.000000  ...   \n",
       "mean      0.055854     0.113319     0.208915     0.515575    74.553706  ...   \n",
       "std       0.229701     0.317068     0.406643     0.499892    12.280576  ...   \n",
       "min       0.000000     0.000000     0.000000     0.000000    40.000000  ...   \n",
       "25%       0.000000     0.000000     0.000000     0.000000    67.000000  ...   \n",
       "50%       0.000000     0.000000     0.000000     1.000000    76.000000  ...   \n",
       "75%       0.000000     0.000000     0.000000     1.000000    83.000000  ...   \n",
       "max       1.000000     1.000000     1.000000     1.000000   100.000000  ...   \n",
       "\n",
       "       S2NihssArrivalFacialPalsy  S2NihssArrivalMotorArmLeft  \\\n",
       "count                1862.000000                 1862.000000   \n",
       "mean                    1.114930                    1.002148   \n",
       "std                     0.930527                    1.479211   \n",
       "min                     0.000000                    0.000000   \n",
       "25%                     0.000000                    0.000000   \n",
       "50%                     1.000000                    0.000000   \n",
       "75%                     2.000000                    2.000000   \n",
       "max                     3.000000                    4.000000   \n",
       "\n",
       "       S2NihssArrivalMotorArmRight  S2NihssArrivalMotorLegLeft  \\\n",
       "count                  1862.000000                 1862.000000   \n",
       "mean                      0.963480                    0.963480   \n",
       "std                       1.441594                    1.406501   \n",
       "min                       0.000000                    0.000000   \n",
       "25%                       0.000000                    0.000000   \n",
       "50%                       0.000000                    0.000000   \n",
       "75%                       2.000000                    2.000000   \n",
       "max                       4.000000                    4.000000   \n",
       "\n",
       "       S2NihssArrivalMotorLegRight  S2NihssArrivalLimbAtaxia  \\\n",
       "count                  1862.000000               1862.000000   \n",
       "mean                      0.910849                  0.216971   \n",
       "std                       1.380606                  0.522643   \n",
       "min                       0.000000                  0.000000   \n",
       "25%                       0.000000                  0.000000   \n",
       "50%                       0.000000                  0.000000   \n",
       "75%                       2.000000                  0.000000   \n",
       "max                       4.000000                  2.000000   \n",
       "\n",
       "       S2NihssArrivalSensory  S2NihssArrivalBestLanguage  \\\n",
       "count            1862.000000                 1862.000000   \n",
       "mean                0.610097                    0.944146   \n",
       "std                 0.771932                    1.121379   \n",
       "min                 0.000000                    0.000000   \n",
       "25%                 0.000000                    0.000000   \n",
       "50%                 0.000000                    0.000000   \n",
       "75%                 1.000000                    2.000000   \n",
       "max                 2.000000                    3.000000   \n",
       "\n",
       "       S2NihssArrivalDysarthria  S2NihssArrivalExtinctionInattention  \n",
       "count               1862.000000                          1862.000000  \n",
       "mean                   0.739527                             0.566595  \n",
       "std                    0.731083                             0.794000  \n",
       "min                    0.000000                             0.000000  \n",
       "25%                    0.000000                             0.000000  \n",
       "50%                    1.000000                             0.000000  \n",
       "75%                    1.000000                             1.000000  \n",
       "max                    2.000000                             2.000000  \n",
       "\n",
       "[8 rows x 51 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Look at overview of data\n",
    "data.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>given</th>\n",
       "      <th>not given</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Clotbuster given</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Hosp_1</th>\n",
       "      <td>0.203728</td>\n",
       "      <td>0.129613</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Hosp_2</th>\n",
       "      <td>0.122503</td>\n",
       "      <td>0.155716</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Hosp_3</th>\n",
       "      <td>0.182423</td>\n",
       "      <td>0.135914</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Hosp_4</th>\n",
       "      <td>0.137150</td>\n",
       "      <td>0.184518</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Hosp_5</th>\n",
       "      <td>0.067909</td>\n",
       "      <td>0.047705</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Hosp_6</th>\n",
       "      <td>0.123835</td>\n",
       "      <td>0.106211</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Hosp_7</th>\n",
       "      <td>0.162450</td>\n",
       "      <td>0.240324</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Male</th>\n",
       "      <td>0.515313</td>\n",
       "      <td>0.515752</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Age</th>\n",
       "      <td>73.303595</td>\n",
       "      <td>75.398740</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>80+</th>\n",
       "      <td>0.346205</td>\n",
       "      <td>0.393339</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Onset Time Known Type_BE</th>\n",
       "      <td>0.149134</td>\n",
       "      <td>0.352835</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Onset Time Known Type_NK</th>\n",
       "      <td>0.010652</td>\n",
       "      <td>0.015302</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Onset Time Known Type_P</th>\n",
       "      <td>0.840213</td>\n",
       "      <td>0.631863</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th># Comorbidities</th>\n",
       "      <td>1.053262</td>\n",
       "      <td>1.258326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2+ comorbidotes</th>\n",
       "      <td>0.298269</td>\n",
       "      <td>0.393339</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Congestive HF</th>\n",
       "      <td>0.041278</td>\n",
       "      <td>0.047705</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Hypertension</th>\n",
       "      <td>0.464714</td>\n",
       "      <td>0.470747</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Atrial Fib</th>\n",
       "      <td>0.186418</td>\n",
       "      <td>0.239424</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Diabetes</th>\n",
       "      <td>0.151798</td>\n",
       "      <td>0.172817</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>TIA</th>\n",
       "      <td>0.209055</td>\n",
       "      <td>0.327633</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Co-mordity</th>\n",
       "      <td>0.676431</td>\n",
       "      <td>0.732673</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Antiplatelet_0</th>\n",
       "      <td>0.097204</td>\n",
       "      <td>0.144014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Antiplatelet_1</th>\n",
       "      <td>0.079893</td>\n",
       "      <td>0.079208</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Antiplatelet_NK</th>\n",
       "      <td>0.822903</td>\n",
       "      <td>0.776778</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Anticoag before stroke_0</th>\n",
       "      <td>0.122503</td>\n",
       "      <td>0.083708</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Anticoag before stroke_1</th>\n",
       "      <td>0.046605</td>\n",
       "      <td>0.129613</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Anticoag before stroke_NK</th>\n",
       "      <td>0.830892</td>\n",
       "      <td>0.786679</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Stroke severity group_1. No stroke symtpoms</th>\n",
       "      <td>0.002663</td>\n",
       "      <td>0.041404</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Stroke severity group_2. Minor</th>\n",
       "      <td>0.061252</td>\n",
       "      <td>0.396040</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Stroke severity group_3. Moderate</th>\n",
       "      <td>0.619174</td>\n",
       "      <td>0.333033</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Stroke severity group_4. Moderate to severe</th>\n",
       "      <td>0.182423</td>\n",
       "      <td>0.105311</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Stroke severity group_5. Severe</th>\n",
       "      <td>0.134487</td>\n",
       "      <td>0.124212</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Stroke Type_I</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.803780</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Stroke Type_PIH</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.196220</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2RankinBeforeStroke</th>\n",
       "      <td>0.360852</td>\n",
       "      <td>0.791179</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrival</th>\n",
       "      <td>12.515313</td>\n",
       "      <td>9.032403</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrivalLocQuestions</th>\n",
       "      <td>0.850866</td>\n",
       "      <td>0.605761</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrivalLocCommands</th>\n",
       "      <td>0.394141</td>\n",
       "      <td>0.360936</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrivalBestGaze</th>\n",
       "      <td>0.521971</td>\n",
       "      <td>0.341134</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrivalVisual</th>\n",
       "      <td>0.809587</td>\n",
       "      <td>0.495050</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrivalFacialPalsy</th>\n",
       "      <td>1.407457</td>\n",
       "      <td>0.917192</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrivalMotorArmLeft</th>\n",
       "      <td>1.215712</td>\n",
       "      <td>0.857786</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrivalMotorArmRight</th>\n",
       "      <td>1.073236</td>\n",
       "      <td>0.889289</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrivalMotorLegLeft</th>\n",
       "      <td>1.165113</td>\n",
       "      <td>0.827183</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrivalMotorLegRight</th>\n",
       "      <td>0.977364</td>\n",
       "      <td>0.865887</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrivalLimbAtaxia</th>\n",
       "      <td>0.214381</td>\n",
       "      <td>0.218722</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrivalSensory</th>\n",
       "      <td>0.762983</td>\n",
       "      <td>0.506751</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrivalBestLanguage</th>\n",
       "      <td>1.181092</td>\n",
       "      <td>0.783978</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrivalDysarthria</th>\n",
       "      <td>0.902796</td>\n",
       "      <td>0.629163</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>S2NihssArrivalExtinctionInattention</th>\n",
       "      <td>0.762983</td>\n",
       "      <td>0.433843</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 given  not given\n",
       "Clotbuster given                              1.000000   0.000000\n",
       "Hosp_1                                        0.203728   0.129613\n",
       "Hosp_2                                        0.122503   0.155716\n",
       "Hosp_3                                        0.182423   0.135914\n",
       "Hosp_4                                        0.137150   0.184518\n",
       "Hosp_5                                        0.067909   0.047705\n",
       "Hosp_6                                        0.123835   0.106211\n",
       "Hosp_7                                        0.162450   0.240324\n",
       "Male                                          0.515313   0.515752\n",
       "Age                                          73.303595  75.398740\n",
       "80+                                           0.346205   0.393339\n",
       "Onset Time Known Type_BE                      0.149134   0.352835\n",
       "Onset Time Known Type_NK                      0.010652   0.015302\n",
       "Onset Time Known Type_P                       0.840213   0.631863\n",
       "# Comorbidities                               1.053262   1.258326\n",
       "2+ comorbidotes                               0.298269   0.393339\n",
       "Congestive HF                                 0.041278   0.047705\n",
       "Hypertension                                  0.464714   0.470747\n",
       "Atrial Fib                                    0.186418   0.239424\n",
       "Diabetes                                      0.151798   0.172817\n",
       "TIA                                           0.209055   0.327633\n",
       "Co-mordity                                    0.676431   0.732673\n",
       "Antiplatelet_0                                0.097204   0.144014\n",
       "Antiplatelet_1                                0.079893   0.079208\n",
       "Antiplatelet_NK                               0.822903   0.776778\n",
       "Anticoag before stroke_0                      0.122503   0.083708\n",
       "Anticoag before stroke_1                      0.046605   0.129613\n",
       "Anticoag before stroke_NK                     0.830892   0.786679\n",
       "Stroke severity group_1. No stroke symtpoms   0.002663   0.041404\n",
       "Stroke severity group_2. Minor                0.061252   0.396040\n",
       "Stroke severity group_3. Moderate             0.619174   0.333033\n",
       "Stroke severity group_4. Moderate to severe   0.182423   0.105311\n",
       "Stroke severity group_5. Severe               0.134487   0.124212\n",
       "Stroke Type_I                                 1.000000   0.803780\n",
       "Stroke Type_PIH                               0.000000   0.196220\n",
       "S2RankinBeforeStroke                          0.360852   0.791179\n",
       "S2NihssArrival                               12.515313   9.032403\n",
       "S2NihssArrivalLocQuestions                    0.850866   0.605761\n",
       "S2NihssArrivalLocCommands                     0.394141   0.360936\n",
       "S2NihssArrivalBestGaze                        0.521971   0.341134\n",
       "S2NihssArrivalVisual                          0.809587   0.495050\n",
       "S2NihssArrivalFacialPalsy                     1.407457   0.917192\n",
       "S2NihssArrivalMotorArmLeft                    1.215712   0.857786\n",
       "S2NihssArrivalMotorArmRight                   1.073236   0.889289\n",
       "S2NihssArrivalMotorLegLeft                    1.165113   0.827183\n",
       "S2NihssArrivalMotorLegRight                   0.977364   0.865887\n",
       "S2NihssArrivalLimbAtaxia                      0.214381   0.218722\n",
       "S2NihssArrivalSensory                         0.762983   0.506751\n",
       "S2NihssArrivalBestLanguage                    1.181092   0.783978\n",
       "S2NihssArrivalDysarthria                      0.902796   0.629163\n",
       "S2NihssArrivalExtinctionInattention           0.762983   0.433843"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Look at mean feature values for those who were given a clotbuster vs those\n",
    "# that weren't\n",
    "mask = data['Clotbuster given'] == 1\n",
    "given = data[mask]\n",
    "\n",
    "mask = data['Clotbuster given'] == 0\n",
    "not_given = data[mask]\n",
    "\n",
    "summary = pd.DataFrame()\n",
    "summary['given'] = given.mean()\n",
    "summary['not given'] = not_given.mean()\n",
    "\n",
    "summary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Divide into features and labels\n",
    "X = data.drop('Clotbuster given', axis=1)\n",
    "y = data['Clotbuster given']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Divide into training and test sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Standardise data\n",
    "def standardise_data(X_train, X_test):\n",
    "\n",
    "    # Initialise a new scaling object for normalising input data\n",
    "    sc = StandardScaler()\n",
    "\n",
    "    # Apply the scaler to the training and test sets\n",
    "    train_std=sc.fit_transform(X_train)\n",
    "    test_std=sc.fit_transform(X_test)\n",
    "\n",
    "    return train_std, test_std\n",
    "\n",
    "X_train_std, X_test_std = standardise_data(X_train, X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: black;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-1 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-1 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-1 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-1 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 1ex;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;LogisticRegression<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>LogisticRegression()</pre></div> </div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Fit (train) Logistic Regression model\n",
    "model = LogisticRegression()\n",
    "model.fit(X_train_std, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of predicting training data = 0.8202005730659025\n",
      "Accuracy of predicting test data = 0.7939914163090128\n"
     ]
    }
   ],
   "source": [
    "# Predict training and test labels, and calculate accuracy\n",
    "y_pred_train = model.predict(X_train_std)\n",
    "y_pred_test = model.predict(X_test_std)\n",
    "\n",
    "accuracy_train = np.mean(y_pred_train == y_train)\n",
    "accuracy_test = np.mean(y_pred_test == y_test)\n",
    "\n",
    "print (f'Accuracy of predicting training data = {accuracy_train}')\n",
    "print (f'Accuracy of predicting test data = {accuracy_test}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>feature</th>\n",
       "      <th>co_eff</th>\n",
       "      <th>abs_co_eff</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>Stroke Type_I</td>\n",
       "      <td>1.121156</td>\n",
       "      <td>1.121156</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>Stroke Type_PIH</td>\n",
       "      <td>-1.121156</td>\n",
       "      <td>1.121156</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>Stroke severity group_2. Minor</td>\n",
       "      <td>-0.709358</td>\n",
       "      <td>0.709358</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>Stroke severity group_3. Moderate</td>\n",
       "      <td>0.594452</td>\n",
       "      <td>0.594452</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>S2NihssArrival</td>\n",
       "      <td>-0.468261</td>\n",
       "      <td>0.468261</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>S2RankinBeforeStroke</td>\n",
       "      <td>-0.458139</td>\n",
       "      <td>0.458139</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47</th>\n",
       "      <td>S2NihssArrivalBestLanguage</td>\n",
       "      <td>0.407136</td>\n",
       "      <td>0.407136</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Age</td>\n",
       "      <td>-0.351431</td>\n",
       "      <td>0.351431</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Onset Time Known Type_BE</td>\n",
       "      <td>-0.311359</td>\n",
       "      <td>0.311359</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>Atrial Fib</td>\n",
       "      <td>-0.304925</td>\n",
       "      <td>0.304925</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Onset Time Known Type_P</td>\n",
       "      <td>0.296688</td>\n",
       "      <td>0.296688</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Hypertension</td>\n",
       "      <td>0.284943</td>\n",
       "      <td>0.284943</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41</th>\n",
       "      <td>S2NihssArrivalMotorArmLeft</td>\n",
       "      <td>0.270736</td>\n",
       "      <td>0.270736</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>Stroke severity group_1. No stroke symtpoms</td>\n",
       "      <td>-0.269664</td>\n",
       "      <td>0.269664</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>Anticoag before stroke_0</td>\n",
       "      <td>0.268555</td>\n",
       "      <td>0.268555</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>Anticoag before stroke_1</td>\n",
       "      <td>-0.265632</td>\n",
       "      <td>0.265632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>S2NihssArrivalLocQuestions</td>\n",
       "      <td>0.259637</td>\n",
       "      <td>0.259637</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40</th>\n",
       "      <td>S2NihssArrivalFacialPalsy</td>\n",
       "      <td>0.249051</td>\n",
       "      <td>0.249051</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49</th>\n",
       "      <td>S2NihssArrivalExtinctionInattention</td>\n",
       "      <td>0.216644</td>\n",
       "      <td>0.216644</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>Stroke severity group_4. Moderate to severe</td>\n",
       "      <td>0.194853</td>\n",
       "      <td>0.194853</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>TIA</td>\n",
       "      <td>-0.193125</td>\n",
       "      <td>0.193125</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42</th>\n",
       "      <td>S2NihssArrivalMotorArmRight</td>\n",
       "      <td>0.186265</td>\n",
       "      <td>0.186265</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38</th>\n",
       "      <td>S2NihssArrivalBestGaze</td>\n",
       "      <td>0.180682</td>\n",
       "      <td>0.180682</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>S2NihssArrivalLocCommands</td>\n",
       "      <td>-0.175957</td>\n",
       "      <td>0.175957</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Hosp_4</td>\n",
       "      <td>-0.171598</td>\n",
       "      <td>0.171598</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>Antiplatelet_0</td>\n",
       "      <td>0.155566</td>\n",
       "      <td>0.155566</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>2+ comorbidotes</td>\n",
       "      <td>-0.145232</td>\n",
       "      <td>0.145232</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Hosp_1</td>\n",
       "      <td>0.122579</td>\n",
       "      <td>0.122579</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Hosp_6</td>\n",
       "      <td>0.116022</td>\n",
       "      <td>0.116022</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>Antiplatelet_NK</td>\n",
       "      <td>-0.110145</td>\n",
       "      <td>0.110145</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>S2NihssArrivalVisual</td>\n",
       "      <td>0.093206</td>\n",
       "      <td>0.093206</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Hosp_2</td>\n",
       "      <td>0.071554</td>\n",
       "      <td>0.071554</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45</th>\n",
       "      <td>S2NihssArrivalLimbAtaxia</td>\n",
       "      <td>0.067437</td>\n",
       "      <td>0.067437</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>S2NihssArrivalMotorLegLeft</td>\n",
       "      <td>0.065901</td>\n",
       "      <td>0.065901</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>80+</td>\n",
       "      <td>0.064134</td>\n",
       "      <td>0.064134</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td># Comorbidities</td>\n",
       "      <td>-0.062878</td>\n",
       "      <td>0.062878</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Hosp_5</td>\n",
       "      <td>-0.047460</td>\n",
       "      <td>0.047460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Hosp_7</td>\n",
       "      <td>-0.046642</td>\n",
       "      <td>0.046642</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46</th>\n",
       "      <td>S2NihssArrivalSensory</td>\n",
       "      <td>0.044662</td>\n",
       "      <td>0.044662</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Onset Time Known Type_NK</td>\n",
       "      <td>0.042662</td>\n",
       "      <td>0.042662</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Hosp_3</td>\n",
       "      <td>-0.034359</td>\n",
       "      <td>0.034359</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Male</td>\n",
       "      <td>0.032534</td>\n",
       "      <td>0.032534</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48</th>\n",
       "      <td>S2NihssArrivalDysarthria</td>\n",
       "      <td>0.031809</td>\n",
       "      <td>0.031809</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>Co-mordity</td>\n",
       "      <td>-0.029874</td>\n",
       "      <td>0.029874</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>Antiplatelet_1</td>\n",
       "      <td>-0.026909</td>\n",
       "      <td>0.026909</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>Stroke severity group_5. Severe</td>\n",
       "      <td>-0.019006</td>\n",
       "      <td>0.019006</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Congestive HF</td>\n",
       "      <td>0.016522</td>\n",
       "      <td>0.016522</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Diabetes</td>\n",
       "      <td>0.013792</td>\n",
       "      <td>0.013792</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>S2NihssArrivalMotorLegRight</td>\n",
       "      <td>-0.009994</td>\n",
       "      <td>0.009994</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>Anticoag before stroke_NK</td>\n",
       "      <td>-0.006123</td>\n",
       "      <td>0.006123</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                        feature    co_eff  abs_co_eff\n",
       "32                                Stroke Type_I  1.121156    1.121156\n",
       "33                              Stroke Type_PIH -1.121156    1.121156\n",
       "28               Stroke severity group_2. Minor -0.709358    0.709358\n",
       "29            Stroke severity group_3. Moderate  0.594452    0.594452\n",
       "35                               S2NihssArrival -0.468261    0.468261\n",
       "34                         S2RankinBeforeStroke -0.458139    0.458139\n",
       "47                   S2NihssArrivalBestLanguage  0.407136    0.407136\n",
       "8                                           Age -0.351431    0.351431\n",
       "10                     Onset Time Known Type_BE -0.311359    0.311359\n",
       "17                                   Atrial Fib -0.304925    0.304925\n",
       "12                      Onset Time Known Type_P  0.296688    0.296688\n",
       "16                                 Hypertension  0.284943    0.284943\n",
       "41                   S2NihssArrivalMotorArmLeft  0.270736    0.270736\n",
       "27  Stroke severity group_1. No stroke symtpoms -0.269664    0.269664\n",
       "24                     Anticoag before stroke_0  0.268555    0.268555\n",
       "25                     Anticoag before stroke_1 -0.265632    0.265632\n",
       "36                   S2NihssArrivalLocQuestions  0.259637    0.259637\n",
       "40                    S2NihssArrivalFacialPalsy  0.249051    0.249051\n",
       "49          S2NihssArrivalExtinctionInattention  0.216644    0.216644\n",
       "30  Stroke severity group_4. Moderate to severe  0.194853    0.194853\n",
       "19                                          TIA -0.193125    0.193125\n",
       "42                  S2NihssArrivalMotorArmRight  0.186265    0.186265\n",
       "38                       S2NihssArrivalBestGaze  0.180682    0.180682\n",
       "37                    S2NihssArrivalLocCommands -0.175957    0.175957\n",
       "3                                        Hosp_4 -0.171598    0.171598\n",
       "21                               Antiplatelet_0  0.155566    0.155566\n",
       "14                              2+ comorbidotes -0.145232    0.145232\n",
       "0                                        Hosp_1  0.122579    0.122579\n",
       "5                                        Hosp_6  0.116022    0.116022\n",
       "23                              Antiplatelet_NK -0.110145    0.110145\n",
       "39                         S2NihssArrivalVisual  0.093206    0.093206\n",
       "1                                        Hosp_2  0.071554    0.071554\n",
       "45                     S2NihssArrivalLimbAtaxia  0.067437    0.067437\n",
       "43                   S2NihssArrivalMotorLegLeft  0.065901    0.065901\n",
       "9                                           80+  0.064134    0.064134\n",
       "13                              # Comorbidities -0.062878    0.062878\n",
       "4                                        Hosp_5 -0.047460    0.047460\n",
       "6                                        Hosp_7 -0.046642    0.046642\n",
       "46                        S2NihssArrivalSensory  0.044662    0.044662\n",
       "11                     Onset Time Known Type_NK  0.042662    0.042662\n",
       "2                                        Hosp_3 -0.034359    0.034359\n",
       "7                                          Male  0.032534    0.032534\n",
       "48                     S2NihssArrivalDysarthria  0.031809    0.031809\n",
       "20                                   Co-mordity -0.029874    0.029874\n",
       "22                               Antiplatelet_1 -0.026909    0.026909\n",
       "31              Stroke severity group_5. Severe -0.019006    0.019006\n",
       "15                                Congestive HF  0.016522    0.016522\n",
       "18                                     Diabetes  0.013792    0.013792\n",
       "44                  S2NihssArrivalMotorLegRight -0.009994    0.009994\n",
       "26                    Anticoag before stroke_NK -0.006123    0.006123"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Examine feature weights and sort by most influential\n",
    "co_eff = model.coef_[0]\n",
    "\n",
    "co_eff_df = pd.DataFrame()\n",
    "co_eff_df['feature'] = list(X)\n",
    "co_eff_df['co_eff'] = co_eff\n",
    "co_eff_df['abs_co_eff'] = np.abs(co_eff)\n",
    "co_eff_df.sort_values(by='abs_co_eff', ascending=False, inplace=True)\n",
    "\n",
    "co_eff_df"
   ]
  }
 ],
 "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}