multiple_linear_regression_compulsory_task_1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 518,
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports relevant modules/packages\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Read diabetes.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 519,
   "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>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
       "0            6      148             72             35        0  33.6   \n",
       "1            1       85             66             29        0  26.6   \n",
       "2            8      183             64              0        0  23.3   \n",
       "3            1       89             66             23       94  28.1   \n",
       "4            0      137             40             35      168  43.1   \n",
       "\n",
       "   DiabetesPedigreeFunction  Age  Outcome  \n",
       "0                     0.627   50        1  \n",
       "1                     0.351   31        0  \n",
       "2                     0.672   32        1  \n",
       "3                     0.167   21        0  \n",
       "4                     2.288   33        1  "
      ]
     },
     "execution_count": 519,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "diabetes_df = pd.read_csv('diabetes.csv') # Loads the dataset\n",
    "diabetes_df.head()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Differentiate between the independent variables and the dependent variable and assign them to variables x and y."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 520,
   "metadata": {},
   "outputs": [],
   "source": [
    "# independent\n",
    "x = diabetes_df.drop(['Outcome'], axis=1)\n",
    "# dependent\n",
    "y = diabetes_df.Outcome"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Generate training and test sets comprising 80% and 20% of the data respectively."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 521,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training data: (614, 8) (614,)\n",
      "Test data: (154, 8) (154,)\n"
     ]
    }
   ],
   "source": [
    "x_train,x_test,y_train,y_test = train_test_split(x,y,test_size = 0.20, shuffle=True, stratify=y)\n",
    "\n",
    "print (\"Training data:\",x_train.shape, y_train.shape)\n",
    "print (\"Test data:\",x_test.shape, y_test.shape)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "768 data points split into an 80:20 ratio of 614 training observations with 8 columns and 154 test observations."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Use a MinMaxScaler and StandardScaler from sklearn.preprocessing. Fit these scalers on the train set and use these fit scalers to transform the train and test sets."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 522,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-0.85099486, -1.23895238, -0.24276622, ..., -1.33611247,\n",
       "        -0.16787455, -0.88331384],\n",
       "       [ 0.33182539, -0.51646464,  0.16715736, ...,  0.64299861,\n",
       "        -0.95541092, -0.45680024],\n",
       "       [ 0.92323551,  1.17981091, -0.24276622, ..., -0.55455268,\n",
       "        -0.54010854,  0.56683241],\n",
       "       ...,\n",
       "       [ 0.33182539, -0.3908146 ,  0.3208787 , ...,  0.52954638,\n",
       "         0.23512257,  2.27288682],\n",
       "       [-0.5552898 , -0.29657707,  0.47460004, ...,  0.95814369,\n",
       "        -0.90618989, -0.79801112],\n",
       "       [-0.25958474, -1.17612736, -0.03780443, ...,  0.01270846,\n",
       "         0.3735567 , -0.7127084 ]])"
      ]
     },
     "execution_count": 522,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# define scaler\n",
    "scaler_minmax = MinMaxScaler()\n",
    "# fit minmaxscaler on train sets\n",
    "min_max = scaler_minmax.fit(x_train)\n",
    "# use fit scaler to transform both sets\n",
    "min_max.transform(x_train)\n",
    "min_max.transform(x_test)\n",
    "\n",
    "# define scaler\n",
    "scaler_std = StandardScaler()\n",
    "# fit stdscaler on train sets\n",
    "std = scaler_std.fit(x_train)\n",
    "# use fit scaler to transform both sets\n",
    "std.transform(x_train)\n",
    "std.transform(x_test)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Generate a multiple linear regression model using the training set. Use all of the independent variables."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 523,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-44 {color: black;background-color: white;}#sk-container-id-44 pre{padding: 0;}#sk-container-id-44 div.sk-toggleable {background-color: white;}#sk-container-id-44 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-44 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-44 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-44 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-44 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-44 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-44 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-44 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-44 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-44 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-44 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-44 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-44 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-44 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-44 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-44 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-44 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-44 div.sk-item {position: relative;z-index: 1;}#sk-container-id-44 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-44 div.sk-item::before, #sk-container-id-44 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-44 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-44 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-44 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-44 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-44 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-44 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-44 div.sk-label-container {text-align: center;}#sk-container-id-44 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-44 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-44\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LinearRegression()</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 sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-44\" type=\"checkbox\" checked><label for=\"sk-estimator-id-44\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LinearRegression</label><div class=\"sk-toggleable__content\"><pre>LinearRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LinearRegression()"
      ]
     },
     "execution_count": 523,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# create an empty linear regression model\n",
    "model_train = LinearRegression()\n",
    "\n",
    "# to create and fit model to training sets\n",
    "model_train.fit(x_train,y_train)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Print out the intercept and coefficients of the trained model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 524,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Intercept: \n",
      " -0.8902748243243805\n",
      "Coefficients: \n",
      " [ 0.01973273  0.00592094 -0.00225274  0.00020191 -0.00030388  0.01403553\n",
      "  0.1241328   0.00339786]\n"
     ]
    }
   ],
   "source": [
    "# prints wanted info\n",
    "print('Intercept: \\n', model_train.intercept_)\n",
    "print('Coefficients: \\n', model_train.coef_)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Generate predictions for the test set."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 525,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([-0.1282261 ,  0.20777078,  0.60209019,  0.5842146 ,  0.12543957,\n",
       "        0.629783  ,  0.32219647,  0.13024789,  0.5739677 ,  0.35595877])"
      ]
     },
     "execution_count": 525,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# make predictions\n",
    "predictions = model_train.predict(x_test)\n",
    "predicted_values = predictions[0:10]\n",
    "predicted_values"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For these predictions, set all predicted values below 0.5 to 0 and all predicted values of 0.5 or above to 1."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 526,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 0, 1, 1, 0, 1, 0, 0, 1, 0]"
      ]
     },
     "execution_count": 526,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# creates an empty list for the adjusted predictions set to 0 and 1\n",
    "adj_predictions = []\n",
    "# iterates through all predictions\n",
    "for i in range(len(predicted_values)):\n",
    "    # set predictions below 0.5 to 0\n",
    "    if predicted_values[i] < 0.5:\n",
    "        adj_predictions.append(0)\n",
    "    # set all predictions of 0.5 and above to 1\n",
    "    else:\n",
    "        adj_predictions.append(1)\n",
    "adj_predictions # new predicted values"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Compute the accuracy_score of your model on the test set. You can get the accuracy_score from sklearn.metrics."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 527,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8"
      ]
     },
     "execution_count": 527,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# computes accuracy score on test set\n",
    "y_true = y_test.iloc[0:10] # defines y_true as values from test set\n",
    "accuracy_score(y_true, adj_predictions)"
   ]
  }
 ],
 "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": "3.11.0"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "fd9e38af040559ad764514e0db59d6a267742561531a8adad5281cf94d911280"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}