Polynomial Regression Model.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Importing the libraries "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np \n",
    "import matplotlib.pyplot as plt \n",
    "import pandas as pd \n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Load Data"
   ]
  },
  {
   "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>Position</th>\n",
       "      <th>Level</th>\n",
       "      <th>Salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Business Analyst</td>\n",
       "      <td>1</td>\n",
       "      <td>45000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Junior Consultant</td>\n",
       "      <td>2</td>\n",
       "      <td>50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Senior Consultant</td>\n",
       "      <td>3</td>\n",
       "      <td>60000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Manager</td>\n",
       "      <td>4</td>\n",
       "      <td>80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Country Manager</td>\n",
       "      <td>5</td>\n",
       "      <td>110000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Position  Level  Salary\n",
       "0   Business Analyst      1   45000\n",
       "1  Junior Consultant      2   50000\n",
       "2  Senior Consultant      3   60000\n",
       "3            Manager      4   80000\n",
       "4    Country Manager      5  110000"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset=pd.read_csv('Position_Salaries.csv') \n",
    "dataset.head()"
   ]
  },
  {
   "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>Level</th>\n",
       "      <th>Salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>10.00000</td>\n",
       "      <td>10.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>5.50000</td>\n",
       "      <td>249500.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.02765</td>\n",
       "      <td>299373.883668</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.00000</td>\n",
       "      <td>45000.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>3.25000</td>\n",
       "      <td>65000.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>5.50000</td>\n",
       "      <td>130000.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>7.75000</td>\n",
       "      <td>275000.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>10.00000</td>\n",
       "      <td>1000000.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Level          Salary\n",
       "count  10.00000       10.000000\n",
       "mean    5.50000   249500.000000\n",
       "std     3.02765   299373.883668\n",
       "min     1.00000    45000.000000\n",
       "25%     3.25000    65000.000000\n",
       "50%     5.50000   130000.000000\n",
       "75%     7.75000   275000.000000\n",
       "max    10.00000  1000000.000000"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.scatterplot(x='Level', y='Salary',data = dataset);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "x = dataset.iloc[:, 1:-1].values  \n",
    "y = dataset.iloc[:, -1].values  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 1]\n",
      " [ 2]\n",
      " [ 3]\n",
      " [ 4]\n",
      " [ 5]\n",
      " [ 6]\n",
      " [ 7]\n",
      " [ 8]\n",
      " [ 9]\n",
      " [10]]\n"
     ]
    }
   ],
   "source": [
    "print(x[:10,:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[  45000   50000   60000   80000  110000  150000  200000  300000  500000\n",
      " 1000000]\n"
     ]
    }
   ],
   "source": [
    "print(y[:10])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Splitting the dataset into training and test set  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.3,random_state = 0) # func returns train and test data. It takes dataset and then split size test_size =0.3 means 30% data is for test and rest for training and random_state \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[10]\n",
      " [ 2]\n",
      " [ 7]\n",
      " [ 8]\n",
      " [ 4]\n",
      " [ 1]\n",
      " [ 6]]\n"
     ]
    }
   ],
   "source": [
    "print(x_train[:10,:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[3]\n",
      " [9]\n",
      " [5]]\n"
     ]
    }
   ],
   "source": [
    "print(x_test[:10,:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[1000000   50000  200000  300000   80000   45000  150000]\n"
     ]
    }
   ],
   "source": [
    "print(y_train[:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[ 60000 500000 110000]\n"
     ]
    }
   ],
   "source": [
    "print(y_test[:10])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Build Model "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import PolynomialFeatures\n",
    "polyMatrix = PolynomialFeatures(degree=4) \n",
    "x_poly = polyMatrix.fit_transform(x_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LinearRegression()"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.linear_model import LinearRegression\n",
    "regressor = LinearRegression()\n",
    "regressor.fit(x_poly,y_train) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "#predicting the test set results\n",
    "y_pred = regressor.predict(polyMatrix.transform(x_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Evaluate Model "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.975539287714958"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import r2_score, mean_absolute_error, mean_squared_error, confusion_matrix, classification_report\n",
    "r2_score(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "21152.351831099426"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean_absolute_error(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "946357779.7390695"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean_squared_error(y_test,y_pred)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}