Linear Regressor Technique

 # -*- coding: utf-8 -*-

"""

Created on Mon Oct 16 13:25:06 2023

@author: Syed Kamran Bukhari

"""

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

#Load CSV file

dataset = pd.read_csv('50_Startups.csv')

X= dataset.iloc[:,:-1].values

Y= dataset.iloc[:,-1].values

#One Hot encoding

from sklearn.compose import ColumnTransformer

from sklearn.preprocessing import OneHotEncoder

ct=ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [3])], remainder ='passthrough')

X= np.array(ct.fit_transform(X))

#dividing the dataset to training and Test

from sklearn.model_selection import train_test_split

X_train,X_test,Y_train,Y_test = train_test_split(X,Y, test_size=0.2, random_state=1)

#import Regressor

from sklearn.linear_model import LinearRegression

regressor=LinearRegression()

regressor.fit(X_train, Y_train)

#prediction values

Y_pred=regressor.predict(X_test)

#RMSE score

residual = abs(Y_test-Y_pred)

ss= residual**2

ss=ss.sum()/len(Y_test)

print('The RMSE score is =', ss)

#R2 score

from sklearn.metrics import r2_score

R2= r2_score(Y_test, Y_pred)

print('The R2 score is =',R2)

#Durbin Watson Statistics

from statsmodels.stats.stattools import durbin_watson

DW = durbin_watson(residual)

print('Durbin Watson Statistics =',DW)

#scatter plot for Training test

plt.scatter(Y_train, regressor.predict(X_train),color = 'red')

#plt.plot(X_train, regressor.predict(X_train), color='Blue')

plt.title('Original vs Predicted Values (training Set')

plt.xlabel('Original Values')

plt.ylabel('Predicted Values')

plt.show()