multiple linear regression.py

# Data Preprocessing Template

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('50_Startups.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 4].values

from sklearn.preprocessing import LabelEncoder,OneHotEncoder
labelencoder=LabelEncoder()
X[:,3]=labelencoder.fit_transform(X[:,3])
onehotencoder=OneHotEncoder(categorical_features=[3])
X=onehotencoder.fit_transform(X).toarray()

X=X[:,1:]

# Splitting the dataset into the Training set and Test set
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 = 0)



from sklearn.linear_model import LinearRegression
regressor=LinearRegression()
regressor.fit(X_train,y_train)

y_pred=regressor.predict(X_test)

import statsmodels.api as sm
X=np.append(arr=np.ones((50,1)).astype(int),values=X,axis=1)
X_opt=X[:,[ 0,3]]
regressor_ols=sm.OLS(endog=y,exog=X_opt).fit()
regressor_ols.summary()

X_train_opt, X_test_opt, y_train, y_test = train_test_split(X_opt, y, test_size = 0.2, random_state = 0)
regressor1=LinearRegression()
regressor1.fit(X_train_opt,y_train)
y_pred_opt=regressor1.predict(X_test_opt)