50startups.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

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

#handling categorical data
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()

#handling dummy variables
x=x[:,1:]

#splitting the dataset
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)

#fitting training set to mlr
from sklearn.linear_model import LinearRegression
regressor=LinearRegression()
regressor.fit(x_train,y_train)

#predicting the regression results
y_pred=regressor.predict(x_test)

import statsmodels.api as sm
x=np.append(np.ones((50,1)).astype(int),values=x,axis=1)
x_opt=x[:,[0,1,2,3,4,5]]
regressor_ols=sm.OLS(endog=y,exog=x_opt).fit()
regressor_ols.summary()

x_opt=x[:,[0,1,3,4,5]]
regressor_ols=sm.OLS(endog=y,exog=x_opt).fit()
regressor_ols.summary()

x_opt=x[:,[0,3,4,5]]
regressor_ols=sm.OLS(endog=y,exog=x_opt).fit()
regressor_ols.summary()

x_opt=x[:,[0,3,5]]
regressor_ols=sm.OLS(endog=y,exog=x_opt).fit()
regressor_ols.summary()

x_opt=x[:,[0,3]]
regressor_ols=sm.OLS(endog=y,exog=x_opt).fit()
regressor_ols.summary()