Write a python program to implement multiple linear regression for given dataset

import pandas as pd

from sklearn import linear_model

import matplotlib.pyplot as plt

import statsmodels.api as sm

Stock_Market = {'Year': [2017,2017,2017,2017,2017,2017,2017,2017,2017,2017,2017,2017,2016,2016,2016,2016,2016,2016,2016,2016,2016,2016,2016,2016],

                'Month': [12, 11,10,9,8,7,6,5,4,3,2,1,12,11,10,9,8,7,6,5,4,3,2,1],

                'Interest_Rate': [2.75,2.5,2.5,2.5,2.5,2.5,2.5,2.25,2.25,2.25,2,2,2,1.75,1.75,1.75,1.75,1.75,1.75,1.75,1.75,1.75,1.75,1.75],

                'Unemployment_Rate': [5.3,5.3,5.3,5.3,5.4,5.6,5.5,5.5,5.5,5.6,5.7,5.9,6,5.9,5.8,6.1,6.2,6.1,6.1,6.1,5.9,6.2,6.2,6.1],

                'Stock_Index_Price': [1464,1394,1357,1293,1256,1254,1234,1195,1159,1167,1130,1075,1047,965,943,958,971,949,884,866,876,822,704,719]        

                }

df = pd.DataFrame(Stock_Market,columns=['Year','Month','Interest_Rate','Unemployment_Rate','Stock_Index_Price'])

X = df[['Interest_Rate','Unemployment_Rate']]

# here we have 2 variables for multiple regression. If you just want to use one variable for simple linear regression, then use X = df['Interest_Rate'] for example.Alternatively, you may add additional variables within the brackets

Y = df['Stock_Index_Price']

 

# with sklearn

regr = linear_model.LinearRegression()

regr.fit(X, Y)

print('Intercept: \n', regr.intercept_)

print('Coefficients: \n', regr.coef_)

# prediction with sklearn

New_Interest_Rate = 2.75

New_Unemployment_Rate = 5.3

print ('Predicted Stock Index Price: \n', regr.predict([[New_Interest_Rate ,New_Unemployment_Rate]]))

# with statsmodels

X = sm.add_constant(X) # adding a constant

 

model = sm.OLS(Y, X).fit()

predictions = model.predict(X)

 

print_model = model.summary()

print(print_model)