# https://medium.com/machine-learning-with-python/multiple-linear-regression-implementation-in-python-2de9b303fc0c
import pandas as pd
import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn import metrics
from sklearn.model_selection import train_test_split

#Reading the dataset
dataset = pd.read_csv("advertising.csv")

dataset.head()

#Setting the value for X and Y
x = dataset[['TV', 'Radio', 'Newspaper']]
y = dataset['Sales']

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3, random_state = 100)

#Fitting the Multiple Linear Regression model
mlr = LinearRegression()  
mlr.fit(x_train, y_train)

#Intercept and Coefficient
print("Intercept: ", mlr.intercept_)
print("Coefficients:",list(zip(x, mlr.coef_)))

#Prediction of test set
y_pred_mlr= mlr.predict(x_test)
#Predicted values
print("Prediction for test set: {}".format(y_pred_mlr))

#Actual value and the predicted value
slr_diff = pd.DataFrame({'Actual value': y_test, 'Predicted value': y_pred_mlr})

#Model Evaluation

meanAbErr = metrics.mean_absolute_error(y_test, y_pred_mlr)
meanSqErr = metrics.mean_squared_error(y_test, y_pred_mlr)
rootMeanSqErr = np.sqrt(metrics.mean_squared_error(y_test, y_pred_mlr))
print('R squared: {:.2f}'.format(mlr.score(x,y)*100))
print('Mean Absolute Error:', meanAbErr)
print('Mean Square Error:', meanSqErr)
print('Root Mean Square Error:', rootMeanSqErr)