Multiple Linear Regression

	Creating a Multiple linear regression model for estimating CO2 emission from a car model using independent variables like Engine size, cylinder, fuel consumption of a car.
	import matplotlib.pyplot as plt
	import pandas as pd
	import pylab as pl
	import numpy as np
	%matplotlib inline
	df = pd.read_csv("FuelConsumptionCo2.csv")
	#df.head()
	cdf = df[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB','CO2EMISSIONS']]
	#cdf.head(9)
	# Plotting
	plt.scatter(cdf.ENGINESIZE, cdf.CO2EMISSIONS, color = 'blue')
	plt.xlabel('Engine Size')
	plt.ylabel('Emissions')
	#plt.show()
	# Creating train and test dataset
	msk = np.random.rand(len(df)) < 0.8
	train = cdf[msk]
	test = cdf[~msk]
	# train data distribution
	plt.scatter(train.ENGINESIZE, train.CO2EMISSIONS, color='blue')
	plt.xlabel("Engine size")
	plt.ylabel("Emission")
	#plt.show()
	#### MULTIPLE REGRESSION MODEL ####
	from sklearn import linear_model
	regr = linear_model.LinearRegression()
	x = np.asanyarray(train[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB']])
	y = np.asanyarray(train[['CO2EMISSIONS']])
	regr.fit (x, y)
	# The coefficients
	#print ('Coefficients: ', regr.coef_)
	# Prediction
	y_hat= regr.predict(test[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB']])
	x = np.asanyarray(test[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB']])
	y = np.asanyarray(test[['CO2EMISSIONS']])
	#print("Residual sum of squares: %.2f" % np.mean((y_hat - y) ** 2))
	# Explained variance score: 1 is perfect prediction
	print('Variance score: %.2f' % regr.score(x, y))