import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
dataset = pd.read_csv('Av cost prediction.csv')
X = dataset.iloc[:,:-1].values
Y = dataset.iloc[:,1].values
from sklearn.cross_validation 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)            # fitted and trained the regressor object on the training set of X and Y.Created a unique linear regression equation for entire dataset
y_pred = regressor.predict(X_test)
plt.scatter(X_train,Y_train,color = 'green')
plt.plot(X_train,regressor.predict(X_train),color = 'red')
plt.title('Month Vs Cost(Training data)')
plt.xlabel('Month')
plt.ylabel('Cost')
plt.show()
plt.scatter(X_test,Y_test,color = 'green')
plt.plot(X_train,regressor.predict(X_train),color = 'red')
plt.title('Month Vs cost(Test data)')
plt.xlabel('Month')
plt.ylabel('Cost')
plt.show()