simple linear regression

# importing dataset
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

dataset=pd.read_csv('Salary_Data.csv')
X=dataset.iloc[:,:-1].values
Y=dataset.iloc[:,1].values

#training and testing test splitting
from sklearn.cross_validation import train_test_split
X_train,X_test,Y_train,Y_test=train_test_split(X,Y,test_size=1/3,random_state=0)

#fitting simple linear regression to training set

from sklearn.linear_model import LinearRegression
regressor=LinearRegression()
regressor.fit(X_train,Y_train)

#predict the testing set
Y_pred=regressor.predict(X_test)

#plotting training test
plt.scatter(X_train,Y_train,color='red')
plt.plot(X_train,regressor.predict(X_train),color='blue')
plt.title('Salary vs Year of Experience(training set)')
plt.xlabel('year of experience')
plt.ylabel('salary')
plt.show()

#plotting testing test
plt.scatter(X_test,Y_test,color='red')
plt.plot(X_test,Y_pred,color='blue')
plt.title('Salary vs Year of Experience(training set)')
plt.xlabel('year of experience')
plt.ylabel('salary')
plt.show()