Linear_Regression.py

"""
Created on Sat  Aug 18  15:17:48  2018
@author: srajan23
"""

# importing the libraries
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

# importing data set
dataset = pd.read_csv('../input/Height_Weight_single_variable_data_101_series_1.0.csv')

# checking for null values if any
dataset.isnull().any()

# Splitting the dataset into test set and training set
X_train, X_test, y_train, y_test = train_test_split(dataset.iloc[:, 1:],
                                                    dataset.iloc[:, 0:1],
                                                    test_size=1/3,random_state = 0)

# Fitting the Model 
regressor = LinearRegression()
regressor.fit(X_train,y_train)

# Calculating R square score
print('R square = ',regressor.score(X_train,y_train))


# Predicting Height
y_pred = regressor.predict(X_test)

# Visualising the Training set
plt.scatter(X_train,y_train,color='blue')
plt.plot(X_train, regressor.predict(X_train),color='red')
plt.title('Training Set')
plt.xlabel('Height')
plt.ylabel('Weight')
plt.show()

# Visualising the test set and plotting the regression line predicted by our model
plt.scatter(X_test,y_test,color='blue')
plt.plot(X_test, regressor.predict(X_test),color='red')
plt.title('Test Set')
plt.xlabel('Height')
plt.ylabel('Weight')
plt.show()