#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Jul 12 19:10:27 2019

@author: nodeflux
"""

import numpy
import pandas
from matplotlib import pyplot
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score


dataset = pandas.read_csv('/home/nodeflux/Documents/mercubuana/UAS_DATA_MINING/data.csv')
x = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 2]


x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=0)
regressor = LinearRegression()
regressor.fit(x_train, y_train)

y_prediction = regressor.predict(x_test)

# Coefficient
print('Coefficient: \n', regressor.coef_)
# Mean Squared Error
print("Mean squared error: %.2f" % mean_squared_error(y_test, y_prediction))
# Variance score
print("Variance score: %.2f" % r2_score(y_test, y_prediction))

pyplot.scatter(x_test[:, 0], y_test, color='black')
pyplot.scatter(x_test[:, 0], y_prediction, color='blue', linewidth=3)
pyplot.xticks(())
pyplot.yticks(())
pyplot.show()

pyplot.scatter(x_test[:, 1], y_test, color='black')
pyplot.scatter(x_test[:, 1], y_prediction, color='blue', linewidth=3)
pyplot.xticks(())
pyplot.yticks(())
pyplot.show()