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

#setting figure size
plt.rcParams['figure.figsize'] = (6.0, 6.0)

#preprocessing training data
data = pd.read_csv('train_data.csv')
X = data.iloc[:, 0]
Y = data.iloc[:, 1]

#creating the training model
m = random.random()
c = random.random()
L = 0.0001


iterations = 100

for i in range (iterations):
    Y_pred = m*X + c  #predicted value of y
    D_m = (-2/(len(X))) * sum(X * (Y - Y_pred))  #derivative wrt m
    D_c = (-2/(len(X))) * sum(Y - Y_pred)  #derivative wrt c
    m = m - L * D_m  #update m
    c = c - L * D_c  #update c

print (m,c)


#testing

test_data = pd.read_csv("test_data.csv")
x_test, y_test = test_data['x_test'], test_data['y_test']
y_pred = m*x_test + c

plt.scatter(x_test, y_test)
plt.plot([min(x_test), max(x_test)], [min(y_pred), max(y_pred)], color='red') # predicted
plt.show()

MSE = np.square(np.subtract(y_test,y_pred)).mean()

print (MSE)