import sklearn
from sklearn import linear_model

import numpy as np

data = []
target = []
with open("data_yequalsx.csv") as inFile:
    for row in inFile:
        vals = row.split(",")
        data.append([float(x) for x in vals[:-1]])
        target.append(float(vals[-1]))

test_samples= len(data)/10

train_data = [0]*(len(data) - test_samples)
train_target = [0]*(len(data) - test_samples)
test_data = [0]*(test_samples)
test_target = [0]*(test_samples)
train_index = 0
test_index = 0
for j in range(len(data)):
    if j >= test_samples:
        train_data[train_index] = data[j]
        train_target[train_index] = target[j]
        train_index += 1
    else:
        test_data[test_index] = data[j]
        test_target[test_index] = target[j]
        test_index += 1

model = linear_model.SGDRegressor(n_iter=100, learning_rate="invscaling", eta0=0.0001, power_t=0.5, penalty="l2", alpha=0.0001, loss="squared_loss")
model.fit(train_data, train_target)
print(model.coef_)
print(model.intercept_)

result = model.predict(test_data)
mse = np.mean((result - test_target) ** 2)
print("Mean Squared Error = %s" % str(mse))