# basic_neural_network.py

# basic_neural_network.py

import time

def py_descent(x, d, mu, N_epochs):
    N = len(x)
    f = 2.0 / N

    # "Empty" predictions, errors, weights, gradients.
    y = [0] * N
    w = [0, 0]
    grad = [0, 0]

    for z in range(N_epochs):
        err = tuple(i - j for i, j in zip(d, y))
        #print err
        grad[0] = f * sum(err)
        grad[1] = f * sum(i * j for i, j in zip(err, x))
        w = [i + mu * j for i, j in zip(w, grad)]
        y = [w[0] + w[1] * i for i in x]
    return ['%f8'%i for i in w]
0

x_list = [0.00009,-0.00052,0.00256,-0.00099,0.00123]
d_list = [-0.00027,-0.00128,0.00027,0.00642,0.00499]

# `mu` is a step size, or scaling factor.
mu = 0.001
N_epochs = 10000

t0 = time.time()
py_w = py_descent(x_list, d_list, mu, N_epochs)
t1 = time.time()

print(py_w)

print('Solve time: {:.3f} seconds'.format(t1 - t0))