import matplotlib.pyplot as plt
import numpy as np

def sigmoid(x):
    return 1.0/(1+ np.exp(-x))

def sigmoid_derivative(x):
    return x * (1.0 - x)

class NeuralNetwork:
    def __init__(self, x, y):
        self.input      = x
        self.weights1   = np.random.rand(self.input.shape[1],3)
        self.weights2   = np.random.rand(3,1)
        self.y          = y
        self.output     = np.zeros(self.y.shape)

    def feedforward(self):
        self.layer1 = sigmoid(np.dot(self.input, self.weights1))
        self.output = sigmoid(np.dot(self.layer1, self.weights2))

    def backprop(self):
        # application of the chain rule to find derivative of the loss function with respect to weights2 and weights1
        d_weights2 = np.dot(self.layer1.T, (2*(self.y - self.output) * sigmoid_derivative(self.output)))
        d_weights1 = np.dot(self.input.T,  (np.dot(2*(self.y - self.output) * sigmoid_derivative(self.output), self.weights2.T) * sigmoid_derivative(self.layer1)))

        # update the weights with the derivative (slope) of the loss function
        self.weights1 += d_weights1
        self.weights2 += d_weights2


if __name__ == "__main__":
    X = np.array([[1/31,1/24,15/60],
                  [1/31,1/24,30/60],
                  [1/31,1/24,45/60],
                  [1/31,1/24,60/60]])
    y = np.array([[15521.7/15534.1],[15534.1/15534.1],[15404.4/15534.1],[15196.3/15534.1]])
    nn = NeuralNetwork(X,y)

    for i in range(10000):
        nn.feedforward()
        nn.backprop()

    print(nn.output)
    print(X)
    #g=np.linspace(0.15,1,4)
    #plt.plot(g,y)
    #plt.show()