Main.py

# Package imports
import numpy as np
import matplotlib.pyplot as plt

np.random.seed(1)

def layer_sizes(X, Y):

    n_x = len(X) # size of input layer
    n_h = 4
    n_y = len(Y) # size of output layer
    ### END CODE HERE ###
    return (n_x, n_h, n_y);

def initialize_parameters(n_x, n_h, n_y):
    np.random.seed(2)

    W1 = np.random.randn(n_h , n_x) * 0.01
    b1 = np.zeros((n_h , 1))
    W2 = np.random.randn(n_y , n_h) * 0.01
    b2 = np.zeros((n_y , 1))

    assert (W1.shape == (n_h, n_x))
    assert (b1.shape == (n_h, 1))
    assert (W2.shape == (n_y, n_h))
    assert (b2.shape == (n_y, 1))

    parameters = {"W1": W1,
                  "b1": b1,
                  "W2": W2,
                  "b2": b2}

    return parameters

def Sigmoid(matris):
    result = 1 / (1 + np.exp((-1) * matris))
    return result;


def Tanh(matris):
    result = np.tanh(matris)
    return result;


def Sigmoid_Derivative(matris):
    date = Sigmoid(matris)
    return date * (1 - date);


def Tanh_Derivative(matris):
    date = Tanh(matris)
    return (1 - date * date);

def forward_propagation(X, parameters):

    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]

    Z1 = np.dot(W1,X) + b1
    A1 = np.tanh(Z1)
    Z2 = np.dot(W2,A1) + b2
    A2 = Sigmoid(Z2)
    ### END CODE HERE ###

    assert(A2.shape == (1, X.shape[1]))

    cache = {"Z1": Z1,
             "A1": A1,
             "Z2": Z2,
             "A2": A2}

    return A2, cache


def compute_cost(A2, Y, parameters):

    m = Y.shape[1] # number of example

    logprobs = np.multiply(np.log(A2),Y)
    cost = - np.sum(logprobs)

    cost = np.squeeze(cost)     # makes sure cost is the dimension we expect.
                                # E.g., turns [[17]] into 17
    assert(isinstance(cost, float))

    return cost


def backward_propagation(parameters, cache, X, Y):

    m = X.shape[1]

    W1 = parameters['W1']
    W2 = parameters['W2']

    A1 = cache['A1']
    A2 = cache['A2']

    dZ2 = A2 - Y
    dW2 = np.dot(dZ2 , np.transpose(A1))/m
    db2 = np.sum(dZ2 , axis = 1 , keepdims = True)/m
    dZ1 = np.dot(np.transpose(W2),dZ2)*(1 - np.power(A1, 2))
    dW1 = np.dot(dZ1 , np.transpose(X))/m
    db1 = np.sum(dZ1 , axis = 1 , keepdims = True)/m
    ### END CODE HERE ###

    grads = {"dW1": dW1,
             "db1": db1,
             "dW2": dW2,
             "db2": db2}

    return grads

def update_parameters(parameters, grads, learning_rate = 1.2):

    W1 = parameters['W1']
    b1 = parameters['b1']
    W2 = parameters['W2']
    b2 = parameters['b2']

    dW1 = grads['dW1']
    db1 = grads['db1']
    dW2 = grads['dW2']
    db2 = grads['db2']

    W1 = W1 - learning_rate * dW1
    b1 = b1 - learning_rate * db1
    W2 = W2 - learning_rate * dW2
    b2 = b2 - learning_rate * db2
    ### END CODE HERE ###

    parameters = {"W1": W1,
                  "b1": b1,
                  "W2": W2,
                  "b2": b2}

    return parameters


def nn_model(X, Y, n_h, num_iterations = 10000, print_cost=False):

    np.random.seed(3)
    n_x = layer_sizes(X, Y)[0]
    n_y = layer_sizes(X, Y)[2]

    parameters = initialize_parameters(n_x, n_h, n_y)
    W1 = parameters['W1']
    b1 = parameters['b1']
    W2 = parameters['W2']
    b2 = parameters['b2']
    ### END CODE HERE ###

    # Loop (gradient descent)

    for i in range(0, num_iterations):

        A2, cache = forward_propagation(X, parameters)

        cost = compute_cost(A2, Y, parameters)

        grads = backward_propagation(parameters, cache, X, Y)

        parameters = update_parameters(parameters, grads, learning_rate = 1.2)

    return parameters