sigmoid.py

from __future__ import division
from load_cifar import *
import numpy as np

imagearray, labelarray = load_batch()
#print imagearray.shape         #   (10000, 3072)   3072 = 3, 32, 32
#print labelarray.shape         #   (10000,)

train_set_x, train_set_y, test_set_x, test_set_y = create_datasets(imagearray, labelarray)
#print train_set_x.shape        #   (3072, 200)
#print train_set_y.shape        #   (1, 200)

def sigmoid(z):

    s = 1/(1+np.exp(-z))

    return s
    
def initialize_with_zeros(dim):

    w = np.zeros((dim,1))
    b = 0

    assert(w.shape == (dim, 1))
    assert(isinstance(b, float) or isinstance(b, int))
    
    return w, b

def propagate(w, b, X, Y):
    
    m = X.shape[1]
    
    A = sigmoid(np.dot(w.T,X)+b)                                            # compute activation
    cost = (1./m) * (-np.dot(Y,np.log(A).T) - np.dot(1-Y, np.log(1-A).T))   # compute cost
    
    # BACKWARD PROPAGATION (TO FIND GRAD)
    dw = 1/m * np.dot(X,(A-Y).T)
    db = 1/m * np.sum(A-Y)

    assert(dw.shape == w.shape)
    assert(db.dtype == float)
    cost = np.squeeze(cost)
    assert(cost.shape == ())
    
    grads = {"dw": dw,
             "db": db}
    
    return grads, cost

#   This function optimizes w and b by running a gradient descent algorithm
def optimize(w, b, X, Y, num_iterations, learning_rate, print_cost = False):

    costs = []
    
    for i in range(num_iterations):
        
        # Cost and gradient calculation (~ 1-4 lines of code)
        grads, cost = propagate(w, b, X, Y)
        
        # Retrieve derivatives from grads
        dw = grads["dw"]
        db = grads["db"]
        
        # update rule (~ 2 lines of code)
        w = w - learning_rate * dw
        b = b - learning_rate * db
        
        # Record the costs
        if i % 100 == 0:
            costs.append(cost)
        
        # Print the cost every 100 training examples
        if print_cost and i % 100 == 0:
            print ("Cost after iteration %i: %f" %(i, cost))
    
    params = {"w": w,
              "b": b}
    
    grads = {"dw": dw,
             "db": db}
    
    return params, grads, costs

#   Predict whether the label is 0 or 1 using learned logistic regression parameters (w, b)
def predict(w, b, X):

    m = X.shape[1]
    Y_prediction = np.zeros((1,m))
    w = w.reshape(X.shape[0], 1)
    
    # Compute vector "A" predicting the probabilities of a cat being present in the picture
    A = sigmoid(np.dot(w.T,X)+b)
    
    for i in range(A.shape[1]):
        
        # Convert probabilities A[0,i] to actual predictions p[0,i]
        if (A[0,i] <= 0.5):
            Y_prediction[0,i] = 0
        else:
            Y_prediction[0,i] = 1
    
    assert(Y_prediction.shape == (1, m))
    
    return Y_prediction

#   Builds the logistic regression model by calling the function you've implemented previously
def model(X_train, Y_train, X_test, Y_test, num_iterations = 2000, learning_rate = 0.5, print_cost = False):

    # initialize parameters with zeros (~ 1 line of code)
    w, b = initialize_with_zeros(X_train.shape[0])
    
    # Gradient descent (~ 1 line of code)
    parameters, grads, costs = optimize(w, b, X_train, Y_train, num_iterations, learning_rate, print_cost)
    
    # Retrieve parameters w and b from dictionary "parameters"
    w = parameters["w"]
    b = parameters["b"]
    
    # Predict test/train set examples (~ 2 lines of code)
    Y_prediction_test = predict(w, b, X_test)
    Y_prediction_train = predict(w, b, X_train)

    # Print train/test Errors    
    print("train accuracy: {} %".format(100 - np.mean(np.abs(Y_prediction_train - Y_train)) * 100))
    print("test accuracy: {} %".format(100 - np.mean(np.abs(Y_prediction_test - Y_test)) * 100))

    
    d = {"costs": costs,
         "Y_prediction_test": Y_prediction_test, 
         "Y_prediction_train" : Y_prediction_train, 
         "w" : w, 
         "b" : b,
         "learning_rate" : learning_rate,
         "num_iterations": num_iterations}
    
    return d
    
if __name__ == '__main__':
    d = model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations = 2000, learning_rate = 0.005, print_cost = True)
    #predict(d["w"], d["b"], x)