deeplearning1 logstic regression as a Neural Networks

# -*- coding: utf-8 -*-
"""
Created on Sat Dec  2 19:10:44 2017

@author: xiaofeixiazyh
"""

# import packages

import numpy as np
import matplotlib.pyplot as plt
import h5py
import scipy
from PIL import Image
from scipy import ndimage
from lr_utils import load_dataset

# load the data

train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset()

##Example of a picture
#index = 24
#plt.imshow(train_set_x_orig[index])
#print("y = " + str(train_set_y[:,index]) + ", it is a " + classes[np.squeeze(train_set_y[:,index])].decode("utf-8") + " picture")
#
#print(np.squeeze(train_set_y[:,index]))

#print(train_set_x_orig.shape)

m_train = train_set_x_orig.shape[0]
m_test = test_set_x_orig.shape[0]
num_px = train_set_x_orig.shape[1]

#print("Number of training example: m_train = " + str(m_train))
#print("Number of testing example : m_test = " + str(m_test))
#print("Height/width of each image: num_px = " + str(num_px))
#print("Each image is of size:(" + str(num_px) + "," + str(num_px) + ",3)")
#print("train_set_x shape: " + str(train_set_x_orig.shape))
#print("train_set_y shape :" + str(train_set_y.shape))
#print("test_set_x shape: " + str(test_set_x_orig.shape))
#print("test_set_y shape :" + str(test_set_y.shape))

#-----------------------------------------
# reshape the train and test set
#----------------------------------------

train_set_x_flatten = train_set_x_orig.reshape(train_set_x_orig.shape[0],-1).T
test_set_x_flatten  = test_set_x_orig.reshape(test_set_x_orig.shape[0],-1).T

#print("train_set_x_flatten shape: " + str(train_set_x_flatten.shape))
#print("train_set_y shape :" + str(train_set_y.shape))
#print("test_set_x_flatten shape :" + str(test_set_x_flatten.shape))
#print("test_set_y shape : " + str(test_set_y.shape))
#print("sanity check atfer reshapeing : " + str(train_set_x_flatten[0:5,0]))

# standarded the train/test data set 
train_set_x = train_set_x_flatten / 255
test_set_x = test_set_x_flatten / 225
#print("check after standarded : " + str(train_set_x[0:5,0]))

# Building the parts of algorithm-----------------------------
#---------------------------------------------------------#

def sigmod(z):
    """
    Compute the sigmoid of z

    Arguments:
    x -- A scalar or numpy array of any size.

    Return:
    s -- sigmoid(z)
    """
    s = 1. / (1 + np.exp(-z))
    return s

#print("sigmod(0) = " + str(sigmod(0)))
#print("sigmod(9) = " + str(sigmod(9)))

def initialize_with_zeros(dim):
    """
    This function creates a vector of zeros of shape (dim, 1) for w and initializes b to 0.

    Argument:
    dim -- size of the w vector we want (or number of parameters in this case)

    Returns:
    w -- initialized vector of shape (dim, 1)
    b -- initialized scalar (corresponds to the bias)
    """
    w = np.zeros((dim, 1))
    b = 0

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

    return w,b

#dim = 2
#w,b = initialize_with_zeros(dim)
#print("w = " + str(w))
#print("b = " + str(b))

def propagate(w,b,X,Y):
    """
    Implement the cost function and its gradient for the propagation explained above

    Arguments:
    w -- weights, a numpy array of size (num_px * num_px * 3, 1)
    b -- bias, a scalar
    X -- data of size (num_px * num_px * 3, number of examples)
    Y -- true "label" vector (containing 0 if non-cat, 1 if cat) of size (1, number of examples)

    Return:
    cost -- negative log-likelihood cost for logistic regression
    dw -- gradient of the loss with respect to w, thus same shape as w
    db -- gradient of the loss with respect to b, thus same shape as b

    Tips:
    - Write your code step by step for the propagation
    """
    m = X.shape[1]

    A = sigmod(np.dot(w.T,X) + b)
    cost = np.sum(Y*np.log(A) + (1-Y) *np.log(1-A)) / (-m)


    dw = np.dot(X, (A-Y).T) / m
    db = np.sum(A-Y) / m

    assert(dw.shape == w.shape)
    assert(db.dtype == float)
    cost = np.squeeze(cost)
    assert(cost.shape == ())

    grads = {
            "dw" : dw,
            "db" : db
            }
    return grads, cost

w, b, X, Y = np.array([[1],[2]]), 2 , np.array([[1,2],[3,4]]), np.array([[1,0]])
#grads, cost = propagate(w,b,X,Y)
#print("dw = " + str(grads["dw"]))
#print("db = " + str(grads["db"]))
#print("cost = " + str(cost))

#==============================================================================
# 从这里开始检查
#==============================================================================

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

    Arguments:
    w -- weights, a numpy array of size (num_px * num_px * 3, 1)
    b -- bias, a scalar
    X -- data of shape (num_px * num_px * 3, number of examples)
    Y -- true "label" vector (containing 0 if non-cat, 1 if cat), of shape (1, number of examples)
    num_iterations -- number of iterations of the optimization loop
    learning_rate -- learning rate of the gradient descent update rule
    print_cost -- True to print the loss every 100 steps

    Returns:
    params -- dictionary containing the weights w and bias b
    grads -- dictionary containing the gradients of the weights and bias with respect to the cost function
    costs -- list of all the costs computed during the optimization, this will be used to plot the learning curve.

    Tips:
    You basically need to write down two steps and iterate through them:
        1) Calculate the cost and the gradient for the current parameters. Use propagate().
        2) Update the parameters using gradient descent rule for w and b.
    """
    costs = []

    for i in range(num_iterations):
        grads , cost = propagate(w,b,X,Y)

        dw = grads["dw"]
        db = grads["db"]

        w = w - learning_rate * dw
        b = b -  learning_rate * db 

        if i % 100 == 0 :
            costs.append(cost)

        if print_cost or 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

params, grads, costs = optimize(w, b, X, Y, num_iterations= 1000, learning_rate = 0.009, print_cost = False)
#print ("w = " + str(params["w"]))
#print ("b = " + str(params["b"]))
#print ("dw = " + str(grads["dw"]))
#print ("db = " + str(grads["db"]))    


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

    Arguments:
    w -- weights, a numpy array of size (num_px * num_px * 3, 1)
    b -- bias, a scalar
    X -- data of size (num_px * num_px * 3, number of examples)

    Returns:
    Y_prediction -- a numpy array (vector) containing all predictions (0/1) for the examples in X
    '''
    m = X.shape[1]
    Y_prediction = np.zeros((1,m))
    w = w.reshape(X.shape[0],1)

    A = sigmod(np.dot(w.T,X))

    for i in range(A.shape[1]):
        if (A[0,i] > 0.5):
            Y_prediction[0][i] = 1
        else:
            Y_prediction[0][1] = 0

    assert(Y_prediction.shape == (1,m) )

    return Y_prediction

#print("prediction = " + str(predict(w,b,X)))


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

    Arguments:
    X_train -- training set represented by a numpy array of shape (num_px * num_px * 3, m_train)
    Y_train -- training labels represented by a numpy array (vector) of shape (1, m_train)
    X_test -- test set represented by a numpy array of shape (num_px * num_px * 3, m_test)
    Y_test -- test labels represented by a numpy array (vector) of shape (1, m_test)
    num_iterations -- hyperparameter representing the number of iterations to optimize the parameters
    learning_rate -- hyperparameter representing the learning rate used in the update rule of optimize()
    print_cost -- Set to true to print the cost every 100 iterations

    Returns:
    d -- dictionary containing information about the model.
    """

    w , b = initialize_with_zeros(X_train.shape[0])
    parameters, grads, costs = optimize(w, b, X_train, Y_train, num_iterations, learning_rate, print_cost = False)
    w = parameters["w"]
    b = parameters["b"]

    Y_prediction_test = predict(w, b, X_test)
    Y_prediction_train = predict(w, b, X_train)

    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


import time
tic = time.process_time()
num_iterations = 10000
d = model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations = num_iterations, learning_rate = 0.5, print_cost = True)
toc = time.process_time()
print('Use num_iterations of %i, run %f sec ' %(num_iterations, toc - tic))