# You will be working with a dataset that contains handwritten digits.
#
# Load Training Data
print('Loading and Visualizing Data ...')
data = scio.loadmat('ex3data1.mat')
X = data['X']
y = data['y'].flatten()
m = y.size
# Randomly select 100 data points to display
rand_indices = np.random.permutation(range(m))
selected = X[rand_indices[0:100], :]
dd.display_data(selected)
input('Program paused. Press ENTER to continue')
# ===================== Part 2-a: Vectorize Logistic Regression =====================
# In this part of the exercise, you will reuse your logistic regression
# code from the last exercise. Your task here is to make sure that your
# regularized logistic regression implementation is vectorized. After
# that, you will implement one-vs-all classification for the handwritten
# digit dataset
#
# Test case for lrCostFunction
print('Testing lrCostFunction()')
theta_t = np.array([-2, -1, 1, 2])
# You will be working with a dataset that contains handwritten digits.
#
# Load Training Data
print('Loading and Visualizing Data ...')
data = scio.loadmat('ex3data1.mat')
X = data['X']
y = data['y'].flatten()
m = y.size
# Randomly select 100 data points to display
rand_indices = np.random.permutation(range(m))
selected = X[rand_indices[0:100], :]
dd.display_data(selected)
input('Program paused. Press ENTER to continue')
# ===================== Part 2: Loading Parameters =====================
# In this part of the exercise, we load some pre-initiated
# neural network parameters
print('Loading Saved Neural Network Parameters ...')
data = scio.loadmat('ex3weights.mat')
theta1 = data['Theta1']
theta2 = data['Theta2']
# ===================== Part 3: Implement Predict =====================
# After training the neural network, we would like to use it to predict
# You will be working with a dataset that contains handwritten digits.
#
# Load Training Data
print('Loading and Visualizing Data ...')
data = scio.loadmat('ex4data1.mat')
X = data['X']
y = data['y'].flatten()
m = y.size
# Randomly select 100 data points to display
rand_indices = np.random.permutation(range(m))
selected = X[rand_indices[0:100], :]
dd.display_data(selected)
input('Program paused. Press ENTER to continue')
# ===================== Part 2: Loading Parameters =====================
# In this part of the exercise, we load some pre-initiated
# neural network parameters
print('Loading Saved Neural Network Parameters ...')
data = scio.loadmat('ex4weights.mat')
theta1 = data['Theta1']
theta2 = data['Theta2']
nn_params = np.concatenate([theta1.flatten(), theta2.flatten()])
hidden_layer_size = 25
# 10 labels, from 1 to 10
num_labels = 10
# =========== Part 1: Loading and Visualizing Data =============
data = load_mat_data("../ex3data1.mat")
X = data['X']
y = data['y']
m = len(y)
# Load Training Data
print('Loading and Visualizing Data ...\n')
# Randomly select 100 data points to display
shuffle_100_X = np.arange(0, m, 1, dtype=int)
np.random.shuffle(shuffle_100_X)
sel = X[shuffle_100_X[0:100], :]
display_data(sel)
print('Program paused. Press enter to continue.\n')
# pause_func()
# ================ Part 2: Loading Pameters ================
# In this part of the exercise, we load some pre-initialized neural network parameters.
print('\nLoading Saved Neural Network Parameters ...\n')
# Load the weights into variables Theta1 and Theta2
theta1_2 = load_mat_data('ex3weights.mat')
Theta1 = theta1_2['Theta1']
Theta2 = theta1_2['Theta2']
# ================= Part 3: Implement Predict =================
# After training the neural network, we would like to use it to predict
# the labels. You will now implement the "predict" function to use the
# neural network to predict the labels of the training set. This lets
rk.draw_line(X_norm[i], X_rec[i])
plt.axis([-4, 3, -4, 3])
plt.show()
input('Program paused. Press ENTER to continue')
# ===================== Part 4: Loading and Visualizing Face Data =====================
# We start the exercise by first loading and visualizing the dataset.
# The following code will load the dataset into your environment
#
print('Loading face dataset.')
# Load Face dataset
data = scio.loadmat('ex7faces.mat')
X = data['X']
disp.display_data(X[0:100])
input('Program paused. Press ENTER to continue')
# ===================== Part 5: PCA on Face Data: Eigenfaces =====================
# Run PCA and visualize the eigenvectors which are in this case eigenfaces
# We display the first 36 eigenfaces.
#
print('Running PCA on face dataset.\n(this might take a minute or two ...)')
# Before running PCA, it is important to first normalize X by subtracting
# the mean value from each feature
X_norm, mu, sigma = fn.feature_normalize(X)
# Run PCA
U, S = pca.pca(X_norm)
print(data.keys())
print(data['X'].shape)
print(data['y'].shape)
X = data['X'] #提取输入特征 5000*400的矩阵 5000个训练样本 每个样本特征维度为400 一行代表一个训练样本
# print(X)
y = data['y'].flatten() #提取标签 data['y']是一个5000*1的2维数组 利用flatten()将其转换为有5000个元素的一维数组
#y中 数字0对应的标签是10
print(y)
m = y.size #训练样本的数量
# 随机抽取100个训练样本 进行可视化
rand_indices = np.random.permutation(range(m)) #获取0-4999 5000个无序随机索引
selected = X[rand_indices[0:100], :] #获取前100个随机索引对应的整条数据的输入特征
dd.display_data(selected) #调用可视化函数 进行可视化
input('Program paused. Press ENTER to continue')
'''第2-1部分 编写逻辑回归的代价函数(正则化),做简单的测试'''
# 逻辑回归（正则化）代价函数的测试用例
print('Testing lrCostFunction()')
theta_t = np.array([-2, -1, 1, 2]) #初始化假设函数的参数 假设有4个参数
X_t = np.c_[np.ones(5), np.arange(1, 16).reshape((3, 5)).T/10] #输入特征矩阵 5个训练样本 每个样本3个输入特征，前面添加一列特征=1
y_t = np.array([1, 0, 1, 0, 1]) #标签 做2分类
lmda_t = 3 #正则化惩罚性系数
cost, grad = lCF.lr_cost_function(theta_t, X_t, y_t, lmda_t) #传入代价函数
# 25 hidden units
hidden_layer_size = 25
# 10 labels, from 1 to 10
num_labels = 10
# =========== Part 1: Loading and Visualizing Data =============
data = load_mat_data("ex4data1.mat")
X = data['X']
y = data['y']
m = len(y)
# Load Training Data
print('Loading and Visualizing Data ...\n')
# Randomly select 100 data points to display
shuffle_100_X = np.arange(0, m, 1, dtype=int)
np.random.shuffle(shuffle_100_X)
sel = X[shuffle_100_X[0:100], :]
display_data(sel)
print('Program paused. Press enter to continue.\n')
# pause_func()
# ================ Part 2: Loading Parameters ================
# In this part of the exercise, we load some pre-initialized neural network parameters.
print('\nLoading Saved Neural Network Parameters ...\n')
# Load the weights into variables Theta1 and Theta2
theta1_2 = load_mat_data('ex4weights.mat')
Theta1 = theta1_2['Theta1']
Theta2 = theta1_2['Theta2']
nn_params = np.append(np.ravel(Theta1, order='F'),
np.ravel(Theta2, order='F'),
axis=0)
# ================ Part 3: Compute Cost (Feedforward) ================
hidden_layer_size = 25
num_labels = 10
# =========== Part 1: Loading and Visualizing Data =============
# Load Data
print('Loading and Visualizing Data ...\n')
data = sio.loadmat('ex4data1.mat')
X, y = data['X'], data['y'].flatten() # flatten is important!
m = X.shape[0]
# Randomly select 100 data points to display
sel = np.random.permutation(range(m))
sel = sel[:100]
display_data(X[sel, :])
plt.show()
input('Program paused. Press enter to continue.\n')
# ================ Part 2: Loading Parameters ================
print('\nLoading Saved Neural Network Parameters ...\n')
# Load the weights into variables Theta1 and Theta2
weights = sio.loadmat('ex4weights.mat')
Theta1, Theta2 = weights['Theta1'], weights['Theta2']
# Unroll parameters
nn_params = np.r_[Theta1.flatten(), Theta2.flatten()]
# ================ Part 3: Compute Cost (Feedforward) ================
# Obtain theta1 and theta2 back from nn_params
print(res)
theta1, theta2 = deserialize_t(res.x, input_layer_size, hidden_layer_size,
num_labels)
input('Program paused. Press ENTER to continue')
# ===================== Part 10: Visualize Weights =====================
# You can now 'visualize' what the neural network is learning by
# displaying the hidden units to see what features they are capturing in
# the data
print('Visualizing Neural Network...')
dd.display_data(theta1[:, 1:])
plt.show()
input('Program paused. Press ENTER to continue')
# ===================== Part 11: Implement Predict =====================
# After the training the neural network, we would like to use it to predict
# the labels. You will now implement the 'predict' function to use the
# neural network to predict the labels of the training set. This lets
# you compute the training set accuracy.
pred = pd.predict(theta1, theta2, X)
print('Training set accuracy: {}'.format(np.mean(pred == y) * 100))
input('ex4 Finished. Press ENTER to exit')
X_rec[0, 0], X_rec[0, 1]))
print('(this value should be about -1.047419 -1.047419)')
# Draw lines connecting the projected points to the original points
plt.scatter(X_rec[:, 0], X_rec[:, 1], facecolors='none', edgecolors='r', s=20)
for i in range(X_norm.shape[0]):
draw_line(X_norm[i, :], X_rec[i, :])
input('Program paused. Press enter to continue.\n')
# =============== Part 4: Loading and Visualizing Face Data =============
print("\nLoading face dataset.\n\n")
data = loadmat('ex7faces.mat')
X = data['X'] # (5000,1024)
# display
display_data(X[:100, :])
input('Program paused. Press enter to continue.\n')
# =========== Part 5: PCA on Face Data: Eigenfaces ===================
print('Running PCA on face dataset.')
print('(this might take a minute or two ...)\n\n')
'''
% Before running PCA, it is important to first normalize X by subtracting
% the mean value from each feature
'''
X_norm, mu, sigma = feature_normalize(X)
# Run PCA
U, S, V = pca(X_norm)
# 20x20 Input Imc c.reshape(2,8,order='F')= a.ravel(order='F')ages of Digits
input_layer_size = 400
# 10 labels, from 1 to 10
num_labels = 10
# =========== Part 1: Loading and Visualizing Data =============
data = load_mat_data("ex3data1.mat")
X = data['X']
y = data['y']
m = len(y)
# Load Training Data
print('Loading and Visualizing Data ...\n')
# Randomly select 100 data points to display
shuffle_100_X = np.arange(0, m, 1, dtype=int)
np.random.shuffle(shuffle_100_X)
sel = X[shuffle_100_X[0:100], :]
display_data(sel)
print('Program paused. Press enter to continue.\n')
# pause_func()
# ============ Part 2a: Vectorize Logistic Regression ============
# Test case for lrCostFunction
print('\nTesting lrCostFunction() with regularization')
theta_t = np.array([[-2], [-1], [1], [2]])
X_t = np.append(np.ones((5, 1)), np.arange(1, 16).reshape(5, 3, order='F') / 10, axis=1)
y_t = np.array([[1], [0], [1], [0], [1]])
lambda_t = 3
J, grad = lr_cost_function(theta_t, X_t, y_t, lambda_t)
print('\nCost: \n', J, '\nExpected cost: 2.534819\n')
print('Gradients:\n', grad, '\nExpected gradients:\n', ' 0.146561\n -0.548558\n 0.724722\n 1.398003\n')
print('Program paused. Press enter to continue.\n')
# pause_func()
input_layer_size = 400
hidden_layer_size = 25
num_labels = 10
print('Loading and Visualizing Data ...\n')
data = sio.loadmat('ex3data1.mat')
m = data['X'].shape[0]
X, y = data['X'], data['y'].flatten()
# Randomly select 100 data points to display
rand_indices = np.random.permutation(range(m))
sel = X[rand_indices[:100], :]
display_data(sel)
plt.show()
input('Program paused. Press enter to continue.\n')
# ================ Part 2: Loading Pameters ================
print('\nLoading Saved Neural Network Parameters ...\n')
weights = sio.loadmat('ex3weights.mat')
Theta1, Theta2 = weights['Theta1'], weights['Theta2']
# print(Theta1.shape) # (25,401)
# print(Theta2.shape) # (10,26)
# ================= Part 3: Implement Predict =================
pred = predict(Theta1, Theta2, X)
print('\nTraining Set Accuracy: {:.1f}%\n'.format(np.mean(pred == y) * 100))
