1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
| import numpy as np
import json
import matplotlib.pyplot as plt
def load_data():
datafile = './data/housing.data'
data = np.fromfile(datafile, sep=' ')
feature_names = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS',
'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV']
feature_num = len(feature_names)
data = data.reshape([data.shape[0] // feature_num, feature_num])
ratio = 0.8
offset = int(data.shape[0] * ratio)
training_data = data[:offset]
maximums, minimums, avgs = training_data.max(axis=0), training_data.min(axis=0), training_data.sum(axis=0) / \
training_data.shape[0]
for i in range(feature_num):
data[:, i] = (data[:, i] - avgs[i]) / (maximums[i] - minimums[i])
training_data = data[:offset]
test_data = data[offset:]
return training_data, test_data
class Network(object):
def __init__(self, num_of_weights):
np.random.seed(0)
self.w = np.random.randn(num_of_weights, 1)
self.b = 0.
def forward(self, x):
z = np.dot(x, self.w) + self.b
return z
def loss(self, z, y):
error = z - y
cost = error * error
cost = np.mean(cost)
return cost
def gradient(self, x, y):
z = self.forward(x)
gradient_w = (z - y) * x
gradient_w = np.mean(gradient_w, axis=0)
gradient_w = gradient_w[:, np.newaxis]
gradient_b = (z - y)
gradient_b = np.mean(gradient_b)
return gradient_w, gradient_b
def update(self, gradient_w, gradient_b, eta=0.01):
self.w = self.w - eta * gradient_w
self.b = self.b - eta * gradient_b
def train(self, x, y, iterations=100, eta=0.01):
losses = []
for i in range(iterations):
z = self.forward(x)
L = self.loss(z, y)
gradient_w, gradient_b = self.gradient(x, y)
self.update(gradient_w, gradient_b, eta)
losses.append(L)
if (i + 1) % 10 == 0:
print('iter {}, loss {}'.format(i, L))
return losses
train_data, test_data = load_data()
x = train_data[:, :-1]
y = train_data[:, -1:]
net = Network(13)
num_iterations=1000
losses = net.train(x,y, iterations=num_iterations, eta=0.01)
plot_x = np.arange(num_iterations)
plot_y = np.array(losses)
plt.plot(plot_x, plot_y)
plt.show()
class NetworkOfSGD(object):
def __init__(self, num_of_weights):
self.w = np.random.randn(num_of_weights, 1)
self.b = 0.
def forward(self, x):
z = np.dot(x, self.w) + self.b
return z
def loss(self, z, y):
error = z - y
num_samples = error.shape[0]
cost = error * error
cost = np.sum(cost) / num_samples
return cost
def gradient(self, x, y):
z = self.forward(x)
N = x.shape[0]
gradient_w = 1. / N * np.sum((z - y) * x, axis=0)
gradient_w = gradient_w[:, np.newaxis]
gradient_b = 1. / N * np.sum(z - y)
return gradient_w, gradient_b
def update(self, gradient_w, gradient_b, eta=0.01):
self.w = self.w - eta * gradient_w
self.b = self.b - eta * gradient_b
def train(self, training_data, num_epoches, batch_size=10, eta=0.01):
n = len(training_data)
losses = []
for epoch_id in range(num_epoches):
np.random.shuffle(training_data)
mini_batches = [training_data[k:k + batch_size] for k in range(0, n, batch_size)]
for iter_id, mini_batch in enumerate(mini_batches):
x = mini_batch[:, :-1]
y = mini_batch[:, -1:]
a = self.forward(x)
loss = self.loss(a, y)
gradient_w, gradient_b = self.gradient(x, y)
self.update(gradient_w, gradient_b, eta)
losses.append(loss)
print('Epoch {:3d} / iter {:3d}, loss = {:.4f}'.
format(epoch_id, iter_id, loss))
return losses
train_data, test_data = load_data()
net = NetworkOfSGD(13)
losses = net.train(train_data, num_epoches=50, batch_size=100, eta=0.1)
plot_x = np.arange(len(losses))
plot_y = np.array(losses)
plt.plot(plot_x, plot_y)
plt.show()
|