-
Notifications
You must be signed in to change notification settings - Fork 0
/
simplemodel.py
136 lines (106 loc) · 5.13 KB
/
simplemodel.py
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
import numpy as np
import time
from dataset import *
# compute sigmoid nonlinearity
def sigmoid(x):
output = 1/(1+np.exp(-x))
return output
# convert output of sigmoid function to its derivative
def sigmoid_output_to_derivative(output):
return output*(1-output)
def clean_up_sentence(sentence):
# tokenize the pattern
sentence_words = nltk.word_tokenize(sentence)
# stem each word
sentence_words = [stemmer.stem(word.lower()) for word in sentence_words]
return sentence_words
# return bag of words array: 0 or 1 for each word in the bag that exists in the sentence
def bow(sentence, words, show_details=False):
# tokenize the pattern
sentence_words = clean_up_sentence(sentence)
# bag of words
bag = [0]*len(words)
for s in sentence_words:
for i,w in enumerate(words):
if w == s:
bag[i] = 1
if show_details:
print ("found in bag: %s" % w)
return(np.array(bag))
def think(sentence, show_details=False):
x = bow(sentence.lower(), words, show_details)
if show_details:
print ("sentence:", sentence, "\n bow:", x)
# input layer is our bag of words
l0 = x
# matrix multiplication of input and hidden layer
l1 = sigmoid(np.dot(l0, synapse_0))
# output layer
l2 = sigmoid(np.dot(l1, synapse_1))
return l2
def train(X, y, hidden_neurons=10, alpha=1, epochs=50000, dropout=False, dropout_percent=0.5):
print ("Training with %s neurons, alpha:%s, dropout:%s %s" % (hidden_neurons, str(alpha), dropout, dropout_percent if dropout else '') )
print ("Input matrix: %sx%s Output matrix: %sx%s" % (len(X),len(X[0]),1, len(classes)) )
np.random.seed(1)
last_mean_error = 1
# randomly initialize our weights with mean 0
synapse_0 = 2*np.random.random((len(X[0]), hidden_neurons)) - 1
synapse_1 = 2*np.random.random((hidden_neurons, len(classes))) - 1
prev_synapse_0_weight_update = np.zeros_like(synapse_0)
prev_synapse_1_weight_update = np.zeros_like(synapse_1)
synapse_0_direction_count = np.zeros_like(synapse_0)
synapse_1_direction_count = np.zeros_like(synapse_1)
for j in iter(range(epochs+1)):
# Feed forward through layers 0, 1, and 2
layer_0 = X
layer_1 = sigmoid(np.dot(layer_0, synapse_0))
if(dropout):
layer_1 *= np.random.binomial([np.ones((len(X),hidden_neurons))],1-dropout_percent)[0] * (1.0/(1-dropout_percent))
layer_2 = sigmoid(np.dot(layer_1, synapse_1))
# how much did we miss the target value?
layer_2_error = y - layer_2
if (j% 10000) == 0 and j > 5000:
# if this 10k iteration's error is greater than the last iteration, break out
if np.mean(np.abs(layer_2_error)) < last_mean_error:
#print ("delta after "+str(j)+" iterations:" + str(np.mean(np.abs(layer_2_error))) )
print ("accuracy after "+str(j)+" iterations:" + str(100-100*(np.mean(np.abs(layer_2_error)))))
last_mean_error = np.mean(np.abs(layer_2_error))
else:
print ("break:", np.mean(np.abs(layer_2_error)), ">", last_mean_error )
break
# in what direction is the target value?
# were we really sure? if so, don't change too much.
layer_2_delta = layer_2_error * sigmoid_output_to_derivative(layer_2)
# how much did each l1 value contribute to the l2 error (according to the weights)?
layer_1_error = layer_2_delta.dot(synapse_1.T)
# in what direction is the target l1?
# were we really sure? if so, don't change too much.
layer_1_delta = layer_1_error * sigmoid_output_to_derivative(layer_1)
#print len(layer_1)
#print len(layer_2_delta)
synapse_1_weight_update = (layer_1.T.dot(layer_2_delta))
synapse_0_weight_update = (layer_0.T.dot(layer_1_delta))
if(j > 0):
synapse_0_direction_count += np.abs(((synapse_0_weight_update > 0)+0) - ((prev_synapse_0_weight_update > 0) + 0))
synapse_1_direction_count += np.abs(((synapse_1_weight_update > 0)+0) - ((prev_synapse_1_weight_update > 0) + 0))
synapse_1 += alpha * synapse_1_weight_update
synapse_0 += alpha * synapse_0_weight_update
prev_synapse_0_weight_update = synapse_0_weight_update
prev_synapse_1_weight_update = synapse_1_weight_update
now = datetime.datetime.now()
# persist synapses
synapse = {'synapse0': synapse_0.tolist(), 'synapse1': synapse_1.tolist(),
'datetime': now.strftime("%Y-%m-%d %H:%M"),
'words': words,
'classes': classes
}
synapse_file = "synapses.json"
with open(synapse_file, 'w') as outfile:
json.dump(synapse, outfile, indent=4, sort_keys=True)
print ("saved synapses to:", synapse_file)
X = np.array(training)
y = np.array(output)
start_time = time.time()
train(X, y, hidden_neurons=len(X[0]), alpha=0.01, epochs=10000, dropout=False, dropout_percent=0.2)
elapsed_time = time.time() - start_time
print ("processing time:", elapsed_time, "seconds")