-
Notifications
You must be signed in to change notification settings - Fork 61
/
train.py
91 lines (70 loc) · 2.47 KB
/
train.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
import nltk
from nltk.stem.lancaster import LancasterStemmer
import numpy as np
import tensorflow as tf
import tflearn
import random
import pickle
from Bot import path
import json
stemmer = LancasterStemmer()
with open(path.getJsonPath()) as json_data:
intents = json.load(json_data)
words = []
classes = []
documents = []
ignore_words = ['?']
for intent in intents['intents']:
for pattern in intent['patterns']:
w = nltk.word_tokenize(pattern)
words.extend(w)
documents.append((w, intent['tag']))
if intent['tag'] not in classes:
classes.append(intent['tag'])
words = [stemmer.stem(w.lower()) for w in words if w not in ignore_words]
words = sorted(list(set(words)))
classes = sorted(list(set(classes)))
print(len(documents), "Docs")
print(len(classes), "Classes", classes)
print(len(words), "Split words", words)
training = []
output = []
output_empty = [0] * len(classes)
for doc in documents:
bag = []
pattern_words = doc[0]
pattern_words = [stemmer.stem(word.lower()) for word in pattern_words]
for w in words:
bag.append(1) if w in pattern_words else bag.append(0)
output_row = list(output_empty)
output_row[classes.index(doc[1])] = 1
training.append([bag, output_row])
random.shuffle(training)
training = np.array(training)
train_x = list(training[:, 0])
train_y = list(training[:, 1])
tf.reset_default_graph()
net = tflearn.input_data(shape=[None, len(train_x[0])])
net = tflearn.fully_connected(net, 8)
net = tflearn.fully_connected(net, 8)
net = tflearn.fully_connected(net, len(train_y[0]), activation='softmax')
net = tflearn.regression(net)
model = tflearn.DNN(net, tensorboard_dir=path.getPath('train_logs'))
model.fit(train_x, train_y, n_epoch=20000, batch_size=500, show_metric=True)
model.save(path.getPath('model.tflearn'))
def clean_up_sentence(sentence):
sentence_words = nltk.word_tokenize(sentence)
sentence_words = [stemmer.stem(word.lower()) for word in sentence_words]
return sentence_words
def bow(sentence, words, show_details=False):
sentence_words = clean_up_sentence(sentence)
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)
pickle.dump({'words': words, 'classes': classes, 'train_x': train_x, 'train_y': train_y},
open(path.getPath('trained_data'), "wb"))