-
Notifications
You must be signed in to change notification settings - Fork 0
/
main.py
157 lines (120 loc) · 4.08 KB
/
main.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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
import random
import json
import tensorflow
import tflearn
import numpy as np
import nltk§
import pickle
from os import path
from nltk.stem.lancaster import LancasterStemmer
stemmer = LancasterStemmer()
# constant
TRAIN_MODEL = False
with open("intents.json") as file:
data = json.load(file)
# try to use saved data
try:
with open("data.pickle", "rb") as f:
words, labels, training, output = pickle.load(f)
# otherwise collect data for training model
except:
# create lists§
# words
words = []
# labels
labels = []
# list of patterns
docs_x = []
# words and groups
docs_y = []
## loop trough intents.json to get data & word roots with stemming ##
for intent in data["intents"]:
for pattern in intent["patterns"]:
words_ex = nltk.word_tokenize(pattern)
words.extend(words_ex)
docs_x.append(words_ex)
docs_y.append(intent["group"])
if intent["group"] not in labels:
labels.append(intent["group"])
words = [stemmer.stem(w.lower()) for w in words if w not in "?"]
# remove duplicate elements
words = sorted(list(set(words)))
labels = sorted(labels)
training = []
output = []
out_empty = [0 for _ in range(len(labels))]
# create bag of words if word exist put 1 if not put 0
for x, doc in enumerate(docs_x):
bag = []
words_ex = [stemmer.stem(w.lower()) for w in doc]
for w in words:
if w in words_ex:
bag.append(1)
else:
bag.append(0)
output_row = out_empty[:]
output_row[labels.index(docs_y[x])] = 1
training.append(bag)
output.append(output_row)
# create numpy arrays for training
training = np.array(training)
output = np.array(output)
with open("data.pickle", "wb") as f:
pickle.dump((words, labels, training, output), f)
## training model neural network taking in bag of words outputs label & group response##
tensorflow.reset_default_graph()
# lenght of the training model
net = tflearn.input_data(shape=[None, len(training[0])])
# neuron hidden layers
net = tflearn.fully_connected(net, 8)
net = tflearn.fully_connected(net, 8)
# output layer with softmax activation (probability)
net = tflearn.fully_connected(net, len(output[0]), activation="softmax")
net = tflearn.regression(net)
model = tflearn.DNN(net)
# if True train the model if False use existing one
if TRAIN_MODEL == False:
model.load("model.tflearn")
# otherwise construct the model
else:
model.fit(training, output, n_epoch=1000, batch_size=8, show_metric=True)
model.save("model.tflearn")
# generate & convert BoW to numpy array
def bag_of_words(s, words):
bag = [0 for _ in range(len(words))]
s_words = nltk.word_tokenize(s)
s_words = [stemmer.stem(word.lower()) for word in s_words]
# generate BoW
for sw in s_words:
for i, w in enumerate(words):
if w == sw:
bag[i] = 1
return np.array(bag)
# function to ask user for questions
def talk():
print("Chippy is happy to help you with all you need. Just ask a question! (type quit to exit the chat)")
while True:
ip = input("You: ")
if ip.lower() == "quit":
break
# predict the group of which the question belongs to
results = model.predict([bag_of_words(ip, words)])[0]
results_index = np.argmax(results)
group = labels[results_index]
# if probability over 70% answer the question
if results[results_index] > 0.7:
for grp in data["intents"]:
if grp['group'] == group:
responses = grp["responses"]
print(random.choice(responses))
else:
print("Sorry I don't understand, try again.")
# pick matching response
# for grp in data["intents"]:
# if grp['group'] == group:
# responses = grp["responses"]
# print(random.choice(responses))
# else:
# print("I didn't get that.")
# print(random.choice(responses))
talk()