Open-Chat-Bot/main.py at main · upes-open/Open-Chat-Bot · GitHub

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
import nltk
from nltk.stem.lancaster import LancasterStemmer
stemmer=LancasterStemmer()


import numpy
import tflearn
import random
import json
import tensorflow

with open("intents.json") as file:
  data=json.load(file)
words=[]
labels=[]
docs=[]
docs_y=[]
docs_x=[]

for intent in data["intents"]:
  for pattern in intent["patterns"]:
    wrds=nltk.word_tokenize(pattern)
    words.extend(wrds)
    docs_x.append(wrds)
    docs_y.append(intent["tag"])

    if intent["tag"] not in labels:
      labels.append(intent["tags"])

words=[stemmer.stem(w.lower()) for w in words if w !="?"]
words=sorted(list(set(words)))

labels=sorted(labels)
training=[]
output=[]

out_empty=[0 for _ in range(len(labels))]
for x, doc in enumerate(docs_x):
  bag=[]
  wrds=[stemmer.stem(w) for w in doc]

  for w in words:
    if w in wrds:
      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)

training=numpy.array(training)
output= numpy.array(output)

training=numpy.array(training)
output=numpy.array(output)

tensorflow.reset_default_graph()

net=tflearn.input_data(shape=[None,len(training[0])])
net=tflearn.fully_connected(net,8)
net=tflearn.fully_connected(net,8)
net=tflearn.fully_connected(net,len(output[0]),activation="softmax")
net=tflearn.regression(net)
model=tflearn.DNN(net)
model.fit(training,output,n_epoch=100,box_size=8,show_metric=True)
model.save("model.tfearn")