-
Notifications
You must be signed in to change notification settings - Fork 0
/
_load_model.py
119 lines (89 loc) · 3.09 KB
/
_load_model.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
import tensorflow as tf
import numpy
import nltk
from nltk.stem.lancaster import LancasterStemmer
stemmer = LancasterStemmer()
import tflearn
import json
import pickle
import random
PATH_TO_DATASET = "model_ml/dataset.json"
PATH_TO_DATAPKL = "model_ml/model/data.pickle"
PATH_TO_MODEL = "model_ml/model/model.tflearn"
def load_model():
with open(PATH_TO_DATASET) as file:
data = json.load(file)
try:
with open(PATH_TO_DATAPKL, "rb") as f:
words, labels, training, output = pickle.load(f)
except:
words = []
labels = []
docs_x = []
docs_y = []
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["tag"])
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.lower()) 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)
with open(PATH_TO_DATAPKL, "wb") as f:
pickle.dump((words, labels, training, output), f)
tf.compat.v1.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.load(PATH_TO_MODEL)
return [model,data,words,labels]
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]
for se in s_words:
for i, w in enumerate(words):
if w == se:
bag[i] = 1
return numpy.array(bag)
model,data,words,labels=load_model()
def chat(query):
results = model.predict([bag_of_words(query, words)])[0]
print(results)
results_index = numpy.argmax(results)
tag = labels[results_index]
if results[results_index]>0.9:
print(results[results_index])
for tg in data["intents"]:
if tg['tag'] == tag:
responses = tg['responses']
output = random.choice(responses)
if tag=="FILE_CREATION":
output=(random.choice(responses))
return output
else:
return "supposed to be google"
print(chat(input(": ")))