-
Notifications
You must be signed in to change notification settings - Fork 1
/
training.py
100 lines (75 loc) · 3.04 KB
/
training.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
import random
import json
import pickle
import numpy as np
import nltk
from nltk.stem import WordNetLemmatizer
# type: ignore
from tensorflow.keras.models import Sequential
# type: ignore
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.optimizers import SGD
# type: ignore
from repository import find_all_intents_for_train
from sqlalchemy.orm import Session
def train(db: Session):
lemmatizer = WordNetLemmatizer()
intents = find_all_intents_for_train(db)
words = []
classes = []
documents = []
ignore_letters = ['?', '!', '.', ',']
for intent in intents:
for pattern in intent.patterns:
# tokenize = splits up sentences into words
word_list = nltk.word_tokenize(pattern)
words.extend(word_list)
# (word_list) is a tuple. Tuple: stores multiple items into a single variable
# (word_list) belongs to the category intent['tag']
documents.append((word_list, intent.tag))
# check if the class is in the classes list
if intent.tag not in classes:
classes.append(intent.tag)
words = [lemmatizer.lemmatize(word)
for word in words if word not in ignore_letters]
words = sorted(set(words))
classes = sorted(set(classes))
pickle.dump(words, open('generated/words.pkl', 'wb'))
pickle.dump(classes, open('generated/classes.pkl', 'wb'))
training = []
output_empty = [0] * len(classes)
for document in documents:
bag = []
word_patterns = document[0]
word_patterns = [lemmatizer.lemmatize(
word.lower()) for word in word_patterns]
for word in words:
bag.append(1) if word in word_patterns else bag.append(0)
output_row = list(output_empty)
output_row[classes.index(document[1])] = 1
training.append([bag, output_row])
max_length = max(len(x) for x, y in training)
for i, (x, y) in enumerate(training):
padding_length = max_length - len(x)
if padding_length > 0:
x = x + [0] * padding_length
padding_length = max_length - len(y)
if padding_length > 0:
y = y + [0] * padding_length
# Update the training list with the padded elements
training[i] = (x, y)
random.shuffle(training)
training = np.array(training)
train_x = list(training[:, 0])
train_y = list(training[:, 1])
model = Sequential()
model.add(Dense(128, input_shape=(len(train_x[0]),), activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(len(train_y[0]), activation='softmax'))
sgd = SGD(learning_rate=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
hist = model.fit(np.array(train_x), np.array(train_y), epochs = 200, batch_size=5, verbose=1)
model.save('generated/chatbotmodel.keras', hist)
return {'message': 'Model trained successfully!'}