MachineLearning_Projects/chatbotmodel.py at master · siddimore/MachineLearning_Projects · 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
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
158
159
160
161
162
163
164
## things we need for NLP
#Learnt a lot from below link and want to reference it here
#https://chatbotsmagazine.com/contextual-chat-bots-with-tensorflow-4391749d0077
import nltk
nltk.download('punkt')
from nltk.stem.lancaster import LancasterStemmer
stemmer = LancasterStemmer()

# things we need for Tensorflow
import numpy as np
import tflearn
import tensorflow as tf
import random

# import chat-bot intents file
import json

with open('intents.json') as json_data:
    intents = json.load(json_data)


words = []
classes = []
documents = []
ignore_words = ['?']


# Loop through sentence in intents patterns

for intent in intents['intents']:
    for pattern in intent['patterns']:
        # tokenize each word in sentence
        w = nltk.word_tokenize(pattern)
        # add to words list
        words.extend(w)
        # add document in corpus
        documents.append((w,intent['tag']))
        # add to class list
        if intent['tag'] not in classes:
            classes.append(intent['tag'])


# stem and lower each word and duplicates
words = [stemmer.stem(w.lower()) for w in words if w not in ignore_words]
words = sorted(list(set(words)))

# remove duplicates
classes = sorted(list(set(classes)))
print (len(documents), "documents")
print (len(classes), "classes", classes)
print (len(words), "unique stemmed words", words)

# Now create our training data

training = []
output = []

# create empty array for output
output_empty = [0]*len(classes)

# training set, bag of words for each sentence
for doc in documents:
    # initialize our bag of ignore_words
    bag = []
    # list of tokenized words for the patterns
    pattern_words = doc[0]
    # stem each words
    pattern_words = [stemmer.stem(word.lower()) for word in pattern_words]

    #create our bag of words
    for w in words:
        bag.append(1) if w in pattern_words else bag.append(0)

    # output is a '0' for each tag and '1' for current tag
    output_row = list(output_empty)
    output_row[classes.index(doc[1])] = 1

    training.append([bag, output_row])

# shuffle our features and turn into np.array
random.shuffle(training)
training = np.array(training)

# create train and test lists
train_x = list(training[:,0])
train_y = list(training[:,1])


# reset underlying graph data
tf.reset_default_graph()
# Build neural network
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)

# Define model and setup tensorboard
model = tflearn.DNN(net, tensorboard_dir='tflearn_logs')
# Start training (apply gradient descent algorithm)
model.fit(train_x, train_y, n_epoch=1000, batch_size=8, show_metric=True)
model.save('model.tflearn')

# save all of our data structures
import pickle
pickle.dump( {'words':words, 'classes':classes, 'train_x':train_x, 'train_y':train_y}, open( "training_data", "wb" ) )

# restore all of our data structures
import pickle
data = pickle.load( open( "training_data", "rb" ) )
words = data['words']
classes = data['classes']
train_x = data['train_x']
train_y = data['train_y']

# reset underlying graph data
tf.reset_default_graph()
# Build neural network
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)

# Define model and setup tensorboard
model = tflearn.DNN(net, tensorboard_dir='tflearn_logs')
# Start training (apply gradient descent algorithm)
model.fit(train_x, train_y, n_epoch=1000, batch_size=8, show_metric=True)
model.save('model.tflearn')

def clean_up_sentence(sentence):
    # tokenize the pattern
    sentence_words = nltk.word_tokenize(sentence)
    # stem each word
    sentence_words = [stemmer.stem(word.lower()) for word in sentence_words]
    return sentence_words

# return bag of words array: 0 or 1 for each word in the bag that exists in the sentence
def bow(sentence, words, show_details=False):
    # tokenize the pattern
    sentence_words = clean_up_sentence(sentence)
    # bag of words
    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))


# p = bow("do you take cards?", words)
p = bow("Was bowling fun?", words)
print (p)
print (classes)

print(model.predict([p]))

# save all of our data structures
import pickle
pickle.dump( {'words':words, 'classes':classes, 'train_x':train_x, 'train_y':train_y}, open( "training_data", "wb" ) )