MachineLearning_Projects/response.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
# imports

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

# things needed from Tensorflow
import numpy as np
import tflearn
import tensorflow as tf
import random

import argparse

# initiate parser
parser = argparse.ArgumentParser()

# add long and short argument
parser.add_argument("--question", "-q", help="question for chatbot")
# read arguments from the command line
args = parser.parse_args()


# restore all saved 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']

# import our chat-bot intents file
import json
with open('intents.json') as json_data:
    intents = json.load(json_data)

# 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')


def clean_up_sentence(sentence):
    # tokenize the pattern s
    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("is your shop open today?", words)
#print (p)
#print (classes)


ERROR_THRESHOLD = 0.25
def classify(sentence):
    # import the trained model
    model.load('./model.tflearn')
    # generate probabilities from the model
    results = model.predict([bow(sentence, words)])[0]
    # filter out predictions below a threshold
    results = [[i,r] for i,r in enumerate(results) if r>ERROR_THRESHOLD]
    # sort by strength of probability
    results.sort(key=lambda x: x[1], reverse=True)
    return_list = []
    for r in results:
        return_list.append((classes[r[0]], r[1]))
    # return tuple of intent and probability
    return return_list

def response(sentence, userID='123', show_details=False):
    results = classify(sentence)
    # if we have a classification then find the matching intent tag
    if results:
        # loop as long as there are matches to process
        while results:
            for i in intents['intents']:
                # find a tag matching the first result
                if i['tag'] == results[0][0]:
                    # a random response from the intent
                    return print(random.choice(i['responses']))

            results.pop(0)

if args.question:
    print (response(args.question))