text ANN functions

text_ANN_part5

import numpy as np
import time

# compute sigmoid nonlinearity
def sigmoid(x):
    output = 1/(1+np.exp(-x))
    return output

# convert output of sigmoid function to its derivative
def sigmoid_output_to_derivative(output):
    return output*(1-output)
 
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))

def think(sentence, show_details=False):
    x = bow(sentence.lower(), words, show_details)
    if show_details:
        print ("sentence:", sentence, "\n bow:", x)
    # input layer is our bag of words
    l0 = x
    # matrix multiplication of input and hidden layer
    l1 = sigmoid(np.dot(l0, synapse_0))
    # output layer
    l2 = sigmoid(np.dot(l1, synapse_1))
    return l2