text ANN bag of words setup

text_ANN_part4

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

# training set, bag of words for each sentence
for doc in documents:
    # initialize our bag of words
    bag = []
    # list of tokenized words for the pattern
    pattern_words = doc[0]
    # stem each word
    pattern_words = [stemmer.stem(word.lower()) for word in pattern_words]
    # create our bag of words array
    for w in words:
        bag.append(1) if w in pattern_words else bag.append(0)

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

# sample training/output
i = 0
w = documents[i][0]
print ([stemmer.stem(word.lower()) for word in w])
print (training[i])
print (output[i])