def populate_sub_words_recursive(thin_structure_words,
depth=6,
_current_depth=0,
root_value=None):
print 'populate sub words recursive {}/{}'.format(_current_depth, depth)
words = populate_sub_words(thin_structure_words, allow_fetch=False)
if _current_depth >= depth:
print 'kill depth'
return words
for word_result in words:
if 'words' in word_result['meta']:
print 'recursive inspection of', len(word_result['meta'])
_words = populate_sub_words_recursive(
word_result['meta'],
depth=depth,
_current_depth=_current_depth + 1,
root_value=root_value,
)
words.extend(_words)
return words
import tensorflow
import random
import json
with open('vendor.json') as file:
data = json.load(file)
words = []
labels = []
docs_x = []
docs_y = []
for intent in data['intents']:
for pattern in intent["patterns"]:
wrds = nltk.word_tokenize(pattern)
words.extend(wrds)
docs_x.append(wrds)
docs_y.append(intent["tag"])
if intent['tag'] not in labels:
labels.append(intent['tag'])
words = [stemmer.stem(w.lower()) for w in words if w != "?"] #convert all cases in small later and convert the words into roots or base form and remove unwanted character
words = sorted(list(set(words))) #remove the duplicate words
# labels = sorted(labels) #remove the duplicate classes
training = []
output = []
out_empty = [0 for _ in range(len(labels))]