predict.py

def get_tf_record(sentence):
    global words
    # tokenize the pattern
    sentence_words = nltk.word_tokenize(sentence)
    # stem each word
    sentence_words = [stemmer.stem(word.lower()) for word in sentence_words]
    # bag of words
    bow = [0]*len(words)
    for s in sentence_words:
        for i, w in enumerate(words):
            if w == s:
                bow[i] = 1

    return(np.array(bow))
  
  with open("./test_data.json", "r") as ins:
    array = []
    for line in ins:
        array.append(line)
   
  for line in array:
    jdata = json.loads(line)
    predict_score = categories[np.argmax(model.predict([get_tf_record(jdata['review'])]))]
    real_score = int(jdata['score'])
    print (real_score, predict_score)