chatapp.py

import nltk
from nltk.stem import WordNetLemmatizer
lemmatizer = WordNetLemmatizer()
import pickle
import numpy as np
from keras.models import load_model
import json
import random
import os
#below is needed for windows local run add dotenv to requirement.txt if running locally.
#from dotenv import load_dotenv
#load_dotenv()

DEEP_LINKING = os.environ.get('DEEP_LINKING')
model = load_model('chatbot_model.h5')
intents = json.loads(open('intents.json').read())
words = pickle.load(open('words.pkl', 'rb'))
classes = pickle.load(open('classes.pkl', 'rb'))
noAnswerEN = ["I'm sorry I don't understand.",
                "Could you phrase that differently for me?",
                "Not sure I understand."]
noAnswerFR = ["Je suis d\u00e9sol\u00e9, je n'ai pas compris.",
                "Pourriez-vous formuler cela autrement pour moi?",
                "Je ne suis pas certain de comprendre."]
def clean_up_sentence(sentence):
    # tokenize the pattern - split words into array
    sentence_words = nltk.word_tokenize(sentence)
    # stem each word - create short form for word
    sentence_words = [lemmatizer.lemmatize(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=True):
    # tokenize the pattern
    sentence_words = clean_up_sentence(sentence)
    # bag of words - matrix of N words, vocabulary matrix
    bag = [0]*len(words)
    for s in sentence_words:
        for i, w in enumerate(words):
            if w == s:
                # assign 1 if current word is in the vocabulary position
                bag[i] = 1
                if show_details:
                    print("found in bag: %s" % w)
    return(np.array(bag))

def predict_class(sentence, model):
    # filter out predictions below a threshold
    p = bow(sentence, words, show_details=False)
    res = model.predict(np.array([p]))[0]
    ERROR_THRESHOLD = 0.33
    results = [[i, r] for i, r in enumerate(res) 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({"intent": classes[r[0]], "probability": str(r[1])})
    return return_list

def getResponse(ints, intents_json):
    print(ints)
    tag = ints[0]['intent']
    list_of_intents = intents_json['intents']
    for i in list_of_intents:
        if( i['tag'] == tag):
            result = random.choice(i['responses'])
            break
    return result

def chatbot_response(lang,text):
    ints = predict_class(text.lower(), model)
    if not ints:
        res = ""
    else:
        res = getResponse(ints, intents)
    if res == "":
        if lang == "en":
            res = random.choice(noAnswerEN)
        else:
            res = random.choice(noAnswerFR)
    else:
        res = res.replace('workbc-test', DEEP_LINKING)
    print(res)
    return res