nahidalam

class ActionOrderProduct(Action):
	def name(self):
		return 'action_order_product'

	def run(self, dispatcher, tracker, domain):
    
		router = tracker.get_slot('router')
		confirmationNumber = 123456 #later generate through some process

		response = """Your product {} is ordered for you. It will be shipped to your address. Your confirmation number is {}""".format(router, confirmationNumber)

nahidalam

def train_nlu(data, configuration, model_dir):
	training_data = load_data(data)
	trainer = Trainer(config.load(configuration))
	trainer.train(training_data)
	model_directory = trainer.persist(model_dir, fixed_model_name = 'customernlu')
	return model_directory

nahidalam

def train_dialogue(domain_file = 'customer_domain.yml',
					model_path = './models/dialogue',
					training_data_file = './data/stories.md'):

	agent = Agent(domain_file, policies = [MemoizationPolicy(), KerasPolicy()])

	agent.train(
				training_data_file,
				epochs = 300,
				batch_size = 50,

nahidalam

def EmbeddingRec(EMBEDDING_SIZE, NUM_MOVIES, NUM_USERS, ROW_COUNT):
    movie_input = keras.Input(shape=(1,), name='movie_id')

    movie_emb = layers.Embedding(output_dim=EMBEDDING_SIZE, input_dim=NUM_MOVIES, input_length=ROW_COUNT, name='movie_emb')(movie_input)
    movie_vec = layers.Flatten(name='FlattenMovie')(movie_emb)

    movie_model = keras.Model(inputs=movie_input, outputs=movie_vec)
    
    user_input = keras.Input(shape=(1,), name='user_id')

nahidalam

#lets assume an user ID 200
TEST_USER_ID = 200
#get the embedding of this user
user_embedding = user_model.predict([TEST_USER_ID]).reshape(1,-1)[0]

#create the KNN model
from sklearn.neighbors import KNeighborsClassifier
clf = KNeighborsClassifier(n_neighbors=11)
clf.fit(MOVIE_EMBEDDING_LIST, knn_train_label)

nahidalam

contraction_map = {"ain't": "is not", "aren't": "are not","can't": "cannot", "'cause": "because", "could've": "could have", "couldn't": "could not",

                           "didn't": "did not", "doesn't": "does not", "don't": "do not", "hadn't": "had not", "hasn't": "has not", "haven't": "have not",

                           "he'd": "he would","he'll": "he will", "he's": "he is", "how'd": "how did", "how'd'y": "how do you", "how'll": "how will", "how's": "how is",

                           "I'd": "I would", "I'd've": "I would have", "I'll": "I will", "I'll've": "I will have","I'm": "I am", "I've": "I have", "i'd": "i would",

                           "i'd've": "i would have", "i'll": "i will",  "i'll've": "i will have","i'm": "i am", "i've": "i have", "isn't": "is not", "it'd": "it would",

nahidalam

import pandas as pd
import numpy as np
import json
import os, glob

from __future__ import unicode_literals, print_function, division
from io import open
import unicodedata
import string
import re

nahidalam

'''
Reusable set of functions to convert a tuple of strings (pair) to tensors
Reference: https://pytorch.org/tutorials/intermediate/seq2seq_translation_tutorial.html
'''

import torch

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

def indexesFromSentence(lang, sentence):

nahidalam

from rouge_score import rouge_scorer


def read_input(filename = 'evaluation_input.txt'):
    input_pair = []
    # read evaluation_input.txt
    # append each line to input_pair
    return input_pair

nahidalam

class Encoder(tf.keras.Model):
    def __init__(self, vocab_size, embedding_dim, enc_units, batch_sz):
        '''
        vocab_size: number of unique words
        embedding_dim: dimension of your embedding output
        enc_units: how many units of RNN cell
        batch_sz: batch of data passed to the training in each epoch
        '''
        super(Encoder, self).__init__()
        self.batch_sz = batch_sz