Machine Learning Projects

Public·2 members

January 16, 2020

Mahine Learning Project Help - Chatbot Using Python NLTK

Creating Chatbot Using Python NLTK

What is a chatbot?

A chatbot is an intelligent piece of software that is capable of communicating and performing actions similar to a human. Chatbots are used a lot in customer interaction, marketing on social network sites and instant messaging the client.

Import Packages

First import all the packages related to chatbot

Importing all the related libraries

#import all libraries
import nltk
from nltk.stem import WordNetLemmatizer
lemmatizer = WordNetLemmatizer()
import json
import pickle
import numpy as np
from keras.models 
import Sequential
from keras.layers import Dense, Activation, Dropout
from keras.optimizers import SGD
import random

Install all packages related to this

#install packages
pip install tensorflow, keras, pickle, nltk

Load the datasets

#load datasets
words=[]
classes = []
documents = []
ignore_words = ['?', '!']
data_file = open('intents.json').read()
intents = json.loads(data_file)

Preprocess data

for intent in intents['intents']:    
      for pattern in intent['patterns']:
     #tokenize each word       
     w = nltk.word_tokenize(pattern)        
     words.extend(w) 
     #add documents in the corpus        
     documents.append((w, intent['tag'])) 
     # add to our classes list        
     if intent['tag'] not in classes:           
         classes.append(intent['tag'])

Now we will lemmatize each word and remove duplicate words from the list

# lemmatize, lower each word and remove duplicates
words = [lemmatizer.lemmatize(w.lower()) for w in words if w not in ignore_words]
words = sorted(list(set(words)))
# sort classes
classes = sorted(list(set(classes)))
# documents = combination between patterns and intents
print (len(documents), "documents")
# classes = intentsprint (len(classes), "classes", classes)
# words = all words, vocabulary
print (len(words), "unique lemmatized words", words)
pickle.dump(words,open('words.pkl','wb'))
pickle.dump(classes,open('classes.pkl','wb'))

Creating the training and testing data

# create our training data
training = []
# create an empty array for our output
output_empty = [0] * len(classes)
for doc in documents: 
     # initialize our bag of words    
     bag = [] 
     # list of tokenized words for the pattern    
     pattern_words = doc[0]    
     pattern_words = [lemmatizer.lemmatize(word.lower()) for word in pattern_words] 
for w in words:
     bag.append(1) if w in pattern_words else bag.append(0) 
    # output is a '0' for each tag and '1' for current tag (for each pattern)    
    output_row = list(output_empty)    
    output_row[classes.index(doc[1])] = 1    
    training.append([bag, output_row])
# shuffle our features and turn into np.array
random.shuffle(training)
training = np.array(training)
# create train and test lists. X - patterns, Y - intent
strain_x = list(training[:,0])
train_y = list(training[:,1])
print("Training data created")