├── README.md
├── intents.json
├── chatbot.py
└── new.py


/README.md:
--------------------------------------------------------------------------------
1 | # create_chatbot_using_python
2 | This code is an implementation of a simple chatbot using TensorFlow, which is a machine learning framework developed by Google. The chatbot is trained using a neural network to classify user inputs into predefined intents and provide appropriate responses based on the detected intent.
3 | The intents.json file is the data that we will provide to our chatbot 
4 | 


--------------------------------------------------------------------------------
/intents.json:
--------------------------------------------------------------------------------
 1 | {"intents": [
 2 |         {"tag": "greeting",
 3 |          "patterns": ["Hi there", "How are you", "Is anyone there?","Hey","Hola", "Hello", "Good day"],
 4 |          "responses": ["Hello", "Good to see you again", "Hi there, how can I help?"],
 5 |          "context": [""]
 6 |         },
 7 |         {"tag": "goodbye",
 8 |          "patterns": ["Bye", "See you later", "Goodbye", "Nice chatting to you, bye", "Till next time"],
 9 |          "responses": ["See you!", "Have a nice day", "Bye! Come back again soon."],
10 |          "context": [""]
11 |         },
12 |         {"tag": "thanks",
13 |          "patterns": ["Thanks", "Thank you", "That's helpful", "Awesome, thanks", "Thanks for helping me"],
14 |          "responses": ["My pleasure", "You're Welcome"],
15 |          "context": [""]
16 |         },
17 |         {"tag": "query",
18 |          "patterns": ["What is Simplilearn?"],
19 |          "responses": ["Simplilearn is the popular online Bootcamp & online courses learning platform "],
20 |          "context": [""]
21 |         } 
22 |     ]}


--------------------------------------------------------------------------------
/chatbot.py:
--------------------------------------------------------------------------------
 1 | import random
 2 | import json
 3 | import pickle
 4 | import numpy as np
 5 | import nltk
 6 | 
 7 | from nltk.stem import WordNetLemmatizer
 8 | from keras.models import load_model
 9 | 
10 | lemmatizer = WordNetLemmatizer()
11 | intents = json.loads(open('C:\Simplilearn\Python\Python projects\chatbot using python\chatbot\intents.json').read())
12 | 
13 | words = pickle.load(open('words.pkl', 'rb'))
14 | classes = pickle.load(open('classes.pkl', 'rb'))
15 | model = load_model('chatbot_model.h5')
16 | 
17 | 
18 | def clean_up_sentence(sentence):
19 |     sentence_words = nltk.word_tokenize(sentence)
20 |     sentence_words = [lemmatizer.lemmatize(word) for word in sentence_words]
21 |     return sentence_words
22 | 
23 | def bag_of_words (sentence):
24 |     sentence_words = clean_up_sentence(sentence)
25 |     bag = [0] * len(words)
26 |     for w in sentence_words:
27 |         for i, word in enumerate(words):
28 |             if word == w:
29 |                 bag[i] = 1
30 |     return np.array(bag)
31 | 
32 | def predict_class (sentence):
33 |     bow = bag_of_words (sentence)
34 |     res = model.predict(np.array([bow]))[0]
35 |     ERROR_THRESHOLD = 0.25
36 |     results = [[i, r] for i, r in enumerate(res) if r > ERROR_THRESHOLD]
37 | 
38 |     results.sort(key=lambda x: x[1], reverse=True)
39 |     return_list = []
40 |     for r in results:
41 |         return_list.append({'intent': classes [r[0]], 'probability': str(r[1])})
42 |     return return_list
43 | 
44 | def get_response(intents_list, intents_json):
45 |     tag = intents_list[0]['intent']
46 |     list_of_intents = intents_json['intents']
47 |     for i in list_of_intents:
48 |         if i['tag'] == tag:
49 |             result = random.choice (i['responses'])
50 |             break
51 |     return result
52 | 
53 | print("GO! Bot is running!")
54 | 
55 | while True:
56 |     message = input("")
57 |     ints = predict_class (message)
58 |     res = get_response (ints, intents)
59 |     print (res)
60 |     


--------------------------------------------------------------------------------
/new.py:
--------------------------------------------------------------------------------
 1 | import random
 2 | import json
 3 | import pickle
 4 | import numpy as np
 5 | import tensorflow as tf
 6 | 
 7 | import nltk
 8 | from nltk.stem import WordNetLemmatizer
 9 | 
10 | lemmatizer = WordNetLemmatizer()
11 | 
12 | intents = json.loads(open('C:\Simplilearn\Python\Python projects\chatbot using python\chatbot\intents.json').read())
13 | 
14 | words = []
15 | classes = []
16 | documents = []
17 | ignoreLetters = ['?', '!', '.', ',']
18 | 
19 | for intent in intents['intents']:
20 |     for pattern in intent['patterns']:
21 |         wordList = nltk.word_tokenize(pattern)
22 |         words.extend(wordList)
23 |         documents.append((wordList, intent['tag']))
24 |         if intent['tag'] not in classes:
25 |             classes.append(intent['tag'])
26 | 
27 | words = [lemmatizer.lemmatize(word) for word in words if word not in ignoreLetters]
28 | words = sorted(set(words))
29 | 
30 | classes = sorted(set(classes))
31 | 
32 | pickle.dump(words, open('words.pkl', 'wb'))
33 | pickle.dump(classes, open('classes.pkl', 'wb'))
34 | 
35 | training = []
36 | outputEmpty = [0] * len(classes)
37 | 
38 | for document in documents:
39 |     bag = []
40 |     wordPatterns = document[0]
41 |     wordPatterns = [lemmatizer.lemmatize(word.lower()) for word in wordPatterns]
42 |     for word in words:
43 |         bag.append(1) if word in wordPatterns else bag.append(0)
44 | 
45 |     outputRow = list(outputEmpty)
46 |     outputRow[classes.index(document[1])] = 1
47 |     training.append(bag + outputRow)
48 | 
49 | random.shuffle(training)
50 | training = np.array(training)
51 | 
52 | trainX = training[:, :len(words)]
53 | trainY = training[:, len(words):]
54 | 
55 | 
56 | model = tf.keras.Sequential()
57 | model.add(tf.keras.layers.Dense(128, input_shape=(len(trainX[0]),), activation = 'relu'))
58 | model.add(tf.keras.layers.Dropout(0.5))
59 | model.add(tf.keras.layers.Dense(64, activation = 'relu'))
60 | model.add(tf.keras.layers.Dropout(0.5))
61 | model.add(tf.keras.layers.Dense(len(trainY[0]), activation='softmax'))
62 | 
63 | sgd = tf.keras.optimizers.SGD(learning_rate=0.01, momentum=0.9, nesterov=True)
64 | model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
65 | 
66 | hist = model.fit(np.array(trainX), np.array(trainY), epochs=200, batch_size=5, verbose=1)
67 | model.save('chatbot_model.h5', hist)
68 | print('Done')
69 | 
70 | 
71 | 
72 | 


--------------------------------------------------------------------------------