from google.colab import drive
drive.mount('/content/drive')
import nltk

nltk.download('punkt')
nltk.download('wordnet')

import json
import random
import numpy as np
import nltk
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.optimizers import SGD
from sklearn.preprocessing import LabelEncoder
from nltk.stem import WordNetLemmatizer

file_path = '/content/drive/MyDrive/Colab_Notebooks/Dataset/intents.json'
with open(file_path,'r') as file:
    data = json.load(file)

lemmatizer = WordNetLemmatizer()
words = []
classes = []
documents = []
ignore_words = ['?', '!', '.']

for intent in data['intents']:
    for pattern in intent['patterns']:
        # Tokenize each word
        word_list = nltk.word_tokenize(pattern)
        words.extend(word_list)
        documents.append((word_list, intent['tag']))
        if intent['tag'] not in classes:
            classes.append(intent['tag'])

words = [lemmatizer.lemmatize(w.lower()) for w in words if w not in ignore_words]
words = sorted(list(set(words)))
classes = sorted(list(set(classes)))

training = []
output_empty = [0] * len(classes)

for doc in documents:
    bag = []
    word_patterns = doc[0]
    word_patterns = [lemmatizer.lemmatize(word.lower()) for word in word_patterns]
    for w in words:
        bag.append(1 if w in word_patterns else 0)
    
    output_row = list(output_empty)
    output_row[classes.index(doc[1])] = 1
    training.append([bag, output_row])
    
random.shuffle(training)
training = np.array(training, dtype=object)

train_x = np.array(list(training[:, 0]))
train_y = np.array(list(training[:, 1]))

model = Sequential()
model.add(Dense(128, input_shape=(len(train_x[0]),), activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(len(train_y[0]), activation='softmax'))

sgd = SGD(learning_rate=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])

hist = model.fit(train_x, train_y, epochs=200, batch_size=5, verbose=1)
model.save('chatbot_model.h5', hist)

print("Model created and saved successfully!")

import tensorflow as tf
model = tf.keras.models.load_model('chatbot_model.h5')

def clean_up_sentence(sentence):
    sentence_words = nltk.word_tokenize(sentence)
    sentence_words = [lemmatizer.lemmatize(word.lower()) for word in sentence_words]
    return sentence_words

def bag_of_words(sentence, words):
    sentence_words = clean_up_sentence(sentence)
    bag = [0] * len(words)
    for s in sentence_words:
        for i, w in enumerate(words):
            if w == s:
                bag[i] = 1
    return np.array(bag)

def predict_class(sentence, model):
    bow = bag_of_words(sentence, words)
    res = model.predict(np.array([bow]))[0]
    ERROR_THRESHOLD = 0.25
    results = [[i, r] for i, r in enumerate(res) if r > ERROR_THRESHOLD]

    results.sort(key=lambda x: x[1], reverse=True)
    return_list = [{"intent": classes[r[0]], "probability": str(r[1])} for r in results]
    return return_list

def get_response(intents_list, intents_json):
    tag = intents_list[0]['intent']
    for i in intents_json['intents']:
        if i['tag'] == tag:
            return random.choice(i['responses'])

print("Bot is ready to chat! Type 'quit' to stop.")
while True:
    message = input("You: ")
    if message.lower() == "quit":
        break

    ints = predict_class(message, model)
    if ints:
        res = get_response(ints, data)
        print("Bot:", res)
    else:
        print("Bot: Sorry, I don't understand that.")\