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

lemmatizer = WordNetLemmatizer()

# Load the intents file
with open('intents.json') as json_file:
    intents = json.load(json_file)

# Initialize lists
words = []
classes = []
documents = []
ignore_words = ['?', '!']

# Process the intents
for intent in intents['intents']:
    for pattern in intent['patterns']:
        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)))

pickle.dump(words, open('words.pkl', 'wb'))
pickle.dump(classes, open('classes.pkl', 'wb'))

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

# Debugging: Print lengths of words and classes
print(f'Number of words: {len(words)}')
print(f'Number of classes: {len(classes)}')

for doc in documents:
    bag = []
    pattern_words = doc[0]
    pattern_words = [lemmatizer.lemmatize(word.lower()) for word in pattern_words]
    for word in words:
        bag.append(1) if word in pattern_words else bag.append(0)
    output_row = list(output_empty)
    output_row[classes.index(doc[1])] = 1
    training.append([bag, output_row])

# Debugging: Check for inconsistencies in training data
for i, t in enumerate(training):
    if len(t[0]) != len(words):
        print(f'Inconsistent length in training data at index {i}: {len(t[0])} != {len(words)}')

random.shuffle(training)
training = np.array(training, dtype=object)

# Debugging: Print shape of training data
print(f'Training data shape: {training.shape}')

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

# Debugging: Print shapes of train_x and train_y
print(f'Shape of train_x: {np.array(train_x).shape}')
print(f'Shape of train_y: {np.array(train_y).shape}')

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(np.array(train_x), np.array(train_y), epochs=200, batch_size=5, verbose=1)
model.save('chatbotmodel.h5', hist)

print("Model trained and saved.")