import tensorflow as tf
import pandas as pd
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import LSTM
from tensorflow.keras.layers import Embedding
from tensorflow.keras.preprocessing import sequence
from sklearn.model_selection import train_test_split

import pickle

dataset = pd.read_csv(r"C:\Users\Ajitha V\OneDrive\Desktop\Neural_network\IMDB Dataset.csv")

dataset['sentiment'] = dataset['sentiment'].map( {'negative': 1, 'positive': 0} )
X = dataset['review'].values
y = dataset['sentiment'].values

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
tokeniser = tf.keras.preprocessing.text.Tokenizer()
tokeniser.fit_on_texts(X_train)
X_train = tokeniser.texts_to_sequences(X_train)
X_test = tokeniser.texts_to_sequences(X_test)
print(X_train[0:2])

vocab_size = len(tokeniser.word_index)+1

max_review_length = 500
X_train = sequence.pad_sequences(X_train, maxlen=max_review_length)
X_test = sequence.pad_sequences(X_test, maxlen=max_review_length)

embedding_vector_length = 32
model = Sequential()
model.add(Embedding(vocab_size, embedding_vector_length, input_length=max_review_length))
model.add(LSTM(100))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(X_train, y_train, epochs=3, batch_size=64)

scores = model.evaluate(X_test, y_test, verbose=0)
print("Accuracy: %.2f%%" % (scores[1]*100))

model.save("lstm_model.h5")
with open("lstm_tokeniser.pkl",'wb') as file:
    pickle.dump(tokeniser, file)