import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Embedding, LSTM, Dense
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
import numpy as np
import pandas as pd

df = pd.read_csv("data/movie_reviews.csv")
texts = df['review'].values
labels = df['sentiment'].values

tokenizer = Tokenizer(num_words=5000)
tokenizer.fit_on_texts(texts)
sequences = tokenizer.texts_to_sequences(texts)
X = pad_sequences(sequences, maxlen=100)
y = labels

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

model = Sequential([
    Embedding(input_dim=5000, output_dim=128, input_length=100),
    LSTM(64, return_sequences=False),
    Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
model.fit(X_train, y_train, epochs=5, batch_size=32, validation_data=(X_test, y_test))

loss, accuracy = model.evaluate(X_test, y_test)
print(f"Test Accuracy: {accuracy * 100:.2f}%")