import gradio as gr
import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import PorterStemmer
from keras.preprocessing.sequence import pad_sequences
import pickle
import tensorflow as tf

try:
    nltk.data.find('corpora/stopwords')
except LookupError:
    nltk.download('stopwords')

try:
    nltk.data.find('tokenizers/punkt/english.pickle')
except LookupError:
    nltk.download('punkt')

try:
    nltk.data.find('tokenizers/punkt_tab/english')
except LookupError:
    nltk.download('punkt_tab')

try:
    with open("movie_sentiment_tokenizer.pkl", "rb") as handle:
        tokenizer = pickle.load(handle)
except FileNotFoundError:
    raise FileNotFoundError("Tokenizer file not found. Make sure 'moviee_sentiment_tokenizer.pkl' is in the same directory.")

try:
    model = tf.keras.models.load_model("movie_sentiment.h5")
except Exception as e:
    raise RuntimeError(f"Failed to load the model. Make sure 'movie_sentiment.h5' is in the same directory. Error: {e}")

def preprocess_text(text):
    text = text.replace("<br /><br />", "")
    tokens = word_tokenize(text)
    stop_words = set(stopwords.words("english"))
    filtered_tokens = [token.lower() for token in tokens if token.isalpha() and token.lower() not in stop_words]
    stemmer = PorterStemmer()
    stemmed_tokens = [stemmer.stem(token) for token in filtered_tokens]
    return " ".join(stemmed_tokens)

def predict_sentiment(text):
    maxlen = 90
    processed_text = preprocess_text(text)
    seq = tokenizer.texts_to_sequences([processed_text])
    padded = pad_sequences(seq, maxlen=maxlen, padding='post')
    prediction = model.predict(padded)[0][0]

    if prediction > 0.5:

        return {"Positive Review  🤩": prediction, "Negative Review  😥": 1 - prediction}
    else:

        return {"Positive Review  🤩": prediction, "Negative Review  😥": 1 - prediction}


iface = gr.Interface(
    fn=predict_sentiment,
    inputs=gr.Textbox(lines=10, placeholder="Enter a movie review..."),
    outputs=gr.Label(label="Sentiment Prediction"),
    title="Sentiment Analysis on Movie Reviews(Eng)",
    description="Analyze whether a movie review is positive or negative."
)

if __name__ == "__main__":
    iface.launch()