import streamlit as st
import joblib
import re

# Load model & vectorizer
model = joblib.load("model_nb.pkl")
vectorizer = joblib.load("tfidf_vectorizer.pkl")

st.title("📰 Klasifikasi Topik Berita (NLP)")
st.write("Masukkan teks berita berbahasa Indonesia")

text = st.text_area("Teks Berita", height=200)

def preprocess_text(text):
    text = text.lower()
    text = re.sub(r"http\S+", "", text)
    text = re.sub(r"[^a-zA-Z\s]", " ", text)
    text = re.sub(r"\s+", " ", text).strip()
    return text

if st.button("Klasifikasikan"):
    if text.strip() == "":
        st.warning("Teks tidak boleh kosong!")
    else:
        clean_text = preprocess_text(text)
        text_tfidf = vectorizer.transform([clean_text])
        prediction = model.predict(text_tfidf)[0]
        st.success(f"Prediksi Topik: **{prediction}**")