Update app.py

app.py

@@ -2,8 +2,17 @@ import gradio as gr
 import numpy as np
 import joblib
 import re
+import nltk
+from nltk.corpus import stopwords
 from sentence_transformers import SentenceTransformer
-from sklearn.feature_extraction.text import ENGLISH_STOP_WORDS
+
+# === Pastikan stopwords tersedia ===
+try:
+    stopwords.words("english")
+except LookupError:
+    nltk.download("stopwords")
+
+stop_words = set(stopwords.words("english"))
 
 # === Load SentenceTransformer ===
 st_model = SentenceTransformer("sentence-transformers/all-mpnet-base-v2")
@@ -18,7 +27,7 @@ def preprocess_text(text: str) -> str:
     text = text.lower()
     text = re.sub(r"\r\n", " ", text)
     text = re.sub(r"[^a-z\s]", "", text)
-    tokens = [w for w in text.split() if w not in ENGLISH_STOP_WORDS]
+    tokens = [w for w in text.split() if w not in stop_words]
     return " ".join(tokens)
 
 # === Prediction function ===
@@ -47,7 +56,7 @@ def predict(text: str, normalize: bool = True):
 # === Gradio UI ===
 with gr.Blocks() as demo:
     gr.Markdown("# Essay Scoring Demo (Embedding + XGBoost)")
-    gr.Markdown("Masukkan teks → embedding dengan `all-mpnet-base-v2` → prediksi 4 skor dengan model XGBoost.")
+    gr.Markdown("Masukkan teks → preprocessing (pakai NLTK stopwords) → embedding → prediksi skor.")
 
     with gr.Row():
         text_in = gr.Textbox(label="Input Kalimat / Essay", placeholder="Tulis di sini...", lines=5)