Update app.py

app.py

@@ -1,53 +1,77 @@
 import gradio as gr
-from sentence_transformers import SentenceTransformer
 import numpy as np
+import joblib
+import re
+from sentence_transformers import SentenceTransformer
+from sklearn.feature_extraction.text import ENGLISH_STOP_WORDS
 
-# Load model once at startup
+# === Load SentenceTransformer ===
 st_model = SentenceTransformer("sentence-transformers/all-mpnet-base-v2")
 
-TITLE = "# Text → Vector (all-mpnet-base-v2)"
-DESC = (
-    "Masukkan **kalimat** lalu dapatkan **embedding vector** "
-    "(opsional dinormalisasi L2). Model: `sentence-transformers/all-mpnet-base-v2`."
-)
+# === Load trained XGBoost models ===
+models = joblib.load("xgb_models_all.joblib")
 
-def embed(text: str, normalize: bool = True):
+# === Preprocessing function ===
+def preprocess_text(text: str) -> str:
+    if not isinstance(text, str) or text.strip() == "":
+        return ""
+    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]
+    return " ".join(tokens)
+
+# === Prediction function ===
+def predict(text: str, normalize: bool = True):
     text = (text or "").strip()
     if not text:
-        return [], 0
-    vec = st_model.encode([text], normalize_embeddings=normalize)[0]
-    return vec.tolist(), int(vec.shape[0])
+        return {}, [], 0
+    
+    # 1. Preprocess
+    clean_text = preprocess_text(text)
+
+    # 2. Embedding
+    vec = st_model.encode([clean_text], normalize_embeddings=normalize)[0]
 
+    # 3. Tambah fitur essay_length
+    essay_length = len(text)
+    X = np.concatenate([vec, [essay_length]])
+
+    # 4. Prediksi dari semua model
+    results = {}
+    for col, model in models.items():
+        results[col] = float(model.predict(X.reshape(1, -1))[0])
+
+    return results, vec.tolist(), int(vec.shape[0])
+
+# === Gradio UI ===
 with gr.Blocks() as demo:
-    gr.Markdown(TITLE)
-    gr.Markdown(DESC)
+    gr.Markdown("# Essay Scoring Demo (Embedding + XGBoost)")
+    gr.Markdown("Masukkan teks → embedding dengan `all-mpnet-base-v2` → prediksi 4 skor dengan model XGBoost.")
 
     with gr.Row():
-        text_in = gr.Textbox(
-            label="Kalimat",
-            placeholder="Tulis kalimat di sini...",
-            lines=3,
-        )
+        text_in = gr.Textbox(label="Input Kalimat / Essay", placeholder="Tulis di sini...", lines=5)
     normalize = gr.Checkbox(value=True, label="Normalize embedding (L2)")
-    btn = gr.Button("Compute Embedding", variant="primary")
+    btn = gr.Button("Prediksi", variant="primary")
 
     with gr.Row():
-        vec_out = gr.JSON(label="Vector (list of floats)")
+        pred_out = gr.JSON(label="Prediksi Skor (XGBoost)")
+    with gr.Row():
+        vec_out = gr.JSON(label="Embedding Vector (list of floats)")
         dim_out = gr.Number(label="Dimensi vektor", interactive=False)
 
     gr.Examples(
         examples=[
             ["Halo dunia!"],
             ["Machine learning is fun."],
-            ["Saya sedang membangun demo embedding sederhana."],
+            ["This is a sample essay for IELTS task."],
         ],
         inputs=[text_in],
-        label="Contoh",
+        label="Contoh input",
     )
 
-    btn.click(embed, inputs=[text_in, normalize], outputs=[vec_out, dim_out])
+    btn.click(predict, inputs=[text_in, normalize], outputs=[pred_out, vec_out, dim_out])
 
-# Enable queue for concurrency
 demo.queue()
 
 if __name__ == "__main__":