Fix ZeroGPU decorator detection, port 7860 conflict, and sklearn version

app.py

@@ -1,29 +1,22 @@
+import os
 import spaces
 import gradio as gr
-from fastapi import FastAPI, HTTPException
+from fastapi import HTTPException
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
 import joblib
 import pandas as pd
 import numpy as np
-import uvicorn
 
-# --- 1. INISIALISASI FASTAPI & CORS (Wajib agar Frontend bisa akses) ---
-app = FastAPI(title="DETEKS AI API (ZeroGPU)", version="1.0")
-
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],  # Mengizinkan akses dari domain frontend mana saja (Vercel/Localhost)
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-# --- 2. LOAD MODEL AI ---
+# --- 1. LOAD MODEL AI ---
+# Mengecek di root folder atau di dalam folder models/
 MODEL_PATH = "deteks_isolation_forest.pkl"
+if not os.path.exists(MODEL_PATH) and os.path.exists("models/deteks_isolation_forest.pkl"):
+    MODEL_PATH = "models/deteks_isolation_forest.pkl"
+
 try:
     ai_model = joblib.load(MODEL_PATH)
-    print("Model AI berhasil di-load!")
+    print(f"Model AI berhasil di-load dari {MODEL_PATH}!")
 except Exception as e:
     ai_model = None
     print(f"Error loading model: {e}")
@@ -33,22 +26,8 @@ FITUR_AI = [
     'n_event_obat', 'n_faskes_obat', 'qty_30d', 'min_interval', 'overlap_days'
 ]
 
-# --- 3. FUNGSI INFERENSI DENGAN DEKORATOR ZEROGPU (@spaces.GPU) ---
+# --- 2. FUNGSI UTAMA DENGAN @spaces.GPU (Terhubung Langsung ke Gradio) ---
 @spaces.GPU
-def run_ai_inference(features_dict: dict) -> float:
-    """
-    Fungsi inti prediksi anomali yang menggunakan dekorator @spaces.GPU
-    agar memenuhi syarat eksekusi Hugging Face ZeroGPU.
-    """
-    if ai_model is None:
-        raise RuntimeError("Model belum ter-load. Pastikan file .pkl sudah di-upload.")
-    
-    df_input = pd.DataFrame([features_dict])[FITUR_AI]
-    # Semakin negatif score_samples = semakin anomali, kita balik dengan tanda minus (-)
-    raw_score = float(-ai_model.score_samples(df_input)[0])
-    return raw_score
-
-
 def calculate_risk_fusion(
     participant_key: str,
     n_event_kunjungan: float,
@@ -62,6 +41,9 @@ def calculate_risk_fusion(
     overlap_days: float,
     rules_score_tambahan: float = 0.0
 ) -> dict:
+    if ai_model is None:
+        raise RuntimeError("Model belum ter-load. Pastikan file .pkl ada di repositori.")
+
     features_dict = {
         'n_event_kunjungan': float(n_event_kunjungan),
         'n_faskes_kunjungan': float(n_faskes_kunjungan),
@@ -74,24 +56,20 @@ def calculate_risk_fusion(
         'overlap_days': float(overlap_days)
     }
 
-    # Jalankan fungsi ZeroGPU (dengan fallback aman jika dipanggil langsung via REST API)
-    try:
-        raw_score = run_ai_inference(features_dict)
-    except Exception:
-        df_input = pd.DataFrame([features_dict])[FITUR_AI]
-        raw_score = float(-ai_model.score_samples(df_input)[0])
+    df_input = pd.DataFrame([features_dict])[FITUR_AI]
+    raw_score = float(-ai_model.score_samples(df_input)[0])
 
-    # Konversi raw_score Isolation Forest (biasanya di rentang 0.35 - 0.75) ke skala persentil 0-100
+    # Konversi raw_score ke persentil (skala 0 - 100)
     ai_percentile = float(np.clip((raw_score - 0.35) / 0.40 * 100, 0, 100))
 
-    # Hitung Skor Rules & Normalisasi ke skala 0-100
+    # Hitung & Normalisasi Skor Rules (skala 0 - 100)
     total_rules = float(same_day_hits) + float(unbundling_hits) + float(rules_score_tambahan)
     rules_norm = float(min((total_rules / 140.0) * 100, 100.0))
 
-    # Formula Risk Fusion DETEKS: 60% Rules + 40% AI
+    # Risk Fusion (60% Rules + 40% AI)
     review_priority = (0.6 * rules_norm) + (0.4 * ai_percentile)
 
-    # Buat Alasan Terdeteksi (Explainability / Reason Codes)
+    # Reason Codes (Explainability)
     reasons = []
     if same_day_hits > 0:
         reasons.append(f"Kunjungan di hari yang sama ({int(same_day_hits)}x)")
@@ -106,7 +84,6 @@ def calculate_risk_fusion(
     if not reasons:
         reasons.append("Pola terpantau normal / risiko rendah")
 
-    # Tentukan Kategori Risiko (Band)
     if review_priority >= 70:
         status = "Tinggi"
     elif review_priority >= 40:
@@ -127,7 +104,38 @@ def calculate_risk_fusion(
         }
     }
 
-# --- 4. MODEL REQUEST & ENDPOINT FASTAPI ---
+# --- 3. ANTARMUKA GRADIO ---
+with gr.Blocks(title="DETEKS AI Engine") as demo:
+    gr.Markdown("## 🏥 DETEKS - AI Risk Scoring Service (ZeroGPU)")
+    gr.Markdown("Antarmuka uji coba model **Hybrid Rules + Isolation Forest**. Endpoint REST API tersedia di `POST /api/v1/analyze_risk`.")
+    
+    with gr.Row():
+        with gr.Column():
+            p_key = gr.Textbox(label="ID Peserta (participant_key)", value="P-0951")
+            n_ev_kunj = gr.Number(label="Total Kunjungan RJTL (n_event_kunjungan)", value=5)
+            n_fas_kunj = gr.Number(label="Jumlah Faskes Kunjungan (n_faskes_kunjungan)", value=1)
+            same_day = gr.Number(label="Same Day Hits", value=0)
+            unbundling = gr.Number(label="Unbundling Hits", value=1)
+        with gr.Column():
+            n_ev_obat = gr.Number(label="Frekuensi Tebus Obat (n_event_obat)", value=2)
+            n_fas_obat = gr.Number(label="Jumlah Faskes Obat (n_faskes_obat)", value=2)
+            qty_30d = gr.Number(label="Kuantitas Obat 30 Hari (qty_30d)", value=2)
+            min_int = gr.Number(label="Interval Terpendek Ambil Obat (min_interval)", value=20)
+            overlap = gr.Number(label="Hari Overlap Obat (overlap_days)", value=5)
+            rules_ext = gr.Number(label="Skor Rules Obat Tambahan", value=10)
+
+    btn = gr.Button("🔍 Analisis Risiko Pasien", variant="primary")
+    output_json = gr.JSON(label="Hasil Output DETEKS (JSON)")
+
+    # Fungsi @spaces.GPU didaftarkan langsung ke komponen Gradio
+    btn.click(
+        fn=calculate_risk_fusion,
+        inputs=[p_key, n_ev_kunj, n_fas_kunj, same_day, unbundling, n_ev_obat, n_fas_obat, qty_30d, min_int, overlap, rules_ext],
+        outputs=output_json,
+        api_name="analyze_risk"
+    )
+
+# --- 4. TAMBAHKAN CUSTOM FASTAPI ENDPOINT KE SERVER GRADIO ---
 class PatientFeatures(BaseModel):
     participant_key: str = "P-0001"
     n_event_kunjungan: float = 2.0
@@ -141,7 +149,16 @@ class PatientFeatures(BaseModel):
     overlap_days: float = 4.0
     rules_score_tambahan: float = 0.0
 
-@app.post("/api/v1/analyze_risk")
+# Mengaktifkan CORS pada aplikasi FastAPI internal milik Gradio
+demo.app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+@demo.app.post("/api/v1/analyze_risk")
 def analyze_risk_api(patient: PatientFeatures):
     try:
         return calculate_risk_fusion(
@@ -160,37 +177,6 @@ def analyze_risk_api(patient: PatientFeatures):
     except Exception as e:
         raise HTTPException(status_code=500, detail=str(e))
 
-# --- 5. ANTARMUKA GRADIO (Wajib untuk ZeroGPU Space) ---
-with gr.Blocks(title="DETEKS AI Engine") as demo:
-    gr.Markdown("## 🏥 DETEKS - AI Risk Scoring Service (ZeroGPU)")
-    gr.Markdown("Antarmuka uji coba model **Hybrid Rules + Isolation Forest**. Untuk dokumentasi REST API, buka endpoint `/docs`.")
-    
-    with gr.Row():
-        with gr.Column():
-            p_key = gr.Textbox(label="ID Peserta (participant_key)", value="P-0951")
-            n_ev_kunj = gr.Number(label="Total Kunjungan RJTL (n_event_kunjungan)", value=5)
-            n_fas_kunj = gr.Number(label="Jumlah Faskes Kunjungan (n_faskes_kunjungan)", value=1)
-            same_day = gr.Number(label="Same Day Hits", value=0)
-            unbundling = gr.Number(label="Unbundling Hits", value=1)
-        with gr.Column():
-            n_ev_obat = gr.Number(label="Frekuensi Tebus Obat (n_event_obat)", value=2)
-            n_fas_obat = gr.Number(label="Jumlah Faskes Obat (n_faskes_obat)", value=2)
-            qty_30d = gr.Number(label="Kuantitas Obat 30 Hari (qty_30d)", value=2)
-            min_int = gr.Number(label="Interval Terpendek Ambil Obat (min_interval)", value=20)
-            overlap = gr.Number(label="Hari Overlap Obat (overlap_days)", value=5)
-            rules_ext = gr.Number(label="Skor Rules Obat Tambahan", value=10)
-
-    btn = gr.Button("🔍 Analisis Risiko Pasien", variant="primary")
-    output_json = gr.JSON(label="Hasil Output DETEKS (JSON)")
-
-    btn.click(
-        fn=calculate_risk_fusion,
-        inputs=[p_key, n_ev_kunj, n_fas_kunj, same_day, unbundling, n_ev_obat, n_fas_obat, qty_30d, min_int, overlap, rules_ext],
-        outputs=output_json
-    )
-
-# Gabungkan Gradio ke dalam aplikasi FastAPI
-app = gr.mount_gradio_app(app, demo, path="/")
-
+# --- 5. JALANKAN DENGAN DEMO.LAUNCH() ---
 if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", port=7860)
+    demo.launch()

requirements.txt

@@ -1,6 +1,6 @@
 fastapi
 uvicorn
-scikit-learn
+scikit-learn==1.6.1
 pandas
 numpy
 pydantic