Update app.py

app.py

@@ -1,179 +1,120 @@
-import os
 import json
-import uvicorn
-import pandas as pd
+from pathlib import Path
+from typing import Dict, Any
 
+import pandas as pd
 from fastapi import FastAPI, HTTPException
-from fastapi.middleware.cors import CORSMiddleware
-from pydantic import BaseModel, ConfigDict
 from catboost import CatBoostClassifier
-from typing import Dict, Any
 
-# =========================================================
-# 1. FASTAPI SETUP
-# =========================================================
+# =========================
+# CONFIG
+# =========================
+ARTIFACTS_DIR = Path("artifacts_final")
+MODEL_FILE = ARTIFACTS_DIR / "catboost_model_top20.cbm"
+UI_SCHEMA_FILE = ARTIFACTS_DIR / "model_ui_schema.json"
+TOP_FEATURES_FILE = ARTIFACTS_DIR / "top20_features.csv"
 
+THRESHOLD = 0.41  # ✅ FINAL OPERATING THRESHOLD
+
+# =========================
+# APP INIT
+# =========================
 app = FastAPI(
     title="PPD Risk Assessment API",
-    description="AI-powered screening tool for Postpartum Depression (CatBoost Top-20)",
+    description="Hybrid ML-based screening API for Postpartum Depression risk",
     version="1.0.0"
 )
 
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-# =========================================================
-# 2. PATH CONFIG (HF SAFE)
-# =========================================================
-
-BASE_DIR = os.path.dirname(os.path.abspath(__file__))
-ARTIFACTS_DIR = os.path.join(BASE_DIR, "artifacts_final")
-
-MODEL_FILE = "catboost_model_top20.cbm"
-TOP_FEATURES_FILE = "top20_features.csv"
-UI_FILE = "model_ui_schema.json"
-
-THRESHOLD = 0.3
-
-# =========================================================
-# 3. LOAD ARTIFACTS
-# =========================================================
-
+# =========================
+# LOAD ARTIFACTS
+# =========================
 print("⏳ Loading AI Models and Config...")
-print("📁 Expected artifacts path:", ARTIFACTS_DIR)
+print(f"📁 Expected artifacts path: {ARTIFACTS_DIR.resolve()}")
 
-if not os.path.isdir(ARTIFACTS_DIR):
-    raise RuntimeError(f"Artifacts directory not found: {ARTIFACTS_DIR}")
+if not ARTIFACTS_DIR.exists():
+    raise RuntimeError("❌ artifacts_final folder not found")
 
-print("📄 Files found:", os.listdir(ARTIFACTS_DIR))
+print(f"📄 Files found: {[f.name for f in ARTIFACTS_DIR.iterdir()]}")
 
-# ---- Load Model ----
-model_path = os.path.join(ARTIFACTS_DIR, MODEL_FILE)
+# --- Load model ---
 model = CatBoostClassifier()
-model.load_model(model_path)
+model.load_model(str(MODEL_FILE))
 print("✅ CatBoost model loaded")
 
-# ---- Load Top 20 Features (SOURCE OF TRUTH) ----
-features_path = os.path.join(ARTIFACTS_DIR, TOP_FEATURES_FILE)
+# --- Load UI schema ---
+with open(UI_SCHEMA_FILE, "r") as f:
+    ui_schema = json.load(f)
+
+# --- Load top features safely ---
+if not TOP_FEATURES_FILE.exists():
+    raise RuntimeError("❌ top20_features.csv not found")
+
 TOP_FEATURES = (
-    pd.read_csv(features_path, header=None)[0]
+    pd.read_csv(TOP_FEATURES_FILE, header=None)
+    .iloc[:, 0]
     .astype(str)
     .tolist()
 )
 
 print(f"✅ Loaded {len(TOP_FEATURES)} top features")
 
-# ---- Load UI Schema ----
-ui_path = os.path.join(ARTIFACTS_DIR, UI_FILE)
-with open(ui_path, "r") as f:
-    ui_schema = json.load(f)
-
-print("✅ UI schema loaded")
-print(f"🚦 Threshold set to {THRESHOLD}")
-
-# =========================================================
-# 4. REQUEST SCHEMA
-# =========================================================
-
-class PatientData(BaseModel):
-    data: Dict[str, Any]
-
-    model_config = ConfigDict(
-        json_schema_extra={
-            "example": {
-                "data": {
-                    "Need for Support": "high",
-                    "Recieved Support": "low",
-                    "Abuse": "no",
-                    "Disease before pregnancy": "none",
-                    "Pregnancy plan": "no",
-                    "Relationship with the in-laws": "bad",
-                    "Relationship with husband": "bad",
-                    "Occupation before latest pregnancy": "housewife",
-                    "Major changes or losses during pregnancy": "no",
-                    "Relationship with the newborn": "good",
-                    "Family type": "nuclear",
-                    "Diseases during pregnancy": "none",
-                    "Relationship between father and newborn": "good",
-                    "Husband's education level": "college",
-                    "Trust and share feelings": "no",
-                    "Birth compliancy": "no",
-                    "Education Level": "college",
-                    "Occupation After Your Latest Childbirth": "housewife",
-                    "Addiction": "none",
-                    "Age": 24
-                }
-            }
-        }
-    )
-
-# =========================================================
-# 5. PREPROCESSING
-# =========================================================
-
-def preprocess_input(raw_data: Dict[str, Any]) -> pd.DataFrame:
-    clean_data = {}
-
-    for k, v in raw_data.items():
-        clean_data[k] = v.lower() if isinstance(v, str) else v
-
-    df = pd.DataFrame([clean_data])
-
-    # Ensure all required features exist
-    for col in TOP_FEATURES:
-        if col not in df.columns:
-            df[col] = "unknown"
+# =========================
+# HELPERS
+# =========================
+def build_input_dataframe(payload: Dict[str, Any]) -> pd.DataFrame:
+    """
+    Build a single-row dataframe aligned with TOP_FEATURES
+    """
+    row = {}
+    for feature in TOP_FEATURES:
+        if feature not in payload:
+            raise HTTPException(
+                status_code=400,
+                detail=f"Missing required feature: {feature}"
+            )
+        row[feature] = payload[feature]
 
-    return df[TOP_FEATURES]
+    return pd.DataFrame([row])
 
-# =========================================================
-# 6. API ENDPOINTS
-# =========================================================
 
+# =========================
+# ROUTES
+# =========================
 @app.get("/")
-def health():
+def health_check():
     return {
         "status": "online",
         "model": "CatBoost Top-20",
-        "threshold": THRESHOLD
+        "threshold": THRESHOLD,
+        "features_used": len(TOP_FEATURES)
     }
 
-@app.get("/config")
-def get_ui_config():
+
+@app.get("/ui-schema")
+def get_ui_schema():
     return ui_schema
 
+
 @app.post("/predict")
-def predict(payload: PatientData):
+def predict_risk(payload: Dict[str, Any]):
     try:
-        input_df = preprocess_input(payload.data)
+        input_df = build_input_dataframe(payload)
 
-        risk_prob = model.predict_proba(input_df)[0][1]
+        # CatBoost handles categoricals internally
+        risk_prob = float(model.predict_proba(input_df)[0][1])
         is_high_risk = risk_prob >= THRESHOLD
 
         return {
-            "prediction": "HIGH RISK" if is_high_risk else "LOW RISK",
-            "risk_probability": round(float(risk_prob), 4),
-            "threshold_used": THRESHOLD,
-            "flag": int(is_high_risk),
-            "clinical_note": (
-                "Refer to specialist"
-                if is_high_risk
-                else "Standard monitoring"
-            )
+            "ppd_risk_probability": round(risk_prob, 4),
+            "threshold": THRESHOLD,
+            "risk_label": "HIGH RISK" if is_high_risk else "LOW RISK",
+            "screening_positive": bool(is_high_risk)
         }
 
+    except HTTPException:
+        raise
     except Exception as e:
-        raise HTTPException(status_code=500, detail=str(e))
-
-# =========================================================
-# 7. RUNNER (HF)
-# =========================================================
-
-if __name__ == "__main__":
-    print("🚀 Starting server...")
-    uvicorn.run(app, host="0.0.0.0", port=7860)
+        raise HTTPException(
+            status_code=500,
+            detail=f"Prediction failed: {str(e)}"
+        )