Update app.py

app.py

@@ -1,137 +1,174 @@
+import os
 import json
-from pathlib import Path
-from typing import Dict, Any
-
+import uvicorn
 import pandas as pd
+import numpy as np
 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
 
-# =========================
-# 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
+# ==========================================
+# 1. SETUP & CONFIGURATION
+# ==========================================
 
-# =========================
-# APP INIT (with docs enabled)
-# =========================
 app = FastAPI(
     title="PPD Risk Assessment API",
-    description="Hybrid ML-based screening API for Postpartum Depression risk",
-    version="1.0.0",
-    docs_url="/docs",    # Swagger UI
-    redoc_url="/redoc"   # ReDoc UI
+    description="AI-powered screening tool for Postpartum Depression Risk (Top 20 Features)",
+    version="1.0.0"
 )
 
-# =========================
-# LOAD ARTIFACTS
-# =========================
-print("⏳ Loading AI Models and Config...")
-print(f"📁 Expected artifacts path: {ARTIFACTS_DIR.resolve()}")
-
-if not ARTIFACTS_DIR.exists():
-    raise RuntimeError("❌ artifacts_final folder not found")
-
-print(f"📄 Files found: {[f.name for f in ARTIFACTS_DIR.iterdir()]}")
-
-# --- Load model ---
-model = CatBoostClassifier()
-model.load_model(str(MODEL_FILE))
-print("✅ CatBoost model loaded")
-
-# --- 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(TOP_FEATURES_FILE, header=None)
-    .iloc[:, 0]
-    .astype(str)
-    .tolist()
+# Enable CORS
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Replace "*" with your frontend URL in production
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
 )
 
-print(f"✅ Loaded {len(TOP_FEATURES)} top features")
-
-# =========================
-# 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 pd.DataFrame([row])
-
-# =========================
-# ROUTES
-# =========================
+# ==========================================
+# 2. ARTIFACT PATH SETUP
+# ==========================================
+
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+ARTIFACTS_DIR = os.path.normpath(os.path.join(BASE_DIR, "..", "artifacts_final"))
+
+print("ARTIFACTS DIR:", ARTIFACTS_DIR)
+print("EXISTS:", os.path.exists(ARTIFACTS_DIR))
+
+# ==========================================
+# 3. LOAD ARTIFACTS
+# ==========================================
+
+print(" Loading AI Models and Config...")
+
+try:
+    # A. Load CatBoost Model
+    model_path = os.path.join(ARTIFACTS_DIR, "catboost_model_top20.cbm")
+    if not os.path.exists(model_path):
+        raise FileNotFoundError(f"Model not found at {model_path}")
+    
+    model = CatBoostClassifier()
+    model.load_model(model_path)
+    print(" Model Loaded.")
+
+    # B. Load Metadata
+    meta_path = os.path.join(ARTIFACTS_DIR, "catboost_metadata.json")
+    with open(meta_path, "r") as f:
+        metadata = json.load(f)
+
+    # ✅ Correct key from your metadata
+    TOP_FEATURES = metadata["features_used"]
+    THRESHOLD = metadata["thresholds"]["optimal_balanced"]
+
+    print(f" Metadata Loaded. Threshold set to: {THRESHOLD}")
+
+    # C. Load UI Schema
+    ui_path = os.path.join(ARTIFACTS_DIR, "model_ui_schema.json")
+    with open(ui_path, "r") as f:
+        ui_schema = json.load(f)
+    print(" UI Schema Loaded.")
+
+except Exception as e:
+    print(f" CRITICAL ERROR LOADING ARTIFACTS: {e}")
+    raise e
+
+# ==========================================
+# 4. DATA VALIDATION
+# ==========================================
+
+class PatientData(BaseModel):
+    data: Dict[str, Any]
+
+    model_config = ConfigDict(
+        json_schema_extra={
+            "example": {
+                "data": {
+                    "Need for Support": "High",
+                    "Recieved Support": "Low",
+                    "Abuse": "Yes",
+                    "Disease before pregnancy": "None",
+                    "Occupation before latest pregnancy": "Housewife",
+                    "Pregnancy plan": "Unplanned",
+                    "Relationship with husband": "Bad",
+                    "Major changes or losses during pregnancy": "Yes",
+                    "Relationship with the in-laws": "Bad",
+                    "Birth compliancy": "No",
+                    "Relationship between father and newborn": "Bad",
+                    "Education Level": "Secondary",
+                    "Family type": "Nuclear",
+                    "Diseases during pregnancy": "Yes",
+                    "Trust and share feelings": "No",
+                    "Relationship with the newborn": "Average",
+                    "Occupation After Your Latest Childbirth": "Unemployed",
+                    "Age": 24,
+                    "Addiction": "No",
+                    "Husband's education level": "Secondary"
+                }
+            }
+        }
+    )
+
+# ==========================================
+# 5. HELPER FUNCTION
+# ==========================================
+
+def preprocess_input(raw_data: dict) -> pd.DataFrame:
+    clean_data = {}
+    
+    for k, v in raw_data.items():
+        if isinstance(v, str):
+            clean_data[k] = v.lower()
+        else:
+            clean_data[k] = v
+            
+    df = pd.DataFrame([clean_data])
+    
+    # Fill missing features
+    for col in TOP_FEATURES:
+        if col not in df.columns:
+            df[col] = "unknown"
+    
+    df = df[TOP_FEATURES]
+    
+    return df
+
+# ==========================================
+# 6. API ENDPOINTS
+# ==========================================
+
 @app.get("/")
-def health_check():
-    """Simple health check"""
-    return {
-        "status": "online",
-        "model": "CatBoost Top-20",
-        "threshold": THRESHOLD,
-        "features_used": len(TOP_FEATURES)
-    }
-
-@app.get("/ui-schema")
-def get_ui_schema():
-    """Return the UI schema for frontend forms"""
+def home():
+    return {"status": "online", "model": "CatBoost Top20", "threshold": THRESHOLD}
+
+@app.get("/config")
+def get_ui_config():
     return ui_schema
 
 @app.post("/predict")
-def predict_risk(payload: Dict[str, Any]):
-    """
-    Predict PPD risk probability given a dictionary of feature values
-    Example payload:
-    {
-        "feature1": 3.2,
-        "feature2": 1.0,
-        ...
-    }
-    """
+def predict_risk(payload: PatientData):
     try:
-        input_df = build_input_dataframe(payload)
-
-        # CatBoost handles categoricals internally
-        risk_prob = float(model.predict_proba(input_df)[0][1])
-        is_high_risk = risk_prob >= THRESHOLD
-
+        input_df = preprocess_input(payload.data)
+        risk_prob = model.predict_proba(input_df)[0][1]
+        is_high_risk = bool(risk_prob >= THRESHOLD)
+        
         return {
-            "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)
+            "prediction": "HIGH RISK" if is_high_risk else "LOW RISK",
+            "risk_probability": round(float(risk_prob), 4),
+            "threshold_used": THRESHOLD,
+            "flag": 1 if is_high_risk else 0,
+            "clinical_note": "Refer to specialist" if is_high_risk else "Standard monitoring"
         }
-
-    except HTTPException:
-        raise
+        
     except Exception as e:
-        raise HTTPException(
-            status_code=500,
-            detail=f"Prediction failed: {str(e)}"
-        )
-
-# =========================
-# RUNNING LOCALLY (optional)
-# =========================
+        raise HTTPException(status_code=500, detail=str(e))
+
+# ==========================================
+# 7. RUNNER
+# ==========================================
+
 if __name__ == "__main__":
-    import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=7860, reload=True)
+    print(" Server starting...")
+    uvicorn.run(app, host="0.0.0.0", port=7860)