Update app.py

app.py

@@ -13,6 +13,10 @@ STATS_PATH = os.getenv("STATS_PATH", "means_std.json")
 CLASSES = ["Top", "Mid-Top", "Mid", "Mid-Low", "Low"]
 # ------------------------------------------
 
+# Debug & decoding control
+FORCE_CORAL = os.getenv("FORCE_CORAL", "0") in ("1", "true", "True", "YES", "yes")
+RETURN_DEBUG = os.getenv("RETURN_DEBUG", "1") in ("1", "true", "True", "YES", "yes")
+
 print("Loading model and stats...")
 model = tf.keras.models.load_model(MODEL_PATH, compile=False)
 
@@ -23,6 +27,7 @@ with open(STATS_PATH, "r") as f:
 FEATURES = list(stats.keys())
 print("Feature order:", FEATURES)
 
+
 # ---------- robust numeric coercion ----------
 def coerce_float(val: Any) -> float:
     """
@@ -60,12 +65,11 @@ def coerce_float(val: Any) -> float:
     elif has_comma and not has_dot:
         # likely decimal is comma
         s = s.replace(",", ".")
-    else:
-        # dots only or pure digits -> leave as is
-        pass
+    # dots only or pure digits -> leave as is
 
     return float(s)
 
+
 def _z(val: Any, mean: float, sd: float) -> float:
     try:
         v = coerce_float(val)
@@ -75,15 +79,17 @@ def _z(val: Any, mean: float, sd: float) -> float:
         return 0.0
     return (v - mean) / sd
 
+
 def coral_probs_from_logits(logits_np: np.ndarray) -> np.ndarray:
     """(N, K-1) logits -> (N, K) probabilities for CORAL ordinal output."""
     logits = tf.convert_to_tensor(logits_np, dtype=tf.float32)
     sig = tf.math.sigmoid(logits)  # (N, K-1)
-    left  = tf.concat([tf.ones_like(sig[:, :1]), sig], axis=1)
+    left = tf.concat([tf.ones_like(sig[:, :1]), sig], axis=1)
     right = tf.concat([sig, tf.zeros_like(sig[:, :1])], axis=1)
     probs = tf.clip_by_value(left - right, 1e-12, 1.0)
     return probs.numpy()
 
+
 # ------------- FastAPI app ----------------
 app = FastAPI(title="Static Fingerprint API", version="1.0.0")
 
@@ -96,9 +102,14 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
+
 @app.get("/")
 def root():
-    return {"message": "Static Fingerprint API is running.", "try": ["GET /health", "POST /predict"]}
+    return {
+        "message": "Static Fingerprint API is running.",
+        "try": ["GET /health", "POST /predict"],
+    }
+
 
 @app.get("/health")
 def health():
@@ -110,11 +121,13 @@ def health():
         "stats_file": STATS_PATH,
     }
 
+
 @app.post("/echo")
 async def echo(req: Request):
     payload = await req.json()
     return {"received": payload}
 
+
 @app.post("/predict")
 async def predict(req: Request):
     """
@@ -136,7 +149,7 @@ async def predict(req: Request):
     missing = []
     for f in FEATURES:
         mean = stats[f]["mean"]
-        sd   = stats[f]["std"]
+        sd = stats[f]["std"]
         if f in payload:
             zf = _z(payload[f], mean, sd)
         else:
@@ -148,20 +161,57 @@ async def predict(req: Request):
     X = np.array([z], dtype=np.float32)
     raw = model.predict(X, verbose=0)
 
-    # Detect CORAL (K-1) vs softmax (K)
-    if raw.ndim == 2 and raw.shape[1] == (len(CLASSES) - 1):
-        probs = coral_probs_from_logits(raw)[0]
-    else:
+    # ---------------- DEBUG INFO ----------------
+    raw_shape = tuple(raw.shape)
+    # --------------------------------------------
+
+    # Decode: CORAL vs Softmax
+    probs = None
+    decode_mode = "auto"
+    try:
+        if FORCE_CORAL:
+            decode_mode = "forced_coral"
+            probs = coral_probs_from_logits(raw)[0]
+        else:
+            if raw.ndim == 2 and raw.shape[1] == (len(CLASSES) - 1):
+                decode_mode = "auto_coral"
+                probs = coral_probs_from_logits(raw)[0]
+            else:
+                decode_mode = "auto_softmax_or_logits"
+                probs = raw[0]
+                s = float(np.sum(probs))
+                if s > 0:  # defensive normalize
+                    probs = probs / s
+    except Exception as e:
+        decode_mode = "fallback_raw_norm"
         probs = raw[0]
         s = float(np.sum(probs))
         if s > 0:
             probs = probs / s
 
     pred_idx = int(np.argmax(probs))
-    return {
+
+    resp = {
         "input_ok": (len(missing) == 0),
         "missing": missing,
         "z_scores": z_detail,
-        "probabilities": {CLASSES[i]: float(probs[i]) for i in range(len(CLASSES))},
+        "probabilities": {
+            CLASSES[i]: float(probs[i]) for i in range(len(CLASSES))
+        },
         "predicted_state": CLASSES[pred_idx],
-    }
+    }
+
+    # Include debug fields so we can see shape & decode path
+    if RETURN_DEBUG:
+        resp["debug"] = {
+            "raw_shape": raw_shape,
+            "decode_mode": decode_mode,
+            "raw_first_row": [
+                float(x)
+                for x in (
+                    raw[0].tolist() if raw.ndim >= 2 else [float(raw)]
+                )
+            ],
+        }
+
+    return resp