Update app.py

app.py

@@ -1,90 +1,65 @@
-import os
 import json
-from pathlib import Path
-
 import numpy as np
 import tensorflow as tf
 import gradio as gr
-from fastapi import FastAPI, Request
-from fastapi.middleware.cors import CORSMiddleware
 
-# ---------- CONFIG (edit these names if yours differ) ----------
-MODEL_PATH = os.environ.get("MODEL_PATH", "best_model.h5")          # or "best_model.keras"
-STATS_PATH = os.environ.get("STATS_PATH", "Means & Std for Excel.json")
+# ---------------- CONFIG ----------------
+MODEL_PATH = "best_model.h5"  # or "best_model.keras" if that’s the saved file
+STATS_PATH = "Means & Std for Excel.json"
 CLASSES = ["Top", "Mid-Top", "Mid", "Mid-Low", "Low"]
-# --------------------------------------------------------------
+# ----------------------------------------
 
-# Global handles (lazy init)
-_model = None
-_stats = None
-_features = None
+print("Loading model and stats...")
+model = tf.keras.models.load_model(MODEL_PATH, compile=False)
+with open(STATS_PATH, "r") as f:
+    stats = json.load(f)
 
-def _exists(p): return Path(p).exists()
+FEATURES = list(stats.keys())
+print("Feature order:", FEATURES)
 
-def _safe_float(x, default=0.0):
-    try:
-        return float(x)
-    except Exception:
-        return default
-
-def _zscore(val, mean, sd):
-    v = _safe_float(val, 0.0)
-    return 0.0 if (sd is None or sd == 0) else (v - mean) / sd
 
 def coral_probs_from_logits(logits_np):
-    logits = tf.convert_to_tensor(logits_np, dtype=tf.float32)  # (N, K-1)
+    """Convert CORAL logits to probabilities if model output is ordinal."""
+    logits = tf.convert_to_tensor(logits_np, dtype=tf.float32)
     sig = tf.math.sigmoid(logits)
-    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()
 
-def lazy_init():
-    """Load model + stats on first use; never crash the process."""
-    global _model, _stats, _features
-    if _model is not None and _stats is not None and _features is not None:
-        return
-
-    problems = []
-    if not _exists(MODEL_PATH):
-        problems.append(f"Model file not found: {MODEL_PATH}")
-    if not _exists(STATS_PATH):
-        problems.append(f"Stats JSON not found: {STATS_PATH}")
-    if problems:
-        # Don’t raise—let callers see the reason in the response
-        raise RuntimeError("; ".join(problems))
 
+def zscore(val, mean, sd):
+    """Z-score normalization (gracefully handles 0 std)."""
     try:
-        _model = tf.keras.models.load_model(MODEL_PATH, compile=False)
-    except Exception as e:
-        raise RuntimeError(f"Failed to load model: {type(e).__name__}: {e}")
-
-    try:
-        with open(STATS_PATH, "r") as f:
-            _stats = json.load(f)
-    except Exception as e:
-        raise RuntimeError(f"Failed to read stats JSON: {type(e).__name__}: {e}")
+        val = float(val)
+        if sd == 0 or sd is None:
+            return 0.0
+        return (val - mean) / sd
+    except Exception:
+        return 0.0
 
-    # Fixed feature order = keys order in JSON
-    _features = list(_stats.keys())
-    print("Feature order:", _features)
 
-def predict_core(ratios: dict):
-    lazy_init()  # may raise RuntimeError with a clear message
+def predict_from_json(ratios):
+    """Main callable function for Gradio."""
+    if isinstance(ratios, list) and len(ratios) == 1 and isinstance(ratios[0], dict):
+        ratios = ratios[0]
+    if not isinstance(ratios, dict):
+        return {"error": "Invalid input, must be dict of feature->value"}
 
+    # Compute z-scores
     zvec = []
     zmap = {}
-    for f in _features:
-        mean = _stats[f]["mean"]
-        sd   = _stats[f]["std"]
-        z    = _zscore(ratios.get(f, 0.0), mean, sd)
+    for f in FEATURES:
+        mean = stats[f]["mean"]
+        sd = stats[f]["std"]
+        z = zscore(ratios.get(f, 0.0), mean, sd)
         zvec.append(z)
         zmap[f] = z
 
     X = np.array([zvec], dtype=np.float32)
-    y = _model.predict(X, verbose=0)
+    y = model.predict(X, verbose=0)
 
-    # Softmax (K) or CORAL (K-1)
+    # Handle output shape
     if y.ndim == 2 and y.shape[1] == len(CLASSES):
         probs = y[0]
     elif y.ndim == 2 and y.shape[1] == len(CLASSES) - 1:
@@ -93,84 +68,27 @@ def predict_core(ratios: dict):
         s = np.maximum(y[0].astype(np.float64).ravel(), 0.0)
         probs = s / s.sum() if s.sum() > 0 else np.ones(len(CLASSES)) / len(CLASSES)
 
-    pred_idx = int(np.argmax(probs))
+    pred = CLASSES[int(np.argmax(probs))]
+
     return {
         "input_ok": True,
-        "missing": [f for f in _features if f not in ratios],
+        "missing": [f for f in FEATURES if f not in ratios],
         "z_scores": zmap,
         "probabilities": {CLASSES[i]: float(probs[i]) for i in range(len(CLASSES))},
-        "predicted_state": CLASSES[pred_idx]
-    }
-
-def predict_from_json(payload):
-    # Accept raw dict or list-of-one
-    if isinstance(payload, list) and len(payload) == 1 and isinstance(payload[0], dict):
-        payload = payload[0]
-    if not isinstance(payload, dict):
-        return {"error": "Invalid payload. Send a JSON object mapping feature->value."}
-    try:
-        return predict_core(payload)
-    except RuntimeError as e:
-        # File/boot issues come here (and we still return 200 JSON)
-        return {"error": str(e)}
-    except Exception as e:
-        return {"error": f"{type(e).__name__}: {e}"}
-
-# ------------------ FastAPI + Gradio ------------------
-app = FastAPI()
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"], allow_methods=["*"], allow_headers=["*"],
-)
-
-@app.get("/health")
-def health():
-    return {
-        "ok": True,
-        "model_exists": _exists(MODEL_PATH),
-        "stats_exists": _exists(STATS_PATH),
-        "model_loaded": (_model is not None),
-        "stats_loaded": (_stats is not None)
+        "predicted_state": pred,
     }
 
-# Plain REST endpoints for Excel (we expose several to be future-proof)
-from fastapi import Request
 
-async def _handle_predict(req: Request):
-    try:
-        body = await req.json()
-    except Exception:
-        return {"error": "Invalid JSON"}
-    # raw dict or {"data":[{...}]}
-    if isinstance(body, dict) and "data" in body and isinstance(body["data"], list) and body["data"]:
-        body = body["data"][0]
-    return predict_from_json(body)
-
-@app.post("/predict")
-async def predict_main(req: Request):
-    return await _handle_predict(req)
-
-@app.post("/run/predict")
-async def predict_compat1(req: Request):
-    return await _handle_predict(req)
-
-@app.post("/gradio_api/call/predict")
-async def predict_compat2(req: Request):
-    return await _handle_predict(req)
-
-# UI at root (keeps your browser demo)
-ui = gr.Interface(
+# ----------------- GRADIO APP -----------------
+iface = gr.Interface(
     fn=predict_from_json,
     inputs=gr.JSON(label="ratios JSON (dict of feature -> value)"),
     outputs="json",
     title="Static Fingerprint Model API",
-    description="POST your 21 ratios as a JSON dict. Returns probabilities + predicted state.",
+    description=(
+        "POST JSON to `/run/predict` with a dict of your 21 ratios. "
+        "Server normalises using saved means/stds and returns probabilities + predicted state."
+    ),
 )
-app = gr.mount_gradio_app(app, ui, path="/")
 
-# Print routes in logs for visibility
-for r in app.router.routes:
-    try:
-        print("ROUTE:", r.path)
-    except Exception:
-        pass
+iface.launch()