Update app.py

app.py

@@ -19,23 +19,18 @@ from sklearn.metrics import mean_squared_error, mean_absolute_error
 # =========================
 # Constants (Ts variant)
 # =========================
-APP_NAME = "ST_Sonic_Ts"
+APP_NAME = "ST_Log_Sonic(Ts)"
 TAGLINE  = "Real-Time Shear Slowness (Ts) Prediction"
 
-# Use the exact column headers you have in Excel (from your screenshot)
-FEATURES  = [
-    "WOB, klbf",
-    "Torque(kft.lbf)",
-    "SPP(psi)",
-    "RPM(1/min)",
-    "ROP(ft/h)",
-    "Flow Rate, gpm",
-]
-TARGET    = "Ts,us/ft_Actual"   # actual Ts column in your sheets
-PRED_COL  = "Ts_Pred"           # predicted Ts column we’ll add
+# Keep your drilling features the same (we'll normalize header variants below)
+FEATURES  = ["WOB(klbf)", "TORQUE(kft.lbf)", "SPP(psi)", "RPM(1/min)", "ROP(ft/h)", "Flow Rate, gpm"]
+
+# Target and pred column for Ts
+TARGET    = "Ts"          # we'll map your file's "Ts,us/ft_Actual" → "Ts"
+PRED_COL  = "Ts_Pred"
 
 MODELS_DIR = Path("models")
-DEFAULT_MODEL = MODELS_DIR / "ts_model.joblib"  # your uploaded model filename
+DEFAULT_MODEL = MODELS_DIR / "ts_model.joblib"
 MODEL_FALLBACKS = [MODELS_DIR / "model.joblib", MODELS_DIR / "model.pkl"]
 COLORS = {"pred": "#1f77b4", "actual": "#f2b702", "ref": "#5a5a5a"}
 
@@ -226,24 +221,49 @@ def _excel_engine() -> str:
 
 def _normalize_columns(df: pd.DataFrame) -> pd.DataFrame:
     out = df.copy()
-    out.columns = [str(c).strip() for c in out.columns]
 
-    # Map legacy/alternate headers -> current headers (so older files still pass)
-    alias = {
-        "WOB(klbf)": "WOB, klbf",
-        "TORQUE(kft.lbf)": "Torque(kft.lbf)",
-        "Flow Rate, gpm ": "Flow Rate, gpm",
-        "Fow Rate, gpm": "Flow Rate, gpm",
-        "Fow Rate, gpm ": "Flow Rate, gpm",
-        "Ts": "Ts,us/ft_Actual",
-        "Ts_Actual": "Ts,us/ft_Actual",
-        "Ts (us/ft)": "Ts,us/ft_Actual",
-        "Depth": "Depth, ft",
+    # Trim and collapse inner spaces like ", " → ", " consistently
+    out.columns = [str(c).strip().replace(" ,", ",").replace(",  ", ", ").replace("  ", " ") for c in out.columns]
+
+    # Canonical rename map: map what you have → what the app expects
+    rename_map = {
+        # Drilling features
+        "WOB, klbf":        "WOB(klbf)",
+        "WOB (klbf)":       "WOB(klbf)",
+        "WOB( klbf)":       "WOB(klbf)",
+        "WOB(klbf)":        "WOB(klbf)",
+
+        "Torque(kft.lbf)":  "TORQUE(kft.lbf)",
+        "TORQUE(kft.lbf)":  "TORQUE(kft.lbf)",
+
+        "SPP(psi)":         "SPP(psi)",
+        "RPM(1/min)":       "RPM(1/min)",
+        "ROP(ft/h)":        "ROP(ft/h)",
+        "Flow Rate, gpm":   "Flow Rate, gpm",
+
+        # Target column variants coming from your file
+        "Ts,us/ft_Actual":  "Ts",
+        "Ts, us/ft_Actual": "Ts",
+        "TS_Actual":        "Ts",
+        "Ts (us/ft)_Actual":"Ts",
+    }
+
+    # Also keep Depth variants tidy (used for Y axis only)
+    depth_variants = {
+        "Depth, ft": "Depth, ft",
         "Depth(ft)": "Depth, ft",
+        "DEPTH, ft": "Depth, ft",
     }
-    out = out.rename(columns={k: v for k, v in alias.items() if k in out.columns})
+
+    # Build final mapping
+    final_map = {**depth_variants}
+    # Only add keys that actually exist to avoid KeyErrors
+    final_map.update({k: v for k, v in rename_map.items() if k in out.columns})
+
+    out = out.rename(columns=final_map)
     return out
 
+
 def _excel_safe_name(name: str) -> str:
     bad = '[]:*?/\\'
     safe = ''.join('_' if ch in bad else ch for ch in str(name))
@@ -639,7 +659,11 @@ except Exception as e:
 # ---------- Load meta (optional) ----------
 meta = {}
 # Prefer a Ts-specific meta, fall back to a generic one if present
-meta_candidates = [MODELS_DIR / "ts_meta.json", MODELS_DIR / "meta.json"]
+meta_candidates = [
+    MODELS_DIR / "ts_meta.json",   # ← add this
+    MODELS_DIR / "meta.json",
+    MODELS_DIR / "ym_meta.json",
+]
 meta_path = next((p for p in meta_candidates if p.exists()), None)
 if meta_path:
     try: