Update app.py

app.py

@@ -1,4 +1,4 @@
-# app_tc.py — ST_Sonic_Tc (Compressional Slowness Tc) — MAPE version
+# app_rhob.py — ST_Log_RHOB (Formation Bulk Density, g/cc) — MAPE version
 
 import io, json, os, base64, math
 from pathlib import Path
@@ -18,12 +18,12 @@ import plotly.graph_objects as go
 from sklearn.metrics import mean_squared_error
 
 # =========================
-# Constants (Tc variant)
+# Constants (RHOB variant)
 # =========================
-APP_NAME = "ST_Log_Sonic (Tc)"
-TAGLINE  = "Real-Time Compressional Slowness (Tc) Prediction"
+APP_NAME = "ST_Log_RHOB"
+TAGLINE  = "Real-Time Formation Bulk Density (RHOB) Prediction"
 
-# Defaults (overridden by tc_meta.json if present)
+# Defaults (overridden by rhob_meta.json if present)
 FEATURES  = [
     "WOB (klbf)",
     "Torque (kft.lbf)",
@@ -32,11 +32,11 @@ FEATURES  = [
     "ROP (ft/h)",
     "Flow Rate (gpm)",
 ]
-TARGET    = "Tc (us/ft_Actual)"
-PRED_COL  = "Tc_Pred"
+TARGET    = "RHOB"          # canonical target name
+PRED_COL  = "RHOB_Pred"
 
 MODELS_DIR = Path("models")
-DEFAULT_MODEL = MODELS_DIR / "tc_model.joblib"
+DEFAULT_MODEL = MODELS_DIR / "rhob_model.joblib"
 MODEL_FALLBACKS = [MODELS_DIR / "model.joblib", MODELS_DIR / "model.pkl"]
 COLORS = {"pred": "#1f77b4", "actual": "#f2b702", "ref": "#5a5a5a"}
 
@@ -143,7 +143,7 @@ def mape(y_true, y_pred) -> float:
     a = np.asarray(y_true, dtype=float)
     p = np.asarray(y_pred, dtype=float)
     mask = np.isfinite(a) & np.isfinite(p) & (a != 0)
-    if not np.any(mask): 
+    if not np.any(mask):
         return float("nan")
     return float(np.mean(np.abs((p[mask] - a[mask]) / a[mask])) * 100.0)
 
@@ -164,7 +164,7 @@ def read_book_bytes(b: bytes):
 def _build_alias_map(canonical_features: list[str], target_name: str) -> dict:
     """
     Map common header variants -> the *canonical* names in canonical_features.
-    Whatever appears in canonical_features (from tc_meta.json) wins.
+    Whatever appears in canonical_features (from rhob_meta.json) wins.
     """
     def pick(expected_list, variants):
         for v in variants:
@@ -193,13 +193,13 @@ def _build_alias_map(canonical_features: list[str], target_name: str) -> dict:
         # Depth (plot only)
         "Depth (ft)": can_DEPTH, "Depth, ft": can_DEPTH, "Depth(ft)": can_DEPTH, "DEPTH, ft": can_DEPTH,
 
-        # Target family (Tc)
-        "Tc (us/ft_Actual)": target_name,
-        "Tc,us/ft_Actual":   target_name,
-        "Tc, us/ft_Actual":  target_name,
-        "Tc":                target_name,
-        "TC_Actual":         target_name,
-        "Tc (us/ft)_Actual": target_name,
+        # Target family (RHOB)
+        "RHOB":               target_name,
+        "RHOB (g/cc)":        target_name,
+        "RHOB_Actual":        target_name,
+        "RHOB (g/cc)_Actual": target_name,
+        "RhoB":               target_name,
+        "RhoB (g/cc)":        target_name,
     }
     return alias
 
@@ -377,7 +377,7 @@ def build_export_workbook(selected: list[str], ndigits: int = 3, do_autofit: boo
             if do_autofit:
                 _excel_autofit(writer, sheet, df)
     bio.seek(0)
-    fname = f"TC_Export_{datetime.now().strftime('%Y%m%d_%H%M%S')}.xlsx"
+    fname = f"RHOB_Export_{datetime.now().strftime('%Y%m%d_%H%M%S')}.xlsx"
     return bio.getvalue(), fname, order
 
 # --------- SIMPLE export UI ----------
@@ -402,7 +402,7 @@ def render_export_button(phase_key: str) -> None:
         st.download_button(
             label="⬇️ Export Excel",
             data=b"",
-            file_name="TC_Export.xlsx",
+            file_name="RHOB_Export.xlsx",
             mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
             disabled=True,
             key=f"download_{phase_key}",
@@ -415,7 +415,7 @@ def render_export_button(phase_key: str) -> None:
     st.download_button(
         "⬇️ Export Excel",
         data=(data or b""),
-        file_name=(fname or "TC_Export.xlsx"),
+        file_name=(fname or "RHOB_Export.xlsx"),
         mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
         disabled=(data is None),
         key=f"download_{phase_key}",
@@ -424,7 +424,7 @@ def render_export_button(phase_key: str) -> None:
 # =========================
 # Cross plot (Matplotlib)
 # =========================
-def cross_plot_static(actual, pred, xlabel="Actual Tc (µs/ft)", ylabel="Predicted Tc (µs/ft)"):
+def cross_plot_static(actual, pred, xlabel="Actual RHOB (g/cc)", ylabel="Predicted RHOB (g/cc)"):
     a = pd.Series(actual, dtype=float)
     p = pd.Series(pred, dtype=float)
 
@@ -486,14 +486,14 @@ def track_plot(df, include_actual=True):
             x=df[PRED_COL], y=y, mode="lines",
             line=dict(color=COLORS["pred"], width=1.8),
             name=PRED_COL,
-            hovertemplate=f"{PRED_COL}: "+"%{x:.0f}<br>"+ylab+": %{y}<extra></extra>"
+            hovertemplate=f"{PRED_COL}: "+"%{x:.3f}<br>"+ylab+": %{y}<extra></extra>"
         ))
     if include_actual and TARGET in df.columns:
         fig.add_trace(go.Scatter(
             x=df[TARGET], y=y, mode="lines",
             line=dict(color=COLORS["actual"], width=2.0, dash="dot"),
             name=f"{TARGET} (actual)",
-            hovertemplate=f"{TARGET}: "+"%{x:.0f}<br>"+ylab+": %{y}<extra></extra>"
+            hovertemplate=f"{TARGET}: "+"%{x:.3f}<br>"+ylab+": %{y}<extra></extra>"
         ))
 
     fig.update_layout(
@@ -506,11 +506,11 @@ def track_plot(df, include_actual=True):
         legend_title_text=""
     )
     fig.update_xaxes(
-        title_text="Tc (μs/ft)",
+        title_text="RHOB (g/cc)",
         title_font=dict(size=20, family=BOLD_FONT, color="#000"),
         tickfont=dict(size=15, family=BOLD_FONT, color="#000"),
         side="top", range=[xmin, xmax],
-        ticks="outside", tickformat=",.0f", tickmode="auto", tick0=tick0,
+        ticks="outside", tickformat=",.3f", tickmode="auto", tick0=tick0,
         showline=True, linewidth=1.2, linecolor="#444", mirror=True,
         showgrid=True, gridcolor="rgba(0,0,0,0.12)", automargin=True
     )
@@ -599,7 +599,7 @@ def ensure_model() -> Path|None:
 
 mpath = ensure_model()
 if not mpath:
-    st.error("Model not found. Upload models/tc_model.joblib (or set MODEL_URL).")
+    st.error("Model not found. Upload models/rhob_model.joblib (or set MODEL_URL).")
     st.stop()
 try:
     model = load_model(str(mpath))
@@ -607,9 +607,9 @@ except Exception as e:
     st.error(f"Failed to load model: {e}")
     st.stop()
 
-# Load meta (prefer Tc-specific)
+# Load meta (prefer RHOB-specific)
 meta = {}
-meta_candidates = [MODELS_DIR / "tc_meta.json", MODELS_DIR / "meta.json"]
+meta_candidates = [MODELS_DIR / "rhob_meta.json", MODELS_DIR / "meta.json"]
 meta_path = next((p for p in meta_candidates if p.exists()), None)
 if meta_path:
     try:
@@ -617,6 +617,9 @@ if meta_path:
         FEATURES = meta.get("features", FEATURES)
         TARGET   = meta.get("target", TARGET)
         PRED_COL = meta.get("pred_col", PRED_COL)
+        # if training ranges were saved in meta, seed them so OOR works before any dev step
+        if isinstance(meta.get("train_ranges"), dict) and "train_ranges" not in st.session_state:
+            st.session_state["train_ranges"] = meta["train_ranges"]
     except Exception as e:
         st.warning(f"Could not parse meta file ({meta_path.name}): {e}")
 
@@ -636,7 +639,7 @@ if STRICT_VERSION_CHECK and meta.get("versions"):
 # =========================
 st.session_state.setdefault("app_step", "intro")
 st.session_state.setdefault("results", {})
-st.session_state.setdefault("train_ranges", None)
+st.session_state.setdefault("train_ranges", st.session_state.get("train_ranges", None))
 st.session_state.setdefault("dev_file_name","")
 st.session_state.setdefault("dev_file_bytes",b"")
 st.session_state.setdefault("dev_file_loaded",False)
@@ -677,12 +680,12 @@ def sticky_header(title, message):
 # =========================
 if st.session_state.app_step == "intro":
     st.header("Welcome!")
-    st.markdown("This software is developed by *Smart Thinking AI-Solutions Team* to estimate **Compressional Slowness (Tc)** from drilling data.")
+    st.markdown("This software is developed by *Smart Thinking AI-Solutions Team* to estimate **RHOB (Bulk Density)** from drilling data.")
     st.subheader("How It Works")
     st.markdown(
         "1) **Upload your data to build the case and preview the model performance.** \n"
         "2) Click **Run Model** to compute metrics and plots. \n"
-        "3) **Proceed to Validation** (with actual Tc) or **Proceed to Prediction** (no Tc)."
+        "3) **Proceed to Validation** (with actual RHOB) or **Proceed to Prediction** (no RHOB)."
     )
     if st.button("Start Showcase", type="primary"):
         st.session_state.app_step = "dev"; st.rerun()
@@ -757,7 +760,7 @@ if st.session_state.app_step == "dev":
     def _dev_block(df, m):
         c1,c2,c3 = st.columns(3)
         c1.metric("R", f"{m['R']:.3f}")
-        c2.metric("RMSE", f"{m['RMSE']:.2f}")
+        c2.metric("RMSE", f"{m['RMSE']:.3f}")
         c3.metric("MAPE (%)", f"{m['MAPE']:.2f}")
         st.markdown("""
             <div style='text-align: left; font-size: 0.8em; color: #6b7280; margin-top: -16px; margin-bottom: 8px;'>
@@ -781,7 +784,7 @@ if st.session_state.app_step == "dev":
         render_export_button(phase_key="dev")
 
 # =========================
-# VALIDATION (with actual Tc)
+# VALIDATION (with actual RHOB)
 # =========================
 if st.session_state.app_step == "validate":
     st.sidebar.header("Validate the Model")
@@ -797,7 +800,7 @@ if st.session_state.app_step == "validate":
     if st.sidebar.button("⬅ Back to Case Building", use_container_width=True): st.session_state.app_step="dev"; st.rerun()
     if st.sidebar.button("Proceed to Prediction ▶", use_container_width=True): st.session_state.app_step="predict"; st.rerun()
 
-    sticky_header("Validate the Model", "Upload a dataset with the same **features** and **Tc** to evaluate performance.")
+    sticky_header("Validate the Model", "Upload a dataset with the same **features** and **RHOB** to evaluate performance.")
 
     if go_btn and up is not None:
         book = read_book_bytes(up.getvalue())
@@ -815,7 +818,7 @@ if st.session_state.app_step == "validate":
             if any_viol.any():
                 tbl = df.loc[any_viol, FEATURES].copy()
                 for c in FEATURES:
-                    if pd.api.types.is_numeric_dtype(tbl[c]): tbl[c] = tbl[c].round(2)
+                    if pd.api.types.is_numeric_dtype(tbl[c]): tbl[c] = tbl[c].round(3)
                 tbl["Violations"] = pd.DataFrame({f:(df[f]<ranges[f][0])|(df[f]>ranges[f][1]) for f in FEATURES}).loc[any_viol].apply(
                     lambda r:", ".join([c for c,v in r.items() if v]), axis=1
                 )
@@ -831,7 +834,7 @@ if st.session_state.app_step == "validate":
         m = st.session_state.results["m_val"]
         c1,c2,c3 = st.columns(3)
         c1.metric("R", f"{m['R']:.3f}")
-        c2.metric("RMSE", f"{m['RMSE']:.2f}")
+        c2.metric("RMSE", f"{m['RMSE']:.3f}")
         c3.metric("MAPE (%)", f"{m['MAPE']:.2f}")
         st.markdown("""
             <div style='text-align: left; font-size: 0.8em; color: #6b7280; margin-top: -16px; margin-bottom: 8px;'>
@@ -859,10 +862,10 @@ if st.session_state.app_step == "validate":
             df_centered_rounded(st.session_state.results["oor_tbl"])
 
 # =========================
-# PREDICTION (no actual Tc)
+# PREDICTION (no actual RHOB)
 # =========================
 if st.session_state.app_step == "predict":
-    st.sidebar.header("Prediction (No Actual Tc)")
+    st.sidebar.header("Prediction (No Actual RHOB)")
     up = st.sidebar.file_uploader("Upload Prediction Excel", type=["xlsx","xls"])
     if up is not None:
         book = read_book_bytes(up.getvalue())
@@ -874,7 +877,7 @@ if st.session_state.app_step == "predict":
     go_btn = st.sidebar.button("Predict", type="primary", use_container_width=True)
     if st.sidebar.button("⬅ Back to Case Building", use_container_width=True): st.session_state.app_step="dev"; st.rerun()
 
-    sticky_header("Prediction", "Upload a dataset with the feature columns (no **Tc**).")
+    sticky_header("Prediction", "Upload a dataset with the feature columns (no **RHOB**).")
 
     if go_btn and up is not None:
         book = read_book_bytes(up.getvalue()); name = list(book.keys())[0]