Update app.py

app.py

@@ -115,7 +115,8 @@ st.markdown("""
 def inline_logo(path="logo.png") -> str:
     try:
         p = Path(path)
-        if not p.exists(): return ""
+        if not p.exists():
+            return ""
         return f"data:image/png;base64,{base64.b64encode(p.read_bytes()).decode('ascii')}"
     except Exception:
         return ""
@@ -194,7 +195,8 @@ def ensure_cols(df, cols):
 def find_sheet(book, names):
     low2orig = {k.lower(): k for k in book.keys()}
     for nm in names:
-        if nm.lower() in low2orig: return low2orig[nm.lower()]
+        if nm.lower() in low2orig:
+            return low2orig[nm.lower()]
     return None
 
 def _nice_tick0(xmin: float, step: int = 5) -> float:
@@ -233,9 +235,8 @@ def to_actual_series(df: pd.DataFrame, target_col: str, actual_col_hint: str, tr
         return pd.Series(df["GR"], dtype=float)
     raise ValueError("Cannot find actual GR column or target to invert.")
 
-# === NEW: Excel export helpers =================================================
+# === Excel export helpers =================================================
 def _excel_engine() -> str:
-    """Prefer xlsxwriter for better formatting; fall back to openpyxl if missing."""
     try:
         import xlsxwriter  # noqa: F401
         return "xlsxwriter"
@@ -243,7 +244,6 @@ def _excel_engine() -> str:
         return "openpyxl"
 
 def _excel_safe_name(name: str) -> str:
-    """Excel sheet names: max 31 chars, no []:*?/\\."""
     bad = '[]:*?/\\'
     safe = ''.join('_' if ch in bad else ch for ch in str(name))
     return safe[:31]
@@ -273,10 +273,6 @@ def _train_ranges_df(ranges: dict[str, tuple[float, float]]) -> pd.DataFrame:
     return _round_numeric(df)
 
 def build_export_workbook() -> tuple[bytes|None, str|None, list[str]]:
-    """
-    Build a multi-sheet Excel workbook (as bytes) from what's currently in session state.
-    Returns: (bytes_or_None, filename_or_None, [sheet_names])
-    """
     res = st.session_state.get("results", {})
     if not res:
         return None, None, []
@@ -379,7 +375,6 @@ def render_export_button(key: str = "export_main") -> None:
         help="Exports all available results, metrics, summaries, OOR, training ranges, and info.",
         key=key,
     )
-# ================================================================================
 
 # =========================
 # Cross plot (Matplotlib) — auto limits for GR
@@ -524,10 +519,8 @@ def track_plot(df, include_actual=True, pred_col="GR_Pred", actual_col="GR"):
 
     return fig
 
-
 # ---------- Preview modal (matplotlib) — y-axis reversed ----------
 def preview_tracks(df: pd.DataFrame, cols: list[str]):
-    # keep only columns that exist
     cols = [c for c in cols if c in df.columns]
     n = len(cols)
     if n == 0:
@@ -535,7 +528,6 @@ def preview_tracks(df: pd.DataFrame, cols: list[str]):
         ax.text(0.5, 0.5, "No selected columns", ha="center", va="center"); ax.axis("off")
         return fig
 
-    # use Depth if present, else 1..N
     depth_col = next((c for c in df.columns if 'depth' in str(c).lower()), None)
     if depth_col is not None:
         y = pd.Series(df[depth_col], dtype=float)
@@ -544,7 +536,6 @@ def preview_tracks(df: pd.DataFrame, cols: list[str]):
         y = pd.Series(np.arange(1, len(df) + 1), dtype=float)
         ylab = "Point Index"
 
-    # IMPORTANT: don't share y so inversion always applies
     fig, axes = plt.subplots(1, n, figsize=(2.4 * n, 7.0), dpi=100, sharey=False)
     if n == 1:
         axes = [axes]
@@ -554,11 +545,8 @@ def preview_tracks(df: pd.DataFrame, cols: list[str]):
         ax.set_xlabel(col)
         ax.xaxis.set_label_position('top')
         ax.xaxis.tick_top()
-
-        # Reverse y-axis universally: shallow at top, deep at bottom
         ax.set_ylim(float(y.min()), float(y.max()))
         ax.invert_yaxis()
-
         ax.grid(True, linestyle=":", alpha=0.3)
         for s in ax.spines.values():
             s.set_visible(True)
@@ -566,7 +554,6 @@ def preview_tracks(df: pd.DataFrame, cols: list[str]):
     axes[0].set_ylabel(ylab)
     return fig
 
-
 # Modal wrapper (Streamlit compatibility)
 try:
     dialog = st.dialog
@@ -584,9 +571,11 @@ except AttributeError:
 # =========================
 def ensure_model() -> Path|None:
     for p in [DEFAULT_MODEL, *MODEL_FALLBACKS]:
-        if p.exists() and p.stat().st_size > 0: return p
+        if p.exists() and p.stat().st_size > 0:
+            return p
     url = os.environ.get("MODEL_URL", "")
-    if not url: return None
+    if not url:
+        return None
     try:
         import requests
         DEFAULT_MODEL.parent.mkdir(parents=True, exist_ok=True)
@@ -594,7 +583,8 @@ def ensure_model() -> Path|None:
             r.raise_for_status()
             with open(DEFAULT_MODEL, "wb") as f:
                 for chunk in r.iter_content(1<<20):
-                    if chunk: f.write(chunk)
+                    if chunk:
+                        f.write(chunk)
         return DEFAULT_MODEL
     except Exception:
         return None
@@ -699,8 +689,10 @@ if st.session_state.app_step == "dev":
         st.session_state.dev_preview = True
 
     run = st.sidebar.button("Run Model", type="primary", use_container_width=True)
-    if st.sidebar.button("Proceed to Validation ▶", use_container_width=True): st.session_state.app_step="validate"; st.rerun()
-    if st.sidebar.button("Proceed to Prediction ▶", use_container_width=True): st.session_state.app_step="predict"; st.rerun()
+    if st.sidebar.button("Proceed to Validation ▶", use_container_width=True):
+        st.session_state.app_step="validate"; st.rerun()
+    if st.sidebar.button("Proceed to Prediction ▶", use_container_width=True):
+        st.session_state.app_step="predict"; st.rerun()
 
     # Sticky helper
     if st.session_state.dev_file_loaded and st.session_state.dev_preview:
@@ -719,7 +711,8 @@ if st.session_state.app_step == "dev":
             st.stop()
         tr = normalize_df(book[sh_train].copy()); te = normalize_df(book[sh_test].copy())
         if not (ensure_cols(tr, FEATURES) and ensure_cols(te, FEATURES)):
-            st.markdown('<div class="st-message-box st-error">Missing required feature columns.</div>', unsafe_allow_html=True); st.stop()
+            st.markdown('<div class="st-message-box st-error">Missing required feature columns.</div>', unsafe_allow_html=True)
+            st.stop()
 
         # predictions (handle log targets)
         tr_pred_raw = model.predict(tr[FEATURES])
@@ -747,42 +740,43 @@ if st.session_state.app_step == "dev":
         st.session_state.train_ranges = {f:(float(tr_min[f]), float(tr_max[f])) for f in FEATURES}
         st.markdown('<div class="st-message-box st-success">Case has been built and results are displayed below.</div>', unsafe_allow_html=True)
 
+    # -------- Metrics + Plots (3 decimals here) --------
     def _dev_block(df, m):
-    c1, c2, c3 = st.columns(3)
-    c1.metric("R",    f"{m['R']:.3f}")
-    c2.metric("RMSE", f"{m['RMSE']:.3f}")
-    c3.metric("MAE",  f"{m['MAE']:.3f}")
-
-    st.markdown(
-        """
-        <div style='text-align:left;font-size:0.8em;color:#6b7280;margin-top:-16px;margin-bottom:8px;'>
-            <strong>R:</strong> Pearson Correlation Coefficient<br>
-            <strong>RMSE:</strong> Root Mean Square Error<br>
-            <strong>MAE:</strong> Mean Absolute Error
-        </div>
-        """,
-        unsafe_allow_html=True,
-    )
+        c1, c2, c3 = st.columns(3)
+        c1.metric("R",    f"{m['R']:.3f}")
+        c2.metric("RMSE", f"{m['RMSE']:.3f}")
+        c3.metric("MAE",  f"{m['MAE']:.3f}")
 
-    col_track, col_cross = st.columns([2, 3], gap="large")
-    with col_track:
-        st.plotly_chart(
-            track_plot(df, include_actual=True, pred_col="GR_Pred", actual_col="GR_Actual"),
-            use_container_width=False,
-            config={"displayModeBar": False, "scrollZoom": True},
+        st.markdown(
+            """
+            <div style='text-align:left;font-size:0.8em;color:#6b7280;margin-top:-16px;margin-bottom:8px;'>
+                <strong>R:</strong> Pearson Correlation Coefficient<br>
+                <strong>RMSE:</strong> Root Mean Square Error<br>
+                <strong>MAE:</strong> Mean Absolute Error
+            </div>
+            """,
+            unsafe_allow_html=True,
         )
-    with col_cross:
-        st.pyplot(cross_plot_static(df["GR_Actual"], df["GR_Pred"]), use_container_width=False)
-
-
-if "Train" in st.session_state.results or "Test" in st.session_state.results:
-    tab1, tab2 = st.tabs(["Training", "Testing"])
-    if "Train" in st.session_state.results:
-        with tab1:
-            _dev_block(st.session_state.results["Train"], st.session_state.results["m_train"])
-    if "Test" in st.session_state.results:
-        with tab2:
-            _dev_block(st.session_state.results["Test"], st.session_state.results["m_test"])
+
+        col_track, col_cross = st.columns([2, 3], gap="large")
+        with col_track:
+            st.plotly_chart(
+                track_plot(df, include_actual=True, pred_col="GR_Pred", actual_col="GR_Actual"),
+                use_container_width=False,
+                config={"displayModeBar": False, "scrollZoom": True},
+            )
+        with col_cross:
+            st.pyplot(cross_plot_static(df["GR_Actual"], df["GR_Pred"]), use_container_width=False)
+
+    if "Train" in st.session_state.results or "Test" in st.session_state.results:
+        tab1, tab2 = st.tabs(["Training", "Testing"])
+        if "Train" in st.session_state.results:
+            with tab1:
+                _dev_block(st.session_state.results["Train"], st.session_state.results["m_train"])
+        if "Test" in st.session_state.results:
+            with tab2:
+                _dev_block(st.session_state.results["Test"],  st.session_state.results["m_test"])
+
 # =========================
 # VALIDATION (with actual GR)
 # =========================
@@ -797,8 +791,10 @@ if st.session_state.app_step == "validate":
     if st.sidebar.button("Preview data", use_container_width=True, disabled=(up is None)):
         st.session_state.show_preview_modal = True
     go_btn = st.sidebar.button("Predict & Validate", 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()
-    if st.sidebar.button("Proceed to Prediction ▶", use_container_width=True): st.session_state.app_step="predict"; st.rerun()
+    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 **GR** to evaluate performance.")
 
@@ -827,7 +823,8 @@ 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(2)
                 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)
 
         st.session_state.results["m_val"]={
@@ -867,7 +864,8 @@ if st.session_state.app_step == "validate":
             )
 
         sv = st.session_state.results["sv_val"]
-        if sv["oor"] > 0: st.markdown('<div class="st-message-box st-warning">Some inputs fall outside **training min–max** ranges.</div>', unsafe_allow_html=True)
+        if sv["oor"] > 0:
+            st.markdown('<div class="st-message-box st-warning">Some inputs fall outside **training min–max** ranges.</div>', unsafe_allow_html=True)
         if st.session_state.results["oor_tbl"] is not None:
             st.write("*Out-of-range rows (vs. Training min–max):*")
             df_centered_rounded(st.session_state.results["oor_tbl"])
@@ -905,7 +903,8 @@ if st.session_state.app_step == "predict":
                 if any_viol.any():
                     oor_tbl = df.loc[any_viol, FEATURES].copy()
                     for c in FEATURES:
-                        if pd.api.types.is_numeric_dtype(oor_tbl[c]): oor_tbl[c] = oor_tbl[c].round(2)
+                        if pd.api.types.is_numeric_dtype(oor_tbl[c]):
+                            oor_tbl[c] = oor_tbl[c].round(2)
                     oor_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)
             st.session_state.results["sv_pred"]={
                 "n":len(df),