Update app.py

app.py

@@ -29,8 +29,6 @@ COLORS = {
 # Page / Theme
 # =========================
 st.set_page_config(page_title="ST_GeoMech_UCS", page_icon="logo.png", layout="wide")
-
-# Hide Streamlit default header/footer and tighten layout
 st.markdown("<style>header, footer{visibility:hidden !important;}</style>", unsafe_allow_html=True)
 st.markdown(
     """
@@ -53,11 +51,10 @@ st.markdown(
 # =========================
 # Helpers
 # =========================
-
-# Prefer real dialog (Streamlit ≥1.31). Fallback to expander if older.
 try:
     dialog = st.dialog
 except AttributeError:
+    # Back-compat shim if st.dialog isn't available
     def dialog(title):
         def deco(fn):
             def wrapper(*args, **kwargs):
@@ -102,31 +99,23 @@ def find_sheet(book, names):
     return None
 
 def cross_plot(actual, pred, title, size=(3.9, 3.9)):
-    """Compact, square cross-plot with a 1:1 reference line."""
     fig, ax = plt.subplots(figsize=size, dpi=100)
     ax.scatter(actual, pred, s=14, alpha=0.85, color=COLORS["pred"])
     lo = float(np.nanmin([actual.min(), pred.min()]))
     hi = float(np.nanmax([actual.max(), pred.max()]))
     pad = 0.03 * (hi - lo if hi > lo else 1.0)
-    ax.plot([lo - pad, hi + pad], [lo - pad, hi + pad],
-            '--', lw=1.2, color=COLORS["ref"])
-    ax.set_xlim(lo - pad, hi + pad)
-    ax.set_ylim(lo - pad, hi + pad)
-    ax.set_aspect('equal', 'box')  # perfect 1:1
+    ax.plot([lo - pad, hi + pad], [lo - pad, hi + pad], '--', lw=1.2, color=COLORS["ref"])
+    ax.set_xlim(lo - pad, hi + pad); ax.set_ylim(lo - pad, hi + pad)
+    ax.set_aspect('equal', 'box')
     ax.set_xlabel("Actual UCS"); ax.set_ylabel("Predicted UCS"); ax.set_title(title)
     ax.grid(True, ls=":", alpha=0.4)
     return fig
 
 def depth_or_index_track(df, title=None, include_actual=True):
-    """
-    Narrow, tall track: predicted solid blue; actual dotted yellow.
-    Works for either Depth on Y or Index on Y.
-    """
     depth_col = next((c for c in df.columns if 'depth' in str(c).lower()), None)
     fig_w = 3.1
     fig_h = 7.6 if depth_col is not None else 7.2
     fig, ax = plt.subplots(figsize=(fig_w, fig_h), dpi=100)
-
     if depth_col is not None:
         ax.plot(df["UCS_Pred"], df[depth_col], '-', lw=1.8, color=COLORS["pred"], label="UCS_Pred")
         if include_actual and TARGET in df.columns:
@@ -140,7 +129,6 @@ def depth_or_index_track(df, title=None, include_actual=True):
             ax.plot(df[TARGET], idx, ':', lw=2.0, color=COLORS["actual"], alpha=0.95, label="UCS (actual)")
         ax.set_ylabel("Point Index"); ax.set_xlabel("UCS")
         ax.xaxis.set_label_position('top'); ax.xaxis.tick_top(); ax.invert_yaxis()
-
     ax.grid(True, linestyle=":", alpha=0.4)
     if title: ax.set_title(title, pad=8)
     ax.legend(loc="best")
@@ -182,9 +170,7 @@ def inline_logo(path="logo.png") -> str:
         return ""
 
 # ---------- Preview modal helpers ----------
-
 def make_index_tracks(df: pd.DataFrame, cols: list[str]):
-    """Build a side-by-side index track figure (log-style) for given columns."""
     cols = [c for c in cols if c in df.columns]
     n = len(cols)
     if n == 0:
@@ -192,14 +178,13 @@ def make_index_tracks(df: pd.DataFrame, cols: list[str]):
         ax.text(0.5, 0.5, "No selected columns in sheet", ha="center", va="center")
         ax.axis("off")
         return fig
-    width_per = 2.2  # width per track
+    width_per = 2.2
     fig_h = 7.0
     fig, axes = plt.subplots(1, n, figsize=(width_per * n, fig_h), sharey=True, dpi=100)
-    if n == 1:
-        axes = [axes]
+    if n == 1: axes = [axes]
     idx = np.arange(1, len(df) + 1)
     for ax, col in zip(axes, cols):
-        ax.plot(df[col], idx, '-', lw=1.4, color="#333333")
+        ax.plot(df[col], idx, '-', lw=1.4, color="#333")
         ax.set_xlabel(col)
         ax.xaxis.set_label_position('top'); ax.xaxis.tick_top(); ax.invert_yaxis()
         ax.grid(True, linestyle=":", alpha=0.3)
@@ -212,47 +197,37 @@ def stats_table(df: pd.DataFrame, cols: list[str]) -> pd.DataFrame:
         return pd.DataFrame({"Feature": [], "Min": [], "Max": [], "Mean": [], "Std": []})
     out = df[cols].agg(['min', 'max', 'mean', 'std']).T
     out = out.rename(columns={"min": "Min", "max": "Max", "mean": "Mean", "std": "Std"})
-    out = out.reset_index().rename(columns={"index": "Feature"})
-    return out
+    return out.reset_index().rename(columns={"index": "Feature"})
 
 @dialog("Preview data")
 def preview_modal_dev(book: dict[str, pd.DataFrame], feature_cols: list[str]):
     if not book:
-        st.info("No data loaded yet.")
-        return
-    # Auto detect Train/Test-like sheets
+        st.info("No data loaded yet."); return
     sh_train = find_sheet(book, ["Train","Training","training2","train","training"])
     sh_test  = find_sheet(book, ["Test","Testing","testing2","test","testing"])
-    tabs = []
-    data = []
+    tabs, data = [], []
     if sh_train: tabs.append("Train"); data.append(book[sh_train])
     if sh_test:  tabs.append("Test");  data.append(book[sh_test])
-    if not tabs:  # nothing matched, just show the first sheet
+    if not tabs:
         first_name = list(book.keys())[0]
         tabs = [first_name]; data = [book[first_name]]
-
     st.write("Use the tabs to switch between Train/Test views (if available).")
     t_objs = st.tabs(tabs)
     for t, df in zip(t_objs, data):
         with t:
-            tab_tracks, tab_summary = st.tabs(["Tracks", "Summary"])
-            with tab_tracks:
-                st.pyplot(make_index_tracks(df, feature_cols), use_container_width=True)
-            with tab_summary:
-                st.dataframe(stats_table(df, feature_cols), use_container_width=True)
+            t1, t2 = st.tabs(["Tracks", "Summary"])
+            with t1: st.pyplot(make_index_tracks(df, feature_cols), use_container_width=True)
+            with t2: st.dataframe(stats_table(df, feature_cols), use_container_width=True)
 
 @dialog("Preview data")
 def preview_modal_val(book: dict[str, pd.DataFrame], feature_cols: list[str]):
     if not book:
-        st.info("No data loaded yet.")
-        return
+        st.info("No data loaded yet."); return
     vname = find_sheet(book, ["Validation","Validate","validation2","Val","val"]) or list(book.keys())[0]
     df = book[vname]
-    tab_tracks, tab_summary = st.tabs(["Tracks", "Summary"])
-    with tab_tracks:
-        st.pyplot(make_index_tracks(df, feature_cols), use_container_width=True)
-    with tab_summary:
-        st.dataframe(stats_table(df, feature_cols), use_container_width=True)
+    t1, t2 = st.tabs(["Tracks", "Summary"])
+    with t1: st.pyplot(make_index_tracks(df, feature_cols), use_container_width=True)
+    with t2: st.dataframe(stats_table(df, feature_cols), use_container_width=True)
 
 # =========================
 # Model presence (local or optional download)
@@ -308,11 +283,14 @@ if "app_step" not in st.session_state: st.session_state.app_step = "intro"
 if "results" not in st.session_state: st.session_state.results = {}
 if "train_ranges" not in st.session_state: st.session_state.train_ranges = None
 if "dev_ready" not in st.session_state: st.session_state.dev_ready = False
+if "dev_file_loaded" not in st.session_state: st.session_state.dev_file_loaded = False
+if "dev_previewed" not in st.session_state: st.session_state.dev_previewed = False
+
 if ("Train" in st.session_state.results) or ("Test" in st.session_state.results):
     st.session_state.dev_ready = True
 
 # =========================
-# Hero header (logo + title) — website link moved to footer
+# Hero header (logo + title)
 # =========================
 st.markdown(
     f"""
@@ -345,9 +323,10 @@ if st.session_state.app_step == "intro":
     )
     st.subheader("How It Works")
     st.markdown(
-        "1. **Upload your development data (Excel)** and click **Run Model** to compute metrics and review plots.  \n"
-        "2. Click **Proceed to Prediction** to upload a new dataset for validation and view results.  \n"
-        "3. Export results to Excel at any time."
+        "1. **Upload your data to build the case and preview the performance of our model.**  \n"
+        "2. Click **Run Model** to compute metrics and plots.  \n"
+        "3. Click **Proceed to Prediction** to validate on a new dataset.  \n"
+        "4. Export results to Excel at any time."
     )
     if st.button("Start Showcase", type="primary", key="start_showcase"):
         st.session_state.app_step = "dev"; st.rerun()
@@ -357,27 +336,32 @@ if st.session_state.app_step == "intro":
 # =========================
 if st.session_state.app_step == "dev":
     st.sidebar.header("Model Development Data")
-    dev_label = "Upload Data (Excel)"
-    if st.session_state.get("dev_file_name"):
-        dev_label = "Replace data (Excel)"
+
+    dev_label = "Upload Data (Excel)" if not st.session_state.get("dev_file_name") else "Replace data (Excel)"
     train_test_file = st.sidebar.file_uploader(dev_label, type=["xlsx","xls"], key="dev_upload")
+
+    # If a file is uploaded, parse once and set flags
     if train_test_file is not None:
         st.session_state.dev_file_name = train_test_file.name
-        # small status line in sidebar
         _book_tmp = read_book(train_test_file)
         if _book_tmp:
             first_df = next(iter(_book_tmp.values()))
             st.sidebar.caption(f"**Data loaded:** {train_test_file.name} • {first_df.shape[0]} rows × {first_df.shape[1]} cols")
+            st.session_state.dev_file_loaded = True
+            # Reset preview + readiness on new upload
+            st.session_state.dev_previewed = False
+            st.session_state.dev_ready = False
 
     # Preview button (modal)
-    preview_btn = st.sidebar.button("Preview data", use_container_width=True, disabled=(train_test_file is None))
-    if preview_btn and train_test_file is not None:
+    preview_btn = st.sidebar.button("Preview data", use_container_width=True, disabled=not st.session_state.dev_file_loaded)
+    if preview_btn and st.session_state.dev_file_loaded and train_test_file is not None:
         _book = read_book(train_test_file)
+        st.session_state.dev_previewed = True   # mark previewed
         preview_modal_dev(_book, FEATURES)
 
     run_btn = st.sidebar.button("Run Model", type="primary", use_container_width=True)
 
-    # Proceed button BELOW run, always visible; enables after first successful run
+    # Proceed button BELOW run, visible always; enables after first successful run
     st.sidebar.button(
         "Proceed to Prediction ▶",
         use_container_width=True,
@@ -385,9 +369,16 @@ if st.session_state.app_step == "dev":
         on_click=(lambda: st.session_state.update(app_step="predict")) if st.session_state.dev_ready else None,
     )
 
-    # Header + helper sentence under the header
+    # ----- Title & helper (ALWAYS visible; state-aware) -----
     st.subheader("Model Development")
-    st.write("**Upload your data to build a case, run the model, and review the development performance.**")
+    if st.session_state.dev_ready:
+        st.success("Case has been built and results are displayed below.")
+    elif st.session_state.dev_file_loaded and st.session_state.dev_previewed:
+        st.info("Previewed ✓ — now click **Run Model** to build the case.")
+    elif st.session_state.dev_file_loaded:
+        st.info("📄 **Preview uploaded data** using the sidebar button, then click **Run Model**.")
+    else:
+        st.write("**Upload your data to build a case, then run the model to review development performance.**")
 
     if run_btn and train_test_file is not None:
         with st.status("Processing…", expanded=False) as status:
@@ -427,8 +418,9 @@ if st.session_state.app_step == "dev":
 
             st.session_state.dev_ready = True  # enable Proceed button immediately
             status.update(label="Done ✓", state="complete"); toast("Model run complete 🚀")
-            st.rerun()  # refresh to enable the sidebar button without a second click
+            st.rerun()  # refresh UI to reflect new helper & enabled button
 
+    # Results
     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:
@@ -436,12 +428,11 @@ if st.session_state.app_step == "dev":
                 df = st.session_state.results["Train"]; m = st.session_state.results["metrics_train"]
                 c1,c2,c3 = st.columns(3)
                 c1.metric("R²", f"{m['R2']:.4f}"); c2.metric("RMSE", f"{m['RMSE']:.4f}"); c3.metric("MAE", f"{m['MAE']:.4f}")
-                left, right = st.columns([0.9, 0.55])  # slim track column
+                left, right = st.columns([0.9, 0.55])
                 with left:
                     st.pyplot(cross_plot(df[TARGET], df["UCS_Pred"], "Training: Actual vs Predicted"), use_container_width=True)
                 with right:
                     st.pyplot(depth_or_index_track(df, title=None, include_actual=True), use_container_width=True)
-
         if "Test" in st.session_state.results:
             with tab2:
                 df = st.session_state.results["Test"]; m = st.session_state.results["metrics_test"]
@@ -475,9 +466,7 @@ if st.session_state.app_step == "dev":
 # =========================
 if st.session_state.app_step == "predict":
     st.sidebar.header("Prediction (Validation)")
-    val_label = "Upload Validation Excel"
-    if st.session_state.get("val_file_name"):
-        val_label = "Replace data (Excel)"
+    val_label = "Upload Validation Excel" if not st.session_state.get("val_file_name") else "Replace data (Excel)"
     validation_file = st.sidebar.file_uploader(val_label, type=["xlsx","xls"], key="val_upload")
     if validation_file is not None:
         st.session_state.val_file_name = validation_file.name
@@ -486,7 +475,6 @@ if st.session_state.app_step == "predict":
             first_df = next(iter(_book_tmp.values()))
             st.sidebar.caption(f"**Data loaded:** {validation_file.name} • {first_df.shape[0]} rows × {first_df.shape[1]} cols")
 
-    # Preview button for validation data
     preview_val_btn = st.sidebar.button("Preview data", use_container_width=True, disabled=(validation_file is None))
     if preview_val_btn and validation_file is not None:
         _book = read_book(validation_file)
@@ -547,17 +535,13 @@ if st.session_state.app_step == "predict":
         c1.metric("points", f"{sv['n_points']}"); c2.metric("Pred min", f"{sv['pred_min']:.2f}")
         c3.metric("Pred max", f"{sv['pred_max']:.2f}"); c4.metric("OOR %", f"{sv['oor_pct']:.1f}%")
 
-        left, right = st.columns([0.9, 0.55])  # slim log-look track
+        left, right = st.columns([0.9, 0.55])
         with left:
             if TARGET in st.session_state.results["Validate"].columns:
-                st.pyplot(
-                    cross_plot(
-                        st.session_state.results["Validate"][TARGET],
-                        st.session_state.results["Validate"]["UCS_Pred"],
-                        "Validation: Actual vs Predicted"
-                    ),
-                    use_container_width=True
-                )
+                st.pyplot(cross_plot(st.session_state.results["Validate"][TARGET],
+                                     st.session_state.results["Validate"]["UCS_Pred"],
+                                     "Validation: Actual vs Predicted"),
+                          use_container_width=True)
             else:
                 st.info("Actual UCS values are not available in the validation data. Cross-plot cannot be generated.")
         with right: