Update app.py

app.py

@@ -13,6 +13,7 @@ import matplotlib.pyplot as plt
 
 import plotly.graph_objects as go
 from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error
+from math import floor, log10
 
 # =========================
 # Defaults
@@ -30,7 +31,6 @@ COLORS = {"pred": "#1f77b4", "actual": "#f2b702", "ref": "#5a5a5a"}
 # =========================
 st.set_page_config(page_title="ST_GeoMech_UCS", page_icon="logo.png", layout="wide")
 
-# ---------- inline logo (used by password gate + header) ----------
 def inline_logo(path="logo.png") -> str:
     try:
         p = Path(path)
@@ -43,18 +43,11 @@ def inline_logo(path="logo.png") -> str:
 # Password (brand-gated)
 # =========================
 def add_password_gate() -> bool:
-    """
-    Shows a branded access screen until the correct password is entered.
-    Requires APP_PASSWORD in Secrets (or environment).
-    """
-    # 1) Read password
-    required = ""
     try:
         required = st.secrets.get("APP_PASSWORD", "")
     except Exception:
         required = os.environ.get("APP_PASSWORD", "")
 
-    # 2) If not configured, BLOCK (admin instruction)
     if not required:
         st.markdown(
             f"""
@@ -75,11 +68,9 @@ def add_password_gate() -> bool:
         )
         st.stop()
 
-    # 3) Already authenticated?
     if st.session_state.get("auth_ok", False):
         return True
 
-    # 4) Branded prompt
     st.markdown(
         f"""
         <div style="display:flex;align-items:center;gap:14px;margin:8px 0 6px 0;">
@@ -107,10 +98,9 @@ def add_password_gate() -> bool:
                 st.error("Incorrect key. Please try again.")
     st.stop()
 
-# 🔒 Gate the app
 add_password_gate()
 
-# … CSS …
+# CSS
 st.markdown("<style>header, footer{visibility:hidden !important;}</style>", unsafe_allow_html=True)
 st.markdown(
     """
@@ -136,7 +126,6 @@ st.markdown(
 try:
     dialog = st.dialog
 except AttributeError:
-    # Fallback (expander) if st.dialog is unavailable
     def dialog(title):
         def deco(fn):
             def wrapper(*args, **kwargs):
@@ -179,7 +168,24 @@ def find_sheet(book, names):
         if nm.lower() in low2orig: return low2orig[nm.lower()]
     return None
 
-# ---------- Interactive plotting (full outline, bold axis titles) ----------
+# ----- Nice tick step for cross-plot -----
+def _nice_dtick(data_range: float) -> float:
+    if data_range <= 0 or np.isnan(data_range): return 1.0
+    raw = data_range / 6.0  # aim ~6 ticks
+    k = floor(log10(raw))
+    base = 10 ** k
+    m = raw / base
+    if m <= 1.5:
+        step = 1 * base
+    elif m <= 3.5:
+        step = 2 * base
+    elif m <= 7.5:
+        step = 5 * base
+    else:
+        step = 10 * base
+    return step
+
+# ---------- Interactive plotting ----------
 def cross_plot_interactive(actual, pred, size=(3.9, 3.9)):
     a = pd.Series(actual).astype(float)
     p = pd.Series(pred).astype(float)
@@ -187,12 +193,13 @@ def cross_plot_interactive(actual, pred, size=(3.9, 3.9)):
     hi = float(np.nanmax([a.max(), p.max()]))
     pad = 0.03 * (hi - lo if hi > lo else 1.0)
     x0, x1 = lo - pad, hi + pad
+    dtick = _nice_dtick(x1 - x0)
 
     fig = go.Figure()
     fig.add_trace(go.Scatter(
         x=a, y=p, mode="markers",
         marker=dict(size=6, color=COLORS["pred"]),
-        hovertemplate="Actual: %{x:.2f}<br>Pred: %{y:.2f}<extra></extra>",
+        hovertemplate="Actual: %{x:.0f}<br>Pred: %{y:.0f}<extra></extra>",
         showlegend=False
     ))
     fig.add_trace(go.Scatter(
@@ -203,18 +210,18 @@ def cross_plot_interactive(actual, pred, size=(3.9, 3.9)):
     fig.update_layout(
         paper_bgcolor="#ffffff", plot_bgcolor="#ffffff",
         margin=dict(l=50, r=10, t=10, b=36),
-        hovermode="closest", font=dict(size=13)
+        hovermode="closest", font=dict(size=13), dragmode="zoom"
     )
     fig.update_xaxes(
         title_text="<b>Actual UCS</b>",
-        range=[x0, x1], ticks="outside",
+        range=[x0, x1], tickmode="linear", dtick=dtick, ticks="outside",
         showline=True, linewidth=1.2, linecolor="#444", mirror=True,
         showgrid=True, gridcolor="rgba(0,0,0,0.12)",
         tickformat=",.0f", automargin=True
     )
     fig.update_yaxes(
         title_text="<b>Predicted UCS</b>",
-        range=[x0, x1], ticks="outside",
+        range=[x0, x1], tickmode="linear", dtick=dtick, ticks="outside",
         showline=True, linewidth=1.2, linecolor="#444", mirror=True,
         showgrid=True, gridcolor="rgba(0,0,0,0.12)",
         tickformat=",.0f", scaleanchor="x", scaleratio=1,
@@ -224,7 +231,7 @@ def cross_plot_interactive(actual, pred, size=(3.9, 3.9)):
     fig.update_layout(width=w, height=h)
     return fig
 
-def depth_or_index_track_interactive(df, title=None, include_actual=True):
+def depth_or_index_track_interactive(df, title=None, include_actual=True, x_range=None):
     depth_col = next((c for c in df.columns if 'depth' in str(c).lower()), None)
     if depth_col is not None:
         y = df[depth_col]; y_label = depth_col
@@ -236,16 +243,17 @@ def depth_or_index_track_interactive(df, title=None, include_actual=True):
         x=df["UCS_Pred"], y=y, mode="lines",
         line=dict(color=COLORS["pred"], width=1.8),
         name="UCS_Pred",
-        hovertemplate="UCS_Pred: %{x:.2f}<br>"+y_label+": %{y}<extra></extra>"
+        hovertemplate="UCS_Pred: %{x:.0f}<br>"+y_label+": %{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="UCS (actual)",
-            hovertemplate="UCS (actual): %{x:.2f}<br>"+y_label+": %{y}<extra></extra>"
+            hovertemplate="UCS (actual): %{x:.0f}<br>"+y_label+": %{y}<extra></extra>"
         ))
 
+    # slimmer & taller like a log profile
     fig.update_layout(
         paper_bgcolor="#ffffff", plot_bgcolor="#ffffff",
         margin=dict(l=60, r=10, t=10, b=36),
@@ -255,14 +263,17 @@ def depth_or_index_track_interactive(df, title=None, include_actual=True):
             bgcolor="rgba(255,255,255,0.75)", bordercolor="#cccccc", borderwidth=1
         ),
         legend_title_text="",
-        width=int(3.1 * 100),
-        height=int((7.6 if depth_col is not None else 7.2) * 100),
+        width=int(2.4 * 100),   # narrower
+        height=int(8.4 * 100),  # taller
+        dragmode="zoom"
     )
     fig.update_xaxes(
         title_text="<b>UCS</b>", side="top",
         ticks="outside", showline=True, linewidth=1.2, linecolor="#444", mirror=True,
         showgrid=True, gridcolor="rgba(0,0,0,0.12)",
-        tickformat=",.0f", automargin=True
+        tickformat=",.0f",
+        automargin=True,
+        range=x_range
     )
     fig.update_yaxes(
         title_text=f"<b>{y_label}</b>", autorange="reversed",
@@ -398,26 +409,15 @@ 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
 
-# Dev page state (persist file)
-for k, v in {
-    "dev_ready": False,
-    "dev_file_loaded": False,
-    "dev_previewed": False,
-    "dev_file_signature": None,
-    "dev_preview_request": False,
-    "dev_file_bytes": b"",
-    "dev_file_name": "",
-    "dev_file_rows": 0,
-    "dev_file_cols": 0,
-    # validation (was predict)
-    "val_file_bytes": b"",
-    "val_file_loaded": False,
-    "val_preview_request": False,
-    # prediction (new)
-    "pred_file_bytes": b"",
-    "pred_file_loaded": False,
-    "pred_preview_request": False,
-}.items():
+# Dev/Val/Pred state
+defaults = {
+    "dev_ready": False, "dev_file_loaded": False, "dev_previewed": False,
+    "dev_file_signature": None, "dev_preview_request": False,
+    "dev_file_bytes": b"", "dev_file_name": "", "dev_file_rows": 0, "dev_file_cols": 0,
+    "val_file_bytes": b"", "val_file_loaded": False, "val_preview_request": False,
+    "pred_file_bytes": b"", "pred_file_loaded": False, "pred_preview_request": False,
+}
+for k, v in defaults.items():
     if k not in st.session_state: st.session_state[k] = v
 
 # =========================
@@ -441,9 +441,7 @@ st.markdown(
 # =========================
 if st.session_state.app_step == "intro":
     st.header("Welcome!")
-    st.markdown(
-        "This software is developed by *Smart Thinking AI-Solutions Team* to estimate UCS from drilling data."
-    )
+    st.markdown("This software is developed by *Smart Thinking AI-Solutions Team* to estimate UCS from drilling data.")
     st.subheader("Expected Input Features (in Order)")
     st.markdown(
         "- Q, gpm — Flow rate (gallons per minute)  \n"
@@ -471,7 +469,6 @@ if st.session_state.app_step == "dev":
     dev_label = "Upload Data (Excel)" if not st.session_state.dev_file_name else "Replace data (Excel)"
     train_test_file = st.sidebar.file_uploader(dev_label, type=["xlsx","xls"], key="dev_upload")
 
-    # Detect new/changed file and PERSIST BYTES
     if train_test_file is not None:
         try:
             file_bytes = train_test_file.getvalue(); size = len(file_bytes)
@@ -503,7 +500,7 @@ if st.session_state.app_step == "dev":
 
     run_btn = st.sidebar.button("Run Model", type="primary", use_container_width=True)
 
-    # Always enabled so users can jump ahead
+    # jump links
     proceed_val = st.sidebar.button("Proceed to Validation ▶", use_container_width=True)
     proceed_pred = st.sidebar.button("Proceed to Prediction ▶", use_container_width=True)
     if proceed_val:
@@ -511,7 +508,6 @@ if st.session_state.app_step == "dev":
     if proceed_pred:
         st.session_state.app_step = "predict"; st.rerun()
 
-    # Helper (always at top)
     with st.container():
         st.subheader("Case Building")
         if st.session_state.dev_ready:
@@ -578,8 +574,20 @@ if st.session_state.app_step == "dev":
                         use_container_width=True, config={"displayModeBar": False}
                     )
                 with right:
+                    # Zoom control for UCS axis
+                    pr_min = float(df["UCS_Pred"].min())
+                    xs = [pr_min]
+                    if TARGET in df: xs.append(float(df[TARGET].min()))
+                    x_min = min(xs)
+                    pr_max = float(df["UCS_Pred"].max())
+                    xs = [pr_max]
+                    if TARGET in df: xs.append(float(df[TARGET].max()))
+                    x_max = max(xs)
+                    with st.expander("Zoom (UCS axis)", expanded=False):
+                        z = st.slider("UCS range", min_value=float(x_min), max_value=float(x_max),
+                                      value=(float(x_min), float(x_max)), step=10.0, key="zoom_train")
                     st.plotly_chart(
-                        depth_or_index_track_interactive(df, title=None, include_actual=True),
+                        depth_or_index_track_interactive(df, title=None, include_actual=True, x_range=z),
                         use_container_width=True, config={"displayModeBar": False}
                     )
         if "Test" in st.session_state.results:
@@ -594,8 +602,19 @@ if st.session_state.app_step == "dev":
                         use_container_width=True, config={"displayModeBar": False}
                     )
                 with right:
+                    pr_min = float(df["UCS_Pred"].min())
+                    xs = [pr_min]
+                    if TARGET in df: xs.append(float(df[TARGET].min()))
+                    x_min = min(xs)
+                    pr_max = float(df["UCS_Pred"].max())
+                    xs = [pr_max]
+                    if TARGET in df: xs.append(float(df[TARGET].max()))
+                    x_max = max(xs)
+                    with st.expander("Zoom (UCS axis)", expanded=False):
+                        z2 = st.slider("UCS range", min_value=float(x_min), max_value=float(x_max),
+                                       value=(float(x_min), float(x_max)), step=10.0, key="zoom_test")
                     st.plotly_chart(
-                        depth_or_index_track_interactive(df, title=None, include_actual=True),
+                        depth_or_index_track_interactive(df, title=None, include_actual=True, x_range=z2),
                         use_container_width=True, config={"displayModeBar": False}
                     )
 
@@ -625,7 +644,7 @@ if st.session_state.app_step == "dev":
             st.warning(str(e))
 
 # =========================
-# 2) VALIDATE THE MODEL (was predict)
+# 2) VALIDATE THE MODEL
 # =========================
 if st.session_state.app_step == "validate":
     st.sidebar.header("Validate the model")
@@ -644,14 +663,11 @@ if st.session_state.app_step == "validate":
         st.session_state.val_preview_request = True
 
     predict_btn = st.sidebar.button("Run Validation", type="primary", use_container_width=True)
-
-    # Always enabled
     proceed_pred = st.sidebar.button("Proceed to Prediction ▶", use_container_width=True)
     st.sidebar.button("⬅ Back to Case Building", on_click=lambda: st.session_state.update(app_step="dev"), use_container_width=True)
     if proceed_pred:
         st.session_state.app_step = "predict"; st.rerun()
 
-    # Helper
     with st.container():
         st.subheader("Validate the model")
         st.write("Upload a validation dataset (with actual UCS if available), preview it, then run to view metrics and plots.")
@@ -661,7 +677,6 @@ if st.session_state.app_step == "validate":
         st.session_state.val_preview_request = False
         preview_modal_val(_book, FEATURES)
 
-    # Run validation
     if predict_btn and st.session_state.val_file_bytes:
         with st.status("Validating…", expanded=False) as status:
             vbook = read_book_bytes(st.session_state.val_file_bytes)
@@ -700,7 +715,6 @@ if st.session_state.app_step == "validate":
             st.session_state.results["oor_table"] = oor_table
             status.update(label="Validation ready ✓", state="complete")
 
-    # Display
     if "Validate" in st.session_state.results:
         sv = st.session_state.results["summary_val"]; oor_table = st.session_state.results.get("oor_table")
 
@@ -733,11 +747,23 @@ if st.session_state.app_step == "validate":
             else:
                 st.info("Actual UCS values are not available in the validation data. Cross-plot cannot be generated.")
         with right:
+            df = st.session_state.results["Validate"]
+            pr_min = float(df["UCS_Pred"].min())
+            xs = [pr_min]
+            if TARGET in df: xs.append(float(df[TARGET].min()))
+            x_min = min(xs)
+            pr_max = float(df["UCS_Pred"].max())
+            xs = [pr_max]
+            if TARGET in df: xs.append(float(df[TARGET].max()))
+            x_max = max(xs)
+            with st.expander("Zoom (UCS axis)", expanded=False):
+                zv = st.slider("UCS range", min_value=float(x_min), max_value=float(x_max),
+                               value=(float(x_min), float(x_max)), step=10.0, key="zoom_val")
             st.plotly_chart(
                 depth_or_index_track_interactive(
-                    st.session_state.results["Validate"],
-                    title=None,
-                    include_actual=(TARGET in st.session_state.results["Validate"].columns)
+                    df, title=None,
+                    include_actual=(TARGET in df.columns),
+                    x_range=zv
                 ),
                 use_container_width=True, config={"displayModeBar": False}
             )
@@ -770,7 +796,7 @@ if st.session_state.app_step == "validate":
             st.warning(str(e))
 
 # =========================
-# 3) PREDICTION (production scoring, no actual UCS)
+# 3) PREDICTION (no actual UCS)
 # =========================
 if st.session_state.app_step == "predict":
     st.sidebar.header("Prediction")
@@ -798,10 +824,8 @@ if st.session_state.app_step == "predict":
     if st.session_state.pred_preview_request and st.session_state.pred_file_bytes:
         _book = read_book_bytes(st.session_state.pred_file_bytes)
         st.session_state.pred_preview_request = False
-        # Reuse the same previewer (no special sheet naming required)
         preview_modal_val(_book, FEATURES)
 
-    # Run prediction
     if predict_btn and st.session_state.pred_file_bytes:
         with st.status("Predicting…", expanded=False) as status:
             pbook = read_book_bytes(st.session_state.pred_file_bytes)
@@ -814,7 +838,6 @@ if st.session_state.app_step == "predict":
             df_pred["UCS_Pred"] = model.predict(df_pred[FEATURES])
             st.session_state.results["Prediction"] = df_pred
 
-            # OOR vs training ranges if available
             ranges = st.session_state.train_ranges; oor_table = None; oor_pct = 0.0
             if ranges:
                 viol = {f: (df_pred[f] < ranges[f][0]) | (df_pred[f] > ranges[f][1]) for f in FEATURES}
@@ -835,13 +858,11 @@ if st.session_state.app_step == "predict":
             st.session_state.results["oor_table_pred"] = oor_table
             status.update(label="Predictions ready ✓", state="complete")
 
-    # Display prediction results (no cross-plot)
     if "Prediction" in st.session_state.results:
         sv = st.session_state.results["summary_pred"]
         if sv.get("oor_pct", 0) > 0:
             st.warning("Some inputs fall outside the **training min–max** ranges. Interpret predictions with caution.")
 
-        # Two columns: table (left), track (right)
         left, right = st.columns([0.6, 0.9])
         with left:
             table = pd.DataFrame(
@@ -858,21 +879,26 @@ if st.session_state.app_step == "predict":
                 }
             )
             st.dataframe(table, use_container_width=True, hide_index=True)
+            # ★ footnote under table
+            st.caption("★ OOR % = percentage of rows where at least one input feature is outside the training set's min–max range.")
         with right:
+            # Optional zoom
+            dfp = st.session_state.results["Prediction"]
+            pmin, pmax = float(dfp["UCS_Pred"].min()), float(dfp["UCS_Pred"].max())
+            with st.expander("Zoom (UCS axis)", expanded=False):
+                zp = st.slider("UCS range", min_value=pmin, max_value=pmax, value=(pmin, pmax), step=10.0, key="zoom_pred")
             st.plotly_chart(
                 depth_or_index_track_interactive(
-                    st.session_state.results["Prediction"], title=None, include_actual=False
+                    dfp, title=None, include_actual=False, x_range=zp
                 ),
                 use_container_width=True, config={"displayModeBar": False}
             )
 
-        # OOR table if any
         if st.session_state.results.get("oor_table_pred") is not None:
             st.write("*Out-of-range rows (vs. Training min–max):*")
             st.dataframe(st.session_state.results["oor_table_pred"], use_container_width=True)
 
         st.markdown("---")
-        # Export predictions + summary
         try:
             buf = io.BytesIO()
             with pd.ExcelWriter(buf, engine="openpyxl") as xw: