Update app.py

app.py

@@ -29,15 +29,15 @@ from sklearn.impute import SimpleImputer
 APP_NAME = "ST_Min_Horizontal_Stress"
 TAGLINE  = "Real-Time Minimum Horizontal Stress Prediction"
 
-# -------- Option B (canonical names = what your files already have) --------
+# -------- Canonical names (match your files) --------
 FEATURES   = ["Q (gpm)", "SPP (psi)", "T (kft.lbf)", "WOB (klbf)", "ROP (ft/h)"]
 TARGET     = "MINStress_Actual"
 PRED_COL   = "MINStress_Pred"
 ACTUAL_COL = TARGET
 TRANSFORM  = "none"     # "none" | "log10" | "ln"
-UNITS      = "MPa"
+UNITS      = "Psi"
 
-# ---- "Best" (fixed) model setup baked into the code (no grid search UI) ----
+# ---- Fixed ("best") model params baked into the code ----
 BEST_PARAMS = dict(
     n_estimators=400,
     max_depth=None,
@@ -354,7 +354,7 @@ def cross_plot_static(actual, pred):
     ax.set_xticks(ticks);  ax.set_yticks(ticks)
     ax.set_aspect("equal", adjustable="box")
 
-    fmt = FuncFormatter(lambda x, _: f"{x:.2f}")
+    fmt = FuncFormatter(lambda x, _: f"{x:.0f}")  # no decimals on cross-plot
     ax.xaxis.set_major_formatter(fmt); ax.yaxis.set_major_formatter(fmt)
 
     ax.set_xlabel(f"Actual Min Stress ({UNITS})",  fontweight="bold", fontsize=10, color="black")
@@ -415,7 +415,9 @@ def track_plot(df, include_actual=True):
         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=",.2f", tickmode="auto", tick0=tick0,
+        ticks="outside",
+        tickformat=",.0f",      # <— no decimals on ticks
+        tickmode="auto", tick0=tick0,
         showline=True, linewidth=1.2, linecolor="#444", mirror=True,
         showgrid=True, gridcolor="rgba(0,0,0,0.12)", automargin=True
     )
@@ -496,8 +498,11 @@ st.session_state.setdefault("dev_file_name","")
 st.session_state.setdefault("dev_file_bytes",b"")
 st.session_state.setdefault("dev_file_loaded",False)
 st.session_state.setdefault("dev_preview",False)
-st.session_state.setdefault("show_preview_modal", False)
-st.session_state.setdefault("fitted_model", None)  # cache trained pipeline
+st.session_state.setdefault("fitted_model", None)      # cache trained pipeline
+
+# NEW: persistent top-of-page preview panel state
+st.session_state.setdefault("show_preview_panel", False)
+st.session_state.setdefault("preview_book", {})        # parsed Excel sheets to preview
 
 # =========================
 # Sidebar branding
@@ -527,6 +532,50 @@ def sticky_header(title, message):
         unsafe_allow_html=True
     )
 
+# ---------- Top-of-page Preview Panel ----------
+def render_preview_panel():
+    """If enabled, draws a preview panel at the very top of the page."""
+    if not st.session_state.get("show_preview_panel"):
+        return
+
+    st.markdown("## 🔎 Data preview")
+    book = st.session_state.get("preview_book", {}) or {}
+    if not book:
+        st.info("No data loaded yet.")
+        col = st.columns(2)[1]
+        with col:
+            if st.button("Hide preview"):
+                st.session_state.show_preview_panel = False
+                st.session_state.preview_book = {}
+                st.rerun()
+        return
+
+    names = list(book.keys())
+    tabs = st.tabs(names + ["✖ Hide preview"])
+    for i, name in enumerate(names):
+        with tabs[i]:
+            df = book[name]
+            t1, t2 = st.tabs(["Tracks", "Summary"])
+            with t1:
+                st.pyplot(preview_tracks(df, FEATURES), use_container_width=True)
+            with t2:
+                feat_present = [c for c in FEATURES if c in df.columns]
+                if not feat_present:
+                    st.info("No feature columns found to summarize.")
+                else:
+                    tbl = (
+                        df[feat_present]
+                          .agg(['min','max','mean','std'])
+                          .T.rename(columns={"min":"Min","max":"Max","mean":"Mean","std":"Std"})
+                          .reset_index(names="Feature")
+                    )
+                    df_centered_rounded(tbl)
+    with tabs[-1]:
+        if st.button("Hide preview", use_container_width=True):
+            st.session_state.show_preview_panel = False
+            st.session_state.preview_book = {}
+            st.rerun()
+
 # =========================
 # INTRO
 # =========================
@@ -567,21 +616,26 @@ if st.session_state.app_step == "dev":
             df0 = next(iter(tmp.values()))
             st.sidebar.caption(f"**Data loaded:** {st.session_state.dev_file_name} • {df0.shape[0]} rows × {df0.shape[1]} cols")
 
+    # PREVIEW button -> show preview panel at top
     if st.sidebar.button("Preview data", use_container_width=True, disabled=not st.session_state.dev_file_loaded):
-        st.session_state.show_preview_modal = True
-        st.session_state.dev_preview = True
+        st.session_state.preview_book = read_book_bytes(st.session_state.dev_file_bytes) if st.session_state.dev_file_bytes else {}
+        st.session_state.show_preview_panel = True
+        st.rerun()
 
     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.session_state.dev_file_loaded and st.session_state.dev_preview:
+    if st.session_state.dev_file_loaded and st.session_state.show_preview_panel:
         sticky_header("Case Building", "Previewed ✓ — now click **Run Model**.")
     elif st.session_state.dev_file_loaded:
         sticky_header("Case Building", "📄 **Preview uploaded data** using the sidebar button, then click **Run Model**.")
     else:
         sticky_header("Case Building", "**Upload your data to build a case, then run the model to review performance.**")
 
+    # Render the preview panel at the very top (above results)
+    render_preview_panel()
+
     if run and st.session_state.dev_file_bytes:
         book = read_book_bytes(st.session_state.dev_file_bytes)
         sh_train = _find_sheet(book, ["Train","Training","training2","train","training"])
@@ -674,13 +728,19 @@ if st.session_state.app_step == "validate":
         if book:
             df0 = next(iter(book.values()))
             st.sidebar.caption(f"**Data loaded:** {up.name} • {df0.shape[0]} rows × {df0.shape[1]} cols")
+
+    # PREVIEW button -> show preview panel at top
     if st.sidebar.button("Preview data", use_container_width=True, disabled=(up is None)):
-        st.session_state.show_preview_modal = True
+        st.session_state.preview_book = read_book_bytes(up.getvalue()) if up is not None else {}
+        st.session_state.show_preview_panel = True
+        st.rerun()
+
     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()
 
     sticky_header("Validate the Model", "Upload a dataset with the same **features** and **MINStress_Actual** to evaluate performance.")
+    render_preview_panel()  # top-of-page preview
 
     if go_btn and up is not None:
         if st.session_state.fitted_model is None:
@@ -759,12 +819,18 @@ if st.session_state.app_step == "predict":
         if book:
             df0 = next(iter(book.values()))
             st.sidebar.caption(f"**Data loaded:** {up.name} • {df0.shape[0]} rows × {df0.shape[1]} cols")
+
+    # PREVIEW button -> show preview panel at top
     if st.sidebar.button("Preview data", use_container_width=True, disabled=(up is None)):
-        st.session_state.show_preview_modal = True
+        st.session_state.preview_book = read_book_bytes(up.getvalue()) if up is not None else {}
+        st.session_state.show_preview_panel = True
+        st.rerun()
+
     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 5 feature columns (no actual column).")
+    render_preview_panel()  # top-of-page preview
 
     if go_btn and up is not None:
         if st.session_state.fitted_model is None:
@@ -809,43 +875,6 @@ if st.session_state.app_step == "predict":
                             use_container_width=False, config={"displayModeBar": False, "scrollZoom": True})
         render_export_button(phase_key="predict")
 
-# =========================
-# Preview modal
-# =========================
-if st.session_state.show_preview_modal:
-    book_to_preview = {}
-    if st.session_state.app_step == "dev":
-        book_to_preview = read_book_bytes(st.session_state.dev_file_bytes)
-    elif st.session_state.app_step in ["validate", "predict"] and 'up' in locals() and up is not None:
-        book_to_preview = read_book_bytes(up.getvalue())
-
-    with st.expander("Preview data", expanded=True):
-        if not book_to_preview:
-            st.markdown('<div class="st-message-box">No data loaded yet.</div>', unsafe_allow_html=True)
-        else:
-            names = list(book_to_preview.keys())
-            tabs = st.tabs(names)
-            for t, name in zip(tabs, names):
-                with t:
-                    df = book_to_preview[name]
-                    t1, t2 = st.tabs(["Tracks", "Summary"])
-                    with t1:
-                        st.pyplot(preview_tracks(df, FEATURES), use_container_width=True)
-                    with t2:
-                        feat_present = [c for c in FEATURES if c in df.columns]
-                        if not feat_present:
-                            st.info("No feature columns found to summarize.")
-                        else:
-                            tbl = (
-                                df[feat_present]
-                                  .agg(['min','max','mean','std'])
-                                  .T.rename(columns={"min":"Min","max":"Max","mean":"Mean","std":"Std"})
-                                  .reset_index(names="Feature")
-                            )
-                            df_centered_rounded(tbl)
-
-    st.session_state.show_preview_modal = False
-
 # =========================
 # Footer
 # =========================