Update app.py

app.py

@@ -4,6 +4,7 @@ import streamlit as st
 import pandas as pd
 import numpy as np
 import joblib
+from datetime import datetime
 
 # Matplotlib for PREVIEW modal and for the CROSS-PLOT (static)
 import matplotlib
@@ -231,6 +232,147 @@ def df_centered_rounded(df: pd.DataFrame, hide_index=True):
             .set_table_styles(TABLE_CENTER_CSS)
     )
     st.dataframe(styler, use_container_width=True, hide_index=hide_index)
+# === NEW: 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"
+    except Exception:
+        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]
+
+def _round_numeric(df: pd.DataFrame, ndigits: int = 2) -> pd.DataFrame:
+    out = df.copy()
+    for c in out.columns:
+        if pd.api.types.is_float_dtype(out[c]) or pd.api.types.is_integer_dtype(out[c]):
+            out[c] = pd.to_numeric(out[c], errors="coerce").round(ndigits)
+    return out
+
+def _summary_table(df: pd.DataFrame, cols: list[str]) -> pd.DataFrame:
+    cols = [c for c in cols if c in df.columns]
+    if not cols:
+        return pd.DataFrame()
+    tbl = (df[cols]
+            .agg(['min','max','mean','std'])
+            .T.rename(columns={"min":"Min","max":"Max","mean":"Mean","std":"Std"})
+            .reset_index(names="Field"))
+    return _round_numeric(tbl)
+
+def _train_ranges_df(ranges: dict[str, tuple[float, float]]) -> pd.DataFrame:
+    if not ranges:
+        return pd.DataFrame()
+    df = pd.DataFrame(ranges).T.reset_index()
+    df.columns = ["Feature", "Min", "Max"]
+    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, []
+
+    sheets: dict[str, pd.DataFrame] = {}
+    order: list[str] = []
+
+    # Training
+    if "Train" in res:
+        tr = _round_numeric(res["Train"])
+        sheets["Training"] = tr; order.append("Training")
+        m = res.get("m_train", {})
+        if m:
+            sheets["Training_Metrics"] = _round_numeric(pd.DataFrame([m])); order.append("Training_Metrics")
+        tr_cols = FEATURES + ([TARGET] if TARGET in tr.columns else []) + (["UCS_Pred"] if "UCS_Pred" in tr.columns else [])
+        s = _summary_table(tr, tr_cols)
+        if not s.empty:
+            sheets["Training_Summary"] = s; order.append("Training_Summary")
+
+    # Testing
+    if "Test" in res:
+        te = _round_numeric(res["Test"])
+        sheets["Testing"] = te; order.append("Testing")
+        m = res.get("m_test", {})
+        if m:
+            sheets["Testing_Metrics"] = _round_numeric(pd.DataFrame([m])); order.append("Testing_Metrics")
+        te_cols = FEATURES + ([TARGET] if TARGET in te.columns else []) + (["UCS_Pred"] if "UCS_Pred" in te.columns else [])
+        s = _summary_table(te, te_cols)
+        if not s.empty:
+            sheets["Testing_Summary"] = s; order.append("Testing_Summary")
+
+    # Validation
+    if "Validate" in res:
+        va = _round_numeric(res["Validate"])
+        sheets["Validation"] = va; order.append("Validation")
+        m = res.get("m_val", {})
+        if m:
+            sheets["Validation_Metrics"] = _round_numeric(pd.DataFrame([m])); order.append("Validation_Metrics")
+        sv = res.get("sv_val", {})
+        if sv:
+            sheets["Validation_Summary"] = _round_numeric(pd.DataFrame([sv])); order.append("Validation_Summary")
+        oor_tbl = res.get("oor_tbl")
+        if oor_tbl is not None and isinstance(oor_tbl, pd.DataFrame) and not oor_tbl.empty:
+            sheets["Validation_OOR"] = _round_numeric(oor_tbl.reset_index(drop=True)); order.append("Validation_OOR")
+
+    # Prediction (no actual)
+    if "PredictOnly" in res:
+        pr = _round_numeric(res["PredictOnly"])
+        sheets["Prediction"] = pr; order.append("Prediction")
+        sv = res.get("sv_pred", {})
+        if sv:
+            sheets["Prediction_Summary"] = _round_numeric(pd.DataFrame([sv])); order.append("Prediction_Summary")
+
+    # Training ranges (from dev step)
+    tr_ranges = st.session_state.get("train_ranges")
+    if tr_ranges:
+        rr = _train_ranges_df(tr_ranges)
+        if not rr.empty:
+            sheets["Training_Ranges"] = rr; order.append("Training_Ranges")
+
+    # Info sheet
+    info = pd.DataFrame([
+        {"Key": "Target", "Value": TARGET},
+        {"Key": "Features", "Value": ", ".join(FEATURES)},
+        {"Key": "ExportedAt", "Value": datetime.now().strftime("%Y-%m-%d %H:%M:%S")},
+    ])
+    sheets["Info"] = info; order.append("Info")
+
+    # Write workbook to memory
+    bio = io.BytesIO()
+    with pd.ExcelWriter(bio, engine=_excel_engine()) as writer:
+        for name in order:
+            df = sheets[name]
+            df.to_excel(writer, sheet_name=_excel_safe_name(name), index=False)
+    bio.seek(0)
+
+    fname = f"UCS_Export_{datetime.now().strftime('%Y%m%d_%H%M%S')}.xlsx"
+    return bio.getvalue(), fname, order
+
+def render_export_button(key: str = "export_main") -> None:
+    """Bottom-of-page export button (main content area)."""
+    data, fname, names = build_export_workbook()
+    st.divider()
+    st.markdown("### Export to Excel")
+    if names:
+        st.caption("Includes sheets: " + ", ".join(names))
+    st.download_button(
+        label="⬇️ Export Excel",
+        data=(data or b""),
+        file_name=(fname or "UCS_Export.xlsx"),
+        mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+        disabled=(data is None),
+        help="Exports all available results, metrics, summaries, OOR, training ranges, and info.",
+        key=key,
+    )
+# ================================================================================
 
 # =========================
 # Cross plot (Matplotlib, fixed limits & ticks)
@@ -772,6 +914,17 @@ if st.session_state.show_preview_modal:
                         df_centered_rounded(tbl.reset_index(names="Feature"))
     # Reset the state variable after the modal is displayed
     st.session_state.show_preview_modal = False
+
+# === Bottom-of-page Export (per step) =========================================
+if st.session_state.app_step in ("dev", "validate", "predict"):
+    has_results = any(
+        k in st.session_state.results
+        for k in ("Train", "Test", "Validate", "PredictOnly")
+    )
+    if has_results:
+        # Unique key per step avoids duplicate-widget clashes when switching steps
+        render_export_button(key=f"export_{st.session_state.app_step}")
+# ==============================================================================
 # =========================
 # Footer
 # =========================