Update src/streamlit_app.py

src/streamlit_app.py

@@ -471,6 +471,9 @@ with tabs[4]:
 
     features = st.multiselect("Model input features (auto-suggested)", numeric_cols, default=suggested)
     st.markdown(f"Auto target: `{target}` · Suggested family hint: `{model_hint}`")
+    # --- Sampling configuration ---
+    max_rows = min(df.shape[0], 20000)
+    sample_size = st.slider("Sample rows", 500, max_rows, min(1500, max_rows), step=100)
 
     # ---------- SAFE target & X preparation ----------
     # Ensure target is a single column name (string). If it's a list, pick the first and warn.
@@ -499,7 +502,8 @@ with tabs[4]:
             st.error(f"Multi-output target detected (shape {y.shape}). Select a single target column.")
             st.stop()
     
-    y = np.ravel(y)
+    y = pd.Series(np.ravel(y), name=target)
+
     
     # Drop known leak or identifier columns
     leak_cols = ["furnace_temp_next", "pred_temp_30s", "run_timestamp", "timestamp", "batch_id_numeric", "batch_id"]
@@ -642,7 +646,8 @@ with tabs[4]:
                 oof = np.zeros(X_sel.shape[0])
                 for tr_idx, val_idx in kf.split(X_sel):
                     X_tr, X_val = X_sel.iloc[tr_idx], X_sel.iloc[val_idx]
-                    y_tr = y.iloc[tr_idx]
+                    y_tr = y[tr_idx] if not hasattr(y, "iloc") else y.iloc[tr_idx]
+
                     try:
                         model_obj.fit(X_tr, y_tr)
                         preds = model_obj.predict(X_val)