Update app.py

app.py

@@ -1388,72 +1388,69 @@ with tab_predict:
                 st.pyplot(fig_w, clear_figure=True)
 
 
-        #Single row SHAP block
+        
+        # Single row SHAP block
         st.subheader("SHAP explanation")
-
+        
         with st.form("shap_form"):
             row = st.number_input("Row index", 0, len(X_inf) - 1, 0)
             explain_btn = st.form_submit_button("Generate SHAP explanation")
-
+        
         if explain_btn:
             X_one = X_inf.iloc[[int(row)]]
             X_one_t = transform_before_clf(pipe, X_one)
-            
+        
             explainer = st.session_state.get("explainer")
             if explainer is None:
                 st.session_state.explainer = build_shap_explainer(pipe, X_inf)
                 explainer = st.session_state.explainer
-            
+        
             shap_vals = explainer.shap_values(X_one_t)
             if isinstance(shap_vals, list):
-                shap_vals = shap_vals[1]
-            
+                shap_vals = shap_vals[1]  # positive class
+        
             names = get_final_feature_names(pipe)
-            if len(names) != len(shap_vals[0]):
+            if len(names) != shap_vals.shape[1]:
                 st.warning(
-                    f"Feature name mismatch: names={len(names)} vs shap_cols={len(shap_vals[0])}. "
+                    f"Feature name mismatch: names={len(names)} vs shap_cols={shap_vals.shape[1]}. "
                     "Using generic names."
                 )
-                names = [f"f{i}" for i in range(len(shap_vals[0]))]
-            
+                names = [f"f{i}" for i in range(shap_vals.shape[1])]
+        
             # Dense row vector for SHAP plots
             try:
                 x_dense = X_one_t.toarray()[0]
             except Exception:
                 x_dense = np.array(X_one_t)[0]
-
-            
-            if len(names) != len(shap_vals[0]):
-                st.warning(
-                    f"Feature name mismatch: names={len(names)} vs shap_cols={len(shap_vals[0])}. "
-                    "Falling back to generic names."
-                )
-                names = [f"f{i}" for i in range(len(shap_vals[0]))]
-
-
-            try:
-                x_dense = X_one_t.toarray()[0]
-            except Exception:
-                x_dense = np.array(X_one_t)[0]
-
+        
+            # Base value
+            base = explainer.expected_value
+            if not np.isscalar(base):
+                base = float(np.array(base).reshape(-1)[0])
+        
             exp = shap.Explanation(
                 values=shap_vals[0],
-                base_values=float(base) if np.isscalar(base) else float(np.array(base).reshape(-1)[0]),
+                base_values=float(base),
                 data=x_dense,
                 feature_names=names,
             )
-
+        
             c1, c2 = st.columns(2)
-
+        
             with c1:
                 st.markdown("**Waterfall**")
-                fig = plt.figure()
+                fig = make_fig(figsize=FIGSIZE, dpi=plot_dpi_screen)
                 shap.plots.waterfall(exp, show=False, max_display=20)
-                st.pyplot(fig, clear_figure=True)
-
+                render_plot_with_download(
+                    fig, title="SHAP waterfall", filename="shap_waterfall_row.png", export_dpi=export_dpi
+                )
+        
             with c2:
                 st.markdown("**Top features**")
-                fig2 = plt.figure()
+                fig2 = make_fig(figsize=FIGSIZE, dpi=plot_dpi_screen)
                 shap.plots.bar(exp, show=False, max_display=20)
-                st.pyplot(fig2, clear_figure=True)
-            st.stop()
+                render_plot_with_download(
+                    fig2, title="SHAP bar", filename="shap_bar_row.png", export_dpi=export_dpi
+                )
+        
+            st.stop()