add shap values for categorical values

autoML.py

@@ -27,11 +27,11 @@ def autoML(csv, task, budget, label, metric_to_minimize_class, metric_to_minimiz
 
     df = pd.read_csv(csv)
 
-    msk = np.random.rand(len(df)) < 0.8
-    df_train, df_test = df[msk], df[~msk]
+    #msk = np.random.rand(len(df)) < 0.8
+    #df_train, df_test = df[msk], df[~msk]
 
-    df_features = df_train[df_train.columns.difference([label])]
-    y = df_train[label]
+    df_features = df[df.columns.difference([label])]
+    y = df[label]
 
     my_bar.progress(50, text=progress_text)
 
@@ -173,7 +173,7 @@ def autoML(csv, task, budget, label, metric_to_minimize_class, metric_to_minimiz
 
         download_model(automl)
     
-
+    """
     with tab3:
         with st.container():
             st.subheader('1D Partial Dependance for the three most important features')
@@ -240,15 +240,25 @@ def autoML(csv, task, budget, label, metric_to_minimize_class, metric_to_minimiz
                                 
                     st.pyplot(display.figure_)
     
-
+    """
     with tab4:
 
-        df_features_test = df_test[df_test.columns.difference([label])]
+        #df_shap = df_features.sample(n=200, random_state=89)
+
+        def get_only_features_names(name):
+            return name[5:]
+            
+        df_transform = pd.DataFrame(data=preprocessor.fit_transform(df_features), 
+                                         columns=list(map(get_only_features_names, 
+                                                          preprocessor.get_feature_names_out())
+                                                          )
+                                        )
 
         with st.container():
             with st.spinner(f'Compute Shap Values...'):
-                explainer = shap.Explainer(pipeline.predict, df_features_test)
-                shap_values = explainer(df_features_test)
+                explainer = shap.Explainer(automl.model.predict, df_transform)
+                shap_values = explainer(df_transform)
+
             st.subheader('Beeswarm Plot')
             plt.figure()
             st.pyplot(shap.plots.beeswarm(shap_values, show=False).figure)