Refactor reassessment logic in app.py to utilize combined frames for 'Manage Portfolio' and 'Export Base', improving data processing and consistency in predictions.

app.py

@@ -186,6 +186,7 @@ selected_tab = st.segmented_control(
     selection_mode='single',
     default='Data Load',
     label_visibility='collapsed',
+    width='stretch',
     key='tab_selector'
 )
 
@@ -1603,7 +1604,18 @@ if selected_tab == 'Manage Portfolio':
                         st.session_state['working_frame']['salary'] = st.session_state['working_frame']['salary'].astype('uint16')
                         
                         # st.session_state['working_frame'] = predict_dupes(st.session_state['working_frame'], st.session_state['map_dict'], site_var, type_var, Contest_Size, strength_var, sport_var)
-                        st.session_state['working_frame'] = reassess_edge(st.session_state['working_frame'], st.session_state['base_frame'], st.session_state['map_dict'], site_var, type_var, Contest_Size, strength_var, sport_var, salary_max)
+                        # st.session_state['working_frame'] = reassess_edge(st.session_state['working_frame'], st.session_state['base_frame'], st.session_state['map_dict'], site_var, type_var, Contest_Size, strength_var, sport_var, salary_max)
+                        # Store the number of rows in the modified frame
+                        num_modified_rows = len(st.session_state['working_frame'])
+                        
+                        # Concatenate the modified frame with the base frame
+                        combined_frame = pd.concat([st.session_state['working_frame'], st.session_state['base_frame']], ignore_index=True)
+                        
+                        # Run predict_dupes on the combined frame
+                        updated_combined_frame = predict_dupes(combined_frame, st.session_state['map_dict'], site_var, type_var, Contest_Size, strength_var, sport_var, salary_max)
+                        
+                        # Extract the first N rows (which correspond to our modified frame)
+                        st.session_state['working_frame'] = updated_combined_frame.head(num_modified_rows).copy()
                         st.session_state['export_merge'] = st.session_state['working_frame'].copy()
                     elif exp_submitted:
                         st.session_state['settings_base'] = False
@@ -1699,7 +1711,17 @@ if selected_tab == 'Manage Portfolio':
                         st.session_state['export_base']['salary'] = st.session_state['export_base']['salary'].astype('uint16')
                         
                         # st.session_state['export_base'] = predict_dupes(st.session_state['export_base'], st.session_state['map_dict'], site_var, type_var, Contest_Size, strength_var, sport_var)
-                        st.session_state['export_base'] = reassess_edge(st.session_state['export_base'], st.session_state['base_frame'], st.session_state['map_dict'], site_var, type_var, Contest_Size, strength_var, sport_var, salary_max)
+                        # st.session_state['export_base'] = reassess_edge(st.session_state['export_base'], st.session_state['base_frame'], st.session_state['map_dict'], site_var, type_var, Contest_Size, strength_var, sport_var, salary_max)
+                        num_modified_rows = len(st.session_state['export_base'])
+                        
+                        # Concatenate the modified frame with the base frame
+                        combined_frame = pd.concat([st.session_state['export_base'], st.session_state['base_frame']], ignore_index=True)
+                        
+                        # Run predict_dupes on the combined frame
+                        updated_combined_frame = predict_dupes(combined_frame, st.session_state['map_dict'], site_var, type_var, Contest_Size, strength_var, sport_var, salary_max)
+                        
+                        # Extract the first N rows (which correspond to our modified frame)
+                        st.session_state['export_base'] = updated_combined_frame.head(num_modified_rows).copy()
                         st.session_state['export_merge'] = st.session_state['export_base'].copy()
                         
         with st.container():