Add duplication info tab and update dataframe handling in app.py

- Introduced a new tab for displaying duplication information alongside player and stack data.
- Added calculations for duplicate counts across various player sets, enhancing data analysis capabilities.
- Updated dataframe display logic to include duplication metrics, ensuring consistent styling and formatting.
- Improved overall user experience by providing comprehensive insights into player usage and duplication trends.

app.py

@@ -240,10 +240,15 @@ with tab2:
         stack_5per_counts = pd.Series(list(players_5per['stack'])).value_counts()
         stack_10per_counts = pd.Series(list(players_10per['stack'])).value_counts()
         stack_20per_counts = pd.Series(list(players_20per['stack'])).value_counts()
+        dupe_counts = pd.Series(list(contest_players['dupes'])).value_counts()
+        dupe_1per_counts = pd.Series(list(players_1per['dupes'])).value_counts()
+        dupe_5per_counts = pd.Series(list(players_5per['dupes'])).value_counts()
+        dupe_10per_counts = pd.Series(list(players_10per['dupes'])).value_counts()
+        dupe_20per_counts = pd.Series(list(players_20per['dupes'])).value_counts()
         each_set_name = ['Overall', ' Top 1%', ' Top 5%', 'Top 10%', 'Top 20%']
         each_frame_set = [contest_players, players_1per, players_5per, players_10per, players_20per]
         with st.container():
-            tab1, tab2 = st.tabs(['Player Used Info', 'Stack Used Info'])
+            tab1, tab2, tab3 = st.tabs(['Player Used Info', 'Stack Used Info', 'Duplication Info'])
             with tab1:
                 player_count_var = 0
                 for each_set in [player_counts, player_1per_counts, player_5per_counts, player_10per_counts, player20_per_counts]:
@@ -257,10 +262,10 @@ with tab2:
                         st.session_state['player_frame'] = pd.merge(st.session_state['player_frame'], set_frame, on='Player', how='outer')
                     player_count_var += 1
                 st.dataframe(st.session_state['player_frame'].
-                             sort_values(by='Exposure Overall', ascending=False).
-                             style.background_gradient(cmap='RdYlGn').
-                             format(formatter='{:.2%}', subset=st.session_state['player_frame'].select_dtypes(include=['number']).columns),
-                             hide_index=True)
+                    sort_values(by='Exposure Overall', ascending=False).
+                    style.background_gradient(cmap='RdYlGn').
+                    format(formatter='{:.2%}', subset=st.session_state['player_frame'].select_dtypes(include=['number']).columns),
+                    hide_index=True)
             with tab2:
                 stack_count_var = 0
                 for each_set in [stack_counts, stack_1per_counts, stack_5per_counts, stack_10per_counts, stack_20per_counts]:
@@ -274,7 +279,24 @@ with tab2:
                         st.session_state['stack_frame'] = pd.merge(st.session_state['stack_frame'], set_frame, on='Stack', how='outer')
                     stack_count_var += 1
                 st.dataframe(st.session_state['stack_frame'].
-                             sort_values(by='Exposure Overall', ascending=False).
-                             style.background_gradient(cmap='RdYlGn').
-                             format(formatter='{:.2%}', subset=st.session_state['stack_frame'].select_dtypes(include=['number']).columns),
-                             hide_index=True)
+                    sort_values(by='Exposure Overall', ascending=False).
+                    style.background_gradient(cmap='RdYlGn').
+                    format(formatter='{:.2%}', subset=st.session_state['stack_frame'].select_dtypes(include=['number']).columns),
+                    hide_index=True)
+            with tab3:
+                dupe_count_var = 0
+                for each_set in [dupe_counts, dupe_1per_counts, dupe_5per_counts, dupe_10per_counts, dupe_20per_counts]:
+                    set_frame = each_set.to_frame().reset_index().rename(columns={'index': 'Dupes', 'count': 'Count'})
+                    set_frame['Percent'] = set_frame['Count'] / len(each_frame_set[dupe_count_var])
+                    set_frame = set_frame[['Dupes', 'Percent']]
+                    set_frame = set_frame.rename(columns={'Percent': f'Exposure {each_set_name[stack_count_var]}'})
+                    if 'dupe_frame' not in st.session_state:
+                        st.session_state['dupe_frame'] = set_frame
+                    else:
+                        st.session_state['dupe_frame'] = pd.merge(st.session_state['dupe_frame'], set_frame, on='Dupes', how='outer')
+                    stack_count_var += 1
+                st.dataframe(st.session_state['dupe_frame'].
+                    sort_values(by='Exposure Overall', ascending=False).
+                    style.background_gradient(cmap='RdYlGn').
+                    format(formatter='{:.2%}', subset=st.session_state['dupe_frame'].select_dtypes(include=['number']).columns),
+                    hide_index=True)