Refactor player exposure calculations in app.py

- Simplified the logic for calculating player exposure metrics by consolidating the percentile finish calculations into a single conditional block, enhancing code clarity and maintainability.
- Updated the handling of player and stack counts to improve accuracy in the displayed metrics, ensuring a more reliable representation of player performance across different percentiles.

app.py

@@ -230,85 +230,40 @@ with tab2:
             hide_index=True
         )
 
-        contest_players = working_df.copy()
-        players_1per = working_df[working_df['percentile_finish'] <= 0.01]
-        players_5per = working_df[working_df['percentile_finish'] <= 0.05]
-        players_10per = working_df[working_df['percentile_finish'] <= 0.10]
-        players_20per = working_df[working_df['percentile_finish'] <= 0.20]
-        contest_len = len(contest_players)
-        len_1per = len(players_1per)
-        len_5per = len(players_5per)
-        len_10per = len(players_10per)
-        len_20per = len(players_20per)
-        ######## Going to try a groupby based on finishing percentiles here next
-        player_counts = pd.Series(list(contest_players[player_columns].values.flatten())).value_counts()
-        player_1per_counts = pd.Series(list(players_1per[player_columns].values.flatten())).value_counts()
-        player_5per_counts = pd.Series(list(players_5per[player_columns].values.flatten())).value_counts()
-        player_10per_counts = pd.Series(list(players_10per[player_columns].values.flatten())).value_counts()
-        player20_per_counts = pd.Series(list(players_20per[player_columns].values.flatten())).value_counts()
-        stack_counts = pd.Series(list(contest_players['stack'])).value_counts()
-        stack_1per_counts = pd.Series(list(players_1per['stack'])).value_counts()
-        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]
-        each_len_set = [contest_len, len_1per, len_5per, len_10per, len_20per]
         with st.container():
             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]:
-                    set_frame = each_set.to_frame().reset_index().rename(columns={'index': 'Player', 'count': 'Count'})
-                    set_frame['Percent'] = set_frame['Count'] / each_len_set[player_count_var]
-                    set_frame = set_frame[['Player', 'Percent']]
-                    set_frame = set_frame.rename(columns={'Percent': f'Exposure {each_set_name[player_count_var]}'})
-                    if 'player_frame' not in st.session_state:
-                        st.session_state['player_frame'] = set_frame
-                    else:
-                        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)
+                if entry_parse_var == 'All':
+                    overall_players = pd.Series(list(working_df[player_columns].values.flatten())).value_counts()
+                    top_1per_players = pd.Series(list(working_df[working_df['percentile_finish'] <= 0.01][player_columns].values.flatten())).value_counts()
+                    top_5per_players = pd.Series(list(working_df[working_df['percentile_finish'] <= 0.05][player_columns].values.flatten())).value_counts()
+                    top_10per_players = pd.Series(list(working_df[working_df['percentile_finish'] <= 0.10][player_columns].values.flatten())).value_counts()
+                    top_20per_players = pd.Series(list(working_df[working_df['percentile_finish'] <= 0.20][player_columns].values.flatten())).value_counts()
+                    contest_len = len(working_df)
+                    len_1per = len(working_df[working_df['percentile_finish'] <= 0.01])
+                    len_5per = len(working_df[working_df['percentile_finish'] <= 0.05])
+                    len_10per = len(working_df[working_df['percentile_finish'] <= 0.10])
+                    len_20per = len(working_df[working_df['percentile_finish'] <= 0.20])
+                    each_set_name = ['Overall', ' Top 1%', ' Top 5%', 'Top 10%', 'Top 20%']
+                    each_frame_set = [overall_players, top_1per_players, top_5per_players, top_10per_players, top_20per_players]
+                    each_len_set = [contest_len, len_1per, len_5per, len_10per, len_20per]
+                    player_count_var = 0
+                    for each_set in each_frame_set:
+                        set_frame = each_set.to_frame().reset_index().rename(columns={'index': 'Player', 'count': 'Count'})
+                        set_frame['Percent'] = set_frame['Count'] / each_len_set[player_count_var]
+                        set_frame = set_frame[['Player', 'Percent']]
+                        set_frame = set_frame.rename(columns={'Percent': f'Exposure {each_set_name[player_count_var]}'})
+                        if 'player_frame' not in st.session_state:
+                            st.session_state['player_frame'] = set_frame
+                        else:
+                            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)
             with tab2:
-                stack_count_var = 0
-                for each_set in [stack_counts, stack_1per_counts, stack_5per_counts, stack_10per_counts, stack_20per_counts]:
-                    set_frame = each_set.to_frame().reset_index().rename(columns={'index': 'Stack', 'count': 'Count'})
-                    set_frame['Percent'] = set_frame['Count'] / each_len_set[stack_count_var]
-                    set_frame = set_frame[['Stack', 'Percent']]
-                    set_frame = set_frame.rename(columns={'Percent': f'Exposure {each_set_name[stack_count_var]}'})
-                    if 'stack_frame' not in st.session_state:
-                        st.session_state['stack_frame'] = set_frame
-                    else:
-                        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)
+                st.write('holding')
             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'] / each_len_set[dupe_count_var]
-                    set_frame = set_frame[['Dupes', 'Percent']]
-                    set_frame = set_frame.rename(columns={'Percent': f'Exposure {each_set_name[dupe_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')
-                    dupe_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)
+                st.write('holding')