Refactor app.py to utilize create_player_exposures function

- Replaced repetitive code for calculating player exposures with a new function, create_player_exposures, improving code maintainability and readability.
- Streamlined the handling of player exposure data for both 'All' and specific entry names, enhancing performance and clarity in the application.

app.py

@@ -7,15 +7,10 @@ from fuzzywuzzy import process
 from collections import Counter
 
 ## import global functions
-from global_func.clean_player_name import clean_player_name
 from global_func.load_contest_file import load_contest_file
 from global_func.load_file import load_file
-from global_func.load_ss_file import load_ss_file
 from global_func.find_name_mismatches import find_name_mismatches
-from global_func.predict_dupes import predict_dupes
-from global_func.highlight_rows import highlight_changes, highlight_changes_winners, highlight_changes_losers
-from global_func.load_csv import load_csv
-from global_func.find_csv_mismatches import find_csv_mismatches
+from global_func.create_player_exposures import create_player_exposures
 
 player_exposure_format = {'Exposure Overall': '{:.2%}', 'Exposure Top 1%': '{:.2%}', 'Exposure Top 5%': '{:.2%}', 'Exposure Top 10%': '{:.2%}', 'Exposure Top 20%': '{:.2%}'}
 if 'calc_toggle' not in st.session_state:
@@ -239,61 +234,16 @@ with tab2:
         with st.container():
             tab1, tab2, tab3 = st.tabs(['Player Used Info', 'Stack Used Info', 'Duplication Info'])
             with tab1:
+                st.session_state['field_frame'] = create_player_exposures(working_df, player_columns)
                 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.session_state['player_frame'] = create_player_exposures(working_df, player_columns)
                     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)
                 else:
-                    overall_players = pd.Series(list(working_df[working_df['BaseName'].isin(entry_names)][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.session_state['player_frame'] = create_player_exposures(working_df, player_columns, entry_names)
                     st.dataframe(st.session_state['player_frame'].
                         sort_values(by='Exposure Overall', ascending=False).
                         style.background_gradient(cmap='RdYlGn').

global_func/create_player_exposures.py

@@ -0,0 +1,33 @@
+import pandas as pd
+
+def create_player_exposures(df: pd.DataFrame, player_columns: list, entrants: list = None):
+    player_frame = pd.DataFrame()
+    if entrants is not None:
+        overall_players = pd.Series(list(df[df['BaseName'].isin(entrants)][player_columns].values.flatten())).value_counts()
+    else:
+        overall_players = pd.Series(list(df[player_columns].values.flatten())).value_counts()
+    top_1per_players = pd.Series(list(df[df['percentile_finish'] <= 0.01][player_columns].values.flatten())).value_counts()
+    top_5per_players = pd.Series(list(df[df['percentile_finish'] <= 0.05][player_columns].values.flatten())).value_counts()
+    top_10per_players = pd.Series(list(df[df['percentile_finish'] <= 0.10][player_columns].values.flatten())).value_counts()
+    top_20per_players = pd.Series(list(df[df['percentile_finish'] <= 0.20][player_columns].values.flatten())).value_counts()
+    contest_len = len(df)
+    len_1per = len(df[df['percentile_finish'] <= 0.01])
+    len_5per = len(df[df['percentile_finish'] <= 0.05])
+    len_10per = len(df[df['percentile_finish'] <= 0.10])
+    len_20per = len(df[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 len(player_frame) == 0:
+            player_frame = set_frame
+        else:
+            player_frame = pd.merge(player_frame, set_frame, on='Player', how='outer')
+        player_count_var += 1
+    
+    return player_frame