Enhance duplication metrics in app.py and create_general_exposures.py

- Added 'under_10' metric to the working DataFrame in app.py, allowing for analysis of lineups with 10 or fewer duplicates.
- Updated the general exposures calculation in create_general_exposures.py to include 'under_10', improving the comprehensiveness of the data analysis.
- Introduced a new tab for duplication information in the app interface, enhancing user access to these metrics.

app.py

@@ -221,15 +221,19 @@ with tab2:
                 axis=1
             )
             working_df['dupes'] = working_df.groupby('sorted').transform('size')
-            # For uniques - count how many unique lineups (dupes == 1) each BaseName has
+
             working_df['uniques'] = working_df.groupby('BaseName').apply(
                 lambda x: (x['dupes'] == 1).sum()
             ).reindex(working_df['BaseName']).values
 
-            # For under_5 - count how many lineups with 5 or fewer duplicates each BaseName has
             working_df['under_5'] = working_df.groupby('BaseName').apply(
                 lambda x: (x['dupes'] <= 5).sum()
             ).reindex(working_df['BaseName']).values
+
+            working_df['under_10'] = working_df.groupby('BaseName').apply(
+                lambda x: (x['dupes'] <= 10).sum()
+            ).reindex(working_df['BaseName']).values
+
             working_df = working_df.reset_index()
             working_df['percentile_finish'] = working_df['index'].rank(pct=True)
             working_df['finish'] = working_df['index']
@@ -325,7 +329,7 @@ with tab2:
         )
 
         with st.container():
-            tab1, tab2, tab3, tab4 = st.tabs(['Player Used Info', 'Stack Used Info', 'Stack Size Info', 'General Info'])
+            tab1, tab2, tab3, tab4, tab5 = st.tabs(['Player Used Info', 'Stack Used Info', 'Stack Size Info', 'General Info', 'Duplication Info'])
             with tab1:
                 with st.form(key='player_info_pos_form'):
                     col1, col2 = st.columns(2)
@@ -419,3 +423,6 @@ with tab2:
                     st.session_state['general_frame'] = create_general_exposures(working_df, entry_names)
                     st.dataframe(st.session_state['general_frame'].style.background_gradient(cmap='RdYlGn', axis=1).format(precision=2), hide_index=True)
 
+            with tab5:
+                st.session_state['duplication_frame'] = working_df[['BaseName', 'dupes', 'uniques', 'under_5', 'under_10']].drop_duplicates(subset='BaseName', keep='first')
+                st.dataframe(st.session_state['duplication_frame'].style.background_gradient(cmap='RdYlGn', axis=1).format(precision=2), hide_index=True)

global_func/create_general_exposures.py

@@ -1,7 +1,7 @@
 import pandas as pd
 
 def create_general_exposures(df: pd.DataFrame, entrants: list = None):
-    check_cols = ['salary', 'actual_fpts', 'actual_own', 'dupes', 'uniques', 'under_5']
+    check_cols = ['salary', 'actual_fpts', 'actual_own', 'dupes', 'uniques', 'under_5', 'under_10']
     general_exposures = pd.DataFrame()
     for each_col in check_cols:
         general_frame = pd.DataFrame()
@@ -19,7 +19,7 @@ def create_general_exposures(df: pd.DataFrame, entrants: list = None):
         general_len_5per = len(df[df['percentile_finish'] <= 0.05])
         general_len_10per = len(df[df['percentile_finish'] <= 0.10])
         general_len_20per = len(df[df['percentile_finish'] <= 0.20])
-        each_set_name = ['Overall', ' Top 1%', ' Top 5%', 'Top 10%', 'Top 20%', 'Uniques', 'Under 5']
+        each_set_name = ['Overall', ' Top 1%', ' Top 5%', 'Top 10%', 'Top 20%', 'Uniques', 'Under 5', 'Under 10']
         each_general_set = [overall_general, top_1per_general, top_5per_general, top_10per_general, top_20per_general]
         each_general_len_set = [general_contest_len, general_len_1per, general_len_5per, general_len_10per, general_len_20per]
         general_count_var = 0
@@ -39,5 +39,5 @@ def create_general_exposures(df: pd.DataFrame, entrants: list = None):
             general_exposures = general_row
         else:
             general_exposures = pd.concat([general_exposures, general_frame], ignore_index = True, axis = 0)
-    general_exposures['Stat'] = general_exposures['Stat'].replace(['salary', 'actual_fpts', 'actual_own', 'dupes', 'uniques', 'under_5'], ['Salary Used', 'Finishing Points', 'Total Ownership', 'Duplications', 'Uniques', 'Under 5'])
+    general_exposures['Stat'] = general_exposures['Stat'].replace(['salary', 'actual_fpts', 'actual_own', 'dupes', 'uniques', 'under_5', 'under_10'], ['Salary Used', 'Finishing Points', 'Total Ownership', 'Duplications', 'Uniques', 'Under 5', 'Under 10'])
     return general_exposures