Add stack size exposure calculations in app.py and create_stack_size_exposures.py

- Introduced the create_stack_size_exposures function to calculate stack size exposures based on player performance metrics.
- Updated app.py to integrate the new function, allowing for the display of stack size exposure data in the user interface.
- Enhanced tab structure in app.py to reflect the addition of stack size information, improving overall data presentation and user experience.

app.py

@@ -12,6 +12,7 @@ from global_func.load_file import load_file
 from global_func.find_name_mismatches import find_name_mismatches
 from global_func.create_player_exposures import create_player_exposures
 from global_func.create_stack_exposures import create_stack_exposures
+from global_func.create_stack_size_exposures import create_stack_size_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:
@@ -238,7 +239,7 @@ with tab2:
     )
 
     with st.container():
-        tab1, tab2, tab3 = st.tabs(['Player Used Info', 'Stack Used Info', 'Duplication Info'])
+        tab1, tab2, tab3 = st.tabs(['Player Used Info', 'Stack Used Info', 'Stack Size Info'])
         with tab1:
 
             if entry_parse_var == 'All':
@@ -272,4 +273,18 @@ with tab2:
                     format(formatter='{:.2%}', subset=st.session_state['stack_frame'].select_dtypes(include=['number']).columns),
                     hide_index=True)
         with tab3:
-            st.write('holding')
+            
+            if entry_parse_var == 'All':
+                st.session_state['stack_size_frame'] = create_stack_size_exposures(working_df)
+                st.dataframe(st.session_state['stack_size_frame'].
+                    sort_values(by='Exposure Overall', ascending=False).
+                    style.background_gradient(cmap='RdYlGn').
+                    format(formatter='{:.2%}', subset=st.session_state['stack_size_frame'].select_dtypes(include=['number']).columns),
+                    hide_index=True)
+            else:
+                st.session_state['stack_size_frame'] = create_stack_size_exposures(working_df, entry_names)
+                st.dataframe(st.session_state['stack_size_frame'].
+                    sort_values(by='Exposure Overall', ascending=False).
+                    style.background_gradient(cmap='RdYlGn').
+                    format(formatter='{:.2%}', subset=st.session_state['stack_size_frame'].select_dtypes(include=['number']).columns),
+                    hide_index=True)

global_func/create_stack_size_exposures.py

@@ -0,0 +1,33 @@
+import pandas as pd
+
+def create_stack_size_exposures(df: pd.DataFrame, entrants: list = None):
+    stack_size_exposures = pd.DataFrame()
+    if entrants is not None:
+        overall_stack_sizes = pd.Series(list(df[df['BaseName'].isin(entrants)]['stack_size'])).value_counts()
+    else:
+        overall_stack_sizes = pd.Series(list(df['stack_size'])).value_counts()
+    top_1per_stack_sizes = pd.Series(list(df[df['percentile_finish'] <= 0.01]['stack_size'])).value_counts()
+    top_5per_stack_sizes = pd.Series(list(df[df['percentile_finish'] <= 0.05]['stack_size'])).value_counts()
+    top_10per_stack_sizes = pd.Series(list(df[df['percentile_finish'] <= 0.10]['stack_size'])).value_counts()
+    top_20per_stack_sizes = pd.Series(list(df[df['percentile_finish'] <= 0.20]['stack_size'])).value_counts()
+    stack_sizes_contest_len = len(df)
+    stack_sizes_len_1per = len(df[df['percentile_finish'] <= 0.01])
+    stack_sizes_len_5per = len(df[df['percentile_finish'] <= 0.05])
+    stack_sizes_len_10per = len(df[df['percentile_finish'] <= 0.10])
+    stack_sizes_len_20per = len(df[df['percentile_finish'] <= 0.20])
+    each_set_name = ['Overall', ' Top 1%', ' Top 5%', 'Top 10%', 'Top 20%']
+    each_stack_sizes_set = [overall_stack_sizes, top_1per_stack_sizes, top_5per_stack_sizes, top_10per_stack_sizes, top_20per_stack_sizes]
+    each_stack_sizes_len_set = [stack_sizes_contest_len, stack_sizes_len_1per, stack_sizes_len_5per, stack_sizes_len_10per, stack_sizes_len_20per]
+    stack_size_count_var = 0
+    for each_stack_size in each_stack_sizes_set:
+        stack_size_frame = each_stack_size.to_frame().reset_index().rename(columns={'index': 'Size', 'count': 'Count'})
+        stack_size_frame['Percent'] = stack_size_frame['Count'] / each_stack_sizes_len_set[stack_size_count_var]
+        stack_size_frame = stack_size_frame[['Size', 'Percent']]
+        stack_size_frame = stack_size_frame.rename(columns={'Percent': f'Exposure {each_set_name[stack_size_count_var]}'})
+        if len(stack_size_exposures) == 0:
+            stack_size_exposures = stack_size_frame
+        else:
+            stack_size_exposures = pd.merge(stack_size_exposures, stack_size_frame, on='Size', how='outer')
+        stack_size_count_var += 1
+
+    return stack_size_exposures