Refactor predict_dupes function call in app.py to use parsed_frame and salary_max, and add reassess_edge function in reassess_edge.py for recalculating metrics based on differences in salary, median, and ownership.

app.py

@@ -1434,7 +1434,7 @@ with tab2:
                         st.session_state['working_frame']['salary'] = st.session_state['working_frame']['salary'].astype('uint16')
                         
                         print(st.session_state['working_frame'].head(10))
-                        st.session_state['working_frame'] = predict_dupes(st.session_state['working_frame'], st.session_state['map_dict'], site_var, type_var, Contest_Size, strength_var, sport_var)
+                        st.session_state['working_frame'] = predict_dupes(parsed_frame, st.session_state['working_frame'], salary_max)
                         st.session_state['export_merge'] = st.session_state['working_frame'].copy()
                     elif exp_submitted:
                         st.session_state['settings_base'] = False

global_func/reassess_edge.py

@@ -0,0 +1,40 @@
+# Rerunning the predict_dupes.py function on a small portfolio after running exposure_spread.py breaks the metrics
+# This is because the preeict_dupes.py function is exclusive of the lineups it takes it, and is meant to give edge around the median expectation of those lineups
+# So what we need to do instead is find the differences across the original set and the post-exposure_spread.py set and calculate new metrics around the diff
+# Need to find the diff in salary, median, and Own to calculate new Dupes, finish_percentile, Win%, Edge, Weighted Own, and Geomean
+# Then at the end run the Diveristy function to set a new column for Diversity
+# This way we only make the changes to the metrics where we have a difference in salary, median, and Own and leave the rest of the lineups alone
+
+import pandas as pd
+import numpy as np
+import math
+
+def reassess_dupes(row: pd.Series, salary_max: int) -> float:
+    if row['salary'] == salary_max:
+        return math.ceil(row['Dupes'] + ((row['salary_diff'] / 100) * (row['own_diff'] / 100))).clip(lower=0)
+    elif row['salary'] != salary_max:
+        return math.ceil(row['Dupes'] + ((row['salary_diff'] / 100) * (row['own_diff'] / 100))).clip(lower=0)
+    else:
+        return row['Dupes']
+
+def reassess_edge(refactored_frame: pd.DataFrame, original_frame: pd.DataFrame, maps_dict: dict, site_var: str, type_var: str, Contest_Size: int, strength_var: str, sport_var: str, salary_max: int) -> pd.DataFrame:
+    orig_df = original_frame.copy()
+    orig_df = orig_df.reset_index(drop=True)
+    refactored_df = refactored_frame.copy()
+    refactored_df = refactored_df.reset_index(drop=True)
+
+    refactored_df['salary_diff'] = refactored_df['salary'] - orig_df['salary']
+    refactored_df['median_diff'] = refactored_df['median'] - orig_df['median']
+    refactored_df['own_diff'] = refactored_df['Own'] - orig_df['Own']
+
+    change_mask = refactored_df[refactored_df['salary_diff'] != 0 | refactored_df['median_diff'] != 0 | refactored_df['own_diff'] != 0]
+
+    for lineups in change_mask.index:
+        refactored_df.loc[lineups, 'Dupes'] = reassess_dupes(refactored_df.loc[lineups, :], salary_max)
+        refactored_df.loc[lineups, 'Finish_percentile'] = refactored_df.loc[lineups, 'Finish_percentile'] + 1
+        refactored_df.loc[lineups, 'Win%'] = refactored_df.loc[lineups, 'Win%'] + 1
+        refactored_df.loc[lineups, 'Edge'] = refactored_df.loc[lineups, 'Edge'] + 1
+        refactored_df.loc[lineups, 'Weighted Own'] = refactored_df.loc[lineups, 'Weighted Own'] + 1
+        refactored_df.loc[lineups, 'Geomean'] = refactored_df.loc[lineups, 'Geomean'] + 1
+
+    return refactored_df