Testing some new logic around stratification

app.py

@@ -2335,7 +2335,7 @@ if selected_tab == 'Manage Portfolio':
                         st.session_state['export_merge'] = st.session_state['export_base'].copy()
             with st.expander('Stratify'):
                 with st.form(key='Stratification'):
-                    sorting_choice = st.selectbox("Stat Choice", options=['median', 'Own', 'Weighted Own', 'Geomean', 'Lineup Edge', 'Finish_percentile', 'Diversity'], index=0)
+                    sorting_choice = st.selectbox("Stat Choice", options=['median', 'Own', 'Weighted Own', 'Geomean', 'Lineup Edge', 'Finish_percentile', 'SE Score', 'Diversity'], index=0)
                     lineup_target = st.number_input("Lineups to produce", value=150, min_value=1, step=1)
                     strat_sample = st.slider("Sample range", value=[0.0, 100.0], min_value=0.0, max_value=100.0, step=1.0)
                     submitted_col, export_col = st.columns(2)

global_func/stratification_function.py

@@ -2,7 +2,7 @@ import pandas as pd
 import numpy as np
 
 def stratification_function(portfolio: pd.DataFrame, lineup_target: int, exclude_cols: list, sport: str, sorting_choice: str, low_threshold: float, high_threshold: float):
-    excluded_cols = ['salary', 'median', 'Own', 'Finish_percentile', 'Dupes', 'Stack', 'Size', 'Win%', 'Lineup Edge', 'Weighted Own', 'Geomean', 'Diversity']
+    excluded_cols = ['salary', 'median', 'Own', 'Finish_percentile', 'Dupes', 'Stack', 'Size', 'Win%', 'Lineup Edge', 'Weighted Own', 'Geomean', 'Diversity', 'SE Score']
     player_columns = [col for col in portfolio.columns if col not in excluded_cols]
     
     # Work with indices instead of copying entire DataFrame
@@ -15,16 +15,21 @@ def stratification_function(portfolio: pd.DataFrame, lineup_target: int, exclude
     similarity_floor = portfolio[sorting_choice].quantile(low_threshold / 100)
     similarity_ceiling = portfolio[sorting_choice].quantile(high_threshold / 100)
     
-    # Create evenly spaced target similarity scores
-    target_similarities = np.linspace(similarity_floor, similarity_ceiling, lineup_target)
-    
-    # Find the closest lineup to each target similarity score
-    selected_indices = []
-    for target_sim in target_similarities:
-        # Find the index of the closest similarity score
-        closest_idx = (portfolio[sorting_choice] - target_sim).abs().idxmin()
-        if closest_idx not in selected_indices:  # Avoid duplicates
-            selected_indices.append(closest_idx)
+    while True:
+        target_similarities = np.linspace(similarity_floor, similarity_ceiling, lineup_target)
+        
+        # Find the closest lineup to each target similarity score
+        selected_indices = []
+        for target_sim in target_similarities:
+            # Find the index of the closest similarity score
+            closest_idx = (portfolio[sorting_choice] - target_sim).abs().idxmin()
+            if closest_idx not in selected_indices:  # Avoid duplicates
+                selected_indices.append(closest_idx)
+        if len(selected_indices) > lineup_target:
+            selected_indices = selected_indices[:lineup_target]
+            break
+        else:
+            lineup_target += 5
     
     # Return view instead of copy
     return portfolio.loc[selected_indices].sort_values(by=sorting_choice, ascending=False)