Implement player name standardization in app.py to enhance data consistency across simulations. Added a new function to remove common suffixes from player names and updated relevant mappings to apply this standardization. This change improves the accuracy of player data handling for contest simulations on DraftKings and FanDuel.

app.py

@@ -192,6 +192,15 @@ def init_baselines(sport):
 
     return dk_raw, fd_raw
 
+@st.cache_data
+def standardize_name(name):
+    # Remove common suffixes and standardize
+    suffixes = [' Jr.', ' Jr', ' Sr.', ' Sr', ' III', ' II', ' IV']
+    name = str(name)  # Ensure name is a string
+    for suffix in suffixes:
+        name = name.replace(suffix, '')
+    return name.strip()
+
 @st.cache_data
 def convert_df(array):
     array = pd.DataFrame(array, columns=column_names)
@@ -216,12 +225,14 @@ def sim_contest(Sim_size, seed_frame, maps_dict, sharp_split, Contest_Size):
     SimVar = 1
     Sim_Winners = []
     fp_array = seed_frame[:sharp_split, :]
+
+    vec_standardize = np.vectorize(standardize_name)
     
     # Pre-vectorize functions
-    vec_projection_map = np.vectorize(maps_dict['Projection_map'].__getitem__)
-    vec_cpt_projection_map = np.vectorize(maps_dict['cpt_projection_map'].__getitem__)
-    vec_stdev_map = np.vectorize(maps_dict['STDev_map'].__getitem__)
-    vec_cpt_stdev_map = np.vectorize(maps_dict['cpt_STDev_map'].__getitem__)
+    vec_projection_map = lambda x: np.vectorize(maps_dict['Projection_map'].__getitem__)(vec_standardize(x))
+    vec_cpt_projection_map = lambda x: np.vectorize(maps_dict['cpt_projection_map'].__getitem__)(vec_standardize(x))
+    vec_stdev_map = lambda x: np.vectorize(maps_dict['STDev_map'].__getitem__)(vec_standardize(x))
+    vec_cpt_stdev_map = lambda x: np.vectorize(maps_dict['cpt_STDev_map'].__getitem__)(vec_standardize(x))
     
     st.write('Simulating contest on frames')
     
@@ -432,15 +443,15 @@ with tab1:
         if st.button("Run Contest Sim"):
             if 'working_seed' in st.session_state:
                 maps_dict = {
-                        'Projection_map':dict(zip(raw_baselines.Player,raw_baselines.Median)),
-                        'cpt_projection_map':dict(zip(raw_baselines.Player,raw_baselines.cpt_Median)),
-                        'Salary_map':dict(zip(raw_baselines.Player,raw_baselines.Salary)),
-                        'Pos_map':dict(zip(raw_baselines.Player,raw_baselines.Position)),
-                        'Own_map':dict(zip(raw_baselines.Player,raw_baselines['Own'])),
-                        'cpt_Own_map':dict(zip(raw_baselines.Player,raw_baselines['CPT_Own'])),
-                        'Team_map':dict(zip(raw_baselines.Player,raw_baselines.Team)),
-                        'STDev_map':dict(zip(raw_baselines.Player,raw_baselines.STDev)),
-                        'cpt_STDev_map':dict(zip(raw_baselines.Player,raw_baselines['CPT_STDev']))
+                        'Projection_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines.Median)),
+                        'cpt_projection_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines.cpt_Median)),
+                        'Salary_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines.Salary)),
+                        'Pos_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines.Position)),
+                        'Own_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines['Own'])),
+                        'cpt_Own_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines['CPT_Own'])),
+                        'Team_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines.Team)),
+                        'STDev_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines.STDev)),
+                        'cpt_STDev_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines['CPT_STDev']))
                         }
                 Sim_Winners = sim_contest(1000, st.session_state.working_seed, maps_dict, sharp_split, Contest_Size)
                 Sim_Winner_Frame = pd.DataFrame(np.concatenate(Sim_Winners))
@@ -473,15 +484,15 @@ with tab1:
                 elif sim_site_var1 == 'Fanduel':
                     st.session_state.working_seed = FD_seed.copy()
                 maps_dict = {
-                        'Projection_map':dict(zip(raw_baselines.Player,raw_baselines.Median)),
-                        'cpt_projection_map':dict(zip(raw_baselines.Player,raw_baselines.cpt_Median)),
-                        'Salary_map':dict(zip(raw_baselines.Player,raw_baselines.Salary)),
-                        'Pos_map':dict(zip(raw_baselines.Player,raw_baselines.Position)),
-                        'Own_map':dict(zip(raw_baselines.Player,raw_baselines['Own'])),
-                        'cpt_Own_map':dict(zip(raw_baselines.Player,raw_baselines['CPT_Own'])),
-                        'Team_map':dict(zip(raw_baselines.Player,raw_baselines.Team)),
-                        'STDev_map':dict(zip(raw_baselines.Player,raw_baselines.STDev)),
-                        'cpt_STDev_map':dict(zip(raw_baselines.Player,raw_baselines['CPT_STDev']))
+                        'Projection_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines.Median)),
+                        'cpt_projection_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines.cpt_Median)),
+                        'Salary_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines.Salary)),
+                        'Pos_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines.Position)),
+                        'Own_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines['Own'])),
+                        'cpt_Own_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines['CPT_Own'])),
+                        'Team_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines.Team)),
+                        'STDev_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines.STDev)),
+                        'cpt_STDev_map':dict(zip(raw_baselines.Player.apply(standardize_name),raw_baselines['CPT_STDev']))
                         }
                 Sim_Winners = sim_contest(1000, st.session_state.working_seed, maps_dict, sharp_split, Contest_Size)
                 Sim_Winner_Frame = pd.DataFrame(np.concatenate(Sim_Winners))
@@ -517,18 +528,18 @@ with tab1:
                 freq_working = pd.DataFrame(np.column_stack(np.unique(freq_copy.iloc[:,0:5].values, return_counts=True)),
                                                 columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
             freq_working['Freq'] = freq_working['Freq'].astype(int)
-            freq_working['Position'] = freq_working['Player'].map(maps_dict['Pos_map'])
+            freq_working['Position'] = freq_working['Player'].apply(standardize_name).apply(standardize_name).map(maps_dict['Pos_map'])
             if sim_site_var1 == 'Draftkings':
                 if sim_sport_var1 == 'NFL':
-                    freq_working['Salary'] = freq_working['Player'].map(maps_dict['Salary_map']) / 1.5
+                    freq_working['Salary'] = freq_working['Player'].apply(standardize_name).map(maps_dict['Salary_map']) / 1.5
                 elif sim_sport_var1 == 'NBA':
-                    freq_working['Salary'] = freq_working['Player'].map(maps_dict['Salary_map'])
+                    freq_working['Salary'] = freq_working['Player'].apply(standardize_name).map(maps_dict['Salary_map'])
             elif sim_site_var1 == 'Fanduel':
-                freq_working['Salary'] = freq_working['Player'].map(maps_dict['Salary_map'])
-            freq_working['Proj Own'] = freq_working['Player'].map(maps_dict['Own_map']) / 100
+                freq_working['Salary'] = freq_working['Player'].apply(standardize_name).map(maps_dict['Salary_map'])
+            freq_working['Proj Own'] = freq_working['Player'].apply(standardize_name).map(maps_dict['Own_map']) / 100
             freq_working['Exposure'] = freq_working['Freq']/(1000)
             freq_working['Edge'] = freq_working['Exposure'] - freq_working['Proj Own']
-            freq_working['Team'] = freq_working['Player'].map(maps_dict['Team_map'])
+            freq_working['Team'] = freq_working['Player'].apply(standardize_name).map(maps_dict['Team_map'])
             st.session_state.player_freq = freq_working.copy()
 
             if sim_site_var1 == 'Draftkings':
@@ -538,15 +549,15 @@ with tab1:
                 cpt_working = pd.DataFrame(np.column_stack(np.unique(freq_copy.iloc[:,0:1].values, return_counts=True)),
                                                 columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
             cpt_working['Freq'] = cpt_working['Freq'].astype(int)
-            cpt_working['Position'] = cpt_working['Player'].map(maps_dict['Pos_map'])
+            cpt_working['Position'] = cpt_working['Player'].apply(standardize_name).map(maps_dict['Pos_map'])
             if sim_sport_var1 == 'NFL':
-                cpt_working['Salary'] = cpt_working['Player'].map(maps_dict['Salary_map'])
+                cpt_working['Salary'] = cpt_working['Player'].apply(standardize_name).map(maps_dict['Salary_map'])
             elif sim_sport_var1 == 'NBA':
-                cpt_working['Salary'] = cpt_working['Player'].map(maps_dict['Salary_map']) * 1.5
-            cpt_working['Proj Own'] = cpt_working['Player'].map(maps_dict['cpt_Own_map']) / 100
+                cpt_working['Salary'] = cpt_working['Player'].apply(standardize_name).map(maps_dict['Salary_map']) * 1.5
+            cpt_working['Proj Own'] = cpt_working['Player'].apply(standardize_name).map(maps_dict['cpt_Own_map']) / 100
             cpt_working['Exposure'] = cpt_working['Freq']/(1000)
             cpt_working['Edge'] = cpt_working['Exposure'] - cpt_working['Proj Own']
-            cpt_working['Team'] = cpt_working['Player'].map(maps_dict['Team_map'])
+            cpt_working['Team'] = cpt_working['Player'].apply(standardize_name).map(maps_dict['Team_map'])
             st.session_state.sp_freq = cpt_working.copy()
             
             if sim_site_var1 == 'Draftkings':
@@ -561,15 +572,15 @@ with tab1:
             flex_working['Position'] = flex_working['Player'].map(maps_dict['Pos_map'])
             if sim_site_var1 == 'Draftkings':
                 if sim_sport_var1 == 'NFL':
-                    flex_working['Salary'] = flex_working['Player'].map(maps_dict['Salary_map']) / 1.5
+                    flex_working['Salary'] = flex_working['Player'].apply(standardize_name).map(maps_dict['Salary_map']) / 1.5
                 elif sim_sport_var1 == 'NBA':
-                    flex_working['Salary'] = flex_working['Player'].map(maps_dict['Salary_map'])
+                    flex_working['Salary'] = flex_working['Player'].apply(standardize_name).map(maps_dict['Salary_map'])
             elif sim_site_var1 == 'Fanduel':
-                flex_working['Salary'] = flex_working['Player'].map(maps_dict['Salary_map'])
-            flex_working['Proj Own'] = (flex_working['Player'].map(maps_dict['Own_map']) / 100) - (flex_working['Player'].map(maps_dict['cpt_Own_map']) / 100)
+                flex_working['Salary'] = flex_working['Player'].apply(standardize_name).map(maps_dict['Salary_map'])
+            flex_working['Proj Own'] = (flex_working['Player'].apply(standardize_name).map(maps_dict['Own_map']) / 100) - (flex_working['Player'].apply(standardize_name).map(maps_dict['cpt_Own_map']) / 100)
             flex_working['Exposure'] = flex_working['Freq']/(1000)
             flex_working['Edge'] = flex_working['Exposure'] - flex_working['Proj Own']
-            flex_working['Team'] = flex_working['Player'].map(maps_dict['Team_map'])
+            flex_working['Team'] = flex_working['Player'].apply(standardize_name).map(maps_dict['Team_map'])
             st.session_state.flex_freq = flex_working.copy()
 
             if sim_site_var1 == 'Draftkings':