Add team name mapping for NFL teams in data processing

src/streamlit_app.py

@@ -22,6 +22,16 @@ fd_hb_columns = ['QB', 'RB1', 'RB2', 'WR1', 'WR2', 'WR3', 'TE', 'FLEX', 'DST']
 dk_sd_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']
 fd_sd_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']
 
+wrong_team_names = ['Denver Broncos', 'Washington Commanders', 'Cincinnati Bengals', 'Arizona Cardinals', 'Los Angeles Rams', 'Pittsburgh Steelers',
+'Jacksonville Jaguars', 'New England Patriots', 'Tampa Bay Buccaneers', 'San Francisco 49ers', 'Green Bay Packers', 'New York Jets',
+'Indianapolis Colts', 'Miami Dolphins', 'Detroit Lions', 'Las Vegas Raiders', 'Atlanta Falcons', 'Seattle Seahawks', 'Houston Texans',
+'New Orleans Saints', 'Carolina Panthers', 'New York Giants', 'Cleveland Browns', 'Tennessee Titans', 'Philadelphia Eagles', 'Dallas Cowboys',
+'Kansas City Chiefs', 'Los Angeles Chargers', 'Baltimore Ravens', 'Buffalo Bills', 'Minnesota Vikings', 'Chicago Bears']
+right_name_teams = ['Broncos', 'Commanders', 'Bengals', 'Cardinals', 'Rams', 'Steelers', 'Jaguars', 'Patriots', 'Buccaneers', '49ers', 'Packers', 
+'Jets', 'Colts', 'Dolphins', 'Lions', 'Raiders', 'Falcons', 'Seahawks', 'Texans', 'Saints', 'Panthers', 'Giants', 'Browns', 'Titans', 'Eagles', 'Cowboys',
+'Chiefs', 'Chargers', 'Ravens', 'Bills', 'Vikings', 'Bears']
+
+
 st.markdown("""
 <style>
     /* Tab styling */
@@ -70,6 +80,7 @@ def init_handbuilder_data(site_var):
         raw_display = raw_display[['Player', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '2x%', '3x%', '4x%',
                                    'Own', 'Small_Field_Own', 'Large_Field_Own', 'Cash_Field_Own', 'CPT_Own', 'LevX', 'version', 'slate', 'timestamp', 'player_id', 'site']]
         load_display = raw_display[raw_display['Position'] != 'K']
+        load_display['Team'] = load_display['Team'].map(dict(zip(wrong_team_names, right_name_teams)))
         return load_display.dropna(subset=['Median'])
     else:
         collection = db["FD_NFL_ROO"] 
@@ -79,6 +90,7 @@ def init_handbuilder_data(site_var):
         raw_display = raw_display[['Player', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '2x%', '3x%', '4x%',
                                    'Own', 'Small_Field_Own', 'Large_Field_Own', 'Cash_Field_Own', 'CPT_Own', 'LevX', 'version', 'slate', 'timestamp', 'player_id', 'site']]
         load_display = raw_display[raw_display['Position'] != 'K']
+        load_display['Team'] = load_display['Team'].map(dict(zip(wrong_team_names, right_name_teams)))
         return load_display.dropna(subset=['Median'])
 
 @st.cache_resource(ttl=60)
@@ -90,6 +102,7 @@ def init_baselines():
     raw_display = pd.DataFrame(list(cursor))
     raw_display = raw_display[['name', 'Team', 'Opp', 'Position', 'Salary', 'team_plays', 'team_pass', 'team_rush', 'team_tds', 'team_pass_tds', 'team_rush_tds', 'dropbacks', 'pass_yards', 'pass_tds',
                                'rush_att', 'rush_yards', 'rush_tds', 'targets', 'rec', 'rec_yards', 'rec_tds', 'PPR', 'Half_PPR', 'Own']]
+    raw_display['Team'] = raw_display['Team'].map(dict(zip(wrong_team_names, right_name_teams)))
     player_stats = raw_display[raw_display['Position'] != 'K']
 
     collection = db["DK_NFL_ROO"] 
@@ -99,6 +112,7 @@ def init_baselines():
     raw_display = raw_display.rename(columns={'player_ID': 'player_id'})
     raw_display = raw_display[['Player', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '2x%', '3x%', '4x%',
                                'Own', 'Small_Field_Own', 'Large_Field_Own', 'Cash_Field_Own', 'CPT_Own', 'LevX', 'version', 'slate', 'timestamp', 'player_id', 'site']]
+    raw_display['Team'] = raw_display['Team'].map(dict(zip(wrong_team_names, right_name_teams)))
     load_display = raw_display[raw_display['Position'] != 'K']
     dk_roo_raw = load_display.dropna(subset=['Median'])
 
@@ -111,6 +125,7 @@ def init_baselines():
     raw_display = raw_display.rename(columns={'player_ID': 'player_id'})
     raw_display = raw_display[['Player', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '2x%', '3x%', '4x%',
                                'Own', 'Small_Field_Own', 'Large_Field_Own', 'Cash_Field_Own', 'CPT_Own', 'LevX', 'version', 'slate', 'timestamp', 'player_id', 'site']]
+    raw_display['Team'] = raw_display['Team'].map(dict(zip(wrong_team_names, right_name_teams)))
     load_display = raw_display[raw_display['Position'] != 'K']
     fd_roo_raw = load_display.dropna(subset=['Median'])
 
@@ -123,6 +138,7 @@ def init_baselines():
     raw_display = raw_display.rename(columns={'player_ID': 'player_id'})
     raw_display = raw_display[['Player', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '2x%', '3x%', '4x%',
                                'Own', 'Small_Field_Own', 'Large_Field_Own', 'Cash_Field_Own', 'CPT_Own', 'LevX', 'version', 'slate', 'timestamp', 'player_id', 'site']]
+    raw_display['Team'] = raw_display['Team'].map(dict(zip(wrong_team_names, right_name_teams)))
     # load_display = raw_display[raw_display['Position'] != 'K']
     dk_sd_roo_raw = raw_display.dropna(subset=['Median'])
 
@@ -135,6 +151,7 @@ def init_baselines():
     raw_display = raw_display.rename(columns={'player_ID': 'player_id'})
     raw_display = raw_display[['Player', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '2x%', '3x%', '4x%',
                                'Own', 'Small_Field_Own', 'Large_Field_Own', 'Cash_Field_Own', 'CPT_Own', 'LevX', 'version', 'slate', 'timestamp', 'player_id', 'site']]
+    raw_display['Team'] = raw_display['Team'].map(dict(zip(wrong_team_names, right_name_teams)))
     # load_display = raw_display[raw_display['Position'] != 'K']
     fd_sd_roo_raw = raw_display.dropna(subset=['Median'])
 
@@ -167,6 +184,7 @@ def init_DK_lineups(type_var, slate_var, prio_var, prio_mix):
             collection = db['DK_NFL_name_map']
             cursor = collection.find()
             raw_data = pd.DataFrame(list(cursor))
+            raw_data['value'] = raw_data['value'].map(dict(zip(wrong_team_names, right_name_teams)))
             names_dict = dict(zip(raw_data['key'], raw_data['value']))
 
             collection = db['DK_NFL_seed_frame']
@@ -186,6 +204,7 @@ def init_DK_lineups(type_var, slate_var, prio_var, prio_mix):
             collection = db['DK_NFL_Secondary_name_map']
             cursor = collection.find()
             raw_data = pd.DataFrame(list(cursor))
+            raw_data['value'] = raw_data['value'].map(dict(zip(wrong_team_names, right_name_teams)))
             names_dict = dict(zip(raw_data['key'], raw_data['value']))
             
             collection = db['DK_NFL_Secondary_seed_frame']
@@ -205,6 +224,7 @@ def init_DK_lineups(type_var, slate_var, prio_var, prio_mix):
             collection = db['DK_NFL_Late_name_map']
             cursor = collection.find()
             raw_data = pd.DataFrame(list(cursor))
+            raw_data['value'] = raw_data['value'].map(dict(zip(wrong_team_names, right_name_teams)))
             names_dict = dict(zip(raw_data['key'], raw_data['value']))
             
             collection = db['DK_NFL_Late_seed_frame']
@@ -232,6 +252,8 @@ def init_DK_lineups(type_var, slate_var, prio_var, prio_mix):
                 raw_display = pd.DataFrame(list(cursor))
 
             raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
+            for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
+                raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)))
         elif slate_var == 'Secondary':
             collection = db['DK_NFL_Secondary_SD_seed_frame']
             if prio_var == None:
@@ -243,6 +265,8 @@ def init_DK_lineups(type_var, slate_var, prio_var, prio_mix):
                 raw_display = pd.DataFrame(list(cursor))
 
             raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
+            for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
+                raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)))
         elif slate_var == 'Auxiliary':
             collection = db['DK_NFL_Auxiliary_SD_seed_frame']
             if prio_var == None:
@@ -254,6 +278,8 @@ def init_DK_lineups(type_var, slate_var, prio_var, prio_mix):
                 raw_display = pd.DataFrame(list(cursor))
 
             raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
+            for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
+                raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)))
 
     DK_seed = raw_display.to_numpy()
 
@@ -270,8 +296,10 @@ def init_FD_lineups(type_var, slate_var, prio_var, prio_mix):
             collection = db['FD_NFL_name_map']
             cursor = collection.find()
             raw_data = pd.DataFrame(list(cursor))
+            raw_data['value'] = raw_data['value'].map(dict(zip(wrong_team_names, right_name_teams)))
             names_dict = dict(zip(raw_data['key'], raw_data['value']))
 
+
             collection = db['FD_NFL_seed_frame']
             if prio_var == None:
                 cursor1 = collection.find().limit(math.ceil(10000 * (prio_mix / 100)))
@@ -289,6 +317,7 @@ def init_FD_lineups(type_var, slate_var, prio_var, prio_mix):
             collection = db['FD_NFL_Secondary_name_map']
             cursor = collection.find()
             raw_data = pd.DataFrame(list(cursor))
+            raw_data['value'] = raw_data['value'].map(dict(zip(wrong_team_names, right_name_teams)))
             names_dict = dict(zip(raw_data['key'], raw_data['value']))
 
             collection = db['FD_NFL_Secondary_seed_frame']
@@ -308,6 +337,7 @@ def init_FD_lineups(type_var, slate_var, prio_var, prio_mix):
             collection = db['FD_NFL_Late_name_map']
             cursor = collection.find()
             raw_data = pd.DataFrame(list(cursor))
+            raw_data['value'] = raw_data['value'].map(dict(zip(wrong_team_names, right_name_teams)))
             names_dict = dict(zip(raw_data['key'], raw_data['value']))
 
             collection = db['FD_NFL_Late_seed_frame']
@@ -336,6 +366,8 @@ def init_FD_lineups(type_var, slate_var, prio_var, prio_mix):
                 raw_display = pd.DataFrame(list(cursor))
 
             raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
+            for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
+                raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)))
         elif slate_var == 'Secondary':
             collection = db['FD_NFL_Secondary_SD_seed_frame']
             if prio_var == None:
@@ -347,6 +379,8 @@ def init_FD_lineups(type_var, slate_var, prio_var, prio_mix):
                 raw_display = pd.DataFrame(list(cursor))
 
             raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
+            for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
+                raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)))
         elif slate_var == 'Auxiliary':
             collection = db['FD_NFL_Auxiliary_SD_seed_frame']
             if prio_var == None:
@@ -358,6 +392,8 @@ def init_FD_lineups(type_var, slate_var, prio_var, prio_mix):
                 raw_display = pd.DataFrame(list(cursor))
 
             raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
+            for column in ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']:
+                raw_display[column] = raw_display[column].map(dict(zip(wrong_team_names, right_name_teams)))
 
     FD_seed = raw_display.to_numpy()