Refactor database connection to remove unused secondary database and streamline data retrieval for Draftkings and Fanduel. Update column selections for showdown formats and enhance summary statistics display based on slate type.

app.py

@@ -11,11 +11,10 @@ def init_conn():
         uri = st.secrets['mongo_uri']
         client = pymongo.MongoClient(uri, retryWrites=True, serverSelectionTimeoutMS=500000)
         db = client["MLB_Database"]
-        db2 = client["MLB_DFS"]
 
-        return db, db2
+        return db
     
-db, db2 = init_conn()
+db = init_conn()
 
 game_format = {'Win Percentage': '{:.2%}','First Inning Lead Percentage': '{:.2%}', 'Top Score': '{:.2%}',
               'Fifth Inning Lead Percentage': '{:.2%}', '8+ runs': '{:.2%}', 'DK LevX': '{:.2%}', 'FD LevX': '{:.2%}'}
@@ -25,6 +24,8 @@ player_roo_format = {'Top_finish': '{:.2%}','Top_5_finish': '{:.2%}', 'Top_10_fi
 
 dk_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']
 fd_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']
+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', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']
 
 @st.cache_resource(ttl = 60)
 def init_baselines():
@@ -107,23 +108,23 @@ def init_DK_lineups(type_var, slate_var):
             raw_display[dict_columns] = raw_display[dict_columns].apply(lambda x: x.map(names_dict))
     elif type_var == 'Showdown':
         if slate_var == 'Main':
-            collection = db2['DK_MLB_SD1_seed_frame']
+            collection = db['DK_MLB_SD1_seed_frame']
             cursor = collection.find().limit(10000)
 
             raw_display = pd.DataFrame(list(cursor))
-            raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Own']]
+            raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
         elif slate_var == 'Secondary':
-            collection = db2['DK_MLB_SD2_seed_frame']
+            collection = db['DK_MLB_SD2_seed_frame']
             cursor = collection.find().limit(10000)
 
             raw_display = pd.DataFrame(list(cursor))
-            raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Own']]
+            raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
         elif slate_var == 'Auxiliary':
-            collection = db2['DK_MLB_SD3_seed_frame']
+            collection = db['DK_MLB_SD3_seed_frame']
             cursor = collection.find().limit(10000)
 
             raw_display = pd.DataFrame(list(cursor))
-            raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Own']]
+            raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
 
     DK_seed = raw_display.to_numpy()
 
@@ -178,23 +179,23 @@ def init_FD_lineups(type_var,slate_var):
 
         elif type_var == 'Showdown':
             if slate_var == 'Main':
-                collection = db2['FD_MLB_SD1_seed_frame']
+                collection = db['FD_MLB_SD1_seed_frame']
                 cursor = collection.find().limit(10000)
 
                 raw_display = pd.DataFrame(list(cursor))
-                raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Own']]
+                raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
             elif slate_var == 'Secondary':
-                collection = db2['FD_MLB_SD2_seed_frame']
+                collection = db['FD_MLB_SD2_seed_frame']
                 cursor = collection.find().limit(10000)
 
                 raw_display = pd.DataFrame(list(cursor))
-                raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Own']]
+                raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
             elif slate_var == 'Auxiliary':
-                collection = db2['FD_MLB_SD3_seed_frame']
+                collection = db['FD_MLB_SD3_seed_frame']
                 cursor = collection.find().limit(10000)
             
                 raw_display = pd.DataFrame(list(cursor))
-                raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Own']]
+                raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
     
         FD_seed = raw_display.to_numpy()
 
@@ -372,7 +373,7 @@ with tab3:
         lineup_num_var = st.number_input("How many lineups do you want to display?", min_value=1, max_value=1000, value=150, step=1)
         
         if slate_type_var3 == 'Regular':
-                raw_baselines = roo_data
+            raw_baselines = roo_data
         elif slate_type_var3 == 'Showdown':
             raw_baselines = sd_roo_data
         
@@ -380,12 +381,14 @@ with tab3:
             if slate_type_var3 == 'Regular':
                 ROO_slice = raw_baselines[raw_baselines['Site'] == 'Draftkings']
                 player_salaries = dict(zip(ROO_slice['Player'], ROO_slice['Salary']))
+                column_names = dk_columns
             elif slate_type_var3 == 'Showdown':
                 player_salaries = dict(zip(raw_baselines['Player'], raw_baselines['Salary']))
+                column_names = dk_sd_columns
             # Get the minimum and maximum ownership values from dk_lineups
-            min_own = np.min(dk_lineups[:,8])
-            max_own = np.max(dk_lineups[:,8])
-            column_names = dk_columns
+            min_own = np.min(dk_lineups[:,12])
+            max_own = np.max(dk_lineups[:,12])
+            
             
             player_var1 = st.radio("Do you want a frame with specific Players?", ('Full Slate', 'Specific Players'), key='player_var1')
             if player_var1 == 'Specific Players':
@@ -398,11 +401,14 @@ with tab3:
             if slate_type_var3 == 'Regular':
                 ROO_slice = raw_baselines[raw_baselines['Site'] == 'Fanduel']
                 player_salaries = dict(zip(ROO_slice['Player'], ROO_slice['Salary']))
+                column_names = fd_columns
             elif slate_type_var3 == 'Showdown':
                 player_salaries = dict(zip(raw_baselines['Player'], raw_baselines['Salary']))
-            min_own = np.min(fd_lineups[:,8])
-            max_own = np.max(fd_lineups[:,8])
-            column_names = fd_columns
+                column_names = fd_sd_columns
+            # Get the minimum and maximum ownership values from dk_lineups
+            min_own = np.min(fd_lineups[:,11])
+            max_own = np.max(fd_lineups[:,11])
+            
             
             player_var1 = st.radio("Do you want a frame with specific Players?", ('Full Slate', 'Specific Players'), key='player_var1')
             if player_var1 == 'Specific Players':
@@ -414,11 +420,17 @@ with tab3:
             name_export = pd.DataFrame(st.session_state.working_seed.copy(), columns=column_names)
             data_export = pd.DataFrame(st.session_state.working_seed.copy(), columns=column_names)
             if site_var == 'Draftkings':
-                map_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']
+                if slate_type_var3 == 'Regular':
+                    map_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']
+                elif slate_type_var3 == 'Showdown':
+                    map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']
                 for col_idx in map_columns:
                     data_export[col_idx] = data_export[col_idx].map(dk_id_map)
             elif site_var == 'Fanduel':
-                map_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']
+                if slate_type_var3 == 'Regular':
+                    map_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']
+                elif slate_type_var3 == 'Showdown':
+                    map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4']
                 for col_idx in map_columns:
                     data_export[col_idx] = data_export[col_idx].map(fd_id_map)
             st.download_button(
@@ -471,11 +483,17 @@ with tab3:
     export_file = st.session_state.data_export_display.copy()
     name_export = st.session_state.data_export_display.copy()
     if site_var == 'Draftkings':
-        map_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']
+        if slate_type_var3 == 'Regular':
+            map_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']
+        elif slate_type_var3 == 'Showdown':
+            map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']
         for col_idx in map_columns:
             export_file[col_idx] = export_file[col_idx].map(dk_id_map)
     elif site_var == 'Fanduel':
-        map_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']
+        if slate_type_var3 == 'Regular':
+            map_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']
+        elif slate_type_var3 == 'Showdown':
+            map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4']
         for col_idx in map_columns:
             export_file[col_idx] = export_file[col_idx].map(fd_id_map)
             
@@ -503,72 +521,79 @@ with tab3:
         )
     
     with st.container():
-        if 'working_seed' in st.session_state:
-            # Create a new dataframe with summary statistics
-            if site_var == 'Draftkings':
-                summary_df = pd.DataFrame({
-                    'Metric': ['Min', 'Average', 'Max', 'STDdev'],
-                    'Salary': [
-                        np.min(st.session_state.working_seed[:,10]),
-                        np.mean(st.session_state.working_seed[:,10]),
-                        np.max(st.session_state.working_seed[:,10]),
-                        np.std(st.session_state.working_seed[:,10])
-                    ],
-                    'Proj': [
-                        np.min(st.session_state.working_seed[:,11]),
-                        np.mean(st.session_state.working_seed[:,11]),
-                        np.max(st.session_state.working_seed[:,11]),
-                        np.std(st.session_state.working_seed[:,11])
-                    ],
-                    'Own': [
-                        np.min(st.session_state.working_seed[:,16]),
-                        np.mean(st.session_state.working_seed[:,16]),
-                        np.max(st.session_state.working_seed[:,16]),
-                        np.std(st.session_state.working_seed[:,16])
-                    ]
-                })
-            elif site_var == 'Fanduel':
-                summary_df = pd.DataFrame({
-                    'Metric': ['Min', 'Average', 'Max', 'STDdev'],
-                    'Salary': [
-                        np.min(st.session_state.working_seed[:,9]),
-                        np.mean(st.session_state.working_seed[:,9]),
-                        np.max(st.session_state.working_seed[:,9]),
-                        np.std(st.session_state.working_seed[:,9])
-                    ],
-                    'Proj': [
-                        np.min(st.session_state.working_seed[:,10]),
-                        np.mean(st.session_state.working_seed[:,10]),
-                        np.max(st.session_state.working_seed[:,10]),
-                        np.std(st.session_state.working_seed[:,10])
-                    ],
-                    'Own': [
-                        np.min(st.session_state.working_seed[:,15]),
-                        np.mean(st.session_state.working_seed[:,15]),
-                        np.max(st.session_state.working_seed[:,15]),
-                        np.std(st.session_state.working_seed[:,15])
-                    ]
-                })
-
-            # Set the index of the summary dataframe as the "Metric" column
-            summary_df = summary_df.set_index('Metric')
-
-            # Display the summary dataframe
-            st.subheader("Optimal Statistics")
-            st.dataframe(summary_df.style.format({
-                'Salary': '{:.2f}',
-                'Proj': '{:.2f}',
-                'Own': '{:.2f}'
-            }).background_gradient(cmap='RdYlGn', axis=0, subset=['Salary', 'Proj', 'Own']), use_container_width=True)
+        if slate_type_var3 == 'Regular':
+            if 'working_seed' in st.session_state:
+                # Create a new dataframe with summary statistics
+                if site_var == 'Draftkings':
+                    summary_df = pd.DataFrame({
+                        'Metric': ['Min', 'Average', 'Max', 'STDdev'],
+                        'Salary': [
+                            np.min(st.session_state.working_seed[:,10]),
+                            np.mean(st.session_state.working_seed[:,10]),
+                            np.max(st.session_state.working_seed[:,10]),
+                            np.std(st.session_state.working_seed[:,10])
+                        ],
+                        'Proj': [
+                            np.min(st.session_state.working_seed[:,11]),
+                            np.mean(st.session_state.working_seed[:,11]),
+                            np.max(st.session_state.working_seed[:,11]),
+                            np.std(st.session_state.working_seed[:,11])
+                        ],
+                        'Own': [
+                            np.min(st.session_state.working_seed[:,16]),
+                            np.mean(st.session_state.working_seed[:,16]),
+                            np.max(st.session_state.working_seed[:,16]),
+                            np.std(st.session_state.working_seed[:,16])
+                        ]
+                    })
+                elif site_var == 'Fanduel':
+                    summary_df = pd.DataFrame({
+                        'Metric': ['Min', 'Average', 'Max', 'STDdev'],
+                        'Salary': [
+                            np.min(st.session_state.working_seed[:,9]),
+                            np.mean(st.session_state.working_seed[:,9]),
+                            np.max(st.session_state.working_seed[:,9]),
+                            np.std(st.session_state.working_seed[:,9])
+                        ],
+                        'Proj': [
+                            np.min(st.session_state.working_seed[:,10]),
+                            np.mean(st.session_state.working_seed[:,10]),
+                            np.max(st.session_state.working_seed[:,10]),
+                            np.std(st.session_state.working_seed[:,10])
+                        ],
+                        'Own': [
+                            np.min(st.session_state.working_seed[:,15]),
+                            np.mean(st.session_state.working_seed[:,15]),
+                            np.max(st.session_state.working_seed[:,15]),
+                            np.std(st.session_state.working_seed[:,15])
+                        ]
+                    })
+
+                # Set the index of the summary dataframe as the "Metric" column
+                summary_df = summary_df.set_index('Metric')
+
+                # Display the summary dataframe
+                st.subheader("Optimal Statistics")
+                st.dataframe(summary_df.style.format({
+                    'Salary': '{:.2f}',
+                    'Proj': '{:.2f}',
+                    'Own': '{:.2f}'
+                }).background_gradient(cmap='RdYlGn', axis=0, subset=['Salary', 'Proj', 'Own']), use_container_width=True)
 
     with st.container():
         tab1, tab2 = st.tabs(["Display Frequency", "Seed Frame Frequency"])
         with tab1:
             if 'data_export_display' in st.session_state:
                 if site_var == 'Draftkings':
-                    player_columns = st.session_state.data_export_display.iloc[:, :10]
+                    if slate_type_var3 == 'Regular':
+                        player_columns = st.session_state.data_export_display.iloc[:, :10]
+                    elif slate_type_var3 == 'Showdown':
+                        player_columns = st.session_state.data_export_display.iloc[:, :6]
                 elif site_var == 'Fanduel':
-                    player_columns = st.session_state.data_export_display.iloc[:, :9]
+                    if slate_type_var3 == 'Regular':
+                        player_columns = st.session_state.data_export_display.iloc[:, :9]
+                    elif slate_type_var3 == 'Showdown':
+                        player_columns = st.session_state.data_export_display.iloc[:, :5]
                 
                 # Flatten the DataFrame and count unique values
                 value_counts = player_columns.values.flatten().tolist()
@@ -602,9 +627,15 @@ with tab3:
         with tab2:
             if 'working_seed' in st.session_state:
                 if site_var == 'Draftkings':
-                    player_columns = st.session_state.working_seed[:, :10]
+                    if slate_type_var3 == 'Regular':
+                        player_columns = st.session_state.working_seed[:, :10]
+                    elif slate_type_var3 == 'Showdown':
+                        player_columns = st.session_state.working_seed[:, :7]
                 elif site_var == 'Fanduel':
-                    player_columns = st.session_state.working_seed[:, :9]
+                    if slate_type_var3 == 'Regular':
+                        player_columns = st.session_state.working_seed[:, :9]
+                    elif slate_type_var3 == 'Showdown':
+                        player_columns = st.session_state.working_seed[:, :6]
                 
                 # Flatten the DataFrame and count unique values
                 value_counts = player_columns.flatten().tolist()