Refactor data processing in app.py to streamline the initialization of pitcher and hitter statistics. Updated variable names and removed unnecessary return values for improved clarity and efficiency.

app.py

@@ -75,18 +75,18 @@ def init_baselines():
         collection = db["Pitcher_Stats"] 
         cursor = collection.find()
         raw_display = pd.DataFrame(cursor)
-        props_frame_hold.rename(columns={"Names": "Player"}, inplace = True)
-        props_frame_hold = props_frame_hold[['Player', 'Team', 'BB', 'Hits', 'HRs', 'ERs', 'Ks', 'Outs', 'Fantasy', 'FD_Fantasy', 'PrizePicks']]
-        pitcher_stats = props_frame_hold.drop_duplicates(subset='Player')
+        raw_display.rename(columns={"Names": "Player"}, inplace = True)
+        pitcher_stats = raw_display[['Player', 'Team', 'BB', 'Hits', 'HRs', 'ERs', 'Ks', 'Outs', 'Fantasy', 'FD_Fantasy', 'PrizePicks']]
+        pitcher_stats = pitcher_stats.drop_duplicates(subset='Player')
         
         collection = db['Hitter_Stats']
         cursor = collection.find()
         raw_display = pd.DataFrame(cursor)
-        props_frame_hold.rename(columns={"Names": "Player"}, inplace = True)
-        props_frame_hold = props_frame_hold[['Player', 'Team', 'Walks', 'Steals', 'Hits', 'Singles', 'Doubles', 'HRs', 'RBIs', 'Runs', 'Fantasy', 'FD_Fantasy', 'PrizePicks']]
-        props_frame_hold['Total Bases'] = props_frame_hold['Singles'] + (props_frame_hold['Doubles'] * 2) + (props_frame_hold['HRs'] * 4)
-        props_frame_hold['Hits + Runs + RBIs'] = props_frame_hold['Hits'] + props_frame_hold['Runs'] + props_frame_hold['RBIs']
-        hitter_stats = props_frame_hold.drop_duplicates(subset='Player')
+        raw_display.rename(columns={"Names": "Player"}, inplace = True)
+        hitter_stats = raw_display[['Player', 'Team', 'Walks', 'Steals', 'Hits', 'Singles', 'Doubles', 'HRs', 'RBIs', 'Runs', 'Fantasy', 'FD_Fantasy', 'PrizePicks']]
+        hitter_stats['Total Bases'] = hitter_stats['Singles'] + (hitter_stats['Doubles'] * 2) + (hitter_stats['HRs'] * 4)
+        hitter_stats['Hits + Runs + RBIs'] = hitter_stats['Hits'] + hitter_stats['Runs'] + hitter_stats['RBIs']
+        hitter_stats = hitter_stats.drop_duplicates(subset='Player')
         
         collection = db['Game_Betting_Model']
         cursor = collection.find()
@@ -113,9 +113,9 @@ def init_baselines():
         raw_display.replace('', np.nan, inplace=True)
         pick_frame = raw_display.dropna(subset='Player')
         
-        return pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame, t_stamp
+        return pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame
 
-pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame, t_stamp = init_baselines()
+pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame = init_baselines()
 
 tab1, tab2, tab3, tab4, tab5, tab6 = st.tabs(["Game Betting Model", "Pitcher Prop Projections", "Hitter Prop Projections", "Player Prop Simulations", "Stat Specific Simulations", "Bet Sheet"])
 
@@ -123,10 +123,9 @@ def convert_df_to_csv(df):
     return df.to_csv().encode('utf-8')
 
 with tab1:
-    st.info(t_stamp)
     if st.button("Reset Data", key='reset1'):
               st.cache_data.clear()
-              pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame, t_stamp = init_baselines()
+              pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame = init_baselines()
     line_var1 = st.radio('How would you like to display odds?', options = ['Percentage', 'American'], key='line_var1')
     if line_var1 == 'Percentage':
         team_frame = team_frame[['Names', 'Game', 'Moneyline', 'Win Percentage', 'ML_Value', 'Spread', 'Cover Spread Percentage', 'Spread_Value', 'Avg Score', 'Game Total', 'Avg Fifth Inning', 'Fifth Inning Lead Percentage']]
@@ -147,10 +146,9 @@ with tab1:
     )
 
 with tab2:
-    st.info(t_stamp)
     if st.button("Reset Data", key='reset2'):
               st.cache_data.clear()
-              pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame, t_stamp = init_baselines()
+              pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame = init_baselines()
     split_var1 = st.radio("Would you like to view all teams or specific ones?", ('All', 'Specific Teams'), key='split_var1')
     if split_var1 == 'Specific Teams':
         team_var1 = st.multiselect('Which teams would you like to include in the tables?', options = pitcher_stats['Team'].unique(), key='team_var1')
@@ -169,10 +167,9 @@ with tab2:
     )
 
 with tab3:
-    st.info(t_stamp)
     if st.button("Reset Data", key='reset3'):
               st.cache_data.clear()
-              pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame, t_stamp = init_baselines()
+              pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame = init_baselines()
     split_var2 = st.radio("Would you like to view all teams or specific ones?", ('All', 'Specific Teams'), key='split_var2')
     if split_var2 == 'Specific Teams':
         team_var2 = st.multiselect('Which teams would you like to include in the tables?', options = hitter_stats['Team'].unique(), key='team_var2')
@@ -191,10 +188,9 @@ with tab3:
     )
 
 with tab4:
-    st.info(t_stamp)
     if st.button("Reset Data", key='reset4'):
               st.cache_data.clear()
-              pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame, t_stamp = init_baselines()
+              pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame = init_baselines()
     col1, col2 = st.columns([1, 5])
     
     with col2:
@@ -355,13 +351,10 @@ with tab4:
                             st.plotly_chart(fig, use_container_width=True)
 
 with tab5:
-    st.info(t_stamp)
     st.info('The Over and Under percentages are a compositve percentage based on simulations, historical performance, and implied probabilities, and may be different than you would expect based purely on the median projection. Likewise, the Edge of a bet is not the only indicator of if you should make the bet or not as the suggestion is using a base acceptable threshold to determine how much edge you should have for each stat category.')
     if st.button("Reset Data/Load Data", key='reset5'):
-              # Clear values from *all* all in-memory and on-disk data caches:
-              # i.e. clear values from both square and cube
               st.cache_data.clear()
-              pitcher_stats, hitter_stats, team_frame, prop_frame, pick_frame, t_stamp = init_baselines()
+              pitcher_stats, hitter_stats, team_frame, prop_frame, pick_frame = init_baselines()
     col1, col2 = st.columns([1, 5])
     
     with col2:
@@ -604,11 +597,10 @@ with tab5:
 
 with tab6:
     col1, col2, col3 = st.columns([2, 2, 2])
-    st.info(t_stamp)
     st.info('This sheet is more or less a static represenation of the Stat Specific Simulations. ROR is rate of return based on hit rate and payout. Use the over and under EDGEs to place bets. 20%+ should be considered a 1 unit bet, 15-20% is .75 units, 10-15% is .50 units, 5-10% is .25 units, and 0-5% is .1 units.')
     if st.button("Reset Data", key='reset6'):
             st.cache_data.clear()
-            pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame, t_stamp = init_baselines()
+            pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame = init_baselines()
     with col1:
         split_var6 = st.radio("Would you like to view all teams or specific ones?", ('All', 'Specific Teams'), key='split_var6')
         if split_var6 == 'Specific Teams':