Update app.py

app.py

@@ -40,6 +40,8 @@ gcservice_account, client, db = init_conn()
 MLB_Data = 'https://docs.google.com/spreadsheets/d/1f42Ergav8K1VsOLOK9MUn7DM_MLMvv4GR2Fy7EfnZTc/edit#gid=340831852'
 
 percentages_format = {'Exposure': '{:.2%}'}
+dk_columns = [['salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']]
+fd_columns = [['salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']]
 
 @st.cache_data(ttl = 600)
 def init_baselines():
@@ -64,8 +66,7 @@ def init_DK_seed_frame():
     collection = db["DK_MLB_seed_frame"] 
     cursor = collection.find()
     
-    raw_display = pd.DataFrame(list(cursor))
-    DK_seed = raw_display[['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'salary', 'proj']]
+    DK_seed = np.array(list(cursor))
 
     return DK_seed
 
@@ -74,16 +75,23 @@ def init_FD_seed_frame():
     collection = db["FD_MLB_seed_frame"] 
     cursor = collection.find()
     
-    raw_display = pd.DataFrame(list(cursor))
-    FD_seed = raw_display[['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'salary', 'proj']]
+    FD_seed = np.array(list(cursor))
 
     return FD_seed
 
 @st.cache_data
-def convert_df(df):
+def convert_df(array):
     # IMPORTANT: Cache the conversion to prevent computation on every rerun
+    array = pd.DataFrame(array, columns=column_names)
     return df.to_csv().encode('utf-8')
 
+@st.cache_data
+def calculate_value_frequencies(np_array):
+    unique, counts = np.unique(np_array, return_counts=True)
+    frequencies = counts / len(np_array)  # Normalize by the number of rows 
+    combined_array = np.column_stack((unique, frequencies))  
+    return combined_array 
+
 dk_raw, fd_raw = init_baselines()
 
 tab1, tab2 = st.tabs(['Data Export', 'Contest Sims'])
@@ -100,6 +108,7 @@ with tab1:
         site_var1 = st.radio("What site are you working with?", ('Draftkings', 'Fanduel'))
         if site_var1 == 'Draftkings':
             raw_baselines = dk_raw
+            column_names = dk_columns
             
             team_var1 = st.radio("Do you want a frame with specific teams?", ('Full Slate', 'Specific Teams'), key='team_var1')
             if team_var1 == 'Specific Teams':
@@ -115,6 +124,7 @@ with tab1:
                     
         elif site_var1 == 'Fanduel':
             raw_baselines = fd_raw
+            column_names = fd_columns
             
             team_var1 = st.radio("Do you want a frame with specific teams?", ('Full Slate', 'Specific Teams'), key='team_var1')
             if team_var1 == 'Specific Teams':
@@ -132,16 +142,13 @@ with tab1:
         if st.button("Load Seed Frame", key='seed_frame_load'):
             if site_var1 == 'Draftkings':
                 
-                DK_seed = init_DK_seed_frame()
-                DK_seed_parse = DK_seed[DK_seed['Team'].isin(team_var2)]
-                DK_seed_parse = DK_seed_parse[DK_seed_parse['Team_count'].isin(stack_var2)]
-                data_export_display = DK_seed_parse.head(1000)
+                working_seed = init_DK_seed_frame()
+                working_seed_parse = working_seed[np.isin(working_seed[:, 2], team_var2)]
+                working_seed_parse = working_seed[np.isin(working_seed[:, 3], stack_var2)]
+                data_export_display = working_seed_parse[0:1000]
                 st.session_state.data_export_display = data_export_display.copy()
-                st.session_state.data_export = DK_seed.copy()
-                st.session_state.data_export_freq = pd.DataFrame(np.column_stack(np.unique(st.session_state.data_export.iloc[:,0:9].values, return_counts=True)),
-                                            columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
-                st.session_state.data_export_freq['Freq'] = st.session_state.data_export_freq['Freq'].astype(int)
-                st.session_state.data_export_freq['Exposure'] = st.session_state.data_export_freq['Freq']/(len(st.session_state.data_export_expo['Team']))
+                st.session_state.data_export = working_seed.copy()
+                st.session_state.data_export_freq = calculate_value_frequencies(my_array)
                 
                 if 'data_export' in st.session_state:
                         st.download_button(
@@ -158,16 +165,14 @@ with tab1:
                         st.dataframe(st.session_state.data_export_freq.style.format(percentages_format, precision=2), height=500, use_container_width=True)
             
             elif site_var1 == 'Fanduel':
-                FD_seed = init_FD_seed_frame()
-                FD_seed_parse = FD_seed[FD_seed['Team'].isin(team_var2)]
-                FD_seed_parse = FD_seed_parse[FD_seed_parse['Team_count'].isin(stack_var2)]
-                data_export_display = FD_seed_parse.head(1000)
+                
+                working_seed = init_FD_seed_frame()
+                working_seed_parse = working_seed[np.isin(working_seed[:, 2], team_var2)]
+                working_seed_parse = working_seed[np.isin(working_seed[:, 3], stack_var2)]
+                data_export_display = working_seed_parse[0:1000]
                 st.session_state.data_export_display = data_export_display.copy()
-                st.session_state.data_export = FD_seed.copy()
-                st.session_state.data_export_freq = pd.DataFrame(np.column_stack(np.unique(st.session_state.data_export.iloc[:,0:8].values, return_counts=True)),
-                                            columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
-                st.session_state.data_export_freq['Freq'] = st.session_state.data_export_freq['Freq'].astype(int)
-                st.session_state.data_export_freq['Exposure'] = st.session_state.data_export_freq['Freq']/(len(st.session_state.data_export_expo['Team']))
+                st.session_state.data_export = working_seed.copy()
+                st.session_state.data_export_freq = calculate_value_frequencies(my_array)
                 
                 if 'data_export' in st.session_state:
                         st.download_button(