Update app.py

app.py

@@ -30,14 +30,14 @@ def init_conn():
         cursor = collection.find()
     
         raw_display = pd.DataFrame(list(cursor))
-        raw_display = raw_display[['salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']]
+        raw_display = raw_display[['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count']]
         DK_seed = raw_display.to_numpy()
 
         collection = db["FD_MLB_seed_frame"] 
         cursor = collection.find()
     
         raw_display = pd.DataFrame(list(cursor))
-        raw_display = raw_display[['salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']]
+        raw_display = raw_display[['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count']]
         FD_seed = raw_display.to_numpy()
         
         MLB_Data = 'https://docs.google.com/spreadsheets/d/1f42Ergav8K1VsOLOK9MUn7DM_MLMvv4GR2Fy7EfnZTc/edit#gid=340831852'
@@ -51,8 +51,8 @@ def init_conn():
 gcservice_account, client, db, DK_seed, FD_seed, MLB_Data = init_conn()
 
 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']]
+dk_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count']
+fd_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count']
 
 @st.cache_data(ttl = 60)
 def init_baselines():
@@ -78,12 +78,19 @@ def convert_df(array):
     return array.to_csv().encode('utf-8')
 
 @st.cache_data
-def calculate_value_frequencies(np_array):
-    unique, counts = np.unique(np_array, return_counts=True)
+def calculate_DK_value_frequencies(np_array):
+    unique, counts = np.unique(np_array[:9], return_counts=True)
     frequencies = counts / len(np_array)  # Normalize by the number of rows 
     combined_array = np.column_stack((unique, frequencies))  
     return combined_array 
 
+@st.cache_data
+def calculate_FD_value_frequencies(np_array):
+    unique, counts = np.unique(np_array[:8], 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'])
@@ -134,20 +141,20 @@ with tab1:
         if site_var1 == 'Draftkings':
             
             st.session_state.working_seed = DK_seed.copy()
-            st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 2], team_var2)]
-            st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 3], stack_var2)]
+            st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 12], team_var2)]
+            st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 13], stack_var2)]
             st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:1000], columns=column_names)
             
-            # st.session_state.data_export_freq = calculate_value_frequencies(st.session_state.data_export)
+            st.session_state.data_export_freq = calculate_DK_value_frequencies(st.session_state.working_seed)
             
         elif site_var1 == 'Fanduel':
             
             st.session_state.working_seed = FD_seed.copy()
-            st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 2], team_var2)]
-            st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 3], stack_var2)]
+            st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 11], team_var2)]
+            st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 12], stack_var2)]
             st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:1000], columns=column_names)
             
-            # st.session_state.data_export_freq = calculate_value_frequencies(st.session_state.data_export)
+            st.session_state.data_export_freq = calculate_FD_value_frequencies(st.session_state.working_seed)
             
         with st.container():
             if 'data_export_display' in st.session_state:
@@ -157,14 +164,13 @@ with tab1:
                 st.dataframe(st.session_state.data_export_freq.style.format(percentages_format, precision=2), height=500, use_container_width=True)
         
         if st.button("Prepare data export", key='data_export'):
-            st.session_state.data_export = st.session_state.working_seed.copy()
-            if 'data_export' in st.session_state:
-                    st.download_button(
-                        label="Export optimals set",
-                        data=convert_df(st.session_state.data_export),
-                        file_name='MLB_optimals_export.csv',
-                        mime='text/csv',
-                    )
+            data_export = st.session_state.working_seed.copy()
+            st.download_button(
+                label="Export optimals set",
+                data=convert_df(st.session_state.data_export),
+                file_name='MLB_optimals_export.csv',
+                mime='text/csv',
+            )
             
 with tab2:
     col1, col2 = st.columns([1, 7])