Refactor contest data processing in app.py for improved clarity and functionality

- Streamlined the initialization of projections and contest data in session state, ensuring name matching occurs only once during the initial load.
- Enhanced the calculation logic for salary, median, and ownership metrics by utilizing a working copy of the contest dataframe, improving data handling.
- Updated pagination controls to reflect changes in the working dataframe, ensuring accurate navigation and display of contest data.

app.py

@@ -75,9 +75,8 @@ with tab1:
             if 'projections_df' not in st.session_state:
                 st.session_state['projections_df'] = projections.copy()
                 st.session_state['projections_df']['salary'] = (st.session_state['projections_df']['salary'].astype(str).str.replace(',', '').astype(float).astype(int))
-            
-            # Update projections_df with any new matches
-            st.session_state['contest_df'], st.session_state['projections_df'] = find_name_mismatches(st.session_state['Contest'], st.session_state['projections_df'])
+                # Run name matching only once when first loading the files
+                st.session_state['contest_df'], st.session_state['projections_df'] = find_name_mismatches(st.session_state['Contest'], st.session_state['projections_df'])
 
 with tab2:
     if st.button('Clear data', key='reset3'):
@@ -92,82 +91,79 @@ with tab2:
                 entry_names = st.multiselect("Select players", options=st.session_state['entry_list'], default=[])
                 submitted = st.form_submit_button("Submit")
 
-
+        # Create mapping dictionaries
         map_dict = {
-            'pos_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['position'])),
-            'team_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['team'])),
-            'salary_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['salary'])),
-            'proj_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['median'])),
-            'own_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['ownership'])),
-            'own_percent_rank':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['ownership'].rank(pct=True))),
-            'cpt_salary_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['salary'])),
-            'cpt_proj_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['median'] * 1.5)),
-            'cpt_own_map':dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['captain ownership']))
+            'pos_map': dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['position'])),
+            'team_map': dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['team'])),
+            'salary_map': dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['salary'])),
+            'proj_map': dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['median'])),
+            'own_map': dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['ownership'])),
+            'own_percent_rank': dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['ownership'].rank(pct=True))),
+            'cpt_salary_map': dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['salary'])),
+            'cpt_proj_map': dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['median'] * 1.5)),
+            'cpt_own_map': dict(zip(st.session_state['projections_df']['player_names'], st.session_state['projections_df']['captain ownership']))
         }
-        
-        if entry_parse_var == 'Specific':
-            st.session_state['contest_df'] = st.session_state['contest_df'][st.session_state['contest_df']['BaseName'].isin(entry_names)]
-        else:
-            st.session_state['contest_df'] = st.session_state['contest_df']
-        
+
+        # Create a copy of the dataframe for calculations
+        working_df = st.session_state['contest_df'].copy()
+
+        # Apply filters if submitted
+        if submitted and entry_parse_var == 'Specific':
+            working_df = working_df[working_df['BaseName'].isin(entry_names)]
+
+        # Calculate metrics based on game type
         if type_var == 'Classic':
-            st.session_state['contest_df']['salary'] = st.session_state['contest_df'].apply(lambda row: sum(map_dict['salary_map'].get(player, 0) for player in row), axis=1)
-            st.session_state['contest_df']['median'] = st.session_state['contest_df'].apply(lambda row: sum(map_dict['proj_map'].get(player, 0) for player in row), axis=1)
-            st.session_state['contest_df']['Own'] = st.session_state['contest_df'].apply(lambda row: sum(map_dict['own_map'].get(player, 0) for player in row), axis=1)
+            working_df['salary'] = working_df.apply(lambda row: sum(map_dict['salary_map'].get(player, 0) for player in row), axis=1)
+            working_df['median'] = working_df.apply(lambda row: sum(map_dict['proj_map'].get(player, 0) for player in row), axis=1)
+            working_df['Own'] = working_df.apply(lambda row: sum(map_dict['own_map'].get(player, 0) for player in row), axis=1)
         elif type_var == 'Showdown':
-            # Calculate salary (CPT uses cpt_salary_map, others use salary_map)
-            st.session_state['contest_df']['salary'] = st.session_state['contest_df'].apply(
+            working_df['salary'] = working_df.apply(
                 lambda row: map_dict['cpt_salary_map'].get(row.iloc[0], 0) + 
                           sum(map_dict['salary_map'].get(player, 0) for player in row.iloc[1:]),
                 axis=1
             )
-            
-            # Calculate median (CPT uses cpt_proj_map, others use proj_map)
-            st.session_state['contest_df']['median'] = st.session_state['contest_df'].apply(
+            working_df['median'] = working_df.apply(
                 lambda row: map_dict['cpt_proj_map'].get(row.iloc[0], 0) + 
                           sum(map_dict['proj_map'].get(player, 0) for player in row.iloc[1:]),
                 axis=1
             )
-            
-            # Calculate ownership (CPT uses cpt_own_map, others use own_map)
-            st.session_state['contest_df']['Own'] = st.session_state['contest_df'].apply(
+            working_df['Own'] = working_df.apply(
                 lambda row: map_dict['cpt_own_map'].get(row.iloc[0], 0) + 
                           sum(map_dict['own_map'].get(player, 0) for player in row.iloc[1:]),
                 axis=1
             )
 
-        with col2:
-            
-            # Initialize pagination in session state if not exists
-            if 'current_page' not in st.session_state:
-                st.session_state.current_page = 0
-            
-            # Calculate total pages
-            rows_per_page = 500
-            total_rows = len(st.session_state['contest_df'])
-            total_pages = (total_rows + rows_per_page - 1) // rows_per_page
-            
-            # Create pagination controls in a single row
-            pagination_cols = st.columns([4, 1, 1, 1, 4])  # Last column for spacing
-            with pagination_cols[1]:
-                if st.button("← Previous", disabled=st.session_state.current_page == 0):
-                    st.session_state.current_page -= 1
-            with pagination_cols[2]:
-                st.markdown(f"**Page {st.session_state.current_page + 1} of {total_pages}**", unsafe_allow_html=True)
-            with pagination_cols[3]:
-                if st.button("Next →", disabled=st.session_state.current_page == total_pages - 1):
-                    st.session_state.current_page += 1
-            
-            # Calculate start and end indices for current page
-            start_idx = st.session_state.current_page * rows_per_page
-            end_idx = min((st.session_state.current_page + 1) * rows_per_page, total_rows)
-            
-            # Display the paginated dataframe
-            st.dataframe(
-                st.session_state['contest_df'].iloc[start_idx:end_idx].style
-                .background_gradient(axis=0)
-                .background_gradient(cmap='RdYlGn')
-                .format(precision=2), 
-                height=1000,
-                use_container_width=True
-            )
+        # Initialize pagination in session state if not exists
+        if 'current_page' not in st.session_state:
+            st.session_state.current_page = 0
+
+        # Calculate total pages
+        rows_per_page = 500
+        total_rows = len(working_df)
+        total_pages = (total_rows + rows_per_page - 1) // rows_per_page
+
+        # Create pagination controls in a single row
+        pagination_cols = st.columns([4, 1, 1, 1, 4])
+        with pagination_cols[1]:
+            if st.button("← Previous", disabled=st.session_state.current_page == 0):
+                st.session_state.current_page -= 1
+        with pagination_cols[2]:
+            st.markdown(f"**Page {st.session_state.current_page + 1} of {total_pages}**", unsafe_allow_html=True)
+        with pagination_cols[3]:
+            if st.button("Next →", disabled=st.session_state.current_page == total_pages - 1):
+                st.session_state.current_page += 1
+
+        # Calculate start and end indices for current page
+        start_idx = st.session_state.current_page * rows_per_page
+        end_idx = min((st.session_state.current_page + 1) * rows_per_page, total_rows)
+
+        # Display the paginated dataframe
+        st.dataframe(
+            working_df.iloc[start_idx:end_idx].style
+            .background_gradient(axis=0)
+            .background_gradient(cmap='RdYlGn')
+            .format(precision=2), 
+            height=1000,
+            use_container_width=True,
+            hide_index=True
+        )