Implement user selection and pagination for duplication frame in app.py

- Added a form for users to select specific usage(s) to view in the duplication frame, enhancing user interactivity.
- Implemented pagination controls to navigate through the duplication frame, improving data accessibility and usability.
- Updated the duplication frame to reflect user selections and maintain clarity in data presentation.

app.py

@@ -442,13 +442,54 @@ with tab2:
                     st.dataframe(st.session_state['general_frame'].style.background_gradient(cmap='RdYlGn', axis=1).format(precision=2), hide_index=True)
 
             with tab5:
+                with st.form(key='dupe_form'):
+                    col1, col2 = st.columns(2)
+                    with col1:
+                        user_dupe_var = st.selectbox("Which usage(s) would you like to view?",  ['All', 'Specific'], key='user_dupe_var')
+                    with col2:
+                        user_dupe_select = st.multiselect("Select your user(s)", working_df['BaseName'].sort_values().unique(), key='user_dupe_select')
+                    submitted = st.form_submit_button("Submit")
+                    if submitted:
+                        if user_dupe_var == 'Specific':
+                            user_dupe_select = user_dupe_select
+                        else:
+                            user_dupe_select = None
+                
                 dupe_frame = working_df[['BaseName', 'EntryCount', 'dupes', 'uniques', 'under_5', 'under_10']]
                 dupe_frame['average_dupes'] = dupe_frame['dupes'].mean()
                 dupe_frame['uniques%'] = dupe_frame['uniques'] / dupe_frame['EntryCount']
                 dupe_frame['under_5%'] = dupe_frame['under_5'] / dupe_frame['EntryCount']
                 dupe_frame['under_10%'] = dupe_frame['under_10'] / dupe_frame['EntryCount']
-                st.session_state['duplication_frame'] = dupe_frame[['BaseName', 'EntryCount', 'average_dupes', 'dupes', 'uniques', 'uniques%', 'under_5', 'under_5%', 'under_10', 'under_10%']].drop_duplicates(subset='BaseName', keep='first')
-                st.dataframe(st.session_state['duplication_frame'].style.
+                dupe_frame = dupe_frame[['BaseName', 'EntryCount', 'average_dupes', 'uniques', 'uniques%', 'under_5', 'under_5%', 'under_10', 'under_10%']].drop_duplicates(subset='BaseName', keep='first')
+                st.session_state['duplication_frame'] = dupe_frame.sort_values(by='EntryCount', ascending=False)
+                if user_dupe_var == 'Specific':
+                    st.session_state['duplication_frame'] = st.session_state['duplication_frame'][st.session_state['duplication_frame']['BaseName'].isin(user_dupe_select)]
+                
+                # Initialize pagination in session state if not exists
+                if 'dupe_page' not in st.session_state:
+                    st.session_state.dupe_page = 1
+
+                # Calculate total pages
+                rows_per_page = 50
+                total_rows = len(st.session_state['duplication_frame'])
+                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(f"Previous Page"):
+                        if st.session_state['dupe_page'] > 1:
+                            st.session_state.dupe_page -= 1
+
+                with pagination_cols[3]:
+                    if st.button(f"Next Page"):
+                        st.session_state.dupe_page += 1
+
+                # Calculate start and end indices for current page
+                start_dupe_idx = (st.session_state.dupe_page - 1) * rows_per_page
+                end_dupe_idx = min((st.session_state.dupe_page) * rows_per_page, total_rows)
+
+                st.dataframe(st.session_state['duplication_frame'].iloc[start_dupe_idx:end_dupe_idx].style.
                              background_gradient(cmap='RdYlGn', subset=['uniques%', 'under_5%', 'under_10%'], axis=0).
-                             background_gradient(cmap='RdYlGn_r', subset=['uniques', 'under_5', 'under_10'], axis=0).
+                             background_gradient(cmap='RdYlGn', subset=['uniques', 'under_5', 'under_10'], axis=0).
                              format(dupe_format, precision=2), hide_index=True)