Update app.py

app.py

@@ -442,69 +442,142 @@ if st.session_state.results:
 
     if selected_user:
         user_df = df[df['user_id'] == selected_user]
-        user_gini_info = user_metrics_df[user_metrics_df['user_id'] == selected_user].iloc[0]
+        # user_gini_info = user_metrics_df[user_metrics_df['user_id'] == selected_user].iloc[0]
         
-        # Display the top-level metrics for the user first
-        c1, c2 = st.columns(2)
-        with c1: st.metric("Total Posts by User", len(user_df))
-        with c2: st.metric("Topic Diversity (Gini)", f"{user_gini_info['gini_coefficient']:.3f}", help=interpret_gini(user_gini_info['gini_coefficient']))
+        # # Display the top-level metrics for the user first
+        # c1, c2 = st.columns(2)
+        # with c1: st.metric("Total Posts by User", len(user_df))
+        # with c2: st.metric("Topic Diversity (Gini)", f"{user_gini_info['gini_coefficient']:.3f}", help=interpret_gini(user_gini_info['gini_coefficient']))
         
-        st.markdown("---") # Add a visual separator
+        # st.markdown("---") # Add a visual separator
 
-        # --- START: New Two-Column Layout for Charts ---
-        col1, col2 = st.columns(2)
+        # # --- START: New Two-Column Layout for Charts ---
+        # col1, col2 = st.columns(2)
 
-        with col1:
-            # --- Chart 1: Topic Distribution Pie Chart ---
-            user_topic_counts = user_df['topic_id'].value_counts().reset_index()
-            user_topic_counts.columns = ['topic_id', 'count']
+        # with col1:
+        #     # --- Chart 1: Topic Distribution Pie Chart ---
+        #     user_topic_counts = user_df['topic_id'].value_counts().reset_index()
+        #     user_topic_counts.columns = ['topic_id', 'count']
             
-            fig_pie = px.pie(
-                user_topic_counts[user_topic_counts.topic_id != -1], 
-                names='topic_id', 
-                values='count', 
-                title=f"Overall Topic Distribution for {selected_user}", 
-                hole=0.4
-            )
-            fig_pie.update_layout(margin=dict(l=0, r=0, t=40, b=0))
-            st.plotly_chart(fig_pie, use_container_width=True)
-
-        with col2:
-            # --- Chart 2: Topic Evolution for User ---
-            if len(user_df) > 1:
-                user_evo_df = user_df[user_df['topic_id'] != -1].copy()
-                user_evo_df['timestamp'] = pd.to_datetime(user_evo_df['timestamp'])
-
-                if not user_evo_df.empty and user_evo_df['timestamp'].nunique() > 1:
-                    user_pivot = user_evo_df.pivot_table(index='timestamp', columns='topic_id', aggfunc='size', fill_value=0)
+        #     fig_pie = px.pie(
+        #         user_topic_counts[user_topic_counts.topic_id != -1], 
+        #         names='topic_id', 
+        #         values='count', 
+        #         title=f"Overall Topic Distribution for {selected_user}", 
+        #         hole=0.4
+        #     )
+        #     fig_pie.update_layout(margin=dict(l=0, r=0, t=40, b=0))
+        #     st.plotly_chart(fig_pie, use_container_width=True)
+
+        # with col2:
+        #     # --- Chart 2: Topic Evolution for User ---
+        #     if len(user_df) > 1:
+        #         user_evo_df = user_df[user_df['topic_id'] != -1].copy()
+        #         user_evo_df['timestamp'] = pd.to_datetime(user_evo_df['timestamp'])
+
+        #         if not user_evo_df.empty and user_evo_df['timestamp'].nunique() > 1:
+        #             user_pivot = user_evo_df.pivot_table(index='timestamp', columns='topic_id', aggfunc='size', fill_value=0)
                     
-                    time_delta = user_pivot.index.max() - user_pivot.index.min()
-                    if time_delta.days > 30: resample_freq = 'D'
-                    elif time_delta.days > 2: resample_freq = 'H'
-                    else: resample_freq = 'T'
+        #             time_delta = user_pivot.index.max() - user_pivot.index.min()
+        #             if time_delta.days > 30: resample_freq = 'D'
+        #             elif time_delta.days > 2: resample_freq = 'H'
+        #             else: resample_freq = 'T'
                     
-                    user_resampled = user_pivot.resample(resample_freq).sum()
-                    row_sums = user_resampled.sum(axis=1)
-                    user_proportions = user_resampled.div(row_sums, axis=0).fillna(0)
+        #             user_resampled = user_pivot.resample(resample_freq).sum()
+        #             row_sums = user_resampled.sum(axis=1)
+        #             user_proportions = user_resampled.div(row_sums, axis=0).fillna(0)
 
-                    topic_name_map = topic_info.set_index('Topic')['Name'].to_dict()
-                    user_proportions.rename(columns=topic_name_map, inplace=True)
+        #             topic_name_map = topic_info.set_index('Topic')['Name'].to_dict()
+        #             user_proportions.rename(columns=topic_name_map, inplace=True)
                     
-                    fig_user_evo = px.area(
-                        user_proportions,
-                        x=user_proportions.index,
-                        y=user_proportions.columns,
-                        title=f"Topic Proportion Over Time for {selected_user}",
-                        labels={'value': 'Topic Proportion', 'variable': 'Topic', 'index': 'Time'},
-                    )
-                    fig_user_evo.update_layout(margin=dict(l=0, r=0, t=40, b=0))
-                    st.plotly_chart(fig_user_evo, use_container_width=True)
+        #             fig_user_evo = px.area(
+        #                 user_proportions,
+        #                 x=user_proportions.index,
+        #                 y=user_proportions.columns,
+        #                 title=f"Topic Proportion Over Time for {selected_user}",
+        #                 labels={'value': 'Topic Proportion', 'variable': 'Topic', 'index': 'Time'},
+        #             )
+        #             fig_user_evo.update_layout(margin=dict(l=0, r=0, t=40, b=0))
+        #             st.plotly_chart(fig_user_evo, use_container_width=True)
+        #         else:
+        #             st.info("This user has no posts in meaningful topics or all posts occurred at the same time.")
+        #     else:
+        #         st.info("Topic evolution requires more than one post to display.")
+
+        # Check if this user exists in the metrics dataframe (i.e., has meaningful posts)
+        user_metrics_filtered = user_metrics_df[user_metrics_df['user_id'] == selected_user]
+    
+        # --- START OF THE FIX ---
+        if not user_metrics_filtered.empty:
+            # If the user has meaningful posts, display all metrics and charts
+            user_gini_info = user_metrics_filtered.iloc[0]
+            
+            # Display the top-level metrics for the user first
+            c1, c2 = st.columns(2)
+            with c1: st.metric("Total Posts by User", len(user_df))
+            with c2: st.metric("Topic Diversity (Gini)", f"{user_gini_info['gini_coefficient']:.3f}", help=interpret_gini(user_gini_info['gini_coefficient']))
+            
+            st.markdown("---") # Add a visual separator
+    
+            # Two-Column Layout for Charts
+            col1, col2 = st.columns(2)
+    
+            with col1:
+                # Chart 1: Topic Distribution Pie Chart
+                user_topic_counts = user_df['topic_id'].value_counts().reset_index()
+                user_topic_counts.columns = ['topic_id', 'count']
+                
+                fig_pie = px.pie(
+                    user_topic_counts[user_topic_counts.topic_id != -1], 
+                    names='topic_id', 
+                    values='count', 
+                    title=f"Overall Topic Distribution for {selected_user}", 
+                    hole=0.4
+                )
+                fig_pie.update_layout(margin=dict(l=0, r=0, t=40, b=0))
+                st.plotly_chart(fig_pie, use_container_width=True)
+    
+            with col2:
+                # Chart 2: Topic Evolution for User
+                if len(user_df) > 1:
+                    user_evo_df = user_df[user_df['topic_id'] != -1].copy()
+                    user_evo_df['timestamp'] = pd.to_datetime(user_evo_df['timestamp'])
+    
+                    if not user_evo_df.empty and user_evo_df['timestamp'].nunique() > 1:
+                        user_pivot = user_evo_df.pivot_table(index='timestamp', columns='topic_id', aggfunc='size', fill_value=0)
+                        
+                        time_delta = user_pivot.index.max() - user_pivot.index.min()
+                        if time_delta.days > 30: resample_freq = 'D'
+                        elif time_delta.days > 2: resample_freq = 'H'
+                        else: resample_freq = 'T'
+                        
+                        user_resampled = user_pivot.resample(resample_freq).sum()
+                        row_sums = user_resampled.sum(axis=1)
+                        user_proportions = user_resampled.div(row_sums, axis=0).fillna(0)
+    
+                        topic_name_map = topic_info.set_index('Topic')['Name'].to_dict()
+                        user_proportions.rename(columns=topic_name_map, inplace=True)
+                        
+                        fig_user_evo = px.area(
+                            user_proportions,
+                            x=user_proportions.index,
+                            y=user_proportions.columns,
+                            title=f"Topic Proportion Over Time for {selected_user}",
+                            labels={'value': 'Topic Proportion', 'variable': 'Topic', 'index': 'Time'},
+                        )
+                        fig_user_evo.update_layout(margin=dict(l=0, r=0, t=40, b=0))
+                        st.plotly_chart(fig_user_evo, use_container_width=True)
+                    else:
+                        st.info("This user has no posts in meaningful topics or all posts occurred at the same time.")
                 else:
-                    st.info("This user has no posts in meaningful topics or all posts occurred at the same time.")
-            else:
-                st.info("Topic evolution requires more than one post to display.")
-
-
+                    st.info("Topic evolution requires more than one post to display.")
+        else:
+            # If the user has NO meaningful posts, show a simplified view
+            st.metric("Total Posts by User", len(user_df))
+            st.warning(f"**{selected_user}** has no posts in any of the identified topics. Their posts may be outliers.")
+        # --- END OF THE FIX ---
+        
+        
         st.markdown("#### User's Most Recent Posts")
         user_posts_table = user_df[['post_content', 'timestamp', 'topic_id']] \
             .sort_values(by='timestamp', ascending=False) \