Update app.py

app.py

@@ -26,7 +26,6 @@ from analytics_data_processing import prepare_filtered_analytics_data
 from analytics_plot_generator import (
     generate_posts_activity_plot, generate_engagement_type_plot,
     generate_mentions_activity_plot, generate_mention_sentiment_plot,
-    # generate_total_follower_growth_plot, # Kept for reference, decide if needed
     generate_followers_count_over_time_plot,
     generate_followers_growth_rate_plot,
     generate_followers_by_demographics_plot,
@@ -49,20 +48,17 @@ def update_analytics_plots(token_state_value, date_filter_option, custom_start_d
     if not token_state_value or not token_state_value.get("token"):
         message = "❌ Access denied. No token. Cannot generate analytics."
         logging.warning(message)
-        # Return placeholders for all plots
-        num_expected_plots = 13 # Number of plots we expect to generate
+        num_expected_plots = 13 
         placeholder_figs = [create_placeholder_plot(title="Access Denied", message="No token.") for _ in range(num_expected_plots)]
         return [message] + placeholder_figs
 
-    # --- Prepare Data ---
     try:
-        # Updated unpacking to match prepare_filtered_analytics_data return signature
         (filtered_merged_posts_df, 
          filtered_mentions_df, 
          date_filtered_follower_stats_df, 
          raw_follower_stats_df, 
          start_dt_for_msg, end_dt_for_msg) = \
-            prepare_filtered_analytics_data( # Direct call to imported function
+            prepare_filtered_analytics_data(
                 token_state_value, date_filter_option, custom_start_date, custom_end_date
             )
     except Exception as e:
@@ -72,47 +68,43 @@ def update_analytics_plots(token_state_value, date_filter_option, custom_start_d
         placeholder_figs = [create_placeholder_plot(title="Data Preparation Error", message=str(e)) for _ in range(num_expected_plots)]
         return [error_msg] + placeholder_figs
 
-    # Date column names (still needed for plot generators if not passed as args or if defaults are not suitable)
     date_column_posts = token_state_value.get("config_date_col_posts", "published_at")
     date_column_mentions = token_state_value.get("config_date_col_mentions", "date")
-    date_column_followers = token_state_value.get("config_date_col_followers", "date") 
+    # This 'date_column_followers' from token_state is for the *source* DataFrame's date column,
+    # but the plot generator now uses 'date_info_column' for the 'category_name' that holds date strings.
+    # We'll use the default 'category_name' in the plot functions directly.
+    # config_date_col_followers_source = token_state_value.get("config_date_col_followers", "date") 
+
 
     logging.info(f"Data for plotting - Filtered Merged Posts: {len(filtered_merged_posts_df)} rows, Filtered Mentions: {len(filtered_mentions_df)} rows.")
     logging.info(f"Date-Filtered Follower Stats: {len(date_filtered_follower_stats_df)} rows, Raw Follower Stats: {len(raw_follower_stats_df)} rows.")
 
-    # --- Generate Plots ---
     try:
-        # Existing plots (using filtered_merged_posts_df for post-related plots)
         plot_posts_activity = generate_posts_activity_plot(filtered_merged_posts_df, date_column=date_column_posts)
-        # Ensure likeCount, commentCount, shareCount are in filtered_merged_posts_df
         plot_engagement_type = generate_engagement_type_plot(filtered_merged_posts_df) 
         plot_mentions_activity = generate_mentions_activity_plot(filtered_mentions_df, date_column=date_column_mentions)
         plot_mention_sentiment = generate_mention_sentiment_plot(filtered_mentions_df) 
 
-        # New Follower Dynamics Plots
+        # Corrected calls for follower plots: use date_info_column (defaults to 'category_name' in plot generator)
         plot_followers_count = generate_followers_count_over_time_plot(
             date_filtered_follower_stats_df, 
-            date_column=date_column_followers, # Make sure 'date' is the correct column name
-            count_column='follower_count_o', # Or relevant count column
-            type_filter_column='follower_count_type',
-            type_value='follower_gains_monthly' # As per your requirement
+            # date_info_column is defaulted in the function to 'category_name'
+            # organic_count_col, paid_count_col are defaulted
+            type_filter_column='follower_count_type', # Ensure this column exists
+            type_value='follower_gains_monthly' 
         )
         plot_followers_growth_rate = generate_followers_growth_rate_plot(
             date_filtered_follower_stats_df,
-            date_column=date_column_followers,
-            count_column='follower_count_o',
+            # date_info_column is defaulted
             type_filter_column='follower_count_type',
             type_value='follower_gains_monthly'
         )
 
-        # New Follower Demographics Plots (using raw_follower_stats_df)
-        plot_followers_by_location = generate_followers_by_demographics_plot(raw_follower_stats_df, category_col='category_name', count_column='follower_count_o', type_filter_column='follower_count_type', type_value='follower_geo', plot_title="Followers by Location")
-        plot_followers_by_role = generate_followers_by_demographics_plot(raw_follower_stats_df, category_col='category_name', count_column='follower_count_o', type_filter_column='follower_count_type', type_value='follower_function', plot_title="Followers by Role")
-        plot_followers_by_industry = generate_followers_by_demographics_plot(raw_follower_stats_df, category_col='category_name', count_column='follower_count_o', type_filter_column='follower_count_type', type_value='follower_industry', plot_title="Followers by Industry")
-        plot_followers_by_seniority = generate_followers_by_demographics_plot(raw_follower_stats_df, category_col='category_name', count_column='follower_count_o', type_filter_column='follower_count_type', type_value='follower_seniority', plot_title="Followers by Seniority")
+        plot_followers_by_location = generate_followers_by_demographics_plot(raw_follower_stats_df, category_col='category_name', type_filter_column='follower_count_type', type_value='follower_geo', plot_title="Followers by Location")
+        plot_followers_by_role = generate_followers_by_demographics_plot(raw_follower_stats_df, category_col='category_name', type_filter_column='follower_count_type', type_value='follower_function', plot_title="Followers by Role")
+        plot_followers_by_industry = generate_followers_by_demographics_plot(raw_follower_stats_df, category_col='category_name', type_filter_column='follower_count_type', type_value='follower_industry', plot_title="Followers by Industry")
+        plot_followers_by_seniority = generate_followers_by_demographics_plot(raw_follower_stats_df, category_col='category_name', type_filter_column='follower_count_type', type_value='follower_seniority', plot_title="Followers by Seniority")
 
-        # New Post Engagement/Performance Plots (using filtered_merged_posts_df)
-        # Ensure 'engagement', 'clickCount', 'impressionCount' are in filtered_merged_posts_df
         plot_engagement_rate = generate_engagement_rate_over_time_plot(filtered_merged_posts_df, date_column=date_column_posts, engagement_rate_col='engagement')
         plot_reach_over_time = generate_reach_over_time_plot(filtered_merged_posts_df, date_column=date_column_posts, reach_col='clickCount')
         plot_impressions_over_time = generate_impressions_over_time_plot(filtered_merged_posts_df, date_column=date_column_posts, impressions_col='impressionCount')
@@ -129,7 +121,7 @@ def update_analytics_plots(token_state_value, date_filter_option, custom_start_d
             plot_followers_by_location, plot_followers_by_role, plot_followers_by_industry, plot_followers_by_seniority,
             plot_engagement_rate, plot_reach_over_time, plot_impressions_over_time
         ]
-        num_plots_generated = sum(1 for p in all_generated_plots if p is not None and not isinstance(p, str)) # Check it's a figure
+        num_plots_generated = sum(1 for p in all_generated_plots if p is not None and not isinstance(p, str)) 
         logging.info(f"Successfully generated {num_plots_generated} plots.")
 
         return [message] + all_generated_plots
@@ -148,14 +140,14 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue", secondary_hue="sky"),
     token_state = gr.State(value={
         "token": None, "client_id": None, "org_urn": None,
         "bubble_posts_df": pd.DataFrame(), 
-        "bubble_post_stats_df": pd.DataFrame(), # Added for merged post data
+        "bubble_post_stats_df": pd.DataFrame(), 
         "bubble_mentions_df": pd.DataFrame(),
         "bubble_follower_stats_df": pd.DataFrame(),
-        "fetch_count_for_api": 0, # Retained from original if used elsewhere
+        "fetch_count_for_api": 0, 
         "url_user_token_temp_storage": None,
         "config_date_col_posts": "published_at", 
         "config_date_col_mentions": "date",     
-        "config_date_col_followers": "date"    
+        "config_date_col_followers": "date" # This is for the original follower data's date column, if different from category_name for time series
     })
 
     gr.Markdown("# 🚀 LinkedIn Organization Dashboard")
@@ -168,7 +160,7 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue", secondary_hue="sky"),
     def initial_load_sequence(url_token, org_urn_val, current_state):
         logging.info(f"Initial load sequence triggered. Org URN: {org_urn_val}, URL Token: {'Present' if url_token else 'Absent'}")
         status_msg, new_state, btn_update = process_and_store_bubble_token(url_token, org_urn_val, current_state)
-        dashboard_content = display_main_dashboard(new_state) # Assumes this function exists and works
+        dashboard_content = display_main_dashboard(new_state) 
         return status_msg, new_state, btn_update, dashboard_content
 
     with gr.Tabs() as tabs:
@@ -254,13 +246,12 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue", secondary_hue="sky"),
                 followers_by_seniority_plot = gr.Plot(label="Followers by Seniority")
 
             gr.Markdown("### Post Performance Insights (Filtered by Date)")
-            with gr.Row(): # Single plot, can take full width or be in a row
+            with gr.Row(): 
                 engagement_rate_plot = gr.Plot(label="Engagement Rate Over Time")
             with gr.Row():
                 reach_over_time_plot = gr.Plot(label="Reach Over Time (Clicks)")
                 impressions_over_time_plot = gr.Plot(label="Impressions Over Time")
 
-            # Define all plot outputs for the analytics tab
             analytics_plot_outputs = [
                 analytics_status_md, posts_activity_plot, engagement_type_plot, 
                 mentions_activity_plot, mention_sentiment_plot,
@@ -277,8 +268,7 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue", secondary_hue="sky"),
                 show_progress="full"
             )
             
-            # Also update analytics plots after a data sync
-            sync_click_event.then( # Chaining after the sync operations
+            sync_click_event.then( 
                 fn=update_analytics_plots,
                 inputs=[token_state, date_filter_selector, custom_start_date_picker, custom_end_date_picker],
                 outputs=analytics_plot_outputs,
@@ -291,7 +281,7 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue", secondary_hue="sky"),
             mentions_sentiment_dist_plot = gr.Plot(label="Mention Sentiment Distribution") 
             refresh_mentions_display_btn.click(
                 fn=run_mentions_tab_display, inputs=[token_state],
-                outputs=[mentions_html, mentions_sentiment_dist_plot], # Assuming run_mentions_tab_display returns these
+                outputs=[mentions_html, mentions_sentiment_dist_plot], 
                 show_progress="full"
             )
 
@@ -306,7 +296,7 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue", secondary_hue="sky"),
 
             refresh_follower_stats_btn.click(
                 fn=run_follower_stats_tab_display, inputs=[token_state],
-                outputs=[follower_stats_html, fs_plot_monthly_gains, fs_plot_seniority, fs_plot_industry], # Assuming this matches
+                outputs=[follower_stats_html, fs_plot_monthly_gains, fs_plot_seniority, fs_plot_industry], 
                 show_progress="full"
             )