Update app.py

app.py

@@ -33,12 +33,16 @@ from analytics_plot_generator import (
     generate_reach_over_time_plot,
     generate_impressions_over_time_plot,
     create_placeholder_plot, # For initializing plots
-    # --- Import new plot functions ---
+    # --- Import existing new plot functions ---
     generate_likes_over_time_plot,
-    generate_clicks_over_time_plot,
+    generate_clicks_over_time_plot, # Note: can be same as reach
     generate_shares_over_time_plot,
     generate_comments_over_time_plot,
-    generate_comments_sentiment_breakdown_plot
+    generate_comments_sentiment_breakdown_plot,
+    # --- Import NEW plot functions for Content Strategy ---
+    generate_post_frequency_plot,
+    generate_content_format_breakdown_plot,
+    generate_content_topic_breakdown_plot
 )
 
 # Configure logging
@@ -52,7 +56,11 @@ def update_analytics_plots(token_state_value, date_filter_option, custom_start_d
     logging.info(f"Updating analytics plots. Filter: {date_filter_option}, Custom Start: {custom_start_date}, Custom End: {custom_end_date}")
 
     # --- Increased number of expected plots ---
-    num_expected_plots = 18 # Was 13, added 5 new plots
+    # Original 13 + 5 engagement = 18
+    # New Content Strategy (3: freq, format, topics)
+    # New Mention Analysis (2: volume, sentiment - these reuse existing plot objects but are new UI slots)
+    # Total = 18 + 3 + 2 = 23
+    num_expected_plots = 23 
 
     if not token_state_value or not token_state_value.get("token"):
         message = "❌ Access denied. No token. Cannot generate analytics."
@@ -61,8 +69,9 @@ def update_analytics_plots(token_state_value, date_filter_option, custom_start_d
         return [message] + placeholder_figs
 
     try:
-        # prepare_filtered_analytics_data might need to be updated if new DFs are required for new plots (e.g. comment sentiment)
-        # For now, we assume it returns the same set of DFs and new plots will try to use them or handle missing data.
+        # prepare_filtered_analytics_data might need to be updated if new DFs are required for new plots
+        # (e.g. if 'media_type' or 'eb_labels' are not in 'bubble_posts_df' and need special handling)
+        # For now, we assume 'filtered_merged_posts_df' contains these columns.
         (filtered_merged_posts_df, 
          filtered_mentions_df, 
          date_filtered_follower_stats_df, 
@@ -72,12 +81,14 @@ def update_analytics_plots(token_state_value, date_filter_option, custom_start_d
                 token_state_value, date_filter_option, custom_start_date, custom_end_date
             )
         
-        # Hypothetical: If prepare_filtered_analytics_data was updated to return comment sentiment data:
-        # filtered_comments_with_sentiment_df = ... # (This would be the 7th item in the tuple)
-        # For now, we will pass filtered_merged_posts_df to generate_comments_sentiment_breakdown_plot,
-        # and that function will handle missing sentiment columns by showing a placeholder.
-        # Or, if you have comment sentiment data in another DataFrame in token_state, retrieve it here.
-        # e.g., comments_df_with_sentiment = token_state_value.get("bubble_comments_sentiment_df", pd.DataFrame())
+        # Ensure 'media_type' and 'eb_labels' exist in filtered_merged_posts_df for new plots,
+        # or handle their absence gracefully in the plot functions themselves (which they do).
+        # Example: Add dummy columns if they might be missing, for robust testing:
+        # if 'media_type' not in filtered_merged_posts_df.columns:
+        # filtered_merged_posts_df['media_type'] = 'Unknown'
+        # if 'eb_labels' not in filtered_merged_posts_df.columns:
+        # filtered_merged_posts_df['eb_labels'] = None
+
 
     except Exception as e:
         error_msg = f"❌ Error preparing analytics data: {e}"
@@ -89,16 +100,17 @@ def update_analytics_plots(token_state_value, date_filter_option, custom_start_d
     date_column_mentions = token_state_value.get("config_date_col_mentions", "date")
     # 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.")
 
     try:
-        # Existing plots
+        # Existing plots (13)
         plot_posts_activity = generate_posts_activity_plot(filtered_merged_posts_df, date_column=date_column_posts)
         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) 
+        
+        # These two will be used for the new "Mention Analysis" section as well
+        fig_mentions_activity_shared = generate_mentions_activity_plot(filtered_mentions_df, date_column=date_column_mentions)
+        fig_mention_sentiment_shared = generate_mention_sentiment_plot(filtered_mentions_df) 
 
         plot_followers_count = generate_followers_count_over_time_plot(
             date_filtered_follower_stats_df, 
@@ -120,23 +132,28 @@ def update_analytics_plots(token_state_value, date_filter_option, custom_start_d
         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')
 
-        # --- Generate new plots ---
+        # Additional Engagement plots (5)
         plot_likes_over_time = generate_likes_over_time_plot(filtered_merged_posts_df, date_column=date_column_posts, likes_col='likeCount')
         plot_clicks_over_time = generate_clicks_over_time_plot(filtered_merged_posts_df, date_column=date_column_posts, clicks_col='clickCount')
         plot_shares_over_time = generate_shares_over_time_plot(filtered_merged_posts_df, date_column=date_column_posts, shares_col='shareCount')
         plot_comments_over_time = generate_comments_over_time_plot(filtered_merged_posts_df, date_column=date_column_posts, comments_col='commentCount')
         
-        # For comment sentiment, pass a DataFrame that is expected to have comment-level sentiment.
-        # If `filtered_merged_posts_df` is passed and lacks 'comment_sentiment' column, the plot function will show a placeholder.
-        # If you have a specific df for this, e.g., `filtered_comments_with_sentiment_df` from `prepare_filtered_analytics_data` (if modified)
-        # or from `token_state_value.get("bubble_comments_sentiment_df")`, use that one.
-        # For this example, we assume `filtered_merged_posts_df` is passed and the plot function handles it.
+        # Assuming 'comment_sentiment' column might exist, or 'sentiment' as fallback (handled in plot function)
         plot_comments_sentiment_breakdown = generate_comments_sentiment_breakdown_plot(
-            filtered_merged_posts_df, # Or your specific df with comment sentiments
-            sentiment_column='sentiment' # Assuming 'sentiment' column in post_df might be a proxy, or change to 'comment_sentiment' if that column exists
-                                         # The plot function will show a placeholder if this column isn't suitable or found.
+            filtered_merged_posts_df, 
+            sentiment_column='comment_sentiment' 
         )
 
+        # --- Generate NEW plots for Content Strategy (3) ---
+        # Assuming 'media_type' and 'eb_labels' are in filtered_merged_posts_df
+        # The plot functions themselves have fallbacks/placeholders if columns are missing.
+        media_type_col_name = token_state_value.get("config_media_type_col", "media_type") # Example if configurable
+        eb_labels_col_name = token_state_value.get("config_eb_labels_col", "eb_labels") # Example if configurable
+
+        plot_post_frequency = generate_post_frequency_plot(filtered_merged_posts_df, date_column=date_column_posts)
+        plot_content_format_breakdown = generate_content_format_breakdown_plot(filtered_merged_posts_df, format_col=media_type_col_name)
+        plot_content_topic_breakdown = generate_content_topic_breakdown_plot(filtered_merged_posts_df, topics_col=eb_labels_col_name)
+
 
         message = f"📊 Analytics updated for period: {date_filter_option}"
         if date_filter_option == "Custom Range":
@@ -145,36 +162,45 @@ def update_analytics_plots(token_state_value, date_filter_option, custom_start_d
             message += f" (From: {s_display} To: {e_display})"
         
         all_generated_plots = [
-            plot_posts_activity, plot_engagement_type, plot_mentions_activity, plot_mention_sentiment,
+            plot_posts_activity, plot_engagement_type, 
+            fig_mentions_activity_shared, fig_mention_sentiment_shared, # Original mention plots
             plot_followers_count, plot_followers_growth_rate,
             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,
-            # --- Add new plot objects to the list ---
+            # Add new engagement plot objects to the list
             plot_likes_over_time, plot_clicks_over_time,
             plot_shares_over_time, plot_comments_over_time,
-            plot_comments_sentiment_breakdown
+            plot_comments_sentiment_breakdown,
+            # --- Add NEW Content Strategy plot objects ---
+            plot_post_frequency, plot_content_format_breakdown, plot_content_topic_breakdown,
+            # --- Add plots for the NEW "Mention Analysis" section (reusing figures) ---
+            fig_mentions_activity_shared, # Reused figure for new UI slot
+            fig_mention_sentiment_shared  # Reused figure for new UI slot
         ]
         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 out of {num_expected_plots} expected.")
+        logging.info(f"Successfully generated {num_plots_generated} plot figures for {num_expected_plots} UI slots.")
         
         # Ensure the number of returned plots matches num_expected_plots, padding with placeholders if necessary
-        # This is crucial if some plot functions might return None on error and we need to match the Gradio outputs list length
         final_plots_list = []
-        for p in all_generated_plots:
-            if p is not None and not isinstance(p, str): # isinstance check for safety, though plots should be figs
-                final_plots_list.append(p)
-            else: # If a plot failed and returned None or an error string (which it shouldn't, should be placeholder fig)
-                logging.warning(f"A plot generation failed or returned unexpected type, using placeholder. Plot: {p}")
-                final_plots_list.append(create_placeholder_plot(title="Plot Error", message="Failed to generate this plot."))
+        for i, p in enumerate(all_generated_plots): # Iterate up to the expected number of plots
+            if i < num_expected_plots: # Ensure we don't exceed the expected number of outputs
+                if p is not None and not isinstance(p, str): # isinstance check for safety
+                    final_plots_list.append(p)
+                else: 
+                    logging.warning(f"A plot generation failed or returned unexpected type for slot {i}, using placeholder. Plot: {p}")
+                    final_plots_list.append(create_placeholder_plot(title="Plot Error", message="Failed to generate this plot."))
+            else:
+                logging.warning(f"Generated more plot figures ({len(all_generated_plots)}) than expected UI slots ({num_expected_plots}). Truncating.")
+                break
+
 
         # If fewer plots were generated than expected (e.g. due to early exit or major error in a plot function)
         while len(final_plots_list) < num_expected_plots:
             logging.warning(f"Padding missing plot with placeholder. Expected {num_expected_plots}, got {len(final_plots_list)} so far.")
             final_plots_list.append(create_placeholder_plot(title="Missing Plot", message="Plot could not be generated."))
             if len(final_plots_list) > num_expected_plots + 5: # Safety break
-                 logging.error("Too many placeholders added, breaking loop.")
-                 break
-
+                logging.error("Too many placeholders added, breaking loop.")
+                break
 
         return [message] + final_plots_list[:num_expected_plots] # Ensure correct number of outputs
 
@@ -196,11 +222,15 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue", secondary_hue="sky"),
         "bubble_mentions_df": pd.DataFrame(),
         "bubble_follower_stats_df": pd.DataFrame(),
         # Consider adding "bubble_comments_sentiment_df": pd.DataFrame() if you plan to fetch this data
+        # Add keys for new data if needed by prepare_filtered_analytics_data, e.g.
+        # "bubble_posts_with_content_details_df": pd.DataFrame(), 
         "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",
+        "config_media_type_col": "media_type", # For new plot
+        "config_eb_labels_col": "eb_labels"    # For new plot
     })
 
     gr.Markdown("# 🚀 LinkedIn Organization Dashboard")
@@ -280,10 +310,11 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue", secondary_hue="sky"),
                 posts_activity_plot = gr.Plot(label="Posts Activity Over Time")
                 engagement_type_plot = gr.Plot(label="Post Engagement Types")
             
+            # Original Mentions Overview - these plots will also be used for the "Mention Analysis" section below
             gr.Markdown("### Mentions Overview (Filtered by Date)")
             with gr.Row():
-                mentions_activity_plot = gr.Plot(label="Mentions Activity Over Time")
-                mention_sentiment_plot = gr.Plot(label="Mention Sentiment Distribution")
+                mentions_activity_plot = gr.Plot(label="Mentions Activity Over Time") # Will be updated by fig_mentions_activity_shared
+                mention_sentiment_plot = gr.Plot(label="Mention Sentiment Distribution") # Will be updated by fig_mention_sentiment_shared
 
             gr.Markdown("### Follower Dynamics")
             with gr.Row():
@@ -301,35 +332,57 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue", secondary_hue="sky"),
             gr.Markdown("### Post Performance Insights (Filtered by Date)")
             with gr.Row(): 
                 engagement_rate_plot = gr.Plot(label="Engagement Rate Over Time")
-                reach_over_time_plot = gr.Plot(label="Reach Over Time (Clicks)") # This was originally in its own row
-            with gr.Row(): # Moved impressions to be paired with reach if desired, or keep separate
+                reach_over_time_plot = gr.Plot(label="Reach Over Time (Clicks)")
+            with gr.Row(): 
                 impressions_over_time_plot = gr.Plot(label="Impressions Over Time")
-                # New plots will start here, keeping 2 per row
                 likes_over_time_plot = gr.Plot(label="Reactions (Likes) Over Time")
 
             gr.Markdown("### Detailed Post Engagement Over Time (Filtered by Date)")
             with gr.Row():
-                clicks_over_time_plot = gr.Plot(label="Clicks Over Time")
+                clicks_over_time_plot = gr.Plot(label="Clicks Over Time") # Can be same as reach
                 shares_over_time_plot = gr.Plot(label="Shares Over Time")
             with gr.Row():
                 comments_over_time_plot = gr.Plot(label="Comments Over Time")
-                # For the 5th new plot, "Breakdown of Comments by Sentiment"
-                # It will be alone in this row, or you can add another plot next to it later.
                 comments_sentiment_plot = gr.Plot(label="Breakdown of Comments by Sentiment")
 
+            # --- NEW: Content Strategy Analysis ---
+            gr.Markdown("### 📊 Content Strategy Analysis (Filtered by Date)")
+            with gr.Row():
+                post_frequency_cs_plot = gr.Plot(label="Post Frequency") # New plot component
+                content_format_breakdown_cs_plot = gr.Plot(label="Breakdown of Content by Format") # New
+            with gr.Row():
+                content_topic_breakdown_cs_plot = gr.Plot(label="Breakdown of Content by Topics") # New (might need more width)
+                # You can add another plot here or make the topic plot wider if needed, e.g. by itself in a row.
+                # For now, placing it here. If it's too cramped:
+                # content_topic_breakdown_cs_plot = gr.Plot(label="Breakdown of Content by Topics", elem_id="topic_plot_wide") # and use CSS for width if needed
+
+            # --- NEW: Mention Analysis (reusing plots from above) ---
+            gr.Markdown("### 💬 Mention Analysis (Filtered by Date)")
+            with gr.Row():
+                mention_analysis_volume_plot = gr.Plot(label="Mentions Volume Over Time") # New UI slot, uses fig_mentions_activity_shared
+                mention_analysis_sentiment_plot = gr.Plot(label="Breakdown of Mentions by Sentiment") # New UI slot, uses fig_mention_sentiment_shared
+            
 
             analytics_plot_outputs = [
-                analytics_status_md, posts_activity_plot, engagement_type_plot, 
-                mentions_activity_plot, mention_sentiment_plot,
+                analytics_status_md, 
+                posts_activity_plot, engagement_type_plot, 
+                mentions_activity_plot, mention_sentiment_plot, # Original mention plots
                 followers_count_plot, followers_growth_rate_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_plot,
-                # --- Add new plot components to the output list in the correct order ---
+                # Add new engagement plot components to the output list
                 likes_over_time_plot, clicks_over_time_plot,
                 shares_over_time_plot, comments_over_time_plot,
-                comments_sentiment_plot
+                comments_sentiment_plot,
+                # --- Add NEW Content Strategy plot components ---
+                post_frequency_cs_plot, content_format_breakdown_cs_plot, content_topic_breakdown_cs_plot,
+                # --- Add NEW Mention Analysis plot components (these will receive the reused figures) ---
+                mention_analysis_volume_plot, mention_analysis_sentiment_plot
             ]
+            # Expected length: 1 (status) + 13 (original plots) + 5 (new engagement) + 3 (content strategy) + 2 (mention analysis) = 24
+            # The update_analytics_plots function returns message + 23 plots. So len(analytics_plot_outputs) should be 24.
+            # Current count: 1 + 2 + 2 + 2 + 4 + 3 + 5 + 3 + 2 = 24. Correct.
 
             apply_filter_btn.click(
                 fn=update_analytics_plots,