Update data_processing/analytics_data_processing.py

data_processing/analytics_data_processing.py

@@ -62,7 +62,6 @@ def filter_dataframe_by_date(df, date_column, start_date, end_date):
     
     return df_filtered_final
 
-
 def prepare_filtered_analytics_data(token_state_value, date_filter_option, custom_start_date, custom_end_date):
     """
     Retrieves data from token_state, determines date range, filters posts, mentions, and follower time-series data.
@@ -80,11 +79,10 @@ def prepare_filtered_analytics_data(token_state_value, date_filter_option, custo
     posts_df = token_state_value.get("bubble_posts_df", pd.DataFrame()).copy()
     mentions_df = token_state_value.get("bubble_mentions_df", pd.DataFrame()).copy()
     follower_stats_df = token_state_value.get("bubble_follower_stats_df", pd.DataFrame()).copy()
-    post_stats_df = token_state_value.get("bubble_post_stats_df", pd.DataFrame()).copy() # Fetch post_stats_df
+    post_stats_df = token_state_value.get("bubble_post_stats_df", pd.DataFrame()).copy()
 
     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")
-    # Assuming follower_stats_df has a 'date' column for time-series data
     date_column_followers = token_state_value.get("config_date_col_followers", "date") 
 
     # Determine date range for filtering
@@ -94,47 +92,48 @@ def prepare_filtered_analytics_data(token_state_value, date_filter_option, custo
     end_dt_filter = current_time_normalized 
     start_dt_filter = None
 
-    if date_filter_option == "Last 7 Days":
+    # --- FIX STARTS HERE ---
+    # The filter option strings from the UI must exactly match the strings being checked here.
+    # The original code checked for "Last 7 Days" but the UI sent "Ultimi 7 Giorni".
+    if date_filter_option == "Ultimi 7 Giorni":
         start_dt_filter = current_time_normalized - timedelta(days=6) 
-    elif date_filter_option == "Last 30 Days":
+    elif date_filter_option == "Ultimi 30 Giorni":
         start_dt_filter = current_time_normalized - timedelta(days=29) 
-    elif date_filter_option == "Custom Range":
+    elif date_filter_option == "Intervallo Personalizzato":
         start_dt_filter_temp = pd.to_datetime(custom_start_date, errors='coerce')
         start_dt_filter = start_dt_filter_temp.replace(hour=0, minute=0, second=0, microsecond=0) if pd.notna(start_dt_filter_temp) else None 
         
         end_dt_filter_temp = pd.to_datetime(custom_end_date, errors='coerce')
+        # If end date is specified, use it. Otherwise, default to today.
         end_dt_filter = end_dt_filter_temp.replace(hour=0, minute=0, second=0, microsecond=0) if pd.notna(end_dt_filter_temp) else current_time_normalized
+    # --- FIX ENDS HERE ---
     
     logging.info(f"Date range for filtering: Start: {start_dt_filter}, End: {end_dt_filter}")
 
     # Merge posts_df and post_stats_df
     merged_posts_df = pd.DataFrame()
     if not posts_df.empty and not post_stats_df.empty:
-        # Assuming posts_df has 'id' and post_stats_df has 'post_id' for merging
         if 'id' in posts_df.columns and 'post_id' in post_stats_df.columns:
             merged_posts_df = pd.merge(posts_df, post_stats_df, left_on='id', right_on='post_id', how='left')
             logging.info(f"Merged posts_df ({len(posts_df)} rows) and post_stats_df ({len(post_stats_df)} rows) into merged_posts_df ({len(merged_posts_df)} rows).")
         else:
             logging.warning("Cannot merge posts_df and post_stats_df due to missing 'id' or 'post_id' columns.")
-            # Fallback to using posts_df if merge fails but provide an empty df for stats-dependent plots
-            merged_posts_df = posts_df # Or handle as an error / empty DF for those plots
+            merged_posts_df = posts_df
     elif not posts_df.empty:
-        logging.warning("post_stats_df is empty. Proceeding with posts_df only for plots that don't require stats.")
-        merged_posts_df = posts_df # Create necessary columns with NaN if they are expected by plots
-        # For columns expected from post_stats_df, add them with NaNs if not present
+        logging.warning("post_stats_df is empty. Proceeding with posts_df only.")
+        merged_posts_df = posts_df
         expected_stat_cols = ['engagement', 'impressionCount', 'clickCount', 'likeCount', 'commentCount', 'shareCount']
         for col in expected_stat_cols:
             if col not in merged_posts_df.columns:
                 merged_posts_df[col] = pd.NA
 
-
     # Filter DataFrames by date
     filtered_merged_posts_data = pd.DataFrame()
     if not merged_posts_df.empty and date_column_posts in merged_posts_df.columns:
         filtered_merged_posts_data = filter_dataframe_by_date(merged_posts_df, date_column_posts, start_dt_filter, end_dt_filter)
     elif not merged_posts_df.empty:
         logging.warning(f"Date column '{date_column_posts}' not found in merged_posts_df. Returning unfiltered merged posts data.")
-        filtered_merged_posts_data = merged_posts_df # Or apply other logic
+        filtered_merged_posts_data = merged_posts_df
     
     filtered_mentions_data = pd.DataFrame()
     if not mentions_df.empty and date_column_mentions in mentions_df.columns:
@@ -144,14 +143,13 @@ def prepare_filtered_analytics_data(token_state_value, date_filter_option, custo
         filtered_mentions_data = mentions_df
 
     date_filtered_follower_stats_df = pd.DataFrame()
-    raw_follower_stats_df = follower_stats_df.copy() # For demographic plots, use raw (or latest snapshot logic)
+    raw_follower_stats_df = follower_stats_df.copy()
 
     if not follower_stats_df.empty and date_column_followers in follower_stats_df.columns:
         date_filtered_follower_stats_df = filter_dataframe_by_date(follower_stats_df, date_column_followers, start_dt_filter, end_dt_filter)
     elif not follower_stats_df.empty:
         logging.warning(f"Date column '{date_column_followers}' not found in follower_stats_df. Time-series follower plots might be empty or use unfiltered data.")
-        # Decide if date_filtered_follower_stats_df should be raw_follower_stats_df or empty
-        date_filtered_follower_stats_df = follower_stats_df # Or pd.DataFrame() if strict filtering is required
+        date_filtered_follower_stats_df = follower_stats_df
 
     logging.info(f"Processed - Filtered Merged Posts: {len(filtered_merged_posts_data)} rows, Filtered Mentions: {len(filtered_mentions_data)} rows, Date-Filtered Follower Stats: {len(date_filtered_follower_stats_df)} rows.")