Create analytics_data_processing.py

analytics_data_processing.py

@@ -0,0 +1,93 @@
+import pandas as pd
+from datetime import datetime, timedelta
+import logging
+
+# Configure logging for this module
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(module)s - %(message)s')
+
+def filter_dataframe_by_date(df, date_column, start_date, end_date):
+    """Filters a DataFrame by a date column within a given date range."""
+    if df is None or df.empty or not date_column:
+        logging.warning(f"Filter by date: DataFrame is None, empty, or no date_column provided. DF: {df is not None}, empty: {df.empty if df is not None else 'N/A'}, date_column: {date_column}")
+        return pd.DataFrame()
+    if date_column not in df.columns:
+        logging.warning(f"Filter by date: Date column '{date_column}' not found in DataFrame columns: {df.columns.tolist()}.")
+        return pd.DataFrame()
+    
+    df_copy = df.copy() # Work on a copy to avoid SettingWithCopyWarning
+    try:
+        if not pd.api.types.is_datetime64_any_dtype(df_copy[date_column]):
+            df_copy[date_column] = pd.to_datetime(df_copy[date_column], errors='coerce')
+    except Exception as e:
+        logging.error(f"Error converting date column '{date_column}' to datetime: {e}")
+        return pd.DataFrame() # Return empty if conversion fails
+
+    df_filtered = df_copy.dropna(subset=[date_column])
+    if df_filtered.empty:
+        logging.info(f"Filter by date: DataFrame became empty after dropping NaNs in date column '{date_column}'.")
+        return pd.DataFrame()
+
+    # Convert start_date and end_date to datetime objects if they are not None
+    # Normalize to remove time part for consistent date comparisons if dates are just dates
+    start_dt_obj = pd.to_datetime(start_date, errors='coerce').normalize() if start_date else None
+    end_dt_obj = pd.to_datetime(end_date, errors='coerce').normalize() if end_date else None
+
+
+    if start_dt_obj and end_dt_obj:
+        # Ensure the DataFrame's date column is also normalized if it contains time
+        df_filtered[date_column] = df_filtered[date_column].dt.normalize()
+        return df_filtered[(df_filtered[date_column] >= start_dt_obj) & (df_filtered[date_column] <= end_dt_obj)]
+    elif start_dt_obj:
+        df_filtered[date_column] = df_filtered[date_column].dt.normalize()
+        return df_filtered[df_filtered[date_column] >= start_dt_obj]
+    elif end_dt_obj:
+        df_filtered[date_column] = df_filtered[date_column].dt.normalize()
+        return df_filtered[df_filtered[date_column] <= end_dt_obj]
+    return df_filtered # No date filtering if neither start_date nor end_date is provided
+
+
+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 and mentions.
+    Returns filtered_posts_df, filtered_mentions_df, follower_stats_df (unfiltered),
+    and the determined start_dt, end_dt for messaging.
+    """
+    logging.info(f"Preparing filtered analytics data. Filter: {date_filter_option}, Custom Start: {custom_start_date}, Custom End: {custom_end_date}")
+
+    posts_df = token_state_value.get("bubble_posts_df", pd.DataFrame())
+    mentions_df = token_state_value.get("bubble_mentions_df", pd.DataFrame())
+    follower_stats_df = token_state_value.get("bubble_follower_stats_df", pd.DataFrame()) 
+
+    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")
+
+    # Determine date range for filtering posts and mentions
+    # Ensure end_dt is also normalized if it's datetime.now() for consistent comparison with normalized dates
+    current_time_normalized = datetime.now().normalize()
+    end_dt_filter = current_time_normalized 
+    start_dt_filter = None
+
+    if date_filter_option == "Last 7 Days":
+        start_dt_filter = current_time_normalized - timedelta(days=6) # Inclusive of start day
+    elif date_filter_option == "Last 30 Days":
+        start_dt_filter = current_time_normalized - timedelta(days=29) # Inclusive of start day
+    elif date_filter_option == "Custom Range":
+        start_dt_filter = pd.to_datetime(custom_start_date, errors='coerce').normalize() if custom_start_date else None
+        # If custom_end_date is not provided, use current_time_normalized for end_dt_filter
+        end_dt_filter = pd.to_datetime(custom_end_date, errors='coerce').normalize() if custom_end_date else current_time_normalized
+    # "All Time" means start_dt_filter remains None, end_dt_filter effectively means up to now or unbounded if None
+
+    logging.info(f"Date range for filtering: Start: {start_dt_filter}, End: {end_dt_filter}")
+
+    # Filter DataFrames
+    filtered_posts_data = pd.DataFrame()
+    if not posts_df.empty:
+        filtered_posts_data = filter_dataframe_by_date(posts_df, date_column_posts, start_dt_filter, end_dt_filter)
+    
+    filtered_mentions_data = pd.DataFrame()
+    if not mentions_df.empty:
+        filtered_mentions_data = filter_dataframe_by_date(mentions_df, date_column_mentions, start_dt_filter, end_dt_filter)
+
+    logging.info(f"Processed - Filtered posts: {len(filtered_posts_data)} rows, Filtered Mentions: {len(filtered_mentions_data)} rows.")
+    
+    return filtered_posts_data, filtered_mentions_data, follower_stats_df, start_dt_filter, end_dt_filter