import pandas as pd from datetime import datetime, timedelta, time import logging import numpy as np # 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: # Ensure the date column is pandas datetime objects 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') # Drop rows where date conversion might have failed (NaT) or was originally NaT df_copy.dropna(subset=[date_column], inplace=True) if df_copy.empty: logging.info(f"Filter by date: DataFrame empty after to_datetime and dropna for column '{date_column}'.") return pd.DataFrame() # Normalize to midnight. This preserves timezone information if present. df_copy[date_column] = df_copy[date_column].dt.normalize() # If the column is timezone-aware, convert its values to naive UTC equivalent. # This allows comparison with naive filter dates. if hasattr(df_copy[date_column].dt, 'tz') and df_copy[date_column].dt.tz is not None: logging.info(f"Column '{date_column}' is timezone-aware ({df_copy[date_column].dt.tz}). Converting to naive (from UTC) for comparison.") df_copy[date_column] = df_copy[date_column].dt.tz_convert('UTC').dt.tz_localize(None) except Exception as e: logging.error(f"Error processing date column '{date_column}': {e}", exc_info=True) return pd.DataFrame() # Convert start_date and end_date (which are naive Python datetime or naive Pandas Timestamp) # to naive pandas Timestamps and normalize them. 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 # Perform the filtering # df_filtered is already df_copy which has NaNs dropped and dates processed if start_dt_obj and end_dt_obj: df_filtered_final = df_copy[(df_copy[date_column] >= start_dt_obj) & (df_copy[date_column] <= end_dt_obj)] elif start_dt_obj: df_filtered_final = df_copy[df_copy[date_column] >= start_dt_obj] elif end_dt_obj: df_filtered_final = df_copy[df_copy[date_column] <= end_dt_obj] else: df_filtered_final = df_copy # No date filtering if neither start_date nor end_date is provided if df_filtered_final.empty: logging.info(f"Filter by date: DataFrame became empty after applying date range to column '{date_column}'.") 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. Merges posts with post stats. Returns: - filtered_merged_posts_df: Posts merged with stats, filtered by date. - filtered_mentions_df: Mentions filtered by date. - date_filtered_follower_stats_df: Follower stats filtered by date (for time-series plots). - raw_follower_stats_df: Unfiltered follower stats (for demographic plots). - start_dt_filter: Determined start date for filtering. - end_dt_filter: Determined end date for filtering. """ 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()).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 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 current_datetime_obj = datetime.now() current_time_normalized = current_datetime_obj.replace(hour=0, minute=0, second=0, microsecond=0) 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) elif date_filter_option == "Last 30 Days": start_dt_filter = current_time_normalized - timedelta(days=29) elif date_filter_option == "Custom Range": 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') 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 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 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 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_mentions_data = pd.DataFrame() if not mentions_df.empty and date_column_mentions in mentions_df.columns: filtered_mentions_data = filter_dataframe_by_date(mentions_df, date_column_mentions, start_dt_filter, end_dt_filter) elif not mentions_df.empty: logging.warning(f"Date column '{date_column_mentions}' not found in mentions_df. Returning unfiltered mentions data.") 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) 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 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.") return filtered_merged_posts_data, filtered_mentions_data, date_filtered_follower_stats_df, raw_follower_stats_df, start_dt_filter, end_dt_filter # --- Helper function to generate textual data summaries for chatbot --- def generate_chatbot_data_summaries( plot_configs_list, filtered_merged_posts_df, filtered_mentions_df, date_filtered_follower_stats_df, # Expected to contain 'follower_gains_monthly' raw_follower_stats_df, # Expected to contain other demographics like 'follower_geo', 'follower_industry' token_state_value ): """ Generates textual summaries for each plot ID to be used by the chatbot, based on the corrected understanding of DataFrame structures and follower count columns. """ data_summaries = {} # --- Date and Config Columns from token_state --- # For Posts date_col_posts = token_state_value.get("config_date_col_posts", "published_at") media_type_col_name = token_state_value.get("config_media_type_col", "media_type") eb_labels_col_name = token_state_value.get("config_eb_labels_col", "li_eb_label") # For Mentions date_col_mentions = token_state_value.get("config_date_col_mentions", "date") mentions_sentiment_col = "sentiment_label" # As per user's mention df structure # For Follower Stats - Actual column names provided by user follower_count_organic_col = "follower_count_organic" follower_count_paid_col = "follower_count_paid" # For Follower Stats (Demographics from raw_follower_stats_df) follower_demographics_type_col = "follower_count_type" # Column indicating 'follower_geo', 'follower_industry' follower_demographics_category_col = "category_name" # Column indicating 'USA', 'Technology' # For Follower Gains/Growth (from date_filtered_follower_stats_df) follower_gains_type_col = "follower_count_type" # Should be 'follower_gains_monthly' follower_gains_date_col = "category_name" # This is 'YYYY-MM-DD' # --- Helper: Safely convert to datetime --- def safe_to_datetime(series, errors='coerce'): return pd.to_datetime(series, errors=errors) # --- Prepare DataFrames (copy and convert dates) --- if filtered_merged_posts_df is not None and not filtered_merged_posts_df.empty: posts_df = filtered_merged_posts_df.copy() if date_col_posts in posts_df.columns: posts_df[date_col_posts] = safe_to_datetime(posts_df[date_col_posts]) else: logging.warning(f"Date column '{date_col_posts}' not found in posts_df for chatbot summary.") else: posts_df = pd.DataFrame() if filtered_mentions_df is not None and not filtered_mentions_df.empty: mentions_df = filtered_mentions_df.copy() if date_col_mentions in mentions_df.columns: mentions_df[date_col_mentions] = safe_to_datetime(mentions_df[date_col_mentions]) else: logging.warning(f"Date column '{date_col_mentions}' not found in mentions_df for chatbot summary.") else: mentions_df = pd.DataFrame() # For date_filtered_follower_stats_df (monthly gains) if date_filtered_follower_stats_df is not None and not date_filtered_follower_stats_df.empty: follower_monthly_df = date_filtered_follower_stats_df.copy() if follower_gains_type_col in follower_monthly_df.columns: follower_monthly_df = follower_monthly_df[follower_monthly_df[follower_gains_type_col] == 'follower_gains_monthly'].copy() if follower_gains_date_col in follower_monthly_df.columns: follower_monthly_df['datetime_obj'] = safe_to_datetime(follower_monthly_df[follower_gains_date_col]) follower_monthly_df = follower_monthly_df.dropna(subset=['datetime_obj']) # Calculate total gains if follower_count_organic_col in follower_monthly_df.columns and follower_count_paid_col in follower_monthly_df.columns: follower_monthly_df[follower_count_organic_col] = pd.to_numeric(follower_monthly_df[follower_count_organic_col], errors='coerce').fillna(0) follower_monthly_df[follower_count_paid_col] = pd.to_numeric(follower_monthly_df[follower_count_paid_col], errors='coerce').fillna(0) follower_monthly_df['total_monthly_gains'] = follower_monthly_df[follower_count_organic_col] + follower_monthly_df[follower_count_paid_col] elif follower_count_organic_col in follower_monthly_df.columns: # Only organic exists follower_monthly_df[follower_count_organic_col] = pd.to_numeric(follower_monthly_df[follower_count_organic_col], errors='coerce').fillna(0) follower_monthly_df['total_monthly_gains'] = follower_monthly_df[follower_count_organic_col] elif follower_count_paid_col in follower_monthly_df.columns: # Only paid exists follower_monthly_df[follower_count_paid_col] = pd.to_numeric(follower_monthly_df[follower_count_paid_col], errors='coerce').fillna(0) follower_monthly_df['total_monthly_gains'] = follower_monthly_df[follower_count_paid_col] else: logging.warning(f"Neither '{follower_count_organic_col}' nor '{follower_count_paid_col}' found in follower_monthly_df for total gains calculation.") follower_monthly_df['total_monthly_gains'] = 0 # Avoid KeyError later else: logging.warning(f"Date column '{follower_gains_date_col}' (from category_name) not found in follower_monthly_df for chatbot summary.") if 'datetime_obj' not in follower_monthly_df.columns: follower_monthly_df['datetime_obj'] = pd.NaT if 'total_monthly_gains' not in follower_monthly_df.columns: follower_monthly_df['total_monthly_gains'] = 0 else: follower_monthly_df = pd.DataFrame(columns=[follower_gains_date_col, 'total_monthly_gains', 'datetime_obj']) if raw_follower_stats_df is not None and not raw_follower_stats_df.empty: follower_demographics_df = raw_follower_stats_df.copy() # Calculate total followers for demographics if follower_count_organic_col in follower_demographics_df.columns and follower_count_paid_col in follower_demographics_df.columns: follower_demographics_df[follower_count_organic_col] = pd.to_numeric(follower_demographics_df[follower_count_organic_col], errors='coerce').fillna(0) follower_demographics_df[follower_count_paid_col] = pd.to_numeric(follower_demographics_df[follower_count_paid_col], errors='coerce').fillna(0) follower_demographics_df['total_follower_count'] = follower_demographics_df[follower_count_organic_col] + follower_demographics_df[follower_count_paid_col] elif follower_count_organic_col in follower_demographics_df.columns: follower_demographics_df[follower_count_organic_col] = pd.to_numeric(follower_demographics_df[follower_count_organic_col], errors='coerce').fillna(0) follower_demographics_df['total_follower_count'] = follower_demographics_df[follower_count_organic_col] elif follower_count_paid_col in follower_demographics_df.columns: follower_demographics_df[follower_count_paid_col] = pd.to_numeric(follower_demographics_df[follower_count_paid_col], errors='coerce').fillna(0) follower_demographics_df['total_follower_count'] = follower_demographics_df[follower_count_paid_col] else: logging.warning(f"Neither '{follower_count_organic_col}' nor '{follower_count_paid_col}' found in follower_demographics_df for total count calculation.") if 'total_follower_count' not in follower_demographics_df.columns: follower_demographics_df['total_follower_count'] = 0 else: follower_demographics_df = pd.DataFrame() for plot_cfg in plot_configs_list: plot_id = plot_cfg["id"] plot_label = plot_cfg["label"] summary_text = f"No specific data summary available for '{plot_label}' for the selected period." try: # --- FOLLOWER STATS --- if plot_id == "followers_count": # Uses follower_monthly_df if not follower_monthly_df.empty and 'total_monthly_gains' in follower_monthly_df.columns and 'datetime_obj' in follower_monthly_df.columns and not follower_monthly_df['datetime_obj'].isnull().all(): df_summary = follower_monthly_df[['datetime_obj', 'total_monthly_gains']].copy() df_summary['datetime_obj'] = df_summary['datetime_obj'].dt.strftime('%Y-%m-%d') df_summary.rename(columns={'datetime_obj': 'Date', 'total_monthly_gains': 'Total Monthly Gains'}, inplace=True) summary_text = f"Follower Count (Total Monthly Gains):\n{df_summary.sort_values(by='Date').tail(5).to_string(index=False)}" else: summary_text = f"Follower count data (total monthly gains) is unavailable or incomplete for '{plot_label}'." elif plot_id == "followers_growth_rate": # Uses follower_monthly_df if not follower_monthly_df.empty and 'total_monthly_gains' in follower_monthly_df.columns and 'datetime_obj' in follower_monthly_df.columns and not follower_monthly_df['datetime_obj'].isnull().all(): df_calc = follower_monthly_df.sort_values(by='datetime_obj').copy() # Growth rate is calculated on the total monthly gains (which are changes, not cumulative counts) # To calculate growth rate of followers, we'd need cumulative follower count. # The plot logic also uses pct_change on the gains themselves. # If 'total_monthly_gains' represents the *change* in followers, then pct_change on this is rate of change of gains. # If it represents the *cumulative* followers at that point, then pct_change is follower growth rate. # Assuming 'total_monthly_gains' is the *change* for the month, like the plot logic. df_calc['total_monthly_gains'] = pd.to_numeric(df_calc['total_monthly_gains'], errors='coerce') if len(df_calc) >= 2: # Calculate cumulative sum to get follower count if 'total_monthly_gains' are indeed just gains # If your 'total_monthly_gains' already IS the total follower count at end of month, remove next line # For now, assuming it's GAINS, so we need cumulative for growth rate of total followers. # However, the original plot logic applies pct_change directly to 'follower_gains_monthly'. # Let's stick to pct_change on the gains/count column for consistency with plot. # If 'total_monthly_gains' is the actual follower count for that month: df_calc['growth_rate_monthly'] = df_calc['total_monthly_gains'].pct_change() * 100 df_calc['growth_rate_monthly'] = df_calc['growth_rate_monthly'].round(2) df_calc.replace([np.inf, -np.inf], np.nan, inplace=True) # Handle division by zero if a gain was 0 df_summary = df_calc[['datetime_obj', 'growth_rate_monthly']].dropna().copy() df_summary['datetime_obj'] = df_summary['datetime_obj'].dt.strftime('%Y-%m-%d') df_summary.rename(columns={'datetime_obj': 'Date', 'growth_rate_monthly': 'Growth Rate (%)'}, inplace=True) if not df_summary.empty: summary_text = f"Follower Growth Rate (Monthly % based on Total Follower Count/Gains):\n{df_summary.sort_values(by='Date').tail(5).to_string(index=False)}" else: summary_text = f"Not enough data points or valid transitions to calculate follower growth rate for '{plot_label}'." else: summary_text = f"Not enough data points (need at least 2) to calculate follower growth rate for '{plot_label}'." else: summary_text = f"Follower growth rate data (total monthly gains) is unavailable or incomplete for '{plot_label}'." elif plot_id in ["followers_by_location", "followers_by_role", "followers_by_industry", "followers_by_seniority"]: demographic_type_map = { "followers_by_location": "follower_geo", "followers_by_role": "follower_function", "followers_by_industry": "follower_industry", "followers_by_seniority": "follower_seniority" } current_demographic_type = demographic_type_map.get(plot_id) if not follower_demographics_df.empty and \ follower_demographics_type_col in follower_demographics_df.columns and \ follower_demographics_category_col in follower_demographics_df.columns and \ 'total_follower_count' in follower_demographics_df.columns: # Check for the calculated total df_filtered_demographics = follower_demographics_df[ follower_demographics_df[follower_demographics_type_col] == current_demographic_type ].copy() if not df_filtered_demographics.empty: df_summary = df_filtered_demographics.groupby(follower_demographics_category_col)['total_follower_count'].sum().reset_index() df_summary.rename(columns={follower_demographics_category_col: 'Category', 'total_follower_count': 'Total Follower Count'}, inplace=True) top_5 = df_summary.nlargest(5, 'Total Follower Count') summary_text = f"Top 5 {plot_label} (Total Followers):\n{top_5.to_string(index=False)}" else: summary_text = f"No data available for demographic type '{current_demographic_type}' in '{plot_label}'." else: summary_text = f"Follower demographic data columns (including total_follower_count) are missing or incomplete for '{plot_label}'." # --- POSTS STATS --- elif plot_id == "engagement_rate": if not posts_df.empty and 'engagement' in posts_df.columns and date_col_posts in posts_df.columns and not posts_df[date_col_posts].isnull().all(): df_resampled = posts_df.set_index(date_col_posts)['engagement'].resample('W').mean().reset_index() df_resampled['engagement'] = pd.to_numeric(df_resampled['engagement'], errors='coerce').round(2) df_summary = df_resampled[[date_col_posts, 'engagement']].dropna().copy() df_summary[date_col_posts] = df_summary[date_col_posts].dt.strftime('%Y-%m-%d') summary_text = f"Engagement Rate Over Time (Weekly Avg %):\n{df_summary.sort_values(by=date_col_posts).tail(5).to_string(index=False)}" else: summary_text = f"Engagement rate data is unavailable for '{plot_label}'." elif plot_id == "reach_over_time": if not posts_df.empty and 'reach' in posts_df.columns and date_col_posts in posts_df.columns and not posts_df[date_col_posts].isnull().all(): df_resampled = posts_df.set_index(date_col_posts)['reach'].resample('W').sum().reset_index() df_resampled['reach'] = pd.to_numeric(df_resampled['reach'], errors='coerce') df_summary = df_resampled[[date_col_posts, 'reach']].dropna().copy() df_summary[date_col_posts] = df_summary[date_col_posts].dt.strftime('%Y-%m-%d') summary_text = f"Reach Over Time (Weekly Sum):\n{df_summary.sort_values(by=date_col_posts).tail(5).to_string(index=False)}" else: summary_text = f"Reach data is unavailable for '{plot_label}'." elif plot_id == "impressions_over_time": if not posts_df.empty and 'impressionCount' in posts_df.columns and date_col_posts in posts_df.columns and not posts_df[date_col_posts].isnull().all(): df_resampled = posts_df.set_index(date_col_posts)['impressionCount'].resample('W').sum().reset_index() df_resampled['impressionCount'] = pd.to_numeric(df_resampled['impressionCount'], errors='coerce') df_summary = df_resampled[[date_col_posts, 'impressionCount']].dropna().copy() df_summary[date_col_posts] = df_summary[date_col_posts].dt.strftime('%Y-%m-%d') df_summary.rename(columns={'impressionCount': 'Impressions'}, inplace=True) summary_text = f"Impressions Over Time (Weekly Sum):\n{df_summary.sort_values(by=date_col_posts).tail(5).to_string(index=False)}" else: summary_text = f"Impressions data is unavailable for '{plot_label}'." elif plot_id == "likes_over_time": if not posts_df.empty and 'likeCount' in posts_df.columns and date_col_posts in posts_df.columns and not posts_df[date_col_posts].isnull().all(): df_resampled = posts_df.set_index(date_col_posts)['likeCount'].resample('W').sum().reset_index() df_resampled['likeCount'] = pd.to_numeric(df_resampled['likeCount'], errors='coerce') df_summary = df_resampled[[date_col_posts, 'likeCount']].dropna().copy() df_summary[date_col_posts] = df_summary[date_col_posts].dt.strftime('%Y-%m-%d') df_summary.rename(columns={'likeCount': 'Likes'}, inplace=True) summary_text = f"Likes Over Time (Weekly Sum):\n{df_summary.sort_values(by=date_col_posts).tail(5).to_string(index=False)}" else: summary_text = f"Likes data is unavailable for '{plot_label}'." elif plot_id == "clicks_over_time": if not posts_df.empty and 'clickCount' in posts_df.columns and date_col_posts in posts_df.columns and not posts_df[date_col_posts].isnull().all(): df_resampled = posts_df.set_index(date_col_posts)['clickCount'].resample('W').sum().reset_index() df_resampled['clickCount'] = pd.to_numeric(df_resampled['clickCount'], errors='coerce') df_summary = df_resampled[[date_col_posts, 'clickCount']].dropna().copy() df_summary[date_col_posts] = df_summary[date_col_posts].dt.strftime('%Y-%m-%d') df_summary.rename(columns={'clickCount': 'Clicks'}, inplace=True) summary_text = f"Clicks Over Time (Weekly Sum):\n{df_summary.sort_values(by=date_col_posts).tail(5).to_string(index=False)}" else: summary_text = f"Clicks data is unavailable for '{plot_label}'." elif plot_id == "shares_over_time": if not posts_df.empty and 'shareCount' in posts_df.columns and date_col_posts in posts_df.columns and not posts_df[date_col_posts].isnull().all(): df_resampled = posts_df.set_index(date_col_posts)['shareCount'].resample('W').sum().reset_index() df_resampled['shareCount'] = pd.to_numeric(df_resampled['shareCount'], errors='coerce') df_summary = df_resampled[[date_col_posts, 'shareCount']].dropna().copy() df_summary[date_col_posts] = df_summary[date_col_posts].dt.strftime('%Y-%m-%d') df_summary.rename(columns={'shareCount': 'Shares'}, inplace=True) summary_text = f"Shares Over Time (Weekly Sum):\n{df_summary.sort_values(by=date_col_posts).tail(5).to_string(index=False)}" elif 'shareCount' not in posts_df.columns and not posts_df.empty : # Check if posts_df is not empty before assuming column is the only issue summary_text = f"Shares data column ('shareCount') not found for '{plot_label}'." else: summary_text = f"Shares data is unavailable for '{plot_label}'." elif plot_id == "comments_over_time": if not posts_df.empty and 'commentCount' in posts_df.columns and date_col_posts in posts_df.columns and not posts_df[date_col_posts].isnull().all(): df_resampled = posts_df.set_index(date_col_posts)['commentCount'].resample('W').sum().reset_index() df_resampled['commentCount'] = pd.to_numeric(df_resampled['commentCount'], errors='coerce') df_summary = df_resampled[[date_col_posts, 'commentCount']].dropna().copy() df_summary[date_col_posts] = df_summary[date_col_posts].dt.strftime('%Y-%m-%d') df_summary.rename(columns={'commentCount': 'Comments'}, inplace=True) summary_text = f"Comments Over Time (Weekly Sum):\n{df_summary.sort_values(by=date_col_posts).tail(5).to_string(index=False)}" else: summary_text = f"Comments data is unavailable for '{plot_label}'." elif plot_id == "comments_sentiment": comment_sentiment_col_posts = "sentiment" if not posts_df.empty and comment_sentiment_col_posts in posts_df.columns: sentiment_counts = posts_df[comment_sentiment_col_posts].value_counts().reset_index() sentiment_counts.columns = ['Sentiment', 'Count'] summary_text = f"Comments Sentiment Breakdown (Posts Data):\n{sentiment_counts.to_string(index=False)}" else: summary_text = f"Comment sentiment data ('{comment_sentiment_col_posts}') is unavailable for '{plot_label}'." elif plot_id == "post_frequency_cs": if not posts_df.empty and date_col_posts in posts_df.columns and not posts_df[date_col_posts].isnull().all(): post_counts_weekly = posts_df.set_index(date_col_posts).resample('W').size().reset_index(name='post_count') post_counts_weekly.rename(columns={date_col_posts: 'Week', 'post_count': 'Posts'}, inplace=True) post_counts_weekly['Week'] = post_counts_weekly['Week'].dt.strftime('%Y-%m-%d (Week of)') summary_text = f"Post Frequency (Weekly):\n{post_counts_weekly.sort_values(by='Week').tail(5).to_string(index=False)}" else: summary_text = f"Post frequency data is unavailable for '{plot_label}'." elif plot_id == "content_format_breakdown_cs": if not posts_df.empty and media_type_col_name in posts_df.columns: format_counts = posts_df[media_type_col_name].value_counts().reset_index() format_counts.columns = ['Format', 'Count'] summary_text = f"Content Format Breakdown:\n{format_counts.nlargest(5, 'Count').to_string(index=False)}" else: summary_text = f"Content format data ('{media_type_col_name}') is unavailable for '{plot_label}'." elif plot_id == "content_topic_breakdown_cs": if not posts_df.empty and eb_labels_col_name in posts_df.columns: try: # Ensure the column is not all NaN before trying to check for lists or explode if posts_df[eb_labels_col_name].notna().any(): if posts_df[eb_labels_col_name].apply(lambda x: isinstance(x, list)).any(): topic_counts = posts_df.explode(eb_labels_col_name)[eb_labels_col_name].value_counts().reset_index() else: topic_counts = posts_df[eb_labels_col_name].value_counts().reset_index() topic_counts.columns = ['Topic', 'Count'] summary_text = f"Content Topic Breakdown (Top 5):\n{topic_counts.nlargest(5, 'Count').to_string(index=False)}" else: summary_text = f"Content topic data ('{eb_labels_col_name}') contains no valid topics for '{plot_label}'." except Exception as e_topic: logging.warning(f"Could not process topic breakdown for '{eb_labels_col_name}': {e_topic}") summary_text = f"Content topic data ('{eb_labels_col_name}') could not be processed for '{plot_label}'." else: summary_text = f"Content topic data ('{eb_labels_col_name}') is unavailable for '{plot_label}'." # --- MENTIONS STATS --- elif plot_id == "mention_analysis_volume": if not mentions_df.empty and date_col_mentions in mentions_df.columns and not mentions_df[date_col_mentions].isnull().all(): mentions_over_time = mentions_df.set_index(date_col_mentions).resample('W').size().reset_index(name='mention_count') mentions_over_time.rename(columns={date_col_mentions: 'Week', 'mention_count': 'Mentions'}, inplace=True) mentions_over_time['Week'] = mentions_over_time['Week'].dt.strftime('%Y-%m-%d (Week of)') if not mentions_over_time.empty: summary_text = f"Mentions Volume (Weekly):\n{mentions_over_time.sort_values(by='Week').tail(5).to_string(index=False)}" else: summary_text = f"No mention activity found for '{plot_label}' in the selected period." else: summary_text = f"Mentions volume data is unavailable for '{plot_label}'." elif plot_id == "mention_analysis_sentiment": if not mentions_df.empty and mentions_sentiment_col in mentions_df.columns: sentiment_counts = mentions_df[mentions_sentiment_col].value_counts().reset_index() sentiment_counts.columns = ['Sentiment', 'Count'] summary_text = f"Mentions Sentiment Breakdown:\n{sentiment_counts.to_string(index=False)}" else: summary_text = f"Mention sentiment data ('{mentions_sentiment_col}') is unavailable for '{plot_label}'." data_summaries[plot_id] = summary_text except KeyError as e: logging.warning(f"KeyError generating summary for {plot_id} ('{plot_label}'): {e}. Using default summary.") data_summaries[plot_id] = f"Data summary generation error for '{plot_label}' (missing column: {e})." except Exception as e: logging.error(f"Error generating summary for {plot_id} ('{plot_label}'): {e}", exc_info=True) data_summaries[plot_id] = f"Error generating data summary for '{plot_label}'." return data_summaries