rds cost analysis by instance id

import pandas as pd from datetime import datetime, timedelta, timezone # Assuming df is your DataFrame and last_n_days is defined # Example: last_n_days = 30 if df is not None: print("DataFrame Columns:", list(df.columns)) # Convert 'lineItem/UsageStartDate' to datetime df['lineItem/UsageStartDate'] = pd.to_datetime(df['lineItem/UsageStartDate']) # Filter out negative costs df = df[df['lineItem/UnblendedCost'] >= 0] # Filter rows for the last N days for RDS cutoff_date = datetime.utcnow().replace(tzinfo=timezone.utc) - timedelta(days=last_n_days) rds_df = df[(df['lineItem/UsageStartDate'] > cutoff_date) & (df['lineItem/ProductCode'] == 'AmazonRDS') & (df['lineItem/ResourceId'].notna())] if not rds_df.empty: # Group by 'lineItem/UsageStartDate' and 'lineItem/ResourceId' rds_result = rds_df.groupby([rds_df['lineItem/UsageStartDate'].dt.date, 'lineItem/ResourceId']).agg( usage_hours=('lineItem/UsageAmount', 'sum'), usage_cost=('lineItem/UnblendedCost', 'sum') ).reset_index() print("Number of rows in result DataFrame:", len(rds_result)) # Plotting the RDS cost data by instance ID context.plot.xlabel = 'Date' context.plot.ylabel = 'RDS Usage Cost($)' context.plot.title = f'RDS Cost by Instance ID (Last {last_n_days} Days)' for instance_id in rds_result['lineItem/ResourceId'].unique(): instance_data = rds_result[rds_result['lineItem/ResourceId'] == instance_id] x = instance_data['lineItem/UsageStartDate'].tolist() y = instance_data['usage_cost'].tolist() context.plot.add_trace(name=f"RDS Instance - {instance_id}", xpts=x, ypts=y, tracetype="line") else: print("No RDS data available for the specified time frame.") else: print("DataFrame is empty. Exiting.")