"""Asset checks for rds_label_maker_annotations data quality.""" import dagster as dg from dagster_snowflake import SnowflakeResource from src.utils.snowflake.constants import Warehouse from src.utils.snowflake.logger import log_query from src.utils.snowflake.query import load_query @dg.asset_check( asset="rds_label_maker_annotations", description="Verify ID uniqueness in partition", blocking=False, ) def check_rds_label_maker_annotations_id_uniqueness( context: dg.AssetCheckExecutionContext, snowflake: SnowflakeResource ) -> dg.AssetCheckResult: """Check that all IDs in the partition are unique.""" logger = context.log partition_key = context.op_execution_context.partition_key partition_parts = partition_key.split("-") p_date = f"{partition_parts[0]}-{partition_parts[1]}-{partition_parts[2]}" p_hour = int(partition_parts[3].split(":")[0]) with snowflake.get_connection() as conn: cursor = conn.cursor() cursor.execute(load_query("src/utils/snowflake/queries/use_warehouse.sql", params={"warehouse": Warehouse.SUNO_PROD_RDS_HOURLY_X_SMALL.value})) query = f""" SELECT COUNT(*) as total, COUNT(DISTINCT ID) as distinct_ids, COUNT(*) - COUNT(DISTINCT ID) as dupes FROM SUNO_PROD.PROD.RDS_LABEL_MAKER_ANNOTATIONS WHERE p_date = '{p_date}' AND p_hour = {p_hour} """ result = cursor.execute(query).fetchone() total, distinct_ids, dupes = result if result else (0, 0, 0) passed = dupes == 0 return dg.AssetCheckResult( passed=passed, description=f"{'No duplicates' if passed else f'{dupes} duplicates found'}", metadata={"total_rows": total, "distinct_ids": distinct_ids, "duplicates": dupes} ) asset_checks = [ check_rds_label_maker_annotations_id_uniqueness, ] __all__ = ["asset_checks"]