TPC-H Skew Q19 — Discounted Revenue

TPC-H Skew benchmark · all TPC-H Skew queries

Revenue for parts with specific conditions

Representative SQL

Rendered for DataFusion with default parameters.

SELECT
  SUM(l_extendedprice * (
    1 - l_discount
  )) AS revenue
FROM lineitem, part
WHERE
  (
    p_partkey = l_partkey
    AND p_brand = 'Brand#12'
    AND p_container IN ('SM CASE', 'SM BOX', 'SM PACK', 'SM PKG')
    AND l_quantity >= 1
    AND l_quantity <= 1 + 10
    AND p_size BETWEEN 1 AND 5
    AND l_shipmode IN ('AIR', 'AIR REG')
    AND l_shipinstruct = 'DELIVER IN PERSON'
  )
  OR (
    p_partkey = l_partkey
    AND p_brand = 'Brand#23'
    AND p_container IN ('MED BAG', 'MED BOX', 'MED PKG', 'MED PACK')
    AND l_quantity >= 10
    AND l_quantity <= 10 + 10
    AND p_size BETWEEN 1 AND 10
    AND l_shipmode IN ('AIR', 'AIR REG')
    AND l_shipinstruct = 'DELIVER IN PERSON'
  )
  OR (
    p_partkey = l_partkey
    AND p_brand = 'Brand#34'
    AND p_container IN ('LG CASE', 'LG BOX', 'LG PACK', 'LG PKG')
    AND l_quantity >= 20
    AND l_quantity <= 20 + 10
    AND p_size BETWEEN 1 AND 15
    AND l_shipmode IN ('AIR', 'AIR REG')
    AND l_shipinstruct = 'DELIVER IN PERSON'
  )

Representative DataFrame

Expression family (Polars, PySpark, DataFusion), default parameters.

def q19_expression_impl(ctx: DataFrameContext) -> Any:
    lineitem = ctx.get_table("lineitem")
    part = ctx.get_table("part")
    col = ctx.col
    lit = ctx.lit

    params = get_tpch_parameters(19)
    brand1 = params["brand1"]
    brand2 = params["brand2"]
    brand3 = params["brand3"]
    quantity1 = params["quantity1"]
    quantity2 = params["quantity2"]
    quantity3 = params["quantity3"]

    sm_containers = ["SM CASE", "SM BOX", "SM PACK", "SM PKG"]
    med_containers = ["MED BAG", "MED BOX", "MED PKG", "MED PACK"]
    lg_containers = ["LG CASE", "LG BOX", "LG PACK", "LG PKG"]
    ship_modes = ["AIR", "AIR REG"]

    return (
        lineitem.join(part, left_on="l_partkey", right_on="p_partkey")
        .filter(
            col("l_shipmode").is_in(ship_modes)
            & (col("l_shipinstruct") == lit("DELIVER IN PERSON"))
            & (
                (
                    (col("p_brand") == lit(brand1))
                    & col("p_container").is_in(sm_containers)
                    & (col("l_quantity") >= lit(quantity1))
                    & (col("l_quantity") <= lit(quantity1 + 10))
                    & (col("p_size") >= lit(1))
                    & (col("p_size") <= lit(5))
                )
                | (
                    (col("p_brand") == lit(brand2))
                    & col("p_container").is_in(med_containers)
                    & (col("l_quantity") >= lit(quantity2))
                    & (col("l_quantity") <= lit(quantity2 + 10))
                    & (col("p_size") >= lit(1))
                    & (col("p_size") <= lit(10))
                )
                | (
                    (col("p_brand") == lit(brand3))
                    & col("p_container").is_in(lg_containers)
                    & (col("l_quantity") >= lit(quantity3))
                    & (col("l_quantity") <= lit(quantity3 + 10))
                    & (col("p_size") >= lit(1))
                    & (col("p_size") <= lit(15))
                )
            )
        )
        .select((col("l_extendedprice") * (lit(1) - col("l_discount"))).alias("revenue"))
        .sum()
    )

Get the exact query for your run

The blocks above are representative. To get the precise statement a specific platform runs at a specific scale, substitute your own values:

from benchbox import TPCHSkew

bench = TPCHSkew(scale_factor=0.01)            # your scale factor
queries = bench.get_queries(dialect="datafusion")   # your platform's dialect; drop dialect= for native SQL
print(queries['19'])

Parameter substitution for this benchmark is seed-driven; pass a seed for a specific stream’s parameters:

print(bench.get_query(19, scale_factor=0.01, seed=42, dialect="datafusion"))

For the DataFrame form:

from benchbox.core.query_catalog import get_dataframe_render

print(get_dataframe_render('tpch_skew', '19', family="expression").source)  # or family="pandas"

Source

Query text: benchbox/_binaries/tpc-h/templates/queries/19.sql