TPC-H Q9 — Product Type Profit Measure

TPC-H benchmark · all TPC-H queries

Profit on a given line of parts

Representative SQL

Rendered for DataFusion with default parameters.

SELECT
  nation,
  o_year,
  SUM(amount) AS sum_profit
FROM (
  SELECT
    n_name AS nation,
    EXTRACT(YEAR FROM o_orderdate) AS o_year,
    l_extendedprice * (
      1 - l_discount
    ) - ps_supplycost * l_quantity AS amount
  FROM part, supplier, lineitem, partsupp, orders, nation
  WHERE
    s_suppkey = l_suppkey
    AND ps_suppkey = l_suppkey
    AND ps_partkey = l_partkey
    AND p_partkey = l_partkey
    AND o_orderkey = l_orderkey
    AND s_nationkey = n_nationkey
    AND p_name LIKE '%green%'
) AS profit
GROUP BY
  nation,
  o_year
ORDER BY
  nation,
  o_year DESC

Representative DataFrame

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

def q9_expression_impl(ctx: DataFrameContext) -> Any:
    part = ctx.get_table("part")
    supplier = ctx.get_table("supplier")
    lineitem = ctx.get_table("lineitem")
    partsupp = ctx.get_table("partsupp")
    orders = ctx.get_table("orders")
    nation = ctx.get_table("nation")
    col = ctx.col
    lit = ctx.lit

    params = get_tpch_parameters(9)
    color = params["color"]

    return (
        part.filter(col("p_name").str.contains(color))
        .join(lineitem, left_on="p_partkey", right_on="l_partkey")
        .join(supplier, left_on="l_suppkey", right_on="s_suppkey")
        .join(
            partsupp,
            left_on=["l_suppkey", "p_partkey"],
            right_on=["ps_suppkey", "ps_partkey"],
        )
        .join(orders, left_on="l_orderkey", right_on="o_orderkey")
        .join(nation, left_on="s_nationkey", right_on="n_nationkey")
        .with_columns(
            col("o_orderdate").dt.year().alias("o_year"),
            (col("l_extendedprice") * (lit(1) - col("l_discount")) - col("ps_supplycost") * col("l_quantity")).alias(
                "amount"
            ),
        )
        .group_by(col("n_name").alias("nation"), "o_year")
        .agg(col("amount").sum().alias("sum_profit"))
        .sort(["nation", "o_year"], descending=[False, True])
    )

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 TPCH

bench = TPCH(scale_factor=0.01)            # your scale factor
queries = bench.get_queries(dialect="datafusion")   # your platform's dialect; drop dialect= for native SQL
print(queries['9'])

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

print(bench.get_query(9, 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', '9', family="expression").source)  # or family="pandas"

Source

Query text: benchbox/_binaries/tpc-h/templates/queries/9.sql