TPC-DS Q34 — Store Sales County Household

TPC-DS benchmark · all TPC-DS queries

Analyzes customer purchases by county and household demographics

Representative SQL

Rendered for DataFusion with default parameters.

SELECT
  c_last_name,
  c_first_name,
  c_salutation,
  c_preferred_cust_flag,
  ss_ticket_number,
  cnt
FROM (
  SELECT
    ss_ticket_number,
    ss_customer_sk,
    COUNT(*) AS cnt
  FROM store_sales, date_dim, store, household_demographics
  WHERE
    store_sales.ss_sold_date_sk = date_dim.d_date_sk
    AND store_sales.ss_store_sk = store.s_store_sk
    AND store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk
    AND (
      date_dim.d_dom BETWEEN 1 AND 3 OR date_dim.d_dom BETWEEN 25 AND 28
    )
    AND (
      household_demographics.hd_buy_potential = '>10000'
      OR household_demographics.hd_buy_potential = 'Unknown'
    )
    AND household_demographics.hd_vehicle_count > 0
    AND (
      CASE
        WHEN household_demographics.hd_vehicle_count > 0
        THEN household_demographics.hd_dep_count / household_demographics.hd_vehicle_count
        ELSE NULL
      END
    ) > 1.2
    AND date_dim.d_year IN (1998, 1998 + 1, 1998 + 2)
    AND store.s_county IN (
      'Williamson County',
      'Williamson County',
      'Williamson County',
      'Williamson County',
      'Williamson County',
      'Williamson County',
      'Williamson County',
      'Williamson County'
    )
  GROUP BY
    ss_ticket_number,
    ss_customer_sk
) AS dn, customer
WHERE
  ss_customer_sk = c_customer_sk AND cnt BETWEEN 15 AND 20
ORDER BY
  c_last_name,
  c_first_name,
  c_salutation,
  c_preferred_cust_flag DESC,
  ss_ticket_number

Representative DataFrame

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

def q34_expression_impl(ctx: DataFrameContext) -> Any:
    params = get_parameters(34)
    year = params.get("year", 1998)
    counties = params.get(
        "counties",
        [
            "Williamson County",
            "Williamson County",
            "Williamson County",
            "Williamson County",
            "Williamson County",
            "Williamson County",
            "Williamson County",
            "Williamson County",
        ],
    )
    buy_potential_1 = params.get("buy_potential_1", ">10000")
    buy_potential_2 = params.get("buy_potential_2", "Unknown")

    store_sales, date_dim, store, household_demographics, customer = _tables(
        ctx, "store_sales", "date_dim", "store", "household_demographics", "customer"
    )
    col = ctx.col
    lit = ctx.lit

    ticket_agg = (
        store_sales.join(date_dim, left_on="ss_sold_date_sk", right_on="d_date_sk")
        .join(store, left_on="ss_store_sk", right_on="s_store_sk")
        .join(household_demographics, left_on="ss_hdemo_sk", right_on="hd_demo_sk")
        .filter(
            (
                (col("d_dom") >= lit(1)) & (col("d_dom") <= lit(3))
                | (col("d_dom") >= lit(25)) & (col("d_dom") <= lit(28))
            )
            & ((col("hd_buy_potential") == lit(buy_potential_1)) | (col("hd_buy_potential") == lit(buy_potential_2)))
            & (col("hd_vehicle_count") > lit(0))
            & ((col("hd_dep_count") / col("hd_vehicle_count")) > lit(1.2))
            & (col("d_year").is_in([year, year + 1, year + 2]))
            & col("s_county").is_in(counties)
        )
        .group_by("ss_ticket_number", "ss_customer_sk")
        .agg(col("ss_ticket_number").count().alias("cnt"))
        .filter((col("cnt") >= lit(15)) & (col("cnt") <= lit(20)))
    )

    result = ticket_agg.join(customer, left_on="ss_customer_sk", right_on="c_customer_sk").select(
        col("c_last_name"),
        col("c_first_name"),
        col("c_salutation"),
        col("c_preferred_cust_flag"),
        col("ss_ticket_number"),
        col("cnt"),
    )
    return _sort_null_largest_expression(
        ctx,
        result,
        ["c_last_name", "c_first_name", "c_salutation", "c_preferred_cust_flag", "ss_ticket_number"],
        [False, False, False, True, False],
    )

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 TPCDS

bench = TPCDS(scale_factor=1.0)            # your scale factor
queries = bench.get_queries(dialect="datafusion")   # your platform's dialect; drop dialect= for native SQL
print(queries['34'])

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

print(bench.get_query(34, scale_factor=1.0, seed=42, dialect="datafusion"))

For the DataFrame form:

from benchbox.core.query_catalog import get_dataframe_render

print(get_dataframe_render('tpcds', '34', family="expression").source)  # or family="pandas"

Source

Query text: _sources/tpc-ds/query_templates/query34.tpl