TPC-DS Q65 — Store Sales Item Profit

TPC-DS benchmark · all TPC-DS queries

Reports store sales item revenue analysis

Representative SQL

Rendered for DataFusion with default parameters.

SELECT
  s_store_name,
  i_item_desc,
  sc.revenue,
  i_current_price,
  i_wholesale_cost,
  i_brand
FROM store, item, (
  SELECT
    ss_store_sk,
    AVG(revenue) AS ave
  FROM (
    SELECT
      ss_store_sk,
      ss_item_sk,
      SUM(ss_sales_price) AS revenue
    FROM store_sales, date_dim
    WHERE
      ss_sold_date_sk = d_date_sk AND d_month_seq BETWEEN 1212 AND 1212 + 11
    GROUP BY
      ss_store_sk,
      ss_item_sk
  ) AS sa
  GROUP BY
    ss_store_sk
) AS sb, (
  SELECT
    ss_store_sk,
    ss_item_sk,
    SUM(ss_sales_price) AS revenue
  FROM store_sales, date_dim
  WHERE
    ss_sold_date_sk = d_date_sk AND d_month_seq BETWEEN 1212 AND 1212 + 11
  GROUP BY
    ss_store_sk,
    ss_item_sk
) AS sc
WHERE
  sb.ss_store_sk = sc.ss_store_sk
  AND sc.revenue <= 0.1 * sb.ave
  AND s_store_sk = sc.ss_store_sk
  AND i_item_sk = sc.ss_item_sk
ORDER BY
  s_store_name,
  i_item_desc
LIMIT 100

Representative DataFrame

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

def q65_expression_impl(ctx: DataFrameContext) -> Any:
    params = get_parameters(65)
    dms = params.get("dms", 1212)
    col = ctx.col
    lit = ctx.lit
    sales = ctx.get_table("store_sales").join(
        ctx.get_table("date_dim").filter(col("d_month_seq").is_between(dms, dms + 11)),
        left_on="ss_sold_date_sk",
        right_on="d_date_sk",
    )
    revenue = sales.group_by("ss_store_sk", "ss_item_sk").agg(
        _sum_or_null_expression(ctx, col("ss_sales_price")).alias("revenue")
    )
    store_avg = revenue.group_by("ss_store_sk").agg(col("revenue").mean().alias("ave"))
    flagged = (
        revenue.join(store_avg, on="ss_store_sk")
        .filter(col("revenue") <= lit(0.1) * col("ave"))
        .select("ss_store_sk", "ss_item_sk", "revenue")
    )
    return (
        flagged.join(ctx.get_table("store"), left_on="ss_store_sk", right_on="s_store_sk")
        .join(ctx.get_table("item"), left_on="ss_item_sk", right_on="i_item_sk")
        .select("s_store_name", "i_item_desc", "revenue", "i_current_price", "i_wholesale_cost", "i_brand")
        .sort(["s_store_name", "i_item_desc"], nulls_last=True)
        .limit(100)
    )

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['65'])

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

print(bench.get_query(65, 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', '65', family="expression").source)  # or family="pandas"

Source

Query text: _sources/tpc-ds/query_templates/query65.tpl