TPC-DS Q59 — Store Weekly Sales Year-over-Year

TPC-DS benchmark · all TPC-DS queries

Compares weekly sales by day of week between current and prior year

Representative SQL

Rendered for DataFusion with default parameters.

WITH wss AS (
  SELECT
    d_week_seq,
    ss_store_sk,
    SUM(CASE WHEN (
      d_day_name = 'Sunday'
    ) THEN ss_sales_price ELSE NULL END) AS sun_sales,
    SUM(CASE WHEN (
      d_day_name = 'Monday'
    ) THEN ss_sales_price ELSE NULL END) AS mon_sales,
    SUM(CASE WHEN (
      d_day_name = 'Tuesday'
    ) THEN ss_sales_price ELSE NULL END) AS tue_sales,
    SUM(CASE WHEN (
      d_day_name = 'Wednesday'
    ) THEN ss_sales_price ELSE NULL END) AS wed_sales,
    SUM(CASE WHEN (
      d_day_name = 'Thursday'
    ) THEN ss_sales_price ELSE NULL END) AS thu_sales,
    SUM(CASE WHEN (
      d_day_name = 'Friday'
    ) THEN ss_sales_price ELSE NULL END) AS fri_sales,
    SUM(CASE WHEN (
      d_day_name = 'Saturday'
    ) THEN ss_sales_price ELSE NULL END) AS sat_sales
  FROM store_sales, date_dim
  WHERE
    d_date_sk = ss_sold_date_sk
  GROUP BY
    d_week_seq,
    ss_store_sk
)
SELECT
  s_store_name1,
  s_store_id1,
  d_week_seq1,
  sun_sales1 / sun_sales2,
  mon_sales1 / mon_sales2,
  tue_sales1 / tue_sales2,
  wed_sales1 / wed_sales2,
  thu_sales1 / thu_sales2,
  fri_sales1 / fri_sales2,
  sat_sales1 / sat_sales2
FROM (
  SELECT
    s_store_name AS s_store_name1,
    wss.d_week_seq AS d_week_seq1,
    s_store_id AS s_store_id1,
    sun_sales AS sun_sales1,
    mon_sales AS mon_sales1,
    tue_sales AS tue_sales1,
    wed_sales AS wed_sales1,
    thu_sales AS thu_sales1,
    fri_sales AS fri_sales1,
    sat_sales AS sat_sales1
  FROM wss, store, date_dim AS d
  WHERE
    d.d_week_seq = wss.d_week_seq
    AND ss_store_sk = s_store_sk
    AND d_month_seq BETWEEN 1185 AND 1185 + 11
) AS y, (
  SELECT
    s_store_name AS s_store_name2,
    wss.d_week_seq AS d_week_seq2,
    s_store_id AS s_store_id2,
    sun_sales AS sun_sales2,
    mon_sales AS mon_sales2,
    tue_sales AS tue_sales2,
    wed_sales AS wed_sales2,
    thu_sales AS thu_sales2,
    fri_sales AS fri_sales2,
    sat_sales AS sat_sales2
  FROM wss, store, date_dim AS d
  WHERE
    d.d_week_seq = wss.d_week_seq
    AND ss_store_sk = s_store_sk
    AND d_month_seq BETWEEN 1185 + 12 AND 1185 + 23
) AS x
WHERE
  s_store_id1 = s_store_id2 AND d_week_seq1 = d_week_seq2 - 52
ORDER BY
  s_store_name1,
  s_store_id1,
  d_week_seq1
LIMIT 100

Representative DataFrame

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

def q59_expression_impl(ctx: DataFrameContext) -> Any:
    params = get_parameters(59)
    dms = params.get("d_month_seq", 1212)

    col = ctx.col
    lit = ctx.lit

    store_sales, date_dim, store = _tables(ctx, "store_sales", "date_dim", "store")

    ss_with_date = store_sales.join(date_dim, left_on="ss_sold_date_sk", right_on="d_date_sk")

    wss = ss_with_date.group_by(["d_week_seq", "ss_store_sk"]).agg(_q59_day_sales_aggs(ctx))
    y = _q59_period_expression(ctx, wss, store, date_dim, dms, 0, "1")
    x = _q59_period_expression(ctx, wss, store, date_dim, dms, 12, "2")

    return _sort_null_largest_expression(
        ctx,
        y.join(
            x,
            left_on=["s_store_id1", (col("d_week_seq1") + lit(52))],
            right_on=["s_store_id2", "d_week_seq2"],
        )
        .with_columns(_q59_ratio_exprs(ctx))
        .select(_Q59_RESULT_COLS),
        ["s_store_name1", "s_store_id1", "d_week_seq1"],
    ).head(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['59'])

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

print(bench.get_query(59, 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', '59', family="expression").source)  # or family="pandas"

Source

Query text: _sources/tpc-ds/query_templates/query59.tpl