TPC-DS-OBT Q58

TPC-DS-OBT benchmark · all TPC-DS-OBT queries

Representative SQL

Rendered for DataFusion with default parameters.

WITH ss_items AS (
  SELECT
    obt.item_i_item_id AS item_id,
    SUM(obt.ext_sales_price) AS ss_item_rev
  FROM tpcds_sales_returns_obt AS obt
  WHERE
    (
      obt.item_sk = obt.item_i_item_sk
      AND obt.sold_date_d_date IN (
        SELECT
          obt.sold_date_d_date
        FROM tpcds_sales_returns_obt AS obt
        WHERE
          obt.sold_date_d_week_seq = (
            SELECT
              MAX(obt.sold_date_d_week_seq)
            FROM tpcds_sales_returns_obt AS obt
            WHERE
              obt.sold_date_d_date = '1998-01-01' AND channel IN ('catalog', 'store', 'web')
          )
          AND channel IN ('catalog', 'store', 'web')
      )
      AND obt.sold_date_sk = obt.sold_date_d_date_sk
    )
    AND channel = 'store'
  GROUP BY
    obt.item_i_item_id
), cs_items AS (
  SELECT
    obt.item_i_item_id AS item_id,
    SUM(obt.ext_sales_price) AS cs_item_rev
  FROM tpcds_sales_returns_obt AS obt
  WHERE
    (
      obt.item_sk = obt.item_i_item_sk
      AND obt.sold_date_d_date IN (
        SELECT
          obt.sold_date_d_date
        FROM tpcds_sales_returns_obt AS obt
        WHERE
          obt.sold_date_d_week_seq = (
            SELECT
              MAX(obt.sold_date_d_week_seq)
            FROM tpcds_sales_returns_obt AS obt
            WHERE
              obt.sold_date_d_date = '1998-01-01' AND channel IN ('catalog', 'store', 'web')
          )
          AND channel IN ('catalog', 'store', 'web')
      )
      AND obt.sold_date_sk = obt.sold_date_d_date_sk
    )
    AND channel = 'catalog'
  GROUP BY
    obt.item_i_item_id
), ws_items AS (
  SELECT
    obt.item_i_item_id AS item_id,
    SUM(obt.ext_sales_price) AS ws_item_rev
  FROM tpcds_sales_returns_obt AS obt
  WHERE
    (
      obt.item_sk = obt.item_i_item_sk
      AND obt.sold_date_d_date IN (
        SELECT
          obt.sold_date_d_date
        FROM tpcds_sales_returns_obt AS obt
        WHERE
          obt.sold_date_d_week_seq = (
            SELECT
              MAX(obt.sold_date_d_week_seq)
            FROM tpcds_sales_returns_obt AS obt
            WHERE
              obt.sold_date_d_date = '1998-01-01' AND channel IN ('catalog', 'store', 'web')
          )
          AND channel IN ('catalog', 'store', 'web')
      )
      AND obt.sold_date_sk = obt.sold_date_d_date_sk
    )
    AND channel = 'web'
  GROUP BY
    obt.item_i_item_id
)
SELECT
  ss_items.item_id,
  ss_item_rev,
  CAST(ss_item_rev AS DOUBLE PRECISION) / (
    CAST((
      ss_item_rev + cs_item_rev + ws_item_rev
    ) AS DOUBLE PRECISION) / 3
  ) * 100 AS ss_dev,
  cs_item_rev,
  CAST(cs_item_rev AS DOUBLE PRECISION) / (
    CAST((
      ss_item_rev + cs_item_rev + ws_item_rev
    ) AS DOUBLE PRECISION) / 3
  ) * 100 AS cs_dev,
  ws_item_rev,
  CAST(ws_item_rev AS DOUBLE PRECISION) / (
    CAST((
      ss_item_rev + cs_item_rev + ws_item_rev
    ) AS DOUBLE PRECISION) / 3
  ) * 100 AS ws_dev,
  CAST((
    ss_item_rev + cs_item_rev + ws_item_rev
  ) AS DOUBLE PRECISION) / 3 AS average
FROM ss_items, cs_items, ws_items
WHERE
  ss_items.item_id = cs_items.item_id
  AND ss_items.item_id = ws_items.item_id
  AND ss_item_rev BETWEEN 0.9 * cs_item_rev AND 1.1 * cs_item_rev
  AND ss_item_rev BETWEEN 0.9 * ws_item_rev AND 1.1 * ws_item_rev
  AND cs_item_rev BETWEEN 0.9 * ss_item_rev AND 1.1 * ss_item_rev
  AND cs_item_rev BETWEEN 0.9 * ws_item_rev AND 1.1 * ws_item_rev
  AND ws_item_rev BETWEEN 0.9 * ss_item_rev AND 1.1 * ss_item_rev
  AND ws_item_rev BETWEEN 0.9 * cs_item_rev AND 1.1 * cs_item_rev
ORDER BY
  ss_items.item_id,
  ss_item_rev
LIMIT 100

Representative DataFrame

No DataFrame implementation is registered for this query.

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 TPCDSOBT

bench = TPCDSOBT(scale_factor=1.0)            # your scale factor
queries = bench.get_queries(dialect="datafusion")   # your platform's dialect; drop dialect= for native SQL
print(queries['58'])

Source

Query text: benchbox/core/tpcds_obt/queries.py