TPC-DS-OBT Q49

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

Representative SQL

Rendered for DataFusion with default parameters.

SELECT
  channel,
  item,
  return_ratio,
  return_rank,
  currency_rank
FROM (
  SELECT
    'web' AS channel,
    web.item,
    web.return_ratio,
    web.return_rank,
    web.currency_rank
  FROM (
    SELECT
      item,
      return_ratio,
      currency_ratio,
      RANK() OVER (ORDER BY return_ratio) AS return_rank,
      RANK() OVER (ORDER BY currency_ratio) AS currency_rank
    FROM (
      SELECT
        item_sk AS item,
        CAST(SUM(COALESCE(return_quantity, 0)) AS DECIMAL(15, 4)) / NULLIF(CAST(SUM(COALESCE(quantity, 0)) AS DECIMAL(15, 4)), 0) AS return_ratio,
        CAST(SUM(COALESCE(return_amount, 0)) AS DECIMAL(15, 4)) / NULLIF(CAST(SUM(COALESCE(net_paid, 0)) AS DECIMAL(15, 4)), 0) AS currency_ratio
      FROM tpcds_sales_returns_obt
      WHERE
        channel = 'web'
        AND return_amount > 10000
        AND net_profit > 1
        AND net_paid > 0
        AND quantity > 0
        AND sold_date_d_year = 1998
        AND sold_date_d_moy = 11
      GROUP BY
        item_sk
    ) AS in_web
  ) AS web
  WHERE
    web.return_rank <= 10 OR web.currency_rank <= 10
  UNION
  SELECT
    'catalog' AS channel,
    catalog.item,
    catalog.return_ratio,
    catalog.return_rank,
    catalog.currency_rank
  FROM (
    SELECT
      item,
      return_ratio,
      currency_ratio,
      RANK() OVER (ORDER BY return_ratio) AS return_rank,
      RANK() OVER (ORDER BY currency_ratio) AS currency_rank
    FROM (
      SELECT
        item_sk AS item,
        CAST(SUM(COALESCE(return_quantity, 0)) AS DECIMAL(15, 4)) / NULLIF(CAST(SUM(COALESCE(quantity, 0)) AS DECIMAL(15, 4)), 0) AS return_ratio,
        CAST(SUM(COALESCE(return_amount, 0)) AS DECIMAL(15, 4)) / NULLIF(CAST(SUM(COALESCE(net_paid, 0)) AS DECIMAL(15, 4)), 0) AS currency_ratio
      FROM tpcds_sales_returns_obt
      WHERE
        channel = 'catalog'
        AND return_amount > 10000
        AND net_profit > 1
        AND net_paid > 0
        AND quantity > 0
        AND sold_date_d_year = 1998
        AND sold_date_d_moy = 11
      GROUP BY
        item_sk
    ) AS in_cat
  ) AS catalog
  WHERE
    catalog.return_rank <= 10 OR catalog.currency_rank <= 10
  UNION
  SELECT
    'store' AS channel,
    store.item,
    store.return_ratio,
    store.return_rank,
    store.currency_rank
  FROM (
    SELECT
      item,
      return_ratio,
      currency_ratio,
      RANK() OVER (ORDER BY return_ratio) AS return_rank,
      RANK() OVER (ORDER BY currency_ratio) AS currency_rank
    FROM (
      SELECT
        item_sk AS item,
        CAST(SUM(COALESCE(return_quantity, 0)) AS DECIMAL(15, 4)) / NULLIF(CAST(SUM(COALESCE(quantity, 0)) AS DECIMAL(15, 4)), 0) AS return_ratio,
        CAST(SUM(COALESCE(return_amount, 0)) AS DECIMAL(15, 4)) / NULLIF(CAST(SUM(COALESCE(net_paid, 0)) AS DECIMAL(15, 4)), 0) AS currency_ratio
      FROM tpcds_sales_returns_obt
      WHERE
        channel = 'store'
        AND return_amount > 10000
        AND net_profit > 1
        AND net_paid > 0
        AND quantity > 0
        AND sold_date_d_year = 1998
        AND sold_date_d_moy = 11
      GROUP BY
        item_sk
    ) AS in_store
  ) AS store
  WHERE
    store.return_rank <= 10 OR store.currency_rank <= 10
) AS combined
ORDER BY
  1,
  4,
  5,
  2
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['49'])

Source

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