TPC-DS-OBT Q78

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

Representative SQL

Rendered for DataFusion with default parameters.

WITH ws AS (
  SELECT
    obt.sold_date_d_year AS ws_sold_year,
    obt.item_sk,
    obt.bill_customer_sk AS ws_customer_sk,
    SUM(obt.quantity) AS ws_qty,
    SUM(obt.wholesale_cost) AS ws_wc,
    SUM(obt.sales_price) AS ws_sp
  FROM tpcds_sales_returns_obt AS obt
  WHERE
    (
      (
        obt.sale_id IS NULL
        AND (
          obt.sale_id = obt.sale_id AND obt.item_sk = obt.item_sk
        )
      )
      AND obt.sold_date_sk = obt.sold_date_d_date_sk
    )
    AND channel = 'web'
  GROUP BY
    obt.sold_date_d_year,
    obt.item_sk,
    obt.bill_customer_sk
), cs AS (
  SELECT
    obt.sold_date_d_year AS cs_sold_year,
    obt.item_sk,
    obt.bill_customer_sk AS cs_customer_sk,
    SUM(obt.quantity) AS cs_qty,
    SUM(obt.wholesale_cost) AS cs_wc,
    SUM(obt.sales_price) AS cs_sp
  FROM tpcds_sales_returns_obt AS obt
  WHERE
    (
      (
        obt.sale_id IS NULL
        AND (
          obt.sale_id = obt.sale_id AND obt.item_sk = obt.item_sk
        )
      )
      AND obt.sold_date_sk = obt.sold_date_d_date_sk
    )
    AND channel = 'catalog'
  GROUP BY
    obt.sold_date_d_year,
    obt.item_sk,
    obt.bill_customer_sk
), ss AS (
  SELECT
    obt.sold_date_d_year AS ss_sold_year,
    obt.item_sk,
    obt.ship_customer_sk,
    SUM(obt.quantity) AS ss_qty,
    SUM(obt.wholesale_cost) AS ss_wc,
    SUM(obt.sales_price) AS ss_sp
  FROM tpcds_sales_returns_obt AS obt
  WHERE
    (
      (
        obt.sale_id IS NULL
        AND (
          obt.sale_id = obt.sale_id AND obt.item_sk = obt.item_sk
        )
      )
      AND obt.sold_date_sk = obt.sold_date_d_date_sk
    )
    AND channel = 'store'
  GROUP BY
    obt.sold_date_d_year,
    obt.item_sk,
    obt.ship_customer_sk
)
SELECT
  ss_sold_year,
  ROUND(
    CAST(ss_qty AS DOUBLE PRECISION) / (
      COALESCE(ws_qty, 0) + COALESCE(cs_qty, 0)
    ),
    2
  ) AS ratio,
  ss_qty AS store_qty,
  ss_wc AS store_wholesale_cost,
  ss_sp AS store_sales_price,
  COALESCE(ws_qty, 0) + COALESCE(cs_qty, 0) AS other_chan_qty,
  COALESCE(ws_wc, 0) + COALESCE(cs_wc, 0) AS other_chan_wholesale_cost,
  COALESCE(ws_sp, 0) + COALESCE(cs_sp, 0) AS other_chan_sales_price
FROM ss
LEFT JOIN ws
  ON (
    ws_sold_year = ss_sold_year
    AND ws.item_sk = ss.item_sk
    AND ws_customer_sk = ship_customer_sk
  )
LEFT JOIN cs
  ON (
    cs_sold_year = ss_sold_year
    AND ss.item_sk = cs.item_sk
    AND cs_customer_sk = ship_customer_sk
  )
WHERE
  (
    (
      (
        COALESCE(ws_qty, 0) > 0 OR COALESCE(cs_qty, 0) > 0
      ) AND ss_sold_year = 1998
    )
    AND (
      ws_sold_year = ss_sold_year
      AND ws.item_sk = ss.item_sk
      AND ws_customer_sk = ship_customer_sk
    )
  )
  AND (
    cs_sold_year = ss_sold_year
    AND ss.item_sk = cs.item_sk
    AND cs_customer_sk = ship_customer_sk
  )
ORDER BY
  ss_sold_year,
  ss_qty DESC,
  ss_wc DESC,
  ss_sp DESC,
  other_chan_qty,
  other_chan_wholesale_cost,
  other_chan_sales_price,
  ratio
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['78'])

Source

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