TPC-DS-OBT Q23b

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

Representative SQL

Rendered for DataFusion with default parameters.

WITH frequent_ss_items AS (
  SELECT
    SUBSTRING(obt.item_i_item_desc FROM 1 FOR 30) AS itemdesc,
    obt.item_i_item_sk AS item_sk,
    obt.sold_date_d_date AS solddate,
    COUNT(*) AS cnt
  FROM tpcds_sales_returns_obt AS obt
  WHERE
    (
      obt.sold_date_sk = obt.sold_date_d_date_sk
      AND obt.item_sk = obt.item_i_item_sk
      AND obt.sold_date_d_year IN (1999, 1999 + 1, 1999 + 2, 1999 + 3)
    )
    AND channel = 'store'
  GROUP BY
    SUBSTRING(obt.item_i_item_desc FROM 1 FOR 30),
    obt.item_i_item_sk,
    obt.sold_date_d_date
  HAVING
    COUNT(*) > 4
), max_store_sales AS (
  SELECT
    MAX(csales) AS tpcds_cmax
  FROM (
    SELECT
      obt.bill_customer_c_customer_sk,
      SUM(obt.quantity * obt.sales_price) AS csales
    FROM tpcds_sales_returns_obt AS obt
    WHERE
      (
        obt.ship_customer_sk = obt.bill_customer_c_customer_sk
        AND obt.sold_date_sk = obt.sold_date_d_date_sk
        AND obt.sold_date_d_year IN (1999, 1999 + 1, 1999 + 2, 1999 + 3)
      )
      AND channel = 'store'
    GROUP BY
      obt.bill_customer_c_customer_sk
  )
), best_ss_customer AS (
  SELECT
    obt.bill_customer_c_customer_sk,
    SUM(obt.quantity * obt.sales_price) AS ssales
  FROM tpcds_sales_returns_obt AS obt
  WHERE
    obt.ship_customer_sk = obt.bill_customer_c_customer_sk AND channel = 'store'
  GROUP BY
    obt.bill_customer_c_customer_sk
  HAVING
    SUM(obt.quantity * obt.sales_price) > (
      CAST(95 AS DOUBLE PRECISION) / 100.0
    ) * (
      SELECT
        *
      FROM max_store_sales
    )
)
SELECT
  bill_customer_c_last_name,
  bill_customer_c_first_name,
  sales
FROM (
  SELECT
    obt.bill_customer_c_last_name,
    obt.bill_customer_c_first_name,
    SUM(obt.quantity * obt.list_price) AS sales
  FROM tpcds_sales_returns_obt AS obt
  WHERE
    (
      obt.sold_date_d_year = 1999
      AND obt.sold_date_d_moy = 1
      AND obt.sold_date_sk = obt.sold_date_d_date_sk
      AND obt.item_sk IN (
        SELECT
          item_sk
        FROM frequent_ss_items
      )
      AND obt.bill_customer_sk IN (
        SELECT
          bill_customer_c_customer_sk
        FROM best_ss_customer
      )
      AND obt.bill_customer_sk = obt.bill_customer_c_customer_sk
    )
    AND channel = 'catalog'
  GROUP BY
    obt.bill_customer_c_last_name,
    obt.bill_customer_c_first_name
  UNION ALL
  SELECT
    obt.bill_customer_c_last_name,
    obt.bill_customer_c_first_name,
    SUM(obt.quantity * obt.list_price) AS sales
  FROM tpcds_sales_returns_obt AS obt
  WHERE
    (
      obt.sold_date_d_year = 1999
      AND obt.sold_date_d_moy = 1
      AND obt.sold_date_sk = obt.sold_date_d_date_sk
      AND obt.item_sk IN (
        SELECT
          item_sk
        FROM frequent_ss_items
      )
      AND obt.bill_customer_sk IN (
        SELECT
          bill_customer_c_customer_sk
        FROM best_ss_customer
      )
      AND obt.bill_customer_sk = obt.bill_customer_c_customer_sk
    )
    AND channel = 'web'
  GROUP BY
    obt.bill_customer_c_last_name,
    obt.bill_customer_c_first_name
)
ORDER BY
  bill_customer_c_last_name,
  bill_customer_c_first_name,
  sales
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['23b'])

Source

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