TPC-DS-OBT Q14b

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

Representative SQL

Rendered for DataFusion with default parameters.

WITH cross_items AS (
  SELECT
    item_i_item_sk
  FROM (
    SELECT DISTINCT
      item_i_item_sk,
      item_i_brand_id,
      item_i_class_id,
      item_i_category_id
    FROM tpcds_sales_returns_obt
    WHERE
      NOT item_i_item_sk IS NULL
  ) AS i
  JOIN (
    SELECT
      item_i_brand_id,
      item_i_class_id,
      item_i_category_id
    FROM tpcds_sales_returns_obt
    WHERE
      channel = 'store' AND sold_date_d_year BETWEEN 1998 AND 1998 + 2
    INTERSECT
    SELECT
      item_i_brand_id,
      item_i_class_id,
      item_i_category_id
    FROM tpcds_sales_returns_obt
    WHERE
      channel = 'catalog' AND sold_date_d_year BETWEEN 1998 AND 1998 + 2
    INTERSECT
    SELECT
      item_i_brand_id,
      item_i_class_id,
      item_i_category_id
    FROM tpcds_sales_returns_obt
    WHERE
      channel = 'web' AND sold_date_d_year BETWEEN 1998 AND 1998 + 2
  ) AS x
    ON i.item_i_brand_id = x.item_i_brand_id
    AND i.item_i_class_id = x.item_i_class_id
    AND i.item_i_category_id = x.item_i_category_id
), avg_sales AS (
  SELECT
    AVG(quantity * list_price) AS average_sales
  FROM tpcds_sales_returns_obt
  WHERE
    sold_date_d_year BETWEEN 1998 AND 1998 + 2
), weekly AS (
  SELECT
    sold_date_d_week_seq AS week_seq,
    item_i_brand_id AS i_brand_id,
    item_i_class_id AS i_class_id,
    item_i_category_id AS i_category_id,
    SUM(quantity * list_price) AS sales,
    COUNT(*) AS number_sales
  FROM tpcds_sales_returns_obt
  WHERE
    channel = 'store'
    AND item_sk IN (
      SELECT
        item_i_item_sk
      FROM cross_items
    )
    AND sold_date_d_week_seq IN (
      SELECT DISTINCT
        sold_date_d_week_seq
      FROM tpcds_sales_returns_obt
      WHERE
        sold_date_d_year IN (1998, 1998 + 1)
        AND sold_date_d_moy = 12
        AND sold_date_d_dom = 16
    )
  GROUP BY
    sold_date_d_week_seq,
    item_i_brand_id,
    item_i_class_id,
    item_i_category_id
  HAVING
    SUM(quantity * list_price) > (
      SELECT
        average_sales
      FROM avg_sales
    )
)
SELECT
  this_year.channel AS ty_channel,
  this_year.i_brand_id AS ty_brand,
  this_year.i_class_id AS ty_class,
  this_year.i_category_id AS ty_category,
  this_year.sales AS ty_sales,
  this_year.number_sales AS ty_number_sales,
  last_year.channel AS ly_channel,
  last_year.i_brand_id AS ly_brand,
  last_year.i_class_id AS ly_class,
  last_year.i_category_id AS ly_category,
  last_year.sales AS ly_sales,
  last_year.number_sales AS ly_number_sales
FROM (
  SELECT
    'store' AS channel,
    w.*
  FROM weekly AS w
  WHERE
    week_seq = (
      SELECT DISTINCT
        sold_date_d_week_seq
      FROM tpcds_sales_returns_obt
      WHERE
        sold_date_d_year = 1998 + 1 AND sold_date_d_moy = 12 AND sold_date_d_dom = 16
    )
) AS this_year, (
  SELECT
    'store' AS channel,
    w.*
  FROM weekly AS w
  WHERE
    week_seq = (
      SELECT DISTINCT
        sold_date_d_week_seq
      FROM tpcds_sales_returns_obt
      WHERE
        sold_date_d_year = 1998 AND sold_date_d_moy = 12 AND sold_date_d_dom = 16
    )
) AS last_year
WHERE
  this_year.i_brand_id = last_year.i_brand_id
  AND this_year.i_class_id = last_year.i_class_id
  AND this_year.i_category_id = last_year.i_category_id
ORDER BY
  this_year.channel,
  this_year.i_brand_id,
  this_year.i_class_id,
  this_year.i_category_id
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['14b'])

Source

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