TPC-DS-OBT Q54

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

Representative SQL

Rendered for DataFusion with default parameters.

WITH my_customers AS (
  SELECT DISTINCT
    obt.bill_customer_c_customer_sk,
    obt.bill_customer_c_current_addr_sk
  FROM tpcds_sales_returns_obt AS obt
  CROSS JOIN (
    SELECT
      obt.sold_date_sk AS sold_date_sk,
      obt.bill_customer_sk AS customer_sk,
      obt.item_sk AS item_sk
    FROM tpcds_sales_returns_obt AS obt
    WHERE
      channel = 'catalog'
    UNION ALL
    SELECT
      obt.sold_date_sk AS sold_date_sk,
      obt.bill_customer_sk AS customer_sk,
      obt.item_sk AS item_sk
    FROM tpcds_sales_returns_obt AS obt
    WHERE
      channel = 'web'
  ) AS cs_or_ws_sales
  WHERE
    (
      obt.sold_date_sk = obt.sold_date_d_date_sk
      AND obt.item_sk = obt.item_i_item_sk
      AND obt.item_i_category = '0'
      AND obt.item_i_class = '0'
      AND obt.bill_customer_c_customer_sk = cs_or_ws_sales.customer_sk
      AND obt.sold_date_d_moy = 1
      AND obt.sold_date_d_year = 1998
    )
    AND channel IN ('catalog', 'store', 'web')
), my_revenue AS (
  SELECT
    obt.bill_customer_c_customer_sk,
    SUM(obt.ext_sales_price) AS revenue
  FROM tpcds_sales_returns_obt AS obt
  CROSS JOIN my_customers AS my_customers
  WHERE
    (
      obt.bill_customer_c_current_addr_sk = obt.bill_addr_ca_address_sk
      AND obt.bill_addr_ca_county = obt.store_s_county
      AND obt.bill_addr_ca_state = obt.store_s_state
      AND obt.sold_date_sk = obt.sold_date_d_date_sk
      AND obt.bill_customer_c_customer_sk = obt.ship_customer_sk
      AND obt.sold_date_d_month_seq BETWEEN (
        SELECT DISTINCT
          obt.sold_date_d_month_seq + 1
        FROM tpcds_sales_returns_obt AS obt
        WHERE
          (
            obt.sold_date_d_year = 1998 AND obt.sold_date_d_moy = 1
          )
          AND channel IN ('catalog', 'store', 'web')
      ) AND (
        SELECT DISTINCT
          obt.sold_date_d_month_seq + 3
        FROM tpcds_sales_returns_obt AS obt
        WHERE
          (
            obt.sold_date_d_year = 1998 AND obt.sold_date_d_moy = 1
          )
          AND channel IN ('catalog', 'store', 'web')
      )
    )
    AND channel = 'store'
  GROUP BY
    obt.bill_customer_c_customer_sk
), segments AS (
  SELECT
    CAST((
      CAST(revenue AS DOUBLE PRECISION) / 50
    ) AS INT) AS segment
  FROM my_revenue
)
SELECT
  segment,
  COUNT(*) AS num_customers,
  segment * 50 AS segment_base
FROM segments
GROUP BY
  segment
ORDER BY
  segment,
  num_customers
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['54'])

Source

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