TPC-DS-OBT Q4 — obt_channel_revenue

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

Total net revenue by channel

Representative SQL

Rendered for DataFusion with default parameters.

WITH year_total AS (
  SELECT
    obt.bill_customer_c_customer_id AS customer_id,
    obt.bill_customer_c_first_name AS customer_first_name,
    obt.bill_customer_c_last_name AS customer_last_name,
    obt.bill_customer_c_preferred_cust_flag AS customer_preferred_cust_flag,
    obt.bill_customer_c_birth_country AS customer_birth_country,
    obt.bill_customer_c_login AS customer_login,
    obt.bill_customer_c_email_address AS customer_email_address,
    obt.sold_date_d_year AS dyear,
    SUM(
      CAST((
        (
          obt.ext_list_price - obt.ext_wholesale_cost - obt.ext_discount_amt
        ) + obt.ext_sales_price
      ) AS DOUBLE PRECISION) / 2
    ) AS year_total,
    's' AS sale_type
  FROM tpcds_sales_returns_obt AS obt
  WHERE
    (
      obt.bill_customer_c_customer_sk = obt.ship_customer_sk
      AND obt.sold_date_sk = obt.sold_date_d_date_sk
    )
    AND channel = 'store'
  GROUP BY
    obt.bill_customer_c_customer_id,
    obt.bill_customer_c_first_name,
    obt.bill_customer_c_last_name,
    obt.bill_customer_c_preferred_cust_flag,
    obt.bill_customer_c_birth_country,
    obt.bill_customer_c_login,
    obt.bill_customer_c_email_address,
    obt.sold_date_d_year
  UNION ALL
  SELECT
    obt.bill_customer_c_customer_id AS customer_id,
    obt.bill_customer_c_first_name AS customer_first_name,
    obt.bill_customer_c_last_name AS customer_last_name,
    obt.bill_customer_c_preferred_cust_flag AS customer_preferred_cust_flag,
    obt.bill_customer_c_birth_country AS customer_birth_country,
    obt.bill_customer_c_login AS customer_login,
    obt.bill_customer_c_email_address AS customer_email_address,
    obt.sold_date_d_year AS dyear,
    SUM(
      (
        CAST((
          (
            obt.ext_list_price - obt.ext_wholesale_cost - obt.ext_discount_amt
          ) + obt.ext_sales_price
        ) AS DOUBLE PRECISION) / 2
      )
    ) AS year_total,
    'c' AS sale_type
  FROM tpcds_sales_returns_obt AS obt
  WHERE
    (
      obt.bill_customer_c_customer_sk = obt.bill_customer_sk
      AND obt.sold_date_sk = obt.sold_date_d_date_sk
    )
    AND channel = 'catalog'
  GROUP BY
    obt.bill_customer_c_customer_id,
    obt.bill_customer_c_first_name,
    obt.bill_customer_c_last_name,
    obt.bill_customer_c_preferred_cust_flag,
    obt.bill_customer_c_birth_country,
    obt.bill_customer_c_login,
    obt.bill_customer_c_email_address,
    obt.sold_date_d_year
  UNION ALL
  SELECT
    obt.bill_customer_c_customer_id AS customer_id,
    obt.bill_customer_c_first_name AS customer_first_name,
    obt.bill_customer_c_last_name AS customer_last_name,
    obt.bill_customer_c_preferred_cust_flag AS customer_preferred_cust_flag,
    obt.bill_customer_c_birth_country AS customer_birth_country,
    obt.bill_customer_c_login AS customer_login,
    obt.bill_customer_c_email_address AS customer_email_address,
    obt.sold_date_d_year AS dyear,
    SUM(
      (
        CAST((
          (
            obt.ext_list_price - obt.ext_wholesale_cost - obt.ext_discount_amt
          ) + obt.ext_sales_price
        ) AS DOUBLE PRECISION) / 2
      )
    ) AS year_total,
    'w' AS sale_type
  FROM tpcds_sales_returns_obt AS obt
  WHERE
    (
      obt.bill_customer_c_customer_sk = obt.bill_customer_sk
      AND obt.sold_date_sk = obt.sold_date_d_date_sk
    )
    AND channel = 'web'
  GROUP BY
    obt.bill_customer_c_customer_id,
    obt.bill_customer_c_first_name,
    obt.bill_customer_c_last_name,
    obt.bill_customer_c_preferred_cust_flag,
    obt.bill_customer_c_birth_country,
    obt.bill_customer_c_login,
    obt.bill_customer_c_email_address,
    obt.sold_date_d_year
)
SELECT
  t_s_secyear.customer_id,
  t_s_secyear.customer_first_name,
  t_s_secyear.customer_last_name,
  t_s_secyear.customer_preferred_cust_flag
FROM year_total AS t_s_firstyear, year_total AS t_s_secyear, year_total AS t_c_firstyear, year_total AS t_c_secyear, year_total AS t_w_firstyear, year_total AS t_w_secyear
WHERE
  t_s_secyear.customer_id = t_s_firstyear.customer_id
  AND t_s_firstyear.customer_id = t_c_secyear.customer_id
  AND t_s_firstyear.customer_id = t_c_firstyear.customer_id
  AND t_s_firstyear.customer_id = t_w_firstyear.customer_id
  AND t_s_firstyear.customer_id = t_w_secyear.customer_id
  AND t_s_firstyear.sale_type = 's'
  AND t_c_firstyear.sale_type = 'c'
  AND t_w_firstyear.sale_type = 'w'
  AND t_s_secyear.sale_type = 's'
  AND t_c_secyear.sale_type = 'c'
  AND t_w_secyear.sale_type = 'w'
  AND t_s_firstyear.dyear = 1998
  AND t_s_secyear.dyear = 1998 + 1
  AND t_c_firstyear.dyear = 1998
  AND t_c_secyear.dyear = 1998 + 1
  AND t_w_firstyear.dyear = 1998
  AND t_w_secyear.dyear = 1998 + 1
  AND t_s_firstyear.year_total > 0
  AND t_c_firstyear.year_total > 0
  AND t_w_firstyear.year_total > 0
  AND CASE
    WHEN t_c_firstyear.year_total > 0
    THEN CAST(t_c_secyear.year_total AS DOUBLE PRECISION) / t_c_firstyear.year_total
    ELSE NULL
  END > CASE
    WHEN t_s_firstyear.year_total > 0
    THEN CAST(t_s_secyear.year_total AS DOUBLE PRECISION) / t_s_firstyear.year_total
    ELSE NULL
  END
  AND CASE
    WHEN t_c_firstyear.year_total > 0
    THEN CAST(t_c_secyear.year_total AS DOUBLE PRECISION) / t_c_firstyear.year_total
    ELSE NULL
  END > CASE
    WHEN t_w_firstyear.year_total > 0
    THEN CAST(t_w_secyear.year_total AS DOUBLE PRECISION) / t_w_firstyear.year_total
    ELSE NULL
  END
ORDER BY
  t_s_secyear.customer_id,
  t_s_secyear.customer_first_name,
  t_s_secyear.customer_last_name,
  t_s_secyear.customer_preferred_cust_flag
LIMIT 100

Representative DataFrame

Expression family (Polars, PySpark, DataFusion), default parameters.

def impl(ctx: DataFrameContext) -> Any:
        table = ctx.get_table(OBT_TABLE)
        for column, op, value in spec.filters:
            table = table.filter(_FILTER_OPS[op](ctx.col(column), ctx.lit(value)))
        aggregates = [getattr(ctx.col(column), func)().alias(alias) for alias, column, func in spec.aggregations]
        if spec.group_keys:
            result = table.group_by(*spec.group_keys).agg(*aggregates)
        else:
            result = table.select(*aggregates)
        if spec.sort_keys:
            descending = list(spec.descending) if spec.descending else [False] * len(spec.sort_keys)
            result = result.sort(list(spec.sort_keys), descending=descending)
        if spec.limit:
            result = result.limit(spec.limit)
        return result

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['4'])

For the DataFrame form:

from benchbox.core.query_catalog import get_dataframe_render

print(get_dataframe_render('tpcds_obt', '4', family="expression").source)  # or family="pandas"

Source

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