BigQuery применяет rank / процент_ранку к столбцу с предложением WHERE

Question

У меня есть довольно широкая таблица больших запросов с ~ 20-30 различными столбцами, каждый из которых должен получить дополнительный столбец процентиль , который показывает значение процентиля столбца по сравнению со всеми другими строками в таблице. Однако каждый из столбцов должен только получить значение процентиля , если значение в другом столбце соответствует определенному порогу. Чтобы продемонстрировать это, я создал воспроизводимый пример ниже:

WITH
  correct_games_played AS
    (
      SELECT "a" as name, 7 as num1, 0.4 as num2, 0.55 as num3
      UNION ALL SELECT "b" as name, 13 as num1, 0.53 as num2, 0.37 as num3
      UNION ALL SELECT "c" as name, 4 as num1, 0.42 as num2, 0.32 as num3
      UNION ALL SELECT "d" as name, 17 as num1, 0.6 as num2, 0.23 as num3
      UNION ALL SELECT "e" as name, 7 as num1, 0.3 as num2, 0.25 as num3
      UNION ALL SELECT "f" as name, 16 as num1, 0.7 as num2, 0.43 as num3
      UNION ALL SELECT "g" as name, 10 as num1, 0.53 as num2, 0.52 as num3
      UNION ALL SELECT "h" as name, 5 as num1, 0.54 as num2, 0.21 as num3
      UNION ALL SELECT "i" as name, 9 as num1, 0.56 as num2, 0.17 as num3
      UNION ALL SELECT "j" as name, 3 as num1, 0.75 as num2, 0.53 as num3
    )

  SELECT 
    a.*,
    -- RANK() OVER(ORDER BY a.num1 DESC) AS num1_rank,
    -- RANK() OVER(ORDER BY a.num2 DESC) AS num2_rank,
    -- RANK() OVER(ORDER BY a.num3 DESC) AS num3_rank
    RANK() OVER(ORDER BY a.num1 DESC) AS num1_rank,
    RANK() OVER(ORDER BY a.num2 WHERE a.num1 > 4 DESC) AS num2_rank
    RANK() OVER(ORDER BY a.num3 WHERE a.num1 > 3 DESC) AS num3_rank
  FROM correct_games_played as a

Этот скрипт выдает ошибку Syntax error: Expected ")" but got keyword WHERE at [22:37], однако это работает, если я заменю rank() на закомментированный rank(). Моя цель на самом деле очень проста:

• num2_rank: только значения ранга в a.num2, если a.num1 больше 4, в противном случае выведите null значение
• num3_rank: только значения ранга в a.num3, если a.num1 больше 3, в противном случае выведите значение null

Моя таблица достаточно широка, и есть вероятность, что для каждого столбца потребуетсясвое собственное условие, чтобы определить, следует ли ранжировать значения строки каждого столбца или нет. Любая помощь с этим будет принята с благодарностью, спасибо!

Answer 1

Ниже для BigQuery Standard SQL

#standardSQL
WITH correct_games_played AS (
  SELECT "a" AS name, 7 AS num1, 0.4 AS num2, 0.55 AS num3 UNION ALL 
  SELECT "b" AS name, 13 AS num1, 0.53 AS num2, 0.37 AS num3 UNION ALL 
  SELECT "c" AS name, 4 AS num1, 0.42 AS num2, 0.32 AS num3 UNION ALL 
  SELECT "d" AS name, 17 AS num1, 0.6 AS num2, 0.23 AS num3 UNION ALL 
  SELECT "e" AS name, 7 AS num1, 0.3 AS num2, 0.25 AS num3 UNION ALL 
  SELECT "f" AS name, 16 AS num1, 0.7 AS num2, 0.43 AS num3 UNION ALL 
  SELECT "g" AS name, 10 AS num1, 0.53 AS num2, 0.52 AS num3 UNION ALL 
  SELECT "h" AS name, 5 AS num1, 0.54 AS num2, 0.21 AS num3 UNION ALL 
  SELECT "i" AS name, 9 AS num1, 0.56 AS num2, 0.17 AS num3 UNION ALL 
  SELECT "j" AS name, 3 AS num1, 0.75 AS num2, 0.53 AS num3
)
SELECT *,
  RANK() OVER(ORDER BY num1 DESC) AS num1_rank,
  IF(num1 > 4, RANK() OVER(ORDER BY IF(num1 > 4, num2, NULL) DESC), NULL)  AS num2_rank,
  IF(num1 > 3, RANK() OVER(ORDER BY IF(num1 > 3, num3, NULL) DESC), NULL) AS num3_rank
FROM correct_games_played