Как получить наиболее частое значение в Google Bigquery

Question

Postgres имеет простую функцию для достижения этой цели, просто с помощью функции mode () мы можем найти наиболее частое значение. Есть ли что-то эквивалентное в Google Bigquery?

Как можно написать такой запрос в Bigquery?

select count(*),
       avg(vehicles)                                         as mean,
       percentile_cont(0.5) within group (order by vehicles) as median,
       mode() within group (order by vehicles)               as most_frequent_value
FROM "driver"
WHERE vehicles is not null;

Answer 1

Ниже для BigQuery Standard SQL

Вариант 1

#standardSQL
SELECT * FROM (
  SELECT COUNT(*) AS cnt,
    AVG(vehicles) AS mean,
    APPROX_TOP_COUNT(vehicles, 1)[OFFSET(0)].value AS most_frequent_value
  FROM `project.dataset.table`
  WHERE vehicles IS NOT NULL
) CROSS JOIN (
  SELECT PERCENTILE_CONT(vehicles, 0.5) OVER() AS median
  FROM `project.dataset.table`
  WHERE vehicles IS NOT NULL
  LIMIT 1
)

Вариант 2

#standardSQL
SELECT * FROM (
  SELECT COUNT(*) cnt,
    AVG(vehicles) AS mean
  FROM `project.dataset.table`
  WHERE vehicles IS NOT NULL
) CROSS JOIN (
  SELECT PERCENTILE_CONT(vehicles, 0.5) OVER() AS median
  FROM `project.dataset.table`
  WHERE vehicles IS NOT NULL
  LIMIT 1
) CROSS JOIN (
  SELECT vehicles AS most_frequent_value
  FROM `project.dataset.table`
  WHERE vehicles IS NOT NULL
  GROUP BY vehicles
  ORDER BY COUNT(1) DESC
  LIMIT 1
)  

Вариант 3

#standardSQL
CREATE TEMP FUNCTION median(arr ANY TYPE) AS ((
  SELECT PERCENTILE_CONT(x, 0.5) OVER() 
  FROM UNNEST(arr) x LIMIT 1 
));
CREATE TEMP FUNCTION most_frequent_value(arr ANY TYPE) AS ((
  SELECT x 
  FROM UNNEST(arr) x
  GROUP BY x
  ORDER BY COUNT(1) DESC
  LIMIT 1  
));
SELECT COUNT(*) cnt,
  AVG(vehicles) AS mean,
  median(ARRAY_AGG(vehicles)) AS median,
  most_frequent_value(ARRAY_AGG(vehicles)) AS most_frequent_value
FROM `project.dataset.table`
WHERE vehicles IS NOT NULL   

и так далее ...

Answer 2

Вы можете использовать APPROX_TOP_COUNT для получения верхних значений, например:

SELECT APPROX_TOP_COUNT(vehicles, 5) AS top_five_vehicles
FROM dataset.driver

Если вы просто хотите получить верхнее значение, вы можете выбрать его из массива:

SELECT APPROX_TOP_COUNT(vehicles, 1)[OFFSET(0)] AS most_frequent_value
FROM dataset.driver