Google bigquery 在BigQuery中查找模式

模式是集合中最常出现的值

我想要一些像：

SELECT
    t.id as t_id,
    GROUP_CONCAT(t.value) as value_list,
    MODE(t.value) AS value_mode
FROM dataset.table as t
GROUP BY t_id

例如：

t_id    value_list     value_mode
1       2,2,2,3,6,6    2

这是怎么做到的

---

编辑：值列表仅用于说明。只需要模式

对于您的示例，我将这样解决它：

SELECT x, w mode
FROM (
  SELECT COUNT(*) c, w, ROW_NUMBER() OVER(ORDER BY c DESC) rn, FIRST(x) x
  FROM (
    SELECT SPLIT(x) w, x FROM (SELECT "2,2,2,3,6,6" x)
  )
  GROUP BY 2
)
WHERE rn=1

在查询中使用组_CONCAT：

SELECT gc, w mode
FROM (
  SELECT COUNT(*) c, w, ROW_NUMBER() OVER(ORDER BY c DESC) rn, FIRST(gc) gc
  FROM (
    SELECT GROUP_CONCAT(w) OVER() gc, w
    FROM (FLATTEN((
      SELECT SPLIT(x) w, x FROM (SELECT "2,2,2,3,6,6" x)), w)
    )
  )
  GROUP BY 2
)
WHERE rn=1

和处理分区：

SELECT tid, gc value_list, w value_mode
FROM (
  SELECT tid, COUNT(*) c, w, ROW_NUMBER() OVER(PARTITION BY tid ORDER BY c DESC) rn, FIRST(gc) gc
  FROM (
    SELECT tid, GROUP_CONCAT(w) OVER(PARTITION BY tid) gc, w
    FROM (FLATTEN((
      SELECT 1 tid, SPLIT(x) w, x FROM (SELECT "2,2,2,3,6,6" x)), w)
    )
  )
  GROUP BY tid, w
)
WHERE rn=1

---

我经常需要找到各个组的价格模式（例如长度和电流），以过滤掉销售价格等。 我通常使用两种方法创建数组和按频率顺序取消嵌套。我使用的一种方法是使用

限制

另一种方法是使用

[OFFSET（0）]

，以防您想要获得第n个值

两者都包括在下面：

WITH t AS (SELECT 18 AS length, 
'HIGH' as amps, 
99.95 price UNION ALL
SELECT 18,  "HIGH", 99.95 UNION ALL
SELECT 18,  "HIGH", 5.95 UNION ALL
SELECT 18,  "LOW", 33.95 UNION ALL
SELECT 18,  "LOW", 33.95 UNION ALL
SELECT 18,  "LOW", 4.5 UNION ALL
SELECT 3,  "HIGH", 77.95 UNION ALL
SELECT 3,  "HIGH", 77.95 UNION ALL
SELECT 3,  "HIGH", 9.99 UNION ALL
SELECT 3,  "LOW", 44.95 UNION ALL
SELECT 3,  "LOW", 44.95 UNION ALL
SELECT 3,  "LOW", 5.65 
)

SELECT
  length,
  amps,

  -- By Limit
  (SELECT x FROM UNNEST(price_array) x 
    GROUP BY x ORDER BY COUNT(*) DESC LIMIT 1 ) most_freq_price,
  (SELECT x FROM UNNEST(price_array) x 
    GROUP BY x ORDER BY COUNT(*) ASC  LIMIT 1 ) least_freq_price,

  -- By Offset
  ARRAY((SELECT x FROM UNNEST(price_array) x 
    GROUP BY x ORDER BY COUNT(*) DESC))[OFFSET(0)] most_freq_price_offset,
  ARRAY((SELECT x FROM UNNEST(price_array) x 
    GROUP BY x ORDER BY COUNT(*) ASC))[OFFSET(0)] least_freq_price_offset

FROM (
  SELECT 
    length,
    amps,
    ARRAY_AGG(price) price_array
  FROM t
  GROUP BY 1,2
 )

---

这将如何与小组合作？是否需要向查询中添加分区依据？如果问题中的示例更复杂，我会这样做：）。（当问题包括我可以使用的表格时，我的答案更具体）根据我的问题格式化你的答案你能稍微修改一下你的答案，这样我就可以把我的反对票（错误地）改为赞成票吗？行，请多多纳。非常感谢。

WITH t AS (SELECT 18 AS length, 
'HIGH' as amps, 
99.95 price UNION ALL
SELECT 18,  "HIGH", 99.95 UNION ALL
SELECT 18,  "HIGH", 5.95 UNION ALL
SELECT 18,  "LOW", 33.95 UNION ALL
SELECT 18,  "LOW", 33.95 UNION ALL
SELECT 18,  "LOW", 4.5 UNION ALL
SELECT 3,  "HIGH", 77.95 UNION ALL
SELECT 3,  "HIGH", 77.95 UNION ALL
SELECT 3,  "HIGH", 9.99 UNION ALL
SELECT 3,  "LOW", 44.95 UNION ALL
SELECT 3,  "LOW", 44.95 UNION ALL
SELECT 3,  "LOW", 5.65 
)

SELECT
  length,
  amps,

  -- By Limit
  (SELECT x FROM UNNEST(price_array) x 
    GROUP BY x ORDER BY COUNT(*) DESC LIMIT 1 ) most_freq_price,
  (SELECT x FROM UNNEST(price_array) x 
    GROUP BY x ORDER BY COUNT(*) ASC  LIMIT 1 ) least_freq_price,

  -- By Offset
  ARRAY((SELECT x FROM UNNEST(price_array) x 
    GROUP BY x ORDER BY COUNT(*) DESC))[OFFSET(0)] most_freq_price_offset,
  ARRAY((SELECT x FROM UNNEST(price_array) x 
    GROUP BY x ORDER BY COUNT(*) ASC))[OFFSET(0)] least_freq_price_offset

FROM (
  SELECT 
    length,
    amps,
    ARRAY_AGG(price) price_array
  FROM t
  GROUP BY 1,2
 )