说我有下表
month region revenue
------ -------- ----------
jan north 100
feb north 150
mar north 250
我如何能够查询上表以获得以下结果？：
month region revenue
------ -------- ----------
jan north 100
feb north 150
mar north 250
apr north 0
may north 0
jun north 0
0 可以是空值，反之亦然。本质上是试图在我的查询中添加空/空字段（在本例中为 apr、may、jun 行）。任何帮助将非常感激
谢谢
以下是 BigQuery Legacy SQL，但请注意 - 强烈建议 BigQuery 团队迁移到BigQuery Standard SQL
下面的例子应该给你一个想法
#legacySQL
SELECT
months.month_abr AS month_abr,
regions.region AS region,
COALESCE(revenues.revenue, 0) revenue
FROM months
CROSS JOIN (
SELECT region FROM revenues
) regions
LEFT JOIN revenues
ON months.month_abr = revenues.month_abr
AND regions.region = revenues.region
-- ORDER BY regions.region, months.month_number
revenues包含收入数据的原始表格 在哪里，month是带有月份列表的表格（或者您可以使用下面示例中的子查询）
您可以使用下面的示例使用您问题中的虚拟数据测试/玩上面的内容
#legacySQL
SELECT
months.month_abr AS month_abr,
regions.region AS region,
COALESCE(revenues.revenue, 0) revenue
FROM (
SELECT month_number, month_abr FROM
(SELECT 1 month_number, 'jan' month_abr),
(SELECT 2 month_number, 'feb' month_abr),
(SELECT 3 month_number, 'mar' month_abr),
(SELECT 4 month_number, 'apr' month_abr),
(SELECT 5 month_number, 'may' month_abr),
(SELECT 6 month_number, 'jun' month_abr)
) AS months
CROSS JOIN (
SELECT region FROM (
SELECT region FROM
(SELECT 'jan' month_abr, 'north' region, 100 revenue),
(SELECT 'feb' month_abr, 'north' region, 150 revenue),
(SELECT 'mar' month_abr, 'north' region, 250 revenue)
) GROUP BY region
) regions
LEFT JOIN (
SELECT month_abr, region, revenue FROM
(SELECT 'jan' month_abr, 'north' region, 100 revenue),
(SELECT 'feb' month_abr, 'north' region, 150 revenue),
(SELECT 'mar' month_abr, 'north' region, 250 revenue)
) AS revenues
ON months.month_abr = revenues.month_abr
AND regions.region = revenues.region
ORDER BY regions.region, months.month_number
结果如下
Row month_abr region revenue
1 jan north 100
2 feb north 150
3 mar north 250
4 apr north 0
5 may north 0
6 jun north 0
最后 - 下面是 BigQuery 标准 SQL 的外观
#standardSQL
WITH regions AS (
SELECT DISTINCT region FROM revenues
), months AS (
SELECT EXTRACT(MONTH FROM month) month_number,
LOWER(FORMAT_DATE('%b', month)) month_abr
FROM UNNEST(GENERATE_DATE_ARRAY(DATE '2010-01-01', DATE '2010-12-01', INTERVAL 1 MONTH)) month
)
SELECT month_abr, region, COALESCE(revenues.revenue, 0) revenue
FROM months
CROSS JOIN regions
LEFT JOIN revenues
USING(month_abr, region)
ORDER BY region, month_number
您可以使用问题中的虚拟数据进行测试，玩这个
#standardSQL
WITH revenues AS (
SELECT 'jan' month_abr, 'north' region, 100 revenue UNION ALL
SELECT 'feb', 'north', 150 UNION ALL
SELECT 'mar', 'north', 250
), regions AS (
SELECT DISTINCT region FROM revenues
), months AS (
SELECT EXTRACT(MONTH FROM month) month_number,
LOWER(FORMAT_DATE('%b', month)) month_abr
FROM UNNEST(GENERATE_DATE_ARRAY(DATE '2010-01-01', DATE '2010-12-01', INTERVAL 1 MONTH)) month
)
SELECT month_abr, region, COALESCE(revenues.revenue, 0) revenue
FROM months
CROSS JOIN regions
LEFT JOIN revenues
USING(month_abr, region)
ORDER BY region, month_number
您应该能够将上述应用到您的实际用例中
一种选择 - 使用您想要通过的值列表运行 LEFT/RIGHT JOIN。
让我们从缺少空值/零的查询开始：
#standardSQL
SELECT year, SUM(number) c
FROM `bigquery-public-data.usa_names.usa_1910_current`
WHERE name='Felipe'
AND year>2014
GROUP BY year
ORDER BY year
如果我们想为 2015 年之前的值获取 0：
SELECT b.year, IFNULL(c, 0) c
FROM (
SELECT year, SUM(number) c
FROM `bigquery-public-data.usa_names.usa_1910_current`
WHERE name='Felipe'
AND year>2014
GROUP BY year
) a
RIGHT JOIN (
SELECT year FROM UNNEST(GENERATE_ARRAY(2012, 2016)) year
) b
ON a.year=b.year
ORDER BY year
相关的子查询也可以节省时间：
SELECT year, (
SELECT IFNULL(SUM(number), 0)
FROM `bigquery-public-data.usa_names.usa_1910_current` a
WHERE name='Felipe'
AND year>2014
AND a.year=b.year
) c
FROM (SELECT year FROM UNNEST(GENERATE_ARRAY(2012, 2016)) year) b
ORDER BY year
