我设法找到的大多数答案都需要指定要融化的每一列的名称。当我在表中有数百到数千列时，这很难处理。这是一个适用于任意宽表的答案。
它利用动态 SQL 并自动从数据模式中提取多个列名，整理命令字符串，然后评估该字符串。这是为了模仿 Python pandas.melt() / R reshape2::melt() 行为。
由于 UDF 的一些不良属性，我故意不创建用户定义的函数。根据您的使用方式，您可能想要也可能不想这样做。
输入：
id0 id1 _2020_05_27 _2020_05_28
1 1 11 12
1 2 13 14
2 1 15 16
2 2 17 18
输出：
id0 id1 date value
1 2 _2020_05_27 13
1 2 _2020_05_28 14
2 2 _2020_05_27 17
2 2 _2020_05_28 18
1 1 _2020_05_27 11
1 1 _2020_05_28 12
2 1 _2020_05_27 15
2 1 _2020_05_28 16
#standardSQL
-- PANDAS MELT FUNCTION IN GOOGLE BIGQUERY
-- author: Luna Huang
-- email: lunahuang@google.com
-- run this script with Google BigQuery Web UI in the Cloud Console
-- this piece of code functions like the pandas melt function
-- pandas.melt(id_vars, value_vars, var_name, value_name, col_level=None)
-- without utilizing user defined functions (UDFs)
-- see below for where to input corresponding arguments
DECLARE cmd STRING;
DECLARE subcmd STRING;
SET cmd = ("""
WITH original AS (
-- query to retrieve the original table
%s
),
nested AS (
SELECT
[
-- sub command to be automatically generated
%s
] as s,
-- equivalent to id_vars in pandas.melt()
%s,
FROM original
)
SELECT
-- equivalent to id_vars in pandas.melt()
%s,
-- equivalent to var_name in pandas.melt()
s.key AS %s,
-- equivalent to value_name in pandas.melt()
s.value AS %s,
FROM nested
CROSS JOIN UNNEST(nested.s) AS s
""");
SET subcmd = ("""
WITH
columns AS (
-- query to retrieve the column names
-- equivalent to value_vars in pandas.melt()
-- the resulting table should have only one column
-- with the name: column_name
%s
),
scs AS (
SELECT FORMAT("STRUCT('%%s' as key, %%s as value)", column_name, column_name) AS sc
FROM columns
)
SELECT ARRAY_TO_STRING(ARRAY (SELECT sc FROM scs), ",\\n")
""");
-- -- -- EXAMPLE BELOW -- -- --
-- SET UP AN EXAMPLE TABLE --
CREATE OR REPLACE TABLE `tmp.example`
(
id0 INT64,
id1 INT64,
_2020_05_27 INT64,
_2020_05_28 INT64,
);
INSERT INTO `tmp.example` VALUES (1, 1, 11, 12);
INSERT INTO `tmp.example` VALUES (1, 2, 13, 14);
INSERT INTO `tmp.example` VALUES (2, 1, 15, 16);
INSERT INTO `tmp.example` VALUES (2, 2, 17, 18);
-- MELTING STARTS --
-- execute these two command to melt the table
-- the first generates the STRUCT commands
-- and saves a string in subcmd
EXECUTE IMMEDIATE FORMAT(
-- please do not change this argument
subcmd,
-- query to retrieve the column names
-- equivalent to value_vars in pandas.melt()
-- the resulting table should have only one column
-- with the name: column_name
"""
SELECT column_name
FROM `tmp.INFORMATION_SCHEMA.COLUMNS`
WHERE (table_name = "example") AND (column_name NOT IN ("id0", "id1"))
"""
) INTO subcmd;
-- the second implements the melting
EXECUTE IMMEDIATE FORMAT(
-- please do not change this argument
cmd,
-- query to retrieve the original table
"""
SELECT *
FROM `tmp.example`
""",
-- please do not change this argument
subcmd,
-- equivalent to id_vars in pandas.melt()
-- !!please type these twice!!
"id0, id1", "id0, id1",
-- equivalent to var_name in pandas.melt()
"date",
-- equivalent to value_name in pandas.melt()
"value"
);