Spark SQL----内置函数Window Functions
- Window Functions
例子：
-- cume_dist
SELECT a, b, cume_dist() OVER (PARTITION BY a ORDER BY b) FROM VALUES ('A1', 2), ('A1', 1), ('A2', 3), ('A1', 1) tab(a, b);
+---+---+--------------------------------------------------------------------------------------------------------------+
| a| b|cume_dist() OVER (PARTITION BY a ORDER BY b ASC NULLS FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)|
+---+---+--------------------------------------------------------------------------------------------------------------+
| A1| 1| 0.6666666666666666|
| A1| 1| 0.6666666666666666|
| A1| 2| 1.0|
| A2| 3| 1.0|
+---+---+--------------------------------------------------------------------------------------------------------------+
-- dense_rank
SELECT a, b, dense_rank(b) OVER (PARTITION BY a ORDER BY b) FROM VALUES ('A1', 2), ('A1', 1), ('A2', 3), ('A1', 1) tab(a, b);
+---+---+--------------------------------------------------------------------------------------------------------------+
| a| b|DENSE_RANK() OVER (PARTITION BY a ORDER BY b ASC NULLS FIRST ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)|
+---+---+--------------------------------------------------------------------------------------------------------------+
| A1| 1| 1|
| A1| 1| 1|
| A1| 2| 2|
| A2| 3| 1|
+---+---+--------------------------------------------------------------------------------------------------------------+
-- lag
SELECT a, b, lag(b) OVER (PARTITION BY a ORDER BY b) FROM VALUES ('A1', 2), ('A1', 1), ('A2', 3), ('A1', 1) tab(a, b);
+---+---+-----------------------------------------------------------------------------------------------------------+
| a| b|lag(b, 1, NULL) OVER (PARTITION BY a ORDER BY b ASC NULLS FIRST ROWS BETWEEN -1 FOLLOWING AND -1 FOLLOWING)|
+---+---+-----------------------------------------------------------------------------------------------------------+
| A1| 1| NULL|
| A1| 1| 1|
| A1| 2| 1|
| A2| 3| NULL|
+---+---+-----------------------------------------------------------------------------------------------------------+
-- lead
SELECT a, b, lead(b) OVER (PARTITION BY a ORDER BY b) FROM VALUES ('A1', 2), ('A1', 1), ('A2', 3), ('A1', 1) tab(a, b);
+---+---+----------------------------------------------------------------------------------------------------------+
| a| b|lead(b, 1, NULL) OVER (PARTITION BY a ORDER BY b ASC NULLS FIRST ROWS BETWEEN 1 FOLLOWING AND 1 FOLLOWING)|
+---+---+----------------------------------------------------------------------------------------------------------+
| A1| 1| 1|
| A1| 1| 2|
| A1| 2| NULL|
| A2| 3| NULL|
+---+---+----------------------------------------------------------------------------------------------------------+
-- nth_value
SELECT a, b, nth_value(b, 2) OVER (PARTITION BY a ORDER BY b) FROM VALUES ('A1', 2), ('A1', 1), ('A2', 3), ('A1', 1) tab(a, b);
+---+---+------------------------------------------------------------------------------------------------------------------+
| a| b|nth_value(b, 2) OVER (PARTITION BY a ORDER BY b ASC NULLS FIRST RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)|
+---+---+------------------------------------------------------------------------------------------------------------------+
| A1| 1| 1|
| A1| 1| 1|
| A1| 2| 1|
| A2| 3| NULL|
+---+---+------------------------------------------------------------------------------------------------------------------+
-- ntile
SELECT a, b, ntile(2) OVER (PARTITION BY a ORDER BY b) FROM VALUES ('A1', 2), ('A1', 1), ('A2', 3), ('A1', 1) tab(a, b);
+---+---+----------------------------------------------------------------------------------------------------------+
| a| b|ntile(2) OVER (PARTITION BY a ORDER BY b ASC NULLS FIRST ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)|
+---+---+----------------------------------------------------------------------------------------------------------+
| A1| 1| 1|
| A1| 1| 1|
| A1| 2| 2|
| A2| 3| 1|
+---+---+----------------------------------------------------------------------------------------------------------+
-- percent_rank
SELECT a, b, percent_rank(b) OVER (PARTITION BY a ORDER BY b) FROM VALUES ('A1', 2), ('A1', 1), ('A2', 3), ('A1', 1) tab(a, b);
+---+---+----------------------------------------------------------------------------------------------------------------+
| a| b|PERCENT_RANK() OVER (PARTITION BY a ORDER BY b ASC NULLS FIRST ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)|
+---+---+----------------------------------------------------------------------------------------------------------------+
| A1| 1| 0.0|
| A1| 1| 0.0|
| A1| 2| 1.0|
| A2| 3| 0.0|
+---+---+----------------------------------------------------------------------------------------------------------------+
-- rank
SELECT a, b, rank(b) OVER (PARTITION BY a ORDER BY b) FROM VALUES ('A1', 2), ('A1', 1), ('A2', 3), ('A1', 1) tab(a, b);
+---+---+--------------------------------------------------------------------------------------------------------+
| a| b|RANK() OVER (PARTITION BY a ORDER BY b ASC NULLS FIRST ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)|
+---+---+--------------------------------------------------------------------------------------------------------+
| A1| 1| 1|
| A1| 1| 1|
| A1| 2| 3|
| A2| 3| 1|
+---+---+--------------------------------------------------------------------------------------------------------+
-- row_number
SELECT a, b, row_number() OVER (PARTITION BY a ORDER BY b) FROM VALUES ('A1', 2), ('A1', 1), ('A2', 3), ('A1', 1) tab(a, b);
+---+---+--------------------------------------------------------------------------------------------------------------+
| a| b|row_number() OVER (PARTITION BY a ORDER BY b ASC NULLS FIRST ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW)|
+---+---+--------------------------------------------------------------------------------------------------------------+
| A1| 1| 1|
| A1| 1| 2|
| A1| 2| 3|
| A2| 3| 1|
+---+---+--------------------------------------------------------------------------------------------------------------+