1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
|
# distinct() produces optimized SQL
Code
(out <- lf %>% head(2) %>% distinct(x, y))
Output
<SQL>
SELECT DISTINCT `q01`.*
FROM (
SELECT `df`.*
FROM `df`
LIMIT 2
) AS `q01`
# distinct respects window_order when .keep_all is TRUE
Code
lf %>% window_order(desc(y)) %>% distinct(x, .keep_all = TRUE)
Output
<SQL>
SELECT `x`, `y`
FROM (
SELECT
`df`.*,
ROW_NUMBER() OVER (PARTITION BY `x` ORDER BY `y` DESC) AS `col01`
FROM `df`
) AS `q01`
WHERE (`col01` = 1)
# distinct uses dummy window order when .keep_all is TRUE and no order is used
Code
lf %>% distinct(x, .keep_all = TRUE)
Output
<SQL>
SELECT `x`, `y`
FROM (
SELECT `df`.*, ROW_NUMBER() OVER (PARTITION BY `x` ORDER BY `x`) AS `col01`
FROM `df`
) AS `q01`
WHERE (`col01` = 1)
|
