Sample blockwise from clustered data
Examples
d <- data.frame(x=rnorm(5), z=rnorm(5), id=c(4,10,10,5,5), v=rnorm(5))
(dd <- blocksample(d,size=20,~id))
#> x z id v
#> 2 -0.9373884 0.4890758 1 -1.12402842
#> 3 1.0134409 -0.4148487 1 -0.22438290
#> 2.1 -0.9373884 0.4890758 2 -1.12402842
#> 3.1 1.0134409 -0.4148487 2 -0.22438290
#> 1 -0.2924015 1.4906009 3 1.06445737
#> 2.2 -0.9373884 0.4890758 4 -1.12402842
#> 3.2 1.0134409 -0.4148487 4 -0.22438290
#> 4 0.1894152 -0.1503866 5 0.07987716
#> 5 -0.6982603 -0.2859336 5 1.52257466
#> 4.1 0.1894152 -0.1503866 6 0.07987716
#> 5.1 -0.6982603 -0.2859336 6 1.52257466
#> 2.3 -0.9373884 0.4890758 7 -1.12402842
#> 3.3 1.0134409 -0.4148487 7 -0.22438290
#> 4.2 0.1894152 -0.1503866 8 0.07987716
#> 5.2 -0.6982603 -0.2859336 8 1.52257466
#> 4.3 0.1894152 -0.1503866 9 0.07987716
#> 5.3 -0.6982603 -0.2859336 9 1.52257466
#> 1.1 -0.2924015 1.4906009 10 1.06445737
#> 2.4 -0.9373884 0.4890758 11 -1.12402842
#> 3.4 1.0134409 -0.4148487 11 -0.22438290
#> 4.4 0.1894152 -0.1503866 12 0.07987716
#> 5.4 -0.6982603 -0.2859336 12 1.52257466
#> 4.5 0.1894152 -0.1503866 13 0.07987716
#> 5.5 -0.6982603 -0.2859336 13 1.52257466
#> 2.5 -0.9373884 0.4890758 14 -1.12402842
#> 3.5 1.0134409 -0.4148487 14 -0.22438290
#> 1.2 -0.2924015 1.4906009 15 1.06445737
#> 1.3 -0.2924015 1.4906009 16 1.06445737
#> 2.6 -0.9373884 0.4890758 17 -1.12402842
#> 3.6 1.0134409 -0.4148487 17 -0.22438290
#> 1.4 -0.2924015 1.4906009 18 1.06445737
#> 4.6 0.1894152 -0.1503866 19 0.07987716
#> 5.6 -0.6982603 -0.2859336 19 1.52257466
#> 4.7 0.1894152 -0.1503866 20 0.07987716
#> 5.7 -0.6982603 -0.2859336 20 1.52257466
attributes(dd)$id
#> [1] 10 10 10 10 4 10 10 5 5 5 5 10 10 5 5 5 5 4 10 10 5 5 5 5 10
#> [26] 10 4 4 10 10 4 5 5 5 5
if (FALSE) { # \dontrun{
blocksample(data.table::data.table(d),1e6,~id)
} # }
d <- data.frame(x=c(1,rnorm(9)),
z=rnorm(10),
id=c(4,10,10,5,5,4,4,5,10,5),
id2=c(1,1,2,1,2,1,1,1,1,2),
v=rnorm(10))
dsample(d,~id, size=2)
#> x z id id2 v id.1
#> 4 1.2373588 0.31202103 5 1 1.0172015 1
#> 5 0.3743871 2.15876995 5 2 -0.5020760 1
#> 8 0.4826865 1.33638222 5 1 -0.3415735 1
#> 10 -0.6877808 -1.16227692 5 2 -1.1133414 1
#> 2 -2.6551641 0.07859043 10 1 -0.8982185 2
#> 3 0.5862268 0.72370982 10 2 -0.1147617 2
#> 9 -0.8040275 0.70668573 10 1 0.4021691 2
dsample(d,.~id+id2)
#> x z v id
#> 3 0.5862268 0.72370982 -0.1147617 1
#> 4 1.2373588 0.31202103 1.0172015 2
#> 8 0.4826865 1.33638222 -0.3415735 2
#> 4.1 1.2373588 0.31202103 1.0172015 3
#> 8.1 0.4826865 1.33638222 -0.3415735 3
#> 4.2 1.2373588 0.31202103 1.0172015 4
#> 8.2 0.4826865 1.33638222 -0.3415735 4
#> 4.3 1.2373588 0.31202103 1.0172015 5
#> 8.3 0.4826865 1.33638222 -0.3415735 5
#> 4.4 1.2373588 0.31202103 1.0172015 6
#> 8.4 0.4826865 1.33638222 -0.3415735 6
#> 4.5 1.2373588 0.31202103 1.0172015 7
#> 8.5 0.4826865 1.33638222 -0.3415735 7
#> 2 -2.6551641 0.07859043 -0.8982185 8
#> 9 -0.8040275 0.70668573 0.4021691 8
#> 4.6 1.2373588 0.31202103 1.0172015 9
#> 8.6 0.4826865 1.33638222 -0.3415735 9
#> 2.1 -2.6551641 0.07859043 -0.8982185 10
#> 9.1 -0.8040275 0.70668573 0.4021691 10
dsample(d,x+z~id|x>0,size=5)
#> x z id
#> 1 1.0000000 0.5716432 1
#> 6 0.3351264 -0.1139183 1
#> 4 1.2373588 0.3120210 2
#> 5 0.3743871 2.1587699 2
#> 8 0.4826865 1.3363822 2
#> 1.1 1.0000000 0.5716432 3
#> 6.1 0.3351264 -0.1139183 3
#> 1.2 1.0000000 0.5716432 4
#> 6.2 0.3351264 -0.1139183 4
#> 3 0.5862268 0.7237098 5