Subset vectors and tables (data.frames and matrix) based on the
frequency of the values (of the vector or a column of the table), and a type
of inequality (less than and greater than).
Usage
nsubset(x, ...)
# Default S3 method
nsubset(x, n, comp = c(">=", ">", "<", "<="), na.rm = TRUE, ...)
# S3 method for class 'data.frame'
nsubset(
x,
col,
n,
comp = c(">=", "<=", ">", "<", "=="),
na.rm = TRUE,
select,
drop = FALSE,
...
)
# S3 method for class 'matrix'
nsubset(
x,
col,
n,
comp = c(">=", "<=", ">", "<", "=="),
na.rm = TRUE,
select,
drop = FALSE,
...
)Arguments
- x
An object to be subsetted, i.e. a vector of atomic type ('logical', 'integer', 'numeric', 'complex', 'character' and 'raw'), a factor, a
data.frameor amatrix.- ...
Further arguments passed to or from other methods.
- n
An integer; either a single value or the same number of values than returned by
table(x)/table(x[, "col"]).- comp
The sign of the inequality, one of
">="(default),">","<"or"<=".- na.rm
Logical; whether NAs should be removed (default) or not (in which case, they will be considered as a value of their own).
- col
Name of the column which is used to compute frequencies (with or without quotes).
- select
Expression, indicating columns to select from a data frame.
- drop
Passed on to
[indexing operator.
Author
Mathieu Basille mathieu@basille.org
Examples
## Simples examples and NAs:
set.seed(42)
bla <- rpois(100, 4)
bla[(1:9)*10] <- NA
bla
#> [1] 7 7 3 6 5 4 5 2 5 NA 4 5 7 3 4 7 8 2 4 NA 7 2 9 7 1
#> [26] 4 3 7 4 NA 5 6 3 5 0 6 0 2 7 NA 3 4 1 8 3 8 6 5 8 NA
#> [51] 3 3 3 5 1 5 5 2 3 NA 5 9 5 4 6 2 3 6 5 NA 1 2 2 4 2
#> [76] 5 0 3 4 NA 4 2 3 5 5 4 2 1 1 NA 5 0 2 7 7 5 3 4 5 4
table(bla, useNA = "ifany")
#> bla
#> 0 1 2 3 4 5 6 7 8 9 <NA>
#> 4 6 12 14 14 19 6 10 4 2 9
nsubset(bla, 5)
#> [1] 7 7 3 6 5 4 5 2 5 4 5 7 3 4 7 2 4 7 2 7 1 4 3 7 4 5 6 3 5 6 2 7 3 4 1 3 6 5
#> [39] 3 3 3 5 1 5 5 2 3 5 5 4 6 2 3 6 5 1 2 2 4 2 5 3 4 4 2 3 5 5 4 2 1 1 5 2 7 7
#> [77] 5 3 4 5 4
nsubset(bla, 14)
#> [1] 3 5 4 5 5 4 5 3 4 4 4 3 4 5 3 5 3 4 3 5 3 3 3 5 5 5 3 5 5 4 3 5 4 5 3 4 4 3
#> [39] 5 5 4 5 5 3 4 5 4
nsubset(bla, 5, comp = "<")
#> [1] 8 9 0 0 8 8 8 9 0 0
nsubset(bla, 5, na.rm = FALSE)
#> [1] 7 7 3 6 5 4 5 2 5 NA 4 5 7 3 4 7 2 4 NA 7 2 7 1 4 3
#> [26] 7 4 NA 5 6 3 5 6 2 7 NA 3 4 1 3 6 5 NA 3 3 3 5 1 5 5
#> [51] 2 3 NA 5 5 4 6 2 3 6 5 NA 1 2 2 4 2 5 3 4 NA 4 2 3 5
#> [76] 5 4 2 1 1 NA 5 2 7 7 5 3 4 5 4
## Factors and n provided for each value:
set.seed(42)
(bli <- factor(LETTERS[sample(1:10, size = 100, replace = TRUE)]))
#> [1] A E A I J D B J A H G D I E D J B C I I D E E D B H C J A J H F J H D D F
#> [38] B E D B H B C H G A E J B F F B D C F E B G F J J H E A A G D J I D I C E
#> [75] H E F B B H A B E H G H E D I D G J B E F C F A I I
#> Levels: A B C D E F G H I J
table(bli)
#> bli
#> A B C D E F G H I J
#> 9 13 6 13 13 9 6 11 9 11
factor(nsubset(bli, n = 7:16))
#> [1] A E A D B A D E D B D E E D B A D D B E D B B A E B B D E B E A A D D E E B
#> [39] B A B E E D D B E A
#> Levels: A B D E
## Data frames:
set.seed(42)
bla <- data.frame(value = rnorm(100), group = sample(letters[1:4],
size = 100, replace = TRUE, prob = (1:4) * 10))
table(bla$group)
#>
#> a b c d
#> 7 16 28 49
bli <- nsubset(bla, group, 25)
head(bli)
#> value group
#> 2 -0.56469817 c
#> 4 0.63286260 c
#> 5 0.40426832 d
#> 6 -0.10612452 c
#> 8 -0.09465904 c
#> 9 2.01842371 d
table(bli$group)
#>
#> c d
#> 28 49
nsubset(bla, group, 25, comp = ">", select = 1, drop = TRUE)
#> [1] -0.56469817 0.63286260 0.40426832 -0.10612452 -0.09465904 2.01842371
#> [7] -0.06271410 1.30486965 2.28664539 -1.38886070 -0.27878877 -0.13332134
#> [13] -0.28425292 -2.65645542 -2.44046693 -0.30663859 -1.78130843 -0.17191736
#> [19] 1.89519346 -0.25726938 -1.76316309 0.46009735 -0.63999488 0.45545012
#> [25] 0.70483734 1.03510352 -0.60892638 -0.78445901 -2.41420765 0.03612261
#> [31] 0.20599860 -0.36105730 0.75816324 -0.72670483 -1.36828104 0.43281803
#> [37] -0.81139318 1.44410126 -0.43144620 0.32192527 -0.78383894 1.57572752
#> [43] 0.64289931 0.08976065 0.67928882 0.08983289 -2.99309008 0.28488295
#> [49] 0.18523056 0.58182373 -0.72729206 1.30254263 1.03850610 -1.04311894
#> [55] 0.62351816 -0.95352336 0.58099650 0.76817874 0.46376759 -0.88577630
#> [61] -1.09978090 1.51270701 0.25792144 0.08844023 -1.19432890 0.61199690
#> [67] -0.21713985 -0.18275671 0.93334633 0.82177311 0.65034856 1.39111046
#> [73] -1.11078888 -0.86079259 -1.45921400 0.07998255 0.65320434
nsubset(bla, group, 25, comp = ">", select = group, drop = TRUE)
#> [1] "c" "c" "d" "c" "c" "d" "d" "c" "c" "d" "d" "c" "c" "d" "c" "c" "d" "c" "d"
#> [20] "d" "d" "d" "d" "d" "d" "d" "d" "d" "c" "c" "d" "c" "d" "d" "c" "c" "d" "d"
#> [39] "c" "d" "d" "d" "c" "d" "d" "c" "c" "c" "d" "d" "c" "d" "d" "d" "c" "d" "d"
#> [58] "d" "c" "c" "d" "c" "d" "d" "d" "d" "c" "d" "d" "d" "d" "d" "d" "d" "c" "d"
#> [77] "d"
## Fast computation:
set.seed(42)
bla <- rpois(1e7, 4)
table(bla)
#> bla
#> 0 1 2 3 4 5 6 7 8 9
#> 183869 732303 1463918 1953614 1954018 1562489 1041924 596057 298141 132588
#> 10 11 12 13 14 15 16 17 18
#> 52921 19180 6343 1909 516 154 45 9 2
system.time(table(nsubset(bla, 1e7)))
#> user system elapsed
#> 0.478 0.243 0.720
bla <- data.frame(value = rnorm(1e7), group = sample(letters[1:4],
size = 1e7, replace = TRUE, prob = (1:4) * 10))
table(bla$group)
#>
#> a b c d
#> 999413 2000466 2999466 4000655
system.time(bli <- nsubset(bla, group, 25))
#> user system elapsed
#> 1.553 0.667 2.226