Generating a sequence in R - r

I am working with a list in R that looks like this
[1] 0 0 4 4 0 4 0
now suppose that I want to generate a list of numbers corresponding to this list like this
[[1]]
[1] 1 1
[[2]]
[1] 2 2
[[3]]
[1] 3 6
[[4]]
[1] 7 10
[[5]]
[1] 11 11
[[6]]
[1] 12 15
[[7]]
[1] 16 16
So in other words, the first list gives the groups of a list of a sequence of numbers from 1 to 16 and the second list gives the start and end of each group.
This is probably easier to see if you consider the sequence
1 2 3-6 7-10 11 12-15 16
Is there an easy way to do this? I think I could do it using some sort of global index and lapply but I wanted to see if there were an easier way.


Here's one way
# alternate input suggested by #MichaelChirico
d = c(0,0,3,3,0,3,0)
# my preferred approach
library(data.table) # version 1.9.5+
Map(c,
seq_along(d)+shift(cumsum(d), type="lag", fill=0),
seq_along(d)+cumsum(d)
)
A similar variation by #akrun:
# alternate input, starting from OP's
d2 = c(0, 0, 4, 4, 0, 4, 0)
d2 = replace( d2, !d2, 1)
# #akrun's answer
Map(c, cumsum(d2)-d2+1, cumsum(d2))
And some more:
# my original answer
start = c(1,head(cumsum(d+1)+1,-1))
Map(c, start, start + d)
# another way
s = sequence(d+1)
Map(c, seq_along(s)[s==1], seq_along(s)[c(diff(s) < 1, TRUE)] )


Here's a slightly different approach:
x <- c(0,0,3,3,0,3,0)
f <- function(x) {
ee <- split(seq_len(sum(x+1)), rep.int(seq_along(x), x+1))
lapply(ee, range)
}
f(x)


Here's a function that'll do it, no way near as elegant as #Frank's answer:
mygenerator <- function(vec){
counter <- 1
outlist <- list()
for(i in 1:length(vec)){
if(vec[i] == 0){
outlist[[i]] <- c(counter, counter)
counter <- counter + 1
} else {
outlist[[i]] <- c(counter, counter + vec[i] - 1)
counter <- counter + vec[i]
}
}
outlist
}
mygenerator(c(0, 0, 4, 4, 0, 4, 0))
[[1]]
[1] 1 1
[[2]]
[1] 2 2
[[3]]
[1] 3 6
[[4]]
[1] 7 10
[[5]]
[1] 11 11
[[6]]
[1] 12 15
[[7]]
[1] 16 16

Related

Applying a function over batches of links - splitting a character vector into subsets [duplicate]

I have to split a vector into n chunks of equal size in R. I couldn't find any base function to do that. Also Google didn't get me anywhere. Here is what I came up with so far;
x <- 1:10
n <- 3
chunk <- function(x,n) split(x, factor(sort(rank(x)%%n)))
chunk(x,n)
$`0`
[1] 1 2 3
$`1`
[1] 4 5 6 7
$`2`
[1] 8 9 10

A one-liner splitting d into chunks of size 20:
split(d, ceiling(seq_along(d)/20))
More details: I think all you need is seq_along(), split() and ceiling():
> d <- rpois(73,5)
> d
[1] 3 1 11 4 1 2 3 2 4 10 10 2 7 4 6 6 2 1 1 2 3 8 3 10 7 4
[27] 3 4 4 1 1 7 2 4 6 0 5 7 4 6 8 4 7 12 4 6 8 4 2 7 6 5
[53] 4 5 4 5 5 8 7 7 7 6 2 4 3 3 8 11 6 6 1 8 4
> max <- 20
> x <- seq_along(d)
> d1 <- split(d, ceiling(x/max))
> d1
$`1`
[1] 3 1 11 4 1 2 3 2 4 10 10 2 7 4 6 6 2 1 1 2
$`2`
[1] 3 8 3 10 7 4 3 4 4 1 1 7 2 4 6 0 5 7 4 6
$`3`
[1] 8 4 7 12 4 6 8 4 2 7 6 5 4 5 4 5 5 8 7 7
$`4`
[1] 7 6 2 4 3 3 8 11 6 6 1 8 4

chunk2 <- function(x,n) split(x, cut(seq_along(x), n, labels = FALSE))

A simplified version:
n = 3
split(x, sort(x%%n))
NB: This will only work on numeric vectors.

Using base R's rep_len:
x <- 1:10
n <- 3
split(x, rep_len(1:n, length(x)))
# $`1`
# [1] 1 4 7 10
#
# $`2`
# [1] 2 5 8
#
# $`3`
# [1] 3 6 9
And as already mentioned if you want sorted indices, simply:
split(x, sort(rep_len(1:n, length(x))))
# $`1`
# [1] 1 2 3 4
#
# $`2`
# [1] 5 6 7
#
# $`3`
# [1] 8 9 10

Try the ggplot2 function, cut_number:
library(ggplot2)
x <- 1:10
n <- 3
cut_number(x, n) # labels = FALSE if you just want an integer result
#> [1] [1,4] [1,4] [1,4] [1,4] (4,7] (4,7] (4,7] (7,10] (7,10] (7,10]
#> Levels: [1,4] (4,7] (7,10]
# if you want it split into a list:
split(x, cut_number(x, n))
#> $`[1,4]`
#> [1] 1 2 3 4
#>
#> $`(4,7]`
#> [1] 5 6 7
#>
#> $`(7,10]`
#> [1] 8 9 10

This will split it differently to what you have, but is still quite a nice list structure I think:
chunk.2 <- function(x, n, force.number.of.groups = TRUE, len = length(x), groups = trunc(len/n), overflow = len%%n) {
if(force.number.of.groups) {
f1 <- as.character(sort(rep(1:n, groups)))
f <- as.character(c(f1, rep(n, overflow)))
} else {
f1 <- as.character(sort(rep(1:groups, n)))
f <- as.character(c(f1, rep("overflow", overflow)))
}
g <- split(x, f)
if(force.number.of.groups) {
g.names <- names(g)
g.names.ordered <- as.character(sort(as.numeric(g.names)))
} else {
g.names <- names(g[-length(g)])
g.names.ordered <- as.character(sort(as.numeric(g.names)))
g.names.ordered <- c(g.names.ordered, "overflow")
}
return(g[g.names.ordered])
}
Which will give you the following, depending on how you want it formatted:
> x <- 1:10; n <- 3
> chunk.2(x, n, force.number.of.groups = FALSE)
$`1`
[1] 1 2 3
$`2`
[1] 4 5 6
$`3`
[1] 7 8 9
$overflow
[1] 10
> chunk.2(x, n, force.number.of.groups = TRUE)
$`1`
[1] 1 2 3
$`2`
[1] 4 5 6
$`3`
[1] 7 8 9 10
Running a couple of timings using these settings:
set.seed(42)
x <- rnorm(1:1e7)
n <- 3
Then we have the following results:
> system.time(chunk(x, n)) # your function
user system elapsed
29.500 0.620 30.125
> system.time(chunk.2(x, n, force.number.of.groups = TRUE))
user system elapsed
5.360 0.300 5.663
Note: Changing as.factor() to as.character() made my function twice as fast.

If you don't like split() and you don't like matrix() (with its dangling NAs), there's this:
chunk <- function(x, n) (mapply(function(a, b) (x[a:b]), seq.int(from=1, to=length(x), by=n), pmin(seq.int(from=1, to=length(x), by=n)+(n-1), length(x)), SIMPLIFY=FALSE))
Like split(), it returns a list, but it doesn't waste time or space with labels, so it may be more performant.

A few more variants to the pile...
> x <- 1:10
> n <- 3
Note, that you don't need to use the factor function here, but you still want to sort o/w your first vector would be 1 2 3 10:
> chunk <- function(x, n) split(x, sort(rank(x) %% n))
> chunk(x,n)
$`0`
[1] 1 2 3
$`1`
[1] 4 5 6 7
$`2`
[1] 8 9 10
Or you can assign character indices, vice the numbers in left ticks above:
> my.chunk <- function(x, n) split(x, sort(rep(letters[1:n], each=n, len=length(x))))
> my.chunk(x, n)
$a
[1] 1 2 3 4
$b
[1] 5 6 7
$c
[1] 8 9 10
Or you can use plainword names stored in a vector. Note that using sort to get consecutive values in x alphabetizes the labels:
> my.other.chunk <- function(x, n) split(x, sort(rep(c("tom", "dick", "harry"), each=n, len=length(x))))
> my.other.chunk(x, n)
$dick
[1] 1 2 3
$harry
[1] 4 5 6
$tom
[1] 7 8 9 10

Yet another possibility is the splitIndices function from package parallel:
library(parallel)
splitIndices(20, 3)
Gives:
[[1]]
[1] 1 2 3 4 5 6 7
[[2]]
[1] 8 9 10 11 12 13
[[3]]
[1] 14 15 16 17 18 19 20
NB: this works only with numeric values though. If you want to split a character vector, you would need to do some indexing: lapply(splitIndices(20, 3), \(x) letters[1:20][x])

You could combine the split/cut, as suggested by mdsummer, with quantile to create even groups:
split(x,cut(x,quantile(x,(0:n)/n), include.lowest=TRUE, labels=FALSE))
This gives the same result for your example, but not for skewed variables.

split(x,matrix(1:n,n,length(x))[1:length(x)])
perhaps this is more clear, but the same idea:
split(x,rep(1:n, ceiling(length(x)/n),length.out = length(x)))
if you want it ordered,throw a sort around it

Here's another variant.
NOTE: with this sample you're specifying the CHUNK SIZE in the second parameter
all chunks are uniform, except for the last;
the last will at worst be smaller, never bigger than the chunk size.
chunk <- function(x,n)
{
f <- sort(rep(1:(trunc(length(x)/n)+1),n))[1:length(x)]
return(split(x,f))
}
#Test
n<-c(1,2,3,4,5,6,7,8,9,10,11)
c<-chunk(n,5)
q<-lapply(c, function(r) cat(r,sep=",",collapse="|") )
#output
1,2,3,4,5,|6,7,8,9,10,|11,|

I needed the same function and have read the previous solutions, however i also needed to have the unbalanced chunk to be at the end i.e if i have 10 elements to split them into vectors of 3 each, then my result should have vectors with 3,3,4 elements respectively. So i used the following (i left the code unoptimised for readability, otherwise no need to have many variables):
chunk <- function(x,n){
numOfVectors <- floor(length(x)/n)
elementsPerVector <- c(rep(n,numOfVectors-1),n+length(x) %% n)
elemDistPerVector <- rep(1:numOfVectors,elementsPerVector)
split(x,factor(elemDistPerVector))
}
set.seed(1)
x <- rnorm(10)
n <- 3
chunk(x,n)
$`1`
[1] -0.6264538 0.1836433 -0.8356286
$`2`
[1] 1.5952808 0.3295078 -0.8204684
$`3`
[1] 0.4874291 0.7383247 0.5757814 -0.3053884

Simple function for splitting a vector by simply using indexes - no need to over complicate this
vsplit <- function(v, n) {
l = length(v)
r = l/n
return(lapply(1:n, function(i) {
s = max(1, round(r*(i-1))+1)
e = min(l, round(r*i))
return(v[s:e])
}))
}

Sorry if this answer comes so late, but maybe it can be useful for someone else. Actually there is a very useful solution to this problem, explained at the end of ?split.
> testVector <- c(1:10) #I want to divide it into 5 parts
> VectorList <- split(testVector, 1:5)
> VectorList
$`1`
[1] 1 6
$`2`
[1] 2 7
$`3`
[1] 3 8
$`4`
[1] 4 9
$`5`
[1] 5 10

Credit to #Sebastian for this function
chunk <- function(x,y){
split(x, factor(sort(rank(row.names(x))%%y)))
}

If you don't like split() and you don't mind NAs padding out your short tail:
chunk <- function(x, n) { if((length(x)%%n)==0) {return(matrix(x, nrow=n))} else {return(matrix(append(x, rep(NA, n-(length(x)%%n))), nrow=n))} }
The columns of the returned matrix ([,1:ncol]) are the droids you are looking for.

I need a function that takes the argument of a data.table (in quotes) and another argument that is the upper limit on the number of rows in the subsets of that original data.table. This function produces whatever number of data.tables that upper limit allows for:
library(data.table)
split_dt <- function(x,y)
{
for(i in seq(from=1,to=nrow(get(x)),by=y))
{df_ <<- get(x)[i:(i + y)];
assign(paste0("df_",i),df_,inherits=TRUE)}
rm(df_,inherits=TRUE)
}
This function gives me a series of data.tables named df_[number] with the starting row from the original data.table in the name. The last data.table can be short and filled with NAs so you have to subset that back to whatever data is left. This type of function is useful because certain GIS software have limits on how many address pins you can import, for example. So slicing up data.tables into smaller chunks may not be recommended, but it may not be avoidable.

I have come up with this solution:
require(magrittr)
create.chunks <- function(x, elements.per.chunk){
# plain R version
# split(x, rep(seq_along(x), each = elements.per.chunk)[seq_along(x)])
# magrittr version - because that's what people use now
x %>% seq_along %>% rep(., each = elements.per.chunk) %>% extract(seq_along(x)) %>% split(x, .)
}
create.chunks(letters[1:10], 3)
$`1`
[1] "a" "b" "c"
$`2`
[1] "d" "e" "f"
$`3`
[1] "g" "h" "i"
$`4`
[1] "j"
The key is to use the seq(each = chunk.size) parameter so make it work. Using seq_along acts like rank(x) in my previous solution, but is actually able to produce the correct result with duplicated entries.

Here's yet another one, allowing you to control if you want the result ordered or not:
split_to_chunks <- function(x, n, keep.order=TRUE){
if(keep.order){
return(split(x, sort(rep(1:n, length.out = length(x)))))
}else{
return(split(x, rep(1:n, length.out = length(x))))
}
}
split_to_chunks(x = 1:11, n = 3)
$`1`
[1] 1 2 3 4
$`2`
[1] 5 6 7 8
$`3`
[1] 9 10 11
split_to_chunks(x = 1:11, n = 3, keep.order=FALSE)
$`1`
[1] 1 4 7 10
$`2`
[1] 2 5 8 11
$`3`
[1] 3 6 9

Not sure if this answers OP's question, but I think the %% can be useful here
df # some data.frame
N_CHUNKS <- 10
I_VEC <- 1:nrow(df)
df_split <- split(df, sort(I_VEC %% N_CHUNKS))

This splits into chunks of size ⌊n/k⌋+1 or ⌊n/k⌋ and does not use the O(n log n) sort.
get_chunk_id<-function(n, k){
r <- n %% k
s <- n %/% k
i<-seq_len(n)
1 + ifelse (i <= r * (s+1), (i-1) %/% (s+1), r + ((i - r * (s+1)-1) %/% s))
}
split(1:10, get_chunk_id(10,3))

Partion of a vector to a list [duplicate]

I have to split a vector into n chunks of equal size in R. I couldn't find any base function to do that. Also Google didn't get me anywhere. Here is what I came up with so far;
x <- 1:10
n <- 3
chunk <- function(x,n) split(x, factor(sort(rank(x)%%n)))
chunk(x,n)
$`0`
[1] 1 2 3
$`1`
[1] 4 5 6 7
$`2`
[1] 8 9 10

A one-liner splitting d into chunks of size 20:
split(d, ceiling(seq_along(d)/20))
More details: I think all you need is seq_along(), split() and ceiling():
> d <- rpois(73,5)
> d
[1] 3 1 11 4 1 2 3 2 4 10 10 2 7 4 6 6 2 1 1 2 3 8 3 10 7 4
[27] 3 4 4 1 1 7 2 4 6 0 5 7 4 6 8 4 7 12 4 6 8 4 2 7 6 5
[53] 4 5 4 5 5 8 7 7 7 6 2 4 3 3 8 11 6 6 1 8 4
> max <- 20
> x <- seq_along(d)
> d1 <- split(d, ceiling(x/max))
> d1
$`1`
[1] 3 1 11 4 1 2 3 2 4 10 10 2 7 4 6 6 2 1 1 2
$`2`
[1] 3 8 3 10 7 4 3 4 4 1 1 7 2 4 6 0 5 7 4 6
$`3`
[1] 8 4 7 12 4 6 8 4 2 7 6 5 4 5 4 5 5 8 7 7
$`4`
[1] 7 6 2 4 3 3 8 11 6 6 1 8 4

chunk2 <- function(x,n) split(x, cut(seq_along(x), n, labels = FALSE))

A simplified version:
n = 3
split(x, sort(x%%n))
NB: This will only work on numeric vectors.

Using base R's rep_len:
x <- 1:10
n <- 3
split(x, rep_len(1:n, length(x)))
# $`1`
# [1] 1 4 7 10
#
# $`2`
# [1] 2 5 8
#
# $`3`
# [1] 3 6 9
And as already mentioned if you want sorted indices, simply:
split(x, sort(rep_len(1:n, length(x))))
# $`1`
# [1] 1 2 3 4
#
# $`2`
# [1] 5 6 7
#
# $`3`
# [1] 8 9 10

Try the ggplot2 function, cut_number:
library(ggplot2)
x <- 1:10
n <- 3
cut_number(x, n) # labels = FALSE if you just want an integer result
#> [1] [1,4] [1,4] [1,4] [1,4] (4,7] (4,7] (4,7] (7,10] (7,10] (7,10]
#> Levels: [1,4] (4,7] (7,10]
# if you want it split into a list:
split(x, cut_number(x, n))
#> $`[1,4]`
#> [1] 1 2 3 4
#>
#> $`(4,7]`
#> [1] 5 6 7
#>
#> $`(7,10]`
#> [1] 8 9 10

This will split it differently to what you have, but is still quite a nice list structure I think:
chunk.2 <- function(x, n, force.number.of.groups = TRUE, len = length(x), groups = trunc(len/n), overflow = len%%n) {
if(force.number.of.groups) {
f1 <- as.character(sort(rep(1:n, groups)))
f <- as.character(c(f1, rep(n, overflow)))
} else {
f1 <- as.character(sort(rep(1:groups, n)))
f <- as.character(c(f1, rep("overflow", overflow)))
}
g <- split(x, f)
if(force.number.of.groups) {
g.names <- names(g)
g.names.ordered <- as.character(sort(as.numeric(g.names)))
} else {
g.names <- names(g[-length(g)])
g.names.ordered <- as.character(sort(as.numeric(g.names)))
g.names.ordered <- c(g.names.ordered, "overflow")
}
return(g[g.names.ordered])
}
Which will give you the following, depending on how you want it formatted:
> x <- 1:10; n <- 3
> chunk.2(x, n, force.number.of.groups = FALSE)
$`1`
[1] 1 2 3
$`2`
[1] 4 5 6
$`3`
[1] 7 8 9
$overflow
[1] 10
> chunk.2(x, n, force.number.of.groups = TRUE)
$`1`
[1] 1 2 3
$`2`
[1] 4 5 6
$`3`
[1] 7 8 9 10
Running a couple of timings using these settings:
set.seed(42)
x <- rnorm(1:1e7)
n <- 3
Then we have the following results:
> system.time(chunk(x, n)) # your function
user system elapsed
29.500 0.620 30.125
> system.time(chunk.2(x, n, force.number.of.groups = TRUE))
user system elapsed
5.360 0.300 5.663
Note: Changing as.factor() to as.character() made my function twice as fast.

If you don't like split() and you don't like matrix() (with its dangling NAs), there's this:
chunk <- function(x, n) (mapply(function(a, b) (x[a:b]), seq.int(from=1, to=length(x), by=n), pmin(seq.int(from=1, to=length(x), by=n)+(n-1), length(x)), SIMPLIFY=FALSE))
Like split(), it returns a list, but it doesn't waste time or space with labels, so it may be more performant.

A few more variants to the pile...
> x <- 1:10
> n <- 3
Note, that you don't need to use the factor function here, but you still want to sort o/w your first vector would be 1 2 3 10:
> chunk <- function(x, n) split(x, sort(rank(x) %% n))
> chunk(x,n)
$`0`
[1] 1 2 3
$`1`
[1] 4 5 6 7
$`2`
[1] 8 9 10
Or you can assign character indices, vice the numbers in left ticks above:
> my.chunk <- function(x, n) split(x, sort(rep(letters[1:n], each=n, len=length(x))))
> my.chunk(x, n)
$a
[1] 1 2 3 4
$b
[1] 5 6 7
$c
[1] 8 9 10
Or you can use plainword names stored in a vector. Note that using sort to get consecutive values in x alphabetizes the labels:
> my.other.chunk <- function(x, n) split(x, sort(rep(c("tom", "dick", "harry"), each=n, len=length(x))))
> my.other.chunk(x, n)
$dick
[1] 1 2 3
$harry
[1] 4 5 6
$tom
[1] 7 8 9 10

Yet another possibility is the splitIndices function from package parallel:
library(parallel)
splitIndices(20, 3)
Gives:
[[1]]
[1] 1 2 3 4 5 6 7
[[2]]
[1] 8 9 10 11 12 13
[[3]]
[1] 14 15 16 17 18 19 20
NB: this works only with numeric values though. If you want to split a character vector, you would need to do some indexing: lapply(splitIndices(20, 3), \(x) letters[1:20][x])

You could combine the split/cut, as suggested by mdsummer, with quantile to create even groups:
split(x,cut(x,quantile(x,(0:n)/n), include.lowest=TRUE, labels=FALSE))
This gives the same result for your example, but not for skewed variables.

split(x,matrix(1:n,n,length(x))[1:length(x)])
perhaps this is more clear, but the same idea:
split(x,rep(1:n, ceiling(length(x)/n),length.out = length(x)))
if you want it ordered,throw a sort around it

Here's another variant.
NOTE: with this sample you're specifying the CHUNK SIZE in the second parameter
all chunks are uniform, except for the last;
the last will at worst be smaller, never bigger than the chunk size.
chunk <- function(x,n)
{
f <- sort(rep(1:(trunc(length(x)/n)+1),n))[1:length(x)]
return(split(x,f))
}
#Test
n<-c(1,2,3,4,5,6,7,8,9,10,11)
c<-chunk(n,5)
q<-lapply(c, function(r) cat(r,sep=",",collapse="|") )
#output
1,2,3,4,5,|6,7,8,9,10,|11,|

I needed the same function and have read the previous solutions, however i also needed to have the unbalanced chunk to be at the end i.e if i have 10 elements to split them into vectors of 3 each, then my result should have vectors with 3,3,4 elements respectively. So i used the following (i left the code unoptimised for readability, otherwise no need to have many variables):
chunk <- function(x,n){
numOfVectors <- floor(length(x)/n)
elementsPerVector <- c(rep(n,numOfVectors-1),n+length(x) %% n)
elemDistPerVector <- rep(1:numOfVectors,elementsPerVector)
split(x,factor(elemDistPerVector))
}
set.seed(1)
x <- rnorm(10)
n <- 3
chunk(x,n)
$`1`
[1] -0.6264538 0.1836433 -0.8356286
$`2`
[1] 1.5952808 0.3295078 -0.8204684
$`3`
[1] 0.4874291 0.7383247 0.5757814 -0.3053884

Simple function for splitting a vector by simply using indexes - no need to over complicate this
vsplit <- function(v, n) {
l = length(v)
r = l/n
return(lapply(1:n, function(i) {
s = max(1, round(r*(i-1))+1)
e = min(l, round(r*i))
return(v[s:e])
}))
}

Sorry if this answer comes so late, but maybe it can be useful for someone else. Actually there is a very useful solution to this problem, explained at the end of ?split.
> testVector <- c(1:10) #I want to divide it into 5 parts
> VectorList <- split(testVector, 1:5)
> VectorList
$`1`
[1] 1 6
$`2`
[1] 2 7
$`3`
[1] 3 8
$`4`
[1] 4 9
$`5`
[1] 5 10

Credit to #Sebastian for this function
chunk <- function(x,y){
split(x, factor(sort(rank(row.names(x))%%y)))
}

If you don't like split() and you don't mind NAs padding out your short tail:
chunk <- function(x, n) { if((length(x)%%n)==0) {return(matrix(x, nrow=n))} else {return(matrix(append(x, rep(NA, n-(length(x)%%n))), nrow=n))} }
The columns of the returned matrix ([,1:ncol]) are the droids you are looking for.

I need a function that takes the argument of a data.table (in quotes) and another argument that is the upper limit on the number of rows in the subsets of that original data.table. This function produces whatever number of data.tables that upper limit allows for:
library(data.table)
split_dt <- function(x,y)
{
for(i in seq(from=1,to=nrow(get(x)),by=y))
{df_ <<- get(x)[i:(i + y)];
assign(paste0("df_",i),df_,inherits=TRUE)}
rm(df_,inherits=TRUE)
}
This function gives me a series of data.tables named df_[number] with the starting row from the original data.table in the name. The last data.table can be short and filled with NAs so you have to subset that back to whatever data is left. This type of function is useful because certain GIS software have limits on how many address pins you can import, for example. So slicing up data.tables into smaller chunks may not be recommended, but it may not be avoidable.

I have come up with this solution:
require(magrittr)
create.chunks <- function(x, elements.per.chunk){
# plain R version
# split(x, rep(seq_along(x), each = elements.per.chunk)[seq_along(x)])
# magrittr version - because that's what people use now
x %>% seq_along %>% rep(., each = elements.per.chunk) %>% extract(seq_along(x)) %>% split(x, .)
}
create.chunks(letters[1:10], 3)
$`1`
[1] "a" "b" "c"
$`2`
[1] "d" "e" "f"
$`3`
[1] "g" "h" "i"
$`4`
[1] "j"
The key is to use the seq(each = chunk.size) parameter so make it work. Using seq_along acts like rank(x) in my previous solution, but is actually able to produce the correct result with duplicated entries.

Here's yet another one, allowing you to control if you want the result ordered or not:
split_to_chunks <- function(x, n, keep.order=TRUE){
if(keep.order){
return(split(x, sort(rep(1:n, length.out = length(x)))))
}else{
return(split(x, rep(1:n, length.out = length(x))))
}
}
split_to_chunks(x = 1:11, n = 3)
$`1`
[1] 1 2 3 4
$`2`
[1] 5 6 7 8
$`3`
[1] 9 10 11
split_to_chunks(x = 1:11, n = 3, keep.order=FALSE)
$`1`
[1] 1 4 7 10
$`2`
[1] 2 5 8 11
$`3`
[1] 3 6 9

Not sure if this answers OP's question, but I think the %% can be useful here
df # some data.frame
N_CHUNKS <- 10
I_VEC <- 1:nrow(df)
df_split <- split(df, sort(I_VEC %% N_CHUNKS))

This splits into chunks of size ⌊n/k⌋+1 or ⌊n/k⌋ and does not use the O(n log n) sort.
get_chunk_id<-function(n, k){
r <- n %% k
s <- n %/% k
i<-seq_len(n)
1 + ifelse (i <= r * (s+1), (i-1) %/% (s+1), r + ((i - r * (s+1)-1) %/% s))
}
split(1:10, get_chunk_id(10,3))

Loop with table function in R

I am a very beginner with R. I have a question about the table function. I have a result like this :
table(my_vector)
1 2 3
11 23 7
And I want to extract elements from a matrix :
From 1 to 11 as my_matrix[1:11,]
Form 11+1 to 11+23 as my_matrix[12:34,]
Form 11+23+1 to 11+23+7 as my_matrix[35:41,]
How can I do a loop with this ?

Think this should do it
my_matrix <- matrix(rep(1:41, times=3), 41)
my_vector <- rep(1:3, times=c(11, 23, 7))
my_tab <- table(my_vector)
my_csum1 <- c(0, cumsum(my_tab)) + 1
my_csum2 <- cumsum(my_tab)
my_list <- list()
for (i in 1:length(my_csum2)) {
my_list[[i]] <- my_matrix[my_csum1[i]:my_csum2[i], ]
}
lapply(my_list, range)
# [[1]]
# [1] 1 11
# [[2]]
# [1] 12 34
# [[3]]
# [1] 35 41

How do I get the column name (or number) of a multi series zoo object when I apply by row?

I have a zoo object of 12 sets of monthly returns on stock tickers. I want to get the symbol, which is the name of the series, or at least the column, of each month's best performing stock. I've been trying to do this with applying the max function, by row. How do I get the column name?
#Apply 'max' function across each row. I need to get the col number out of this.
apply(tsPctChgs, 1, max, na.rm = TRUE)

The usual answer would be via which.max() however, do note that this will return only the first of the maximums if there are two or more observations taking the maximum value.
An alternative is which(x == max(x)), which would return all value taking the maximum in the result of a tie.
You can then use the index returned to select the series maximum. Handling NAs is covered below to try to keep the initial discussion simple.
require("zoo")
set.seed(1)
m <- matrix(runif(50), ncol = 5)
colnames(m) <- paste0("Series", seq_len(ncol(m)))
ind <- seq_len(nrow(m))
mz <- zoo(m, order.by = ind)
> apply(mz, 1, which.max)
1 2 3 4 5 6 7 8 9 10
3 5 5 1 4 1 1 2 3 2
> apply(mz, 1, function(x) which(x == max(x)))
1 2 3 4 5 6 7 8 9 10
3 5 5 1 4 1 1 2 3 2
So use that to select the series name
i1 <- apply(mz, 1, function(x) which(x == max(x)))
colnames(mz)[i1]
> i1 <- apply(mz, 1, function(x) which(x == max(x)))
> colnames(mz)[i1]
[1] "Series3" "Series5" "Series5" "Series1" "Series4" "Series1" "Series1"
[8] "Series2" "Series3" "Series2"
Handling tied maximums
To illustrate the different behaviour, copy the maximum from month 1 (series 3) into series 1
mz2 <- mz ## copy
mz2[1,1] <- mz[1,3]
mz2[1,]
> mz2[1,]
1 0.9347052 0.2059746 0.9347052 0.4820801 0.8209463
Now try the two approaches again
> apply(mz2, 1, which.max)
1 2 3 4 5 6 7 8 9 10
1 5 5 1 4 1 1 2 3 2
> apply(mz2, 1, function(x) which(x == max(x)))
$`1`
Series1 Series3
1 3
.... ## truncated output ###
Notice how which.max only returns the maximum in series 1.
To use this approach to select the series name, you need to apply something to the list returned by apply(), e.g.
i2 <- apply(mz2, 1, function(x) which(x == max(x)))
lapply(i2, function (i, zobj) colnames(zobj)[i], zobj = mz2)
$`1`
[1] "Series1" "Series3"
$`2`
[1] "Series5"
$`3`
[1] "Series5"
$`4`
[1] "Series1"
$`5`
[1] "Series4"
$`6`
[1] "Series1"
$`7`
[1] "Series1"
$`8`
[1] "Series2"
$`9`
[1] "Series3"
$`10`
[1] "Series2"
Handling NAs
As you have potential for NAs, I would do the following:
apply(mz, 1, which.max, na.rm = TRUE) ## as you did already
apply(mz, 1, function(x, na.rm = TRUE) {
if(na.rm) {
x <- x[!is.na(x)]
}
which(x == max(x))
})

Since apply converts to matrix, I would use rollapply with width=1:
require("zoo")
set.seed(1)
m <- matrix(runif(50), ncol=5)
mz <- setNames(zoo(m, seq(nrow(m))), paste0("Series",seq(ncol(m))))
rollapply(mz, 1, function(r) colnames(mz)[which.max(r)], by.column=FALSE)

Split a vector into chunks

I have to split a vector into n chunks of equal size in R. I couldn't find any base function to do that. Also Google didn't get me anywhere. Here is what I came up with so far;
x <- 1:10
n <- 3
chunk <- function(x,n) split(x, factor(sort(rank(x)%%n)))
chunk(x,n)
$`0`
[1] 1 2 3
$`1`
[1] 4 5 6 7
$`2`
[1] 8 9 10

A one-liner splitting d into chunks of size 20:
split(d, ceiling(seq_along(d)/20))
More details: I think all you need is seq_along(), split() and ceiling():
> d <- rpois(73,5)
> d
[1] 3 1 11 4 1 2 3 2 4 10 10 2 7 4 6 6 2 1 1 2 3 8 3 10 7 4
[27] 3 4 4 1 1 7 2 4 6 0 5 7 4 6 8 4 7 12 4 6 8 4 2 7 6 5
[53] 4 5 4 5 5 8 7 7 7 6 2 4 3 3 8 11 6 6 1 8 4
> max <- 20
> x <- seq_along(d)
> d1 <- split(d, ceiling(x/max))
> d1
$`1`
[1] 3 1 11 4 1 2 3 2 4 10 10 2 7 4 6 6 2 1 1 2
$`2`
[1] 3 8 3 10 7 4 3 4 4 1 1 7 2 4 6 0 5 7 4 6
$`3`
[1] 8 4 7 12 4 6 8 4 2 7 6 5 4 5 4 5 5 8 7 7
$`4`
[1] 7 6 2 4 3 3 8 11 6 6 1 8 4

chunk2 <- function(x,n) split(x, cut(seq_along(x), n, labels = FALSE))

A simplified version:
n = 3
split(x, sort(x%%n))
NB: This will only work on numeric vectors.

Using base R's rep_len:
x <- 1:10
n <- 3
split(x, rep_len(1:n, length(x)))
# $`1`
# [1] 1 4 7 10
#
# $`2`
# [1] 2 5 8
#
# $`3`
# [1] 3 6 9
And as already mentioned if you want sorted indices, simply:
split(x, sort(rep_len(1:n, length(x))))
# $`1`
# [1] 1 2 3 4
#
# $`2`
# [1] 5 6 7
#
# $`3`
# [1] 8 9 10

Try the ggplot2 function, cut_number:
library(ggplot2)
x <- 1:10
n <- 3
cut_number(x, n) # labels = FALSE if you just want an integer result
#> [1] [1,4] [1,4] [1,4] [1,4] (4,7] (4,7] (4,7] (7,10] (7,10] (7,10]
#> Levels: [1,4] (4,7] (7,10]
# if you want it split into a list:
split(x, cut_number(x, n))
#> $`[1,4]`
#> [1] 1 2 3 4
#>
#> $`(4,7]`
#> [1] 5 6 7
#>
#> $`(7,10]`
#> [1] 8 9 10

This will split it differently to what you have, but is still quite a nice list structure I think:
chunk.2 <- function(x, n, force.number.of.groups = TRUE, len = length(x), groups = trunc(len/n), overflow = len%%n) {
if(force.number.of.groups) {
f1 <- as.character(sort(rep(1:n, groups)))
f <- as.character(c(f1, rep(n, overflow)))
} else {
f1 <- as.character(sort(rep(1:groups, n)))
f <- as.character(c(f1, rep("overflow", overflow)))
}
g <- split(x, f)
if(force.number.of.groups) {
g.names <- names(g)
g.names.ordered <- as.character(sort(as.numeric(g.names)))
} else {
g.names <- names(g[-length(g)])
g.names.ordered <- as.character(sort(as.numeric(g.names)))
g.names.ordered <- c(g.names.ordered, "overflow")
}
return(g[g.names.ordered])
}
Which will give you the following, depending on how you want it formatted:
> x <- 1:10; n <- 3
> chunk.2(x, n, force.number.of.groups = FALSE)
$`1`
[1] 1 2 3
$`2`
[1] 4 5 6
$`3`
[1] 7 8 9
$overflow
[1] 10
> chunk.2(x, n, force.number.of.groups = TRUE)
$`1`
[1] 1 2 3
$`2`
[1] 4 5 6
$`3`
[1] 7 8 9 10
Running a couple of timings using these settings:
set.seed(42)
x <- rnorm(1:1e7)
n <- 3
Then we have the following results:
> system.time(chunk(x, n)) # your function
user system elapsed
29.500 0.620 30.125
> system.time(chunk.2(x, n, force.number.of.groups = TRUE))
user system elapsed
5.360 0.300 5.663
Note: Changing as.factor() to as.character() made my function twice as fast.

If you don't like split() and you don't like matrix() (with its dangling NAs), there's this:
chunk <- function(x, n) (mapply(function(a, b) (x[a:b]), seq.int(from=1, to=length(x), by=n), pmin(seq.int(from=1, to=length(x), by=n)+(n-1), length(x)), SIMPLIFY=FALSE))
Like split(), it returns a list, but it doesn't waste time or space with labels, so it may be more performant.

A few more variants to the pile...
> x <- 1:10
> n <- 3
Note, that you don't need to use the factor function here, but you still want to sort o/w your first vector would be 1 2 3 10:
> chunk <- function(x, n) split(x, sort(rank(x) %% n))
> chunk(x,n)
$`0`
[1] 1 2 3
$`1`
[1] 4 5 6 7
$`2`
[1] 8 9 10
Or you can assign character indices, vice the numbers in left ticks above:
> my.chunk <- function(x, n) split(x, sort(rep(letters[1:n], each=n, len=length(x))))
> my.chunk(x, n)
$a
[1] 1 2 3 4
$b
[1] 5 6 7
$c
[1] 8 9 10
Or you can use plainword names stored in a vector. Note that using sort to get consecutive values in x alphabetizes the labels:
> my.other.chunk <- function(x, n) split(x, sort(rep(c("tom", "dick", "harry"), each=n, len=length(x))))
> my.other.chunk(x, n)
$dick
[1] 1 2 3
$harry
[1] 4 5 6
$tom
[1] 7 8 9 10

Yet another possibility is the splitIndices function from package parallel:
library(parallel)
splitIndices(20, 3)
Gives:
[[1]]
[1] 1 2 3 4 5 6 7
[[2]]
[1] 8 9 10 11 12 13
[[3]]
[1] 14 15 16 17 18 19 20
NB: this works only with numeric values though. If you want to split a character vector, you would need to do some indexing: lapply(splitIndices(20, 3), \(x) letters[1:20][x])

You could combine the split/cut, as suggested by mdsummer, with quantile to create even groups:
split(x,cut(x,quantile(x,(0:n)/n), include.lowest=TRUE, labels=FALSE))
This gives the same result for your example, but not for skewed variables.

split(x,matrix(1:n,n,length(x))[1:length(x)])
perhaps this is more clear, but the same idea:
split(x,rep(1:n, ceiling(length(x)/n),length.out = length(x)))
if you want it ordered,throw a sort around it

Here's another variant.
NOTE: with this sample you're specifying the CHUNK SIZE in the second parameter
all chunks are uniform, except for the last;
the last will at worst be smaller, never bigger than the chunk size.
chunk <- function(x,n)
{
f <- sort(rep(1:(trunc(length(x)/n)+1),n))[1:length(x)]
return(split(x,f))
}
#Test
n<-c(1,2,3,4,5,6,7,8,9,10,11)
c<-chunk(n,5)
q<-lapply(c, function(r) cat(r,sep=",",collapse="|") )
#output
1,2,3,4,5,|6,7,8,9,10,|11,|

I needed the same function and have read the previous solutions, however i also needed to have the unbalanced chunk to be at the end i.e if i have 10 elements to split them into vectors of 3 each, then my result should have vectors with 3,3,4 elements respectively. So i used the following (i left the code unoptimised for readability, otherwise no need to have many variables):
chunk <- function(x,n){
numOfVectors <- floor(length(x)/n)
elementsPerVector <- c(rep(n,numOfVectors-1),n+length(x) %% n)
elemDistPerVector <- rep(1:numOfVectors,elementsPerVector)
split(x,factor(elemDistPerVector))
}
set.seed(1)
x <- rnorm(10)
n <- 3
chunk(x,n)
$`1`
[1] -0.6264538 0.1836433 -0.8356286
$`2`
[1] 1.5952808 0.3295078 -0.8204684
$`3`
[1] 0.4874291 0.7383247 0.5757814 -0.3053884

Simple function for splitting a vector by simply using indexes - no need to over complicate this
vsplit <- function(v, n) {
l = length(v)
r = l/n
return(lapply(1:n, function(i) {
s = max(1, round(r*(i-1))+1)
e = min(l, round(r*i))
return(v[s:e])
}))
}

Sorry if this answer comes so late, but maybe it can be useful for someone else. Actually there is a very useful solution to this problem, explained at the end of ?split.
> testVector <- c(1:10) #I want to divide it into 5 parts
> VectorList <- split(testVector, 1:5)
> VectorList
$`1`
[1] 1 6
$`2`
[1] 2 7
$`3`
[1] 3 8
$`4`
[1] 4 9
$`5`
[1] 5 10

Credit to #Sebastian for this function
chunk <- function(x,y){
split(x, factor(sort(rank(row.names(x))%%y)))
}

If you don't like split() and you don't mind NAs padding out your short tail:
chunk <- function(x, n) { if((length(x)%%n)==0) {return(matrix(x, nrow=n))} else {return(matrix(append(x, rep(NA, n-(length(x)%%n))), nrow=n))} }
The columns of the returned matrix ([,1:ncol]) are the droids you are looking for.

I need a function that takes the argument of a data.table (in quotes) and another argument that is the upper limit on the number of rows in the subsets of that original data.table. This function produces whatever number of data.tables that upper limit allows for:
library(data.table)
split_dt <- function(x,y)
{
for(i in seq(from=1,to=nrow(get(x)),by=y))
{df_ <<- get(x)[i:(i + y)];
assign(paste0("df_",i),df_,inherits=TRUE)}
rm(df_,inherits=TRUE)
}
This function gives me a series of data.tables named df_[number] with the starting row from the original data.table in the name. The last data.table can be short and filled with NAs so you have to subset that back to whatever data is left. This type of function is useful because certain GIS software have limits on how many address pins you can import, for example. So slicing up data.tables into smaller chunks may not be recommended, but it may not be avoidable.

I have come up with this solution:
require(magrittr)
create.chunks <- function(x, elements.per.chunk){
# plain R version
# split(x, rep(seq_along(x), each = elements.per.chunk)[seq_along(x)])
# magrittr version - because that's what people use now
x %>% seq_along %>% rep(., each = elements.per.chunk) %>% extract(seq_along(x)) %>% split(x, .)
}
create.chunks(letters[1:10], 3)
$`1`
[1] "a" "b" "c"
$`2`
[1] "d" "e" "f"
$`3`
[1] "g" "h" "i"
$`4`
[1] "j"
The key is to use the seq(each = chunk.size) parameter so make it work. Using seq_along acts like rank(x) in my previous solution, but is actually able to produce the correct result with duplicated entries.

Here's yet another one, allowing you to control if you want the result ordered or not:
split_to_chunks <- function(x, n, keep.order=TRUE){
if(keep.order){
return(split(x, sort(rep(1:n, length.out = length(x)))))
}else{
return(split(x, rep(1:n, length.out = length(x))))
}
}
split_to_chunks(x = 1:11, n = 3)
$`1`
[1] 1 2 3 4
$`2`
[1] 5 6 7 8
$`3`
[1] 9 10 11
split_to_chunks(x = 1:11, n = 3, keep.order=FALSE)
$`1`
[1] 1 4 7 10
$`2`
[1] 2 5 8 11
$`3`
[1] 3 6 9

Not sure if this answers OP's question, but I think the %% can be useful here
df # some data.frame
N_CHUNKS <- 10
I_VEC <- 1:nrow(df)
df_split <- split(df, sort(I_VEC %% N_CHUNKS))

This splits into chunks of size ⌊n/k⌋+1 or ⌊n/k⌋ and does not use the O(n log n) sort.
get_chunk_id<-function(n, k){
r <- n %% k
s <- n %/% k
i<-seq_len(n)
1 + ifelse (i <= r * (s+1), (i-1) %/% (s+1), r + ((i - r * (s+1)-1) %/% s))
}
split(1:10, get_chunk_id(10,3))

Resources