This is a very fast solution for one-dimensional atomic vectors. It relies on match(), so it is compatible with NA:
x <- c("a", NA, "a", "c", "a", "b", NA, "c")
fn <- function(x) {
u <- unique.default(x)
out <- list(x = u, freq = .Internal(tabulate(match(x, u), length(u))))
class(out) <- "data.frame"
attr(out, "row.names") <- seq_along(u)
out
}
fn(x)
#> x freq
#> 1 a 3
#> 2 <NA> 2
#> 3 c 2
#> 4 b 1
You could also tweak the algorithm so that it doesn't run unique().
fn2 <- function(x) {
y <- match(x, x)
out <- list(x = x, freq = .Internal(tabulate(y, length(x)))[y])
class(out) <- "data.frame"
attr(out, "row.names") <- seq_along(x)
out
}
fn2(x)
#> x freq
#> 1 a 3
#> 2 <NA> 2
#> 3 a 3
#> 4 c 2
#> 5 a 3
#> 6 b 1
#> 7 <NA> 2
#> 8 c 2
In cases where that output is desirable, you probably don't even need it to re-return the original vector, and the second column is probably all you need. You can get that in one line with the pipe:
match(x, x) %>% `[`(tabulate(.), .)
#> [1] 3 2 3 2 3 1 2 2
There is a standard function in R for that
tabulate(numbers)
You can make a function to give you results.
# your list
numbers <- c(4,23,4,23,5,43,54,56,657,67,67,435,
453,435,324,34,456,56,567,65,34,435)
function1<-function(x){
if(x==value){return(1)}else{ return(0) }
}
# set your value here
value<-4
# make a vector which return 1 if it equal to your value, 0 else
vector<-sapply(numbers,function(x) function1(x))
sum(vector)
result: 2
One more way i find convenient is:
numbers <- c(4,23,4,23,5,43,54,56,657,67,67,435,453,435,324,34,456,56,567,65,34,435)
(s<-summary (as.factor(numbers)))
This converts the dataset to factor, and then summary() gives us the control totals (counts of the unique values).
Output is:
4 5 23 34 43 54 56 65 67 324 435 453 456 567 657
2 1 2 2 1 1 2 1 2 1 3 1 1 1 1
This can be stored as dataframe if preferred.
as.data.frame(cbind(Number = names(s),Freq = s), stringsAsFactors=F, row.names = 1:length(s))
here row.names has been used to rename row names. without using row.names, column names in s are used as row names in new dataframe
Output is:
Number Freq
1 4 2
2 5 1
3 23 2
4 34 2
5 43 1
6 54 1
7 56 2
8 65 1
9 67 2
10 324 1
11 435 3
12 453 1
13 456 1
14 567 1
15 657 1
here's one fast and dirty way:
x <- 23
length(subset(numbers, numbers==x))
This can be done with outer to get a metrix of equalities followed by rowSums, with an obvious meaning.
In order to have the counts and numbers in the same dataset, a data.frame is first created. This step is not needed if you want separate input and output.
df <- data.frame(No = numbers)
df$count <- rowSums(outer(df$No, df$No, FUN = `==`))
There are different ways of counting a specific elements
library(plyr)
numbers =c(4,23,4,23,5,43,54,56,657,67,67,435,453,435,7,65,34,435)
print(length(which(numbers==435)))
#Sum counts number of TRUE's in a vector
print(sum(numbers==435))
print(sum(c(TRUE, FALSE, TRUE)))
#count is present in plyr library
#o/p of count is a DataFrame, freq is 1 of the columns of data frame
print(count(numbers[numbers==435]))
print(count(numbers[numbers==435])[['freq']])
I would probably do something like this
length(which(numbers==x))
But really, a better way is
table(numbers)
The most direct way is sum(numbers == x).
numbers == x creates a logical vector which is TRUE at every location that x occurs, and when suming, the logical vector is coerced to numeric which converts TRUE to 1 and FALSE to 0.
However, note that for floating point numbers it's better to use something like: sum(abs(numbers - x) < 1e-6).
numbers <- c(4,23,4,23,5,43,54,56,657,67,67,435 453,435,324,34,456,56,567,65,34,435)
> length(grep(435, numbers))
[1] 3
> length(which(435 == numbers))
[1] 3
> require(plyr)
> df = count(numbers)
> df[df$x == 435, ]
x freq
11 435 3
> sum(435 == numbers)
[1] 3
> sum(grepl(435, numbers))
[1] 3
> sum(435 == numbers)
[1] 3
> tabulate(numbers)[435]
[1] 3
> table(numbers)['435']
435
3
> length(subset(numbers, numbers=='435'))
[1] 3
My preferred solution uses rle, which will return a value (the label, x in your example) and a length, which represents how many times that value appeared in sequence.
By combining rle with sort, you have an extremely fast way to count the number of times any value appeared. This can be helpful with more complex problems.
Example:
> numbers <- c(4,23,4,23,5,43,54,56,657,67,67,435,453,435,324,34,456,56,567,65,34,435)
> a <- rle(sort(numbers))
> a
Run Length Encoding
lengths: int [1:15] 2 1 2 2 1 1 2 1 2 1 ...
values : num [1:15] 4 5 23 34 43 54 56 65 67 324 ...
If the value you want doesn't show up, or you need to store that value for later, make a a data.frame.
> b <- data.frame(number=a$values, n=a$lengths)
> b
values n
1 4 2
2 5 1
3 23 2
4 34 2
5 43 1
6 54 1
7 56 2
8 65 1
9 67 2
10 324 1
11 435 3
12 453 1
13 456 1
14 567 1
15 657 1
I find it is rare that I want to know the frequency of one value and not all of the values, and rle seems to be the quickest way to get count and store them all.
There is also count(numbers) from plyr package. Much more convenient than table in my opinion.
Here is a way you could do it with dplyr:
library(tidyverse)
numbers <- c(4,23,4,23,5,43,54,56,657,67,67,435,
453,435,324,34,456,56,567,65,34,435)
ord <- seq(1:(length(numbers)))
df <- data.frame(ord,numbers)
df <- df %>%
count(numbers)
numbers n
<dbl> <int>
1 4 2
2 5 1
3 23 2
4 34 2
5 43 1
6 54 1
7 56 2
8 65 1
9 67 2
10 324 1
11 435 3
12 453 1
13 456 1
14 567 1
15 657 1
A method that is relatively fast on long vectors and gives a convenient output is to use lengths(split(numbers, numbers)) (note the S at the end of lengths):
# Make some integer vectors of different sizes
set.seed(123)
x <- sample.int(1e3, 1e4, replace = TRUE)
xl <- sample.int(1e3, 1e6, replace = TRUE)
xxl <-sample.int(1e3, 1e7, replace = TRUE)
# Number of times each value appears in x:
a <- lengths(split(x,x))
# Number of times the value 64 appears:
a["64"]
#~ 64
#~ 15
# Occurences of the first 10 values
a[1:10]
#~ 1 2 3 4 5 6 7 8 9 10
#~ 13 12 6 14 12 5 13 14 11 14
The output is simply a named vector.
The speed appears comparable to rle proposed by JBecker and even a bit faster on very long vectors. Here is a microbenchmark in R 3.6.2 with some of the functions proposed:
library(microbenchmark)
f1 <- function(vec) lengths(split(vec,vec))
f2 <- function(vec) table(vec)
f3 <- function(vec) rle(sort(vec))
f4 <- function(vec) plyr::count(vec)
microbenchmark(split = f1(x),
table = f2(x),
rle = f3(x),
plyr = f4(x))
#~ Unit: microseconds
#~ expr min lq mean median uq max neval cld
#~ split 402.024 423.2445 492.3400 446.7695 484.3560 2970.107 100 b
#~ table 1234.888 1290.0150 1378.8902 1333.2445 1382.2005 3203.332 100 d
#~ rle 227.685 238.3845 264.2269 245.7935 279.5435 378.514 100 a
#~ plyr 758.866 793.0020 866.9325 843.2290 894.5620 2346.407 100 c
microbenchmark(split = f1(xl),
table = f2(xl),
rle = f3(xl),
plyr = f4(xl))
#~ Unit: milliseconds
#~ expr min lq mean median uq max neval cld
#~ split 21.96075 22.42355 26.39247 23.24847 24.60674 82.88853 100 ab
#~ table 100.30543 104.05397 111.62963 105.54308 110.28732 168.27695 100 c
#~ rle 19.07365 20.64686 23.71367 21.30467 23.22815 78.67523 100 a
#~ plyr 24.33968 25.21049 29.71205 26.50363 27.75960 92.02273 100 b
microbenchmark(split = f1(xxl),
table = f2(xxl),
rle = f3(xxl),
plyr = f4(xxl))
#~ Unit: milliseconds
#~ expr min lq mean median uq max neval cld
#~ split 296.4496 310.9702 342.6766 332.5098 374.6485 421.1348 100 a
#~ table 1151.4551 1239.9688 1283.8998 1288.0994 1323.1833 1385.3040 100 d
#~ rle 399.9442 430.8396 464.2605 471.4376 483.2439 555.9278 100 c
#~ plyr 350.0607 373.1603 414.3596 425.1436 437.8395 506.0169 100 b
Importantly, the only function that also counts the number of missing values NA is plyr::count. These can also be obtained separately using sum(is.na(vec))
One option could be to use vec_count() function from the vctrs library:
vec_count(numbers)
key count
1 435 3
2 67 2
3 4 2
4 34 2
5 56 2
6 23 2
7 456 1
8 43 1
9 453 1
10 5 1
11 657 1
12 324 1
13 54 1
14 567 1
15 65 1
The default ordering puts the most frequent values at top. If looking for sorting according keys (a table()-like output):
vec_count(numbers, sort = "key")
key count
1 4 2
2 5 1
3 23 2
4 34 2
5 43 1
6 54 1
7 56 2
8 65 1
9 67 2
10 324 1
11 435 3
12 453 1
13 456 1
14 567 1
15 657 1
You can change the number to whatever you wish in following line
length(which(numbers == 4))
If you want to count the number of appearances subsequently, you can make use of the sapply function:
index<-sapply(1:length(numbers),function(x)sum(numbers[1:x]==numbers[x]))
cbind(numbers, index)
Output:
numbers index
[1,] 4 1
[2,] 23 1
[3,] 4 2
[4,] 23 2
[5,] 5 1
[6,] 43 1
[7,] 54 1
[8,] 56 1
[9,] 657 1
[10,] 67 1
[11,] 67 2
[12,] 435 1
[13,] 453 1
[14,] 435 2
[15,] 324 1
[16,] 34 1
[17,] 456 1
[18,] 56 2
[19,] 567 1
[20,] 65 1
[21,] 34 2
[22,] 435 3
Using table but without comparing with names:
numbers <- c(4,23,4,23,5,43,54,56,657,67,67,435)
x <- 67
numbertable <- table(numbers)
numbertable[as.character(x)]
#67
# 2
table is useful when you are using the counts of different elements several times. If you need only one count, use sum(numbers == x)
Source: Stackoverflow.com