计算特定元素有不同的方法

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']])

这是一维原子向量的快速解。它依赖于match()，所以它与NA兼容:

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

您还可以调整算法，使其不运行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

在需要该输出的情况下，您甚至可能不需要它来重新返回原始向量，而第二列可能就是您所需要的全部。你可以用pipe在一行中得到:

match(x, x) %>% `[`(tabulate(.), .)

#> [1] 3 2 3 2 3 1 2 2

另外一个我觉得方便的方法是:

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)))

这将数据集转换为因子，然后summary()为我们提供控制总数(唯一值的计数)。

输出是:

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 

如果愿意，可以将其存储为数据帧。

as.data.frame(cbind(Number = names(s)，Freq = s)， stringsAsFactors=F, row.names = 1:length(s))

这里row.names用于重命名行名。 在不使用row.names的情况下，s中的列名被用作new dataframe中的行名

输出是:

     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

计算特定元素有不同的方法

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']])

一种相对快速处理长向量并提供方便输出的方法是使用长度(split(numbers, numbers))(注意长度后面的S):

# 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 

输出只是一个命名向量。 速度似乎可以与JBecker提出的rle相媲美，甚至在非常长的向量上更快。下面是R 3.6.2中的一个微基准测试，其中包含了一些提议的功能:

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  

重要的是，唯一计算缺失值NA数量的函数是plyr::count。这些也可以使用sum(is.na(vec))单独获得。

如果你想计算随后出现的次数，你可以使用sapply函数:

index<-sapply(1:length(numbers),function(x)sum(numbers[1:x]==numbers[x]))
cbind(numbers, index)

输出:

        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