如何统计多个列中唯一类别值的出现频率并按年龄分组

Question

我有如下数据集：

Age      Monday Tuesday Wednesday
6-9        a     b        c
6-9        b     a        c
6-9        b     c        a
9-10       c     c        b
9-10       c     a        b

我想要找出a，b，c在不同年龄组中的总频率，使用R如下：

Age    a     b    c
6-9    3     3    3
9-10   1     2    3

Answer 1

我们可以获得更长格式的数据，count它们，并再次转换为宽格式。

library(dplyr)
library(tidyr)

df %>%
  pivot_longer(cols = -Age) %>%
  count(Age, value) %>%
  pivot_wider(names_from = value, values_from = n)

#  Age       a     b     c
#  <fct> <int> <int> <int>
#1 6-9       3     3     3
#2 9-10      1     2     3

data

df <- structure(list(Age = structure(c(1L, 1L, 1L, 2L, 2L), .Label = c("6-9", 
"9-10"), class = "factor"), Monday = structure(c(1L, 2L, 2L, 
3L, 3L), .Label = c("a", "b", "c"), class = "factor"), Tuesday = structure(c(2L, 
1L, 3L, 3L, 1L), .Label = c("a", "b", "c"), class = "factor"), 
Wednesday = structure(c(3L, 3L, 1L, 2L, 2L), .Label = c("a", 
"b", "c"), class = "factor")), class = "data.frame", row.names = c(NA, -5L))

Answer 2

给定输入数据df为

df <- structure(list(Age = structure(c(1L, 1L, 1L, 2L, 2L), .Label = c("6-9", 
"9-10"), class = "factor"), Monday = structure(c(1L, 2L, 2L, 
3L, 3L), .Label = c("a", "b", "c"), class = "factor"), Tuesday = structure(c(2L, 
1L, 3L, 3L, 1L), .Label = c("a", "b", "c"), class = "factor"), 
Wednesday = structure(c(3L, 3L, 1L, 2L, 2L), .Label = c("a", 
"b", "c"), class = "factor")), class = "data.frame", row.names = c(NA, -5L))

然后，如果您计划使用base R，以下内容可能会有所帮助

# make a list of categorized by Age
lst <- split(df,df$Age)
# combine the list of data frame 
zlst <- do.call(rbind,sapply(seq_along(lst), function(k) cbind(data.frame(Age = names(lst)[k]), t(as.data.frame.factor(table(unlist(lst[[k]][,-1]))))),simplify = F))
# rename the row names 
rownames(zlst) <- seq(nrow(zlst))

这最终给出了：

> zlst
   Age a b c
1  6-9 3 3 3
2 9-10 1 2 3

Answer 3

我们可以只使用base R中的table

table(rep(df$Age, 3), unlist(df[-1]))
#       a b c
#  6-9  3 3 3
#  9-10 1 2 3

数据

df <- structure(list(Age = structure(c(1L, 1L, 1L, 2L, 2L), .Label = c("6-9", 
"9-10"), class = "factor"), Monday = structure(c(1L, 2L, 2L, 
3L, 3L), .Label = c("a", "b", "c"), class = "factor"), Tuesday = structure(c(2L, 
1L, 3L, 3L, 1L), .Label = c("a", "b", "c"), class = "factor"), 
Wednesday = structure(c(3L, 3L, 1L, 2L, 2L), .Label = c("a", 
"b", "c"), class = "factor")), class = "data.frame", row.names = c(NA, -5L))