База R
Использовать агрегат по числовым переменным и таблицу / prop.table по фактору.
ag <- aggregate(cbind(value1, value2) ~ group, data,
function(x) c(min = min(x), max = max(x)))
tab12 <- as.data.frame.matrix(setNames(as.data.frame(t(ag[-1])),
ag[[1]]))
counts <- table(data$group)
tab3 <- prop.table(table(group = data$value3, value3 = data$group), 2)
rownames(tab3) <- paste("value3", rownames(tab3), sep = " = ")
rbind(tab12, n = counts, as.data.frame.matrix(tab3))
дает следующее
0 1
value1.min 1.0 2.0
value1.max 9.0 10.0
value2.min 1.0 2.0
value2.max 9.0 10.0
n 10.0 10.0
value3 = 1 0.4 0.4
value3 = 2 0.2 0.4
value3 = 3 0.4 0.2
sqldf
Эта альтернатива немного утомительна, но проста:
library(sqldf)
res <- sqldf('select
[group],
min(value1) [value1.min],
max(value1) [value1.max],
min(value2) [value2.min],
max(value2) [value2.max],
count(*) n,
avg(value3 = 1) [value3 == 1],
avg(value3 = 2) [value3 == 2],
avg(value3 = 3) [value3 == 3]
from data
group by [group]')
setNames(as.data.frame(t(res[-1])), res$group)
дает:
0 1
value1.min 1.0 2.0
value1.max 9.0 10.0
value2.min 1.0 2.0
value2.max 9.0 10.0
n 10.0 10.0
value3 == 1 0.4 0.4
value3 == 2 0.2 0.4
value3 == 3 0.4 0.2
skimr
Используя пакет skimr, мы можем сделать это:
library(dplyr)
library(skimr)
library(tidyr)
# L <- list("fraction = 1" = function(x) mean(x == 1),
# "fraction = 2" = function(x) mean(x == 2),
# "fraction = 3" = function(x) mean(x == 3))
levs <- levels(data$value3)
L <- lapply(levs, function(lv) function(x) mean(x == lv))
names(L) <- paste("fraction =", levs)
skim_with(integer = list(min = min, max = max),
factor = c(L, n = length), append = FALSE)
data %>%
group_by(group) %>%
skim %>%
ungroup %>%
select(group, variable, stat, value) %>%
spread(group, value)
дает следующее:
# A tibble: 8 x 4
variable stat `0` `1`
<chr> <chr> <dbl> <dbl>
1 value1 max 9 10
2 value1 min 1 2
3 value2 max 9 10
4 value2 min 1 2
5 value3 fracion = 1 0.4 0.4
6 value3 fracion = 2 0.2 0.4
7 value3 fracion = 3 0.4 0.2
8 value3 n 10 10
Обновление
Пересмотренное базовое решение; добавлены решения sqldf и skimr. Улучшенное решение скимра.