我有麻烦重新安排以下数据帧:
set.seed(45)
dat1 <- data.frame(
name = rep(c("firstName", "secondName"), each=4),
numbers = rep(1:4, 2),
value = rnorm(8)
)
dat1
name numbers value
1 firstName 1 0.3407997
2 firstName 2 -0.7033403
3 firstName 3 -0.3795377
4 firstName 4 -0.7460474
5 secondName 1 -0.8981073
6 secondName 2 -0.3347941
7 secondName 3 -0.5013782
8 secondName 4 -0.1745357
我想重塑它，以便每个唯一的“name”变量都是一个行名，“值”作为该行的观察值，“数字”作为冒号。就像这样:
name 1 2 3 4
1 firstName 0.3407997 -0.7033403 -0.3795377 -0.7460474
5 secondName -0.8981073 -0.3347941 -0.5013782 -0.1745357
我试过熔化和铸造，还有其他一些方法，但似乎都不行。
对于tidyr，有pivot_wider()和pivot_longer()，它们分别被广义为从long -> wide或wide -> long进行重塑。使用OP的数据:
单列长>宽
library(tidyr)
dat1 %>%
pivot_wider(names_from = numbers, values_from = value)
# # A tibble: 2 x 5
# name `1` `2` `3` `4`
# <fct> <dbl> <dbl> <dbl> <dbl>
# 1 firstName 0.341 -0.703 -0.380 -0.746
# 2 secondName -0.898 -0.335 -0.501 -0.175
多列长>宽
Pivot_wider()还能够执行更复杂的枢轴操作。例如，你可以同时对多个列进行主元操作:
# create another column for showing the functionality
dat2 <- dat1 %>%
dplyr::rename(valA = value) %>%
dplyr::mutate(valB = valA * 2)
dat2 %>%
pivot_wider(names_from = numbers, values_from = c(valA, valB))
# # A tibble: 2 × 9
# name valA_1 valA_2 valA_3 valA_4 valB_1 valB_2 valB_3 valB_4
# <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
# 1 firstName 0.341 -0.703 -0.380 -0.746 0.682 -1.41 -0.759 -1.49
# 2 secondName -0.898 -0.335 -0.501 -0.175 -1.80 -0.670 -1.00 -0.349
在文档中可以找到更多的功能。
其他两种选择:
基本包:
df <- unstack(dat1, form = value ~ numbers)
rownames(df) <- unique(dat1$name)
df
sqldf包:
library(sqldf)
sqldf('SELECT name,
MAX(CASE WHEN numbers = 1 THEN value ELSE NULL END) x1,
MAX(CASE WHEN numbers = 2 THEN value ELSE NULL END) x2,
MAX(CASE WHEN numbers = 3 THEN value ELSE NULL END) x3,
MAX(CASE WHEN numbers = 4 THEN value ELSE NULL END) x4
FROM dat1
GROUP BY name')
如果考虑性能，另一个选择是使用数据。表格对reshape2的melt和dcast函数的扩展
(参考:使用data.tables进行高效重塑)
library(data.table)
setDT(dat1)
dcast(dat1, name ~ numbers, value.var = "value")
# name 1 2 3 4
# 1: firstName 0.1836433 -0.8356286 1.5952808 0.3295078
# 2: secondName -0.8204684 0.4874291 0.7383247 0.5757814
至于数据。表v1.9.6可以对多个列进行强制转换
## add an extra column
dat1[, value2 := value * 2]
## cast multiple value columns
dcast(dat1, name ~ numbers, value.var = c("value", "value2"))
# name value_1 value_2 value_3 value_4 value2_1 value2_2 value2_3 value2_4
# 1: firstName 0.1836433 -0.8356286 1.5952808 0.3295078 0.3672866 -1.6712572 3.190562 0.6590155
# 2: secondName -0.8204684 0.4874291 0.7383247 0.5757814 -1.6409368 0.9748581 1.476649 1.1515627
只使用dplyr和map。
library(dplyr)
library(purrr)
set.seed(45)
dat1 <- data.frame(
name = rep(c("firstName", "secondName"), each=4),
numbers = rep(1:4, 2), value = rnorm(8)
)
longer_to_wider <- function(data, name_from, value_from){
group <- colnames(data)[!(colnames(data) %in% c(name_from,value_from))]
data %>% group_by(.data[[group]]) %>%
summarise( name = list(.data[[name_from]]),
value = list(.data[[value_from]])) %>%
{
d <- data.frame(
name = .[[name_from]] %>% unlist() %>% unique()
)
e <- map_dfc(.[[group]],function(x){
y <- data_frame(
x = data %>% filter(.data[[group]] == x) %>% pull(value_from)
)
colnames(y) <- x
y
})
cbind(d,e)
}
}
longer_to_wider(dat1, "name", "value")
# name 1 2 3 4
# 1 firstName 0.3407997 -0.7033403 -0.3795377 -0.7460474
# 2 secondName -0.8981073 -0.3347941 -0.5013782 -0.1745357
