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。
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
简单多了!
devtools::install_github("yikeshu0611/onetree") #install onetree package
library(onetree)
widedata=reshape_toWide(data = dat1,id = "name",j = "numbers",value.var.prefix = "value")
widedata
name value1 value2 value3 value4
firstName 0.3407997 -0.7033403 -0.3795377 -0.7460474
secondName -0.8981073 -0.3347941 -0.5013782 -0.1745357
如果你想从宽返回到长,只改变宽为长,不改变对象。
reshape_toLong(data = widedata,id = "name",j = "numbers",value.var.prefix = "value")
name numbers value
firstName 1 0.3407997
secondName 1 -0.8981073
firstName 2 -0.7033403
secondName 2 -0.3347941
firstName 3 -0.3795377
secondName 3 -0.5013782
firstName 4 -0.7460474
secondName 4 -0.1745357
将三列数据框架重塑为矩阵(“长”到“宽”格式)。这个问题已经结束了,所以我在这里写了一个替代解。
我找到了另一种解决方案,可能对寻找将三列转换为矩阵的人有用。我指的是去耦(2.3.2)包。以下摘自他们的网站
生成一种表,其中行来自id_cols,列来自names_from,值来自values_from。
使用
pivot_wider_profile(
data,
id_cols,
names_from,
values_from,
values_fill = NA,
to_matrix = FALSE,
to_sparse = FALSE,
...
)
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