R 将多组测量列（宽格式）重塑为单列（长格式）
我有一个宽格式的数据框，在不同的日期范围内重复测量。在我的示例中，有三个不同的时段，都有相应的值。例如，第一次测量（R 将多组测量列（宽格式）重塑为单列（长格式）,r,reshape,tidyr,reshape2,r-faq,R,Reshape,Tidyr,Reshape2,R Faq,我有一个宽格式的数据框，在不同的日期范围内重复测量。在我的示例中，有三个不同的时段，都有相应的值。例如，第一次测量（Value1）是在DateRange1Start到DateRange1End期间测量的： ID DateRange1Start DateRange1End Value1 DateRange2Start DateRange2End Value2 DateRange3Start DateRange3End Value3 1 1/1/90 3/1/90 4.4 4/5/91 6/7/91
Value1DateRange1StartDateRange1EndID DateRange1Start DateRange1End Value1 DateRange2Start DateRange2End Value2 DateRange3Start DateRange3End Value3
1 1/1/90 3/1/90 4.4 4/5/91 6/7/91 6.2 5/5/95 6/6/96 3.3
ID DateRangeStart DateRangeEnd Value
1 1/1/90 3/1/90 4.4
1 4/5/91 6/7/91 6.2
1 5/5/95 6/6/96 3.3
我知道一定有办法用
重塑2熔化重铸tidyrRa <- read.table(textConnection("
ID DateRange1Start DateRange1End Value1 DateRange2Start DateRange2End Value2 DateRange3Start DateRange3End Value3
1 1/1/90 3/1/90 4.4 4/5/91 6/7/91 6.2 5/5/95 6/6/96 3.3
"),header=TRUE)
b1 <- a[,c(1:4)]; b2 <- a[,c(1,5:7)]; b3 <- a[,c(1,8:10)]
colnames(b1) <- colnames(b2) <- colnames(b3) <- c("ID","DateRangeStart","DateRangeEnd","Value")
b <- rbind(b1,b2,b3)
a
（根据Josh的建议添加了v.names。）以下是使用tidyr
解决问题的方法。这是其函数extract\u numeric（）
的一个有趣的用例，我用它从列名中提取组
library(dplyr)
library(tidyr)
a <- read.table(textConnection("
ID DateRange1Start DateRange1End Value1 DateRange2Start DateRange2End Value2 DateRange3Start DateRange3End Value3
1 1/1/90 3/1/90 4.4 4/5/91 6/7/91 6.2 5/5/95 6/6/96 3.3
"),header=TRUE)
a %>%
gather(variable,value,-ID) %>%
mutate(group = extract_numeric(variable)) %>%
mutate(variable = gsub("\\d","",x = variable)) %>%
spread(variable,value)
ID group DateRangeEnd DateRangeStart Value
1 1 1 3/1/90 1/1/90 4.4
2 1 2 6/7/91 4/5/91 6.2
3 1 3 6/6/96 5/5/95 3.3
库（dplyr）
图书馆（tidyr）
a%
聚集（变量，值，-ID）%%>%
变异（组=提取\数值（变量））%>%
突变（变量=gsub（“\\d”，“x=variable））%>%
排列（变量、值）
ID组DateRangeEnd DateRangeStart值
1 1 1 3/1/90 1/1/90 4.4
2 1 2 6/7/91 4/5/91 6.2
3 1 3 6/6/96 5/5/95 3.3
数据。表
的require(data.table)
melt(setDT(dat), id=1L,
measure=patterns("Start$", "End$", "^Value"),
value.name=c("DateRangeStart", "DateRangeEnd", "Value"))
# ID variable DateRangeStart DateRangeEnd Value
# 1: 1 1 1/1/90 3/1/90 4.4
# 2: 1 2 4/5/91 6/7/91 6.2
# 3: 1 3 5/5/95 6/6/96 3.3
或者，也可以通过列位置引用三组度量列：
melt(setDT(dat), id = 1L,
measure = list(c(2,5,8), c(3,6,9), c(4,7,10)),
value.name = c("DateRangeStart", "DateRangeEnd", "Value"))
l <- lapply(split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))),
setNames, c('DateRangeStart','DateRangeEnd','Value'))
data.frame(ID = d[,1], do.call(rbind, l), row.names = NULL)
library(dplyr)
library(purrr)
split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))) %>%
map_dfr(~set_names(., c('DateRangeStart','DateRangeEnd','Value'))) %>%
bind_cols(ID = rep(d$ID, nrow(.)/nrow(d)), .)
library(sjmisc)
to_long(d, keys = 'group',
values = c('DateRangeStart','DateRangeEnd','Value'),
c('DateRange1Start','DateRange2Start','DateRange3Start'),
c('DateRange1End','DateRange2End','DateRange3End'),
c('Value1','Value2','Value3'))[,-2]
l <- lapply(split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))),
setNames, c('DateRangeStart','DateRangeEnd','Value'))
data.frame(ID = d[,1],
group = rep(seq_along(l), each = nrow(d)),
do.call(rbind, l), row.names = NULL)
split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))) %>%
map_dfr(~set_names(., c('DateRangeStart','DateRangeEnd','Value'))) %>%
bind_cols(ID = rep(d$ID, nrow(.)/nrow(d)),
group = rep(1:(nrow(.)/nrow(d)), each = nrow(d)), .)
library(sjmisc)
to_long(d, keys = 'group', recode.key = TRUE,
values = c('DateRangeStart','DateRangeEnd','Value'),
c('DateRange1Start','DateRange2Start','DateRange3Start'),
c('DateRange1End','DateRange2End','DateRange3End'),
c('Value1','Value2','Value3'))
d <- read.table(text = "ID DateRange1Start DateRange1End Value1 DateRange2Start DateRange2End Value2 DateRange3Start DateRange3End Value3
1 1/1/90 3/1/90 4.4 4/5/91 6/7/91 6.2 5/5/95 6/6/96 3.3
2 1/2/90 3/2/90 6.1 4/6/91 6/8/91 3.2 5/5/97 6/6/98 1.3", header = TRUE, stringsAsFactors = FALSE)
tidyversel <- lapply(split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))),
setNames, c('DateRangeStart','DateRangeEnd','Value'))
data.frame(ID = d[,1], do.call(rbind, l), row.names = NULL)
library(dplyr)
library(purrr)
split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))) %>%
map_dfr(~set_names(., c('DateRangeStart','DateRangeEnd','Value'))) %>%
bind_cols(ID = rep(d$ID, nrow(.)/nrow(d)), .)
library(sjmisc)
to_long(d, keys = 'group',
values = c('DateRangeStart','DateRangeEnd','Value'),
c('DateRange1Start','DateRange2Start','DateRange3Start'),
c('DateRange1End','DateRange2End','DateRange3End'),
c('Value1','Value2','Value3'))[,-2]
l <- lapply(split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))),
setNames, c('DateRangeStart','DateRangeEnd','Value'))
data.frame(ID = d[,1],
group = rep(seq_along(l), each = nrow(d)),
do.call(rbind, l), row.names = NULL)
split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))) %>%
map_dfr(~set_names(., c('DateRangeStart','DateRangeEnd','Value'))) %>%
bind_cols(ID = rep(d$ID, nrow(.)/nrow(d)),
group = rep(1:(nrow(.)/nrow(d)), each = nrow(d)), .)
library(sjmisc)
to_long(d, keys = 'group', recode.key = TRUE,
values = c('DateRangeStart','DateRangeEnd','Value'),
c('DateRange1Start','DateRange2Start','DateRange3Start'),
c('DateRange1End','DateRange2End','DateRange3End'),
c('Value1','Value2','Value3'))
d <- read.table(text = "ID DateRange1Start DateRange1End Value1 DateRange2Start DateRange2End Value2 DateRange3Start DateRange3End Value3
1 1/1/90 3/1/90 4.4 4/5/91 6/7/91 6.2 5/5/95 6/6/96 3.3
2 1/2/90 3/2/90 6.1 4/6/91 6/8/91 3.2 5/5/97 6/6/98 1.3", header = TRUE, stringsAsFactors = FALSE)
sjmiscl <- lapply(split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))),
setNames, c('DateRangeStart','DateRangeEnd','Value'))
data.frame(ID = d[,1], do.call(rbind, l), row.names = NULL)
library(dplyr)
library(purrr)
split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))) %>%
map_dfr(~set_names(., c('DateRangeStart','DateRangeEnd','Value'))) %>%
bind_cols(ID = rep(d$ID, nrow(.)/nrow(d)), .)
library(sjmisc)
to_long(d, keys = 'group',
values = c('DateRangeStart','DateRangeEnd','Value'),
c('DateRange1Start','DateRange2Start','DateRange3Start'),
c('DateRange1End','DateRange2End','DateRange3End'),
c('Value1','Value2','Value3'))[,-2]
l <- lapply(split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))),
setNames, c('DateRangeStart','DateRangeEnd','Value'))
data.frame(ID = d[,1],
group = rep(seq_along(l), each = nrow(d)),
do.call(rbind, l), row.names = NULL)
split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))) %>%
map_dfr(~set_names(., c('DateRangeStart','DateRangeEnd','Value'))) %>%
bind_cols(ID = rep(d$ID, nrow(.)/nrow(d)),
group = rep(1:(nrow(.)/nrow(d)), each = nrow(d)), .)
library(sjmisc)
to_long(d, keys = 'group', recode.key = TRUE,
values = c('DateRangeStart','DateRangeEnd','Value'),
c('DateRange1Start','DateRange2Start','DateRange3Start'),
c('DateRange1End','DateRange2End','DateRange3End'),
c('Value1','Value2','Value3'))
d <- read.table(text = "ID DateRange1Start DateRange1End Value1 DateRange2Start DateRange2End Value2 DateRange3Start DateRange3End Value3
1 1/1/90 3/1/90 4.4 4/5/91 6/7/91 6.2 5/5/95 6/6/96 3.3
2 1/2/90 3/2/90 6.1 4/6/91 6/8/91 3.2 5/5/97 6/6/98 1.3", header = TRUE, stringsAsFactors = FALSE)
如果您还需要“组/时间”列，可以将上述方法调整为： 1）带基数R:
l <- lapply(split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))),
setNames, c('DateRangeStart','DateRangeEnd','Value'))
data.frame(ID = d[,1], do.call(rbind, l), row.names = NULL)
library(dplyr)
library(purrr)
split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))) %>%
map_dfr(~set_names(., c('DateRangeStart','DateRangeEnd','Value'))) %>%
bind_cols(ID = rep(d$ID, nrow(.)/nrow(d)), .)
library(sjmisc)
to_long(d, keys = 'group',
values = c('DateRangeStart','DateRangeEnd','Value'),
c('DateRange1Start','DateRange2Start','DateRange3Start'),
c('DateRange1End','DateRange2End','DateRange3End'),
c('Value1','Value2','Value3'))[,-2]
l <- lapply(split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))),
setNames, c('DateRangeStart','DateRangeEnd','Value'))
data.frame(ID = d[,1],
group = rep(seq_along(l), each = nrow(d)),
do.call(rbind, l), row.names = NULL)
split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))) %>%
map_dfr(~set_names(., c('DateRangeStart','DateRangeEnd','Value'))) %>%
bind_cols(ID = rep(d$ID, nrow(.)/nrow(d)),
group = rep(1:(nrow(.)/nrow(d)), each = nrow(d)), .)
library(sjmisc)
to_long(d, keys = 'group', recode.key = TRUE,
values = c('DateRangeStart','DateRangeEnd','Value'),
c('DateRange1Start','DateRange2Start','DateRange3Start'),
c('DateRange1End','DateRange2End','DateRange3End'),
c('Value1','Value2','Value3'))
d <- read.table(text = "ID DateRange1Start DateRange1End Value1 DateRange2Start DateRange2End Value2 DateRange3Start DateRange3End Value3
1 1/1/90 3/1/90 4.4 4/5/91 6/7/91 6.2 5/5/95 6/6/96 3.3
2 1/2/90 3/2/90 6.1 4/6/91 6/8/91 3.2 5/5/97 6/6/98 1.3", header = TRUE, stringsAsFactors = FALSE)
tidyversel <- lapply(split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))),
setNames, c('DateRangeStart','DateRangeEnd','Value'))
data.frame(ID = d[,1], do.call(rbind, l), row.names = NULL)
library(dplyr)
library(purrr)
split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))) %>%
map_dfr(~set_names(., c('DateRangeStart','DateRangeEnd','Value'))) %>%
bind_cols(ID = rep(d$ID, nrow(.)/nrow(d)), .)
library(sjmisc)
to_long(d, keys = 'group',
values = c('DateRangeStart','DateRangeEnd','Value'),
c('DateRange1Start','DateRange2Start','DateRange3Start'),
c('DateRange1End','DateRange2End','DateRange3End'),
c('Value1','Value2','Value3'))[,-2]
l <- lapply(split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))),
setNames, c('DateRangeStart','DateRangeEnd','Value'))
data.frame(ID = d[,1],
group = rep(seq_along(l), each = nrow(d)),
do.call(rbind, l), row.names = NULL)
split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))) %>%
map_dfr(~set_names(., c('DateRangeStart','DateRangeEnd','Value'))) %>%
bind_cols(ID = rep(d$ID, nrow(.)/nrow(d)),
group = rep(1:(nrow(.)/nrow(d)), each = nrow(d)), .)
library(sjmisc)
to_long(d, keys = 'group', recode.key = TRUE,
values = c('DateRangeStart','DateRangeEnd','Value'),
c('DateRange1Start','DateRange2Start','DateRange3Start'),
c('DateRange1End','DateRange2End','DateRange3End'),
c('Value1','Value2','Value3'))
d <- read.table(text = "ID DateRange1Start DateRange1End Value1 DateRange2Start DateRange2End Value2 DateRange3Start DateRange3End Value3
1 1/1/90 3/1/90 4.4 4/5/91 6/7/91 6.2 5/5/95 6/6/96 3.3
2 1/2/90 3/2/90 6.1 4/6/91 6/8/91 3.2 5/5/97 6/6/98 1.3", header = TRUE, stringsAsFactors = FALSE)
sjmiscl <- lapply(split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))),
setNames, c('DateRangeStart','DateRangeEnd','Value'))
data.frame(ID = d[,1], do.call(rbind, l), row.names = NULL)
library(dplyr)
library(purrr)
split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))) %>%
map_dfr(~set_names(., c('DateRangeStart','DateRangeEnd','Value'))) %>%
bind_cols(ID = rep(d$ID, nrow(.)/nrow(d)), .)
library(sjmisc)
to_long(d, keys = 'group',
values = c('DateRangeStart','DateRangeEnd','Value'),
c('DateRange1Start','DateRange2Start','DateRange3Start'),
c('DateRange1End','DateRange2End','DateRange3End'),
c('Value1','Value2','Value3'))[,-2]
l <- lapply(split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))),
setNames, c('DateRangeStart','DateRangeEnd','Value'))
data.frame(ID = d[,1],
group = rep(seq_along(l), each = nrow(d)),
do.call(rbind, l), row.names = NULL)
split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))) %>%
map_dfr(~set_names(., c('DateRangeStart','DateRangeEnd','Value'))) %>%
bind_cols(ID = rep(d$ID, nrow(.)/nrow(d)),
group = rep(1:(nrow(.)/nrow(d)), each = nrow(d)), .)
library(sjmisc)
to_long(d, keys = 'group', recode.key = TRUE,
values = c('DateRangeStart','DateRangeEnd','Value'),
c('DateRange1Start','DateRange2Start','DateRange3Start'),
c('DateRange1End','DateRange2End','DateRange3End'),
c('Value1','Value2','Value3'))
d <- read.table(text = "ID DateRange1Start DateRange1End Value1 DateRange2Start DateRange2End Value2 DateRange3Start DateRange3End Value3
1 1/1/90 3/1/90 4.4 4/5/91 6/7/91 6.2 5/5/95 6/6/96 3.3
2 1/2/90 3/2/90 6.1 4/6/91 6/8/91 3.2 5/5/97 6/6/98 1.3", header = TRUE, stringsAsFactors = FALSE)
已用数据：
l <- lapply(split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))),
setNames, c('DateRangeStart','DateRangeEnd','Value'))
data.frame(ID = d[,1], do.call(rbind, l), row.names = NULL)
library(dplyr)
library(purrr)
split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))) %>%
map_dfr(~set_names(., c('DateRangeStart','DateRangeEnd','Value'))) %>%
bind_cols(ID = rep(d$ID, nrow(.)/nrow(d)), .)
library(sjmisc)
to_long(d, keys = 'group',
values = c('DateRangeStart','DateRangeEnd','Value'),
c('DateRange1Start','DateRange2Start','DateRange3Start'),
c('DateRange1End','DateRange2End','DateRange3End'),
c('Value1','Value2','Value3'))[,-2]
l <- lapply(split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))),
setNames, c('DateRangeStart','DateRangeEnd','Value'))
data.frame(ID = d[,1],
group = rep(seq_along(l), each = nrow(d)),
do.call(rbind, l), row.names = NULL)
split.default(d[-1], cumsum(grepl('Start$', names(d)[-1]))) %>%
map_dfr(~set_names(., c('DateRangeStart','DateRangeEnd','Value'))) %>%
bind_cols(ID = rep(d$ID, nrow(.)/nrow(d)),
group = rep(1:(nrow(.)/nrow(d)), each = nrow(d)), .)
library(sjmisc)
to_long(d, keys = 'group', recode.key = TRUE,
values = c('DateRangeStart','DateRangeEnd','Value'),
c('DateRange1Start','DateRange2Start','DateRange3Start'),
c('DateRange1End','DateRange2End','DateRange3End'),
c('Value1','Value2','Value3'))
d <- read.table(text = "ID DateRange1Start DateRange1End Value1 DateRange2Start DateRange2End Value2 DateRange3Start DateRange3End Value3
1 1/1/90 3/1/90 4.4 4/5/91 6/7/91 6.2 5/5/95 6/6/96 3.3
2 1/2/90 3/2/90 6.1 4/6/91 6/8/91 3.2 5/5/97 6/6/98 1.3", header = TRUE, stringsAsFactors = FALSE)
d使用回收：
data.frame(ID = d[, 1],
DateRangeStart = unlist(d[, -1][, c(TRUE, FALSE, FALSE)]),
DateRangeEnd = unlist(d[, -1][, c(FALSE, TRUE, FALSE)]),
Value = unlist(d[, -1][, c(FALSE, FALSE, TRUE)]))
从1.0.0版起，使用tidyr软件包的函数pivot\u longer（）
可以将具有多个值/度量值列的宽格式重塑为长格式
这比之前的tidyr策略gather（）
优于spread（）
（请参见@AndrewMacDonald的答案），因为属性不再被删除（在下面的示例中，日期仍然是日期，数字仍然是数字）
library（“tidyr”）
图书馆（“magrittr”）
[4]“值\u 1”“日期范围开始\u 2”“日期范围结束\u 2”
#>[7]“值\u 2”“日期范围开始\u 3”“日期范围结束\u 3”
#>[10]“价值3”
枢轴_更长（a，
cols=-ID，
名称_to=c（“.value”，“group”），
#名称\u prefix=“DateRange”，
名称\u sep=“\u”）
#>#tibble:3 x 5
#>ID组DateRangeEnd DateRangeStart值
#>
#> 1 1 1 1990-01-03 1990-01-01 4.4
#> 2 1 2 1991-07-06 1991-05-04 6.2
#> 3 1 3 1996-06-06 1995-05-05 3.3
或者，可以使用提供更精细控制的轴心规范进行重塑（请参见下面的链接）：
spec%
构建\u更长\u规范（cols=-ID）%>%
dplyr:：transmute（.name=.name，
group=readr:：parse_编号（名称），
.value=stringr:：str|u extract（名称，“开始|结束|值”））
枢轴长度（a，等级=等级）
由（v0.2.1）于2019-03-26创建
另请参见：+1以展示variable=
参数的强大功能。接下来，v.names
参数还可以修饰这些列名，如下所示：v.names=c（“DateRangeStart”、“DateRangeEnd”、“Value”）
一般来说，您可能希望将来有一个更好的命名模式。例如，使用“DateRangeStart1”、“DateRangeEnd1”、“Value1”（换言之，“VariableMeasurement”）比将测量值固定在变量名称的某个位置更容易/更清晰。答案必须使用重塑2/melt/recast/tidyr
？（这个问题是一个更好、更一般的dupe目标，如果不是的话）这实际上是对一个稍微不同的问题的回答，即如何使用整洁的方法避免属性丢失。最初被接受的答案（使用stats:：restrape
）从未出现过这个问题。而最初的问题显然也没有日期分类变量。重塑函数保留了因子级别和日期类。我完全同意您的stats:：restrape（）
solution（+1）同样出色。正则表达式可以简化为名称（a）