R 如何根据条件提取列名?
考虑这个简单的例子R 如何根据条件提取列名?,r,dplyr,purrr,R,Dplyr,Purrr,考虑这个简单的例子 mytest <- data_frame(group = c('a', 'a', 'a', 'b', 'b', 'b'), x = c(NA,NA,NA,5,6,7), other_var = c(NA, NA, NA, 1,2,3), y = c(3,5,6,NA,NA,NA), another_var
mytest <- data_frame(group = c('a', 'a', 'a', 'b', 'b', 'b'),
x = c(NA,NA,NA,5,6,7),
other_var = c(NA, NA, NA, 1,2,3),
y = c(3,5,6,NA,NA,NA),
another_var = c(1,2,3, NA,NA,NA),
label_x = c('hello','hello','hello','world','world','world'),
label_y =c('bada','bada','bada','boom','boom','boom'),
label_other_var = c('ak','ak','ak','run','run','run'),
label_another_var = c('noo','noo','noo','bie','bie','bie'))
# A tibble: 6 x 9
group x other_var y another_var label_x label_y label_other_var label_another_var
<chr> <dbl> <dbl> <dbl> <dbl> <chr> <chr> <chr> <chr>
1 a NA NA 3 1 hello bada ak noo
2 a NA NA 5 2 hello bada ak noo
3 a NA NA 6 3 hello bada ak noo
4 b 5 1 NA NA world boom run bie
5 b 6 2 NA NA world boom run bie
6 b 7 3 NA NA world boom run bie
事实上,以a组为例。只有一个非缺失变量是y和另一个_变量。但是,y的名称是bada,如标签_y变量所示,另一个_变量的名称是noo。b的理由也一样
我不知道在跑步后如何通过地图调用来实现这一点
mytest %>% group_by(group) %>% nest()
# A tibble: 2 x 2
group data
<chr> <list>
1 a <tibble [3 x 8]>
2 b <tibble [3 x 8]>
有什么想法吗?
谢谢
编辑:最初的,较小的,tibble提议如下
mytest <- data_frame(group = c('a', 'a', 'a', 'b', 'b', 'b'),
+ x = c(NA,NA,NA,5,6,7),
+ y = c(3,5,6,NA,NA,NA),
+ label_x = c('hello','hello','hello','world','world','world'),
+ label_y =c('bada','bada','bada','boom','boom','boom'))
按嵌套分组后,使用map循环“data”,通过提取第一个非NA元素总结“label”列,将其收集到一个列,同时删除NA NA.rm=TRUE,选择“var”列,然后在仅保留感兴趣的列后执行unnest
mytest %>%
group_by(group) %>%
nest %>%
mutate(var = map(data, ~
.x %>%
summarise(label_x = label_x[!is.na(x)][1],
label_y = label_y[!is.na(y)][1]) %>%
gather(key, var, na.rm = TRUE) %>%
select(var))) %>%
select(-data) %>%
unnest
# A tibble: 2 x 2#
# group var
# <chr> <chr>
#1 a bada
#2 b world
这将输出您想要的结果:
mytest <- data_frame(group = c('a', 'a', 'a', 'b', 'b', 'b'),
x = c(NA,NA,NA,5,6,7),
y = c(3,5,6,NA,NA,NA),
label_x = c('hello','hello','hello','world','world','world'),
label_y =c('bada','bada','bada','boom','boom','boom'))
extract_good_colnames <- function(df, subgroup){
subset <- filter(df, group == subgroup)
if(sum(is.na(subset$x)) > 0){
colname = 'label_y'
}else if(sum(is.na(subset$y)) > 0){
colname = 'label_x'
}
return(tibble(group = subgroup, var = as.character(subset[1, colname])))
}
groups <- unique(mytest$group)
map_df(groups, function(x) extract_good_colnames(mytest, x))
嗨,阿克伦,这很好,但我不能真正概括。也就是说,在我的dataframe中,有许多不同的变量具有不同的名称。但是,标签变量的形式始终为label_X,其中X是给定的变量。我正在考虑在这里使用summary_,但没有看到一条清晰的道路。。。有什么想法吗?谢谢@ℕʘʘḆḽḘ 我正要问你这件事。如果您有一个相应的标签列,实际的列名是后缀part,那么我们可以通过循环列的名称来完成。是的,让我创建一个稍微大一点的示例,这样循环就更有意义了。再次感谢!完成!再次感谢,是的,这在现实生活中非常有用:@ℕʘʘḆḽḘ 更新后,您还可以保留原始数据集并将其作为更新,这样我就不必更改原始答案。我会更新答案好的,我也可以添加旧答案
nm1 <- unique(sub("label_", "", setdiff(names(mytest), "group")))
nm2 <- paste0("label_", nm1)
mytest %>%
group_by(group) %>%
nest %>%
mutate(var = map(data, ~
map2_chr(.x %>%
select(nm1),
.x %>%
select(nm2), ~
.y[!is.na(.x)][1]) %>%
na.omit %>%
tibble(var = .))) %>%
select(-data) %>%
unnest
# A tibble: 4 x 2
# group var
# <chr> <chr>
#1 a bada
#2 a noo
#3 b world
#4 b run
mytest <- data_frame(group = c('a', 'a', 'a', 'b', 'b', 'b'),
x = c(NA,NA,NA,5,6,7),
y = c(3,5,6,NA,NA,NA),
label_x = c('hello','hello','hello','world','world','world'),
label_y =c('bada','bada','bada','boom','boom','boom'))
extract_good_colnames <- function(df, subgroup){
subset <- filter(df, group == subgroup)
if(sum(is.na(subset$x)) > 0){
colname = 'label_y'
}else if(sum(is.na(subset$y)) > 0){
colname = 'label_x'
}
return(tibble(group = subgroup, var = as.character(subset[1, colname])))
}
groups <- unique(mytest$group)
map_df(groups, function(x) extract_good_colnames(mytest, x))