我有以下列表清单。它包含两个变量:对和基因。 pair
的包含始终是带有两个字符串的向量。变量genes
是一个可以包含多个值的向量。
lol <- list(structure(list(pair = c("BoneMarrow", "Pulmonary"), genes = "PRR11"), .Names = c("pair",
"genes")), structure(list(pair = c("BoneMarrow", "Umbilical"),
genes = "GNB2L1"), .Names = c("pair", "genes")), structure(list(
pair = c("Pulmonary", "Umbilical"), genes = "ATP1B1"), .Names = c("pair",
"genes")))
lol
#> [[1]]
#> [[1]]$pair
#> [1] "BoneMarrow" "Pulmonary"
#>
#> [[1]]$genes
#> [1] "PRR11"
#>
#>
#> [[2]]
#> [[2]]$pair
#> [1] "BoneMarrow" "Umbilical"
#>
#> [[2]]$genes
#> [1] "GNB2L1"
#>
#>
#> [[3]]
#> [[3]]$pair
#> [1] "Pulmonary" "Umbilical"
#>
#> [[3]]$genes
#> [1] "ATP1B1"
如何将其转换为此数据框:
pair1 pair2 genes_vec
BoneMarrow Pulmonary PRR11
BoneMarrow Umbilical GNB2L1
Pulmonary Umbilical ATP1B1
请注意,genes
变量是一个向量而不是单个字符串。
我最好的尝试就是没有给出我想要的东西:
> do.call(rbind, lapply(lol, data.frame, stringsAsFactors=FALSE))
pair genes
1 BoneMarrow PRR11
2 Pulmonary PRR11
3 BoneMarrow GNB2L1
4 Umbilical GNB2L1
5 Pulmonary ATP1B1
6 Umbilical ATP1B1
更新:
使用新示例显示genes
的矢量内容
lol2 <- list(structure(list(pair = c("BoneMarrow", "Pulmonary"), genes = c("GNB2L1",
"PRR11")), .Names = c("pair", "genes")), structure(list(pair = c("BoneMarrow",
"Umbilical"), genes = "GNB2L1"), .Names = c("pair", "genes")),
structure(list(pair = c("Pulmonary", "Umbilical"), genes = "ATP1B1"), .Names = c("pair",
"genes")))
lol2
#> [[1]]
#> [[1]]$pair
#> [1] "BoneMarrow" "Pulmonary"
#>
#> [[1]]$genes
#> [1] "GNB2L1" "PRR11"
#>
#>
#> [[2]]
#> [[2]]$pair
#> [1] "BoneMarrow" "Umbilical"
#>
#> [[2]]$genes
#> [1] "GNB2L1"
#>
#>
#> [[3]]
#> [[3]]$pair
#> [1] "Pulmonary" "Umbilical"
#>
#> [[3]]$genes
#> [1] "ATP1B1"
预期输出为:
pair1 pair2 genes_vec
BoneMarrow Pulmonary PRR11,GNB2L1
BoneMarrow Umbilical GNB2L1
Pulmonary Umbilical ATP1B1
答案 0 :(得分:9)
使用tidyverse
,您可以使用purrr
来帮助您
library(dplyr)
library(purrr)
tibble(
pair = map(lol, "pair"),
genes_vec = map_chr(lol, "genes")
) %>%
mutate(
pair1 = map_chr(pair, 1),
pair2 = map_chr(pair, 2)
) %>%
select(pair1, pair2, genes_vec)
#> # A tibble: 3 x 3
#> pair1 pair2 genes_vec
#> <chr> <chr> <chr>
#> 1 BoneMarrow Pulmonary PRR11
#> 2 BoneMarrow Umbilical GNB2L1
#> 3 Pulmonary Umbilical ATP1B1
使用第二个示例,只需将map_chr(lol, "genes")
替换为map(lol2, "genes")
,因为您希望使用列表列保留嵌套数据框。
tibble(
pair = map(lol2, "pair"),
genes_vec = map(lol2, "genes")
) %>%
mutate(
pair1 = map_chr(pair, 1),
pair2 = map_chr(pair, 2)
) %>%
select(pair1, pair2, genes_vec)
#> # A tibble: 3 x 3
#> pair1 pair2 genes_vec
#> <chr> <chr> <list>
#> 1 BoneMarrow Pulmonary <chr [2]>
#> 2 BoneMarrow Umbilical <chr [1]>
#> 3 Pulmonary Umbilical <chr [1]>
更通用的方法是使用嵌套的元素并根据需要删除它们
library(dplyr)
library(purrr)
library(tidyr)
tab1 <-lol %>%
transpose() %>%
as_tibble() %>%
mutate(pair = map(pair, ~as_tibble(t(.x)))) %>%
mutate(pair = map(pair, ~set_names(.x, c("pair1", "pair2"))))
tab1
#> # A tibble: 3 x 2
#> pair genes
#> <list> <list>
#> 1 <tibble [1 x 2]> <chr [1]>
#> 2 <tibble [1 x 2]> <chr [1]>
#> 3 <tibble [1 x 2]> <chr [1]>
对于lol2
,除非列表lol2
代替lol1
tab2 <- lol2 %>%
transpose() %>%
as_tibble() %>%
mutate(pair = map(pair, ~as_tibble(t(.x)))) %>%
mutate(pair = map(pair, ~set_names(.x, c("pair1", "pair2"))))
tab2
#> # A tibble: 3 x 2
#> pair genes
#> <list> <list>
#> 1 <tibble [1 x 2]> <chr [2]>
#> 2 <tibble [1 x 2]> <chr [1]>
#> 3 <tibble [1 x 2]> <chr [1]>
然后您可以取消想要的列
tab1 %>%
unnest()
#> # A tibble: 3 x 3
#> genes pair1 pair2
#> <chr> <chr> <chr>
#> 1 PRR11 BoneMarrow Pulmonary
#> 2 GNB2L1 BoneMarrow Umbilical
#> 3 ATP1B1 Pulmonary Umbilical
tab2 %>%
unnest(pair)
#> # A tibble: 3 x 3
#> genes pair1 pair2
#> <list> <chr> <chr>
#> 1 <chr [2]> BoneMarrow Pulmonary
#> 2 <chr [1]> BoneMarrow Umbilical
#> 3 <chr [1]> Pulmonary Umbilical
答案 1 :(得分:2)
编辑:更新以使用vector lol2。
也许是这样的:
as.data.frame(do.call(rbind,lapply(lol2, function(x) {c(unlist(x[1]),gene=paste(unlist(x[2]),collapse=","))})),stringsAsFactors = F)
pair1 pair2 genes
1 BoneMarrow Pulmonary GNB2L1, PRR11
2 BoneMarrow Umbilical GNB2L1
3 Pulmonary Umbilical ATP1B1
答案 2 :(得分:1)
> lol1 <- data.frame(t(sapply(lol,c)))
> as.data.frame(t(apply(lol1, 1, unlist)))
pair1 pair2 genes
1 BoneMarrow Pulmonary PRR11
2 BoneMarrow Umbilical GNB2L1
3 Pulmonary Umbilical ATP1B1
答案 3 :(得分:1)
对于第一个问题,与其他答案几乎相同,但更短或更紧凑:
library(tidyverse)
lol <- list(structure(list(pair = c("BoneMarrow", "Pulmonary"), genes = "PRR11"),
.Names = c("pair", "genes")),
structure(list(pair = c("BoneMarrow", "Umbilical"), genes = "GNB2L1"),
.Names = c("pair", "genes")),
structure(list(pair = c("Pulmonary", "Umbilical"), genes = "ATP1B1"), .Names = c("pair","genes")))
map_dfr(lol, ~as_tibble(.) %>%
mutate(row=paste0("pair", row_number()))%>%
spread(row, pair) %>%
select(pair1, pair2, genes))
#> # A tibble: 3 x 3
#> pair1 pair2 genes
#> <chr> <chr> <chr>
#> 1 BoneMarrow Pulmonary PRR11
#> 2 BoneMarrow Umbilical GNB2L1
#> 3 Pulmonary Umbilical ATP1B1
由reprex package(v0.3.0)于2020-12-04创建
答案 4 :(得分:0)
这应该有效:
data.frame(do.call(rbind,lol2))
data.frame(do.call(rbind,lol2))
pair genes
1 BoneMarrow, Pulmonary GNB2L1, PRR11
2 BoneMarrow, Umbilical GNB2L1
3 Pulmonary, Umbilical ATP1B1
将基因视为向量的方式与将对数作为向量处理的方式相同,而不是对1和2只使用它们。