将字符向量列表混合到统一数据帧中

Question

我正在尝试使用stringr包将字符串拆分为列。

> df <- dput(head(facs,3))
structure(list(geo_accession = structure(1:3, .Names = c("V2", 
"V3", "V4"), .Label = c("GSM1494875", "GSM1494877", "GSM1494879", 
"GSM1494881", "GSM1494883", "GSM1494885", "GSM1494887", "GSM1494889", 
"GSM1494891", "GSM1494893", "GSM1494895", "GSM1494897", "GSM1494899", 
"GSM1494901", "GSM1494903", "GSM1494906", "GSM1494908", "GSM1494910", 
"GSM1494912", "GSM1494914", "GSM1494917", "GSM1494919", "GSM1494921", 
"GSM1494923"), class = "factor"), title = structure(1:3, .Names = c("V2", 
"V3", "V4"), .Label = c("2818 - Akt treated TIL - repeat 1 - mAdbID:125971", 
"2818 - Akt treated TIL - repeat 2 - mAdbID:125972", "2818 - Akt treated TIL - repeat 3 - mAdbID:125973", 
"2818 - Akt treated TIL - repeat 4 - mAdbID:125974", "2818 - Untreated TIL - repeat 1 - mAdbID:125975", 
"2818 - Untreated TIL - repeat 2 - mAdbID:125976", "2818 - Untreated TIL - repeat 3 - mAdbID:125977", 
"2818 - Untreated TIL - repeat 4 - mAdbID:125978", "3289 - Akt treated TIL - repeat 1 - mAdbID:125979", 
"3289 - Akt treated TIL - repeat 2 - mAdbID:125980", "3289 - Akt treated TIL - repeat 3 - mAdbID:125981", 
"3289 - Akt treated TIL - repeat 4 - mAdbID:125982", "3289 - Untreated TIL - repeat 1 - mAdbID:125983", 
"3289 - Untreated TIL - repeat 2 - mAdbID:125984", "3289 - Untreated TIL - repeat 3 - mAdbID:125985", 
"3289 - Untreated TIL - repeat 4 - mAdbID:125986", "3784 - Akt treated TIL - repeat 1 - mAdbID:125987", 
"3784 - Akt treated TIL - repeat 2 - mAdbID:125988", "3784 - Akt treated TIL - repeat 3 - mAdbID:125989", 
"3784 - Akt treated TIL - repeat 4 - mAdbID:125990", "3784 - Untreated TIL - repeat 1 - mAdbID:125991", 
"3784 - Untreated TIL - repeat 2 - mAdbID:125992", "3784 - Untreated TIL - repeat 3 - mAdbID:125993", 
"3784 - Untreated TIL - repeat 4 - mAdbID:125994"), class = "factor")), .Names = c("geo_accession", 
"title"), row.names = c("GSM1494875", "GSM1494877", "GSM1494879"
), class = "data.frame")  

现在它是一个2列数据帧。

> sapply(df, class)
geo_accession         title 
 "factor"      "factor"   

如果我使用str_split_fixed，

> df$title = str_split_fixed(df[,"title"], " - ", 4)
> df
           geo_accession title.1         title.2  title.3       title.4
GSM1494875    GSM1494875    2818 Akt treated TIL repeat 1 mAdbID:125971
GSM1494877    GSM1494877    2818 Akt treated TIL repeat 2 mAdbID:125972

> sapply(df, class)
geo_accession         title 
 "factor"      "matrix" 

我希望看到的是5列数据帧，而不是2列混合数据帧（因子，矩阵）。

> df
       geo_accession title1          title2   title3        title4
GSM1494875    GSM1494875   2818 Akt treated TIL repeat 1 mAdbID:125971
GSM1494877    GSM1494877   2818 Akt treated TIL repeat 2 mAdbID:125972

> sapply(df, class)
geo_accession       title.1       title.2       title.3       title.4 
 "factor"      "factor"      "factor"      "factor"      "factor" 

我不知道如何清理混合数据帧。如何将其转换为5列数据帧？

Answer 1

str_split_fixed的输出是list的{​​{1}}。将vectors分配给单个列是导致问题的原因。一种方法是将其分配给多个列，否则，我们可以使用list来修复它，即

do.call(data.frame

或者我们可以在facs1 <- do.call(data.frame, facs) 之前和之后删除空格base R，然后使用第一列删除read.csv/read.table

-

或来自cbind

的紧凑选项为facs2 <- cbind(facs[1], read.csv(text=gsub("\\s+-\\s+", "-", facs$title), sep="-", header=FALSE, col.names = paste0("title.", 1:4), stringsAsFactors=FALSE)) facs2 # geo_accession title.1 title.2 title.3 title.4 #GSM1494875 GSM1494875 2818 Akt treated TIL repeat 1 mAdbID:125971 #GSM1494877 GSM1494877 2818 Akt treated TIL repeat 2 mAdbID:125972 str(facs2) #'data.frame': 2 obs. of 5 variables: #$ geo_accession: chr "GSM1494875" "GSM1494877" #$ title.1 : int 2818 2818 #$ title.2 : chr "Akt treated TIL" "Akt treated TIL" #$ title.3 : chr "repeat 1" "repeat 2" #$ title.4 : chr "mAdbID:125971" "mAdbID:125972"

cSplit

Answer 2

您可以使用separate包中的tidyr：

library(tidyr)
df %>% separate(title, paste0('title',1:4) ,' - ')

           geo_accession title1          title2   title3        title4
1 GSM1494875  GSM1494875   2818 Akt treated TIL repeat 1 mAdbID:125971
2  GSM1494877 GSM1494877   2818 Akt treated TIL repeat 2 mAdbID:125972