Question

输入是列表列表。请看下面。文件名是一个列表，其中包含的名称与列表中的列表（name1，name2，name3）一样多。
每个名称都附加到路径：path/name1-path/name2-path/name3

程序在遍历包含列表的路径时进行遍历，并打印路径及其文件名。我希望输出为path/name1-path/name2-path/name3。但是我得到下面的输出。请在输入之后输入

输入

[[1]]
[1] "150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt"   "160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt"
[3] "JF_160426_Dep2Plas_ctryp_Gpep_SIDtargFULL__PSMs.txt"       "JF_160426_Dep2Plas_tryp_Gpep_SIDtarg-(06)_PSMs.txt"       

[[2]]
[1] "150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt"   "160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt"
[3] "JF_160426_Dep2Plas_ctryp_Gpep_SIDtargFULL__PSMs.txt"      

[[3]]
[1] "150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt"   
"160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt"

输出

我希望输出为path/nam1-path/name2-path/name3

[1] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/name1.tsv", 
[1] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/name2.tsv", 
[1] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/name3.tsv".

但是我得到下面的输出：

[1] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/name1.tsv"

我无法理解为什么在遍历列表列表时无法遍历具有文件名的路径列表。我希望这有助于澄清问题。有人可以帮忙吗？

我已经使用打印方法分析了每条语句，除了下面代码的输出之外，一切工作都很好

for (i in 1:length(lc)) { 

    for (j in 1:length(lc[[i]])) { # fetch and read files
        if (j==1) {
            newFile <- paste(dataFnsDir, lc[[i]][j], sep="/")
            newFile <- tryCatch(read.delim(newFile, header = TRUE, sep = '/'), error=function(e) NULL)
            newFile<- tryCatch(newFile, error=function(e) data.frame())
            print(tmpFn[i])
        } else {
            newFile <- paste(dataFnsDir, lc[[i]][j], sep="/")
            newFile <- tryCatch(read.delim(newFilei, header = TRUE, sep = '/'), error=function(e) NULL)
            newFile <- tryCatch(newFile, error=function(e) data.frame())
            newFile <- dplyr::bind_rows(newFile, newFile)
            print(tmpFn[i])
        }     
    }
}

Answer 1

无需使用嵌套循环。试试这个：

# sample data
dataFnsDir <- "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/"
lc <- list()
lc[[1]] <- c("150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt","160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt"
, "JF_160426_Dep2Plas_ctryp_Gpep_SIDtargFULL__PSMs.txt"       ,"JF_160426_Dep2Plas_tryp_Gpep_SIDtarg-(06)_PSMs.txt"  
)
lc[[2]] <- c(
"150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt"  , "160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt",
"JF_160426_Dep2Plas_ctryp_Gpep_SIDtargFULL__PSMs.txt"    
)
lc[[3]] <- c(
  "150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt",
"160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt"
)

# actual code
lc.path.v <- paste0(dataFnsDir,unlist(lc))
# maybe this is what you want?

lc.path.v
#> [1] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt"  
#> [2] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt"
#> [3] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/JF_160426_Dep2Plas_ctryp_Gpep_SIDtargFULL__PSMs.txt"      
#> [4] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/JF_160426_Dep2Plas_tryp_Gpep_SIDtarg-(06)_PSMs.txt"       
#> [5] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt"  
#> [6] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt"
#> [7] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/JF_160426_Dep2Plas_ctryp_Gpep_SIDtargFULL__PSMs.txt"      
#> [8] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt"  
#> [9] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt"

如果您想阅读所有内容并将它们组合在一起，请尝试以下操作（可能不起作用，因为我不知道数据是什么样的）：

lc.alldf <- lapply(lc.path, read.delim, header = TRUE, sep = "/")
lc.onedf <- dplyr::bind_rows(lc.alldf)

编辑： 代码改进，谢谢！ @Onyambu

Answer 2

如果我理解正确，OP希望从每个列表元素中作为字符向量给出的文件名中分别创建3个新文件。

OP代码的主要问题是newFile在嵌套循环的每次迭代中都被覆盖。

这就是我使用我喜欢的工具（未试用）的情况：

library(data.table)   # for fread() and rbindlist()
library(magrittr)   # use piping for clarity
lapply(
  lc, 
  function(x) {
    filenames <- file.path(dataFnsDir, x)
    lapply(filenames, fread) %>% 
      rbindlist()
  }
)

这将返回三个数据帧（data.tables）的列表。

我没有OP的输入文件，但我们可以模拟演示效果。如果我们删除对lapply()的第二次调用，我们将获得3个元素的列表，每个元素包含一个带有前缀路径的文件名字符向量。

lapply(
  lc, 
  function(x) {
    filenames <- file.path(dataFnsDir, x)
    print(filenames)
  }
)

[[1]]
[1] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt"

[2] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt"
[3] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/JF_160426_Dep2Plas_ctryp_Gpep_SIDtargFULL__PSMs.txt"

[4] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/JF_160426_Dep2Plas_tryp_Gpep_SIDtarg-(06)_PSMs.txt"


[[2]]
[1] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt"

[2] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt"
[3] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/JF_160426_Dep2Plas_ctryp_Gpep_SIDtargFULL__PSMs.txt"


[[3]]
[1] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt"

[2] "/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA/160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt"

数据

dataFnsDir <-"/home/giuseppa/Development/glycoPipeApp/OUT/openMS/INPUT_DATA"
lc <- list(
  c("150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt",
    "160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt",
    "JF_160426_Dep2Plas_ctryp_Gpep_SIDtargFULL__PSMs.txt",
    "JF_160426_Dep2Plas_tryp_Gpep_SIDtarg-(06)_PSMs.txt"
  ),
  c(
    "150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt"  ,
    "160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt",
    "JF_160426_Dep2Plas_ctryp_Gpep_SIDtargFULL__PSMs.txt"
  ),
  c(
    "150413_JF_GPeps_SIDtarg_GPstdMix_Tryp_2runs_v3_PSMs.txt",
    "160824_JF_udep_tryp_Hi_SIDdda_FULL_NewParse-(05)_PSMs.txt"
  )
)

我遍历列表清单时无法遍历列表

2 个答案:

数据