有人要求我将此功能添加到stackoverflow R包中。鉴于它是一个tinyverse包(不能依赖于第三方包)，以下是我想到的:

#' Bulk import data files 
#' 
#' Read in each file at a path and then unnest them. Defaults to csv format.
#' 
#' @param path        a character vector of full path names
#' @param pattern     an optional \link[=regex]{regular expression}. Only file names which match the regular expression will be returned.
#' @param reader      a function that can read data from a file name.
#' @param ...         optional arguments to pass to the reader function (eg \code{stringsAsFactors}).
#' @param reducer     a function to unnest the individual data files. Use I to retain the nested structure. 
#' @param recursive     logical. Should the listing recurse into directories?
#'  
#' @author Neal Fultz
#' @references \url{https://stackoverflow.com/questions/11433432/how-to-import-multiple-csv-files-at-once}
#' 
#' @importFrom utils read.csv
#' @export
read.directory <- function(path='.', pattern=NULL, reader=read.csv, ..., 
                           reducer=function(dfs) do.call(rbind.data.frame, dfs), recursive=FALSE) {
  files <- list.files(path, pattern, full.names = TRUE, recursive = recursive)

  reducer(lapply(files, reader, ...))
}

通过参数化读卡器和减速器功能，人们可以使用数据。table或dplyr(如果他们选择的话)，或者只使用适用于较小数据集的基本R函数。

有人要求我将此功能添加到stackoverflow R包中。鉴于它是一个tinyverse包(不能依赖于第三方包)，以下是我想到的:

#' Bulk import data files 
#' 
#' Read in each file at a path and then unnest them. Defaults to csv format.
#' 
#' @param path        a character vector of full path names
#' @param pattern     an optional \link[=regex]{regular expression}. Only file names which match the regular expression will be returned.
#' @param reader      a function that can read data from a file name.
#' @param ...         optional arguments to pass to the reader function (eg \code{stringsAsFactors}).
#' @param reducer     a function to unnest the individual data files. Use I to retain the nested structure. 
#' @param recursive     logical. Should the listing recurse into directories?
#'  
#' @author Neal Fultz
#' @references \url{https://stackoverflow.com/questions/11433432/how-to-import-multiple-csv-files-at-once}
#' 
#' @importFrom utils read.csv
#' @export
read.directory <- function(path='.', pattern=NULL, reader=read.csv, ..., 
                           reducer=function(dfs) do.call(rbind.data.frame, dfs), recursive=FALSE) {
  files <- list.files(path, pattern, full.names = TRUE, recursive = recursive)

  reducer(lapply(files, reader, ...))
}

通过参数化读卡器和减速器功能，人们可以使用数据。table或dplyr(如果他们选择的话)，或者只使用适用于较小数据集的基本R函数。

基于dnlbrk的注释，对于大文件，assign可以比list2env快得多。

library(readr)
library(stringr)

List_of_file_paths <- list.files(path ="C:/Users/Anon/Documents/Folder_with_csv_files/", pattern = ".csv", all.files = TRUE, full.names = TRUE)

通过将full.names参数设置为true，您将在文件列表中获得每个文件的完整路径作为单独的字符串，例如，List_of_file_paths[1]将类似于"C:/Users/Anon/Documents/Folder_with_csv_files/ fil1 .csv"

for(f in 1:length(List_of_filepaths)) {
  file_name <- str_sub(string = List_of_filepaths[f], start = 46, end = -5)
  file_df <- read_csv(List_of_filepaths[f])  
  assign( x = file_name, value = file_df, envir = .GlobalEnv)
}

你可以利用这些数据。table package的fread或base R read.csv而不是read_csv。file_name步骤允许您整理名称，以便每个数据帧不保留文件的完整路径作为其名称。 在将数据表传输到全局环境之前，您可以扩展循环对数据表做进一步的处理，例如:

for(f in 1:length(List_of_filepaths)) {
  file_name <- str_sub(string = List_of_filepaths[f], start = 46, end = -5)
  file_df <- read_csv(List_of_filepaths[f])  
  file_df <- file_df[,1:3] #if you only need the first three columns
  assign( x = file_name, value = file_df, envir = .GlobalEnv)
}

下面是一些使用R base将.csv文件转换为data.frame的选项，以及一些可用来读取R文件的包。

这比下面的选项要慢。

# Get the files names
files = list.files(pattern="*.csv")
# First apply read.csv, then rbind
myfiles = do.call(rbind, lapply(files, function(x) read.csv(x, stringsAsFactors = FALSE)))

编辑:-更多的额外选择使用数据。表和读取器

一个fread()版本，它是数据的函数。表方案。这是目前为止R中最快的选项。

library(data.table)
DT = do.call(rbind, lapply(files, fread))
# The same using `rbindlist`
DT = rbindlist(lapply(files, fread))

使用readr，这是另一个读取csv文件的包。它比fread慢，比base R快，但功能不同。

library(readr)
library(dplyr)
tbl = lapply(files, read_csv) %>% bind_rows()

这是我读取多个文件并将它们组合成1个数据帧的具体示例:

path<- file.path("C:/folder/subfolder")
files <- list.files(path=path, pattern="/*.csv",full.names = T)
library(data.table)
data = do.call(rbind, lapply(files, function(x) read.csv(x, stringsAsFactors = FALSE)))

只要你的电脑有多个核，下面的代码就能让你以最快的速度处理大数据:

if (!require("pacman")) install.packages("pacman")
pacman::p_load(doParallel, data.table, stringr)

# get the file name
dir() %>% str_subset("\\.csv$") -> fn

# use parallel setting
(cl <- detectCores() %>%
  makeCluster()) %>%
  registerDoParallel()

# read and bind all files together
system.time({
  big_df <- foreach(
    i = fn,
    .packages = "data.table"
  ) %dopar%
    {
      fread(i, colClasses = "character")
    } %>%
    rbindlist(fill = TRUE)
})

# end of parallel work
stopImplicitCluster(cl)

更新于20/04/16: 当我发现一个可用于并行计算的新包时，使用以下代码提供了一个替代解决方案。

if (!require("pacman")) install.packages("pacman")
pacman::p_load(future.apply, data.table, stringr)

# get the file name
dir() %>% str_subset("\\.csv$") -> fn

plan(multiprocess)

future_lapply(fn,fread,colClasses = "character") %>% 
  rbindlist(fill = TRUE) -> res

# res is the merged data.table