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)
}

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

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。

一个快速而简洁的解决方案: (比Base R的read.csv快两倍多)

tbl <-
    list.files(pattern = "*.csv") %>% 
    map_df(~read_csv(.))

和数据。Table的fread()甚至可以再次将加载时间减少一半。(1/4底R乘以)

library(data.table)

tbl_fread <- 
    list.files(pattern = "*.csv") %>% 
    map_df(~fread(.))

stringsAsFactors = FALSE参数保持数据帧因子不受影响(正如marbel指出的那样，这是fread的默认设置)。

如果类型转换不够厚颜无耻，可以使用col_types参数强制所有列都是字符。

tbl <-
    list.files(pattern = "*.csv") %>% 
    map_df(~read_csv(., col_types = cols(.default = "c")))

如果您想要深入子目录来构造最终要绑定的文件列表，那么请确保包含路径名，并在列表中以文件的全名注册这些文件。这将允许绑定工作在当前目录之外进行。(将完整的路径名视为护照，允许跨目录“边界”返回。)

tbl <-
    list.files(path = "./subdirectory/",
               pattern = "*.csv", 
               full.names = T) %>% 
    map_df(~read_csv(., col_types = cols(.default = "c"))) 

正如Hadley在这里描述的(大约在中间):

Map_df (x, f)实际上与do相同。调用("rbind"， lapply(x, f))....

额外功能-添加文件名的记录每尼克功能请求在评论下面: *为每条记录添加原始文件名。

代码解释:创建一个函数，在初始读取表期间将文件名附加到每个记录。然后使用该函数而不是简单的read_csv()函数。

read_plus <- function(flnm) {
    read_csv(flnm) %>% 
        mutate(filename = flnm)
}

tbl_with_sources <-
    list.files(pattern = "*.csv", 
               full.names = T) %>% 
    map_df(~read_plus(.))

(类型强制转换和子目录处理方法也可以在read_plus()函数中以与上面建议的第二个和第三个变体相同的方式进行处理。)

### Benchmark Code & Results 
library(tidyverse)
library(data.table)
library(microbenchmark)

### Base R Approaches
#### Instead of a dataframe, this approach creates a list of lists
#### removed from analysis as this alone doubled analysis time reqd
# lapply_read.delim <- function(path, pattern = "*.csv") {
#     temp = list.files(path, pattern, full.names = TRUE)
#     myfiles = lapply(temp, read.delim)
# }

#### `read.csv()`
do.call_rbind_read.csv <- function(path, pattern = "*.csv") {
    files = list.files(path, pattern, full.names = TRUE)
    do.call(rbind, lapply(files, function(x) read.csv(x, stringsAsFactors = FALSE)))
}

map_df_read.csv <- function(path, pattern = "*.csv") {
    list.files(path, pattern, full.names = TRUE) %>% 
    map_df(~read.csv(., stringsAsFactors = FALSE))
}


### *dplyr()*
#### `read_csv()`
lapply_read_csv_bind_rows <- function(path, pattern = "*.csv") {
    files = list.files(path, pattern, full.names = TRUE)
    lapply(files, read_csv) %>% bind_rows()
}

map_df_read_csv <- function(path, pattern = "*.csv") {
    list.files(path, pattern, full.names = TRUE) %>% 
    map_df(~read_csv(., col_types = cols(.default = "c")))
}

### *data.table* / *purrr* hybrid
map_df_fread <- function(path, pattern = "*.csv") {
    list.files(path, pattern, full.names = TRUE) %>% 
    map_df(~fread(.))
}

### *data.table*
rbindlist_fread <- function(path, pattern = "*.csv") {
    files = list.files(path, pattern, full.names = TRUE)
    rbindlist(lapply(files, function(x) fread(x)))
}

do.call_rbind_fread <- function(path, pattern = "*.csv") {
    files = list.files(path, pattern, full.names = TRUE)
    do.call(rbind, lapply(files, function(x) fread(x, stringsAsFactors = FALSE)))
}


read_results <- function(dir_size){
    microbenchmark(
        # lapply_read.delim = lapply_read.delim(dir_size), # too slow to include in benchmarks
        do.call_rbind_read.csv = do.call_rbind_read.csv(dir_size),
        map_df_read.csv = map_df_read.csv(dir_size),
        lapply_read_csv_bind_rows = lapply_read_csv_bind_rows(dir_size),
        map_df_read_csv = map_df_read_csv(dir_size),
        rbindlist_fread = rbindlist_fread(dir_size),
        do.call_rbind_fread = do.call_rbind_fread(dir_size),
        map_df_fread = map_df_fread(dir_size),
        times = 10L) 
}

read_results_lrg_mid_mid <- read_results('./testFolder/500MB_12.5MB_40files')
print(read_results_lrg_mid_mid, digits = 3)

read_results_sml_mic_mny <- read_results('./testFolder/5MB_5KB_1000files/')
read_results_sml_tny_mod <- read_results('./testFolder/5MB_50KB_100files/')
read_results_sml_sml_few <- read_results('./testFolder/5MB_500KB_10files/')

read_results_med_sml_mny <- read_results('./testFolder/50MB_5OKB_1000files')
read_results_med_sml_mod <- read_results('./testFolder/50MB_5OOKB_100files')
read_results_med_med_few <- read_results('./testFolder/50MB_5MB_10files')

read_results_lrg_sml_mny <- read_results('./testFolder/500MB_500KB_1000files')
read_results_lrg_med_mod <- read_results('./testFolder/500MB_5MB_100files')
read_results_lrg_lrg_few <- read_results('./testFolder/500MB_50MB_10files')

read_results_xlg_lrg_mod <- read_results('./testFolder/5000MB_50MB_100files')


print(read_results_sml_mic_mny, digits = 3)
print(read_results_sml_tny_mod, digits = 3)
print(read_results_sml_sml_few, digits = 3)

print(read_results_med_sml_mny, digits = 3)
print(read_results_med_sml_mod, digits = 3)
print(read_results_med_med_few, digits = 3)

print(read_results_lrg_sml_mny, digits = 3)
print(read_results_lrg_med_mod, digits = 3)
print(read_results_lrg_lrg_few, digits = 3)

print(read_results_xlg_lrg_mod, digits = 3)

# display boxplot of my typical use case results & basic machine max load
par(oma = c(0,0,0,0)) # remove overall margins if present
par(mfcol = c(1,1)) # remove grid if present
par(mar = c(12,5,1,1) + 0.1) # to display just a single boxplot with its complete labels
boxplot(read_results_lrg_mid_mid, las = 2, xlab = "", ylab = "Duration (seconds)", main = "40 files @ 12.5MB (500MB)")
boxplot(read_results_xlg_lrg_mod, las = 2, xlab = "", ylab = "Duration (seconds)", main = "100 files @ 50MB (5GB)")

# generate 3x3 grid boxplots
par(oma = c(12,1,1,1)) # margins for the whole 3 x 3 grid plot
par(mfcol = c(3,3)) # create grid (filling down each column)
par(mar = c(1,4,2,1)) # margins for the individual plots in 3 x 3 grid
boxplot(read_results_sml_mic_mny, las = 2, xlab = "", ylab = "Duration (seconds)", main = "1000 files @ 5KB (5MB)", xaxt = 'n')
boxplot(read_results_sml_tny_mod, las = 2, xlab = "", ylab = "Duration (milliseconds)", main = "100 files @ 50KB (5MB)", xaxt = 'n')
boxplot(read_results_sml_sml_few, las = 2, xlab = "", ylab = "Duration (milliseconds)", main = "10 files @ 500KB (5MB)",)

boxplot(read_results_med_sml_mny, las = 2, xlab = "", ylab = "Duration (microseconds)        ", main = "1000 files @ 50KB (50MB)", xaxt = 'n')
boxplot(read_results_med_sml_mod, las = 2, xlab = "", ylab = "Duration (microseconds)", main = "100 files @ 500KB (50MB)", xaxt = 'n')
boxplot(read_results_med_med_few, las = 2, xlab = "", ylab = "Duration (seconds)", main = "10 files @ 5MB (50MB)")

boxplot(read_results_lrg_sml_mny, las = 2, xlab = "", ylab = "Duration (seconds)", main = "1000 files @ 500KB (500MB)", xaxt = 'n')
boxplot(read_results_lrg_med_mod, las = 2, xlab = "", ylab = "Duration (seconds)", main = "100 files @ 5MB (500MB)", xaxt = 'n')
boxplot(read_results_lrg_lrg_few, las = 2, xlab = "", ylab = "Duration (seconds)", main = "10 files @ 50MB (500MB)")

中等用例

更大的用例

用例的多样性

行:文件计数(1000,100,10) 列:最终数据帧大小(5MB, 50MB, 500MB) (点击图片查看原始尺寸)

在最小的用例中，使用purrr和dplyr的C库带来的开销超过了执行大规模处理任务时所观察到的性能收益，因此基本R结果更好。

如果您想运行自己的测试，您可能会发现这个bash脚本很有帮助。

for ((i=1; i<=$2; i++)); do 
  cp "$1" "${1:0:8}_${i}.csv";
done

bash what_you_name_this_script.sh " filename_you_want_copies " 100将创建100份按顺序编号的文件(在文件名的前8个字符和下划线之后)。

归因和欣赏

特别感谢:

Tyler Rinker和Akrun演示了微基准测试。 Jake Kaupp向我介绍了map_df()。 David McLaughlin提供了关于改进可视化和讨论/确认在小文件、小数据框架分析结果中观察到的性能反转的有用反馈。 Marbel指出了fread()的默认行为。(我需要研究一下数据表。)

使用readr 2.0.0以后，您可以一次读取多个文件，只需提供文件参数的路径列表。下面是一个使用readr::read_csv()的示例。

packageVersion("readr")
#> [1] '2.0.1'
library(readr)
library(fs)

# create files to read in
write_csv(read_csv("1, 2 \n 3, 4", col_names = c("x", "y")), file = "file1.csv")
write_csv(read_csv("5, 6 \n 7, 8", col_names = c("x", "y")), file = "file2.csv")

# get a list of files
files <- dir_ls(".", glob = "file*csv")
files
#> file1.csv file2.csv

# read them in at once
# record paths in a column called filename
read_csv(files, id = "filename")
#> # A tibble: 4 × 3
#>   filename      x     y
#>   <chr>     <dbl> <dbl>
#> 1 file1.csv     1     2
#> 2 file1.csv     3     4
#> 3 file2.csv     5     6
#> 4 file2.csv     7     8

由reprex包于2021-09-16创建(v2.0.1)

在我看来，大多数其他答案都被里约热内卢::import_list淘汰了，这是一个简洁的一行程序:

library(rio)
my_data <- import_list(dir("path_to_directory", pattern = ".csv"), rbind = TRUE)

任何额外的参数都传递给里约热内卢::import。里约热内卢几乎可以处理R可以读取的任何文件格式，而且它使用数据。桌子的fread在可能的地方，所以它也应该快。