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()

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。)

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)))

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。

我喜欢使用list.files()， lapply()和list2env()(或fs::dir_ls()， purrr::map()和list2env())的方法。这看起来既简单又灵活。

或者，您可以尝试小包{tor} (to-R):默认情况下，它将文件从工作目录导入到列表(list_*()变量)或全局环境(load_*()变量)。

例如，这里我使用tor::list_csv()将我工作目录中的所有.csv文件读入一个列表:

library(tor)

dir()
#>  [1] "_pkgdown.yml"     "cran-comments.md" "csv1.csv"        
#>  [4] "csv2.csv"         "datasets"         "DESCRIPTION"     
#>  [7] "docs"             "inst"             "LICENSE.md"      
#> [10] "man"              "NAMESPACE"        "NEWS.md"         
#> [13] "R"                "README.md"        "README.Rmd"      
#> [16] "tests"            "tmp.R"            "tor.Rproj"

list_csv()
#> $csv1
#>   x
#> 1 1
#> 2 2
#> 
#> $csv2
#>   y
#> 1 a
#> 2 b

现在我用tor::load_csv()将这些文件加载到我的全局环境中:

# The working directory contains .csv files
dir()
#>  [1] "_pkgdown.yml"     "cran-comments.md" "CRAN-RELEASE"    
#>  [4] "csv1.csv"         "csv2.csv"         "datasets"        
#>  [7] "DESCRIPTION"      "docs"             "inst"            
#> [10] "LICENSE.md"       "man"              "NAMESPACE"       
#> [13] "NEWS.md"          "R"                "README.md"       
#> [16] "README.Rmd"       "tests"            "tmp.R"           
#> [19] "tor.Rproj"

load_csv()

# Each file is now available as a dataframe in the global environment
csv1
#>   x
#> 1 1
#> 2 2
csv2
#>   y
#> 1 a
#> 2 b

如果您需要读取特定的文件，您可以使用regexp, ignore匹配它们的文件路径。大小写颠倒。

---

为了获得更大的灵活性，请使用list_any()。它允许您通过参数.f提供reader函数。

(path_csv <- tor_example("csv"))
#> [1] "C:/Users/LeporeM/Documents/R/R-3.5.2/library/tor/extdata/csv"
dir(path_csv)
#> [1] "file1.csv" "file2.csv"

list_any(path_csv, read.csv)
#> $file1
#>   x
#> 1 1
#> 2 2
#> 
#> $file2
#>   y
#> 1 a
#> 2 b

通过…传递附加参数或者在函数内部。

path_csv %>% 
  list_any(readr::read_csv, skip = 1)
#> Parsed with column specification:
#> cols(
#>   `1` = col_double()
#> )
#> Parsed with column specification:
#> cols(
#>   a = col_character()
#> )
#> $file1
#> # A tibble: 1 x 1
#>     `1`
#>   <dbl>
#> 1     2
#> 
#> $file2
#> # A tibble: 1 x 1
#>   a    
#>   <chr>
#> 1 b

path_csv %>% 
  list_any(~read.csv(., stringsAsFactors = FALSE)) %>% 
  map(as_tibble)
#> $file1
#> # A tibble: 2 x 1
#>       x
#>   <int>
#> 1     1
#> 2     2
#> 
#> $file2
#> # A tibble: 2 x 1
#>   y    
#>   <chr>
#> 1 a    
#> 2 b

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()