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。)

除了使用lapply或R中的其他循环构造，您还可以将CSV文件合并到一个文件中。

在Unix中，如果文件没有头文件，那么很简单:

cat *.csv > all.csv

或者如果有标题，你可以找到一个字符串匹配标题，只有标题(即假设标题行都以“年龄”开头)，你会这样做:

cat *.csv | grep -v ^Age > all.csv

我认为在Windows中，你可以通过DOS命令框中的COPY和SEARCH(或FIND或其他什么)来做到这一点，但为什么不安装cygwin并获得Unix命令shell的强大功能呢?

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()

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

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。