r - 导入多个 csv 文件并将 NA 替换为 Zeros

Question

我知道如何单独做到这一点。但是，我有超过 1000 个文件。我决定使用 for 循环。但是，似乎我没有找到评估变量的正确方法。

这是我的代码

setwd('C:/data')
filenames=dir() #find file names

for (i in filenames){
  adt = substr(x = i, start = 1, stop = nchar(i)-4)
  name=paste("data_", adt, sep="")
  assign(name, read.csv(i,header=T,sep=",")) #read each file and assign a variable name starting with data_ to it
  func=paste('name[is.na(name)] <- 0',sep="") # here is the place I have problem. R will not consider name is a parameter whose values change in each iteration
  eval((text=func))

  }

Answer 1

您可以将结果分配给read.csv临时变量，替换NAs，然后分配给name

for (i in filenames){
  adt = substr(x = i, start = 1, stop = nchar(i)-4)
  name=paste("data_", adt, sep="")
  tmp <- read.csv(i, header=TRUE, sep=",")
  tmp[is.na(tmp)] <- 0
  assign(name, tmp, pos=.GlobalEnv)
}

Answer 2

library(plyr)
# change the pattern to match whatever file type you are reading
filenames <- list.files(path = ".", pattern = ".csv", all.files = FALSE, 
full.names = FALSE, recursive = FALSE, ignore.case = FALSE)
data <- llply(filenames, read.csv)
cleaned_data <- llply(data, function(x)  {x[is.na(x)] <- 0; return(x)})
names(cleaned_data) <- paste0("data_", 1:length(cleaned_data))