r

Question

我正在尝试分析6个非常大的CSV文件（至少对我们的计算资源来说很重要）。我开发了一个能够分析所有文件的脚本。但我一直收到错误告诉我“无法读取文件Z：〜/ AC2561图像的设置/ EMT1.csv：没有足够的存储空间来处理此命令。”我使用rm（）来删除不再需要的变量，并通过自己更改索引使其“手动”运行。但是我无法运行for循环。

我将来需要在大量文件上运行此脚本，因此获取for循环（或其他替代工作）非常有用

#loading necessary packages
library(dplyr)
library(readr)

#making list of file names (6 csv files in this case)
temp = list.files(pattern="*.csv")

#starting empty list to save summary per file
summary_data <- list()


for (i in seq_along(temp)){
    df <- read_csv(temp[i])%>%
        #selecting only the columns I will work with (original file has 68 columns)
      select(`Dye 2 Positive`, `Dye 3 Positive`, `Dye 4 Positive`, `Dye 4 Cytoplasm Intensity` )

    #Each of these objects is a distinct subset of cells 
    #I'm trying to measure n() of `Dye 4 Positive` and mean() of `Dye 4 Cytoplasm Intensity`

    FITCPos_CD45Neg <- df%>%
        filter(`Dye 2 Positive` == 1, `Dye 3 Positive` == 0)%>%
        summarise(Total_GD2_count = n(), MFI = mean(`Dye 4 Cytoplasm Intensity`))
    FITCPos_CD45Pos <- df%>%
        filter(`Dye 2 Positive` == 1, `Dye 3 Positive` == 1)%>%
        summarise(Total_GD2_count = n(), MFI = mean(`Dye 4 Cytoplasm Intensity`))
    FITCNeg_CD45Neg <- df%>%
        filter(`Dye 2 Positive` == 1, `Dye 3 Positive` == 0)%>%
        summarise(Total_GD2_count = n(), MFI = mean(`Dye 4 Cytoplasm Intensity`))

    FITCNeg_CD45Pos <- df%>%
        filter(`Dye 2 Positive` == 1, `Dye 3 Positive` == 0)%>%
        summarise(Total_GD2_count = n(), MFI = mean(`Dye 4 Cytoplasm Intensity`))
    #generating name for each file summary
    item_nam <- temp[i]

    #Appending the summary to initial list
    summary_data[item_nam] <- list(FITCPos_CD45Neg,FITCPos_CD45Pos,FITCNeg_CD45Neg,FITCNeg_CD45Pos)
    #removing "objects" that are no longer needed
    rm( "FITCNeg_CD45Neg", "FITCNeg_CD45Pos", "FITCPos_CD45Neg","FITCPos_CD45Pos", "df")

}