Question

我已经找到了代码的一部分，我将在下面介绍，但我发现很难在函数列表上迭代（循环）函数：

library(Hmisc)
filter_173 <- c("kp|917416", "kp|835898", "kp|829747", "kp|767311") 
# This is a vector of values that I want to exclude from the files
setwd("full_path_of_directory_with_desired_files")
filepath <- "//full_path_of_directory_with_desired_files"
list.files(filepath)
predict_files <- list.files(filepath, pattern="predict.txt") 
# all files that I want to filter have _predict.txt in them
predict_full <- file.path(filepath, predict_files)
# generates full pathnames of all desired files I want to filter
sample_names <- sample_names <- sapply(strsplit(predict_files , "_"), `[`, 1)

现在这里是一个我想用一个特定示例文件做的简单过滤的例子，这很好用。如何在predict_full

中的所有文件名循环中重复此操作

test_predict <- read.table("a550673-4308980_A05_RepliG_rep2_predict.txt", header = T, sep = "\t")
# this is a file in my current working directory that I set with setwd above
test_predict_filt <- test_predict[test_predict$target_id %nin% filter_173]
     write.table(test_predict_filt, file = "test_predict")

最后，如何将过滤后的文件放在与原始文件名相同的文件夹中，后缀是否已过滤？

predict_filt <- file.path(filepath, "filtered") 
 # Place filtered files in 
filtered/ subdirectory
filtPreds <- file.path(predict_filt, paste0(sample_names, "_filt_predict.txt"))

我总是陷入循环！很难分享100％可重复的示例，因为每个人的工作目录和文件路径都是唯一的，但是如果您将其调整到计算机上适当的路径名，我共享的所有代码都可以工作。

Answer 1

这应该可以循环遍历每个文件，并使用您需要的文件名规范将它们写入新位置。请务必先更改目录路径。

filter_173 <- c("kp|917416", "kp|835898", "kp|829747", "kp|767311") #This is a vector of values that I want to exclude from the files

filepath <- "//full_path_of_directory_with_desired_files"
filteredpath <- "//full_path_of_directory_with_filtered_results/"

# Get vector of predict.txt files
predict_files <- list.files(filepath, pattern="predict.txt") 

# Get vector of full paths for predict.txt files
predict_full <- file.path(filepath, predict_files) 

# Get vector of sample names
sample_names <- sample_names <- sapply(strsplit(predict_files , "_"), `[`, 1)

# Set for loop to go from 1 to the number of predict.txt files
for(i in 1:length(predict_full))
{
  # Load the current file into a dataframe
  df.predict <- read.table(predict_full[i], header=T, sep="\t")

  # Filter out the unwanted rows
  df.predict <- df.predict[!(df.predict$target_id %in% filter_173)]

  # Write the filtered dataframe to the new directory
  write.table(df.predict, file = file.path(filteredpath, paste(sample_names[i],"_filt_predict.txt",sep = "")))
}

将子集循环到目录中的多个文件，并将文件输出到带有后缀

1 个答案: