R 在目录中的多个文件上循环子集，并将文件输出到带有后缀的新目录中

我已经理解了代码的某些部分，我将在下面进行描述，但我发现很难在文件列表上迭代（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)

最后，如何将过滤后的文件放在与原始文件同名且后缀为filtered的文件夹中

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

---

predict\u filt这应该可以循环遍历每个文件，并使用所需的文件名规范将它们写入新位置。只需确保先更改目录路径即可

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 = "")))
}

filter_173嗨，马特，谢谢你的回答。这个循环对我打算做的事情很有效。对于未来的读者，我只是想提醒一下，我想过滤变量
target\u id
中与
filter\u 173
向量对应的行，因此在末尾添加一个
，
非常重要。同样在
write.table
中，
sep
应该在文件函数用
关闭后出现
write.table
中的默认值有
quotes=T
和
row.names=T
。如果将来的脚本对制表符分隔的文件中的“”敏感（我猜它们会是这样），那么这将破坏您的脚本。因此，有效地执行以下循环：
for（I in 1:length（predict#full））{#将当前文件加载到dataframe df.predict中
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 = "")))
}