I am struggling with creating a for loop over all txt.files in a specific repository. The goal is to merge all separately saved txt.files in a dataframe and add an ID-variable that can always be found in the txt-file-names (e.g., ID=10 for the file "10_1. Recording 01.10.2015 131514_CsvData.txt" )
txt_files <- list.files("Data/study", pattern = ".txt")
txt_files [1] "1_1. Recording 18.09.2015 091037_CsvData.txt" "10_1. Recording 01.10.2015 131514_CsvData.txt"
[3] "100_1. Recording 02.10.2015 091630_CsvData.txt" "104_1. Recording 22.09.2015 142604_CsvData.txt"
[5] "107_1. Recording 18.09.2015 104300_CsvData.txt" "110_1. Recording 29.09.2015 081558_CsvData.txt"
[7] "112_1. Recording 21.09.2015 082908_CsvData.txt" "114_1. Recording 29.09.2015 101159_CsvData.txt"
[9] "115_1. Recording 23.09.2015 141204_CsvData.txt" "116_1. Recording 30.09.2015 110624_CsvData.txt"
[11] "117_1. Recording 01.10.2015 141227_CsvData.txt" "120_1. Recording 17.09.2015 153516_CsvData.txt"
Read in and merge txt.files
for ( file in txt_files){
# if the merged dataframe "final_df" doesn't already exist, create it
if (!exists("final_df")){
final_df<- read.table(paste("Data/study/",file, sep=""), header=TRUE, fill=TRUE)
temp_ID <- substring(file, 0,str_locate_all(pattern ='_1.',file)[[1]][1]-1)
final_df$ID <- temp_ID
final_df <- as.data.frame(final_df)
}
# if the merged dataframe does already exist, append to it
else {
temp_dataset <- read.table(paste("Data/study/",file, sep=""), header=TRUE, fill=TRUE)
# extract ID column from filename
temp_ID <- substring(file, 0,str_locate_all(pattern ='_1.',file)[[1]][1]-1)
temp_dataset$ID <- temp_ID
final_df<-rbind(final_df, temp_dataset)
}
return(as.data.frame(final_df))
}
Aucun commentaire:
Enregistrer un commentaire