Batch Editing TXT to CSV in R - r

Question

I have a series of .txt files that look like this:
Button,Intensity,Acc,Intensity,RT,Time
0,30,0,0,0,77987.931
1,30,1,13.5,0,78084.57
1,30,1,15,0,78098.624
1,30,1,6,0,78114.132
1,30,1,15,0,78120.669
They have file names like 1531_Day49.txt, 1531_Day50.txt, 1532_Day49.txt, 1532_Day50.txt etc
I want to load all the files in this directory into data frames, append a column that is the difference between the Time in the row above (tdelta), and append two columns that are the first 4 digits (i.e. 1531, 1532) and one column that's the Day code uncoded so the column title would be PrePost and each row would be, if filename Day49, then "Pre" and if filename Day50 then "Post".
So ideal output for a 1531 Day 49 file would be:
Button,Intensity,Acc,Intensity,RT,Time,Tdelta,ID,PrePost
0,30,0,0,0,77987.931,0 ,1531,Pre
1,30,1,13.5,0,78084.57,96.693 ,1531,Pre
1,30,1,15,0,78098.624, 14.054,1531,Pre
So far I have:
#call library
library(data.table)
#batch enter .txt files and put them into a data frame
setwd("~/Documents/PVTPASAT/PVT")
temp = list.files(pattern="*.txt")
list.DFs <- lapply(myfiles,fread)
#view print out to visually check
View(list.DFs)
#add column of time difference
list.DFs <- lapply(list.DFs, cbind, tDelta = c(0, diff(df$Time)))
#Add empty columns for ID and PrePost
list.DFs <- lapply(list.DFs, cbind, ID = c(""))
list.DFs <- lapply(list.DFs, cbind, PrePost = c(""))
#print one to visually check
View(list.DFs[3])

Answer 1

I would create a function to do the processing and then apply it to your list of files like so:
example <- read.delim(textConnection('
Button, Intensity, Acc, Intensity, RT, Time
0,30,0,0,0,77987.931
1,30,1,13.5,0,78084.57
1,30,1,15,0,78098.624
1,30,1,6,0,78114.132
1,30,1,15,0,78120.669'),
header = T,
sep = ','
)
write.table(example, '1531_Day49.txt', row.names = F)
temp <- list.files(pattern="*.txt")
process_txt <- function(x) {
dat <- data.table::fread(x, header = T)
dat$tdelta <- c(0, diff(dat$Time))
dat$ID <- substr(x, 1, 4)
dat$PrePost <- if (grepl('49\\.', x)) {'Pre'} else {'Post'}
dat
}
out <- lapply(temp, process_txt)

Answer 2

#Heather, the main guidance is to first solve properly one file. Then, place all that working code into a function.
library(dplyr) ## for lag function
library(stringr) ## for str_detect
# make two test files
dt <- read.csv(text=
'Button,Intensity,Acc,Intensity,RT,Time
0,30,0,0,0,77987.931
1,30,1,13.5,0,78084.57
1,30,1,15,0,78098.624
1,30,1,6,0,78114.132
1,30,1,15,0,78120.669
')
write.csv(dt,"1531_Day49.txt")
write.csv(dt,"1532_Day50.txt")
# function to do the work for one file name - returns a dataframe
doOne <- function (file) {
# read
contents <- fread(file)
# compute delta
contents$Tdelta <- contents$Time - lag(contents$Time)
# prefix up to underscore
contents$ID <- strsplit(file, c("_"))[[1]][[1]]
# add the prepost using ifelse and str_detetct
contents$PrePost <- ifelse(str_detect(file, "Day49"), "Pre", "Post")
return(contents)
}
#test files
files <- c("1531_Day49.txt", "1532_Day50.txt")
# call the function for each file -- result is
# a list of dataframes
lapply(files, doOne)
# better get them all into a single data frame for analysis
do.call(rbind, lapply(files, doOne))
# V1 Button Intensity Acc Intensity.1 RT Time Tdelta ID PrePost
# 1: 1 0 30 0 0.0 0 77987.93 NA 1531 Pre
# 2: 2 1 30 1 13.5 0 78084.57 96.639 1531 Pre
# 3: 3 1 30 1 15.0 0 78098.62 14.054 1531 Pre
# 4: 4 1 30 1 6.0 0 78114.13 15.508 1531 Pre
# 5: 5 1 30 1 15.0 0 78120.67 6.537 1531 Pre
# 6: 1 0 30 0 0.0 0 77987.93 NA 1532 Post
# 7: 2 1 30 1 13.5 0 78084.57 96.639 1532 Post
# 8: 3 1 30 1 15.0 0 78098.62 14.054 1532 Post
# 9: 4 1 30 1 6.0 0 78114.13 15.508 1532 Post
# 10: 5 1 30 1 15.0 0 78120.67 6.537 1532 Post