Select CSV files and read in pairs - r

Question

I am comparing two pairs of csv files each at a time. The files I have each end with a number like cars_file2.csv, Lorries_file3.csv, computers_file4.csv, phones_file5.csv. I have like 70 files per folder and the way I am comparing is, I compare cars_file2.csv and Lorries_file3.csv then Lorries_file3.csv and
computers_file4.csv, and the pattern is 2,3,3,4,4,5 like that. Is there a smart way I can handle this instead of manually coming back and change file like the way I am reading here or I can use the last number on each csv to read them smartly. NOTE the files have same suffixes _file:
library(daff)
setwd("path")
# Load csvs to compare into data frames
x_original <- read.csv("cars_file2.csv", strip.white=TRUE, stringsAsFactors = FALSE)
x_changed <- read.csv("Lorries_file3.csv", strip.white=TRUE, stringsAsFactors = FALSE)
render(diff_data(x_original,x_changed ,ignore_whitespace=TRUE,count_like_a_spreadsheet = FALSE))
My intention is to compare each two pairs of csv and recorded, Field additions, deletions and modified

Answer 1

You may want to load all files at once and do your comparison with a full list of files.
This may help:
# your path
path <- "insert your path"
# get folders in this path
dir_data <- as.list(list.dirs(path))
# get all filenames
dir_data <- lapply(dir_data,function(x){
# list of folders
files <- list.files(x)
files <- paste(x,files,sep="/")
# only .csv files
files <- files[substring(files,nchar(files)-3,nchar(files)) %in% ".csv"]
# remove possible errors
files <- files[!is.na(files)]
# save if there are files
if(length(files) >= 1){
return(files)
}
})
# delete NULL-values
dir_data <- compact(dir_data)
# make it a named vector
dir_data <- unique(unlist(dir_data))
names(dir_data) <- sub(pattern = "(.*)\\..*$", replacement = "\\1", basename(dir_data))
names(dir_data) <- as.numeric(substring(names(dir_data),nchar(names(dir_data)),nchar(names(dir_data))))
# remove possible NULL-values
dir_data <- dir_data[!is.na(names(dir_data))]
# make it a list again
dir_data <- as.list(dir_data)
# load data
data_upload <- lapply(dir_data,function(x){
if(file.exists(x)){
data <- read.csv(x,header=T,sep=";")
}else{
data <- "file not found"
}
return(data)
})
# setup for comparison
diffs <- lapply(as.character(sort(as.numeric(names(data_upload)))),function(x){
# check if the second dataset exists
if(as.character(as.numeric(x)+1) %in% names(data_upload)){
# first dataset
print(data_upload[[x]])
# second dataset
print(data_upload[[as.character(as.numeric(x)+1)]])
# do your operations here
comparison <- render(diff_data(data_upload[[x]],
data_upload[[as.character(as.numeric(x)+1)]],
ignore_whitespace=T,count_like_a_spreadsheet = F))
numbers <- c(x, as.numeric(x)+1)
# save both the comparison data and the numbers of the datasets
return(list(comparison,numbers))
}
})
# you can find the differences here
diffs
This script loads all csv-files in a folder and its sub-folders and puts them into a list by their numbers. In case there are no doubles, this will work. If you have doubles, you will have to adjust the part where the vector is named so that you can index the full names of the files afterwards.

Answer 2

A simple for- loop using paste will read-in the pairs:
for (i in 1:70) { # assuming the last pair is cars_file70.csv and Lorries_file71.csv
x_original <- read.csv(paste0("cars_file",i,".csv"), strip.white=TRUE, stringsAsFactors = FALSE)
x_changed <- read.csv(paste0("Lorries_file3",i+1,".csv"), strip.white=TRUE, stringsAsFactors = FALSE)
render(diff_data(x_original,x_changed ,ignore_whitespace=TRUE,count_like_a_spreadsheet = FALSE))
}

Answer 3

For simplicity I used 2 .csv files.
csv_1
1,2,4
csv_2
1,8,10
Load all the .csv files from folder,
files <- dir("Your folder path", pattern = '\\.csv', full.names = TRUE)
tables <- lapply(files, read.csv)
#create empty list to store comparison output
diff <- c()
Loop through all loaded files and compare,
for (pos in 1:length(csv)) {
if (pos != length(csv)) { #ignore last one
#save comparison output
diff[[pos]] <- diff_data(as.data.frame(csv[pos]), as.data.frame(csv[pos + 1]), ignore_whitespace=TRUE,count_like_a_spreadsheet = FALSE)
}
}
Compared output by diff
[[1]]
Daff Comparison: ‘as.data.frame(tables[pos])’ vs. ‘as.data.frame(tables[pos + 1])’
+++ +++ --- ---
## X1 X8 X10 X2 X4