Applying strsplit function for multiple files

Go To StackoverFlow.com

0

could somebody spot what I am doing wrong in the step 4 of my codes please (strsplit)?

I have 3 files in the directory with names '101_E45_N66.csv','102_E46_N76.csv', '103_E47_N86.csv'

I am reading them in a list and trying to split the names and add 3 new coloumns in each files for example, 'id'=101, 'easting' = E904690, 'Northing' = N936410

I know from my previous question about how I could perform for individual file which as follows:

filename <- '101_E45_N66.csv'
    ## spliting name "101_E45_N66.csv" to create 3 new coloumn within dataframe
            s = strsplit(filename,"_",,fixed=TRUE)[[1]] 
    df1= cbind(df[,c("type","date")],ID=s[1],name1=s[2],name2=s[3],df[,3:ncol(df)])

But when I am trying to create a lapply function to apply on a list I am not sure what I am doing wrong as it seems to use only 1 of the file name and add in coloumns in all 3 files the same name when I write the files back in the directory (please see step 4 of my code), the codes I am using are:

 mycsv = dir(pattern=".csv")

n <- length(mycsv) 

## step 1 - read file 
mylist <- vector("list", n) 

for(i in 1:n) mylist[[i]] <- read.csv(mycsv[i],header = TRUE,skip =5, nrow = length(count.fields(mycsv[i])) - 12) 

## step 2 - Change coloumn name
mylist <- lapply(mylist, function(x) {names(x) <- c("type","date","v1","v2","v3","v4","v5","v6","v7") ; return(x)}) 

## step 3 - changing type coloumn for weekday/weekend

mylist <- lapply(mylist, function(x) {
    f = c("wd", "we", "we", "wd", "wd", "wd", "wd")
    x$type = rep(f,52, length.out = 30)
    return(x)
}) 

## Step 4 - spliting filename to create 3 new coloumn within dataframe

    mylist <- lapply(mylist, function(x) {
            s = strsplit(mycsv[i],"_",,fixed=TRUE)[[1]]
    d = cbind(x[,c("type","date")],ID=s[1],Easting=s[2],Northing=s[3],x[,3:ncol(x)])
    return(d)
})  
    ## Step 5- writre the data back in the directory
      for(i in 1:n)    
        write.csv(file = paste("file", i, ".csv", sep = ""),    mylist[i], row.names = F)

Could you suggest what I am doing wrong in step 4 please?

Many thanks,
Ayan

my sample data:

> dput (mylist)
list(structure(list(type = c("wd", "we", "we", "wd", "wd", "wd", 
"wd", "wd", "we", "we", "wd", "wd", "wd", "wd", "wd", "we", "we", 
"wd", "wd", "wd", "wd", "wd", "we", "we", "wd", "wd", "wd", "wd", 
"wd", "we"), date = structure(c(1L, 11L, 18L, 9L, 26L, 30L, 22L, 
5L, 14L, 15L, 6L, 23L, 27L, 19L, 2L, 10L, 16L, 7L, 24L, 28L, 
20L, 3L, 12L, 17L, 8L, 25L, 29L, 21L, 4L, 13L), .Label = c("Fri 1 Jan", 
"Fri 15 Jan", "Fri 22 Jan", "Fri 29 Jan", "Fri 8 Jan", "Mon 11 Jan", 
"Mon 18 Jan", "Mon 25 Jan", "Mon 4 Jan", "Sat 16 Jan", "Sat 2 Jan", 
"Sat 23 Jan", "Sat 30 Jan", "Sat 9 Jan", "Sun 10 Jan", "Sun 17 Jan", 
"Sun 24 Jan", "Sun 3 Jan", "Thu 14 Jan", "Thu 21 Jan", "Thu 28 Jan", 
"Thu 7 Jan", "Tue 12 Jan", "Tue 19 Jan", "Tue 26 Jan", "Tue 5 Jan", 
"Wed 13 Jan", "Wed 20 Jan", "Wed 27 Jan", "Wed 6 Jan"), class = "factor"), 
    v1 = c(322L, 89L, 242L, NA, 136L, 113L, 70L, 134L, 232L, 
    NA, 127L, 124L, 120L, 162L, 179L, 374L, 477L, NA, 147L, 136L, 
    152L, 196L, 384L, 491L, 136L, NA, 143L, 172L, 226L, 509L), 
    v2 = c(409L, 71L, 206L, NA, 104L, 57L, NA, 98L, 201L, NA, 
    74L, 94L, 69L, 98L, 117L, 277L, 445L, NA, 131L, 90L, 83L, 
    NA, 329L, 473L, 73L, NA, 104L, 113L, 136L, 427L), v3 = c(367L, 
    54L, 211L, NA, 107L, 69L, 51L, 63L, 157L, NA, 56L, 115L, 
    96L, 100L, 118L, 250L, 388L, NA, 124L, 85L, 96L, 118L, 313L, 
    431L, 79L, NA, 93L, 135L, 134L, 290L), v4 = c(343L, 60L, 
    183L, NA, 110L, 53L, 32L, 77L, 123L, NA, 37L, 100L, 64L, 
    68L, 99L, 199L, 333L, NA, 107L, 71L, 81L, 89L, 219L, 393L, 
    43L, NA, 72L, 96L, 127L, NA), v5 = c(231L, 42L, 79L, NA, 
    74L, 58L, 48L, 59L, 78L, NA, 62L, 74L, 63L, 59L, 74L, 110L, 
    134L, NA, 74L, 82L, 59L, 73L, 135L, 170L, 53L, NA, 61L, 72L, 
    67L, 186L), v6 = c(140L, 41L, 57L, NA, 104L, 92L, 89L, 94L, 
    68L, NA, 116L, 131L, NA, 110L, 125L, 89L, 89L, NA, 113L, 
    124L, 115L, 116L, 95L, 77L, 126L, NA, 110L, 122L, 119L, 122L
    ), v7 = c(90L, 104L, 82L, NA, 368L, 258L, NA, 289L, 117L, 
    NA, 395L, 416L, 397L, 391L, 400L, 132L, 101L, NA, 397L, 426L, 
    418L, 411L, 151L, 66L, 396L, NA, 457L, 437L, 428L, 128L)), .Names = c("type", 
"date", "v1", "v2", "v3", "v4", "v5", "v6", "v7"), row.names = c(NA, 
-30L), class = "data.frame"), structure(list(type = c("wd", "we", 
"we", "wd", "wd", "wd", "wd", "wd", "we", "we", "wd", "wd", "wd", 
"wd", "wd", "we", "we", "wd", "wd", "wd", "wd", "wd", "we", "we", 
"wd", "wd", "wd", "wd", "wd", "we"), date = structure(c(1L, 11L, 
18L, 9L, 26L, 30L, 22L, 5L, 14L, 15L, 6L, 23L, 27L, 19L, 2L, 
10L, 16L, 7L, 24L, 28L, 20L, 3L, 12L, 17L, 8L, 25L, 29L, 21L, 
4L, 13L), .Label = c("Fri 1 Jan", "Fri 15 Jan", "Fri 22 Jan", 
"Fri 29 Jan", "Fri 8 Jan", "Mon 11 Jan", "Mon 18 Jan", "Mon 25 Jan", 
"Mon 4 Jan", "Sat 16 Jan", "Sat 2 Jan", "Sat 23 Jan", "Sat 30 Jan", 
"Sat 9 Jan", "Sun 10 Jan", "Sun 17 Jan", "Sun 24 Jan", "Sun 3 Jan", 
"Thu 14 Jan", "Thu 21 Jan", "Thu 28 Jan", "Thu 7 Jan", "Tue 12 Jan", 
"Tue 19 Jan", "Tue 26 Jan", "Tue 5 Jan", "Wed 13 Jan", "Wed 20 Jan", 
"Wed 27 Jan", "Wed 6 Jan"), class = "factor"), v1 = c(322L, 89L, 
242L, NA, 136L, 113L, 70L, 134L, 232L, NA, 127L, 124L, 120L, 
162L, 179L, 374L, 477L, NA, 147L, 136L, 152L, 196L, 384L, 491L, 
136L, NA, 143L, 172L, 226L, 509L), v2 = c(409L, 71L, 206L, NA, 
104L, 57L, NA, 98L, 201L, NA, 74L, 94L, 69L, 98L, 117L, 277L, 
445L, NA, 131L, 90L, 83L, NA, 329L, 473L, 73L, NA, 104L, 113L, 
136L, 427L), v3 = c(367L, 54L, 211L, NA, 107L, 69L, 51L, 63L, 
157L, NA, 56L, 115L, 96L, 100L, 118L, 250L, 388L, NA, 124L, 85L, 
96L, 118L, 313L, 431L, 79L, NA, 93L, 135L, 134L, 290L), v4 = c(343L, 
60L, 183L, NA, 110L, 53L, 32L, 77L, 123L, NA, 37L, 100L, 64L, 
68L, 99L, 199L, 333L, NA, 107L, 71L, 81L, 89L, 219L, 393L, 43L, 
NA, 72L, 96L, 127L, NA), v5 = c(231L, 42L, 79L, NA, 74L, 58L, 
48L, 59L, 78L, NA, 62L, 74L, 63L, 59L, 74L, 110L, 134L, NA, 74L, 
82L, 59L, 73L, 135L, 170L, 53L, NA, 61L, 72L, 67L, 186L), v6 = c(140L, 
41L, 57L, NA, 104L, 92L, 89L, 94L, 68L, NA, 116L, 131L, NA, 110L, 
125L, 89L, 89L, NA, 113L, 124L, 115L, 116L, 95L, 77L, 126L, NA, 
110L, 122L, 119L, 122L), v7 = c(90L, 104L, 82L, NA, 368L, 258L, 
NA, 289L, 117L, NA, 395L, 416L, 397L, 391L, 400L, 132L, 101L, 
NA, 397L, 426L, 418L, 411L, 151L, 66L, 396L, NA, 457L, 437L, 
428L, 128L)), .Names = c("type", "date", "v1", "v2", "v3", "v4", 
"v5", "v6", "v7"), row.names = c(NA, -30L), class = "data.frame"), 
    structure(list(type = c("wd", "we", "we", "wd", "wd", "wd", 
    "wd", "wd", "we", "we", "wd", "wd", "wd", "wd", "wd", "we", 
    "we", "wd", "wd", "wd", "wd", "wd", "we", "we", "wd", "wd", 
    "wd", "wd", "wd", "we"), date = structure(c(1L, 11L, 18L, 
    9L, 26L, 30L, 22L, 5L, 14L, 15L, 6L, 23L, 27L, 19L, 2L, 10L, 
    16L, 7L, 24L, 28L, 20L, 3L, 12L, 17L, 8L, 25L, 29L, 21L, 
    4L, 13L), .Label = c("Fri 1 Jan", "Fri 15 Jan", "Fri 22 Jan", 
    "Fri 29 Jan", "Fri 8 Jan", "Mon 11 Jan", "Mon 18 Jan", "Mon 25 Jan", 
    "Mon 4 Jan", "Sat 16 Jan", "Sat 2 Jan", "Sat 23 Jan", "Sat 30 Jan", 
    "Sat 9 Jan", "Sun 10 Jan", "Sun 17 Jan", "Sun 24 Jan", "Sun 3 Jan", 
    "Thu 14 Jan", "Thu 21 Jan", "Thu 28 Jan", "Thu 7 Jan", "Tue 12 Jan", 
    "Tue 19 Jan", "Tue 26 Jan", "Tue 5 Jan", "Wed 13 Jan", "Wed 20 Jan", 
    "Wed 27 Jan", "Wed 6 Jan"), class = "factor"), v1 = c(322L, 
    89L, 242L, NA, 136L, 113L, 70L, 134L, 232L, NA, 127L, 124L, 
    120L, 162L, 179L, 374L, 477L, NA, 147L, 136L, 152L, 196L, 
    384L, 491L, 136L, NA, 143L, 172L, 226L, 509L), v2 = c(409L, 
    71L, 206L, NA, 104L, 57L, NA, 98L, 201L, NA, 74L, 94L, 69L, 
    98L, 117L, 277L, 445L, NA, 131L, 90L, 83L, NA, 329L, 473L, 
    73L, NA, 104L, 113L, 136L, 427L), v3 = c(367L, 54L, 211L, 
    NA, 107L, 69L, 51L, 63L, 157L, NA, 56L, 115L, 96L, 100L, 
    118L, 250L, 388L, NA, 124L, 85L, 96L, 118L, 313L, 431L, 79L, 
    NA, 93L, 135L, 134L, 290L), v4 = c(343L, 60L, 183L, NA, 110L, 
    53L, 32L, 77L, 123L, NA, 37L, 100L, 64L, 68L, 99L, 199L, 
    333L, NA, 107L, 71L, 81L, 89L, 219L, 393L, 43L, NA, 72L, 
    96L, 127L, NA), v5 = c(231L, 42L, 79L, NA, 74L, 58L, 48L, 
    59L, 78L, NA, 62L, 74L, 63L, 59L, 74L, 110L, 134L, NA, 74L, 
    82L, 59L, 73L, 135L, 170L, 53L, NA, 61L, 72L, 67L, 186L), 
        v6 = c(140L, 41L, 57L, NA, 104L, 92L, 89L, 94L, 68L, 
        NA, 116L, 131L, NA, 110L, 125L, 89L, 89L, NA, 113L, 124L, 
        115L, 116L, 95L, 77L, 126L, NA, 110L, 122L, 119L, 122L
        ), v7 = c(90L, 104L, 82L, NA, 368L, 258L, NA, 289L, 117L, 
        NA, 395L, 416L, 397L, 391L, 400L, 132L, 101L, NA, 397L, 
        426L, 418L, 411L, 151L, 66L, 396L, NA, 457L, 437L, 428L, 
        128L)), .Names = c("type", "date", "v1", "v2", "v3", 
    "v4", "v5", "v6", "v7"), row.names = c(NA, -30L), class = "data.frame"))
2012-04-03 20:28
by Achak


1

The problem is that you try to index you filenames by i which does not exists in the lapply call.

As you need a common index for mylist and mycsv, you could use a simple loop or if you'd insist on calling lapply here then try something like:

lapply(1:length(mylist), function(i) {
    mylist.i <- mylist[[i]]
    s = strsplit(mycsv[i], "_" , fixed = TRUE)[[1]]
    d = cbind(mylist.i[, c("type", "date")], ID = s[1], Easting = s[2], Northing = s[3], mylist.i[, 3:ncol(mylist.i)])
    return(d)
})

Please note that without mycsv I could not test this and did not try to check other parts of you code.

2012-04-03 21:41
by daroczig
Thank you ever so much! it works great when I ran it :))) - Achak 2012-04-03 22:03
No problem, I am really happy to hear that @Ayan : - daroczig 2012-04-03 22:09
Ads