thr3ads.net - R help - [R] Help avoiding setting column type two times [Nov 2017]

If this information is useful, please help other people find it:
Share via:

Martin Møller Skarbiniks Pedersen

2017-Nov-30 14:27 UTC

[R] Help avoiding setting column type two times

Hi,
  I think and hope this a good place to ask for code review for a R
beginners?

  I have made a R script which generates a dataset based on 2009 danish
referendum and it does work.

  But I think the code could be better and I would any comments how the
code can be improved.
  At least I would like to know how I avoid converting several of the
columns to factors in the end of the code?

Description of the code:

  It reads a lot of xml-files from ../raw/ and saves a data.frame with
information
from these xml-files.

  In the ../raw/ directiory I have placed the xml-files which I got from
"Statistics Denmark"
  I have also put these xml-files on my website and they can be download
freely from http://20dage.dk/R/referendum-2009/raw.tar.gz

  The code is below but I have also put the code at this place:
http://20dage.dk/R/referendum-2009/convert_from_xml.R

Best Regards
Martin M. S. Pedersen

-------
library(xml2)

convert_one_file <- function(url) {
    x <- read_xml(url)

    Sted <- xml_find_first(x, ".//Sted")
    StedType <- xml_attr(Sted, "Type")
    StedTekst <- xml_text(Sted)

    Parti <- xml_find_all(x, ".//Parti")
    PartiId <- xml_attr(Parti, "Id")
    PartiBogstav <- xml_attr(Parti, "Bogstav")
    PartiNavn <- xml_attr(Parti, "Navn")


    StemmerAntal <- xml_attr(Parti, "StemmerAntal")
    Stemmeberettigede <- xml_integer(xml_find_first(x,
".//Stemmeberettigede"))
    DeltagelsePct <- xml_double(xml_find_first(x,
".//DeltagelsePct"))
    IAltGyldigeStemmer <- xml_integer(xml_find_first(x,
".//IAltGyldigeStemmer"))
    BlankeStemmer <- xml_integer(xml_find_first(x,
".//BlankeStemmer"))
    AndreUgyldigeStemmer <- xml_integer(xml_find_first(x,
".//AndreUgyldigeStemmer"))

    data.frame(cbind(StedType, StedTekst, PartiId, PartiBogstav, PartiNavn,
                 StemmerAntal, Stemmeberettigede, DeltagelsePct,
IAltGyldigeStemmer,
       BlankeStemmer, AndreUgyldigeStemmer), stringsAsFactors = FALSE)
}

raw_path <- "../raw"
filenames <- dir(path = raw_path, pattern = "fintal_.*", full.names
= T)

result <- data.frame(StedType = factor(),
                     StedTekst = character(),
                     PartiId   = factor(),
                     PartiBogstav = factor(),
                     PartiNavn    = factor(),
                     StemmerAntal = integer(),
                     Stemmeberettigede = integer(),
                     DeltagelsePct = numeric(),
                     IAltGyldigeStemmer = integer(),
                     BlankeStemmer = integer(),
                     AndreUgyldigeStemmer = integer(),
                     stringsAsFactors = FALSE)

for (i in 1:length(filenames)) {
    #cat(paste0(filenames[i],"\n"))
    returnCode <-  tryCatch({
       result <- rbind(result, convert_one_file(filenames[i]))
    }, error = function(e) {
       cat(paste0(filenames[i]," failed:\n",e,"\n"))
    })
}

result$StedType <- as.factor(result$StedType)
result$PartiId <- as.factor(result$PartiId)
result$PartiBogstav <- as.factor(result$PartiBogstav)
result$PartiNavn <- as.factor(result$PartiNavn)
result$StemmerAntal <- as.integer(result$StemmerAntal)
result$Stemmeberettigede <- as.integer(result$Stemmeberettigede)
result$DeltagelsePct <- as.numeric(result$DeltagelsePct)
result$IAltGyldigeStemmer <- as.integer(result$IAltGyldigeStemmer)
result$BlankeStemmer <- as.integer(result$BlankeStemmer)
result$AndreUgyldigeStemmer <- as.integer(result$AndreUgyldigeStemmer)
str(result)
save(result, file = "folkeafstemning2009.Rdata")

	[[alternative HTML version deleted]]

Gerrit Eichner

2017-Nov-30 14:33 UTC

head link

[R] Help avoiding setting column type two times

See below.

Am 30.11.2017 um 15:27 schrieb Martin M?ller Skarbiniks
Pedersen:> Hi,
>    I think and hope this a good place to ask for code review for a R
> beginners?
> 
>    I have made a R script which generates a dataset based on 2009 danish
> referendum and it does work.
> 
>    But I think the code could be better and I would any comments how the
> code can be improved.
>    At least I would like to know how I avoid converting several of the
> columns to factors in the end of the code?
> 
> Description of the code:
> 
>    It reads a lot of xml-files from ../raw/ and saves a data.frame with
> information
> from these xml-files.
> 
>    In the ../raw/ directiory I have placed the xml-files which I got from
> "Statistics Denmark"
>    I have also put these xml-files on my website and they can be download
> freely from http://20dage.dk/R/referendum-2009/raw.tar.gz
> 
>    The code is below but I have also put the code at this place:
> http://20dage.dk/R/referendum-2009/convert_from_xml.R
> 
> Best Regards
> Martin M. S. Pedersen
> 
> -------
> library(xml2)
> 
> convert_one_file <- function(url) {
>      x <- read_xml(url)
> 
>      Sted <- xml_find_first(x, ".//Sted")
>      StedType <- xml_attr(Sted, "Type")
>      StedTekst <- xml_text(Sted)
> 
>      Parti <- xml_find_all(x, ".//Parti")
>      PartiId <- xml_attr(Parti, "Id")
>      PartiBogstav <- xml_attr(Parti, "Bogstav")
>      PartiNavn <- xml_attr(Parti, "Navn")
> 
> 
>      StemmerAntal <- xml_attr(Parti, "StemmerAntal")
>      Stemmeberettigede <- xml_integer(xml_find_first(x,
> ".//Stemmeberettigede"))
>      DeltagelsePct <- xml_double(xml_find_first(x,
".//DeltagelsePct"))
>      IAltGyldigeStemmer <- xml_integer(xml_find_first(x,
> ".//IAltGyldigeStemmer"))
>      BlankeStemmer <- xml_integer(xml_find_first(x,
".//BlankeStemmer"))
>      AndreUgyldigeStemmer <- xml_integer(xml_find_first(x,
> ".//AndreUgyldigeStemmer"))
> 
>      data.frame(cbind(StedType, StedTekst, PartiId, PartiBogstav,
PartiNavn,
>                   StemmerAntal, Stemmeberettigede, DeltagelsePct,
> IAltGyldigeStemmer,
>         BlankeStemmer, AndreUgyldigeStemmer), stringsAsFactors = FALSE)
> }
> 
> raw_path <- "../raw"
> filenames <- dir(path = raw_path, pattern = "fintal_.*",
full.names = T)
> 
> result <- data.frame(StedType = factor(),
>                       StedTekst = character(),
>                       PartiId   = factor(),
>                       PartiBogstav = factor(),
>                       PartiNavn    = factor(),
>                       StemmerAntal = integer(),
>                       Stemmeberettigede = integer(),
>                       DeltagelsePct = numeric(),
>                       IAltGyldigeStemmer = integer(),
>                       BlankeStemmer = integer(),
>                       AndreUgyldigeStemmer = integer(),
>                       stringsAsFactors = FALSE)
> 
> for (i in 1:length(filenames)) {
>      #cat(paste0(filenames[i],"\n"))
>      returnCode <-  tryCatch({
>         result <- rbind(result, convert_one_file(filenames[i]))
>      }, error = function(e) {
>         cat(paste0(filenames[i]," failed:\n",e,"\n"))
>      })
> }
> 
> result$StedType <- as.factor(result$StedType)
> result$PartiId <- as.factor(result$PartiId)
> result$PartiBogstav <- as.factor(result$PartiBogstav)
> result$PartiNavn <- as.factor(result$PartiNavn)
> result$StemmerAntal <- as.integer(result$StemmerAntal)
> result$Stemmeberettigede <- as.integer(result$Stemmeberettigede)
> result$DeltagelsePct <- as.numeric(result$DeltagelsePct)
> result$IAltGyldigeStemmer <- as.integer(result$IAltGyldigeStemmer)
> result$BlankeStemmer <- as.integer(result$BlankeStemmer)
> result$AndreUgyldigeStemmer <- as.integer(result$AndreUgyldigeStemmer)
> str(result)
> save(result, file = "folkeafstemning2009.Rdata")
Maybe two loops simplify this a little bit for you (not tested):

for(v in c("StedType", <etc.>))
  result[[v]] <- factor(result[[v]])

for(v in c("StemmerAntal", <etc.>))
  result[[v]] <- as.integer(result[[v]])

  Hth  --  Gerrit

---------------------------------------------------------------------
Dr. Gerrit Eichner                   Mathematical Institute, Room 212
gerrit.eichner at math.uni-giessen.de   Justus-Liebig-University Giessen
Tel: +49-(0)641-99-32104          Arndtstr. 2, 35392 Giessen, Germany
Fax: +49-(0)641-99-32109            http://www.uni-giessen.de/eichner
---------------------------------------------------------------------
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

David Winsemius

2017-Nov-30 16:23 UTC

head link

[R] Help avoiding setting column type two times

> On Nov 30, 2017, at 6:27 AM, Martin M?ller Skarbiniks Pedersen
<traxplayer at gmail.com> wrote:
> 
> Hi,
>  I think and hope this a good place to ask for code review for a R
> beginners?
> 
>  I have made a R script which generates a dataset based on 2009 danish
> referendum and it does work.
> 
>  But I think the code could be better and I would any comments how the
> code can be improved.
>  At least I would like to know how I avoid converting several of the
> columns to factors in the end of the code?
> 
> Description of the code:
> 
>  It reads a lot of xml-files from ../raw/ and saves a data.frame with
> information
> from these xml-files.
> 
>  In the ../raw/ directiory I have placed the xml-files which I got from
> "Statistics Denmark"
>  I have also put these xml-files on my website and they can be download
> freely from http://20dage.dk/R/referendum-2009/raw.tar.gz
> 
>  The code is below but I have also put the code at this place:
> http://20dage.dk/R/referendum-2009/convert_from_xml.R
> 
> Best Regards
> Martin M. S. Pedersen
> 
> -------
> library(xml2)
> 
> convert_one_file <- function(url) {
>    x <- read_xml(url)
> 
>    Sted <- xml_find_first(x, ".//Sted")
>    StedType <- xml_attr(Sted, "Type")
>    StedTekst <- xml_text(Sted)
> 
>    Parti <- xml_find_all(x, ".//Parti")
>    PartiId <- xml_attr(Parti, "Id")
>    PartiBogstav <- xml_attr(Parti, "Bogstav")
>    PartiNavn <- xml_attr(Parti, "Navn")
> 
> 
>    StemmerAntal <- xml_attr(Parti, "StemmerAntal")
>    Stemmeberettigede <- xml_integer(xml_find_first(x,
> ".//Stemmeberettigede"))
>    DeltagelsePct <- xml_double(xml_find_first(x,
".//DeltagelsePct"))
>    IAltGyldigeStemmer <- xml_integer(xml_find_first(x,
> ".//IAltGyldigeStemmer"))
>    BlankeStemmer <- xml_integer(xml_find_first(x,
".//BlankeStemmer"))
>    AndreUgyldigeStemmer <- xml_integer(xml_find_first(x,
> ".//AndreUgyldigeStemmer"))
> 
>    data.frame(cbind(StedType, StedTekst, PartiId, PartiBogstav, PartiNavn,
>                 StemmerAntal, Stemmeberettigede, DeltagelsePct,
> IAltGyldigeStemmer,
>       BlankeStemmer, AndreUgyldigeStemmer), stringsAsFactors = FALSE)
The construction `data.frame(cbind( ...` is a serious source of potential error.
The cbind coerces to matrix class which also then coerces to a single atomic
class, either numeric or character. Factors loose all their meaning. Dates get
messed up. Error ensues. Better would be:

 data.frame( StedType, StedTekst, PartiId, PartiBogstav, PartiNavn,
             StemmerAntal, Stemmeberettigede, DeltagelsePct,
             IAltGyldigeStemmer, BlankeStemmer, AndreUgyldigeStemmer,
             stringsAsFactors = FALSE)

-- 
David.

> }
> 
> raw_path <- "../raw"
> filenames <- dir(path = raw_path, pattern = "fintal_.*",
full.names = T)
> 
> result <- data.frame(StedType = factor(),
>                     StedTekst = character(),
>                     PartiId   = factor(),
>                     PartiBogstav = factor(),
>                     PartiNavn    = factor(),
>                     StemmerAntal = integer(),
>                     Stemmeberettigede = integer(),
>                     DeltagelsePct = numeric(),
>                     IAltGyldigeStemmer = integer(),
>                     BlankeStemmer = integer(),
>                     AndreUgyldigeStemmer = integer(),
>                     stringsAsFactors = FALSE)
> 
> for (i in 1:length(filenames)) {
>    #cat(paste0(filenames[i],"\n"))
>    returnCode <-  tryCatch({
>       result <- rbind(result, convert_one_file(filenames[i]))
>    }, error = function(e) {
>       cat(paste0(filenames[i]," failed:\n",e,"\n"))
>    })
> }
> 
> result$StedType <- as.factor(result$StedType)
> result$PartiId <- as.factor(result$PartiId)
> result$PartiBogstav <- as.factor(result$PartiBogstav)
> result$PartiNavn <- as.factor(result$PartiNavn)
> result$StemmerAntal <- as.integer(result$StemmerAntal)
> result$Stemmeberettigede <- as.integer(result$Stemmeberettigede)
> result$DeltagelsePct <- as.numeric(result$DeltagelsePct)
> result$IAltGyldigeStemmer <- as.integer(result$IAltGyldigeStemmer)
> result$BlankeStemmer <- as.integer(result$BlankeStemmer)
> result$AndreUgyldigeStemmer <- as.integer(result$AndreUgyldigeStemmer)
> str(result)
> save(result, file = "folkeafstemning2009.Rdata")
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
David Winsemius
Alameda, CA, USA

'Any technology distinguishable from magic is insufficiently advanced.' 
-Gehm's Corollary to Clarke's Third Law

R help - Nov 2017 - Help avoiding setting column type two times

[R] Help avoiding setting column type two times

[R] Help avoiding setting column type two times

[R] Help avoiding setting column type two times