アールメカブ

Rの備忘録

古い記事だがhttp://tolstoy.newcastle.edu.au/R/e2/help/06/10/3064.html に以下のような関数がある

expand.dft <- function(x, na.strings = "NA", as.is = FALSE, dec = ".") { 
 # Take each row in the source data frame table and replicate it   
# using the Freq value 
 DF <- sapply(1:nrow(x), function(i) x[rep(i, each = x$Freq[i]), ],     simplify = FALSE)

 # Take the above list and rbind it to create a single DF   
# Also subset the result to eliminate the Freq column

  DF <- subset(do.call("rbind", DF), select = -Freq)

 # Now apply type.convert to the character coerced factor
 #  columns   # to facilitate data type selection for each column    

DF <- as.data.frame(lapply(DF, 
        function(x) 
            type.convert(as.character(x),
                       na.strings = na.strings,
                       as.is = as.is,
                        dec = dec)))
 # Return data frame 
 DF 
}

これを応用したのだと思う関数がNCStatsパッケージ の expandTable 関数に実装されている．

> source("http://www.rforge.net/NCStats/InstallNCStats.R")
> library(NCStats)
> ?NCStats

> expandTable
function (x, var.names = NULL, ...) 
{
   x <- as.data.frame.table(x)
   df <- sapply(1:nrow(x), function(i) x[rep(i, each = x[i, 
       "Freq"]), ], simplify = FALSE)
   df <- subset(do.call("rbind", df), select = -Freq)
   for (i in 1:ncol(df)) {
       df[[i]] <- type.convert(as.character(df[[i]]), ...)
   }
   rownames(df) <- NULL
   if (!is.null(var.names)) {
       if (length(var.names) < dim(df)[2]) 
           stop("Too few var.names given.")
       else if (length(var.names) > dim(df)[2]) 
           stop("Too many var.names given.")
       else names(df) <- var.names
   }
   df
}
<environment: namespace:NCStats>