Make sure a data frame has been "fun through" a function

d <- data.frame(X=1:5, Y=log(1:5), G=factor(rep(c("a","b"),c(2,3))))
attr(d, "checked") <- TRUE
wasChecked <- function(x) isTRUE(attr(x, "checked"))
wasChecked(d)

wasChecked(d[1:4,]) # select some rows

wasChecked(d[,1:2]) # select some columns

d[1,1] <- 10 # change a single value
wasChecked(d)

d$NewColumn <- 11:15 # add a column
wasChecked(d)

On Tue, 21 Feb 2017, stephen sefick wrote:

Sorry for not being clear. I have never used S3 methods before. Below is
some R code that sketches out my idea. Is this a sensible solution?

Sure. See comments (untested) inline.

Chuck

test_data <- data.frame(a=1:10, b=1:10, c=1:10)

functionA <- function(x, impossible_genotype){
   ##some data processing
   y <- x

   ##return S3 to be able to use impossible genotype later
   class(y) <- append(class(y),"genotypes")

     class(y) <- c("genotypes",class(y))

   attr(y, "impossible_genotype") <- impossible_genotype

   return(y)
}

test_data_genotypes <- functionA(test_data, impossible_genotype="Ref")

functionB <- function(x){
   ##stop if pre-processed with functionA
   if(sum(class(x)=="genotypes")!=1){stop("Need to pre-process data with
functionA")}

    if(!(inherits("genotypes")){
        stop("Need to pre-process data with functionA")}


or in functionA you could skip the class()<- and just set the
"impossible_genotypes" attribute to FALSE when there are none such.

Then here test

     if (is.null(attr(x,"impossible_genotypes"))){
                stop("Need to pre-process data with functionA")
        } else {
                return(alleles)
        }

   ##use this later in functionB to
   impossible_genotype <- attributes(x)$impossible_genotype

     impossible_genotype <- attr(x,"impossible_genotype")

   alleles <- c("Ref", "Alt")

   coded_genotype <- alleles[alleles!=impossible_genotype]

     maybe `!is.element(alleles,impossible_genotype)' is safer than `!='

   return(coded_genotype)
}

##stop if not pre-processed with functionA
functionB(test_data)

##processed with functionA
functionB(test_data_genotypes)