R/blank2na.R

In emilBeBri/dttools: Useful Tools Built Around Data.Table

#' Replaces blank-ish elements of a factor or character vector to NA
#' @description Replaces blank-ish elements of a factor or character vector to NA
#' @param x a vector of factor or character or any type
#' @param na.strings case sensitive strings that will be coverted to NA. The function will do a trimws(x,'both') before conversion. If NULL, do only trimws, no conversion to NA.
#' @return Returns a vector trimws (always for factor, character) and NA converted (if matching na.strings). Attributes will also be kept ('label','labels', 'value.labels').
#' @export
#' 

  # https://stackoverflow.com/a/53176586/396566

blank2na = function(x,na.strings=c('','.','NA','na','N/A','n/a','NaN','nan')) {
    if (is.factor(x)) {
        lab = attr(x, 'label', exact = T)
        labs1 <- attr(x, 'labels', exact = T)
        labs2 <- attr(x, 'value.labels', exact = T)

        # trimws will convert factor to character
        x = trimws(x,'both')
        if (! is.null(lab)) lab = trimws(lab,'both')
        if (! is.null(labs1)) labs1 = trimws(labs1,'both')
        if (! is.null(labs2)) labs2 = trimws(labs2,'both')

        if (!is.null(na.strings)) {
            # convert to NA
            x[x %in% na.strings] = NA
            # also remember to remove na.strings from value labels 
            labs1 = labs1[! labs1 %in% na.strings]
            labs2 = labs2[! labs2 %in% na.strings]
        }

        # the levels will be reset here
        x = factor(x)

        if (! is.null(lab)) attr(x, 'label') <- lab
        if (! is.null(labs1)) attr(x, 'labels') <- labs1
        if (! is.null(labs2)) attr(x, 'value.labels') <- labs2
    } else if (is.character(x)) {
        lab = attr(x, 'label', exact = T)
        labs1 <- attr(x, 'labels', exact = T)
        labs2 <- attr(x, 'value.labels', exact = T)

        # trimws will convert factor to character
        x = trimws(x,'both')
        if (! is.null(lab)) lab = trimws(lab,'both')
        if (! is.null(labs1)) labs1 = trimws(labs1,'both')
        if (! is.null(labs2)) labs2 = trimws(labs2,'both')

        if (!is.null(na.strings)) {
            # convert to NA
            x[x %in% na.strings] = NA
            # also remember to remove na.strings from value labels 
            labs1 = labs1[! labs1 %in% na.strings]
            labs2 = labs2[! labs2 %in% na.strings]
        }

        if (! is.null(lab)) attr(x, 'label') <- lab
        if (! is.null(labs1)) attr(x, 'labels') <- labs1
        if (! is.null(labs2)) attr(x, 'value.labels') <- labs2
    } else {
        x = x
    }
    return(x)
}