Enable dependent variable discretization the same as FSelector:::equal.frequency.binning.discretization about fselectorrcpp HOT 14 CLOSED

> FSelector:::information.gain.body
function (formula, data, type = c("infogain", "gainratio", "symuncert"), 
    unit) 
{
    type = match.arg(type)
    new_data = get.data.frame.from.formula(formula, data)
    new_data = discretize.all(formula, new_data)
    attr_entropies = sapply(new_data, entropyHelper, unit)
    class_entropy = attr_entropies[1]
    attr_entropies = attr_entropies[-1]
    joint_entropies = sapply(new_data[-1], function(t) {
        entropyHelper(data.frame(cbind(new_data[[1]], t)), unit)
    })
    results = class_entropy + attr_entropies - joint_entropies
    if (type == "gainratio") {
        results = ifelse(attr_entropies == 0, 0, results/attr_entropies)
    }
    else if (type == "symuncert") {
        results = 2 * results/(attr_entropies + class_entropy)
    }
    attr_names = dimnames(new_data)[[2]][-1]
    return(data.frame(attr_importance = results, row.names = attr_names))
}
<environment: namespace:FSelector>
> FSelector:::discretize.all
function (formula, data) 
{
    new_data = get.data.frame.from.formula(formula, data)
    dest_column_name = dimnames(new_data)[[2]][1]
    if (!is.factor(new_data[[1]])) {
        new_data[[1]] = equal.frequency.binning.discretization(new_data[[1]], 
            5)
    }
    new_data = supervised.discretization(formula, data = new_data)
    new_data = get.data.frame.from.formula(formula, new_data)
    return(new_data)
}
<environment: namespace:FSelector>
> FSelector:::equal.frequency.binning.discretization
function (data, bins) 
{
    bins = as.integer(bins)
    if (!is.numeric(data)) 
        stop("Data must be numeric")
    if (bins < 1) 
        stop("Number of bins too small")
    complete = complete.cases(data)
    ord = order(data)
    len = length(data[complete])
    blen = len/bins
    new_data = data
    p1 = p2 = 0
    for (i in 1:bins) {
        p1 = p2 + 1
        p2 = round(i * blen)
        new_data[ord[p1:min(p2, len)]] = i
    }
    return(factor(new_data))
}
<environment: namespace:FSelector>

information_gain( equal = FALSE)
@param equal A logical; whether to discretize dependent variable with the \code{equal frequency binning discretization} or whether to not provide discretization for the dependent variable?