r 删除不同类型的nas的功能...来自http://stackoverflow.com/questions/4862178/remove-rows-with-nas-in-data-frame

Posted 2021-05-24

#' keep rows that have a certain number of NAs anywhere/somewhere and delete others
#' @param df a data frame
#' @param col restrict to the columns where you would like to search for NA; eg, 3, c(3), 2:5, "place", c("place","age")
#' \cr default is NULL, search for all columns
#' @param n integer or vector, 0, c(3,5), number/range of NAs allowed.
#' \cr Range includes both ends 3<=n<=5
#' \cr Range could be -Inf, Inf
#' @return returns a new df with rows that have NA(s) removed
#' @export
z.na.keep = function(df, col=NULL, n=0){
    if (!is.null(col)) {
        df.temp = df[,col]
    } else {
        df.temp = df
    }

    if (length(n)==1){
        if (n==0) {
            # simply call complete.cases which might be faster
            result = df[complete.cases(df.temp),]
        } else {
            # credit: http://stackoverflow.com/a/30461945/2292993
            log <- apply(df.temp, 2, is.na)
            logindex <- apply(log, 1, function(x) sum(x) == n)
            result = df[logindex, ]
        }
    }

    if (length(n)==2){
        min = n[1]; max = n[2]
        log <- apply(df.temp, 2, is.na)
        logindex <- apply(log, 1, function(x) {sum(x) >= min && sum(x) <= max})
        result = df[logindex, ]
    }

    return(result)
}