【Bioinfo Blog 001】【R Code 001】——TukeyMethodToRemoveOutliers

Introduction

Tukey’s Test：用于计算出数据集中最大和最小估计值，超出的值即被认为是异常值。

计算过程：有哪些比较好的做异常值检测的方法？

R Code

outlierKD <- function(dt, var) {
  var_name <- eval(substitute(var),eval(dt))
  tot <- sum(!is.na(var_name))
  na1 <- sum(is.na(var_name))
  m1 <- mean(var_name, na.rm = T)
  par(mfrow=c(2, 2), oma=c(0,0,3,0))
  boxplot(var_name, main="With outliers") 
  hist(var_name, main="With outliers", xlab=NA, ylab=NA)
  outlier <- boxplot.stats(var_name)$out
  mo <- mean(outlier)
  var_name <- ifelse(var_name %in% outlier, NA, var_name)
  boxplot(var_name, main="Without outliers")
  hist(var_name, main="Without outliers", xlab=NA, ylab=NA)
  title("Outlier Check", outer=TRUE)
  na2 <- sum(is.na(var_name))
  cat("Outliers identified:", na2 - na1, "\n")
  cat("Propotion (%) of outliers:", round((na2 - na1) / tot*100, 1), "\n")
  cat("Mean of the outliers:", round(mo, 2), "\n")
  m2 <- mean(var_name, na.rm = T)
  cat("Mean without removing outliers:", round(m1, 2), "\n")
  cat("Mean if we remove outliers:", round(m2, 2), "\n")
  response <- readline(prompt="Do you want to remove outliers and to replace with NA? [yes/no]: ")
  if(response == "y" | response == "yes"){
    dt[as.character(substitute(var))] <- invisible(var_name)
    assign(as.character(as.list(match.call())$dt), dt, envir = .GlobalEnv)
    cat("Outliers successfully removed", "\n")
    return(invisible(dt))
  } else{
    cat("Nothing changed", "\n")
    return(invisible(var_name))
  }
}

outlierKD(dataset, dataset$chosencol)