数据框中的异常值，但我想对 R 中的数据框中的分组行执行此操作

Question

Example dataframe.

I want to detect outliers per group and display it in a separate dataframe, for example, for each species name, anthopleura aureradiata , I want to look at values 27.75, 6.83, and 23.91, and calculate the outliers between these values. If I find that row 4 is an outlier for that particular species, I want to display it in my new dataframe. Does anyone know how to get about this?

Reproducible example:

x = data.frame("species" = c("Agao", "Beta", "Beta", "Beta", "Carrot", "Carrot"), "sum" = c(1, 100, 5, 4, 3, 0))

Answer 1

We can modify this function based on our requirement and use it to filter outliers for each group and create a new dataframe.

library(dplyr)

remove_outliers <- function(x, na.rm = TRUE, ...) {
    qnt <- quantile(x, probs=c(.25, .75), na.rm = na.rm, ...)
    H <- 1.5 * IQR(x, na.rm = na.rm)
    x < (qnt[1] - H) | x > (qnt[2] + H)
}

separate_dataframe <- x %>% group_by(species) %>% filter(remove_outliers(sum))
separate_dataframe

# species   sum
#  <fct>   <dbl>
#1 Beta     -100

data

x = data.frame(species = c("Agao", "Beta", "Beta", "Beta", "Beta", 
              "Carrot", "Carrot"),sum = c(1, 1, 5, 4, -100, 3,0))