我有一个类似于iris
的数据集,需要编写一个以以下方式处理离群值的函数:对于每个物种setosa
,versicolor
和virginica
,在每个变量iris$Sepal.Length
中, iris$Sepal.Width
,iris$Petal.Length
和Petal.Width
将超出1.5 * IQR的值替换为IQR +/- 1.5 * IQR的值(取决于它是高于还是低于IQR)。我一直在使用以下代码来实现此目的,但是它非常重复,耗时且容易出错。同样,以这种方式执行此操作会更改原始对象中的值。最好将参数合并到一个函数中,该函数不仅可以实现此目的,还可以告诉我更改了哪些值,并将所有输出保存到新的数据框中,而不用更改原始数据集中的值。
data(iris)
#create separate objects containing the data for each species
setosa <-
iris%>%
filter(Species == "setosa")
versicolor <-
iris%>%
filter(Species == "versicolor")
virginica <-
iris%>%
filter(Species == "virginica")
#for each variable within each species, do the following:
#create an object (qnt) that contains the 25th and 75th percentile
#create an object (H) containing the value of 1.5 times the interquartile range(IQR)
#replace any number less than the 25th percentile minus H with the value of the
#25th percentile minus H
#replace any number greater than the 75th percentile plus H with the value of the
#75th percentile plus H
qnt <- quantile(setosa$Sepal.Length, probs = c(.25, .75), na.rm = T)
H <- 1.5*IQR(setosa$Sepal.Length, na.rm = T)
setosa$Sepal.Length[setosa$Sepal.Length < (qnt[1] - H)] <- qnt[1]-H
setosa$Sepal.Length[setosa$Sepal.Length > (qnt[2] + H)] <- qnt[2]+H
qnt <- quantile(setosa$Sepal.Width, probs = c(.25, .75), na.rm = T)
H <- 1.5*IQR(setosa$Sepal.Width, na.rm = T)
setosa$Sepal.Width[setosa$Sepal.Width < (qnt[1] - H)] <- qnt[1]-H
setosa$Sepal.Width[setosa$Sepal.Width > (qnt[2] + H)] <- qnt[2]+H
qnt <- quantile(setosa$Petal.Length, probs = c(.25, .75), na.rm = T)
H <- 1.5*IQR(setosa$Petal.Length, na.rm = T)
setosa$Petal.Length[setosa$Petal.Length < (qnt[1] - H)] <- qnt[1]-H
setosa$Petal.Length[setosa$Petal.Length > (qnt[2] + H)] <- qnt[2]+H
qnt <- quantile(setosa$Petal.Width, probs = c(.25, .75), na.rm = T)
H <- 1.5*IQR(setosa$Petal.Width, na.rm = T)
setosa$Sepal.Width[setosa$Petal.Width < (qnt[1] - H)] <- qnt[1]-H
setosa$Sepal.Width[setosa$Petal.Width > (qnt[2] + H)] <- qnt[2]+H
#now do versicolor
qnt <- quantile(versicolor$Sepal.Length, probs = c(.25, .75), na.rm = T)
H <- 1.5*IQR(versicolor$Sepal.Length, na.rm = T)
versicolor$Sepal.Length[versicolor$Sepal.Length < (qnt[1] - H)] <- qnt[1]-H
versicolor$Sepal.Length[versicolor$Sepal.Length > (qnt[2] + H)] <- qnt[2]+H
qnt <- quantile(versicolor$Sepal.Width, probs = c(.25, .75), na.rm = T)
H <- 1.5*IQR(versicolor$Sepal.Width, na.rm = T)
versicolor$Sepal.Width[versicolor$Sepal.Width < (qnt[1] - H)] <- qnt[1]-H
versicolor$Sepal.Width[versicolor$Sepal.Width > (qnt[2] + H)] <- qnt[2]+H
qnt <- quantile(versicolor$Petal.Length, probs = c(.25, .75), na.rm = T)
H <- 1.5*IQR(versicolor$Petal.Length, na.rm = T)
versicolor$Petal.Length[versicolor$Petal.Length < (qnt[1] - H)] <- qnt[1]-H
versicolor$Petal.Length[versicolor$Petal.Length > (qnt[2] + H)] <- qnt[2]+H
qnt <- quantile(versicolor$Petal.Width, probs = c(.25, .75), na.rm = T)
H <- 1.5*IQR(versicolor$Petal.Width, na.rm = T)
versicolor$Sepal.Width[versicolor$Petal.Width < (qnt[1] - H)] <- qnt[1]-H
versicolor$Sepal.Width[versicolor$Petal.Width > (qnt[2] + H)] <- qnt[2]+H
#now do virginica
qnt <- quantile(virginica$Sepal.Length, probs = c(.25, .75), na.rm = T)
H <- 1.5*IQR(virginica$Sepal.Length, na.rm = T)
virginica$Sepal.Length[virginica$Sepal.Length < (qnt[1] - H)] <- qnt[1]-H
virginica$Sepal.Length[virginica$Sepal.Length > (qnt[2] + H)] <- qnt[2]+H
qnt <- quantile(virginica$Sepal.Width, probs = c(.25, .75), na.rm = T)
H <- 1.5*IQR(virginica$Sepal.Width, na.rm = T)
virginica$Sepal.Width[virginica$Sepal.Width < (qnt[1] - H)] <- qnt[1]-H
virginica$Sepal.Width[virginica$Sepal.Width > (qnt[2] + H)] <- qnt[2]+H
qnt <- quantile(virginica$Petal.Length, probs = c(.25, .75), na.rm = T)
H <- 1.5*IQR(virginica$Petal.Length, na.rm = T)
virginica$Petal.Length[virginica$Petal.Length < (qnt[1] - H)] <- qnt[1]-H
virginica$Petal.Length[virginica$Petal.Length > (qnt[2] + H)] <- qnt[2]+H
qnt <- quantile(virginica$Petal.Width, probs = c(.25, .75), na.rm = T)
H <- 1.5*IQR(virginica$Petal.Width, na.rm = T)
virginica$Sepal.Width[virginica$Petal.Width < (qnt[1] - H)] <- qnt[1]-H
virginica$Sepal.Width[virginica$Petal.Width > (qnt[2] + H)] <- qnt[2]+H
创建函数,然后按'Species'分组后将其应用于列,然后将其分配给新对象会更容易。对于dplyr
,除非我们使用magrittr
中的特殊运算符(%<>%
而不是%>%
),否则原始数据集不会即时更改。
f1 <- function(x) {
qnt <- quantile(x, probs = c(.25, .75), na.rm = TRUE)
H <- 1.5*IQR(x, na.rm = TRUE)
x[x< (qnt[1] - H)] <- qnt[1]-H
x[x> (qnt[2] + H)] <- qnt[2]+H
x
}
library(dplyr)
iris1 <- iris %>%
group_by(Species) %>%
mutate_at(vars(-group_cols()), f1)