Boxplot names returning integer instead of name - r

Question

I am trying to use the $names operator on my OutVals (outliers) to find the class these outliers are associated to and then put the outliers and their class name inside a data frame so I can see clearly from which class these outliers came from.
However, when trying to implement this, my class names return as "1", "2" etc... and not "Van", "Bus etc.. as it is in the dataset.
Have I missed something or am I approaching this completely wrong?
The goal is to get the outliers in the data and place them inside a table which shows from which class the outliers came from
Any help would be appreciated
I have shown my data frame as well as my reproduceable code below
library(reshape2)
vehData <-
structure(
list(
Samples = 1:6,
Comp = c(95L, 91L, 104L, 93L, 85L,
107L),
Circ = c(48L, 41L, 50L, 41L, 44L, 57L),
D.Circ = c(83L,
84L, 106L, 82L, 70L, 106L),
Rad.Ra = c(178L, 141L, 209L, 159L,
205L, 172L),
Pr.Axis.Ra = c(72L, 57L, 66L, 63L, 103L, 50L),
Max.L.Ra = c(10L,
9L, 10L, 9L, 52L, 6L),
Scat.Ra = c(162L, 149L, 207L, 144L, 149L,
255L),
Elong = c(42L, 45L, 32L, 46L, 45L, 26L),
Pr.Axis.Rect = c(20L,
19L, 23L, 19L, 19L, 28L),
Max.L.Rect = c(159L, 143L, 158L, 143L,
144L, 169L),
Sc.Var.Maxis = c(176L, 170L, 223L, 160L, 241L, 280L),
Sc.Var.maxis = c(379L, 330L, 635L, 309L, 325L, 957L),
Ra.Gyr = c(184L,
158L, 220L, 127L, 188L, 264L),
Skew.Maxis = c(70L, 72L, 73L,
63L, 127L, 85L),
Skew.maxis = c(6L, 9L, 14L, 6L, 9L, 5L),
Kurt.maxis = c(16L,
14L, 9L, 10L, 11L, 9L),
Kurt.Maxis = c(187L, 189L, 188L, 199L,
180L, 181L),
Holl.Ra = c(197L, 199L, 196L, 207L, 183L, 183L),
Class = c("van", "van", "saab", "van", "bus", "bus")
),
row.names = c(NA,
6L), class = "data.frame")
#Remove outliers function
removeOutliers <- function(data) {
OutVals <- boxplot(data)$out
namesforgroups <- boxplot(OutVals)$names #get group name of the outliers
dataf <- as.data.frame(OutVals, col.names = namesforgroups)#dataframe of outlier + names
print(OutVals) # show all outliers
remOutliers <- sapply(data, function(x) x[!x %in% OutVals]) #remove outliers from data
return (remOutliers)
}
#Remove class column and sample number
vehDataRemove1 <- vehData[, -1]
vehDataRemove2 <- vehDataRemove1[,-19]
vehData <- vehDataRemove2 #assign to new variable
vehClass <- vehData$Class #store original class names
#Begin removing outliers
removeOutliers1 <- removeOutliers(vehData) #remove first set of outliers
removeOutliers2 <- removeOutliers(removeOutliers1) #test again for more and remove
Output data frame

Answer 1

The information about which row/class name the outlier is tied to is not provided in the boxplot object. You have to get it yourself. What is given is the column that the outlier came from, inside boxplot(data)$group, so you can use which to see which row it was from, and use that to get what class it is. I rewrote your function and it now prints a table of the outlier value, the column it came from, and the row/class it came from. There are 5 outliers from 3 rows in the first iteration, and no outliers in the second iteration - makes sense because they've been removed.
removeOutliers <- function(data, class) {
x=boxplot(data)
OutVals <- x$out
columns <- x$group #get group name of the outliers
ind=numeric()
classes=c()
if (length(columns) > 0) {
for (i in 1:length(columns)) {
rows=which(data[,columns[i]]==OutVals[i])
ind=union(ind, rows)
classes=c(classes, class[rows])
}
dt=data.frame(OutVals, columns, classes) # show all outliers
print(dt)
return (list(data[-ind,], class[-ind]))
}
return(list(data, class))
}
#Remove class column and sample number
vehData1 <- vehData[, -c(1,20)]
vehClass <- vehData$Class #store original class names
#Begin removing outliers
removeOutliers1 <- removeOutliers(vehData1, vehClass) #remove first set of outliers
OutVals columns classes
1 103 5 bus
2 52 6 bus
3 6 6 bus
4 127 14 bus
5 14 15 saab
removeOutliers2 <- removeOutliers(removeOutliers1[[1]], removeOutliers1[[2]])
The first function returns a data frame with the outlier rows removed. The second function returns a table containing information about each outlier (the class, the column, and the value).
removeOutliers=function(data) {
x=boxplot(data %>% select(-Class), plot=FALSE)
outlierRows=c()
for (i in 1:length(x$out)) {
outlierRows=c(outlierRows, which(data[,x$group[i]]==x$out[i]))
}
return(data[-outlierRows,])
}
getOutliers=function(data) {
x=boxplot(data %>% select(-Class))
outlierInfo=data.frame()
for (i in 1:length(x$out)) {
rows=which(data[,x$group[i]]==x$out[i])
outlierInfo=bind_rows(outlierInfo, data.frame(class=data$Class[rows],
value=x$out[i],
column=names(data)[x$group[i]]))
}
return(outlierInfo)
}
removeOutliers(vehData)
Samples Comp Circ D.Circ Rad.Ra Pr.Axis.Ra Max.L.Ra Scat.Ra Elong Pr.Axis.Rect Max.L.Rect
1 1 95 48 83 178 72 10 162 42 20 159
2 2 91 41 84 141 57 9 149 45 19 143
4 4 93 41 82 159 63 9 144 46 19 143
Sc.Var.Maxis Sc.Var.maxis Ra.Gyr Skew.Maxis Skew.maxis Kurt.maxis Kurt.Maxis Holl.Ra Class
1 176 379 184 70 6 16 187 197 van
2 170 330 158 72 9 14 189 199 van
4 160 309 127 63 6 10 199 207 van
getOutliers(vehData)
class value column
1 bus 103 Pr.Axis.Ra
2 bus 52 Max.L.Ra
3 bus 6 Max.L.Ra
4 bus 127 Skew.Maxis
5 saab 14 Skew.maxis