LOF vs kNN
It is common to look first at the points with highest anomaly scores before taking any action. When several algorithms are used, the points with highest scores may differ.
In this final exercise, you'll calculate new LOF and kNN distance scores for the wine
data, and print the highest scoring point for each.
This exercise is part of the course
Introduction to Anomaly Detection in R
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Scaled wine data
wine_scaled <- scale(wine)
# Calculate distance matrix
wine_nn <-
# Append score column to data
wine$score_knn <-