Skor jarak k-nearest neighbors

Pengantar Deteksi Anomali di R

Alastair Rushworth

Data Scientist

Dimensi furnitur

plot(Width ~ Height, data = furniture)

Pengantar Deteksi Anomali di R

Jarak k-nearest neighbors (kNN)

Anomali biasanya jauh dari tetangganya

Pengantar Deteksi Anomali di R

Input untuk perhitungan matriks jarak

library(FNN)
furniture_knn <- get.knn(data = furniture, k = 5)

 

Argumen

  • data: matriks data
  • k: jumlah tetangga
Pengantar Deteksi Anomali di R

Keluaran matriks jarak

get.knn() mengembalikan dua matriks

names(furniture_knn)
"nn.index" "nn.dist" 

Matriks jarak

head(furniture_knn$nn.dist, 3)
         [,1]     [,2]     [,3]     [,4]     [,5]
[1,] 5.128300 5.367791 5.390801 5.740713 8.477025
[2,] 4.300093 5.367791 6.159139 7.091966 7.428176
[3,] 3.047502 3.545978 4.426266 5.006570 5.654202
Pengantar Deteksi Anomali di R

Skor jarak kNN

Rata-rata jarak ke tetangga terdekat

furniture_score <- rowMeans(furniture_knn$nn.dist)

 

Skor terbesar?

which.max(furniture_score)
29
Pengantar Deteksi Anomali di R

Ayo berlatih!

Pengantar Deteksi Anomali di R

Preparing Video For Download...