Local Outlier Factor (LOF)
LOF: Identifying Density-Based Local Outliers.
LOF( U, seq_k = c(4, 10, 30), combine = max, robMaha = FALSE, log = TRUE, ncores = 1 )
U |
A matrix, from which to detect outliers (rows). E.g. PC scores. |
seq_k |
Sequence of numbers of nearest neighbors to use.
If multiple |
combine |
How to combine results for multiple |
robMaha |
Whether to use a robust Mahalanobis distance instead of the
normal euclidean distance? Default is |
log |
Whether to return the logarithm of LOFs? Default is |
ncores |
Number of cores to use. Default is |
Breunig, Markus M., et al. "LOF: identifying density-based local outliers." ACM sigmod record. Vol. 29. No. 2. ACM, 2000.
X <- readRDS(system.file("testdata", "three-pops.rds", package = "bigutilsr"))
svd <- svds(scale(X), k = 10)
llof <- LOF(svd$u)
hist(llof, breaks = nclass.scottRob)
tukey_mc_up(llof)
llof_maha <- LOF(svd$u, robMaha = TRUE)
hist(llof_maha, breaks = nclass.scottRob)
tukey_mc_up(llof_maha)
lof <- LOF(svd$u, log = FALSE)
hist(lof, breaks = nclass.scottRob)
str(hist_out(lof))
str(hist_out(lof, nboot = 100))
str(hist_out(lof, nboot = 100, breaks = "FD"))Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.