View source: R/nearestNeighbors.R
nearestNeighbors | R Documentation |
Find nearest neighbors of each instance using relief.method Used for npdr (no hits or misses specified in neighbor function).
nearestNeighbors(
attr.mat,
nbd.method = "multisurf",
nbd.metric = "manhattan",
sd.vec = NULL,
sd.frac = 0.5,
k = 0,
neighbor.sampling = "none",
att_to_remove = c(),
fast.dist = FALSE,
dopar.nn = FALSE
)
attr.mat |
m x p matrix of m instances and p attributes, or m x m distance matrix if metric is 'precomputed' |
nbd.method |
neighborhood method 'multisurf' or 'surf' (no k) or 'relieff' if you want to specify k (required k). |
nbd.metric |
used in npdrDistances for distance matrix between instances. parameter can be 'precomputed' if user-supplied distance matrix. default to 'manhattan' (numeric input). |
sd.vec |
vector of standard deviations for surf |
sd.frac |
multiplier of the standard deviation from the mean distances, subtracted from mean distance to create for SURF or multiSURF radius. The multiSURF default "dead-band radius" is sd.frac=0.5: mean - sd/2 |
k |
number of constant nearest hits/misses for |
neighbor.sampling |
"none" or |
att_to_remove |
attributes for removal (possible confounders) from the distance matrix calculation. |
fast.dist |
whether or not distance is computed by faster algorithm in wordspace, default as F |
dopar.nn |
whether or not neighborhood is computed in parallel, default as F |
Ri_NN.idxmat, matrix of Ri's (first column) and their NN's (second column)
# multisurf neighborhood with sigma/2 (sd.frac=0.5) "dead-band" boundary
neighbor.pairs.idx <- nearestNeighbors(
predictors.mat,
nbd.method = "multisurf",
nbd.metric = "manhattan",
sd.frac = 0.5
)
head(neighbor.pairs.idx)
# reliefF (fixed-k) neighborhood using default `k` equal to
# theoretical surf expected value.
# One can change the theoretical value by changing sd.frac (default 0.5).
neighbor.pairs.idx <- nearestNeighbors(
predictors.mat,
nbd.method = "relieff",
nbd.metric = "manhattan"
)
head(neighbor.pairs.idx)
# reliefF (fixed-k) neighborhood with a user-specified k
neighbor.pairs.idx <- nearestNeighbors(
predictors.mat,
nbd.method = "relieff",
nbd.metric = "manhattan",
k = 10
)
head(neighbor.pairs.idx)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.