CMeansConfig

Properties

k

integer≥ 1

Number of clusters.

max_iter

integer≥ 1

Maximum number of iterations.

dist

string

Distance measure.

one of"euclidean""manhattan"

method

string

"cmeans" = fuzzy c-means; "ufcl" = on-line update.

one of"cmeans""ufcl"

m

number> 1

Degree of fuzzification.

rate_par

number | null≥ 0≤ 1

Learning rate for the online (ufcl) variant.

weightstunable

number

Case weights: either a scalar, applied to every case, or a vector. A vector must have one value per case.

control

object

Control parameters passed to the clustering backend.

Relationships