@saehrimnir/druidjs / KMedoids

Class: KMedoids

Defined in: clustering/KMedoids.js:21

K-Medoids (PAM - Partitioning Around Medoids)

A robust clustering algorithm similar to K-Means, but uses actual data points (medoids) as cluster centers and can work with any distance metric.

See

KMeans for a faster but less robust alternative

Extends

• Clustering

Constructors

Constructor

new KMedoids(points: InputType, parameters?: Partial<ParametersKMedoids>): KMedoids;

Defined in: clustering/KMedoids.js:27

Parameters

Parameter	Type	Description
points	InputType	Data matrix
parameters	Partial<ParametersKMedoids>	-

Returns

KMedoids

See

https://link.springer.com/chapter/10.1007/978-3-030-32047-8_16 Faster k-Medoids Clustering: Improving the PAM, CLARA, and CLARANS Algorithms

Overrides

Clustering.constructor

Properties

Property	Type	Inherited from	Defined in
_A	Float64Array<ArrayBufferLike>[]	-	clustering/KMedoids.js:29
_cluster_medoids	number[]	-	clustering/KMedoids.js:40
_clusters	any[]	-	clustering/KMedoids.js:39
_D	number	Clustering._D	clustering/Clustering.js:19
_distance_matrix	Matrix	-	clustering/KMedoids.js:33
_is_initialized	boolean	-	clustering/KMedoids.js:41
_matrix	Matrix	Clustering._matrix	clustering/Clustering.js:15
_max_iter	number	-	clustering/KMedoids.js:32
_N	number	Clustering._N	clustering/Clustering.js:17
_parameters	ParametersKMedoids	Clustering._parameters	clustering/Clustering.js:13
_points	InputType	Clustering._points	clustering/Clustering.js:11
_randomizer	Randomizer	-	clustering/KMedoids.js:38

Accessors

k

Get Signature

get k(): number;

Defined in: clustering/KMedoids.js:72

Returns

number

---

medoids

Get Signature

get medoids(): number[];

Defined in: clustering/KMedoids.js:77

Returns

number[]

Methods

generator()

generator(): AsyncGenerator<number[][], void, unknown>;

Defined in: clustering/KMedoids.js:90

Returns

AsyncGenerator<number[][], void, unknown>

---

get_cluster_list()

get_cluster_list(): number[];

Defined in: clustering/KMedoids.js:45

Returns

number[]

The cluster list

Overrides

Clustering.get_cluster_list

---

get_clusters()

get_clusters(): number[][];

Defined in: clustering/KMedoids.js:53

Returns

number[][]

• Array of clusters with the indices of the rows in given points.

Overrides

Clustering.get_clusters

---

get_medoids()

get_medoids(): number[];

Defined in: clustering/KMedoids.js:82

Returns

number[]

---

init()

init(K: number, cluster_medoids: number[]): KMedoids;

Defined in: clustering/KMedoids.js:324

Computes K clusters out of the matrix.

Parameters

Parameter	Type	Description
K	number	Number of clusters.
cluster_medoids	number[]	-

Returns

KMedoids