Density Based Clustering for JavaScript

Package contains popular methods for cluster analysis in data mining:

• DBSCAN
• OPTICS
• K-MEANS

Overview

DBSCAN

Density-based spatial clustering of applications with noise (DBSCAN) is one of the most popular algorithm for clustering data.

http://en.wikipedia.org/wiki/DBSCAN

OPTICS

Ordering points to identify the clustering structure (OPTICS) is an algorithm for clustering data similar to DBSCAN. The main difference between OPTICS and DBSCAN is that it can handle data of varying densities.

http://en.wikipedia.org/wiki/OPTICS_algorithm

Important

Clustering returned by OPTICS is nearly indistinguishable from a clustering created by DBSCAN. To extract different density-based clustering as well as hierarchical structure you need to analyse reachability plot generated by OPTICS.

For more information visit http://en.wikipedia.org/wiki/OPTICS_algorithm#Extracting_the_clusters

K-MEANS

K-means clustering is one of the most popular method of vector quantization, originally from signal processing. Although this method is not density-based, it's included in the library for completeness.

http://en.wikipedia.org/wiki/K-means_clustering

Installation

Node:

1npm install density-clustering

Browser:

1bower install density-clustering
2# build
3npm install
4gulp

Examples

DBSCAN

1var dataset = [
2    [1,1],[0,1],[1,0],
3    [10,10],[10,13],[13,13],
4    [54,54],[55,55],[89,89],[57,55]
5];
6
7var clustering = require('density-clustering');
8var dbscan = new clustering.DBSCAN();
9// parameters: 5 - neighborhood radius, 2 - number of points in neighborhood to form a cluster
10var clusters = dbscan.run(dataset, 5, 2);
11console.log(clusters, dbscan.noise);
12
13/*
14RESULT:
15[
16    [0,1,2],
17    [3,4,5],
18    [6,7,9],
19    [8]
20]
21
22NOISE: [ 8 ]
23*/

OPTICS

1// REGULAR DENSITY
2var dataset = [
3  [1,1],[0,1],[1,0],
4  [10,10],[10,11],[11,10],
5  [50,50],[51,50],[50,51],
6  [100,100]
7];
8
9var clustering = require('density-clustering');
10var optics = new clustering.OPTICS();
11// parameters: 2 - neighborhood radius, 2 - number of points in neighborhood to form a cluster
12var clusters = optics.run(dataset, 2, 2);
13var plot = optics.getReachabilityPlot();
14console.log(clusters, plot);
15
16/*
17RESULT:
18[
19  [0,1,2],
20  [3,4,5],
21  [6,7,8],
22  [9]
23]
24*/

1// VARYING DENSITY
2var dataset = [
3  [0,0],[6,0],[-1,0],[0,1],[0,-1],
4  [45,45],[45.1,45.2],[45.1,45.3],[45.8,45.5],[45.2,45.3],
5  [50,50],[56,50],[50,52],[50,55],[50,51]
6];
7
8var clustering = require('density-clustering');
9var optics = new clustering.OPTICS();
10// parameters: 6 - neighborhood radius, 2 - number of points in neighborhood to form a cluster
11var clusters = optics.run(dataset, 6, 2);
12var plot = optics.getReachabilityPlot();
13console.log(clusters, plot);
14
15/*
16RESULT:
17[
18  [0, 2, 3, 4],
19  [1],
20  [5, 6, 7, 9, 8],
21  [10, 14, 12, 13],
22  [11]
23]
24*/

K-MEANS

1var dataset = [
2  [1,1],[0,1],[1,0],
3  [10,10],[10,13],[13,13],
4  [54,54],[55,55],[89,89],[57,55]
5];
6
7var clustering = require('density-clustering');
8var kmeans = new clustering.KMEANS();
9// parameters: 3 - number of clusters
10var clusters = kmeans.run(dataset, 3);
11console.log(clusters);
12
13/*
14RESULT:
15[
16  [0,1,2,3,4,5],
17  [6,7,9],
18  [8]
19]
20*/

Testing

Open folder and run:

1mocha -R spec

License

Software is licensed under MIT license. For more information check LICENSE file.