npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2024 – Pkg Stats / Ryan Hefner

k-means-plus

v1.0.0

Published

K-means++ clustering a classification of data, so that points assigned to the same cluster are similar (in some sense). It is identical to the K-means algorithm, except for the selection of initial conditions.

Downloads

3

Readme

major-colors

K-means++ clustering a classification of data, so that points assigned to the same cluster are similar (in some sense). It is identical to the K-means algorithm, except for the careful selection of initial conditions. It is a way of avoiding the sometimes poor clusterings found by the standard k-means algorithm. k-means++ variance address this major theoretic shortcoming and guarantee an approximation ratio O(log k) in expectation (over the randomness of the algorithm), where k is the number of clusters used.

Install

npm i k-means-plus
yarn add k-means-plus

Usage

import KMeansCluster from 'k-means-plus';
const cluster = new KMeansCluster({ distance, maximumIterations, convergedFn });
const results = cluster.cluster(vectors, k);
import KMeansCluster from 'k-means-plus';

const data = [
  {'company': 'Microsoft' , 'size': 91259, 'revenue': 60420},
  {'company': 'IBM' , 'size': 400000, 'revenue': 98787},
  {'company': 'Skype' , 'size': 700, 'revenue': 716},
  {'company': 'SAP' , 'size': 48000, 'revenue': 11567},
  {'company': 'Yahoo!' , 'size': 14000 , 'revenue': 6426 },
  {'company': 'eBay' , 'size': 15000, 'revenue': 8700},
];

// Create the data 2D-array (vectors) describing the data
let vectors = [];
for (let i = 0 ; i < data.length ; i++) {
  vectors.push([ data[i]['size'] , data[i]['revenue']]);
}

const k = 4;

const cluster = new KMeansCluster();

const {
  model: { observations, centroids, assignments },
  iterations,
  durationMs
} = cluster.cluster(vectors, k);

Constructor

  • distance - (vector1: [number], vector2: [number]) => number distance function used for clustering between two vectors.
  • Default: euclidean distance
  • maximumIterations - number maximum iterations of clustering.
  • Default: 200
  • convergedFn - (centroids1: [[number]], centroids2: [[number]]) => boolean determine if two consecutive set of centroids are converged.
  • Default: the clusters are converged if the cluster assignments are the same.

Inputs

  • vectors - [[number]] point vectors to cluster
  • k - number of final clusters

Outputs

type result = {
  model: {
    observations: [[number]], // the original vectors to cluster
    centroids: [[number]], // vectors of the centers of cluster
    assignments: [number] // mapping from index of original vector to the index of cluter center it belongs to
  },
  iterations: number, // number of iterations ran before converging
  durationMs: number // the duration of the algorithm
}