Sign Up for Free

RunKit +

Try any Node.js package right in your browser

This is a playground to test code. It runs a full Node.js environment and already has all of npm’s 400,000 packages pre-installed, including @aidanconnelly/tsnejs with all npm packages installed. Try it out:

var tsnejs = require("@aidanconnelly/tsnejs")

This service is provided by RunKit and is not affiliated with npm, Inc or the package authors.

@aidanconnelly/tsnejs v0.1.4

t-SNE visualization algorithm

tSNEJS

tSNEJS is an implementation of t-SNE visualization algorithm in Javascript.

t-SNE is a visualization algorithm that embeds things in 2 or 3 dimensions. If you have some data and you can measure their pairwise differences, t-SNE visualization can help you identify clusters in your data.

Online demo

The main project website has a live example and more description.

There is also the t-SNE CSV demo that allows you to simply paste CSV data into a textbox and tSNEJS computes and visualizes the embedding on the fly (no coding needed).

Research Paper

The algorithm was originally described in this paper:

L.J.P. van der Maaten and G.E. Hinton.
Visualizing High-Dimensional Data Using t-SNE. Journal of Machine Learning Research
9(Nov):2579-2605, 2008.

You can find the PDF here.

Example

npm --save i @jwalsh/tsnejs
import * as tsnejs from '@jwalsh/tsnejs';

const opt = {
  epsilon: 10,    // epsilon is learning rate (10 = default)
  perplexity: 30, // roughly how many neighbors each point influences (30 = default)
  dim: 2 // dimensionality of the embedding (2 = default)
};

const tsne = new tsnejs.tSNE(opt); // create a tSNE instance

// initialize data. Here we have 3 points and some example pairwise dissimilarities
const dists = [[1.0, 0.1, 0.2], [0.1, 1.0, 0.3], [0.2, 0.1, 1.0]];
tsne.initDataDist(dists);

// every time you call this, solution gets better
[...Array(500)].forEach((_, i) => tsne.step());

const Y = tsne.getSolution(); // Y is an array of 2-D points that you can plot

The data can be passed to tSNEJS as a set of high-dimensional points using the tsne.initDataRaw(X) function, where X is an array of arrays (high-dimensional points that need to be embedded). The algorithm computes the Gaussian kernel over these points and then finds the appropriate embedding.

API

getopt

syntax sugar

Parameters

  • opt
  • field
  • defaultval

return_v

return 0 mean unit standard deviation random number

randn

return random normal number

zeros

utilitity that creates contiguous vector of zeros of size n

Parameters

  • n

randn2d

utility that returns 2d array filled with random numbers or with value s, if provided

L2

compute L2 distance between two vectors

xtod

compute pairwise distance in all vectors in X

d2p

compute (p_{i|j} + p_{j|i})/(2n)

sign

helper function

Parameters

  • x

tSNE

t-SNE visualization algorithm

Web Demos

There are two web interfaces to this library that we are aware of:

  • By Andrej, here.
  • By Laurens, here, which takes data in different format and can also use Google Spreadsheet input.

About

Send questions to @karpathy.

License

MIT

Metadata

RunKit is a free, in-browser JavaScript dev environment for prototyping Node.js code, with every npm package installed. Sign up to share your code.
Sign Up for Free