https://github.com/danaugrs/go-tsne

t-Distributed Stochastic Neighbor Embedding (t-SNE) in Go
https://github.com/danaugrs/go-tsne

3d data-science dimensionality-reduction go machine-learning tsne unsupervised-learning visualization

Last synced: 2 months ago
JSON representation

t-Distributed Stochastic Neighbor Embedding (t-SNE) in Go

• Host: GitHub
• URL: https://github.com/danaugrs/go-tsne
• Owner: danaugrs
• License: bsd-3-clause
• Created: 2018-09-03T21:27:53.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2023-12-10T17:52:11.000Z (about 1 year ago)
• Last Synced: 2024-06-21T18:52:29.080Z (7 months ago)
• Topics: 3d, data-science, dimensionality-reduction, go, machine-learning, tsne, unsupervised-learning, visualization
• Language: Go
• Homepage:
• Size: 90.2 MB
• Stars: 203
• Watchers: 12
• Forks: 24
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-golang-repositories - go-tsne - Distributed Stochastic Neighbor Embedding (t-SNE) in Go (Repositories)

README

        
# go-tsne

A Go implementation of [t-Distributed Stochastic Neighbor Embedding (t-SNE)](https://lvdmaaten.github.io/tsne/), a prize-winning technique for dimensionality reduction particularly well suited for visualizing high-dimensional datasets.



  

   



### Usage

Import this library:

```Go

import "github.com/danaugrs/go-tsne/tsne"

```

Create the TSNE object:

```Go

t := tsne.NewTSNE(2, 300, 100, 300, true)

```

The parameters are

* Number of output dimensions

* Perplexity

* Learning rate

* Max number of iterations

* Verbosity

There are two ways to start the t-SNE embedding optimization. The regular way is to provide an `n` by `d` matrix where each row is a datapoint and each column is a dimension:

```Go

Y := t.EmbedData(X, nil)

```

The alternative is to provide a distance matrix directly:

```Go

Y := t.EmbedDistances(D, nil)

```

In either case, the returned matrix `Y` will contain the final embedding.

For more fine-grained control, a step function can be provided in either case:

```Go

Y := t.EmbedData(X, func(iter int, divergence float64, embedding mat.Matrix) bool {

  fmt.Printf("Iteration %d: divergence is %v\n", iter, divergence)

  return false

})

```

The step function has access to the iteration, the current divergence, and the embedding optimized so far.

You can return `true` to halt the optimization.

### Examples

Two examples are provided - `mnist2d` and `mnist3d`. They both use the same data - a subset of [MNIST](http://yann.lecun.com/exdb/mnist/) with 2500 handwritten digits. `mnist2d` generates plots throughout the optimization process, and `mnist3d` shows the optimization happening in real-time, in 3D. `mnist3d` depends on [G3N](https://github.com/g3n/engine).

To run an example, `cd` to the example's directory, build it, and execute it, e.g:

```

cd examples/mnist2d

go build

./mnist2d

```

### Support

I hope you enjoy using and learning from go-tsne as much as I enjoyed writing it.

If you come across any issues, please [report them](https://github.com/danaugrs/go-tsne/issues).