| Title: | T-Distributed Stochastic Neighbor Embedding for R (t-SNE) |
|---|---|
| Description: | A "pure R" implementation of the t-SNE algorithm. |
| Authors: | Justin Donaldson <[email protected]> |
| Maintainer: | Justin Donaldson <[email protected]> |
| License: | GPL |
| Version: | 0.1-3 |
| Built: | 2024-11-08 06:13:57 UTC |
| Source: | https://github.com/jdonaldson/rtsne |
This package contains one function called tsne which contains all the functionality.
| Package: | tsne |
| Type: | Package |
| Version: | 0.1 |
| Date: | 2010-02-19 |
| License: | GPL |
| LazyLoad: | yes |
Justin Donaldson https://github.com/jdonaldson/rtsne Maintainer: Justin Donaldson ([email protected])
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.
L.J.P. van der Maaten. Learning a Parametric Embedding by Preserving Local Structure. In Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS), JMLR W&CP 5:384-391, 2009.
Provides a simple function interface for specifying t-SNE dimensionality reduction on R matrices or "dist" objects.
tsne(X, initial_config = NULL, k = 2, initial_dims = 30, perplexity = 30, max_iter = 1000, min_cost = 0, epoch_callback = NULL, whiten = TRUE, epoch=100)tsne(X, initial_config = NULL, k = 2, initial_dims = 30, perplexity = 30, max_iter = 1000, min_cost = 0, epoch_callback = NULL, whiten = TRUE, epoch=100)
X |
The R matrix or "dist" object |
initial_config |
an argument providing a matrix specifying the initial embedding for X. See Details. |
k |
the dimension of the resulting embedding. |
initial_dims |
The number of dimensions to use in reduction method. |
perplexity |
Perplexity parameter. (optimal number of neighbors) |
max_iter |
Maximum number of iterations to perform. |
min_cost |
The minimum cost value (error) to halt iteration. |
epoch_callback |
A callback function used after each epoch (an epoch here means a set number of iterations) |
whiten |
A boolean value indicating whether the matrix data should be whitened. |
epoch |
The number of iterations in between update messages. |
When the initial_config argument is specified, the algorithm will automatically enter the final momentum stage. This stage has less large scale adjustment to the embedding, and is intended for small scale tweaking of positioning. This can greatly speed up the generation of embeddings for various similar X datasets, while also preserving overall embedding orientation.
An R object containing a ydata embedding matrix, as well as a the matrix of probabilities P
Justin Donaldson ([email protected])
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.
L.J.P. van der Maaten. Learning a Parametric Embedding by Preserving Local Structure. In Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS), JMLR W&CP 5:384-391, 2009.
## Not run: colors = rainbow(length(unique(iris$Species))) names(colors) = unique(iris$Species) ecb = function(x,y){ plot(x,t='n'); text(x,labels=iris$Species, col=colors[iris$Species]) } tsne_iris = tsne(iris[,1:4], epoch_callback = ecb, perplexity=50) # compare to PCA dev.new() pca_iris = princomp(iris[,1:4])$scores[,1:2] plot(pca_iris, t='n') text(pca_iris, labels=iris$Species,col=colors[iris$Species]) ## End(Not run)## Not run: colors = rainbow(length(unique(iris$Species))) names(colors) = unique(iris$Species) ecb = function(x,y){ plot(x,t='n'); text(x,labels=iris$Species, col=colors[iris$Species]) } tsne_iris = tsne(iris[,1:4], epoch_callback = ecb, perplexity=50) # compare to PCA dev.new() pca_iris = princomp(iris[,1:4])$scores[,1:2] plot(pca_iris, t='n') text(pca_iris, labels=iris$Species,col=colors[iris$Species]) ## End(Not run)