Uniform manifold approximation and projection is a technique for dimension reduction. The algorithm was described by [McInnes et al., 2018].
UniformManifoldApproximationProjection(DataOrDistances, k,Epochs,OutputDimension=2,Algorithm='umap_pkg',PlotIt=FALSE,Cls,...)
List of
[1:n,OutputDimension], n by OutputDimension matrix containing coordinates of the Projection
output of umap or of package uwot depending on Algorithm
specific settings used in UniformManifoldApproximationProjection
Numerical matrix defined as either
Data, i.e., [1:n,1:d], nonsymmetric, and consists of n cases of d-dimensional data points with every case having d attributes, variables or features,
or
Distances, i.e.,[1:n,1:n], symmetric and consists of n cases, e.g., as.matrix(dist(Data,method))
number of k nearest neighbors, Important parameter, if not given, settings of package umap will be used, default of package umap is currently 15
Number of eppochs (scalar), i.e, training length, default of package umap is currently 200
Number of dimensions in the Outputspace, default=2
"umap_pkg": provides an interface for two implementations. One is written from scratch other one requires python umap
"uwot_pkg": complete re-implementation in R (and C++, via the 'Rcpp' package) of uwot
Default: FALSE, If TRUE: Plots the projection as a 2d visualization. OutputDimension>2: only the first two dimensions will be shown
Optional,: only relevant if PlotIt=TRUE. Numeric vector, given Classification in numbers: every element is the cluster number of a certain corresponding element of data.
one of the other 21 parameters that can be specified, please see umap.defaults of package umap for details or parameters to be set in package uwot depending on the choice of Algorithm.
Michael Thrun
To the knowledge of the author of this function no peer-reviewed publication of the method exists. Use with greate care.
[McInnes et al., 2018] McInnes, L., Healy, J., & Melville, J.: Umap: Uniform manifold approximation and projection for dimension reduction, arXiv preprint arXiv:1802.03426, 2018.
[Ultsch/Siemon, 1990] Ultsch, A., & Siemon, H. P.: Kohonen's Self Organizing Feature Maps for Exploratory Data Analysis, International Neural Network Conference, pp. 305-308, Kluwer Academic Press, Paris, France, 1990.
umap of umap
umap of uwot
data('Hepta')
Data=Hepta$Data
Proj=UniformManifoldApproximationProjection(Data)
if (FALSE) {
PlotProjectedPoints(Proj$ProjectedPoints,Hepta$Cls)
}
Run the code above in your browser using DataLab