KLMeasure: Rank-based smoothed precision/recall measure for projection.

In ProjectionBasedClustering: Projection Based Clustering

Rank-based smoothed precision/recall measure for projection.

Description

Computes rank-based smoothed precision/recall, with cost function based on Kullback-Leibler-divergence (see [Venna2010]).

Usage

KLMeasure(Data, pData, NeighborhoodSize = 20L)

Arguments

Data	numerical matrix of data: n cases in rows, d variables in columns
pData	numerical matrix of projected data: n cases in rows, k variables in columns, where k is the projection output dimension
NeighborhoodSize	Number of points in neighborhood to be considered. Default is 20

Value

SmoothedPrecision	Scalar, smoothed precision value
SmoothedRecall	Scalar, smoothed recall value

Note

C++ source code comes from https://research.cs.aalto.fi/pml/software/dredviz/

Author(s)

Michael Thrun

References

[Venna2010]: Jarkko Venna, Jaakko Peltonen, Kristian Nybo, Helena Aidos, and Samuel Kaski. Information Retrieval Perspective to Nonlinear Dimensionality Reduction for Data Visualization. Journal of Machine Learning Research, 11:451-490, 2010.

See Also

An alternative measure is the ContTrustMeasure

Examples

data('Hepta')
Data=Hepta$Data
res=MDS(Data)
Proj = res$ProjectedPoints

kl_m = KLMeasure(Hepta$Data, Proj)
# Smoothed precision
print(kl_m[[1]])
# Smoothed recall
print(kl_m[[2]])

ProjectionBasedClustering documentation built on Oct. 12, 2023, 1:07 a.m.