Package: som.nn 1.4.4

som.nn: Topological k-NN Classifier Based on Self-Organising Maps

A topological version of k-NN: An abstract model is build as 2-dimensional self-organising map. Samples of unknown class are predicted by mapping them on the SOM and analysing class membership of neurons in the neighbourhood.

Authors:Andreas Dominik

som.nn_1.4.4.tar.gz
som.nn_1.4.4.zip(r-4.5)som.nn_1.4.4.zip(r-4.4)som.nn_1.4.4.zip(r-4.3)
som.nn_1.4.4.tgz(r-4.4-any)som.nn_1.4.4.tgz(r-4.3-any)
som.nn_1.4.4.tar.gz(r-4.5-noble)som.nn_1.4.4.tar.gz(r-4.4-noble)
som.nn_1.4.4.tgz(r-4.4-emscripten)som.nn_1.4.4.tgz(r-4.3-emscripten)
som.nn.pdf |som.nn.html✨
som.nn/json (API)

# Install 'som.nn' in R:

install.packages('som.nn', repos = c('https://andreasdominik.r-universe.dev', 'https://cloud.r-project.org'))

On CRAN:

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

22 exports 2.14 score 7 dependencies 9 mentions 25 scripts 167 downloads

Last updated 6 months agofrom:f5d6f4842d. Checks:OK: 7. Indexed: yes.

Target	Result	Date
Doc / Vignettes	OK	Sep 01 2024
R-4.5-win	OK	Sep 01 2024
R-4.5-linux	OK	Sep 01 2024
R-4.4-win	OK	Sep 01 2024
R-4.4-mac	OK	Sep 01 2024
R-4.3-win	OK	Sep 01 2024
R-4.3-mac	OK	Sep 01 2024

Exports:dist.fun.bubble dist.fun.inverse dist.fun.linear dist.fun.tricubic dist.torus initialize norm.linear norm.softmax plot predict som.nn.accuracy som.nn.all.accuracy som.nn.confusion som.nn.continue som.nn.export.kohonen som.nn.export.som som.nn.multitrain som.nn.set som.nn.train som.nn.validate som.nn.visual SOMnn

Dependencies:class hexbin kohonen lattice MASS Rcpp som

Citation

Readme and manuals

Help Manual

Help page	Topics
Topological k-NN Classifier Based on Self-Organising Maps	som.nn-package som.nn
Bubble distance functions for topological k-NN classifier	dist.fun.bubble
Inverse exponential distance functions for topological k-NN classifier	dist.fun.inverse
Linear distance functions for topological k-NN classifier	dist.fun.linear
Tricubic distance functions for topological k-NN classifier	dist.fun.tricubic
Torus distance matrix	dist.torus
Constructor of SOMnn Class	initialize,ANY,ANY-method initialize,SOMnn-method
Linear normalisation	norm.linear
Softmax normalisation	norm.softmax
Plot method for S4 class 'SOMnn'	plot,SOMnn,ANY-method plot,SOMnn-method
predict method for S4 class 'SOMnn'	predict,SOMnn-method
Advanced rounding of vectors	round.probabilities
Calculate accuracy measures	som.nn.accuracy
Calculate overall accuracy	som.nn.all.accuracy
Calculate confusion matrix	som.nn.confusion
Continue hexagonal som training	som.nn.continue
Export a som.nn model as object of type 'kohonen'	som.nn.export.kohonen
Export a som.nn model as object of type 'SOM'	som.nn.export.som
Multi-step hexagonal som training	som.nn.multitrain
Set parameters for k-NN-like classifier in som.nn model	som.nn.set
Hexagonal som training	som.nn.train
Predict class labels for a validation dataset	som.nn.validate
Mapping function for SOMnn	som.nn.visual
An S4 class to hold a model for the topological classifier som.nn	SOMnn SOMnn-class

Package: som.nn 1.4.4

som.nn: Topological k-NN Classifier Based on Self-Organising Maps

Citation

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)