Package: PPCI 0.1.5

David Hofmeyr

PPCI: Projection Pursuit for Cluster Identification

Implements recently developed projection pursuit algorithms for finding optimal linear cluster separators. The clustering algorithms use optimal hyperplane separators based on minimum density, Pavlidis et. al (2016) <https://jmlr.csail.mit.edu/papers/volume17/15-307/15-307.pdf>; minimum normalised cut, Hofmeyr (2017) <doi:10.1109/TPAMI.2016.2609929>; and maximum variance ratio clusterability, Hofmeyr and Pavlidis (2015) <doi:10.1109/SSCI.2015.116>.

Authors:David Hofmeyr <[email protected]> [aut, cre] Nicos Pavlidis <[email protected]> [aut]

# Install 'PPCI' in R:

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

Uses libs:

Datasets:

On CRAN:

Last updated 5 years agofrom:aa8fa12f6c. Checks:1 OK, 10 WARNING. Indexed: yes.

Help page	Topics
Projection Pursuit for Cluster Identification	PPCI-package PPCI
Discrimination of Cancerous and Non-Cancerous Breast Masses	breastcancer
External Cluster Validity Metrics	cluster_performance
Eryhemato-Squamous Disease Identification	dermatology
Divisive Clustering Using Maximum Clusterability	mcdc
Maximum Clusterability Dimension Reduction	mcdr
Maximum Clusteriability Hyperplane	mch
Divisive Clustering Using Minimum Density Hyperplanes	mddc
Minimum Density Dimension Reduction	mddr
Minimum Density Hyperplane	mdh
Divisive Clustering Using Minimum Normalised Cut Hyperplanes	ncutdc
Minimum Normalised Cut Dimension Reduction	ncutdr
Minimum Normalised Cut Hyperplane	ncuth
Optical Recognition of Handwritten Digits	optidigits
Visualise Cluster Means from optidigits data set	optidigits_mean_images
Pen-based Recognition of Handwritten Digits	pendigits
Speech Recognition through Phoneme Identification	phoneme
Evaluate External Valifity os a Binary Partition	success_ratio
Prune a Hierarchical Clustering Model	tree_prune
Split a Leaf in a Hierarchical Clustering Model	tree_split
Face Recognition	yale