No packages match

IBclust - Information Bottleneck Methods for Clustering Mixed-Type Data

Implements multiple variants of the Information Bottleneck ('IB') method for clustering datasets containing continuous, categorical (nominal/ordinal) and mixed-type variables. The package provides deterministic, agglomerative, generalised, sequential, and standard IB clustering algorithms that preserve relevant information while forming interpretable clusters. The Deterministic Information Bottleneck is described in Costa et al. (2026) <doi:10.1016/j.patcog.2026.113580>. The standard IB method originates from Tishby et al. (2000) <doi:10.48550/arXiv.physics/0004057>, the agglomerative variant from Slonim and Tishby (1999) <https://papers.nips.cc/paper/1651-agglomerative-information-bottleneck>, the generalised IB from Strouse and Schwab (2017) <doi:10.1162/NECO_a_00961>, and the sequential IB from Slonim et al. (2002) <doi:10.1145/564376.564401>. Diagnostic and plotting functions are provided to summarise, visualise, and predict from the resulting clusterings.

Last updated

cpp

3.74 score 1 stars 10 scripts 373 downloads

clustrd - Methods for Joint Dimension Reduction and Clustering

A class of methods that combine dimension reduction and clustering of continuous, categorical or mixed-type data (Markos, Iodice D'Enza and van de Velden 2019; <DOI:10.18637/jss.v091.i10>). For continuous data, the package contains implementations of factorial K-means (Vichi and Kiers 2001; <DOI:10.1016/S0167-9473(00)00064-5>) and reduced K-means (De Soete and Carroll 1994; <DOI:10.1007/978-3-642-51175-2_24>); both methods that combine principal component analysis with K-means clustering. For categorical data, the package provides MCA K-means (Hwang, Dillon and Takane 2006; <DOI:10.1007/s11336-004-1173-x>), i-FCB (Iodice D'Enza and Palumbo 2013, <DOI:10.1007/s00180-012-0329-x>) and Cluster Correspondence Analysis (van de Velden, Iodice D'Enza and Palumbo 2017; <DOI:10.1007/s11336-016-9514-0>), which combine multiple correspondence analysis with K-means. For mixed-type data, it provides mixed Reduced K-means and mixed Factorial K-means (van de Velden, Iodice D'Enza and Markos 2019; <DOI:10.1002/wics.1456>), which combine PCA for mixed-type data with K-means.

Last updated

1.67 score 47 scripts 511 downloads

idm - Incremental Decomposition Methods

Incremental Multiple Correspondence Analysis and Principal Component Analysis.

Last updated

1.11 score 13 scripts 475 downloads