Genie: Fast and Robust Hierarchical Clustering

Genie is a robust hierarchical clustering algorithm (Gagolewski, Bartoszuk, Cena, 2016 ). 'genieclust' is its faster, more capable implementation (Gagolewski, 2021 ). It enables clustering with respect to mutual reachability distances, allowing it to act as an alternative to 'HDBSCAN*' that can identify any number of clusters or their entire hierarchy. When combined with the 'deadwood' package, it can act as an outlier detector. Additional package features include the Gini and Bonferroni inequality indices, external cluster validity measures (e.g., the normalised clustering accuracy, the adjusted Rand index, the Fowlkes-Mallows index, and normalised mutual information), and internal cluster validity indices (e.g., the Calinski-Harabasz, Davies-Bouldin, Ball-Hall, Silhouette, and generalised Dunn indices). The 'Python' version of 'genieclust' is available via 'PyPI'.

Proactive Conservation Index

Calculates the Proactive Conservation Index, a new tool to prioritize species for conservation, which can incorporate information about future threats.

An Implementation of the Stratification Index

An implementation of the stratification index proposed by Zhou (2012) . The package provides two functions, srank, which returns stratum-specific information, including population share and average percentile rank; and strat, which returns the stratification index and its approximate standard error. When a grouping factor is specified, strat also provides a detailed decomposition of the overall stratification into between-group and within-group components.

Repertoire Dissimilarity Index

Methods for calculation and visualization of the Repertoire Dissimilarity Index. Citation: Bolen and Rubelt, et al (2017) .

Constrained Single Index Model Estimation

Estimation of function and index vector in single index model ('sim') with (and w/o) shape constraints including different smoothness conditions. See, e.g., Kuchibhotla and Patra (2020) .

Single-Index Models with a Surface-Link

An implementation of a single-index regression for optimizing individualized dose rules from an observational study. To model interaction effects between baseline covariates and a treatment variable defined on a continuum, we employ two-dimensional penalized spline regression on an index-treatment domain, where the index is defined as a linear combination of the covariates (a single-index). An unspecified main effect for the covariates is allowed, which can also be modeled through a parametric model. A unique contribution of this work is in the parsimonious single-index parametrization specifically defined for the interaction effect term. We refer to Park, Petkova, Tarpey, and Ogden (2020) (for the case of a discrete treatment) and Park, Petkova, Tarpey, and Ogden (2021) "A single-index model with a surface-link for optimizing individualized dose rules" for detail of the method. The model can take a member of the exponential family as a response variable and can also take an ordinal categorical response. The main function of this package is simsl().

Efficient Computations of Standard Clustering Comparison Measures

Implements an efficient O(n) algorithm based on bucket-sorting for fast computation of standard clustering comparison measures. Available measures include adjusted Rand index (ARI), normalized information distance (NID), normalized mutual information (NMI), normalized variation information (NVI) and entropy, as described in Vinh et al (2009) . Include AMI (Adjusted Mutual Information) since version 0.1.2, a modified version of ARI (MARI), as described in Sundqvist et al. and simple Chi-square distance since version 1.0.0.

Penalized Youden Index Estimator

Implements the Penalized Youden Index Estimator (PYE) and the Covariate-Adjusted Youden Index Estimator (covYI), providing a novel framework for feature and covariate selection and combination in high-dimensional binary classification problems. Methodologies are based on Salaroli and Pardo (2023) and an unpublished manuscript by Salaroli and Pardo (2026) under review.

Compute Uniform Error Index

Uniform Error Index is the weighted average of different error measures. Uniform Error Index utilizes output from different error function and gives more robust and stable error values. This package has been developed to compute Uniform Error Index from ten different loss function like Error Square, Square of Square Error, Quasi Likelihood Error, LogR-Square, Absolute Error, Absolute Square Error etc. The weights are determined using Principal Component Analysis (PCA) algorithm of Yeasin and Paul (2024) .

Pacific Decadal Oscillation Index Data

Monthly Pacific Decadal Oscillation (PDO) index values from January 1900 to September 2018. Superseded by 'rsoi' package which includes the historical and most recent monthly PDO index values together with related climate indices.