Quantification is a prominent machine learning task that has received an increasing amount of attention in the last years. The objective is to predict the class distribution of a data sample. This package is a collection of machine learning algorithms for class distribution estimation. This package include algorithms from different paradigms of quantification. These methods are described in the paper: A. Maletzke, W. Hassan, D. dos Reis, and G. Batista. The importance of the test set size in quantification assessment. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI20, pages 2640â 2646, 2020. <doi:10.24963/ijcai.2020/366>.

Generates Raven like matrices according to different rules and the response list associated to the matrix. The package can generate matrices composed of 4 or 9 cells, along with a response list of 11 elements (the correct response + 10 incorrect responses). The matrices can be generated according to both logical rules (i.e., the relationships between the elements in the matrix are manipulated to create the matrix) and visual-spatial rules (i.e., the visual or spatial characteristics of the elements are manipulated to generate the matrix). The graphical elements of this package are based on the DescTools package. This package has been developed within the PRIN2020 Project (Prot. 20209WKCLL) titled "Computerized, Adaptive and Personalized Assessment of Executive Functions and Fluid Intelligence" and founded by the Italian Ministry of Education and Research.

This package provides a collection of functions for computations and visualizations of microbial pan-genomes.

Supports visual interpretation of hierarchical composite endpoints (HCEs). HCEs are complex constructs used as primary endpoints in clinical trials, combining outcomes of different types into ordinal endpoints, in which each patient contributes the most clinically important event (one and only one) to the analysis. See Karpefors M et al. (2022) <doi:10.1177/17407745221134949>.

This package provides functions for comparing survival curves using the max-combo test at a single timepoint or repeatedly at successive respective timepoints while controlling type I error (i.e., the group sequential setting), as published by Prior (2020) <doi:10.1177/0962280220931560>. The max-combo test is a generalization of the weighted log-rank test, which itself is a generalization of the log-rank test, which is a commonly used statistical test for comparing survival curves, e.g., during or after a clinical trial as part of an effort to determine if a new drug or therapy is more effective at delaying undesirable outcomes than an established drug or therapy or a placebo.

Perform multivariate modeling of evolved traits, with special attention to understanding the interplay of the multi-factorial determinants of their origins in complex ecological settings (Stephens, 2007 <doi:10.1016/j.tree.2006.12.003>). This software primarily concentrates on phylogenetic regression analysis, enabling implementation of tree transformation averaging and visualization functionality. Functions additionally support information theoretic approaches (Grueber, 2011 <doi:10.1111/j.1420-9101.2010.02210.x>; Garamszegi, 2011 <doi:10.1007/s00265-010-1028-7>) such as model averaging and selection of phylogenetic models. Accessory functions are also implemented for coef standardization (Cade 2015), selection uncertainty, and variable importance (Burnham & Anderson 2000). There are other numerous functions for visualizing confounded variables, plotting phylogenetic trees, as well as reporting and exporting modeling results. Lastly, as challenges to ecology are inherently multifarious, and therefore often multi-dataset, this package features several functions to support the identification, interpolation, merging, and updating of missing data and outdated nomenclature.

This package provides tools for multiscale systematic conservation planning using the H3 hierarchical hexagonal grid system (Uber Technologies (2024) <https://h3geo.org>) and the prioritizr package (Hanson et al. (2025) <doi:10.1111/cobi.14376>). Supports the definition and solution of conservation problems across nested H3 resolutions with resolution-specific features, costs, and management attributes, including cross-scale connectivity penalties derived from parent-child relationships. Also includes utilities to evaluate solutions using multiscale-aware diagnostics and to post-process optimization outputs into alternative area-targeted conservation scenarios.

This package provides a lavaan'-like syntax for OpenMx models. The syntax supports definition variables, bounds, and parameter transformations. This allows for latent growth curve models with person-specific measurement occasions, moderated nonlinear factor analysis and much more.

The user must supply a matrix filled with similarity values. The software will search for significant differences between similarity values at different hierarchical levels. The algorithm will return a Loess-smoothed plot of the similarity values along with the inflection point, if there are any. There is the option to search for an inflection point within a specified range. The package also has a function that will return the matrix components at a specified cutoff. References: Mullner. <ArXiv:1109.2378>; Cserhati, Carter. (2020, Journal of Creation 34(3):41-50), <https://dl0.creation.com/articles/p137/c13759/j34-3_64-73.pdf>.

This package provides a graphical user interface tool to estimate ploidy from DNA cells stained with fluorescent dyes and analyzed by flow cytometry, following the methodology of Gómez-Muñoz and Fischer (2024) <doi:10.1101/2024.01.24.577056>. Features include multiple file uploading and configuration, peak fluorescence intensity detection, histogram visualizations, peak error curation, ploidy and genome size calculations, and easy results export.

The effects of the site may severely bias the accuracy of a multisite machine-learning model, even if the analysts removed them when fitting the model in the training set and applying the model in the test set (Solanes et al., Neuroimage 2023, 265:119800). This simple R package estimates the accuracy of a multisite machine-learning model unbiasedly, as described in (Solanes et al., Psychiatry Research: Neuroimaging 2021, 314:111313). It currently supports the estimation of sensitivity, specificity, balanced accuracy (for binary or multinomial variables), the area under the curve, correlation, mean squarer error, and hazard ratio for binomial, multinomial, gaussian, and survival (time-to-event) outcomes.

This package provides a user-friendly tool for visualizing categorical or group movement.

This package provides a variety of functions useful for data analysis, selection, manipulation, and graphics.

An ensemble classifier for multiclass classification. This is a novel classifier that natively works as an ensemble. It projects data on a large number of matrices, and uses very simple classifiers on each of these projections. The results are then combined, ideally via Dempster-Shafer Calculus.

Interfaces the python library zuko implementing Masked Autoregressive Flows. See Rozet, Divo and Schnake (2023) <doi:10.5281/zenodo.7625672> and Papamakarios, Pavlakou and Murray (2017) <doi:10.48550/arXiv.1705.07057>.

Clean the MS/MS spectrum, calculate spectral entropy, unweighted entropy similarity, and entropy similarity for mass spectrometry data. The entropy similarity is a novel similarity measure for MS/MS spectra which outperform the widely used dot product similarity in compound identification. For more details, please refer to the paper: Yuanyue Li et al. (2021) "Spectral entropy outperforms MS/MS dot product similarity for small-molecule compound identification" <doi:10.1038/s41592-021-01331-z>.

Density evaluation, random generation, and maximum likelihood estimation for the Mobius-von Mises-Fisher and isotropic scaled von Mises-Fisher distributions on the hypersphere, introduced in Garcia-Portugues and Kato (2026) <doi:10.48550/arXiv.2607.29280>. Both distributions arise from Mobius transport of a von Mises-Fisher distribution.

Multi-penalty linear, logistic and cox ridge regression, including estimation of the penalty parameters by efficient (repeated) cross-validation and marginal likelihood maximization. Multiple high-dimensional data types that require penalization are allowed, as well as unpenalized variables. Paired and preferential data types can be specified. See Van de Wiel et al. (2021), <arXiv:2005.09301>.

This package provides methods and classes for adding m-activation ("multiplicative activation") layers to MLR or multivariate logistic regression models. M-activation layers created in this library detect and add input interaction (polynomial) effects into a predictive model. M-activation can detect high-order interactions -- a traditionally non-trivial challenge. Details concerning application, methodology, and relevant survey literature can be found in this library's vignette, "About.".

Mass-balance-adjusted Regression algorithm for streamflow reconstruction at sub-annual resolution (e.g., seasonal or monthly). The algorithm implements a penalty term to minimize the differences between the total sub-annual flows and the annual flow. The method is described in Nguyen et al (2020) <DOI:10.1002/essoar.10504791.1>.

Estimates models that extend the standard GLM to take misclassification into account. The models require side information from a secondary data set on the misclassification process, i.e. some sort of misclassification probabilities conditional on some common covariates. A detailed description of the algorithm can be found in Dlugosz, Mammen and Wilke (2015) <https://ftp.zew.de/pub/zew-docs/dp/dp15043.pdf>.

This package provides tools for training, selecting, and evaluating maximum entropy (and standard logistic regression) distribution models. This package provides tools for user-controlled transformation of explanatory variables, selection of variables by nested model comparison, and flexible model evaluation and projection. It follows principles based on the maximum- likelihood interpretation of maximum entropy modeling, and uses infinitely- weighted logistic regression for model fitting. The package is described in Vollering et al. (2019; <doi:10.1002/ece3.5654>).

Provides an interactive toolkit for educational and psychological measurement implemented using the shiny framework. The package supports content validity analysis, dimensionality assessment, and Classical Test Theory using the CTT package (Willse, 2018) <doi:10.32614/CRAN.package.CTT>. Item Response Theory (IRT) analyses are conducted via mirt (Chalmers, 2012) <doi:10.18637/jss.v048.i06>. Exploratory Factor Analysis is performed using psych (Revelle, 2025), while Confirmatory Factor Analysis (CFA) and Structural Equation Modeling (SEM) are based on the lavaan framework (Rosseel, 2012) <doi:10.18637/jss.v048.i02>. The CFA/SEM module features interactive model specification, automatic model comparison, modification indices, comprehensive fit diagnostics, path diagram visualization, and HTML report generation. The application allows users to upload data, evaluate statistical models, visualize results, and export outputs through an intuitive graphical interface without requiring programming experience.

This package contains functions intended to facilitate the production of plant taxonomic monographs. The package includes functions to convert tables into taxonomic descriptions, lists of collectors, examined specimens, identification keys (dichotomous and interactive), and can generate a monograph skeleton. Additionally, wrapper functions to batch the production of phenology histograms and distributional and diversity maps are also available.