Extrema-weighted feature extraction for varying length functional data. Functional data analysis method that performs dimensionality reduction based on predefined features and allows for quantile weighting. Method implemented as presented in van den Boom et al. (2018) <doi:10.1093/bioinformatics/bty120>.

Fit a two-step kernel ridge regression model for predicting edges in networks, and carry out cross-validation using shortcuts for swift and accurate performance assessment (Stock et al, 2018 <doi:10.1093/bib/bby095> ).

An implementation of the RuleFit algorithm as described in Friedman & Popescu (2008) <doi:10.1214/07-AOAS148>. eXtreme Gradient Boosting ('XGBoost') is used to build rules, and glmnet is used to fit a sparse linear model on the raw and rule features. The result is a model that learns similarly to a tree ensemble, while often offering improved interpretability and achieving improved scoring runtime in live applications. Several algorithms for reducing rule complexity are provided, most notably hyperrectangle de-overlapping. All algorithms scale to several million rows and support sparse representations to handle tens of thousands of dimensions.

This package implements exact algorithms for computing the distributions of the maximum, the minimum, the range, and the sum of the J largest order statistics of a multinomial random vector. Two complementary algorithm families are provided: the recursive tree-traversal method of Bonetti, Cirillo, and Ogay (2019) <doi:10.1098/rsos.190198>, which covers all four statistics under the equiprobable hypothesis; and the stochastic matrix method of Corrado (2011) <doi:10.1007/s11222-010-9174-3>, which handles the maximum, minimum, and range for arbitrary probability vectors. Functions for power evaluation and sample size determination for goodness-of-fit tests based on these order statistics are also provided. Computationally intensive routines are implemented in C++ for efficiency.

Compute surrogate explanation groves for predictive machine learning models and analyze complexity vs. explanatory power of an explanation according to Szepannek, G. and von Holt, B. (2023) <doi:10.1007/s41237-023-00205-2>.

Provide R functions to read/write/format Excel 2007 and Excel 97/2000/XP/2003 file formats.

The xlsxjars package collects all the external jars required for the xlxs package. This release corresponds to POI 3.13.

This package implements panel cointegration tests allowing for structural breaks and cross-section dependence following the methodology of Banerjee and Carrion-i-Silvestre (2015) <doi:10.1002/jae.2348>. The package provides iterative factor-break estimation, individual ADF tests on defactored residuals, standardized panel test statistics, and the Bai and Ng (2004) <doi:10.1111/j.1468-0262.2004.00528.x> MQ test for identifying common stochastic trends. Supports five model specifications with varying deterministic components and break structures.

Diagnostics for non-linear mixed-effects (population) models from NONMEM <https://www.iconplc.com/solutions/technologies/nonmem/>. xpose facilitates data import, creation of numerical run summary and provide ggplot2'-based graphics for data exploration and model diagnostics.

Extremely fast hashing of R objects using xxHash'. R objects are hashed via the standard serialization mechanism in R. Raw byte vectors and strings can be handled directly for compatibility with hashes created on other systems. This implementation is a wrapper around the xxHash C library which is available from <https://github.com/Cyan4973/xxHash>.

Translates a BNF (Backus-Naur Form) specification of a context-free language into an R grammar object which consists of the start symbol, the symbol table, the production table, and a short production table. The short production table is non-recursive. The grammar object contains the file name from which it was generated (without a path). In addition, it provides functions to determine the type of a symbol (isTerminal() and isNonterminal()) and functions to access the production table (rules() and derives()). For the BNF specification, see Backus, John et al. (1962) "Revised Report on the Algorithmic Language ALGOL 60". (ALGOL60 standards page <http://www.algol60.org/2standards.htm>, html-edition <https://www.masswerk.at/algol60/report.htm>) A preprocessor for macros which expand to standard BNF is included. The grammar compiler is an extension of the APL2 implementation in Geyer-Schulz, Andreas (1997, ISBN:978-3-7908-0830-X).

Support for interfaces from R to other languages, built around a class for evaluators and a combination of functions, classes and methods for communication. Will be used through a specific language interface package. Described in the book "Extending R".

This package provides tools to analyze sex differences in omics data for complex diseases. It includes functions for differential expression analysis using the limma method <doi:10.1093/nar/gkv007>, interaction testing between sex and disease, pathway enrichment with clusterProfiler <doi:10.1089/omi.2011.0118>, and gene regulatory network (GRN) construction and analysis using igraph'. The package enables a reproducible workflow from raw data processing to biological interpretation.

This package implements the bootstrap slope heterogeneity test for panel data based on Blomquist and Westerlund (2015) <doi:10.1007/s00181-015-0978-z>. Tests the null hypothesis that slope coefficients are homogeneous across cross-sectional units. Provides both standard and adjusted Delta statistics with bootstrap p-values. Supports partialling out of control variables and cross-sectional averages for dealing with cross-sectional dependence.

Calculates a number of valuation adjustments including CVA, DVA, FBA, FCA, MVA and KVA. A two-way margin agreement has been implemented. For the KVA calculation four regulatory frameworks are supported: CEM, (simplified) SA-CCR, OEM and IMM. The probability of default is implied through the credit spreads curve. The package supports an exposure calculation based on SA-CCR which includes several trade types and a simulated path which is currently available only for Interest Rate Swaps. The latest regulatory capital charge methodologies have been implementing including BA-CVA & SA-CVA.

An extension for the xml2 package to transform XML documents by applying an xslt style-sheet.

Analysis of crossover interference in experimental crosses, particularly regarding the gamma model. See, for example, Broman and Weber (2000) <doi:10.1086/302923>.

Create beautifully color-coordinated and customized themes for your xaringan slides, without writing any CSS. Complete your slide theme with ggplot2 themes that match the font and colors used in your slides. Customized styles can be created directly in your slides R Markdown source file or in a separate external script.

Adding some at-present missing functionality, or functions unlikely to be added to the base xpose package. This includes some diagnostic plots that have been missing in translation from xpose4', but also some useful features that truly extend the capabilities of what can be done with xpose'. These extensions include the concept of a set of xpose objects, and diagnostics for likelihood-based models.

Import an XML document with nested object structures and convert it into a relational data model. The result is a set of R dataframes with foreign key relationships. The data model and the data can be exported as SQL code of different SQL flavors.

Derivation tree operations are needed for implementing grammar-based genetic programming and grammatical evolution: Generating a random derivation trees of a context-free grammar of bounded depth, decoding a derivation tree, choosing a random node in a derivation tree, extracting a tree whose root is a specified node, and inserting a subtree into a derivation tree at a specified node. These operations are necessary for the initialization and for decoders of a random population of programs, as well as for implementing crossover and mutation operators. Depth-bounds are guaranteed by switching to a grammar without recursive production rules. For executing the examples, the package BNF is needed. The basic tree operations for generating, extracting, and inserting derivation trees as well as the conditions for guaranteeing complete derivation trees have been presented in Geyer-Schulz (1997, ISBN:978-3-7908-0830-X). The use of random integer vectors for the generation of derivation trees has been introduced in Ryan, C., Collins, J. J., and O'Neill, M. (1998) <doi:10.1007/BFb0055930> for grammatical evolution.

There are two new network metrics, RWC (random walk centrality) and CBET (counting betweenness). Also available are the normalized versions of those metrics. These measures of centrality and betweenness are particularly useful for the analysis of very dense weighted networks which include loops. Traditional measures do not work as well for those network characteristics. The main reference is DePaolis at al (2022) <doi:10.1007/s41109-022-00519-2>.

Representation-dependent gene-level operations for genetic and evolutionary algorithms with real-coded genes used in the R-package xega <https://CRAN.R-project.org/package=xega> are collected in this package. The common feature of the gene operations is that all of them are useful for derivation-free optimization algorithms. At the moment the package implements initialization, mutation, crossover, and replication operations for differential evolution as described in Price, Kenneth V., Storn, Rainer M. and Lampinen, Jouni A. (2005) <doi:10.1007/3-540-31306-0>. In addition, several (more recent) methods for determining the scale factor are provided. For xega''s architecture, see Geyer-Schulz, A. (2025) <doi:10.5445/IR/1000187255>.

This package implements a probabilistic approach to time series forecasting combining XGBoost regression with conformal inference methods. The package provides functionality for generating predictive distributions, evaluating uncertainty, and optimizing hyperparameters using Bayesian, coarse-to-fine, or random search strategies.