STG is a method for feature selection in neural network. The procedure is based on probabilistic relaxation of the l0 norm of features, or the count of the number of selected features. The framework simultaneously learns either a nonlinear regression or classification function while selecting a small subset of features. Read more: Yamada et al. (2020) <https://proceedings.mlr.press/v119/yamada20a.html>.

Converts LESS to CSS. It uses V8 engine, where LESS parser is run. Functions for LESS text, file or folder conversion are provided. This work was supported by a junior grant research project by Czech Science Foundation GACR no. GJ18-04150Y'.

Perform robust estimation and inference in platform trials and other master protocol trials. Yuhan Qian, Yifan Yi, Jun Shao, Yanyao Yi, Gregory Levin, Nicole Mayer-Hamblett, Patrick J. Heagerty, Ting Ye (2025) <doi:10.48550/arXiv.2411.12944>.

Quantifies and explains end-to-end traceability between clinical submission artifacts (ADaM (Analysis Data Model) outputs, derivations, SDTM (Study Data Tabulation Model) sources, specs, code). Builds trace models from metadata and mapping sheets, computes trace levels, and emits standardized R4SUB (R for Regulatory Submission) evidence table rows via r4subcore'.

Wrapper for Datamuse API to find rhyming and other associated words. This includes words of similar meaning, spelling, or other related words. Learn more about the Datamuse API here <https://www.datamuse.com/api/>.

Multi-block data analysis concerns the analysis of several sets of variables (blocks) observed on the same group of individuals. The main aims of the RGCCA package are: to study the relationships between blocks and to identify subsets of variables of each block which are active in their relationships with the other blocks. This package allows to (i) run R/SGCCA and related methods, (ii) help the user to find out the optimal parameters for R/SGCCA such as regularization parameters (tau or sparsity), (iii) evaluate the stability of the RGCCA results and their significance, (iv) build predictive models from the R/SGCCA. (v) Generic print() and plot() functions apply to all these functionalities.

The visualization tool offers a nuanced understanding of regression dynamics, going beyond traditional per-unit interpretation of continuous variables versus categorical ones. It highlights the impact of unit changes as well as larger shifts like interquartile changes, acknowledging the distribution of empirical data. Furthermore, it generates visualizations depicting alterations in Odds Ratios for predictors across minimum, first quartile, median, third quartile, and maximum values, aiding in comprehending predictor-outcome interplay within empirical data distributions, particularly in logistic regression frameworks.

We rewrite of RAMpath software developed by John McArdle and Steven Boker as an R package. In addition to performing regular SEM analysis through the R package lavaan, RAMpath has unique features. First, it can generate path diagrams according to a given model. Second, it can display path tracing rules through path diagrams and decompose total effects into their respective direct and indirect effects as well as decompose variance and covariance into individual bridges. Furthermore, RAMpath can fit dynamic system models automatically based on latent change scores and generate vector field plots based upon results obtained from a bivariate dynamic system. Starting version 0.4, RAMpath can conduct power analysis for both univariate and bivariate latent change score models.

This package provides methods readMat() and writeMat() for reading and writing MAT files. For user with MATLAB v6 or newer installed (either locally or on a remote host), the package also provides methods for controlling MATLAB (trademark) via R and sending and retrieving data between R and MATLAB.

Perform derivative-free optimization algorithms in R using C++. A wrapper interface is provided to call C function of the bobyqa implementation (See <https://github.com/emmt/Algorithms/tree/master/bobyqa>).

This package provides functions to calculate several ecological indices of individual and population niche width (Araujo's E, clustering and pairwise similarity among individuals, IS, Petraitis W, and Roughgarden's WIC/TNW) to assess individual specialization based on data of resource use. Resource use can be quantified by counts of categories, measures of mass or length, or proportions. Monte Carlo resampling procedures are available for hypothesis testing against multinomial null models. Details are provided in Zaccarelli et al. (2013) <doi:10.1111/2041-210X.12079> and associated references.

Spatial Dispersion Index (SDI) is a generalized measurement index, or rather a family of indices to evaluate spatial dispersion of movements/flows in a network in a problem neutral way as described in: Gencer (2023) <doi:10.1007/s12061-023-09545-8>. This package computes and optionally visualizes this index with minimal hassle.

This package provides a fast implementation of the greedy algorithm for the set cover problem using Rcpp'.

This package provides point estimates and confidence intervals for receiver operating characteristic (ROC)â based diagnostic accuracy metrics for tests and biomarkers subject to verification bias. Supported metrics include the Area Under the ROC Curve (AUC), the Youden index, and the sensitivity at a userâ specified specificity level for twoâ class continuous tests under missingâ atâ random (MAR) disease verification. Point estimation follows Alonzo and Pepe (2005) <doi:10.1111/j.1467-9876.2005.00477.x>. Multiple types of confidence intervals are implemented and compared, including bootstrapâ based, Method of Variance Estimates Recovery (MOVER)â based, and empirical likelihood (EL)â based intervals; see Wang et al. (2025) <doi:10.1177/09622802251322989> and <https://github.com/swang1021/rocvb>.

Generate basic charts either by custom applications, or from a small script launched from the system console, or within the R console. Two ASCII text files are necessary: (1) The graph parameters file, which name is passed to the function rplotengine()'. The user can specify the titles, choose the type of the graph, graph output formats (e.g. png, eps), proportion of the X-axis and Y-axis, position of the legend, whether to show or not a grid at the background, etc. (2) The data to be plotted, which name is specified as a parameter ('data_filename') in the previous file. This data file has a tabulated format, with a single character (e.g. tab) between each column. Optionally, the file could include data columns for showing confidence intervals.

Enhances the R Optimization Infrastructure ('ROI') package with the quadratic solver qpOASES'. More information about qpOASES can be found at <https://github.com/coin-or/qpOASES>.

Handle climate data from the DWD ('Deutscher Wetterdienst', see <https://www.dwd.de/EN/climate_environment/cdc/cdc_node_en.html> for more information). Choose observational time series from meteorological stations with selectDWD()'. Find raster data from radar and interpolation according to <https://brry.github.io/rdwd/raster-data.html>. Download (multiple) data sets with progress bars and no re-downloads through dataDWD()'. Read both tabular observational data and binary gridded datasets with readDWD()'.

Iterative least cost path and minimum spanning tree methods for projecting forest road networks. The methods connect a set of target points to an existing road network using igraph <https://igraph.org> to identify least cost routes. The cost of constructing a road segment between adjacent pixels is determined by a user supplied weight raster and a weight function; options include the average of adjacent weight raster values, and a function of the elevation differences between adjacent cells that penalizes steep grades. These road network projection methods are intended for integration into R workflows and modelling frameworks used for forecasting forest change, and can be applied over multiple time-steps without rebuilding a graph at each time-step.

This package provides clean, tidy access to Australian Electoral Commission (AEC) federal election data. Includes results for the House of Representatives and Senate from 2007 onwards, at both division and polling place level. Data is downloaded directly from the AEC <https://results.aec.gov.au> on first use and cached locally for subsequent calls.

Enables binary package installations on Linux distributions. Provides access to RStudio public repositories at <https://packagemanager.posit.co>, and transparent management of system requirements without administrative privileges. Currently supported distributions are CentOS / RHEL', and several RHEL derivatives ('Rocky Linux', AlmaLinux', Oracle Linux', and Amazon Linux'), openSUSE / SLES', Debian', and Ubuntu LTS.

Analysis of DNA mixtures involving relatives by computation of likelihood ratios that account for dropout and drop-in, mutations, silent alleles and population substructure. This is useful in kinship cases, like non-invasive prenatal paternity testing, where deductions about individuals relationships rely on DNA mixtures, and in criminal cases where the contributors to a mixed DNA stain may be related. Relationships are represented by pedigrees and can include kinship between more than two individuals. The main function is relMix() and its graphical user interface relMixGUI(). The implementation and method is described in Dorum et al. (2017) <doi:10.1007/s00414-016-1526-x>, Hernandis et al. (2019) <doi:10.1016/j.fsigss.2019.09.085> and Kaur et al. (2016) <doi:10.1007/s00414-015-1276-1>.

Enhances the R Optimization Infrastructure ('ROI') package with the SCS solver for solving convex cone problems.

The minimal rrapply'-package contains a single function rrapply(), providing an extended implementation of R'-base rapply() by allowing to recursively apply a function to elements of a nested list based on a general condition function and including the possibility to prune or aggregate nested list elements from the result. In addition, special arguments can be supplied to access the name, location, parents and siblings in the nested list of the element under evaluation. The rrapply() function builds upon rapply()'s native C implementation and requires no other package dependencies.

This package provides tools for RFM (recency, frequency and monetary value) analysis. Generate RFM score from both transaction and customer level data. Visualize the relationship between recency, frequency and monetary value using heatmap, histograms, bar charts and scatter plots. Includes a shiny app for interactive segmentation. References: i. Blattberg R.C., Kim BD., Neslin S.A (2008) <doi:10.1007/978-0-387-72579-6_12>.