Enter the query into the form above. You can look for specific version of a package by using @ symbol like this: gcc@10.
API method:
GET /api/packages?search=hello&page=1&limit=20
where search is your query, page is a page number and limit is a number of items on a single page. Pagination information (such as a number of pages and etc) is returned
in response headers.
If you'd like to join our channel search send a patch to ~whereiseveryone/toys@lists.sr.ht adding your channel as an entry in channels.scm.
Implementations for two different Bayesian models of differential co-expression. scdeco.cop() fits the bivariate Gaussian copula model from Zichen Ma, Shannon W. Davis, Yen-Yi Ho (2023) <doi:10.1111/biom.13701>, while scdeco.pg() fits the bivariate Poisson-Gamma model from Zhen Yang, Yen-Yi Ho (2022) <doi:10.1111/biom.13457>.
We provide functionality to implement penalized PCA with an option to smooth the objective function using Nesterov smoothing. Two functions are available to compute a user-specified number of eigenvectors. The function unsmoothed_penalized_EV() computes a penalized PCA without smoothing and has three parameters (the input matrix, the Lasso penalty, and the number of desired eigenvectors). The function smoothed_penalized_EV() computes a smoothed penalized PCA using the same parameters and additionally requires the specification of a smoothing parameter. Both functions return a matrix having the desired eigenvectors as columns.
This package provides functions are provided for the density function, distribution function, quantiles and random number generation for the skew hyperbolic t-distribution. There are also functions that fit the distribution to data. There are functions for the mean, variance, skewness, kurtosis and mode of a given distribution and to calculate moments of any order about any centre. To assess goodness of fit, there are functions to generate a Q-Q plot, a P-P plot and a tail plot.
This package implements a regularization method for cumulative link models using the Smooth-Effect-on-Response Penalty (SERP). This method allows flexible modeling of ordinal data by enabling a smooth transition from a general cumulative link model to a simplified version of the same model. As the tuning parameter increases from zero to infinity, the subject-specific effects for each variable converge to a single global effect. The approach addresses common issues in cumulative link models, such as parameter unidentifiability and numerical instability, by maximizing a penalized log-likelihood instead of the standard non-penalized version. Fitting is performed using a modified Newton's method. Additionally, the package includes various model performance metrics and descriptive tools. For details on the implemented penalty method, see Ugba (2021) <doi:10.21105/joss.03705> and Ugba et al. (2021) <doi:10.3390/stats4030037>.
This package provides several functions for area level of small area estimation using hierarchical Bayesian (HB) methods with several univariate distributions for variables of interest. The dataset that is used in every function is generated accordingly in the Example. The rjags package is employed to obtain parameter estimates. Model-based estimators involve the HB estimators which include the mean and the variation of mean. For the reference, see Rao and Molina (2015) <doi:10.1002/9781118735855>.
Fits univariate and multivariate spatio-temporal random effects models for point-referenced data using Markov chain Monte Carlo (MCMC). Details are given in Finley, Banerjee, and Gelfand (2015) <doi:10.18637/jss.v063.i13> and Finley and Banerjee <doi:10.1016/j.envsoft.2019.104608>.
Allows users to easily build custom docker images <https://docs.docker.com/> from Amazon Web Service Sagemaker <https://aws.amazon.com/sagemaker/> using Amazon Web Service CodeBuild <https://aws.amazon.com/codebuild/>.
Fits a structural equation multidimensional scaling (SEMDS) model for asymmetric and three-way input dissimilarities. It assumes that the dissimilarities are measured with errors. The latent dissimilarities are estimated as factor scores within an SEM framework while the objects are represented in a low-dimensional space as in MDS.
The computation of a seasonal index is a fundamental step in time-series forecasting when the data exhibits seasonality. Specifically, a seasonal index quantifies â for each season (e.g. month, quarter, week) â the relative magnitude of the seasonal effect compared to the overall average level of the series. This package has been developed to compute seasonal index for time series data and it also seasonalise and desesaonalise the time series data.
Calculate and compare lower confidence bounds for binomial series system reliability. The R shiny application, launched by the function launch_app(), weaves together a workflow of customized simulations and delta coverage calculations to output recommended lower confidence bound methods.
Bayesian analysis of censored linear mixed-effects models that replace Gaussian assumptions with a flexible class of distributions, such as the scale mixture of normal family distributions, considering a damped exponential correlation structure which was employed to account for within-subject autocorrelation among irregularly observed measures. For more details, see Kelin Zhong, Fernanda L. Schumacher, Luis M. Castro, Victor H. Lachos (2025) <doi:10.1002/sim.10295>.
An interface to the Python package stanza <https://stanfordnlp.github.io/stanza/index.html>. stanza is a Python NLP library for many human languages. It contains support for running various accurate natural language processing tools on 60+ languages.
Computes a proportional trimmed mean that resolves the integer truncation problem of base R's mean(..., trim). When k = trim * n is non-integer, a fractional discount (1 - delta) is applied to boundary observations, where delta = k - floor(k). The resulting estimator is continuous in alpha for any fixed n, syntactically identical to mean(..., trim), and compatible with the Statgraphics implementation. See Gaviria Chaverra (2026) <doi:10.32614/CRAN.package.sgmean>.
This package provides drop-in Liquid Glass themes for shiny'. Call glass_theme() and pass the result as theme = to fluidPage(), navbarPage(), or any bslib'-aware page function to get translucent surfaces, backdrop blur, and system typography on Bootstrap components. Includes light and dark presets with runtime switching and an OS-following auto mode, an iOS-style intensity control from Ultra Clear to Tinted, optional persistence of the look, named wallpaper scenes, helpers to match ggplot2', plotly', gt', and DT output to the glass pack, a flatten mode for print and screenshots, and documented CSS tokens.
Nonparametric method for testing the equality of the spectral densities of two time series of possibly different lengths. The time series are preprocessed with the discrete cosine transform and the variance stabilising transform to obtain an approximate Gaussian regression setting for the log-spectral density function. The test statistic is based on the squared L2 norm of the difference between the estimated log-spectral densities. The test returns the result, the statistic value, and the p-value. It also provides the estimated empirical quantile and null distribution under the hypothesis of equal spectral densities. An example using EEG data is included. For details see Nadin, Krivobokova, Enikeeva (2026), <doi:10.48550/arXiv.2602.10774>.
This package implements a parameter expanded variational Bayes algorithm for linear regression models with high-dimensional variable selection. The methodology utilizes spike-and-slab priors to perform simultaneous estimation and selection. Details can be found in Olejua et al. (2024) <doi:10.21203/rs.3.rs-7208847/v1>.
This package provides confidence intervals in least-squares regressions when the variable of interest has a shift-share structure, and in instrumental variables regressions when the instrument has a shift-share structure. The confidence intervals implement the AKM and AKM0 methods developed in Adão, Kolesár, and Morales (2019) <doi:10.1093/qje/qjz025>.
Use inverse probability weighting methods to estimate treatment effect under marginal structure model (MSM) for the transition hazard of semi competing risk data, i.e. illness death model. We implement two specific such models, the usual Markov illness death structural model and the general Markov illness death structural model. We also provide the predicted three risks functions from the marginal structure models. Zhang, Y. and Xu, R. (2022) <arXiv:2204.10426>.
Analysis of species count data in ecology often requires normalization to an identical sample size. Rarefying (random subsampling without replacement), which is a popular method for normalization, has been widely criticized for its poor reproducibility and potential distortion of the community structure. In the context of microbiome count data, researchers explicitly advised against the use of rarefying. An alternative to rarefying is scaling with ranked subsampling (SRS). SRS consists of two steps. In the first step, the total counts for all OTUs (operational taxonomic units) or species in each sample are divided by a scaling factor chosen in such a way that the sum of the scaled counts Cscaled equals Cmin. In the second step, the non-integer Cscaled values are converted into integers by an algorithm that we dub ranked subsampling. The Cscaled value for each OTU or species is split into the integer part Cint (Cint = floor(Cscaled)) and the fractional part Cfrac (Cfrac = Cscaled - Cints). Since the sum of Cint is smaller or equal to Cmin, additional delta C = Cmin - the sum of Cint counts have to be added to the library to reach the total count of Cmin. This is achieved as follows. OTUs are ranked in the descending order of their Cfrac values. Beginning with the OTU of the highest rank, single count per OTU is added to the normalized library until the total number of added counts reaches delta C and the sum of all counts in the normalized library equals Cmin. When the lowest Cfrag involved in picking delta C counts is shared by several OTUs, the OTUs used for adding a single count to the library are selected in the order of their Cint values. This selection minimizes the effect of normalization on the relative frequencies of OTUs. OTUs with identical Cfrag as well as Cint are sampled randomly without replacement. See Beule & Karlovsky (2020) <doi:10.7717/peerj.9593> for details.
An implementation of semi-supervised regression methods including self-learning and co-training by committee based on Hady, M. F. A., Schwenker, F., & Palm, G. (2009) <doi:10.1007/978-3-642-04274-4_13>. Users can define which set of regressors to use as base models from the caret package, other packages, or custom functions.
Random Forest-like tree ensemble that works with groups of predictor variables. When building a tree, a number of variables is taken randomly from each group separately, thus ensuring that it considers variables from each group for the splits. Useful when rows contain information about different things (e.g. user information and product information) and it's not sensible to make a prediction with information from only one group of variables, or when there are far more variables from one group than the other and it's desired to have groups appear evenly on trees. Trees are grown using the C5.0 algorithm rather than the usual CART algorithm. Supports parallelization (multithreaded), missing values in predictors, and categorical variables (without doing One-Hot encoding in the processing). Can also be used to create a regular (non-stratified) Random Forest-like model, but made up of C5.0 trees and with some additional control options. As it's built with C5.0 trees, it works only for classification (not for regression).
Fits linear regression models on datasets residing in SQL databases without pulling data into R memory. Computes sufficient statistics inside the database engine via a single aggregation query and solves the normal equations in R.
Fit design-based linear and logistic elastic nets with complex survey data considering the sampling design when defining training and test sets using replicate weights. Methods implemented in this package are described in: A. Iparragirre, T. Lumley, I. Barrio, I. Arostegui (2024) <doi:10.1002/sta4.578>.
Renders plots to a temporary image using the ragg graphics device and returns knitr::include_graphics() output. Optionally saves the image to a specified path. This helps ensure consistent appearance across interactive sessions, saved files, and knitted documents. For more details see Pedersen and Shemanarev (2025) <doi: 10.32614/CRAN.package.ragg>.