Builds and optimizes Hopfield artificial neural networks (Hopfield, 1982, <doi:10.1073/pnas.79.8.2554>). One-layer and three-layer models are implemented. The energy of the Hopfield network is minimized with formula from Krotov and Hopfield (2016, <doi:10.48550/ARXIV.1606.01164>). Optimization (supervised learning) is done through a gradient-based method. Classification is done with S3 methods predict(). Parallelization with OpenMP is used if available during compilation.

This package provides a novel decision tree algorithm in the hypothesis testing framework. The algorithm examines the distribution difference between two child nodes over all possible binary partitions. The test statistic of the hypothesis testing is equivalent to the generalized energy distance, which enables the algorithm to be more powerful in detecting the complex structure, not only the mean difference. It is applicable for numeric, nominal, ordinal explanatory variables and the response in general metric space of strong negative type. The algorithm has superior performance compared to other tree models in type I error, power, prediction accuracy, and complexity.

Initializes a class that obtains API credentials and provides a method to use those credentials to make GET requests to the Hakai API server. Usage instructions are documented at <https://hakaiinstitute.github.io/hakai-api/>.

This package provides the posterior estimates of the regression coefficients when horseshoe prior is specified. The regression models considered here are logistic model for binary response and log normal accelerated failure time model for right censored survival response. The linear model analysis is also available for completeness. All models provide deviance information criterion and widely applicable information criterion. See <doi:10.1111/rssc.12377> Maity et. al. (2019) <doi:10.1111/biom.13132> Maity et. al. (2020).

Fits regression models on high dimensional data to estimate coefficients and use bootstrap method to obtain confidence intervals. Choices for regression models are Lasso, Lasso+OLS, Lasso partial ridge, Lasso+OLS partial ridge.

This package provides a simple implementation of doughnut plots - pie charts with a blank center. The package is named after Homer Simpson - arguably the best-known lover of doughnuts.

This package implements methods developed by Ding, Feller, and Miratrix (2016) <doi:10.1111/rssb.12124> <doi:10.48550/arXiv.1412.5000>, and Ding, Feller, and Miratrix (2018) <doi:10.1080/01621459.2017.1407322> <doi:10.48550/arXiv.1605.06566> for testing whether there is unexplained variation in treatment effects across observations, and for characterizing the extent of the explained and unexplained variation in treatment effects. The package includes wrapper functions implementing the proposed methods, as well as helper functions for analyzing and visualizing the results of the test.

Base R's default setting for stringsAsFactors within data.frame() and as.data.frame() is supposedly the most often complained about piece of code in the R infrastructure. The hellno package provides an explicit solution without changing R itself or having to mess around with options. It tries to solve this problem by providing alternative data.frame() and as.data.frame() functions that are in fact simple wrappers around base R's data.frame() and as.data.frame() with stringsAsFactors option set to HELLNO ( which in turn equals FALSE ) by default.

This package provides data for functions typically used in the healthyR package.

In streaming data analysis, it is crucial to detect significant shifts in the data distribution or the accuracy of predictive models over time, a phenomenon known as concept drift. The package aims to identify when concept drift occurs and provide methodologies for adapting models in non-stationary environments. It offers a range of state-of-the-art techniques for detecting concept drift and maintaining model performance. Additionally, the package provides tools for adapting models in response to these changes, ensuring continuous and accurate predictions in dynamic contexts. Methods for concept drift detection are described in Tavares (2022) <doi:10.1007/s12530-021-09415-z>.

Generates high-entropy integer synthetic populations from marginal and (optionally) seed data using quasirandom sampling, in arbitrary dimensionality (Smith, Lovelace and Birkin (2017) <doi:10.18564/jasss.3550>). The package also provides an implementation of the Iterative Proportional Fitting (IPF) algorithm (Zaloznik (2011) <doi:10.13140/2.1.2480.9923>).

This package provides tools for computing HUM (Hypervolume Under the Manifold) value to estimate features ability to discriminate the class labels, visualizing the ROC curve for two or three class labels (Natalia Novoselova, Cristina Della Beffa, Junxi Wang, Jialiang Li, Frank Pessler, Frank Klawonn (2014) <doi:10.1093/bioinformatics/btu086>).

By binding R functions and the Highcharts <http://www.highcharts.com/> charting library, hpackedbubble package provides a simple way to draw split packed bubble charts.

This package performs linear discriminant analysis in high dimensional problems based on reliable covariance estimators for problems with (many) more variables than observations. Includes routines for classifier training, prediction, cross-validation and variable selection.

An implementation of an algorithm for outlier detection that can handle a) data with a mixed categorical and continuous variables, b) many columns of data, c) many rows of data, d) outliers that mask other outliers, and e) both unidimensional and multidimensional datasets. Unlike ad hoc methods found in many machine learning papers, HDoutliers is based on a distributional model that uses probabilities to determine outliers.

This package provides a case conversion between common cases like CamelCase and snake_case. Using the rust crate heck <https://github.com/withoutboats/heck> as the backend for a highly performant case conversion for R'.

This package provides a modern idiomatic header-only C++ interface for libhdf5'. Original software can be found at <https://github.com/highfive-devs/highfive/>.

Generates (half-)normal plots with simulation envelopes using different diagnostics from a range of different fitted models. A few example datasets are included.

Offers efficient algorithms for fitting regularization paths for lasso or elastic-net penalized regression models with Huber loss, quantile loss or squared loss. Reference: Congrui Yi and Jian Huang (2017) <doi:10.1080/10618600.2016.1256816>.

Set of tools to help interested researchers to build hospital networks from data on hospitalized patients transferred between hospitals. Methods provided have been used in Donker T, Wallinga J, Grundmann H. (2010) <doi:10.1371/journal.pcbi.1000715>, and Nekkab N, Crépey P, Astagneau P, Opatowski L, Temime L. (2020) <doi:10.1038/s41598-020-71212-6>.

This package performs a homogeneity analysis (multiple correspondence analysis) and various extensions. Rank restrictions on the category quantifications can be imposed (nonlinear PCA). The categories are transformed by means of optimal scaling with options for nominal, ordinal, and numerical scale levels (for rank-1 restrictions). Variables can be grouped into sets, in order to emulate regression analysis and canonical correlation analysis.

This package provides flexible maximum likelihood estimation and inference for Hidden Markov Models (HMMs) and Hidden Semi-Markov Models (HSMMs), as well as the underlying systems in which they operate. The package supports a wide range of observation and dwell-time distributions, offering a flexible modelling framework suitable for diverse practical data. Efficient implementations of the forward-backward and Viterbi algorithms are provided via Rcpp for enhanced computational performance. Additional functionality includes model simulation, residual analysis, non-initialised estimation, local and global decoding, calculation of diverse information criteria, computation of confidence intervals using parametric bootstrap methods, numerical covariance matrix estimation, and comprehensive visualisation functions for interpreting the data-generating processes inferred from the models. Methods follow standard approaches described by Guédon (2003) <doi:10.1198/1061860032030>, Zucchini and MacDonald (2009, ISBN:9781584885733), and O'Connell and Højsgaard (2011) <doi:10.18637/jss.v039.i04>.

HDF5 (Hierarchical Data Format 5) is a high-performance library and file format for storing and managing large, complex data. This package provides the static libraries and headers for the HDF5 C library (release 2.0.0). It is intended for R package developers to use in the LinkingTo field, which eliminates the need for users to install system-level HDF5 dependencies. This build is compiled with thread-safety enabled and supports dynamic loading of external compression filters. HDF5 is developed by The HDF Group <https://www.hdfgroup.org/>.

We provide a collection of various classical tests and latest normal-reference tests for comparing high-dimensional mean vectors including two-sample and general linear hypothesis testing (GLHT) problem. Some existing tests for two-sample problem [see Bai, Zhidong, and Hewa Saranadasa.(1996) <https://www.jstor.org/stable/24306018>; Chen, Song Xi, and Ying-Li Qin.(2010) <doi:10.1214/09-aos716>; Srivastava, Muni S., and Meng Du.(2008) <doi:10.1016/j.jmva.2006.11.002>; Srivastava, Muni S., Shota Katayama, and Yutaka Kano.(2013)<doi:10.1016/j.jmva.2012.08.014>]. Normal-reference tests for two-sample problem [see Zhang, Jin-Ting, Jia Guo, Bu Zhou, and Ming-Yen Cheng.(2020) <doi:10.1080/01621459.2019.1604366>; Zhang, Jin-Ting, Bu Zhou, Jia Guo, and Tianming Zhu.(2021) <doi:10.1016/j.jspi.2020.11.008>; Zhang, Liang, Tianming Zhu, and Jin-Ting Zhang.(2020) <doi:10.1016/j.ecosta.2019.12.002>; Zhang, Liang, Tianming Zhu, and Jin-Ting Zhang.(2023) <doi:10.1080/02664763.2020.1834516>; Zhang, Jin-Ting, and Tianming Zhu.(2022) <doi:10.1080/10485252.2021.2015768>; Zhang, Jin-Ting, and Tianming Zhu.(2022) <doi:10.1007/s42519-021-00232-w>; Zhu, Tianming, Pengfei Wang, and Jin-Ting Zhang.(2023) <doi:10.1007/s00180-023-01433-6>]. Some existing tests for GLHT problem [see Fujikoshi, Yasunori, Tetsuto Himeno, and Hirofumi Wakaki.(2004) <doi:10.14490/jjss.34.19>; Srivastava, Muni S., and Yasunori Fujikoshi.(2006) <doi:10.1016/j.jmva.2005.08.010>; Yamada, Takayuki, and Muni S. Srivastava.(2012) <doi:10.1080/03610926.2011.581786>; Schott, James R.(2007) <doi:10.1016/j.jmva.2006.11.007>; Zhou, Bu, Jia Guo, and Jin-Ting Zhang.(2017) <doi:10.1016/j.jspi.2017.03.005>]. Normal-reference tests for GLHT problem [see Zhang, Jin-Ting, Jia Guo, and Bu Zhou.(2017) <doi:10.1016/j.jmva.2017.01.002>; Zhang, Jin-Ting, Bu Zhou, and Jia Guo.(2022) <doi:10.1016/j.jmva.2021.104816>; Zhu, Tianming, Liang Zhang, and Jin-Ting Zhang.(2022) <doi:10.5705/ss.202020.0362>; Zhu, Tianming, and Jin-Ting Zhang.(2022) <doi:10.1007/s00180-021-01110-6>; Zhang, Jin-Ting, and Tianming Zhu.(2022) <doi:10.1016/j.csda.2021.107385>].