October 2019: “Top 40” New R Packages

November 17, 2019
By

[This article was first published on R Views, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

Two Hundred twenty-three new packages made it to CRAN in October. Here are my “Top 40” picks in ten categories: Computational Methods, Data, Genomics, Machine Learning, Mathematics, Medicine, Pharmacology, Statistics, Utilities, and Visualization.

Computational Methods

admmDensestSubmatrix v0.1.0: Implements a method to identify the densest sub-matrix in a given or sampled binary matrix. See Bombina et al. (2019) for the technical details and the vignette for examples.

mbend v1.2.3: Provides functions to “bend”” non-positive-definite (symmetric) matrices to positive-definite matrices using weighted and unweighted methods. See Jorjani et al. (2003) and Schaeffer (2010) for background and the vignette for an Introduction.

Data

cqcr v0.1.2: Provides access to data from the Care Quality Commission, the health and adult social care regulator for England. Data available under the Open Government License include information on service providers, hospitals, care homes, and medical clinics locations, and ratings and inspection reports.

fpp3 v0.1: Contains all data sets required for the examples and exercises in the book Forecasting: principles and practice by Rob J Hyndman and George Athanasopoulos.

fsbrain v0.0.2: Provides high-level access to FreeSurfer neuroimaging data on the level of subjects and groups. There is a vignette.

opendatatoronto v0.1.0: Provides access to data from the City of Toronto Open Data Portal. There is an Introduction and vignettes on Geospatial Data, Zip Resources, Retrieving Multiple Resources, and Retrieving XLS/XLSX Resources.

povcalnetR v0.1.0: Provides an interface to Povcalnet, a computational tool that allows users to estimate poverty rates for regions, sets of countries or individual countries, over time, and at any poverty line that is managed by the World Bank’s development economics division. There is a Getting Started Guide, and vignettes on Examples and Advanced Usage.

Genomics

dynwrap v1.1.4: Provides functions to infer trajectories from single-cell data, represent them into a common format, and adapt them. See Saelens et al. (2019) for background. There are vignettes on Containers, Scripts, Adding Methods, and Wrapping Trajectories.

phyr v1.0.2: Provides a collection of functions to do model-based phylogenetic analysis, including functions to calculate community phylogenetic diversity, to estimate correlations among functional traits while accounting for phylogenetic relationships, and to fit phylogenetic generalized linear mixed models. The Bayesian phylogenetic generalized linear mixed models are fitted with the INLA package. There is a Performance Benchmark and vignettes on Usage and Plotting.

Machine Learning

cwbtools v0.1.0: Provides tools to create, modify, and manage Corpus Workbench (CWB) Corpora. See Evert and Hardie (2011) for background, and the vignettes Introducing cwbtools and Europal for information on the package.

discrim v0.0.1: Provides bindings for additional classification models for use with the parsnip package including linear discriminate (See Fisher (1936).), regularized discriminant analysis (See Friedman (1989).), and flexible discriminate analysis (See (Hastie et al. (1994).), as well as naive for Bayes classifiers Hand and Yu (2007).

forecastML v0.5.0: Provides functions for forecasting time series using machine learning models and an approach inspired by Bergmeir, Hyndman, and Koo’s (2018). There is an Overview, and vignettes on Customizing Wrapper Functions, Multiple Time Series, and Custom Feature Lags.

interpret v0.1.23: Implements the Explainable Boosting Machine (EBM) framework for machine learning interpretability. See Caruana et al. (2015), for details, and look here for help with the package.

mlr3pipelines v0.1.1: Implements a dataflow programming toolkit that enriches mlr3 with a diverse set of pipelining operators that can be composed into graphs. Operations exist for data preprocessing, model fitting, and ensemble learning. There is an Introduction and a vignette on Comparing Frameworks.

postDoubleR v1.4.12: Implements the double/debiased machine learning algorithm described in Chernozhukov et al. (2017).

SLEMI v1.0: Implements the method described in Jetka et al. (2019) for estimating mutual information and channel capacity from experimental data by classification procedures (logistic regression). The vignette describes how to use the package.

tfprobability v0.0.2: Provides an interface to TensorFlow Probability, a Python library built on TensorFlow that makes it easy to combine probabilistic models and deep learning on modern hardware including TPUs and GPUs. There are vignettes on Dynamic Linear Models, Multi-level Modeling with Hamiltonian Monte Carlo, and Uncertainty Estimates.

Mathematics

Ryacas0 v0.4.2: Provides and interface to the yacas computer algebra system. There is a Getting Started Guide and vignettes on Ryacas functionality, a Naive Bayes Model, a State Space Model and Matric and Vector Objects.

silicate v0.2.0: Provides functions to generate common forms for complex hierarchical and relational data structures inspired by the simplicial complex. There is a vignette.

Medicine

diyar v0.0.2: Implements multistage record linkage and case definition for epidemiological analyses. There are vignettes on Case Definitions and Multistage Deterministic Linkage.

ushr v0.1.0: Presents an analysis of longitudinal data of HIV decline in patients on antiretroviral therapy using the canonical biphasic exponential decay model described in Perelson et al. (1997) and Wu and Ding (1999), and includes options to calculate the time to viral suppression. The vignette walks through the analysis.

Pharmacology

chlorpromazineR v0.1.2: Provides functions to convert doses of antipsychotic medications to chlorpromazine-equivalent doses using conversion keys generated from Gardner et. al (2010) and Leucht et al. (201). See the vignette.

ubiquity v1.0.0: Implements a complete work flow for the analysis of pharmacokinetic pharmacodynamic (PKPD), physiologically-based pharmacokinetic (PBPK) and systems pharmacology models including: creation of ODE-based models, pooled parameter estimation, simulations for clinical trial design and modeling assays and deployment with Shiny and reporting with PowerPoint. There are vignettes on Deployment, Estimation, Language, NCA, Reporting, Simulation, and Titration.

Statistics

DPQ v0.3-5: Provides the computations for approximations and alternatives for the density, cumulative density and quantile functions for R’s probability distributions. This package from researchers working with R-core is intended primarily for researchers working to improve R’s beta, gamma and related distributions. See the vignettes Non-central Chi-Swuared Probabilities – Algorithms in R and Computing Beta for Large Arguments.

hypr v0.1.3: Provides functions to translate between experimental null hypotheses, hypothesis matrices, and contrast matrices as used in linear regression models based on the method described in Schad et al. (2019). There is an Introduction and vignettes on Contrasts and Linear Regression.

HTLR v0.4-1: Implements Bayesian multinomial logistic regression based on heavy-tailed (hyper-LASSO, non-convex) priors for high-dimensional feature selection. Li and Yao (2018) provides a detailed description of the method, and the vignette introduces the package.

meteorits v0.1.0: Provides a unified mixture-of-experts (ME) modeling and estimation framework to model, cluster and classify heterogeneous data in many complex situations where the data are distributed according to non-normal, possibly skewed distributions. See Chamroukhi et al. (2009), Chamroukhi (2010). Chamroukhi (2015), Chamroukhi (2016), and Chamroukhi (2017) for background, and the vignettes NMoE, SNMoE, StMoE and tMoE.

mHHMbayes v0.1.1: Implements multilevel (mixed or random effects) hidden Markov model using Bayesian estimation in R. For background see Rabiner (1989) and de Haan-Rietdijk et al. (2017). There is a Tutorial and a vignette on Estimation.

nhm v0.1.0: Provides functions to fit non-homogeneous Markov multistate models and misclassification-type hidden Markov models in continuous time to intermittently observed data. See Titman (2011) for background and the User Guide for package details.

mniw v1.0: Implements the Matrix-Normal Inverse-Wishart (MNIW) distribution, as well as the the Matrix-Normal, Matrix-T, Wishart, and Inverse-Wishart distributions. the vignette does the math.

PosteriorBootstrap v0.1.0: Implements a non-parametric statistical model using a parallelized Monte Carlo sampling scheme that allows non-parametric inference to be regularized for small sample sizes. The method is described in full in Lyddon et al. (2018). There is a vignette.

spBFA v1.0: Implements functions for spatial Bayesian non-parametric factor analysis model with inference. See Berchuck et al. (2019) for the technical background and the vignette for package details.

VARshrink v0.3.1: Provides functions that integrate shrinkage estimation with vector autoregressive models including nonparametric, parametric, and semiparametric methods such as the multivariate ridge regression (See Golub et al. (1979).), a James-Stein type nonparametric shrinkage method (See Opgen-Rhein and Strimmer (2007).), and Bayesian estimation methods as in Lee et al. (2016) and Ni and Sun (2005). There is a vignette.

Utilities

geospark v0.2.1: Provides simple features bindings to GeoSpark extending the sparklyr package to bring geocomputing to Spark distributed systems. See README for more information.

laelmachine v1.0.0: Provides functions to assign meaningful labels to data frame columns, and to manage label assignment rules in yaml files making it easy to use the same labels in multiple projects. There is a Getting Started Guide and vignettes on Altering lama-dictionaries, Creating lama-dictionaries, and Translating Variables.

renv v0.8-3: Implements a dependency management toolkit that enables creating and managing project-local R libraries, saving the state of these libraries and later restoring them. There is an Introduction and a series of vignettes: Continuous Integration,
Collaborating with renv, Using renv with Docker, Frequently Asked Questions, Local Sources, Lockfiles, and Using Python with renv.

ymlthis v0.1.0: Provides functions to write YAML front matter for R Markdown and related documents. There is an Introduction to the package, a YAML Field Guide and an YAML Overview.

Visualization

geometr v0.1.1: Provides tools that generate and process tidy geometric shapes. There is a vignette.

ggVennDiagram v0.3: Provides functions to generae publication quality Venn diagrams using two to four sets. See README for more information.

rayrender v0.4.2: Provides functions to render scenes using path tracing including building 3D scenes out of geometrical shapes and 3D models in the Wavefront OBJ file format. Look here for more information.

sankeywheel v0.1.0: Implements bindings to the Highcharts library to provide a simple way to draw dependency wheels and sankey diagrams. There is a
vignette.

To leave a comment for the author, please follow the link and comment on their blog: R Views.

R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.



If you got this far, why not subscribe for updates from the site? Choose your flavor: e-mail, twitter, RSS, or facebook...

Comments are closed.

Search R-bloggers

Sponsors

Never miss an update!
Subscribe to R-bloggers to receive
e-mails with the latest R posts.
(You will not see this message again.)

Click here to close (This popup will not appear again)