Two hundred ninety-two new packages made it to CRAN in November. Picking forty was unusually difficult. Nevertheless, here are my “Top 40” selections in twelve categories: Archaeology, Computational Methods, Data, Epidemiology, Games, Machine Learning, Mathematics, Medicine, Statistics, Time Series, Utilities, and Visualization. R developers continue to extend the reach of R. November featured a new package on Archaeology, one of only seventeen I could find on CRAN
pkgsearch::pkg_search(query="Archaeology ",size=200), as well as a package that wraps Python’s
Looking back over the last twelve months my impression is that R continues to grow in the life sciences. Packages that I have classified as belonging to the categories Epidemiology, Genomics, or Medicine have comprised between ten and fourteen percent of the packages I have reviewed each month.
archeofrag v0.6.0: Implements methods based on graphs and graph theory for the stratigraphic analysis of fragmented objects in archaeology using “refitting” relationships between fragments scattered in stratigraphic layers. See the vignette.
ADtools v0.5.4: Implements the forward-mode automatic differentiation for multivariate functions using the matrix-calculus notation from Magnus and Neudecker (2019). See the vignette for an introduction.
ML2Pvae v1.0.0: Provides functions to create a variational autoencoder (VAE) for parameter estimation in Item Response Theory (IRT) which allows straight-forward construction, training, and evaluation. Only minimal knowledge of
keras is required. See Curi et al. (2019) for background and the vignette for an overview.
campfin v1.0.4: Provides tools to explore and normalize American campaign finance data. This package was created by the Investigative Reporting Workshop to facilitate work on The Accountability Project. See the vignette to get started.
cpsvote v0.1.0: Provides automated methods for downloading, recoding, and merging selected years of the Current Population Survey’s Voting and Registration Supplement, a large national survey about registration, voting, and non-voting in United States federal elections. There are vignettes on basics, background, voting, and adding variables.
SEIRfansy v1.1.0: Implements the Extended Susceptible-Exposed-Infected-Recovery Model for handling high false negative rate and symptom based administration of diagnostic tests. See Bhaduri et al. (2020) and the GitHub site for examples.
chess v1.0.1: Implements an “opinionated” wrapper around the
python-chess library allowing users to read and write PGN files as well as create and explore game trees such as the ones seen in chess books. See the vignettes chess, games, and advanced.
codebreaker v0.0.2: Inspired by Mastermind, the package implements a logic game in the style of the early 1980s home computers that can be played in the R console. Can you break the code? See README to start playing.
fastai v2.0.2: Implements functions to simplify training neural networks based on best practices developed at fast.ai. See the website to get started and the twenty-three vignettes which include Audio Classification, Multilabel Classification and Medical Images.
mikropml v0.0.2: Implements the ML pipeline described in Topçuoğlu et al. (2020) For building machine learning models for classification and regression problems. There is an Introduction and an Overview.
BaseSet v0.0.14: Implements a class and methods to work with sets, doing intersection, union, complementary sets, power sets, cartesian product and other set operations in a “tidy” way. See the Introduction, and the vignettes Advanced Examples and Fuzzy Sets.
causalCmprisk v1.0.0: Provides functions to estimate average treatment effects of two static treatment regimes on time-to-event outcomes with competing events. The method uses propensity scores weighting for emulation of baseline randomization. See the vignette.
eventglm v1.0.2 Implements methods for doing event history regression for marginal estimands, including cumulative incidence the restricted mean survival, as described in the methodology reviewed in Andersen & Perme (2010). See the vignette for examples.
IPDfromKM v0.1.10: Implements a method to reconstruct individual patient data from Kaplan-Meier (KM) survival curves, visualize and assess the accuracy of the reconstruction, and perform secondary analysis on the reconstructed data. The package also implements iterative KM estimation algorithm proposed in Guyot (2012).
packDAMipd v0.1.2: Provides functions to construct both time-homogenous and time-dependent Markov models for cost-effectiveness analyses, perform decision analyses, and conduct deterministic and probabilistic sensitivity analyses. There are vignettes on deterministic and probabilistic sensitivity analyses, simple “sick-sicker” models, age-dependent “sick-sicker” models, and cycle dependent models.
reconstructKM v0.3.0: Provides functions for reconstructing individual-level data (time, status, arm) from Kaplan-MEIER curves published in academic journals. See Sun et al. (2018) for background and the vignette for the reconstruction procedure.
ceser v1.0.0: Implements the Cluster Estimated Standard Errors method proposed in Jackson (2020) to compute clustered standard errors of linear coefficients in regression models with grouped data. See the vignette.
gfilmm v2.0.2: Implements generalized Fiducial inference for normal linear mixed models. Fiducial inference is similar to Bayesian inference in the sense that it represents the uncertainty about the parameters with a probability distribution. However, it does not require a prior. See Cisewski and Hannig (2012) for background and the vignette for examples.
sftrack v0.5.2: Implements classes for tracking and movement data, building on
sf spatial infrastructure, and early theoretical work from Turchin (1998), and Calenge et al. (2009). There is an Overview along with the vignettes Reading in an sftrack, Structure, Fantastic Groups, and Getting Spatial.
simrec v1.0.0: Provides functions to simulate recurrent event data with a non-constant baseline hazard and possibly risk-free intervals and competing events. See Jahn-Eimermacher et al. (2015) for background and the vignette for an introduction.
modeltime.resample v0.1.0: A
modeltime extension which implements forecast resampling tools to asses time-based model performance and stability for time series, panel data, and cross-sectional time series. There is a Getting Started guide and a vignette on Resampling.
tfarima v0.1.1: Provides tools to build customized transfer functions and ARIMA models with multiple operators and parameter restrictions. see Bell & Hilmer (1983) and Box & Tiao (1973) for background and the vignette for some theory and examples.
sdcLog v0.1.0: Tools for researchers to explicitly show that their results comply to rules for statistical disclosure control imposed by research data centers. The methods used are described in Bond et al. (2015). There is an Introduction and a vignette on options.
htmlwidgets package. Visualizations can be used from the R console, in R Markdown documents and in Shiny apps. See the vignette to get started.