April: "Top 40" New CRAN Packages

Computational Methods

hmer v1.0.1: Provides objects and functions for Bayes Linear emulation and history matching, including functions for automated training of emulators, diagnostic functions to ensure suitability, and a variety of methods for generating waves of points. There is a vignette Demo of the package, an Emulation and History matching Handbook, and vignettes on Examples, and Stochastic Emulation.

rminqa v0.1.1: Implements a wrapper for the C++ function bobyqa to perform derivative-free optimization algorithms in R.

rolog v0.9.4: Embeds SWI-Prolog, so that R can send deterministic and non-deterministic queries to Prolog. See README for examples.

torchopt v0..1.1: Implements optimizers for the torch deep learning that are not among the optimizers offered in torch. These include:adabelief by Zhuang et al (2020), adabound by Luo et al.(2019), adamw by Loshchilov & Hutter (2019), madgrad by Defazio and Jelassi (2021), nadam by Dozat (2019), qhadam by Ma and Yarats (2019), radam by Liu et al. (2019), swats by Shekar and Sochee (2018), and yogi by Zaheer et al.(2019)

villager v1.1.1: Provides a set of base classes with core functionality to allow users to create and run Agent Based Models. There are vignettes on Extending Agents and Extending Resources.

Data

baseballr v1.2.0: Provides numerous utilities for acquiring and analyzing baseball data from online sources such as Baseball Reference, FanGraphs, and the MLB Stats API. See the Getting Started Guide and the vignettes NCAA Scraping and Plotting Statcast data.

toRvik v1.0.2: Provides a suite of functions to quickly scrape and tidy advanced metrics, detailed player and game statistics, team and coach histories, and more from Barttorvik. See the vignette.

ustfd v0.1.0: Lets users make requests from the US Treasury Fiscal Data API endpoints. See README for an example.

valet v0.9.0: Implements a client for the recently updated Bank of Canada Valet API. See README for examples.

Ecology

OBIC v2.0.1: Provides functions to calculate the Open Boden Index method used in the Netherlands to evaluate the quality of soils of agricultural fields and evaluate the sustainability of the current agricultural practices. There are vignettes on the Open soil index, Score aggregation, and Workability.

timbeR v2.0.1: Provides functions to estimate wood volumes, for example, number of logs, diameters along the stem and heights at which certain diameters occur. See Weiskittel, A. (2021) for background and the vignette for an introduction.

Finance

AssetAllocation v1.0.0: Provides functions to implement customizable asset allocation strategies and automatically download data from Yahoo Finance. See the vignette.

multilateral v1.0.0: Implements multilateral price index calculations focused on time product dummy regression and GEKS variations, and allows for extension of the methods through automatic window splicing. See Krsinich (2016) for information on window splicing and the vignette for examples.

Machine Learning

clusterHD Provides tools for clustering high dimensional data as described in Raymaekers and Zamar (2020) and Raymaekers and Zamar (2020).

tglkmeans v0.3.4: Efficiently implements the Kmeans algorithm. See Arthur and Vassilvitskii (2007) and Ostrovsky et al. (2013) for background and the vignette to get started.

Mathematics

hilbert v0.2.1: Provides utilities for encoding and decoding coordinates to and from Hilbert curves based on the iterative encoding implementation described in Chen et al. (2006). See the vignette to get started.

gellipsoid v0.7.2: provides functions to represent degenerate and unbounded generalized geometric ellipsoids together with methods for linear and duality transformations, and for plotting. The ideas are described in Friendly, Monette & Fox (2013). See README for examples.

Medicine

crossnma v1.0.1: Provides functions for cross-design and cross-format Network Meta-Analysis Regression as described in Hamza et al. 2022. See the vignette.

exact.n v1.0.0: Allows the user to determine minimum sample sizes that achieve target size and power at a specified alternative. See Lloyd & Ripamonti (2021) for the theory and README for examples.

stoppingrules v0.1.1: Provides functions for creating, displaying, and evaluating stopping rules for safety monitoring in clinical studies including stopping rule methods described in Goldman (1987), Geller et al. (2003), Ivanova, Qaqish, & Schell (2005), and Kulldorff et al. (2011). See README for an example.

Networks

incidentally v0.9.0: Provides functions to generate random incidence matrices and bipartite graphs under different constraints or using different generative models. See the vignette.

networkscaleup v0.1-1: Provides a variety of network scale-up models to analyze aggregated relational data, including models from Laga et al. (2021) Zheng et al. (2006), Killworth et al. (1998), and Killworth et al. (1998). See the vignette.

pald v0.0.1: Implements the partitioned local depths algorithm described in Berenhaut, Moore, & Melvin (2022) which may be helpful in determining both local and global structure in data. Look here to get started.

Statistics

bmstdr v0.1.4: Provides functions to fit, validate, and compares a number of Bayesian models for spatial and space-time point referenced and areal unit data. See the vignette for theory and examples.

cubble v0.1.0: Implements a spatiotemperal data object in a relational data structure to separate the recording of time variant and invariant variables. See the vignettes: aggregation, design, cubble, import, and matching.

incubate v1.1.8: Fits parametric models to time-to-event data that show an initial incubation period, i.e., a variable phase where the hazard is zero. The delayed Weibull distribution serves as the foundational data model. Look here for an example.

pspatreg v1.0.2: Provides functions to estimate and analyze spatial and spatio-temporal semiparametric models including spatial or spatio-temporal non-parametric trends, parametric and non-parametric covariates with a possible spatial lag for the dependent variable, and temporal correlation in the noise. See Basile et al. (2014), Rodriguez-Alvarez et al. (2015), and especially Minguez et al. (2020) for background. There is an Introduction, and vignettes on Cross-sectional data and Spatial panel data.

sfdep v0.1.0: Provides and interface to spdep to integrate sf objects and the tidyverse. There are vignettes on The Basics, Conditional Permutations, and spdep and pysal.

smile v1.0.4.1: Provides functions to estimate, predict, and interpolate areal data. For estimation and prediction, areal data are assumed to be an average of an underlying continuous spatial process as in Moraga et al. (2017), Johnson et al. (2020), and Wilson and Wakefield (2020). There are vignettes on Fitting Models, Areal Interpolation, Converting to spm, Spatial Covariance, and Method.

SpatialPOP v0.1.0: Provides functions to generate a spatial population from a spatially varying regression model under the assumption that observations are collected from a uniform two-dimensional grid with unit distance between any two neighboring points. See Chao et al. (2018) for method details and the vignette for an example.

Time Series

lite v1.0.0: Performs likelihood-based inference for stationary time series extremes following the approach of Fawcett and Walshaw (2012). Marginal extreme value inferences are adjusted for cluster dependence using the methodology of Chandler and Bate (2007). See the vignette.

spooky v1.1.0: Uses the Discrete Fast Fourier Transformation to extrapolate time features beyond their boundaries. Look here for examples and references.

Utilities

chromote v0.1.0: Implements the Chrome DevTools Protocol for controlling a headless Chrome web browser. Look here for examples.

chkptstanr v0.1.1: Implements a framework to checkpoint Bayesian models fit with Stan and brms. The MCMC sampler can be stopped and then restarted where it left off. There is a vignette for brms and another for Stan.

ivs v0.1.0: Implements a new interval vector class for generic interval manipulations including locating various kinds of relationships between two interval vectors, merging overlaps within a single interval vector, splitting an interval vector on its overlapping endpoints, and applying set theoretical operations on interval vectors. The package was inspired by Allen (1983). See the vignette for an introduction.

listr v0.0.2: Pools for common operations on lists such as selecting and merging data stored in lists which can be used with pipes. See the vignette.

shinyGizmo v0.1: Provides UI components and input widgets for Shiny applications to apply non-standard operations and address performance issues. See README for examples.

shinytest2 v0.1.0: Provides automated unit testing of Shiny applications through a headless Chromium browser. There is a Getting Started Guide and seven additional vignettes including Testing in depth, Robust testing, and Monkey testing.

thaipdf v0.1.2: Provides R Markdown templates and aLaTeX preamble to create PDFs from R Markdown documents in the Thai language. See the vignette for examples.

Visualization

ggtrendline v1.0.3: Enhances ggplot2 with tools to add a trendline with a confidence interval for linear or nonlinear regression models and show the equation. See Ritz and Streibig (2008) and Greenwell and Schubert Kabban (2014) for background and look here for examples.