January 2020: “Top 40” New R Packages
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.
One hundred forty-seven new packages made it to CRAN in January. Here are my “Top 40” picks in nine categories: Computational Methods, Genomics, Machine Learning, Mathematics, Medicine, Statistics, Time Series, Utilities and Visualization.
FSSF v0.1.1: Provides three methods proposed by Shang & Apley (2019) to generate fully-sequential space-filling designs inside a unit hypercube.
seagull v1.0.5: Implements a proximal gradient descent solver for the operators lasso, group lasso, and sparse-group lasso. There is an Introduction.
babette v2.1.2: Provides access to the BEAST2 Bayesian phylogenetic tool, that uses DNA/RNA/protein data and many model priors to create a posterior of jointly estimated phylogenies and parameters. There is a Tutorial, a Basic Demo, a Step by Step Demo, a vignette on Nested Sampling, and another with Examples.
statgenGWAS v1.0.3: Provides fast single trait Genome Wide Association Studies (GWAS) following the method described in Kang et al. (2010). See the vignette for details.
akc 0.9.4: Provides a tidy framework for automatic knowledge classification and visualization. There is a Tutorial and a vignette on classification based on keyword co-occurrence.
ced v1.0.1: Provides R bindings for the Google Compact Encoding Detection library which takes as input a source buffer of raw text bytes and probabilistically determines the most likely encoding for that text.
forestError v0.1.1: Provides functions to estimate the conditional error distributions of random forest predictions and common parameters of those distributions, including conditional mean squared prediction errors, conditional biases, and conditional quantiles as proposed by Lu & Hardin (2019).
ksharpv0.1.0.1: Provides functions to sharpen clusters by adjusting existing clusters to create contrast between groups. The vignette provides examples and references.
mosmafs v0.1.1: Provides functions for simultaneous hyperparameter tuning and feature selection through both single-objective and multi-objective optimization as described in Binder et al. (2019). There is an Introduction and another vignette on Multi-Fidelity.
themis v0.1.0: Provides recipes for dealing with unbalanced data sets including balancing by increasing the number of minority cases using SMOTE, Borderline-SMOTE and ADASYN; or by decreasing the number of majority cases using NearMiss or Tomek link removal. Look here examples.
caracas v0.1.0: Implements computer algebra by providing access to the Python
SymPy library making it possible to solve equations symbolically, find symbolic integrals, symbolic sums and other important quantities. There is a vignette.
clifford v1.0-1: Provides a suite of routines for Clifford algebras. Special cases include Lorentz transforms, quaternion multiplication, and Grassman algebra. See the vignette for details.
metan v1.3.0: Provides functions for the stability analysis of multi-environment trial data using parametric and non-parametric methods including additive main effects and multiplicative interaction analysis, Gauch (2013); genotype plus genotype-environment biplot analysis, Yan & Kang (2003); joint regression analysis, Eberhart & Russel (1966) and much more. See the vignette to get started.
nosoi v1.0.0: Implements a flexible agent-based stochastic transmission chain, epidemic simulator. There is a Getting Started Guide and vignettes on Homogenous Populations, Discrete Populations, Continuous Populations, and Visualization.
shinySIR v0.1.1: Provides interactive plotting for mathematical models of infectious disease spread. Users can choose from a variety of common built-in ordinary differential equation models or create their own. See Keeling & Rohani (2008) and Bjornstad (2018) for background and the vignette for details.
transplantr v0.1.0: Provides a set of vectorised functions to calculate medical equations used in transplantation, focused mainly on transplantation of abdominal organs. There are vignettes on Estimated GFR, HLA Mismatch Level, Kidney Risk Scores, and Liver Recipient Scoring.
bggum v1.0.2: Provides a Metropolis-coupled Markov chain Monte Carlo sampler, post-processing, parameter estimation functions, and plotting utilities for the generalized graded unfolding model of Roberts et al.(2000). See the vignette for the math and examples.
cSEM v0.1.0: Provides functions to estimate, assess, test, and study linear, nonlinear, hierarchical and multigroup structural equation models using composite-based approaches and procedures, including estimation techniques such as partial least squares path modeling (PLS-PM) and its derivatives (PLSc, ordPLSc, robustPLSc), generalized structured component analysis (GSCA) and others. There is an Introduction and vignettes on Notation, Terminology, and Post Estimation.
mcp v0.2.0: Implements regression with multiple change points which can be for means, variances, autocorrelation structure, and any combination of these. It provides a generalization of the approach described in Carlin et al. (1992) and Stephens (1994). See README for examples.
metopolis v0.1.5: Provides functions for learning how the Metropolis algorithm works. The vignette includes examples of hand-coding a logistic model using several variants of the Metropolis algorithm.
miceRanger v1.3.1: Implements multiple imputation by chained equations with Random Forests. There are vignettes on the Mice Algorithm, Filling in Missing Data, and Diagnostics Plotting.
momentfit v0.1-0. Provides functions to perform method of moment fits including the Generalized method of moments, (Hansen (1982) and the Generalized Empirical Likelihood, (Smith (1997). There are vignettes on Generalized Empirical Likelihood and Generalized Method of Moments.
nlraa v0.53: Implements nonlinear regression functions using self-start algorithms including the Beta growth function proposed by Yin et al. (2003). There is an Introduction, a vignette with examples from Archontoulis & Miguez (2015) and another vignette with examples from Oddi et al. (2019).
PoissonBinomial v1.0.2: Implements multiple exact and approximate methods for computing the probability mass, cumulative distribution and quantile functions, as well as generating random numbers for the Poisson Binomial distribution as described in Hong (2013) and Biscarri et al. (2018). There are vignettes on Efficient Computation, Approximate Procedures, Exact Procedures, and Usage with Rcpp.
relgam v1.0: Implements a method for fitting the entire regularization path of the reluctant generalized additive model (RGAM) for linear regression, logistic, Poisson and Cox regression models. See Tay & Tibshirani (2019) for details.
s2net v1.0.1: Implements the generalized semi-supervised elastic-net, extending the supervised elastic-net to make it practical to perform feature selection in semi-supervised contexts. See Culp (2013) for references on the Joint Trained Elastic-Net and the vignette for an example.
signnet v0.5.1: Implements methods for the analysis of signed networks including several measures for structural balance as introduced by Cartwright & Harary (1956), blockmodeling algorithms from Doreian (2008), various centrality indices, and projections introduced by Schoch (2020). There are vignettes on Blockmodeling, Centrality, Complex Matrices, Signed Two-Mode Networks, Signed Networks, and Structural Balance.
survParamSim v0.1.0: Provides functions to perform survival simulation with parametric survival model generated from
survreg function in
survival package. See the vignette.
xnet v0.1.11: Provides functions to fit a two-step kernel ridge regression model for predicting edges in networks, and carry out cross-validation. See Stock et al. (2018) for background. There is an Introduction, and vignettes on Data Preparation, and the S4 Class Structure.
pcts v0.14-4: Provides classes and methods for modeling and simulating periodically correlated and periodically integrated time series. For background see Boshnakov & Iqelan (2009) and Boshnakov (1996).
fdaACF v0.1.0: Provides functions to compute autocorrelation functions for functional time series. Look here for examples.
dmdScheme v1.0.0: Provides a framework for developing domain specific metadata. There is an Introduction and vignettes on Creating a New Scheme and Minimum Requirements.
gridtext v0.1.0: Provides support for rendering of formatted text using
grid graphics. Look here for examples.
netstat v0.1.1: Implements an interface to the netstat command line utility for retrieving and parsing network statistics from Transmission Control Protocol (TCP) ports. See The Linux System Administrator’s Manual, and the Microsoft website for basic information.
progressr v0.4.0: Provides a minimal, unifying API for scripts and packages to report progress updates including when using parallel processing. The vignette offers an introduction.
PROJ v0.1.0: Implements a wrapper around the generic coordinate transformation software, PROJ that transforms geospatial coordinates from one coordinate reference system to another, and cartographic projections as well as geodetic transformations. See the vignette.
round v0.12-1: Provides functions to explore differences between current and potential future versions of the base R
round() function along with some partly related C99 math lib functions not in base R. See the vignette for the details.
warp v0.1.0: Implements tooling to group dates by a variety of periods including: yearly, monthly, by second, by week of the month, and more. See the vignette for examples.
apyramid v0.1.0: Provides a quick method for visualizing non-aggregated line-list or aggregated census data stratified by age and one or two categorical variables (e.g. gender and health status) with any number of values. This package is part of the R4Epis Project. See the vignette for examples.
mlr3viz v0.1.1: Provides visualizations for
mlr3 objects including barplots, boxplots, histograms, ROC curves, and Precision-Recall curves. README offers some examples.
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.