Nov 2017: New Package Picks

December 21, 2017
By

(This article was first published on R Views, and kindly contributed to R-bloggers)

Two hundred thirty-seven new packages made it to CRAN in November. Here are my picks for the “Top 40” organized into the categories: Computational Methods, Data, Data Science, Science, Social Science, Utilities and Visualizations.

Computational Methods

CVXR v0.94-4: Implements an object-oriented modeling language for disciplined convex programming (DCP) which allows users to formulate and solve convex optimization problems. The vignette introduces the package. Look here for examples and theory.

PreciseSums v0.1: Implements the Kahan (1965) sum, Neumaier (1974) sum, pairwise-sum adapted from ‘NumPy’ and arbitrary precision sum.

Data

ballr v0.1.1: Provides functions for accessing data/tables from basketball-reference.com. There is a vignette.

biofiles v1.0.0: Provides functions to parse GenBank/GenPept records into native R objects, access and manipulate the sequence and annotation information. There is an Introduction.

ipumsr v0.1.1: Enables users to import census, survey and geographic data from IPUMS. There is an Introduction and vignettes on CPS Extraction, Geographic Data, NHDIS Datasets and on Using Value Labels.

proPubBills v0.1: Implements an API wrapper around the ProPublica API. The brief vignette shows how to use it.

Rpolyhedra v0.1.0: Contains a 142 polyhedra database scraped from PHD files as R6 objects, and provides rgl visualizing capabilities. The PHD format was created to describe the geometric polyhedra definitions derived mathematically by Andrew Hume and by the Kaleido program of Zvi Har’El. The vignette will get you started.

voteogram v0.2.0: Provides tools to retrieve United States Congressional voting data from ProPublica, prepare the data for plotting with ggplot2 and create vote cartograms and themes. The vignette provides examples.

Data Science

imbalance v0.1.1: Provides algorithms to treat unbalanced datasets. See the vignette for details.

intrinsicdimension v1.1.0: Implements a variety of methods for estimating intrinsic dimension of data sets (i.e the manifold or Hausdorff dimension of the support of the distribution that generated the data) as reviewed in Johnsson et al.(2015). The vignette provides an Overview.

ppclust v0.1.0: Implements probabilistic clustering algorithms for partitioning datasets including Fuzzy C-Means (Bezdek, 1974), Possibilistic C-Means (Krishnapuram & Keller, 1993), Possibilistic Fuzzy C-Means (Pal et al, 2005), Possibilistic Clustering Algorithm (Yang et al, 2006), Possibilistic C-Means with Repulsion (Wachs et al, 2006) and the other variants. There are vignettes on Fuzzy C-Means, Probabilistic C-Means, Probabilistic Fuzzy C-Means and Unsupervised Probabilistic Fuzzy C-Means.

textrank v0.2.0: Implements the textrank algorithm, an extension of the Pagerank algorithm for text. See the paper Mihalcea & Tarau (2004) and the vignette.

TrajDataMining v0.1.4: Contains a set of methods for trajectory data preparation, such as filtering, compressing and clustering, and for trajectory pattern discovery. The vignette provides examples.

Science

benthos v1.3-4: Provides preprocessing tools and biodiversity measures for analyzing marine benthic data. See Van Loon et al. (2015) for an application and the vignette for an introduction to the package.

nlmixr v0.9.0-1: Provides functions to fit and compare nonlinear mixed-effects models in differential equations with flexible dosing information commonly seen in pharmacokinetics and pharmacodynamics. See Almquist et al. (2015). The vignette shows how to use the package.

PCRedux v0.2.5-1: Provides functions to extract Polymerase Chain Reactions (qPCR) amplification curve data for machine learning purposes. For details see Pabinger et al.(2014) and the vignette. Clustering via Hausdorff distance

PDN v0.1.0: Provides tools for building patient level networks for predicting medical outcomes based on the paper by Cabrera et al. (2016). See the vignette for an introduction.

Rraven v1.0.0: Provides a tool to exchange data between R and Raven sound analysis software. The vignette shows how to use the software.

spew v1.3.0: Provides tools for generating Synthetic Populations and Ecosystems. See Gallagher et al. (2017) for details and the vignette for a brief tour.

Social Science

EvolutionaryGames v0.1.0: Provides a set of tools to illustrate the core concepts of evolutionary game theory, such as evolutionary stability or various evolutionary dynamics, for teaching and academic research. See the vignette for details.

Statistics

[bang(https://CRAN.R-project.org/package=bang)] v1.0.0: Provides functions for the Bayesian analysis of some simple common models, without using Markov Chain Monte Carlo (MCMC) methods such as Gibbs sampling. There is an Introduction and vignettes on Hierarchical 1-way ANOVA, Conjugate Hierarchical Models and Posterior Predictive Checking.

beast v1.0: Provides a method for the Bayesian estimation of change-points in the slope of multivariate time series. See Papastamoulis et al (2017) for a detailed presentation of the method.

CorShrink v0.1.1: Offers functions to perform adaptive shrinkage of correlation and covariance matrices using a mixture model prior over the Fisher z-transformation of the correlations. See Stephens (2016) for details. The vignette contains examples.

dvmisc v1.1.1: Provides faster versions of base R functions (e.g. mean, standard deviation, covariance, weighted mean), mostly written in C++, along with other miscellaneous functions.

inlabru v2.1.2: Facilitates spatial modeling using integrated nested Laplace approximation via the INLA package and also implements a log Gaussian Cox process likelihood for modeling univariate and spatial point processes. Yuan et al. (2017).

outbreaker2 v1.0-0: Allows users to reconstruct disease outbreaks using epidemiological and genetic information. See Jombart et al. (2014) for the details. There is a package Overview as well as an Introduction and vignettes on Using Custom Priors and The Rcpp API.

probout v1.0: Provides functions to estimate unsupervised outlier probabilities for multivariate numeric data with many observations from a nonparametric outlier statistic. There is a vignette.

quokar v0.1.0: Provides diagnostics for quantile regression models including detecting influential observations, robust distance methods, generalized Cook’s distance and Q-function distance (see Benites et al. (2015)) and mean posterior probability and Kullback–Leibler divergence methods (see Santos & Bolfarine (2016)). The vignette introduces the package.

Robust Distance-Residual Plot 

tidyposterior v0.0.1: This memorably named package implements a Bayesian approach for examining the differences between models and aims to answer the question: “When looking at resampling results, are the differences between models real?” The methods included are similar to those described in Benavoli et al (2017). There is a Getting Started Guide and a vignette on Bayesian Models.

trialr v0.0.1: Offers a showcase of Bayesian clinical trial designs, implemented in RStan and R including some designs implemented in R for the first time (e.g. EffTox’ by Thall & Cook (2004). There are vignettes on the BEBOP Design, EffTox and Hierarchical Bayesian Models for Binary Responses.

tvReg v0.2.1: Provides functions for fitting simultaneous equations with time varying coefficients, for both independent and correlated equations. The vignette contains examples.

Utilities

cli v1.0.0: Implements a suite of tools designed to build attractive command line interfaces. Includes tools for drawing rules, boxes, trees, and ‘Unicode’ symbols with ‘ASCII’ alternatives. See README for details.

float v0.1-1: Extends R’s linear algebra facilities to include 32-bit float (single precision) data. There is a vignette.

mudata2 v1.0.0: Offers functions and data structures designed to easily organize and visualize spatiotemporal data. There are vignettes for usinng and creating mudata2 objects.

rhub v1/0.2: Provides an interface to the R-Hub package build system sponsored by the R Consortium. Run R CMD check on Windows, macOS, Solari and various Linux distributions.

Visualizations

ALEPlot v1.0: Offers functions to visualizes the main effects of individual predictor variables and their second-order interaction effects in black-box supervised learning models. The vignette contains several examples.

dbplot v0.1.1: Leverages dplyr to process the calculations for a plot inside a database. Helper functions abstract the work at three levels: outputs the ggplot, the calculations and the formula needed to calculate bins. See README to get started.

ggalluvial v0.5.0: Implements ggplot2 stat and geom layers for alluvial diagrams, charts that use x-splines (alluvia and flows), sometimes augmented with stacked bars (lodes or strata), to visualize incidence structures derived from several data types. The vignette provides examples.

shinyaframe v1.0.1: Enables users to make R data available in Web-based virtual reality experiences for immersive, cross-platform data visualizations. It provides functions to create 3-dimensional data visualizations with Mozilla A-Frame. The vignette shows how.

tactile v0.1.0: Extends lattice, providing new high-level functions, methods for existing functions, panel functions, and a theme. There are vignettes for New High-Level Functions, New Methods for Lattice and the tactile Theme.

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 on topics such as: Data science, Big Data, R jobs, visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...



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)