July 2022: "Top 40" New CRAN Packages

by Joseph Rickert

Ninety-four new packages stuck to CRAN in July. Here are my “Top 40” selections in thirteen categories: Climate Modeling, Computational Methods, Data, Ecology, Genomics, Machine Learning, Mathematics, Medicine, Networks, Proteomics, Statistics, Utilities, and Visualization.

Climate Modeling

climetrics v1.0-5: Provides a framework that facilitates the spatio-temporal analysis of climate dynamics through exploring and measuring different dimensions of climate change in space and time. See the vignette.

Plot of  changes in climate extremes over portion of Europe

HurreconR v1.0: Implements the HURRECON model which estimates wind speed, wind direction, enhanced Fujita scale wind damage, and duration of EF0 to EF5 winds as a function of hurricane location and maximum sustained wind speed. See Boose et al. (2001) and Boose et al. (2004) for background, and the vignette for an overview.

TrenchR v0.1.0: Provides tools for translating environmental change into organism response. The biophysical modeling tools include both general models for heat flows and specific models to predict body temperatures for a variety of ectothermic taxa. See Gates (1980) for background. There are vignettes on Allometries and conversions, Estimating microclimates, and Estimating body temperatures.

Plot of  azimuth angle variation over the year

Computational Methods

elastes v0.1.6: Provides functions to compute functional elastic shape means over sets of open planar curves using a novel approach where planar curves are treated as complex functions. Also, a full Procrustes mean is estimated from the corresponding smoothed Hermitian covariance surface. See Steyer et al. (2022) and Stöcker et. al. (2022) for background and the vignette for examples.

Plot of smooth polynomial mean

ino v0.1.0: Provides a comprehensive toolbox for comparing different initialization strategies when performing numerical optimization. There is an Introduction and a vignette with an HMM example.

Data

giedata v0.1.0: Provides functions to access the API for GIE, Europe’s Gas Infrastructure database. See README to get started.

Ecology

rgrass v0.3-3: Implements a new interface to the GRASS geographical information system that supports both starting R from within the GRASS environment, or running a free-standing R session in a temporary GRASS location. There is an Introduction and a vignette on object formats.

riverconn v0.3.22: Provides functions to calculate indices for river network connectivity. See Jumani et al. (2021) for a review of the incdices and Baldan et al. (2022) for a list of package capabilities and architecture. Have a look at the vignette for examples.

Plots of river connectivity graphs

Genomics

dcifer v1.1.1: Implements Dcifer (Distance for complex infections: fast estimation of relatedness), an identity by descent based method to calculate genetic relatedness between polyclonal infections from biallelic and multiallelic data. See Gerlovina et al. (2022) for the details, and the vignette for an example.

Plot of pairwise relatedness for infection strains. Points representing significantly related strains are outlined

qPCRtools v0.1.1: Provides methods to calculate the amplification efficiency of genes, a crucial step in the qPCR process. See the vignette.

Box plots for relative gene expression distributions

scAnnotate v0.0.4: Implements a data-driven cell type annotation tool for single-cell RNA sequencing data. See Ji et al. (2022) for details and the vignette for an introduction.

Machine Learning

cito v1.0.0: Provides functions for building and training custom neural networks using torch. See the vignette.

Structure plot of a generated neural network

etree v0.1.0: Provides functions to implement Energy Trees, statistical models that perform classification and regression with structured and mixed-type data. See Giubilei et al. (2022) for a description of Energy Trees and the vignettes eforest and etree for examples.

Plot of an Energy Tree

LDABiplots v0.1.2: Provides tools to extract, explore, analyze, and visualize news published on the web by digital newspapers using Latent Dirichlet and machine learning algorithms. See Ble et al. (2003) and Gabriel (1971) for background. There are English and Spanish versions of the vignette.

mildsvm v0.4.0: Implements a support vector machine classifier for weakly supervised, multiple instance data. See Kent and Yu (2022) and Muandet et al. (2012) for the theory and README for an example.

nestedcv v0.2.3: Provides functions to perform nested cross-validation as described in Stone (1977) for lasso and elastic-net regularized linear models for glmnet. See the vignette.

Block diagram for nested cross validation

Mathematics

delaunay v1.1.0: Provides functions to construct and visualize 2D and 3D Delaunay triangulations. See README for some visual examples.

3D Delaunay triangulation

Medicine

activeAnalyzer v1.0.4: Provides a tool to analyse Actigraphy accelerometer data using PROactive Physical Activity in COPD (chronic obstructive pulmonary disease) instruments. See the vignette for examples.

Plots of actigraphydata

pedbp v1.0.0: Provides data and utilities for estimating pediatric blood pressure percentiles by sex, age, and height. See Lo et al. (2013) and Martin et al. (2022) for background, and the vignette for an overview.

Plot showing median blood pressure by age for different heights based on percentiles for age

tipmap v 0.1.7: Implements tipping point analysis for clinical trials using Bayesian dynamic borrowing via robust meta-analytic predictive priors as described in Best et al. (2021).

Networks

ergm.multi v0.1.0: Provides a set of extensions for the ergm package to fit multilayer, multiplex, and multirelational networks as well as samples of multiple networks. See Krivitsky et al. (2020) and Krivitsky et, al. (2022) for the details and the vignette for an extended example.

Pearson residuals vs. fitted values

Families v1.0.1: Provides tools to study kinship networks, grand parenthood, and double burden (presence of children and oldest old parents) in virtual population produced by VirtualPop. See the vignette for examples.

Distribution of age of child with reference to distributions of events in mothers life

Proteomics

promor v0.1.0: Implements a comprehensive set of tools for label-free proteomics data analysis and machine learning modeling including differential expression analysis, predictive modeling and performance assessment. Data from MaxQuant may be used. See the vignette for an introduction.

Block diagram of promor workflow

Statistics

GPCERF v0.1.0: Provides a non-parametric Bayesian framework based on Gaussian process priors for estimating causal effects of a continuous exposure and detecting change points in the causal exposure response curves using observational data. See Ren et al. (2021). Have a look at the Introduction and the vignettes Full Gaussian Process and Nearest-neighbor Gaussian Process.

Plots of CERF vs. Exposure level

lnmCluster v0.3.1: Extends the logistic normal multinomial (LNM) clustering model proposed by Fang and Subedi (2020) to provide LNM clustering for compositional data. Details of model assumptions and interpretation can be found in the papers Tu & Subedi (2021) and Tu & Subedi (2022). See the vignette for an example.

tlars v0.0.1: Provides functions to compute the solution path of the Terminating-LARS (T-LARS) algorithm. See Machkour et al. 2022, Efron et al. (2004) and Tibshirani (1996) for the theory, and the vignette for examples.

Utilities

codebookr v0.1.5: Provides functions to create code books (i.e. data dictionaries) directly from a data frame. See README for examples.

datadictionary v0.1.0: Provides tools to creates a data dictionary from any dataset in an R environment. It includes functions to add variable labels and write to Excel.

dtrackr v0.2.4: Provides tools to track and document dplyr data pipelines. As you filter, mutate, and join your way through a data set, functions seamlessly track data flow and generate publication ready documentation of the data pipeline. See the vignettes Consort statment example, Configuration example, Basic Operation, and Joining data pipelines.

Flowchart of a pipeline

howler v0.2.0: Enables audio interactivity within shiny applications using howler.js. See the vignette.

ixplorer v0.2.2: Provides tools to create and view tickets in gitea, a self-hosted git service, using an RStudio addin. It includes helper functions to publish documentation and use git. There are several vignettes including ixplorer basics and Credential management.

nextGenShinyApps v1.5: Provides responsive tools for designing and developing Shiny dashboards and applications. The scripts and style sheets are based on jQuery and Bootstrap. See the vignette for examples.

Example of a shiny app page

nplyr v0.1.0: Provides functions for manipulating nested data frames in a list-column using dplyr without first having to unnest()them. See the vignette.

renderthis v0.1.0: Provides tools to render slides to different formats, including html, pdf, png, gif, pptx, and mp4, as well as tool to make a png file of the first slide of a presentation that is re-sized for sharing on social media. There is an Overview and a vignette on basic usage.

video video: 0.1.0: Enables video interactivity within shiny applications using video.js. See the vignette.

Visualization

ensModelVis v0.1.0: Provides a function to display model fits for multiple models and their ensembles. There are vignettes for Classification and Regression.

Plot of prediction accuracy for an ensemble

ggpackets v0.2.0: Provides tools to create groups of ggplot2 layers that can be easily migrated from one plot to another, reducing redundant code and improving the ability to format many plots that draw from the same source. See the Getting Started Guide and the vignettes Composing Templates & Functions and Misc Examples.

Plot of growth vs. age for multiple seeds built from template

ggseqplot v0.7.2: Provides wrappers to render TraMinR sequence plots in ggplot2. See the vignette.

Plot of Months vs. Sequences

RcppColors v0.1.1: Provides C++ header files to deal with color conversion from color spaces to hexadecimal with Rcpp, and exports some color mapping functions to R. Look here for examples.

Multicolored rotating sphere

xadmix 1.0.0: Provides functions that provide a quick way of subsetting genomic admixture data and generating customizable stacked barplots. See the vignette.

Admixture barplots for individuals from various countries

Share Comments · · ·

You may leave a comment below or discuss the post in the forum community.rstudio.com.