Site icon R-bloggers

September 2022: “Top 40” New CRAN Packages

[This article was first published on R Views, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

Two hundred and two new packages made it to CRAN in September. Here are my “Top 40” selections in fourteen categories: Computational Methods, Data, Genomics, Machine Learning, Mathematics, Medicine, Pharmacology, Psychology, Science, Social Science, Statistics, Time Series, Utilities, and Visualization.

Computational Methods

kimfilter v1.0.0: Provides an Rcpp implementation of the multivariate Kim filter, which combines the Kalman and Hamilton filters for state probability inference. The filter is designed for state space models and can handle missing values and exogenous data in the observation and state equations. See Kim et al. (1999) for details and the vignette for examples.

SparseChol v0.1.1: Provides a C++ implementation of sparse LDL decomposition of symmetric matrices and solvers as described in Davis (2016). See README for an example.

Data

allhomes v0.3.0: Provides tools to extract past sales data for specific suburbs and years from the Australian property website including the address and property details, date, price, block size and unimproved value of properties. See README to get started.

kgp 1.1.0: Provides access to the metadata about populations and data about samples from the 1000 Genomes Project, including the 2,504 samples sequenced for the Phase 3 release and the expanded collection of 3,202 samples with 602 additional trios. The data is described in Auton et al. (2015) and Byrska-Bishop et al. (2022), and raw data is available here. See Turner (2022) for details and look here for examples.

eHDPrep v1.2.1: Provides a tool for the preparation and enrichment of health datasets for analysis including functions to assess data quality and enable semantic enrichment of a dataset by discovering metavariables from relationships among input variables determined from user-provided ontologies. See the vignette.

Genomics

refdb v0.1.1: Implements a reference database manager offering a set of functions to import, organize, clean, filter, audit and export reference genetic data and includes functions to download sequence data from Bold Systems and NCBI GenBank. There is an Introduction and a vignette on Downloading and combining data.

RestoreNet v1.0: Implements a random-effects stochastic model that starts from an Ito-type equation describing the dynamics of cells duplication, death and differentiation at clonal level to detect clonal dominance events in gene therapy studies. See Del Core et al., (2022) for details and the vignette for the math and examples.

Machine Learning

DynForest v1.0.0: Implements a random forests model that uses multiple longitudinal predictors to make survival predictions for individual subjects. See Devaux et al.(2022) for the details and the vignette for an example.

multiview v0.4: Provides functions to fit cooperative learning models which are supervised learning models for multiple sets of features (“views”), as described in Ding et al. (2022). See the vignette for an introduction.

survex v0.1.1: Implements methods for explaining survival models. Methods include SurvSHAP(t) as described in Krzyzinski et al. (2022), SurvLIME introduced in Kovalev et al. (2020), as well as methods described in Biecek et al. (2021). See the vignettes Creating custom extensions and Package usage.

voice v0.4.14: Provides general purpose tools for voice analysis, speaker recognition and mood inference. See thevignette for an example.

Mathematics

collatz v1.0.0: Provides functions to explore the Collatz conjecture including the ability to retrieve the hailstone sequence, the stopping time, total stopping time and tree-graph. There are four vignettes including: collat, Hailstone Sequences, and Tree Graphs.

greta.dynamics v0.2.0: Implements a greta extension for analyzing transition matrices and ordinary differential equations representing dynamical systems. Have a look at the iterate-matrix and ode-solve examples.

Medicine

historicalborrow v1.0.4: Implements a hierarchical model and a mixture model to borrow historical control data from other studies to better characterize the control response a study. See Viele et al. (2013) for a discussion of the methods and the vignettes Methods and Usage.

nphRCT v0.1.0: Provides functions to perform a stratified weighted log-rank test in a randomized controlled trial which can be visualized as a difference in average score on the two treatment arms. See Magirr and Burman (2018), Magirr (2020), and Magirr (2022) for a description of the tests and the vignettes Survival tests as differences-of-means and The weighted log-rank test for examples.

Pharmacology

rPBK v0.2.0: Provides functions to fit and simulate any kind of physiologically-based kinetic model which allows for multiple compartments, links between pairs of compartments, and links between compartments and the external medium. See Charles et al. (2022) for background and the vignette for examples.

xhaz v2.0.1: Provides functions to fit relative survival regression models with or without proportional excess hazards and with the additional possibility to correct for background mortality by one or more parameters. See Touraine et al. (2020), Mba et al. (2020), and Goungounga et al. (2019) for a description of the models and the vignette for an introduction.

Psychology

rempsyc v0.0.9: Provides convenience functions for Psychology including functions to customize plots and tables following the style of the American Psychological Association which are exportable to Microsoft Word. There are nine vignettes including Test linear regression assumptions, Planned Contrasts Analyses, and Publication-ready scatter plots.

Science

Karen v1.0: Implements a stochastic framework that combines biochemical reaction networks with extended Kalman filter and Rauch-Tung-Striebel smoothing allowing biologists to investigate the dynamics of cell differentiation from high-dimensional clonal tracking data subject to measurement noise, false negative errors, and systematically unobserved cell types. See Del Core et al. (2022) for details and the vignette for an example.

LMD v1.0.0: Implements Local Mean Decomposition, an iterative and self-adaptive approach for demodulating, processing, and analyzing multi-component amplitude modulated and frequency modulated signals. See Smith (2005) for background and the vignette to get started.

oceanexplorer v0.0.2: Provides tools to explore the NOAA world ocean atlas including functions to extract NetCDF data and visualize physical and chemical parameters. A shiny app allows interactive exploration. Look here for background information and see the vignette for examples.

WormTensor v0.1.0: Implements a toolkit to detect clusters from distance matrices calculated between the cells of multiple animals (Caenorhabditis elegans) from input time-series matrices. Includes functions to generate, cluster, and visualize distance matrices, and to retrieve calculated distance matrices from figshare. See the vignette.

Social Science

demcon v0.3.0: Implements an open-source toolkit developed by ISciences and the DANTE Project for exploring popular political, institutional, and constitutional datasets with the goal of reducing barriers to entry in political science research by automating common acquisition and pre-processing procedures. This package focuses on the V-Dem dataset. There are four vignettes including A Brief Review of Constitutional Datasets and Country Coding Considerations for Dataset Harmonization.

sdam v1.1.4: Provides tools for performing social dynamics and complexity analyses about the Ancient Mediterranean in the context of the SDAM project based at the Department of History and Classical Studies at Aarhus University. There are vignettes on Dates, Re-encoding people, Datasets, and Maps and Networks.

Statistics

adjustedCurves v0.9.0: Provides functions to estimate and plot confounder-adjusted survival curves using either direct adjustment, inverse probability weighting, empirical likelihood estimation, or targeted maximum likelihood estimation. See Denz et. al (2022) for details and the vignette for an introduction.

CovRegRF 1.0.1: Implements a method that uses random forests to estimate the covariance matrix of a multivariate response given a set of covariates as described in in Alakus et al. (2022). The vignette provides an example.

greta.gp v0.2.0: Provides the syntax to create and combine full rank or sparse Gaussian process kernels in greta. See Golding (2019) for background on greta and the vignette to get started.

fwb v0.1.1: Implements the fractional weighted bootstrap (aka the Bayesian bootstrap) to be used as a drop-in for functions in the boot package. The fractional weighted bootstrap involves drawing weights randomly that are applied to the data rather than resampling units from the data. See Xu et al. (2020) for the theory and README for an example.

glmmrBase v0.1.2: Provides the R6 classes Covariance, MeanFunction and Model to allow for the flexible specification of generalized linear mixed models, and also functions to produce relevant matrices, values, and analyses. See README for details.

rocbc v0.1.1: Provides functions for inferences and comparisons around the AUC, the Youden index, the sensitivity at a given specificity level, the optimal operating point of the ROC curve, and the Youden based cutoff. See Bantis et al. (2018) and Bantis et al. (2021 and the vignette for examples.

vglmer v1.0.2: Provides functions to estimate hierarchical models using mean-field variational Bayes which can accommodate models with an arbitrary number of random effects and requires no integration to estimate. See Goplerud (2022) for details and README for an example.

Time Series

bsvars v1.0.0: Implements MCMC algorithms for Bayesian estimation of Structural Vector Autoregressive (SVAR) models including a wide range of SVAR models. See Lütkepohl & Woźniak (2020), Waggoner & Zha (2003) for background.

gasmodel v0.1.0: Provides functions to estimate, forecast and simulate generalized autoregressive score (GAS) models of Creal, Koopman, and Lucas (2013) and Harvey (2013). There are two case study vignettes Bookshop Orders and Hockey Rankings and another on Probability Distributions.

kalmanfilter v2.0.0: Uses Rcpp to implement a multivariate Kalman filter for state space models that can handle missing values and exogenous data in the observation and state equations. See Kim & Nelson (1999) for details and the vignette for an example.

MultiGlarmaVarSel v1.0: Provides functions to perform variable selection in high-dimensional sparse GLARMA models. See Gomtsyan et al. (2022) for details and the vignette for examples.

VedicDateTime v0.1.1: Provides functions to facilitate conversion between the Gregorian and Vedic calendar systems. See Bokde (2021) and Ramakumar (2011) and the vignette for an overview with examples.

Utilities

bundle v0.1.0P Provides functions to serialize model objects with a consistent interface. See the vignette to get started.

r2resize v1.3: Implements an automatic resizing toolbar for containers, images and tables for markdown, rmarkdown and quarto documents. There is Welcome vignette and another on New features.

Visualization

figuRes2 v1.0.0: Provides functions and supporting documentation to streamline a variety of figure production tasks. There are vignettes on Basics, Forest plots, KM plots, and Production Workflows.

openairmaps v0.5.1: Combines openair air quality maps with leaflet to plot site maps with directional analysis figures such as polar plots, and air mass trajectories. See README for examples.

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 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.