One hundred forty-one new packages made it to CRAN in October. Here are my “Top 40” picks in twelve categories: Computational Methods, Data, Genomics, Machine Learning, Medicine, Networks, Science, Social Science, Statistics, Time Series, Utilities, and Visualization.

Computational Methods

gslnls v1.0.2: Implements an R interface to nonlinear least-squares optimization with the GNU Scientific Library (GSL). See M. Galassi et al. (2009).

rsvddpd v1.0.0: Implements a robust method for computing the singular value decomposition using power density divergence. See Roy et. al (2021) for background and the vignette for an example.

Data

blsR v0.2.1: Implements v2 of the Bureau of Labor Statistics API for requests of survey information and time series data. See README to get started.

insiderTrades v0.0.1: Provides functions to download insider trading transactions and insider holdings from a public NoSQL SEC database using keyword criteria and generate a relational dataframe. See the vignettes insiderTrades and pullAndScrape.

KingCountyHouses v0.1.0: Contains data on houses in and around Seattle WA are included. Basic characteristics are given along with sale prices. See README.

meteospain v0.0.3: Provides access to different Spanish meteorological stations data services and APIs including AEMET, SMC, MG, and Meteoclimatic. There are seven short vignettes including API limits and loops and Compatibility between services.

owidR v1.1.0: Provides function to import, search, download, and visualize data from the Our World in Data website. See the vignette.

QBMS v0.6: Enables users to query the Breeding Management System database. There is a short Tutorial.

Genomics

digitalDLSorteR v0.1.1: Implements tools for the deconvolution of bulk RNA-Seq data using context-specific deconvolution models based on Deep Neural Networks using scRNA-Seq data as input. See Torroja & Sanchez-Cabo (2019) for details. There are five vignettes including Keras/TensorFlow installation and configuration and Building new deconvolution models.

Platypus v3.2.3: Implements an open-source software platform for investigating B-cell receptor and T-cell receptor repertoires from scSeq experiments which also incorporates transcriptional information involving unsupervised clustering, gene expression and gene ontology. See Yermanos et al. (2021) and the vignette to get started.

quincunx v0.1.4: Provides programmatic access to the PGS Catalog through the REST API. See README for the cheatsheet.

SNPfilter v0.1.0: Provides functions to interactively and reproducibly visualize and filter SNP (single-nucleotide polymorphism) datasets, including functions for visualizing various quality and missing data metrics for a SNP dataset, and then filtering the dataset based on user specified cutoffs. See the vignette.

Machine Learning

conText v1.0.0: Implements a framework to estimate context-specific word and short document embeddings using the a la carte embeddings approach developed by Khodak et al. (2018) and evaluate hypotheses about covariate effects on embeddings using the regression framework developed by Rodriguez et al. (2021). There is a Quick Start Guide.

pixelclassifier v1.0.0: Implements a Support Vector Machine to classify the pixels of an image file by its color. See the vignette.

predtools v0.0.2: Provides functions for evaluating predictive models, including plotting calibration curves and model-based Receiver Operating Characteristic (mROC) curves based on Sadatsafavi et al. (2021). There are three vignettes: Calibration Plot, Intercept Adjustment, and Model-based ROC.

text2sdg v0.1.1: Provides functions to identify Sustainable Development Goals in text using scientifically developed query systems, opening up the opportunity to monitor any type of text-based data, such as scientific output or corporate publications. There is a vignette.

Twitmo v0.1.1: Provides functions to collect, pre-process and analyze the contents of tweets using LDA and STM models including functions to generate tweet and hashtag maps and built-in support for LDAvis. See README for examples.

Medicine

ctrialsgov v0.2.5: Provides tools to access and query the U.S. National Library of Medicine’s Clinical Trials database including functions for searching the data using range queries, categorical filtering, and by searching for full-text keywords. There is an Introduction and a vignette on Text Analysis.

epidemia v1.0.0: Implements functions to specify and fit Bayesian statistical models for epidemics. Infections are propagated over time using self-exciting point processes. Multiple regions can be modeled simultaneously with multilevel models. See Bhatt et al. (2021) for background on the models and the package website for examples and extensive documentation.

Networks

dissCqN v0.1.0: Provides functions to calculate multiple or pairwise dissimilarity for orders q = 0-N for a set of species assemblages or interaction networks. See Chao et al. 2008 for background and the vignette for an example.

modnets v0.9.0: Implements methods for modeling moderator variables in cross-sectional, temporal, and multi-level networks including model selection techniques and a variety of plotting functions. See Swanson (2020) for details and the README for an example.

Science

cmpsR v0.1.0: Implements the Congruent Matching Profile Segments (CMPS) method Chen et al. (2019) to provide an objective comparison of striated tool marks for fired bullet correlation. See the vignette.

pvcurveanalysis v1.0.0: Provides functions to analyze and display pressure volume curves which enable the derivation of the turgor loss point, osmotic potential and apoplastic fraction. See Bartlett et al. (2012) for background and the vignette for examples.

Social Science

rcbayes v0.1.0: Provides functions to estimate Rogers-Castro migration age schedules using Stan. See Rogers and Castro (1978) for background and the vignettes on Model Convergence and Rogers Castro Migration Models.

QCAcluster v0.1.0: Provides functions to allow Qualitative Comparative Analysis researchers to supplement the analysis of pooled data with a disaggregated perspective focusing on selected partitions of the data. The pooled data can be partitioned along the dimensions of the clustered data (individual cross sections or time series) to perform partition-specific truth table minimizations. There are vignettes that discuss the Aggregation, Diversity, Miimization, and Weight of partitions.

Statistics

bayesPO v0.3.1: Provides functions to create Bayesian point process models of presence only data. See Moreira (2020) for background, and the vignette for examples.

hierbase v0.1.2: Implements the algorithms for hierarchical testing of variable importance described in Meinshausen (2008) which control for family-wise error rate. See the vignette for an example.

pedmod v0.1.0: Provides functions to estimate mixed probit models, commonly called liability threshold models, for pedigree data such as that studied in Pawitan et al. (2004). See Genz & Bretz (2012) for background. There is an introduction to pedigree models and a vignette on positioning families.

slasso v1.0.0: Implements the smooth LASSO estimator for the function-on-function linear regression model described in Centofanti et al. (2020). See README for examples.

StanMoMo v1.0.0: Implements Bayesian mortality models including those developed in Lee & Carter (1992) and Cairns, Blake & Dowd (2006). There is a vignette introducing the Lee & Carter model and another on Bayesian Model Averaging.

Time Series

esemifar v1.0.1: Implements algorithms that provide non-parametric estimates of trend and its derivatives in equidistant time series with long-memory errors. See Letmathe et al. (2021) for a description of the smoothing methods employed, and README for an example.

GDPuc v0.5.1: Provides a function to convert GDP time series from one unit to another. All common GDP units are included, i.e. current and constant local currency units, US$ via market exchange rates and international dollars via purchasing power parities. See README for examples.

Utilities

framecleaner v0.2.0: Provides a friendly interface for modifying data frames with a sequence of piped commands built upon the tidyverse. See the vignette for examples.

presentr v0.1.1: Implements wrapper functions using packages openxlsx, flextable, and officer to create highly formatted MS office friendly output of data frames. Vignettes include: exportToExcel, flextableAndPowerpoint, and formattedFlextable.

shinyGovstyle v0.0.7: Implements a collection of shiny application styling tools that are the based on the GOV.UK Design System. See README for an introduction and examples.

validata v0.1.0: Provides functions for validating the structure and properties of data frames helping users to answer essential questions about a data set such as: What are the unique or missing values? and What columns form a primary key?. See the vignette for an introduction.

Visualization

easylabel v0.2.4: Implements interactive labeling of scatter plots, volcano plots and Manhattan plots using a shiny or plotly interface. Users can hover over points to see where specific points are located and click points on/off to easily label them. See the vignette for examples.

ggokabeito v0.1.0: Provides discrete scales for the colorblind-friendly Okabe-Ito palette, including color, fill, and edge_colour. See README for examples.

metaconfoundr v0.1.0: Implements an approach for evaluating bias in meta-analysis studies based on the causal inference framework. See the vignette for examples.

scatterPlotMatrix v0.1.0: Provides functions which make use of the packages htmlwidgets package and d3.js to create scatter plot matrices. See the vignette.