Scelestial infers a lineage tree from single-cell DNA mutation matrix. It generates a tree with approximately maximum parsimony through a Steiner tree approximation algorithm.

Recursive partitioning for least absolute deviation regression trees. Another algorithm from the 1984 book by Breiman, Friedman, Olshen and Stone in addition to the rpart package (Breiman, Friedman, Olshen, Stone (1984, ISBN:9780412048418).

This package provides a series of functions in some way considered useful to the author. These include methods for subsetting tables and generating indices for arrays, conditioning and intervening in probability distributions, generating combinations, fast transformations, and more...

Ensemble model, for classification, regression and unsupervised learning, based on a forest of unpruned and randomized binary decision trees. Each tree is grown by sampling, with replacement, a set of variables at each node. Each cut-point is generated randomly, according to the continuous Uniform distribution. For each tree, data are either bootstrapped or subsampled. The unsupervised mode introduces clustering, dimension reduction and variable importance, using a three-layer engine. Random Uniform Forests are mainly aimed to lower correlation between trees (or trees residuals), to provide a deep analysis of variable importance and to allow native distributed and incremental learning.

Calculate rarefaction-based alpha- and beta-diversity. Offer parametric extrapolation to estimate the total expected species in a single community and the total expected shared species between two communities. Visualize the curve-fitting for these estimators.

Ensmallen is a templated C++ mathematical optimization library (by the MLPACK team) that provides a simple set of abstractions for writing an objective function to optimize. Provided within are various standard and cutting-edge optimizers that include full-batch gradient descent techniques, small-batch techniques, gradient-free optimizers, and constrained optimization. The RcppEnsmallen package includes the header files from the Ensmallen library and pairs the appropriate header files from armadillo through the RcppArmadillo package. Therefore, users do not need to install Ensmallen nor Armadillo to use RcppEnsmallen'. Note that Ensmallen is licensed under 3-Clause BSD, Armadillo starting from 7.800.0 is licensed under Apache License 2, RcppArmadillo (the Rcpp bindings/bridge to Armadillo') is licensed under the GNU GPL version 2 or later. Thus, RcppEnsmallen is also licensed under similar terms. Note that Ensmallen requires a compiler that supports C++14 and Armadillo 10.8.2 or later.

Read the data from Origin(R) project files ('*.opj') <https://www.originlab.com/doc/User-Guide/Origin-File-Types>. No write support is planned.

Connects dataframes/tables with a remote data source. Raw data downloaded from the data source can be further processed and transformed using data preparation code that is also baked into the dataframe/table. Refreshable dataframes can be shared easily (e.g. as R data files). Their users do not need to care about the inner workings of the data update mechanisms.

Regularized calibrated estimation for causal inference and missing-data problems with high-dimensional data, based on Tan (2020a) <doi:10.1093/biomet/asz059>, Tan (2020b) <doi:10.1214/19-AOS1824> and Sun and Tan (2020) <arXiv:2009.09286>.

The RMM fits Revenue Management Models using the RDE(Robust Demand Estimation) method introduced in the paper by <doi:10.2139/ssrn.3598259>, one of the customer choice-based Revenue Management Model. Furthermore, it is possible to select a multinomial model as well as a conditional logit model as a model of RDE.

Population genetic data such as Single Nucleotide Polymorphisms (SNPs) is often used to identify genomic regions that have been under recent natural or artificial selection and might provide clues about the molecular mechanisms of adaptation. One approach, the concept of an Extended Haplotype Homozygosity (EHH), introduced by (Sabeti 2002) <doi:10.1038/nature01140>, has given rise to several statistics designed for whole genome scans. The package provides functions to compute three of these, namely: iHS (Voight 2006) <doi:10.1371/journal.pbio.0040072> for detecting positive or Darwinian selection within a single population as well as Rsb (Tang 2007) <doi:10.1371/journal.pbio.0050171> and XP-EHH (Sabeti 2007) <doi:10.1038/nature06250>, targeted at differential selection between two populations. Various plotting functions are included to facilitate visualization and interpretation of these statistics.

We generate random variables following general Marchenko-Pastur distribution and Tracy-Widom distribution. We compute limits and distributions of eigenvalues and generalized components of spiked covariance matrices. We give estimation of all population eigenvalues of spiked covariance matrix model. We give tests of population covariance matrix. We also perform matrix denoising for signal-plus-noise model.

The SPRITE algorithm creates possible distributions of discrete responses based on reported sample parameters, such as mean, standard deviation and range (Heathers et al., 2018, <doi:10.7287/peerj.preprints.26968v1>). This package implements it, drawing heavily on the code for Nick Brown's rSPRITE Shiny app <https://shiny.ieis.tue.nl/sprite/>. In addition, it supports the modeling of distributions based on multi-item (Likert-type) scales and the use of restrictions on the frequency of particular responses.

Provide a simple interface to Bloomberg's OpenFIGI API. Please see <https://openfigi.com> for API details and registration. You may be eligible to have an API key to accelerate your loading process.

This package provides an Rcmdr "plug-in" based on the TeachingDemos package, and is primarily for illustrative purposes.

Automated performance of common transformations used to fulfill parametric assumptions of normality and identification of the best performing method for the user. Output for various normality tests (Thode, 2002) corresponding to the best performing method and a descriptive statistical report of the input data in its original units (5-number summary and mathematical moments) are also presented. Lastly, the Rankit, an empirical normal quantile transformation (ENQT) (Soloman & Sawilowsky, 2009), is provided to accommodate non-standard use cases and facilitate adoption. <DOI: 10.1201/9780203910894>. <DOI: 10.22237/jmasm/1257034080>.

Calculate the flow of particles between polygons by two integration methods: integration by a cubature method and integration on a grid of points. Annie Bouvier, Kien Kieu, Kasia Adamczyk and Herve Monod (2009) <doi:10.1016/j.envsoft.2008.11.006>.

This package provides methods to easily build requests in the non-standard JSON schema required by the National Institute of Health (NIH)'s RePORTER Project API <https://api.reporter.nih.gov/#/Search/post_v2_projects_search>. Also retrieve and process result sets as either a ragged or flattened tibble'.

Weave and tangle drivers for Sweave extending the standard drivers. RweaveExtraLatex and RtangleExtra provide options to completely ignore code chunks on weaving, tangling, or both. Chunks ignored on weaving are not parsed, yet are written out verbatim on tangling. Chunks ignored on tangling may be evaluated as usual on weaving, but are completely left out of the tangled scripts. The driver RtangleExtra also provides options to control the separation between code chunks in the tangled script, and to specify the extension of the file name (or remove it entirely) when splitting is selected.

The renewal Hawkes (RHawkes) process (Wheatley, Filimonov, and Sornette, 2016 <doi:10.1016/j.csda.2015.08.007>) is an extension to the classical Hawkes self-exciting point process widely used in the modelling of clustered event sequence data. This package provides functions to simulate the RHawkes process with a given immigrant hazard rate function and offspring birth time density function, to compute the exact likelihood of a RHawkes process using the recursive algorithm proposed by Chen and Stindl (2018) <doi:10.1080/10618600.2017.1341324>, to compute the Rosenblatt residuals for goodness-of-fit assessment, and to predict future event times based on observed event times up to a given time. A function implementing the linear time RHawkes process likelihood approximation algorithm proposed in Stindl and Chen (2021) <doi:10.1007/s11222-021-10002-0> is also included.

Visualize your favorite XKCD comic strip directly from R. XKCD <https://xkcd.com> web comic content is provided under the Creative Commons Attribution-NonCommercial 2.5 License.

Allow for easy-to-use testing or evaluating of linear equality and inequality restrictions about parameters and effects in (generalized) linear statistical models.

The Linear Programming via Regularized Least Squares (LPPinv) is a two-stage estimation method that reformulates linear programs as structured least-squares problems. Based on the Convex Least Squares Programming (CLSP) framework, LPPinv solves linear inequality, equality, and bound constraints by (1) constructing a canonical constraint system and computing a pseudoinverse projection, followed by (2) a convex-programming correction stage to refine the solution under additional regularization (e.g., Lasso, Ridge, or Elastic Net). LPPinv is intended for underdetermined and ill-posed linear problems, for which standard solvers fail.

This package provides a collection of tools for measuring the similarity of text messages and tracing the flow of messages over time and across media.