{"id":18085647,"url":"https://github.com/aebilgrau/correlater","last_synced_at":"2025-04-12T22:07:39.881Z","repository":{"id":18885130,"uuid":"22102775","full_name":"AEBilgrau/correlateR","owner":"AEBilgrau","description":"General purpose correlation and covariance estimation","archived":false,"fork":false,"pushed_at":"2023-11-02T20:31:16.000Z","size":233,"stargazers_count":6,"open_issues_count":1,"forks_count":2,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-12T22:07:06.147Z","etag":null,"topics":["covariance","covariance-estimation","cross-correlation","cross-covariance","partial-correlations","r"],"latest_commit_sha":null,"homepage":"","language":"R","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AEBilgrau.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2014-07-22T12:19:17.000Z","updated_at":"2023-11-02T20:31:03.000Z","dependencies_parsed_at":"2024-10-31T16:00:37.476Z","dependency_job_id":"a4d2ffb7-3bff-4452-8d75-c9a41edcd71b","html_url":"https://github.com/AEBilgrau/correlateR","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AEBilgrau%2FcorrelateR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AEBilgrau%2FcorrelateR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AEBilgrau%2FcorrelateR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AEBilgrau%2FcorrelateR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AEBilgrau","download_url":"https://codeload.github.com/AEBilgrau/correlateR/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248637769,"owners_count":21137538,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["covariance","covariance-estimation","cross-correlation","cross-covariance","partial-correlations","r"],"created_at":"2024-10-31T16:00:19.592Z","updated_at":"2025-04-12T22:07:39.859Z","avatar_url":"https://github.com/AEBilgrau.png","language":"R","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![Build Status](https://api.travis-ci.org/AEBilgrau/correlateR.svg?branch=master)](https://travis-ci.org/AEBilgrau/correlateR)\n[![Coverage status](https://coveralls.io/repos/github/AEBilgrau/correlateR/badge.svg)](https://coveralls.io/r/AEBilgrau/correlateR?branch=master)\n![Maintained](https://img.shields.io/maintenance/no/2019.svg)\n\n\ncorrelateR\n==========\n#### General purpose correlation and covariance estimation\n\nThe R-package `correlateR` is planned to be a comprehensive resource of\nfunctions related to correlations and covariances. It features fast, robust, and\nefficient (as well as inefficient) marginal, partial, semi-partial correlations\nand covariances of arbitrary conditional order. A good discussion and\nexplanation of marginal (unconditioned), partial, and semi-partial (or, part)\ncorrelations can be found\n[here.](https://web.archive.org/web/20140206182503/http://luna.cas.usf.edu/~mbrannic/files/regression/Partial.html)\nAnother good resource is found\n[here.](http://www.johndcook.com/blog/2008/11/05/how-to-calculate-pearson-correlation-accurately/)\n\nThe package is designed to perform well in both high and low dimensional cases\nas well as both on dense and sparse matrices.\n\nThe package is not being actively developed as of 2019. I might pick it up again in\nthe future if there is a need.\n\nInstallation\n------------\nIf you wish to install the latest version of `correlateR` directly from the master branch here at GitHub, run \n\n```R\n#install.packages(\"devtools\")  # Uncomment if devtools is not installed\ndevtools::install_github(\"AEBilgrau/correlateR\")\n```\n\nThe package is still under heavy development and should be considered unstable. Be sure that you have the [package development prerequisites](http://www.rstudio.com/ide/docs/packages/prerequisites) if you wish to install the package from the source.\n\n**NOTE** The interface and function names may still see significant changes and\nmodifications!\n\nFeatures\n--------\nCurrently, the packages is planned to feature:\n\n - [x] `cor`/`cov` Marginal (unconditional) correlation/covariance. These basic \n       functions can be prefixed to yield other correlation/covariance \n       estimates. This covariance is also known as the auto-correlation, the \n       variance-covariance, or simply the variance (in the generalized sense).\n    - [x] `p`-prefix: partial (arbitrary order) correlation and covariance.\n    - [x] `x`-prefix: cross correlation and covariance.\n    - [ ] `P`-prefix: Part (semi-partial) correlation and covariances\n    - [ ] `s`-prefix: sparse shrinkage estimation methods\n    - [ ] `r`-prefix: robust estimation methods. E.g. Minimum covariance \n          determinant, Robust midweight correlation, etc\n    - [x] `S`-prefix: Shrinkage estimation. (Or, `d` for dense shrinkage?) \n - [ ] Interface using formulas `~`.\n - [ ] Conversion between `cov` and `cor` and `pcor` functions.\n    - [ ] `cov2cor` `cor2cov` `cor2pcor` `pcor2cor`\n - [ ] Conditional and unconditional independence test\n    - [ ] `cor.text` `pcor.test` `xcor.test` `pxcor.test`\n    - [ ] Also with cross, sparse, shrinked, robust, etc., versions\n - [ ] Canonical correlation analysis (CCA)\n    - [ ] Also with cross, sparse, shrinked, robust, etc., versions\n - [ ] `pre` (alternative to `cov`) direct estimation of the precision matrix\n       or concentration matrix.\n    - [ ]  Also with cross, sparse, robust, etc., versions\n - [ ] ... and more! (??)\n \nHence the following core-functons are available:\n - [x] `xcor` Cross-correlation\n - [x] `xcov` Cross-covariance\n - [x] `pcor` Partial correlation (arbitrary order)\n - [x] `pcov` Partial covariance (arbitrary order)\n - [x] `pxcor` Partial cross-correlation (arbitrary order)\n - [x] `pxcov` Partial cross-covariance (arbitrary order)\n - [ ] `scor` Sparse correlation\n - [ ] `scov` Sparse covariance\n - [ ] `sxcor` Sparse cross-correlation\n - [ ] `sxcov` Sparse cross-covariance\n - [ ] `spcor` Sparse partial correlation (arbitrary order)\n - [ ] `spcov` Sparse partial covariance (arbitrary order)\n - [ ] `spxcor` Sparse partial cross-correlation (arbitrary order)\n - [ ] `spxcov` Sparse partial cross-covariance (arbitrary order)\n\n\n## Naming conventions and interface\nTo easily navigate the package some naming conventions has been decided upon.\n\nLower-case `x`, `y`, `z` always denotes `numeric` vectors while the upper-case counterparts `X`, `Y`, or `Z` denote a `numeric` `matrix` where observations correspond to rows and variables/feature to columns. The `Z` and `z` always express the variables conditioned on. Furthermore, `S` is used to denote the empirical (marginal) covariance matrix.\n\nFunction names are in camelCase except for some special cases. Otherwise `cor` is for correlation `cov` is for covariance. These are prefixed with `x` or `p` (or both) to denote cross or partial correlations/covariance respectively. For example, `pcor` is the partial correlation and `pxcov` is the partial cross covariance. \n\n\nAlternative packages\n--------------------\nThere are some alternative packages on CRAN form which some inspiration have been drawn. \n* `corpcor`: Only features estimation of the full partial correlations.\n* `ppcor`: Partial and semi-partial correlations\n\n--------------------------------------------------------------------------------\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faebilgrau%2Fcorrelater","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faebilgrau%2Fcorrelater","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faebilgrau%2Fcorrelater/lists"}