{ "_id": "6a5343749b92047c28d5741c", "Package": "scutr", "Title": "Balancing Multiclass Datasets for Classification Tasks", "Version": "0.2.0", "Authors@R": "person(given = \"Keenan\",\nfamily = \"Ganz\",\nrole = c(\"aut\", \"cre\"),\nemail = \"ganzkeenan1@gmail.com\")", "Maintainer": "Keenan Ganz ", "Description": "Imbalanced training datasets impede many popular\nclassifiers. To balance training data, a combination of\noversampling minority classes and undersampling majority\nclasses is useful. This package implements the SCUT (SMOTE and\nCluster-based Undersampling Technique) algorithm as described\nin Agrawal et. al. (2015) . Their\npaper uses model-based clustering and synthetic oversampling to\nbalance multiclass training datasets, although other resampling\nmethods are provided in this package.", "License": "MIT + file LICENSE", "Encoding": "UTF-8", "LazyData": "true", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.2.3", "URL": "https://github.com/s-kganz/scutr", "BugReports": "https://github.com/s-kganz/scutr/issues", "Config/testthat/edition": "2", "Config/pak/sysreqs": "libglpk-dev libxml2-dev", "Repository": "https://s-kganz.r-universe.dev", "Date/Publication": "2023-11-18 18:34:36 UTC", "RemoteUrl": "https://github.com/s-kganz/scutr", "RemoteRef": "HEAD", "RemoteSha": "624f415cd45406d862f335028b41cc153861d279", "NeedsCompilation": "no", "Packaged": { "Date": "2026-07-12 07:30:15 UTC", "User": "root" }, "Author": "Keenan Ganz [aut, cre]", "_user": "s-kganz", "_type": "src", "_file": "scutr_0.2.0.tar.gz", "_fileid": "https://r2.ropensci.org/8c291f96546e231d6896b72af84db9106106629dab698994a34435161ae6c537", "_filesize": 324176, "_sha256": "8c291f96546e231d6896b72af84db9106106629dab698994a34435161ae6c537", "_expires": "2026-10-20T07:34:08.000Z", "_created": "2026-07-12T07:30:15.000Z", "_published": "2026-07-12T07:34:10.295Z", "_jobs": [ { "job": 86627649290, "time": 147, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8257504950" }, { "job": 86627649287, "time": 143, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8257504309" }, { "job": 86627649282, "time": 197, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "8257507549" }, { "job": 86627649284, "time": 193, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8257505787" }, { "job": 86627438777, "time": 175, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8257481908" }, { "job": 86627649274, "time": 102, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8257497760" }, { "job": 86627649302, "time": 100, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "8257497802" }, { "job": 86627649304, "time": 102, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "8257498173" }, { "job": 86627649318, "time": 89, "config": "windows-release", "r": "4.6.1", "check": "OK", "artifact": "8257495641" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/s-kganz/actions/runs/29184260959", "_status": "success", "_upstream": "https://github.com/s-kganz/scutr", "_commit": { "id": "624f415cd45406d862f335028b41cc153861d279", "author": "Keenan Ganz <38630604+s-kganz@users.noreply.github.com>", "committer": "GitHub ", "message": "Merge pull request #2 from s-kganz/cran-release\n\nSubmit v0.2.0 to cran", "time": 1700332476 }, "_maintainer": { "name": "Keenan Ganz", "email": "ganzkeenan1@gmail.com", "login": "s-kganz", "description": "PhD Student @ Remote Sensing and Geospatial Analysis Laboratory, UW Seattle", "uuid": 38630604 }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 2.10", "role": "Depends" }, { "package": "smotefamily", "role": "Imports" }, { "package": "parallel", "role": "Imports" }, { "package": "mclust", "role": "Imports" }, { "package": "testthat", "version": ">= 2.0.0", "role": "Suggests" } ], "_owner": "s-kganz", "_selfowned": true, "_usedby": 1, "_updates": [], "_tags": [], "_stars": 2, "_contributors": [ { "user": "s-kganz", "count": 91, "uuid": 38630604 } ], "_userbio": { "uuid": 38630604, "type": "user", "name": "Keenan Ganz", "followers": 12, "description": "PhD Student @ Remote Sensing and Geospatial Analysis Laboratory, UW Seattle" }, "_downloads": { "count": 284, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/scutr" }, "_devurl": "https://github.com/s-kganz/scutr", "_searchresults": 55, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "extra/scutr.html", "LICENSE", "manual.pdf" ], "_homeurl": "https://github.com/s-kganz/scutr", "_realowner": "s-kganz", "_cranurl": true, "_releases": [ { "version": "0.1.2", "date": "2021-06-24" }, { "version": "0.2.0", "date": "2023-11-18" } ], "_exports": [ "oversample_smote", "resample_random", "sample_classes", "SCUT", "SCUT_parallel", "undersample_hclust", "undersample_kmeans", "undersample_mclust", "undersample_mindist", "undersample_tomek" ], "_datasets": [ { "name": "bullseye", "title": "An imbalanced dataset with a minor class centered around the origin with a majority class surrounding the center.", "object": "bullseye", "class": [ "data.frame" ], "fields": [ "x", "y", "minor" ], "rows": 1000, "table": true, "tojson": true }, { "name": "imbalance", "title": "An imbalanced dataset with randomly placed normal distributions around the origin. The nth class has n * 10 observations.", "object": "imbalance", "class": [ "data.frame" ], "fields": [ "V1", "V2", "V3", "V4", "V5", "V6", "V7", "V8", "V9", "V10", "class" ], "rows": 2100, "table": true, "tojson": true }, { "name": "wine", "title": "Type and chemical analysis of three different kinds of wine.", "object": "wine", "class": [ "data.frame" ], "fields": [ "type", "x1", "x2", "x3", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13" ], "rows": 178, "table": true, "tojson": true } ], "_help": [ { "page": "bullseye", "title": "An imbalanced dataset with a minor class centered around the origin with a majority class surrounding the center.", "topics": [ "bullseye" ] }, { "page": "imbalance", "title": "An imbalanced dataset with randomly placed normal distributions around the origin. The nth class has n * 10 observations.", "topics": [ "imbalance" ] }, { "page": "oversample_smote", "title": "Oversample a dataset by SMOTE.", "topics": [ "oversample_smote" ] }, { "page": "resample_random", "title": "Randomly resample a dataset.", "topics": [ "resample_random" ] }, { "page": "sample_classes", "title": "Stratified index sample of different values in a vector.", "topics": [ "sample_classes" ] }, { "page": "SCUT", "title": "SMOTE and cluster-based undersampling technique.", "topics": [ "SCUT", "SCUT_parallel" ] }, { "page": "undersample_hclust", "title": "Undersample a dataset by hierarchical clustering.", "topics": [ "undersample_hclust" ] }, { "page": "undersample_kmeans", "title": "Undersample a dataset by kmeans clustering.", "topics": [ "undersample_kmeans" ] }, { "page": "undersample_mclust", "title": "Undersample a dataset by expectation-maximization clustering", "topics": [ "undersample_mclust" ] }, { "page": "undersample_mindist", "title": "Undersample a dataset by iteratively removing the observation with the lowest total distance to its neighbors of the same class.", "topics": [ "undersample_mindist" ] }, { "page": "undersample_tomek", "title": "Undersample a dataset by removing Tomek links.", "topics": [ "undersample_tomek" ] }, { "page": "validate_dataset", "title": "Validate a dataset for resampling.", "topics": [ "validate_dataset" ] }, { "page": "wine", "title": "Type and chemical analysis of three different kinds of wine.", "topics": [ "wine" ] } ], "_readme": "https://github.com/s-kganz/scutr/raw/HEAD/README.md", "_rundeps": [ "cli", "cpp11", "dbscan", "FNN", "generics", "glue", "igraph", "lattice", "lifecycle", "magrittr", "Matrix", "mclust", "pkgconfig", "Rcpp", "rlang", "smotefamily", "vctrs" ], "_score": 4.217483944213907, "_indexed": true, "_nocasepkg": "scutr", "_universes": [ "s-kganz" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.2.0", "date": "2026-07-12T07:32:23.000Z", "distro": "resolute", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "https://r2.ropensci.org/96510adc2dac9cb5f2487de99d37288a61d5621af305e44693205b55c7893b02", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/29184260959" }, { "r": "4.6.1", "os": "linux", "version": "0.2.0", "date": "2026-07-12T07:32:20.000Z", "distro": "resolute", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "https://r2.ropensci.org/626c2953f68c972eca75f1bb1ddaab64bf050ab409142a44cb0f5fe3c4f44c21", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/29184260959" }, { "r": "4.5.3", "os": "mac", "version": "0.2.0", "date": "2026-07-12T07:32:46.000Z", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "https://r2.ropensci.org/ffcc81ba0d5bcd8cbb9653839fe156aaeaa3d394f30c7bbb607070b56109c459", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/29184260959" }, { "r": "4.6.1", "os": "mac", "version": "0.2.0", "date": "2026-07-12T07:32:18.000Z", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "https://r2.ropensci.org/2309c007d0a9a8c6b6739355ea6a754597007518b4ed522efdd50c8cb60b44c8", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/29184260959" }, { "r": "4.6.0", "os": "wasm", "version": "0.2.0", "date": "2026-07-12T07:32:10.000Z", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "https://r2.ropensci.org/c501385682fc865c262176ea5de1983069315f10e54970493611a085e7b5a0fd", "status": "success", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/29184260959" }, { "r": "4.7.0", "os": "win", "version": "0.2.0", "date": "2026-07-12T07:31:31.000Z", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "https://r2.ropensci.org/0fd9fd26e472399f5c3aa88cdd847365897da6c5275678590444ffcf1833f06f", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/29184260959" }, { "r": "4.5.3", "os": "win", "version": "0.2.0", "date": "2026-07-12T07:31:33.000Z", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "https://r2.ropensci.org/65f7e28e2c7544b1fdc0431dd8193c81cccf6177418186d168f53eadcc81ace0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/29184260959" }, { "r": "4.6.1", "os": "win", "version": "0.2.0", "date": "2026-07-12T07:31:20.000Z", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "https://r2.ropensci.org/902497a305e89b8c87ab43957ec0ee57f5f9456705b83da89669ecfaabf02996", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/29184260959" } ] }