{ "_id": "6a1029f0acfb0bcc41c91abb", "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": "2026-05-13 07:13:55 UTC", "User": "root" }, "Author": "Keenan Ganz [aut, cre]", "MD5sum": "3926830af513741fa7a5262631397584", "_user": "s-kganz", "_type": "src", "_file": "scutr_0.2.0.tar.gz", "_fileid": "41b3ec913109bc652e2ba15d46ad09aec6be39710f59870b5f8e130fb91ac051", "_filesize": 323263, "_sha256": "41b3ec913109bc652e2ba15d46ad09aec6be39710f59870b5f8e130fb91ac051", "_created": "2026-05-13T07:13:55.000Z", "_published": "2026-05-22T10:03:28.868Z", "_distro": "noble", "_jobs": [ { "job": 77358025847, "time": 136, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "6963847534" }, { "job": 77358025991, "time": 139, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "6963848647" }, { "job": 77358026215, "time": 235, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "6963915284" }, { "job": 77358026218, "time": 174, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "6963903972" }, { "job": 77358025609, "time": 182, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "6963805426" }, { "job": 77358025387, "time": 118, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7157899627" }, { "job": 77358026289, "time": 93, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "6963833522" }, { "job": 77358026421, "time": 91, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "6963832722" }, { "job": 77358026430, "time": 89, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "6963832184" } ], "_buildurl": "https://github.com/r-universe/s-kganz/actions/runs/25784136423", "_status": "success", "_host": "GitHub-Actions", "_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", "uuid": 38630604 }, "_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", "description": "PhD Student @ Remote Sensing and Geospatial Analysis Laboratory, UW Seattle" }, "_downloads": { "count": 231, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/scutr" }, "_devurl": "https://github.com/s-kganz/scutr", "_searchresults": 55, "_rbuild": "4.6.0", "_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", "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": "2026-05-13T07:16:02.000Z", "distro": "noble", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "c531943286508960d21f4005a472cdecaac98c56f1da93bc6b32ecfa4cc60994", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/25784136423" }, { "r": "4.6.0", "os": "linux", "version": "0.2.0", "date": "2026-05-13T07:16:06.000Z", "distro": "noble", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "f0c32820f9168562dffe5b7762fc632870cc1d95271bb1f62ed0d9b3d8414bdf", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/25784136423" }, { "r": "4.5.3", "os": "mac", "version": "0.2.0", "date": "2026-05-13T07:19:53.000Z", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "59167bb9a5cc868a98d9b20346a20ff7ad2bdee8042e88372345831b22f4c793", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/25784136423" }, { "r": "4.6.0", "os": "mac", "version": "0.2.0", "date": "2026-05-13T07:19:17.000Z", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "828eb58480e41baa322efecac18cdf0aac305bdd99b29d460195169d5ada8dc2", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/25784136423" }, { "r": "4.7.0", "os": "win", "version": "0.2.0", "date": "2026-05-13T07:15:09.000Z", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "15d75b8b36ac701fde8847e7753f8826adda0991dee42afcea6b2870b73143a4", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/25784136423" }, { "r": "4.5.3", "os": "win", "version": "0.2.0", "date": "2026-05-13T07:15:06.000Z", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "843f48b9b09f8f48385761b1b7d7fef703dd8c1f60f8f1518429e108f6d0b9a4", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/25784136423" }, { "r": "4.6.0", "os": "win", "version": "0.2.0", "date": "2026-05-13T07:15:04.000Z", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "91b2182ab1d29381e43ff363b5d9b0e484fbcdc8a45104083eb75d7d5192a130", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/25784136423" }, { "r": "4.6.0", "os": "wasm", "version": "0.2.0", "date": "2026-05-22T10:03:10.000Z", "commit": "624f415cd45406d862f335028b41cc153861d279", "fileid": "99fa51aa162dfdaba54b344073590cd7b170289bf867ee20fb5bf05ed81546d6", "status": "success", "buildurl": "https://github.com/r-universe/s-kganz/actions/runs/25784136423" } ] }