{ "_id": "6ab3baa13d719c1f84093188", "Package": "themis", "Title": "Extra Recipes Steps for Dealing with Unbalanced Data", "Version": "1.1.0.9000", "Authors@R": "c(\nperson(\"Emil\", \"Hvitfeldt\", , \"emil.hvitfeldt@posit.co\", role = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0002-0679-1945\")),\nperson(\"Posit Software, PBC\", role = c(\"cph\", \"fnd\"),\ncomment = c(ROR = \"03wc8by49\"))\n)", "Description": "A dataset with an uneven number of cases in each class is\nsaid to be unbalanced. Many models produce a subpar performance\non unbalanced datasets. A dataset can be balanced by increasing\nthe number of minority cases using SMOTE 2011\n, BorderlineSMOTE 2005\n and ADASYN 2008. Or by decreasing the\nnumber of majority cases using NearMiss 2003\n or\nTomek link removal 1976.", "License": "MIT + file LICENSE", "URL": "https://github.com/tidymodels/themis,\nhttps://themis.tidymodels.org", "BugReports": "https://github.com/tidymodels/themis/issues", "Config/Needs/website": "tidyverse/tidytemplate", "Config/testthat/edition": "3", "Config/usethis/last-upkeep": "2025-04-24", "Encoding": "UTF-8", "LazyData": "true", "Roxygen": "list(markdown = TRUE)", "Config/roxygen2/version": "8.0.0", "Config/pak/sysreqs": "libicu-dev", "Repository": "https://tidymodels.r-universe.dev", "Date/Publication": "2026-08-20 19:56:39 UTC", "RemoteUrl": "https://github.com/tidymodels/themis", "RemoteRef": "HEAD", "RemoteSha": "762e11fccde6bffbbf823f1609f00a1846f695d5", "NeedsCompilation": "no", "Packaged": { "Date": "2026-09-23 11:34:55 UTC", "User": "root" }, "Author": "Emil Hvitfeldt [aut, cre] (ORCID:\n),\nPosit Software, PBC [cph, fnd] (ROR: )", "Maintainer": "Emil Hvitfeldt ", "_user": "tidymodels", "_type": "src", "_file": "themis_1.1.0.9000.tar.gz", "_fileid": "https://r2.ropensci.org/1290ed4c8630ed03d36c4094be646186468ced110d74293b868b1ac766fdbd79", "_filesize": 638565, "_sha256": "1290ed4c8630ed03d36c4094be646186468ced110d74293b868b1ac766fdbd79", "_expires": "2027-01-01T11:40:15.000Z", "_created": "2026-09-23T11:34:55.000Z", "_published": "2026-09-23T11:40:17.437Z", "_jobs": [ { "job": 107162589512, "time": 268, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "10747810569" }, { "job": 107162589453, "time": 278, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "10747681539" }, { "job": 107162589440, "time": 191, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "10747471011" }, { "job": 107162589384, "time": 220, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "10747875489" }, { "job": 107161167768, "time": 267, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "10747510410" }, { "job": 107162589403, "time": 128, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "10746599151" }, { "job": 107162589481, "time": 177, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "10747430997" }, { "job": 107162589508, "time": 208, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "10747975040" }, { "job": 107162589602, "time": 205, "config": "windows-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "10747710529" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/tidymodels/actions/runs/35854931237", "_status": "success", "_upstream": "https://github.com/tidymodels/themis", "_commit": { "id": "762e11fccde6bffbbf823f1609f00a1846f695d5", "author": "Emil Hvitfeldt ", "committer": "GitHub ", "message": "Add tidy-add-step-argument skill (#346)", "time": 1787255799 }, "_maintainer": { "name": "Emil Hvitfeldt", "email": "emil.hvitfeldt@posit.co", "login": "emilhvitfeldt", "bluesky": "@emilhvitfeldt.bsky.social", "description": "All things @tidymodels", "uuid": 14034784, "orcid": "0000-0002-0679-1945" }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.1", "role": "Depends" }, { "package": "recipes", "version": ">= 1.1.0", "role": "Depends" }, { "package": "cli", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "generics", "version": ">= 0.1.0", "role": "Imports" }, { "package": "glue", "role": "Imports" }, { "package": "gower", "role": "Imports" }, { "package": "hardhat", "role": "Imports" }, { "package": "lifecycle", "version": ">= 1.0.3", "role": "Imports" }, { "package": "purrr", "role": "Imports" }, { "package": "RANN", "role": "Imports" }, { "package": "rlang", "version": ">= 1.1.0", "role": "Imports" }, { "package": "ROSE", "role": "Imports" }, { "package": "tibble", "role": "Imports" }, { "package": "vctrs", "role": "Imports" }, { "package": "withr", "role": "Imports" }, { "package": "covr", "role": "Suggests" }, { "package": "dials", "version": ">= 1.2.0", "role": "Suggests" }, { "package": "ggplot2", "role": "Suggests" }, { "package": "kernlab", "role": "Suggests" }, { "package": "modeldata", "role": "Suggests" }, { "package": "philentropy", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" } ], "_owner": "tidymodels", "_selfowned": true, "_usedby": 2, "_updates": [ { "week": "2026-04", "n": 1 }, { "week": "2026-14", "n": 8 }, { "week": "2026-15", "n": 18 }, { "week": "2026-29", "n": 12 }, { "week": "2026-30", "n": 37 }, { "week": "2026-31", "n": 18 }, { "week": "2026-34", "n": 1 } ], "_tags": [ { "name": "v1.1.0", "date": "2026-08-01" } ], "_stars": 143, "_contributors": [ { "user": "emilhvitfeldt", "count": 556, "uuid": 14034784 }, { "user": "robertgregg", "count": 12, "uuid": 44711193 }, { "user": "topepo", "count": 7, "uuid": 5731043 }, { "user": "juliasilge", "count": 4, "uuid": 12505835 }, { "user": "hfrick", "count": 4, "uuid": 12950918 }, { "user": "jeroenjanssens", "count": 2, "uuid": 1368256 }, { "user": "rpln", "count": 2, "uuid": 14273214 }, { "user": "jxu", "count": 2, "uuid": 7989982 }, { "user": "bebru", "count": 1, "uuid": 12512888 }, { "user": "dodothereal", "count": 1, "uuid": 129273127 }, { "user": "mine-cetinkaya-rundel", "count": 1, "uuid": 5965649 }, { "user": "pursuitofdatascience", "count": 1, "uuid": 54338793 } ], "_userbio": { "uuid": 29100987, "type": "organization", "name": "tidymodels", "followers": 571 }, "_downloads": { "count": 10410, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/themis" }, "_devurl": "https://github.com/tidymodels/themis", "_pkgdown": "https://themis.tidymodels.org", "_searchresults": 1944, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "extra/themis.html", "LICENSE" ], "_homeurl": "https://github.com/tidymodels/themis", "_realowner": "tidymodels", "_cranurl": true, "_releases": [ { "version": "0.1.0", "date": "2020-01-13" }, { "version": "0.1.1", "date": "2020-05-17" }, { "version": "0.1.2", "date": "2020-08-14" }, { "version": "0.1.3", "date": "2020-11-12" }, { "version": "0.1.4", "date": "2021-06-12" }, { "version": "0.2.0", "date": "2022-03-30" }, { "version": "0.2.1", "date": "2022-04-13" }, { "version": "0.2.2", "date": "2022-05-11" }, { "version": "1.0.0", "date": "2022-07-02" }, { "version": "1.0.1", "date": "2023-04-15" }, { "version": "1.0.2", "date": "2023-08-14" }, { "version": "1.0.3", "date": "2025-01-23" }, { "version": "1.1.0", "date": "2026-08-02" } ], "_exports": [ "adasyn", "bsmote", "cluster_centroids", "cnn", "enn", "instance_hardness", "kmeans_smote", "ncl", "nearmiss", "oss", "required_pkgs", "rose", "smogn", "smote", "smoten", "smotenc", "step_adasyn", "step_bsmote", "step_cluster_centroids", "step_cnn", "step_downsample", "step_enn", "step_instance_hardness", "step_kmeans_smote", "step_ncl", "step_nearmiss", "step_oss", "step_rose", "step_smogn", "step_smote", "step_smoten", "step_smotenc", "step_svmsmote", "step_tomek", "step_upsample", "svmsmote", "tidy", "tomek", "tunable" ], "_datasets": [ { "name": "circle_example", "title": "Synthetic Dataset With a Circle", "object": "circle_example", "class": [ "data.frame" ], "fields": [ "x", "y", "class", "id" ], "rows": 400, "table": true, "tojson": true } ], "_help": [ { "page": "adasyn", "title": "Adaptive Synthetic Algorithm", "concept": [ "Direct Implementations" ], "topics": [ "adasyn" ] }, { "page": "bsmote", "title": "Borderline-SMOTE Algorithm", "concept": [ "Direct Implementations" ], "topics": [ "bsmote" ] }, { "page": "circle_example", "title": "Synthetic Dataset With a Circle", "topics": [ "circle_example" ] }, { "page": "cluster_centroids", "title": "ClusterCentroids Algorithm", "concept": [ "Direct Implementations" ], "topics": [ "cluster_centroids" ] }, { "page": "cnn", "title": "Condensed Nearest Neighbors", "concept": [ "Direct Implementations" ], "topics": [ "cnn" ] }, { "page": "enn", "title": "Edited Nearest Neighbors", "concept": [ "Direct Implementations" ], "topics": [ "enn" ] }, { "page": "instance_hardness", "title": "Remove hard to classify points", "concept": [ "Direct Implementations" ], "topics": [ "instance_hardness" ] }, { "page": "kmeans_smote", "title": "KMeans-SMOTE Algorithm", "concept": [ "Direct Implementations" ], "topics": [ "kmeans_smote" ] }, { "page": "ncl", "title": "Neighborhood Cleaning Rule", "concept": [ "Direct Implementations" ], "topics": [ "ncl" ] }, { "page": "nearmiss", "title": "Remove Points Near Other Classes", "concept": [ "Direct Implementations" ], "topics": [ "nearmiss" ] }, { "page": "oss", "title": "One-Sided Selection", "concept": [ "Direct Implementations" ], "topics": [ "oss" ] }, { "page": "rose", "title": "ROSE Algorithm", "concept": [ "Direct Implementations" ], "topics": [ "rose" ] }, { "page": "smogn", "title": "SMOGN Algorithm", "concept": [ "Direct Implementations" ], "topics": [ "smogn" ] }, { "page": "smote", "title": "SMOTE Algorithm", "concept": [ "Direct Implementations" ], "topics": [ "smote" ] }, { "page": "smoten", "title": "SMOTEN Algorithm", "concept": [ "Direct Implementations" ], "topics": [ "smoten" ] }, { "page": "smotenc", "title": "SMOTENC Algorithm", "concept": [ "Direct Implementations" ], "topics": [ "smotenc" ] }, { "page": "step_adasyn", "title": "Apply Adaptive Synthetic Algorithm", "concept": [ "Steps for over-sampling" ], "topics": [ "step_adasyn", "tidy.step_adasyn" ] }, { "page": "step_bsmote", "title": "Apply Borderline-SMOTE Algorithm", "concept": [ "Steps for over-sampling" ], "topics": [ "step_bsmote", "tidy.step_bsmote" ] }, { "page": "step_cluster_centroids", "title": "Under-Sampling by Cluster Centroids", "concept": [ "Steps for under-sampling" ], "topics": [ "step_cluster_centroids", "tidy.step_cluster_centroids" ] }, { "page": "step_cnn", "title": "Condensed Nearest Neighbors", "concept": [ "Steps for under-sampling" ], "topics": [ "step_cnn", "tidy.step_cnn" ] }, { "page": "step_downsample", "title": "Down-Sample a Data Set Based on a Factor Variable", "concept": [ "Steps for under-sampling" ], "topics": [ "step_downsample", "tidy.step_downsample" ] }, { "page": "step_enn", "title": "Edited Nearest Neighbors", "concept": [ "Steps for under-sampling" ], "topics": [ "step_enn", "tidy.step_enn" ] }, { "page": "step_instance_hardness", "title": "Remove hard to classify points", "concept": [ "Steps for under-sampling" ], "topics": [ "step_instance_hardness", "tidy.step_instance_hardness" ] }, { "page": "step_kmeans_smote", "title": "Apply KMeans-SMOTE Algorithm", "concept": [ "Steps for over-sampling" ], "topics": [ "step_kmeans_smote", "tidy.step_kmeans_smote" ] }, { "page": "step_ncl", "title": "Neighborhood Cleaning Rule", "concept": [ "Steps for under-sampling" ], "topics": [ "step_ncl", "tidy.step_ncl" ] }, { "page": "step_nearmiss", "title": "Remove Points Near Other Classes", "concept": [ "Steps for under-sampling" ], "topics": [ "step_nearmiss", "tidy.step_nearmiss" ] }, { "page": "step_oss", "title": "One-Sided Selection", "concept": [ "Steps for under-sampling" ], "topics": [ "step_oss", "tidy.step_oss" ] }, { "page": "step_rose", "title": "Apply ROSE Algorithm", "concept": [ "Steps for over-sampling" ], "topics": [ "step_rose", "tidy.step_rose" ] }, { "page": "step_smogn", "title": "Apply SMOGN Algorithm", "concept": [ "Steps for over-sampling" ], "topics": [ "step_smogn", "tidy.step_smogn" ] }, { "page": "step_smote", "title": "Apply SMOTE Algorithm", "concept": [ "Steps for over-sampling" ], "topics": [ "step_smote", "tidy.step_smote" ] }, { "page": "step_smoten", "title": "Apply SMOTEN Algorithm", "concept": [ "Steps for over-sampling" ], "topics": [ "step_smoten", "tidy.step_smoten" ] }, { "page": "step_smotenc", "title": "Apply SMOTENC Algorithm", "concept": [ "Steps for over-sampling" ], "topics": [ "step_smotenc", "tidy.step_smotenc" ] }, { "page": "step_svmsmote", "title": "Apply SVM-SMOTE Algorithm", "concept": [ "Steps for over-sampling" ], "topics": [ "step_svmsmote", "tidy.step_svmsmote" ] }, { "page": "step_tomek", "title": "Remove Tomek's Links", "concept": [ "Steps for under-sampling" ], "topics": [ "step_tomek", "tidy.step_tomek" ] }, { "page": "step_upsample", "title": "Up-Sample a Data Set Based on a Factor Variable", "concept": [ "Steps for over-sampling" ], "topics": [ "step_upsample", "tidy.step_upsample" ] }, { "page": "svmsmote", "title": "SVM-SMOTE Algorithm", "concept": [ "Direct Implementations" ], "topics": [ "svmsmote" ] }, { "page": "tomek", "title": "Remove Tomek's Links", "concept": [ "Direct Implementations" ], "topics": [ "tomek" ] } ], "_pkglogo": "https://github.com/tidymodels/themis/raw/HEAD/man/figures/logo.png", "_readme": "https://github.com/tidymodels/themis/raw/HEAD/README.md", "_rundeps": [ "class", "cli", "clock", "codetools", "cpp11", "data.table", "diagram", "digest", "dplyr", "farver", "future", "future.apply", "generics", "ggplot2", "globals", "glue", "gower", "gtable", "hardhat", "ipred", "isoband", "KernSmooth", "labeling", "lattice", "lava", "lifecycle", "listenv", "lubridate", "magrittr", "MASS", "Matrix", "nnet", "numDeriv", "parallelly", "pillar", "pkgconfig", "prodlim", "progressr", "purrr", "R6", "RANN", "RColorBrewer", "Rcpp", "recipes", "rlang", "ROSE", "rpart", "S7", "scales", "shape", "sparsevctrs", "SQUAREM", "stringi", "stringr", "survival", "tibble", "tidyr", "tidyselect", "timechange", "timeDate", "tzdb", "utf8", "vctrs", "viridisLite", "withr" ], "_score": 10.825095007457998, "_indexed": true, "_nocasepkg": "themis", "_universes": [ "tidymodels", "emilhvitfeldt" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.1.0.9000", "date": "2026-09-23T11:38:05.000Z", "distro": "resolute", "commit": "762e11fccde6bffbbf823f1609f00a1846f695d5", "fileid": "https://r2.ropensci.org/fb44863b6e205abb5b2bf25a664cdb08c6ad53f953f836fbb1111ab6e0e23750", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/35854931237" }, { "r": "4.6.1", "os": "linux", "version": "1.1.0.9000", "date": "2026-09-23T11:37:56.000Z", "distro": "resolute", "commit": "762e11fccde6bffbbf823f1609f00a1846f695d5", "fileid": "https://r2.ropensci.org/f910bb4a8fbbbc515bb7011718703bb43e31c488de7cdd91116ed2788cff8335", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/35854931237" }, { "r": "4.5.3", "os": "mac", "version": "1.1.0.9000", "date": "2026-09-23T11:36:50.000Z", "commit": "762e11fccde6bffbbf823f1609f00a1846f695d5", "fileid": "https://r2.ropensci.org/62139f8b275bd625dbe9cbf0479da8e12e77593ecfc05a71d95a51fdd49ae174", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/35854931237" }, { "r": "4.6.1", "os": "mac", "version": "1.1.0.9000", "date": "2026-09-23T11:36:59.000Z", "commit": "762e11fccde6bffbbf823f1609f00a1846f695d5", "fileid": "https://r2.ropensci.org/cc2cde0bbfed4b266c586d32e8f726852abddc4caec1b893b0857b7cc8a89857", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/35854931237" }, { "r": "4.6.0", "os": "wasm", "version": "1.1.0.9000", "date": "2026-09-23T11:37:27.000Z", "commit": "762e11fccde6bffbbf823f1609f00a1846f695d5", "fileid": "https://r2.ropensci.org/00b9cb1e41ef90d632105b7078a37196af77b439e5fab953b1a31d305b55629b", "status": "success", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/35854931237" }, { "r": "4.7.0", "os": "win", "version": "1.1.0.9000", "date": "2026-09-23T11:36:08.000Z", "commit": "762e11fccde6bffbbf823f1609f00a1846f695d5", "fileid": "https://r2.ropensci.org/2cf43fe206bac0d7dc083c7bbc7f0770cca2e2b3eceff803fa650481cce0a7c0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/35854931237" }, { "r": "4.5.3", "os": "win", "version": "1.1.0.9000", "date": "2026-09-23T11:36:13.000Z", "commit": "762e11fccde6bffbbf823f1609f00a1846f695d5", "fileid": "https://r2.ropensci.org/18c7222b112e2e79ac1032f405b4e9415eef46611c6f0fb33f3bc27e25b1a303", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/35854931237" }, { "r": "4.6.1", "os": "win", "version": "1.1.0.9000", "date": "2026-09-23T11:36:05.000Z", "commit": "762e11fccde6bffbbf823f1609f00a1846f695d5", "fileid": "https://r2.ropensci.org/11cdd561eb9fc885ea19314cd60e8963104af663f712639a2c78993bfa3bc992", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/35854931237" } ] }