{ "_id": "6a47b20be06c18f0a651b3c1", "Package": "themis", "Title": "Extra Recipes Steps for Dealing with Unbalanced Data", "Version": "1.0.3.9000", "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\n. Or by\ndecreasing the number of majority cases using NearMiss 2003\n or\nTomek link removal 1976\n.", "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)", "RoxygenNote": "7.3.3", "Config/pak/sysreqs": "libicu-dev", "Repository": "https://tidymodels.r-universe.dev", "Date/Publication": "2026-04-10 00:12:25 UTC", "RemoteUrl": "https://github.com/tidymodels/themis", "RemoteRef": "HEAD", "RemoteSha": "76cf8d0add894b8b1151bcd87c1964656c866fad", "NeedsCompilation": "no", "Packaged": { "Date": "2026-07-03 12:54:55 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_1.0.3.9000.tar.gz", "_fileid": "https://r2.ropensci.org/16e0e21362f606371fef61714f3eabe70b6da5d4cdedcc7273e1f9aa70fd5da1", "_filesize": 362025, "_sha256": "16e0e21362f606371fef61714f3eabe70b6da5d4cdedcc7273e1f9aa70fd5da1", "_expires": "2026-10-11T12:58:50.000Z", "_created": "2026-07-03T12:54:55.000Z", "_published": "2026-07-03T12:58:51.115Z", "_jobs": [ { "job": 85004425677, "time": 194, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8067103467" }, { "job": 85004425686, "time": 188, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8067101680" }, { "job": 85004425710, "time": 96, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "8067067833" }, { "job": 85004425682, "time": 117, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8067075778" }, { "job": 85003833270, "time": 207, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8067031303" }, { "job": 85004425658, "time": 161, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8067091707" }, { "job": 85004425690, "time": 136, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "8067082731" }, { "job": 85004425706, "time": 132, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "8067081470" }, { "job": 85004425688, "time": 170, "config": "windows-release", "r": "4.6.1", "check": "OK", "artifact": "8067094765" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/tidymodels/actions/runs/28661737189", "_status": "success", "_upstream": "https://github.com/tidymodels/themis", "_commit": { "id": "76cf8d0add894b8b1151bcd87c1964656c866fad", "author": "Emil Hvitfeldt ", "committer": "GitHub ", "message": "More docs (#220)", "time": 1775779945 }, "_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": "modeldata", "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 } ], "_tags": [], "_stars": 142, "_contributors": [ { "user": "emilhvitfeldt", "count": 490, "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": "mine-cetinkaya-rundel", "count": 1, "uuid": 5965649 }, { "user": "pursuitofdatascience", "count": 1, "uuid": 54338793 } ], "_userbio": { "uuid": 29100987, "type": "organization", "name": "tidymodels", "followers": 555 }, "_downloads": { "count": 17230, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/themis" }, "_devurl": "https://github.com/tidymodels/themis", "_pkgdown": "https://themis.tidymodels.org", "_searchresults": 1820, "_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/themis.html", "LICENSE", "manual.pdf" ], "_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" } ], "_exports": [ "adasyn", "bsmote", "nearmiss", "required_pkgs", "rose", "smote", "smotenc", "step_adasyn", "step_bsmote", "step_downsample", "step_nearmiss", "step_rose", "step_smote", "step_smotenc", "step_tomek", "step_upsample", "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": "nearmiss", "title": "Remove Points Near Other Classes", "concept": [ "Direct Implementations" ], "topics": [ "nearmiss" ] }, { "page": "rose", "title": "ROSE Algorithm", "concept": [ "Direct Implementations" ], "topics": [ "rose" ] }, { "page": "smote", "title": "SMOTE Algorithm", "concept": [ "Direct Implementations" ], "topics": [ "smote" ] }, { "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_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_nearmiss", "title": "Remove Points Near Other Classes", "concept": [ "Steps for under-sampling" ], "topics": [ "step_nearmiss", "tidy.step_nearmiss" ] }, { "page": "step_rose", "title": "Apply ROSE Algorithm", "concept": [ "Steps for over-sampling" ], "topics": [ "step_rose", "tidy.step_rose" ] }, { "page": "step_smote", "title": "Apply SMOTE Algorithm", "concept": [ "Steps for over-sampling" ], "topics": [ "step_smote", "tidy.step_smote" ] }, { "page": "step_smotenc", "title": "Apply SMOTENC algorithm", "concept": [ "Steps for over-sampling" ], "topics": [ "step_smotenc", "tidy.step_smotenc" ] }, { "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": "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": 10.602887519255484, "_indexed": true, "_nocasepkg": "themis", "_universes": [ "tidymodels", "emilhvitfeldt" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.0.3.9000", "date": "2026-07-03T12:57:25.000Z", "distro": "resolute", "commit": "76cf8d0add894b8b1151bcd87c1964656c866fad", "fileid": "https://r2.ropensci.org/349b2bfcde8c084db8f7cdffb2f902a3c4cef4e37799bca3916f27df6ecaa27d", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/28661737189" }, { "r": "4.6.1", "os": "linux", "version": "1.0.3.9000", "date": "2026-07-03T12:57:20.000Z", "distro": "resolute", "commit": "76cf8d0add894b8b1151bcd87c1964656c866fad", "fileid": "https://r2.ropensci.org/7e56e5648e6bfa0ac9a5126e77cd3a45071bc9cb99d5e5c73c39829ce07096d0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/28661737189" }, { "r": "4.5.3", "os": "mac", "version": "1.0.3.9000", "date": "2026-07-03T12:56:18.000Z", "commit": "76cf8d0add894b8b1151bcd87c1964656c866fad", "fileid": "https://r2.ropensci.org/088212f428e01cf0aba49e12a33aaeb4be0fa341ad7b85d1e7604cf932bf99a4", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/28661737189" }, { "r": "4.6.1", "os": "mac", "version": "1.0.3.9000", "date": "2026-07-03T12:56:33.000Z", "commit": "76cf8d0add894b8b1151bcd87c1964656c866fad", "fileid": "https://r2.ropensci.org/8a436526d31fc666cd73cd69ecd9263ba65ea3a72c5ac184bee2f4fc063f0b52", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/28661737189" }, { "r": "4.6.0", "os": "wasm", "version": "1.0.3.9000", "date": "2026-07-03T12:57:56.000Z", "commit": "76cf8d0add894b8b1151bcd87c1964656c866fad", "fileid": "https://r2.ropensci.org/8d2fd537c8002f2adf4083769d496bf6b217381b75b5b7286ca02c981c3967ae", "status": "success", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/28661737189" }, { "r": "4.7.0", "os": "win", "version": "1.0.3.9000", "date": "2026-07-03T12:56:16.000Z", "commit": "76cf8d0add894b8b1151bcd87c1964656c866fad", "fileid": "https://r2.ropensci.org/efa64b2dcb848b03c0398e842101b5fc46a6b56406b6c3a669de302da4976d45", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/28661737189" }, { "r": "4.5.3", "os": "win", "version": "1.0.3.9000", "date": "2026-07-03T12:56:12.000Z", "commit": "76cf8d0add894b8b1151bcd87c1964656c866fad", "fileid": "https://r2.ropensci.org/78ac7a7ad5222e5279d913543ec6390dc9b2dfcf3e1dbaf3a469427046bd960f", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/28661737189" }, { "r": "4.6.1", "os": "win", "version": "1.0.3.9000", "date": "2026-07-03T12:56:26.000Z", "commit": "76cf8d0add894b8b1151bcd87c1964656c866fad", "fileid": "https://r2.ropensci.org/ab7bbe4543d4c8fb876d3816a01689cba371d9d0237d03ec738874531ffccd9c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/tidymodels/actions/runs/28661737189" } ] }