{ "_id": "6a102101acfb0bcc41c8bdfe", "Package": "janitor", "Title": "Simple Tools for Examining and Cleaning Dirty Data", "Version": "2.2.1.9000", "Authors@R": "c(\nperson(\"Sam\", \"Firke\", , \"samuel.firke@gmail.com\", role = c(\"aut\", \"cre\")),\nperson(\"Bill\", \"Denney\", , \"wdenney@humanpredictions.com\", role = \"ctb\"),\nperson(\"Chris\", \"Haid\", , \"chrishaid@gmail.com\", role = \"ctb\"),\nperson(\"Ryan\", \"Knight\", , \"ryangknight@gmail.com\", role = \"ctb\"),\nperson(\"Malte\", \"Grosser\", , \"malte.grosser@gmail.com\", role = \"ctb\"),\nperson(\"Jonathan\", \"Zadra\", , \"jonathan.zadra@sorensonimpact.com\", role = \"ctb\"),\nperson(\"Olivier\", \"Roy\", role = \"ctb\"),\nperson(\"Josep\", family = \"Pueyo-Ros\", email = \"josep.pueyo@udg.edu\", role = \"ctb\")\n)", "Description": "The main janitor functions can: perfectly format\ndata.frame column names; provide quick counts of variable\ncombinations (i.e., frequency tables and crosstabs); and\nexplore duplicate records. Other janitor functions nicely\nformat the tabulation results. These tabulate-and-report\nfunctions approximate popular features of SPSS and Microsoft\nExcel. This package follows the principles of the \"tidyverse\"\nand works well with the pipe function %>%. janitor was built\nwith beginning-to-intermediate R users in mind and is optimized\nfor user-friendliness.", "License": "MIT + file LICENSE", "URL": "https://github.com/sfirke/janitor,\nhttps://sfirke.github.io/janitor/", "BugReports": "https://github.com/sfirke/janitor/issues", "VignetteBuilder": "knitr", "Config/testthat/edition": "3", "Encoding": "UTF-8", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.3.2", "Config/pak/sysreqs": "libicu-dev", "Repository": "https://nmrgroup.r-universe.dev", "Date/Publication": "2024-12-23 14:15:15 UTC", "RemoteUrl": "https://github.com/sfirke/janitor", "RemoteRef": "HEAD", "RemoteSha": "81702b6ed2b97a143319700a8edf48e8e4cce9cd", "NeedsCompilation": "no", "Packaged": { "Date": "2026-05-14 05:55:12 UTC", "User": "root" }, "Author": "Sam Firke [aut, cre],\nBill Denney [ctb],\nChris Haid [ctb],\nRyan Knight [ctb],\nMalte Grosser [ctb],\nJonathan Zadra [ctb],\nOlivier Roy [ctb],\nJosep Pueyo-Ros [ctb]", "Maintainer": "Sam Firke ", "MD5sum": "588ce2c3059b47b78550d1c54a71636b", "_user": "nmrgroup", "_type": "src", "_file": "janitor_2.2.1.9000.tar.gz", "_fileid": "01dceb4c35f72cf803f1e132e41fec01d12a796faa02e4934d1a77af760bad39", "_filesize": 478812, "_sha256": "01dceb4c35f72cf803f1e132e41fec01d12a796faa02e4934d1a77af760bad39", "_created": "2026-05-14T05:55:12.000Z", "_published": "2026-05-22T09:25:21.668Z", "_distro": "noble", "_jobs": [ { "job": 77352266647, "time": 147, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "6988160016" }, { "job": 77352266868, "time": 146, "config": "linux-release-x86_64", "r": "4.6.0", "check": "NOTE", "artifact": "6988159952" }, { "job": 77352266749, "time": 87, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "NOTE", "artifact": "6988146018" }, { "job": 77352266540, "time": 86, "config": "macos-release-arm64", "r": "4.6.0", "check": "NOTE", "artifact": "6988146142" }, { "job": 77352265985, "time": 178, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "6988127304" }, { "job": 77352266149, "time": 114, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7157207876" }, { "job": 77352266609, "time": 110, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "6988151170" }, { "job": 77352266506, "time": 109, "config": "windows-oldrel", "r": "4.5.3", "check": "NOTE", "artifact": "6988150700" }, { "job": 77352266723, "time": 187, "config": "windows-release", "r": "4.6.0", "check": "NOTE", "artifact": "6988166997" } ], "_buildurl": "https://github.com/r-universe/nmrgroup/actions/runs/25844325262", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/sfirke/janitor", "_commit": { "id": "81702b6ed2b97a143319700a8edf48e8e4cce9cd", "author": "Sam Firke ", "committer": "GitHub ", "message": "Incorporate v2.2.1 branch into main (#590)\n\n* cherried some of #584 for CRAN bugfix release\r\n\r\n* bump version number\r\n\r\n* use Debian-friendly timezone\r\n\r\n* gitignore/rbuildignore revdep\r\n\r\n* fix codecov shield URL\r\n\r\n* prep for release\r\n\r\n* add CRAN-SUBMISSIONS to Rbuildignore\r\n\r\n* bump to dev pkg number\r\n\r\n---------\r\n\r\nCo-authored-by: Bill Denney ", "time": 1734963315 }, "_maintainer": { "name": "Sam Firke", "email": "samuel.firke@gmail.com", "login": "sfirke", "uuid": 7569808 }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.1.2", "role": "Depends" }, { "package": "dplyr", "version": ">= 1.0.0", "role": "Imports" }, { "package": "hms", "role": "Imports" }, { "package": "lifecycle", "role": "Imports" }, { "package": "lubridate", "role": "Imports" }, { "package": "magrittr", "role": "Imports" }, { "package": "purrr", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "snakecase", "version": ">= 0.9.2", "role": "Imports" }, { "package": "stringi", "role": "Imports" }, { "package": "stringr", "role": "Imports" }, { "package": "tidyr", "version": ">= 1.0.0", "role": "Imports" }, { "package": "tidyselect", "version": ">= 1.0.0", "role": "Imports" }, { "package": "dbplyr", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "RSQLite", "role": "Suggests" }, { "package": "sf", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "tibble", "role": "Suggests" }, { "package": "tidygraph", "role": "Suggests" } ], "_owner": "sfirke", "_selfowned": false, "_usedby": 273, "_updates": [], "_tags": [], "_topics": [ "data-analysis", "data-cleaning", "data-science", "dirty-data", "excel", "pivot-tables", "spss", "tabulations", "tidyverse" ], "_stars": 1446, "_contributors": [ { "user": "sfirke", "count": 781, "uuid": 7569808 }, { "user": "billdenney", "count": 84, "uuid": 10359931 }, { "user": "matanhakim", "count": 24, "uuid": 111883851 }, { "user": "rgknight", "count": 12, "uuid": 8363375 }, { "user": "josiahparry", "count": 12, "uuid": 13534508 }, { "user": "olivroy", "count": 10, "uuid": 52606734 }, { "user": "juba", "count": 8, "uuid": 245367 }, { "user": "tazinho", "count": 6, "uuid": 11295192 }, { "user": "mattroumaya", "count": 3, "uuid": 40671730 }, { "user": "khueyama", "count": 3, "uuid": 15066334 }, { "user": "jasonaizkalns", "count": 2, "uuid": 5184911 }, { "user": "jsta", "count": 2, "uuid": 7844578 }, { "user": "henryn218", "count": 2, "uuid": 52625719 }, { "user": "romainfrancois", "count": 2, "uuid": 2625526 }, { "user": "fernandovmacedo", "count": 2, "uuid": 16786320 }, { "user": "jzadra", "count": 2, "uuid": 25590353 }, { "user": "gdutz", "count": 1, "uuid": 30431062 }, { "user": "nelson-gon", "count": 1, "uuid": 42792514 }, { "user": "lionel-", "count": 1, "uuid": 4465050 }, { "user": "krlmlr", "count": 1, "uuid": 1741643 }, { "user": "kgilds", "count": 1, "uuid": 4209605 }, { "user": "anthonytyler27", "count": 1, "uuid": 36506021 }, { "user": "jospueyo", "count": 1, "uuid": 56930644 }, { "user": "jonleslie", "count": 1, "uuid": 32072409 }, { "user": "jjsteph", "count": 1, "uuid": 12075625 }, { "user": "garthtarr", "count": 1, "uuid": 2189134 }, { "user": "francisbarton", "count": 1, "uuid": 1819920 }, { "user": "daniel-barnett", "count": 1, "uuid": 16076593 }, { "user": "danchaltiel", "count": 1, "uuid": 15105152 }, { "user": "bfgray3", "count": 1, "uuid": 20310144 }, { "user": "bbolker", "count": 1, "uuid": 78918 }, { "user": "andrewbarros", "count": 1, "uuid": 941149 } ], "_userbio": { "uuid": 86622210, "type": "organization", "name": "NMRgroup" }, "_downloads": { "count": 290483, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/janitor" }, "_mentions": 11, "_devurl": "https://github.com/sfirke/janitor", "_pkgdown": "https://sfirke.github.io/janitor/", "_searchresults": 53632, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/janitor.html", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_homeurl": "https://github.com/sfirke/janitor", "_realowner": "sfirke", "_cranurl": true, "_releases": [ { "version": "0.2.0", "date": "2016-10-03" }, { "version": "0.2.1", "date": "2016-10-31" }, { "version": "0.3.0", "date": "2017-05-06" }, { "version": "0.3.1", "date": "2018-01-04" }, { "version": "1.0.0", "date": "2018-03-22" }, { "version": "1.1.0", "date": "2018-07-18" }, { "version": "1.1.1", "date": "2018-07-31" }, { "version": "1.2.0", "date": "2019-04-21" }, { "version": "1.2.1", "date": "2020-01-22" }, { "version": "2.0.0", "date": "2020-04-08" }, { "version": "2.0.1", "date": "2020-04-12" }, { "version": "2.1.0", "date": "2021-01-05" }, { "version": "2.2.0", "date": "2023-02-02" }, { "version": "2.2.1", "date": "2024-12-22" } ], "_exports": [ "%>%", "add_totals_col", "add_totals_row", "adorn_crosstab", "adorn_ns", "adorn_pct_formatting", "adorn_percentages", "adorn_rounding", "adorn_title", "adorn_totals", "as_tabyl", "chisq.test", "clean_names", "compare_df_cols", "compare_df_cols_same", "convert_to_date", "convert_to_datetime", "convert_to_NA", "crosstab", "describe_class", "excel_numeric_to_date", "excel_time_to_numeric", "find_header", "fisher.test", "get_dupes", "get_one_to_one", "make_clean_names", "paste_skip_na", "remove_constant", "remove_empty", "remove_empty_cols", "remove_empty_rows", "round_half_up", "round_to_fraction", "row_to_names", "sas_numeric_to_date", "signif_half_up", "single_value", "tabyl", "top_levels", "untabyl", "use_first_valid_of" ], "_help": [ { "page": "adorn_ns", "title": "Add underlying Ns to a tabyl displaying percentages.", "topics": [ "adorn_ns" ] }, { "page": "adorn_pct_formatting", "title": "Format a 'data.frame' of decimals as percentages.", "topics": [ "adorn_pct_formatting" ] }, { "page": "adorn_percentages", "title": "Convert a data.frame of counts to percentages.", "topics": [ "adorn_percentages" ] }, { "page": "adorn_rounding", "title": "Round the numeric columns in a data.frame.", "topics": [ "adorn_rounding" ] }, { "page": "adorn_title", "title": "Add column name to the top of a two-way tabyl.", "topics": [ "adorn_title" ] }, { "page": "adorn_totals", "title": "Append a totals row and/or column to a data.frame", "topics": [ "adorn_totals" ] }, { "page": "as_tabyl", "title": "Add 'tabyl' attributes to a data.frame", "topics": [ "as_tabyl" ] }, { "page": "chisq.test", "title": "Apply 'stats::chisq.test()' to a two-way tabyl", "topics": [ "chisq.test", "chisq.test.default", "chisq.test.tabyl" ] }, { "page": "clean_names", "title": "Cleans names of an object (usually a data.frame).", "concept": [ "Set names" ], "topics": [ "clean_names", "clean_names.default", "clean_names.sf", "clean_names.tbl_graph", "clean_names.tbl_lazy" ] }, { "page": "compare_df_cols", "title": "Compare data frames columns before merging", "concept": [ "data frame type comparison" ], "topics": [ "compare_df_cols" ] }, { "page": "compare_df_cols_same", "title": "Do the the data.frames have the same columns & types?", "concept": [ "data frame type comparison" ], "topics": [ "compare_df_cols_same" ] }, { "page": "convert_to_date", "title": "Parse dates from many formats", "concept": [ "date-time cleaning" ], "topics": [ "convert_to_date", "convert_to_datetime" ] }, { "page": "describe_class", "title": "Describe the class(es) of an object", "concept": [ "data frame type comparison" ], "topics": [ "describe_class", "describe_class.default", "describe_class.factor" ] }, { "page": "excel_numeric_to_date", "title": "Convert dates encoded as serial numbers to Date class.", "concept": [ "date-time cleaning" ], "topics": [ "excel_numeric_to_date" ] }, { "page": "excel_time_to_numeric", "title": "Convert a time that may be inconsistently or inconveniently formatted from Microsoft Excel to a numeric number of seconds between 0 and 86400.", "concept": [ "date-time cleaning" ], "topics": [ "excel_time_to_numeric" ] }, { "page": "find_header", "title": "Find the header row in a data.frame", "concept": [ "Set names" ], "topics": [ "find_header" ] }, { "page": "fisher.test", "title": "Apply 'stats::fisher.test()' to a two-way tabyl", "topics": [ "fisher.test", "fisher.test.default", "fisher.test.tabyl" ] }, { "page": "get_dupes", "title": "Get rows of a 'data.frame' with identical values for the specified variables.", "topics": [ "get_dupes" ] }, { "page": "get_one_to_one", "title": "Find the list of columns that have a 1:1 mapping to each other", "topics": [ "get_one_to_one" ] }, { "page": "make_clean_names", "title": "Cleans a vector of text, typically containing the names of an object.", "topics": [ "make_clean_names" ] }, { "page": "mu_to_u", "title": "Constant to help map from mu to u", "concept": [ "Set names" ], "topics": [ "mu_to_u" ] }, { "page": "paste_skip_na", "title": "Like 'paste()', but missing values are omitted", "topics": [ "paste_skip_na" ] }, { "page": "remove_constant", "title": "Remove constant columns from a data.frame or matrix.", "concept": [ "remove functions" ], "topics": [ "remove_constant" ] }, { "page": "remove_empty", "title": "Remove empty rows and/or columns from a data.frame or matrix.", "concept": [ "remove functions" ], "topics": [ "remove_empty" ] }, { "page": "round_half_up", "title": "Round a numeric vector; halves will be rounded up, ala Microsoft Excel.", "topics": [ "round_half_up" ] }, { "page": "round_to_fraction", "title": "Round to the nearest fraction of a specified denominator.", "topics": [ "round_to_fraction" ] }, { "page": "row_to_names", "title": "Elevate a row to be the column names of a data.frame.", "concept": [ "Set names" ], "topics": [ "row_to_names" ] }, { "page": "sas_numeric_to_date", "title": "Convert a SAS date, time or date/time to an R object", "concept": [ "date-time cleaning" ], "topics": [ "sas_numeric_to_date" ] }, { "page": "signif_half_up", "title": "Round a numeric vector to the specified number of significant digits; halves will be rounded up.", "topics": [ "signif_half_up" ] }, { "page": "single_value", "title": "Ensure that a vector has only a single value throughout.", "topics": [ "single_value" ] }, { "page": "tabyl", "title": "Generate a frequency table (1-, 2-, or 3-way).", "topics": [ "tabyl", "tabyl.data.frame", "tabyl.default" ] }, { "page": "top_levels", "title": "Generate a frequency table of a factor grouped into top-n, bottom-n, and all other levels.", "topics": [ "top_levels" ] }, { "page": "untabyl", "title": "Remove 'tabyl' attributes from a data.frame.", "topics": [ "untabyl" ] } ], "_readme": "https://github.com/sfirke/janitor/raw/HEAD/README.md", "_rundeps": [ "cli", "cpp11", "dplyr", "generics", "glue", "hms", "lifecycle", "lubridate", "magrittr", "pillar", "pkgconfig", "purrr", "R6", "rlang", "snakecase", "stringi", "stringr", "tibble", "tidyr", "tidyselect", "timechange", "utf8", "vctrs", "withr" ], "_vignettes": [ { "source": "janitor.Rmd", "filename": "janitor.html", "title": "Overview of janitor functions", "engine": "knitr::rmarkdown", "headings": [ "Major functions", "Cleaning", "Clean data.frame names with clean_names()", "Do those data.frames actually contain the same columns?", "Check with compare_df_cols()", "Exploring", "tabyl() - a better version of table()", "Explore records with duplicated values for specific combinations of variables with get_dupes()", "Explore relationships between columns with get_one_to_one()", "Minor functions", "Manipulate vectors of names with make_clean_names()", "Validate that a column has a single_value() per group", "remove_empty() rows and columns", "remove_constant() columns", "Directionally-consistent rounding behavior with round_half_up()", "Round decimals to precise fractions of a given denominator with round_to_fraction()", "Fix dates stored as serial numbers with excel_numeric_to_date()", "Convert a mix of date and datetime formats to date", "Elevate column names stored in a data.frame row", "Find the header row buried within a messy data.frame", "Count factor levels in groups of high, medium, and low with top_levels()" ], "created": "2018-01-07 18:25:32", "modified": "2023-06-14 14:01:46", "commits": 19 }, { "source": "tabyls.Rmd", "filename": "tabyls.html", "title": "tabyls: a tidy, fully-featured approach to counting things", "engine": "knitr::rmarkdown", "headings": [ "Motivation: why tabyl?", "How it works", "Examples", "One-way tabyl", "Two-way tabyl", "Three-way tabyl", "Other features of tabyls", "The adorn_* functions", "The adorn functions are:", "BYOt (Bring Your Own tabyl)", "Questions? Comments?" ], "created": "2017-10-11 12:02:49", "modified": "2023-07-11 13:43:44", "commits": 31 } ], "_score": 18.757358602326672, "_indexed": false, "_nocasepkg": "janitor", "_universes": [ "nmrgroup" ], "_indexurl": "https://sfirke.r-universe.dev/janitor", "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "2.2.1.9000", "date": "2026-05-14T05:57:39.000Z", "distro": "noble", "commit": "81702b6ed2b97a143319700a8edf48e8e4cce9cd", "fileid": "947de0ff87c8a2f1d5e0c6060d99fbaf0afc9f82b4a5664c052f2997f002d3ab", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/nmrgroup/actions/runs/25844325262" }, { "r": "4.6.0", "os": "linux", "version": "2.2.1.9000", "date": "2026-05-14T05:57:37.000Z", "distro": "noble", "commit": "81702b6ed2b97a143319700a8edf48e8e4cce9cd", "fileid": "ad758c7cdef7a15f293fe8b4a17d13dc3e6bdd1b7e0a211d09b378626d135b9f", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/nmrgroup/actions/runs/25844325262" }, { "r": "4.5.3", "os": "mac", "version": "2.2.1.9000", "date": "2026-05-14T05:56:41.000Z", "commit": "81702b6ed2b97a143319700a8edf48e8e4cce9cd", "fileid": "d3891566542dadbfc21d91653e1b36dc357cdccbb093ec27f8a88aa9347b8364", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/nmrgroup/actions/runs/25844325262" }, { "r": "4.6.0", "os": "mac", "version": "2.2.1.9000", "date": "2026-05-14T05:56:43.000Z", "commit": "81702b6ed2b97a143319700a8edf48e8e4cce9cd", "fileid": "32b8163d65713fc8f21ddf9460e413a979c9e76fb2300709ce3731b90c541453", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/nmrgroup/actions/runs/25844325262" }, { "r": "4.7.0", "os": "win", "version": "2.2.1.9000", "date": "2026-05-14T05:56:45.000Z", "commit": "81702b6ed2b97a143319700a8edf48e8e4cce9cd", "fileid": "1d89f8379e2d9ae51fd5c5fbf5596b15843d8d0e5ab6fca2451b08442d38d685", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/nmrgroup/actions/runs/25844325262" }, { "r": "4.5.3", "os": "win", "version": "2.2.1.9000", "date": "2026-05-14T05:56:36.000Z", "commit": "81702b6ed2b97a143319700a8edf48e8e4cce9cd", "fileid": "ec9dc4bccf822030c3e8ee8970b82b8cf24274edca6378e29f6f57cbcb706eab", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/nmrgroup/actions/runs/25844325262" }, { "r": "4.6.0", "os": "win", "version": "2.2.1.9000", "date": "2026-05-14T05:58:03.000Z", "commit": "81702b6ed2b97a143319700a8edf48e8e4cce9cd", "fileid": "244c150d978c9815d3fbd09c23015219d5ddb1d4fe4d7ac9980db242861ee790", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/nmrgroup/actions/runs/25844325262" }, { "r": "4.6.0", "os": "wasm", "version": "2.2.1.9000", "date": "2026-05-22T09:25:00.000Z", "commit": "81702b6ed2b97a143319700a8edf48e8e4cce9cd", "fileid": "55def04cf5d0caf9cdf6063364af31c2420ede5c899b5d8b9218d1fd8af07d39", "status": "success", "buildurl": "https://github.com/r-universe/nmrgroup/actions/runs/25844325262" } ] }