{ "_id": "6a107809acfb0bcc41cad165", "Package": "cleanepi", "Title": "Clean and Standardize Epidemiological Data", "Version": "1.1.2.9000", "Authors@R": "c(\nperson(\"Karim\", \"Mané\", , \"karim.mane@lshtm.ac.uk\", role = \"aut\",\ncomment = c(ORCID = \"0000-0002-9892-2999\")),\nperson(\"Thibaut\", \"Jombart\", , \"thibautjombart@gmail.com\", role = \"ctb\",\ncomment = \"Thibaut contributed in development of date_guess().\"),\nperson(\"Abdoelnaser\", \"Degoot\", , \"abdoelnaser-mahmood.degoot@lshtm.ac.uk\", role = \"aut\",\ncomment = c(ORCID = \"0000-0001-8788-2496\")),\nperson(\"Bankolé\", \"Ahadzie\", , \"Bankole.Ahadzie@lshtm.ac.uk\", role = \"aut\"),\nperson(\"Nuredin\", \"Mohammed\", , \"Nuredin.Mohammed@lshtm.ac.uk\", role = \"aut\"),\nperson(\"Bubacarr\", \"Bah\", , \"Bubacarr.Bah1@lshtm.ac.uk\", role = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0003-3318-6668\")),\nperson(\"Hugo\", \"Gruson\", , \"hugo@data.org\", role = c(\"ctb\", \"rev\"),\ncomment = c(ORCID = \"0000-0002-4094-1476\")),\nperson(\"Pratik R.\", \"Gupte\", , \"pratik.gupte@lshtm.ac.uk\", role = \"rev\",\ncomment = c(ORCID = \"0000-0001-5294-7819\")),\nperson(\"James M.\", \"Azam\", , \"james.azam@lshtm.ac.uk\", role = \"rev\",\ncomment = c(ORCID = \"0000-0001-5782-7330\")),\nperson(\"Joshua W.\", \"Lambert\", , \"joshua.lambert@lshtm.ac.uk\", role = c(\"rev\", \"ctb\"),\ncomment = c(ORCID = \"0000-0001-5218-3046\")),\nperson(\"Chris\", \"Hartgerink\", , \"chris@data.org\", role = \"rev\",\ncomment = c(ORCID = \"0000-0003-1050-6809\")),\nperson(\"Andree\", \"Valle-Campos\", , \"avallecam@gmail.com\", role = c(\"rev\", \"ctb\"),\ncomment = c(ORCID = \"0000-0002-7779-481X\")),\nperson(\"London School of Hygiene and Tropical Medicine, LSHTM\", role = \"cph\",\ncomment = c(ROR = \"00a0jsq62\")),\nperson(\"data.org\", role = \"fnd\")\n)", "Description": "Cleaning and standardizing tabular data package, tailored\nspecifically for curating epidemiological data. It streamlines\nvarious data cleaning tasks that are typically expected when\nworking with datasets in epidemiology. It returns the processed\ndata in the same format, and generates a comprehensive report\ndetailing the outcomes of each cleaning task.", "License": "MIT + file LICENSE", "URL": "https://epiverse-trace.github.io/cleanepi/,\nhttps://github.com/epiverse-trace/cleanepi", "BugReports": "https://github.com/epiverse-trace/cleanepi/issues", "VignetteBuilder": "knitr", "Config/Needs/website": "epiverse-trace/epiversetheme", "Config/potools/style": "explicit", "Config/testthat/edition": "3", "Encoding": "UTF-8", "Language": "en-US", "LazyData": "true", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.3.2", "Config/pak/sysreqs": "libicu-dev libx11-dev", "Repository": "https://epiverse-trace.r-universe.dev", "Date/Publication": "2026-01-29 15:38:21 UTC", "RemoteUrl": "https://github.com/epiverse-trace/cleanepi", "RemoteRef": "HEAD", "RemoteSha": "6fb22d1aa55ebbe7edcc020771e6ab6006a26a26", "NeedsCompilation": "no", "Packaged": { "Date": "2026-05-06 09:23:39 UTC", "User": "root" }, "Author": "Karim Mané [aut] (ORCID: ),\nThibaut Jombart [ctb] (Thibaut contributed in development of\ndate_guess().),\nAbdoelnaser Degoot [aut] (ORCID:\n),\nBankolé Ahadzie [aut],\nNuredin Mohammed [aut],\nBubacarr Bah [aut, cre] (ORCID:\n),\nHugo Gruson [ctb, rev] (ORCID: ),\nPratik R. Gupte [rev] (ORCID: ),\nJames M. Azam [rev] (ORCID: ),\nJoshua W. Lambert [rev, ctb] (ORCID:\n),\nChris Hartgerink [rev] (ORCID: ),\nAndree Valle-Campos [rev, ctb] (ORCID:\n),\nLondon School of Hygiene and Tropical Medicine, LSHTM [cph] (ROR:\n),\ndata.org [fnd]", "Maintainer": "Bubacarr Bah ", "MD5sum": "3fc60208d2204f2fb396a5503a2bd665", "_user": "epiverse-trace", "_type": "src", "_file": "cleanepi_1.1.2.9000.tar.gz", "_fileid": "ae7a3bf4fc21cd76369b56f98c7beb76b673e9a19db1f4a65a6d056cc8b4ee35", "_filesize": 834991, "_sha256": "ae7a3bf4fc21cd76369b56f98c7beb76b673e9a19db1f4a65a6d056cc8b4ee35", "_created": "2026-05-06T09:23:39.000Z", "_published": "2026-05-22T15:36:41.656Z", "_distro": "noble", "_jobs": [ { "job": 77412109247, "time": 171, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "6826768779" }, { "job": 77412109515, "time": 166, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "6826769451" }, { "job": 77412109354, "time": 122, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "6826752904" }, { "job": 77412109393, "time": 114, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "6826750767" }, { "job": 77412108625, "time": 219, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "6826710619" }, { "job": 77412108479, "time": 123, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7164424147" }, { "job": 77412109407, "time": 115, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "6826750773" }, { "job": 77412109535, "time": 108, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "6826748143" }, { "job": 77412109299, "time": 128, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "6826755191" } ], "_buildurl": "https://github.com/r-universe/epiverse-trace/actions/runs/25426872308", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/epiverse-trace/cleanepi", "_commit": { "id": "6fb22d1aa55ebbe7edcc020771e6ab6006a26a26", "author": "github-actions ", "committer": "Karim MANE <84502011+Karim-Mane@users.noreply.github.com>", "message": "docs(license): update copyright year(s)\n", "time": 1769701101 }, "_maintainer": { "name": "Bubacarr Bah", "email": "bubacarr.bah1@lshtm.ac.uk", "login": "bbah74", "uuid": 28865380, "orcid": "0000-0003-3318-6668" }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.0.0", "role": "Depends" }, { "package": "checkmate", "role": "Imports" }, { "package": "cli", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "janitor", "role": "Imports" }, { "package": "linelist", "version": ">= 1.0.0", "role": "Imports" }, { "package": "lubridate", "role": "Imports" }, { "package": "magrittr", "role": "Imports" }, { "package": "matchmaker", "role": "Imports" }, { "package": "numberize", "role": "Imports" }, { "package": "readr", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "tibble", "role": "Imports" }, { "package": "htmlwidgets", "role": "Suggests" }, { "package": "kableExtra", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "lintr", "role": "Suggests" }, { "package": "markdown", "role": "Suggests" }, { "package": "naniar", "role": "Suggests" }, { "package": "reactable", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "spelling", "role": "Suggests" }, { "package": "systemfonts", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" } ], "_owner": "epiverse-trace", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2025-22", "n": 5 }, { "week": "2025-28", "n": 40 }, { "week": "2025-29", "n": 51 }, { "week": "2025-36", "n": 5 }, { "week": "2025-37", "n": 9 }, { "week": "2025-42", "n": 4 }, { "week": "2025-43", "n": 2 }, { "week": "2025-44", "n": 17 }, { "week": "2026-05", "n": 2 } ], "_tags": [ { "name": "v1.1.1", "date": "2025-07-16" }, { "name": "v1.1.2", "date": "2025-10-28" } ], "_topics": [ "data-cleaning", "epidemiology", "epiverse" ], "_stars": 12, "_contributors": [ { "user": "karim-mane", "count": 610, "uuid": 84502011 }, { "user": "bisaloo", "count": 51, "uuid": 10783929 }, { "user": "degoot-am", "count": 38, "uuid": 19929487 }, { "user": "joshwlambert", "count": 36, "uuid": 46606402 }, { "user": "bahadzie", "count": 9, "uuid": 41001537 }, { "user": "pratikunterwegs", "count": 8, "uuid": 25272594 }, { "user": "thibautjombart", "count": 7, "uuid": 10757154 } ], "_userbio": { "uuid": 101338582, "type": "organization", "name": "Epiverse-TRACE" }, "_downloads": { "count": 296, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/cleanepi" }, "_devurl": "https://github.com/epiverse-trace/cleanepi", "_pkgdown": "https://epiverse-trace.github.io/cleanepi/", "_searchresults": 44, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/cleanepi.html", "extra/contents.json", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_homeurl": "https://github.com/epiverse-trace/cleanepi", "_realowner": "epiverse-trace", "_cranurl": true, "_releases": [ { "version": "1.0.2", "date": "2024-06-17" }, { "version": "1.1.0", "date": "2025-03-04" }, { "version": "1.1.1", "date": "2025-07-16" }, { "version": "1.1.2", "date": "2025-10-29" } ], "_exports": [ "%>%", "add_to_dictionary", "add_to_report", "check_date_sequence", "check_subject_ids", "clean_data", "clean_using_dictionary", "convert_numeric_to_date", "convert_to_numeric", "correct_misspelled_values", "correct_subject_ids", "find_duplicates", "get_default_params", "print_report", "remove_constants", "remove_duplicates", "replace_missing_values", "scan_data", "standardize_column_names", "standardize_dates", "timespan" ], "_datasets": [ { "name": "common_na_strings", "title": "Common strings representing missing values", "object": "common_na_strings", "class": [ "character" ], "fields": [], "table": false, "tojson": true } ], "_help": [ { "page": "add_to_dictionary", "title": "Add an element to the data dictionary", "topics": [ "add_to_dictionary" ] }, { "page": "add_to_report", "title": "Add an element to the report object", "topics": [ "add_to_report" ] }, { "page": "check_date_sequence", "title": "Checks whether the order in a sequence of date events is chronological. order.", "topics": [ "check_date_sequence" ] }, { "page": "check_subject_ids", "title": "Check whether the subject IDs comply with the expected format. When incorrect IDs are found, the function sends a warning and the user can call the 'correct_subject_ids' function to correct them.", "topics": [ "check_subject_ids" ] }, { "page": "clean_data", "title": "Clean and standardize data", "topics": [ "clean_data" ] }, { "page": "clean_using_dictionary", "title": "Perform dictionary-based cleaning", "topics": [ "clean_using_dictionary" ] }, { "page": "common_na_strings", "title": "Common strings representing missing values", "topics": [ "common_na_strings" ] }, { "page": "convert_numeric_to_date", "title": "Convert numeric to date", "topics": [ "convert_numeric_to_date" ] }, { "page": "convert_to_numeric", "title": "Convert columns into numeric", "topics": [ "convert_to_numeric" ] }, { "page": "correct_misspelled_values", "title": "Correct misspelled values by using approximate string matching techniques to compare them against the expected values.", "topics": [ "correct_misspelled_values" ] }, { "page": "correct_subject_ids", "title": "Correct the wrong subject IDs based on the user-provided values.", "topics": [ "correct_subject_ids" ] }, { "page": "find_duplicates", "title": "Identify and return duplicated rows in a data frame or linelist.", "topics": [ "find_duplicates" ] }, { "page": "get_default_params", "title": "Set and return 'clean_data' default parameters", "topics": [ "get_default_params" ] }, { "page": "print_report", "title": "Generate report from data cleaning operations", "topics": [ "print_report" ] }, { "page": "remove_constants", "title": "Remove constant data, including empty rows, empty columns, and columns with constant values.", "topics": [ "remove_constants" ] }, { "page": "remove_duplicates", "title": "Remove duplicates", "topics": [ "remove_duplicates" ] }, { "page": "replace_missing_values", "title": "Replace missing values with 'NA'", "topics": [ "replace_missing_values" ] }, { "page": "scan_data", "title": "Scan through a data frame and return the proportion of 'missing', 'numeric', 'Date', 'character', 'logical' values.", "topics": [ "scan_data" ] }, { "page": "standardize_column_names", "title": "Standardize column names of a data frame or line list", "topics": [ "standardize_column_names" ] }, { "page": "standardize_dates", "title": "Standardize date variables", "topics": [ "standardize_dates" ] }, { "page": "timespan", "title": "Calculate time span between dates", "topics": [ "timespan" ] } ], "_pkglogo": "https://github.com/epiverse-trace/cleanepi/raw/HEAD/man/figures/logo.svg", "_readme": "https://github.com/epiverse-trace/cleanepi/raw/HEAD/README.md", "_rundeps": [ "backports", "bit", "bit64", "checkmate", "cli", "clipr", "cpp11", "crayon", "dplyr", "forcats", "generics", "glue", "hms", "janitor", "lifecycle", "linelist", "lubridate", "magrittr", "matchmaker", "numberize", "pillar", "pkgconfig", "prettyunits", "progress", "purrr", "R6", "readr", "rlang", "snakecase", "stringi", "stringr", "tibble", "tidyr", "tidyselect", "timechange", "tzdb", "utf8", "vctrs", "vroom", "withr" ], "_vignettes": [ { "source": "cleanepi.Rmd", "filename": "cleanepi.html", "title": "Introduction to cleanepi", "engine": "knitr::rmarkdown", "headings": [ "An overview", "General data cleaning tasks", "Using {cleanepi} functionalities with pipe operators", "Printing the report", "Specific data cleaning tasks", "Remove constant data", "Cleaning column names", "Replacing missing entries with NA", "Standardizing Dates", "Standardizing subject IDs", "Detecting incorrect, duplicated, and missing subject IDs", "Correct wrong subject ids", "Checking date sequence", "Converting character columns into numeric", "Converting numeric values into date", "Finding duplicated rows", "Removing duplicates", "Dictionary based data substituting", "Correct misspelled values", "Calculating time span in different time scales (“years”, “months”, “weeks”, or “days”)" ], "created": "2023-03-07 22:47:30", "modified": "2025-07-15 16:30:23", "commits": 73 }, { "source": "design_principle.Rmd", "filename": "design_principle.html", "title": "Package Design vignette for {cleanepi}", "engine": "knitr::rmarkdown", "headings": [ "Concept and motivation", "Design decisions", "Scope", "Input", "Output", "Modules in", "1. Standardization of column names", "2. Removal of empty rows and columns and constant columns", "3. Detection and removal of duplicates", "4. Replacement of missing values with NA", "5. Standardization of date values", "6. Standardization of subject IDs", "7. Dictionary based substitution", "8. Conversion of values when necessary", "9. Verification of the sequence of date-events", "10. Transformation of selected columns", "Surrogate functions", "Related packages", "Dependencies", "Contribute" ], "created": "2024-01-20 13:42:02", "modified": "2025-07-08 10:52:24", "commits": 55 } ], "_score": 7.455027682356782, "_indexed": true, "_nocasepkg": "cleanepi", "_universes": [ "epiverse-trace", "bbah74" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.1.2.9000", "date": "2026-05-06T09:26:06.000Z", "distro": "noble", "commit": "6fb22d1aa55ebbe7edcc020771e6ab6006a26a26", "fileid": "8f575cb88231e6b51781529f7c96d401e17dffb71132190cd242e48b4592b4ed", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/epiverse-trace/actions/runs/25426872308" }, { "r": "4.6.0", "os": "linux", "version": "1.1.2.9000", "date": "2026-05-06T09:26:09.000Z", "distro": "noble", "commit": "6fb22d1aa55ebbe7edcc020771e6ab6006a26a26", "fileid": "7e38c0cf27efc900370d78a50e7c4bedcd03c947193f6f43125646603726f472", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/epiverse-trace/actions/runs/25426872308" }, { "r": "4.5.3", "os": "mac", "version": "1.1.2.9000", "date": "2026-05-06T09:25:29.000Z", "commit": "6fb22d1aa55ebbe7edcc020771e6ab6006a26a26", "fileid": "57cb44e4ba91fc57d06ac9e6f69d4429b11a15feeb78166031822d3e0841c7c0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/epiverse-trace/actions/runs/25426872308" }, { "r": "4.6.0", "os": "mac", "version": "1.1.2.9000", "date": "2026-05-06T09:25:24.000Z", "commit": "6fb22d1aa55ebbe7edcc020771e6ab6006a26a26", "fileid": "edbbf85124c633b313a74ebf72d43bc317f8555aacea8a0ffe866610244ecf70", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/epiverse-trace/actions/runs/25426872308" }, { "r": "4.7.0", "os": "win", "version": "1.1.2.9000", "date": "2026-05-06T09:25:01.000Z", "commit": "6fb22d1aa55ebbe7edcc020771e6ab6006a26a26", "fileid": "a50a98344ffc1d46a5ce902cf2edfedb0f47a8a218b73a9ad1c053ac1f4ddfd0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/epiverse-trace/actions/runs/25426872308" }, { "r": "4.5.3", "os": "win", "version": "1.1.2.9000", "date": "2026-05-06T09:24:52.000Z", "commit": "6fb22d1aa55ebbe7edcc020771e6ab6006a26a26", "fileid": "eb14c2d2733e1cbe0c6d36e5d5359477f878651ce9bdfe3480a58f4d3de75856", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/epiverse-trace/actions/runs/25426872308" }, { "r": "4.6.0", "os": "win", "version": "1.1.2.9000", "date": "2026-05-06T09:25:09.000Z", "commit": "6fb22d1aa55ebbe7edcc020771e6ab6006a26a26", "fileid": "2120f0895f8f0527a40c8fb92cc18fd750880c2b3366184f139212bfb65191d9", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/epiverse-trace/actions/runs/25426872308" }, { "r": "4.6.0", "os": "wasm", "version": "1.1.2.9000", "date": "2026-05-22T15:36:22.000Z", "commit": "6fb22d1aa55ebbe7edcc020771e6ab6006a26a26", "fileid": "f52d4f1d7a1eb8cb360b5bca81e126e6bd3461c16ac718d72ed1b32b0dd35828", "status": "success", "buildurl": "https://github.com/r-universe/epiverse-trace/actions/runs/25426872308" } ] }