{ "_id": "6a1ed620b401979e7340e911", "Package": "dataPreparation", "Title": "Automated Data Preparation", "Version": "1.1.2", "Authors@R": "person(\"Emmanuel-Lin\", \"Toulemonde\", email = \"el.toulemonde@protonmail.com\", role = c(\"aut\", \"cre\"))", "Description": "Do most of the painful data preparation for a data science\nproject with a minimum amount of code; Take advantages of\n'data.table' efficiency and use some algorithmic trick in order\nto perform data preparation in a time and RAM efficient way.", "License": "GPL-3 | file LICENSE", "LazyData": "true", "Encoding": "UTF-8", "RoxygenNote": "7.3.2", "BugReports": "https://github.com/ELToulemonde/dataPreparation/issues", "Config/pak/sysreqs": "libicu-dev", "Repository": "https://eltoulemonde.r-universe.dev", "Date/Publication": "2025-09-02 11:41:20 UTC", "RemoteUrl": "https://github.com/eltoulemonde/datapreparation", "RemoteRef": "HEAD", "RemoteSha": "5748e2dd552e449302ada05d35e20eb6b8ac4ad8", "NeedsCompilation": "no", "Packaged": { "Date": "2026-05-20 10:26:41 UTC", "User": "root" }, "Author": "Emmanuel-Lin Toulemonde [aut, cre]", "Maintainer": "Emmanuel-Lin Toulemonde ", "MD5sum": "8004721783b943a2181b404b04af2056", "_user": "eltoulemonde", "_type": "src", "_file": "dataPreparation_1.1.2.tar.gz", "_fileid": "6aa86d78cf733db8b40b84df69c2794b819998a73e705b1571904526999cce4f", "_filesize": 1490806, "_sha256": "6aa86d78cf733db8b40b84df69c2794b819998a73e705b1571904526999cce4f", "_created": "2026-05-20T10:26:41.000Z", "_published": "2026-06-02T13:09:52.056Z", "_distro": "noble", "_jobs": [ { "job": 79077989882, "time": 146, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7107533640" }, { "job": 79077990149, "time": 163, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7107538710" }, { "job": 79077989875, "time": 182, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7107554362" }, { "job": 79077989877, "time": 137, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7107537177" }, { "job": 79077988768, "time": 175, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7107485034" }, { "job": 79077989253, "time": 110, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7358566887" }, { "job": 79077989601, "time": 122, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7107525526" }, { "job": 79077990323, "time": 108, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7107521173" }, { "job": 79077989991, "time": 111, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7107522595" } ], "_buildurl": "https://github.com/r-universe/eltoulemonde/actions/runs/26156499395", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/eltoulemonde/datapreparation", "_commit": { "id": "5748e2dd552e449302ada05d35e20eb6b8ac4ad8", "author": "Emmanuel-Lin Toulemonde ", "committer": "Emmanuel-Lin Toulemonde ", "message": "Finish fixing doc\n", "time": 1756813280 }, "_maintainer": { "name": "Emmanuel-Lin Toulemonde", "email": "el.toulemonde@protonmail.com", "login": "eltoulemonde", "description": "", "uuid": 27816336 }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.6.0", "role": "Depends" }, { "package": "data.table", "role": "Imports" }, { "package": "lubridate", "role": "Imports" }, { "package": "stringr", "role": "Imports" }, { "package": "Matrix", "role": "Imports" }, { "package": "progress", "role": "Imports" }, { "package": "testthat", "version": ">= 2.0.0", "role": "Suggests" } ], "_owner": "eltoulemonde", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2025-36", "n": 3 } ], "_tags": [], "_topics": [ "data-preparation", "data-preprocessing", "data-science", "date-conversion", "speed", "variable-elimination", "variable-selection" ], "_stars": 33, "_contributors": [ { "user": "eltoulemonde", "count": 82, "uuid": 27816336 }, { "user": "xavierfontaine", "count": 2, "uuid": 12429906 }, { "user": "earino", "count": 1, "uuid": 3258 } ], "_userbio": { "uuid": 27816336, "type": "user", "name": "ELToulemonde" }, "_downloads": { "count": 707, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/dataPreparation" }, "_devurl": "https://github.com/eltoulemonde/datapreparation", "_searchresults": 147, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/dataPreparation.html", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_homeurl": "https://github.com/eltoulemonde/datapreparation", "_realowner": "eltoulemonde", "_cranurl": true, "_releases": [ { "version": "0.1", "date": "2017-07-07" }, { "version": "0.2", "date": "2017-08-18" }, { "version": "0.3.2", "date": "2017-10-25" }, { "version": "0.3.4", "date": "2017-12-20" }, { "version": "0.3.5", "date": "2018-02-16" }, { "version": "0.3.6", "date": "2018-05-11" }, { "version": "0.3.7", "date": "2018-08-20" }, { "version": "0.3.8", "date": "2018-10-17" }, { "version": "0.3.9", "date": "2019-01-02" }, { "version": "0.4.0", "date": "2019-03-25" }, { "version": "0.4.1", "date": "2019-07-19" }, { "version": "0.4.2", "date": "2019-11-14" }, { "version": "0.4.3", "date": "2020-02-12" }, { "version": "1.0.0", "date": "2020-11-13" }, { "version": "1.0.1", "date": "2020-12-16" }, { "version": "1.0.2", "date": "2021-09-20" }, { "version": "1.0.3", "date": "2021-11-19" }, { "version": "1.0.4", "date": "2021-12-21" }, { "version": "1.0.5", "date": "2022-07-15" }, { "version": "1.1.1", "date": "2023-07-04" }, { "version": "1.1.2", "date": "2025-09-02" } ], "_exports": [ "aggregate_by_key", "as.POSIXct_fast", "build_bins", "build_date_factor", "build_encoding", "build_scales", "build_target_encoding", "compute_probability_ratio", "compute_weight_of_evidence", "data_preparation_news", "date_format_unifier", "description", "fast_discretization", "fast_filter_variables", "fast_handle_na", "fast_is_equal", "fast_round", "fast_scale", "find_and_transform_dates", "find_and_transform_numerics", "generate_date_diffs", "generate_factor_from_date", "generate_from_character", "generate_from_factor", "get_most_frequent_element", "identify_dates", "one_hot_encoder", "prepare_set", "remove_percentile_outlier", "remove_rare_categorical", "remove_sd_outlier", "same_shape", "set_as_numeric_matrix", "set_col_as_character", "set_col_as_date", "set_col_as_factor", "set_col_as_numeric", "shape_set", "target_encode", "un_factor", "which_are_bijection", "which_are_constant", "which_are_in_double", "which_are_included" ], "_datasets": [ { "name": "adult", "title": "Adult for UCI repository", "object": "adult", "class": [ "data.frame" ], "fields": [ "age", "type_employer", "fnlwgt", "education", "education_num", "marital", "occupation", "relationship", "race", "sex", "capital_gain", "capital_loss", "hr_per_week", "country", "income" ], "rows": 32561, "table": true, "tojson": true }, { "name": "messy_adult", "title": "Adult with some ugly columns added", "object": "messy_adult", "class": [ "data.table", "data.frame" ], "fields": [ "date1", "date2", "date3", "date4", "num1", "num2", "constant", "mail", "num3", "age", "type_employer", "fnlwgt", "education", "education_num", "marital", "occupation", "relationship", "race", "sex", "capital_gain", "capital_loss", "hr_per_week", "country", "income" ], "rows": 32561, "table": true, "tojson": true }, { "name": "tiny_messy_adult", "title": "First 500 rows of 'messy_adult'", "object": "tiny_messy_adult", "class": [ "data.table", "data.frame" ], "fields": [ "date1", "date2", "date3", "date4", "num1", "num2", "constant", "mail", "num3", "age", "type_employer", "fnlwgt", "education", "education_num", "marital", "occupation", "relationship", "race", "sex", "capital_gain", "capital_loss", "hr_per_week", "country", "income" ], "rows": 500, "table": true, "tojson": true } ], "_help": [ { "page": "adult", "title": "Adult for UCI repository", "topics": [ "adult" ] }, { "page": "aggregate_by_key", "title": "Automatic data_set aggregation by key", "topics": [ "aggregate_by_key" ] }, { "page": "as.POSIXct_fast", "title": "Faster date transformation", "topics": [ "as.POSIXct_fast" ] }, { "page": "build_bins", "title": "Compute bins", "topics": [ "build_bins" ] }, { "page": "build_date_factor", "title": "Date Factor", "topics": [ "build_date_factor" ] }, { "page": "build_encoding", "title": "Compute encoding", "topics": [ "build_encoding" ] }, { "page": "build_scales", "title": "Compute scales", "topics": [ "build_scales" ] }, { "page": "build_target_encoding", "title": "Build target encoding", "topics": [ "build_target_encoding" ] }, { "page": "compute_probability_ratio", "title": "Compute probability ratio", "topics": [ "compute_probability_ratio" ] }, { "page": "compute_weight_of_evidence", "title": "Compute weight of evidence", "topics": [ "compute_weight_of_evidence" ] }, { "page": "data_preparation_news", "title": "Show the NEWS file", "topics": [ "data_preparation_news" ] }, { "page": "date_format_unifier", "title": "Unify dates format", "topics": [ "date_format_unifier" ] }, { "page": "description", "title": "Describe data set", "topics": [ "description" ] }, { "page": "fast_discretization", "title": "Discretization", "topics": [ "fast_discretization" ] }, { "page": "fast_filter_variables", "title": "Filtering useless variables", "topics": [ "fast_filter_variables" ] }, { "page": "fast_handle_na", "title": "Handle NA values", "topics": [ "fast_handle_na" ] }, { "page": "fast_is_equal", "title": "Fast checks of equality", "topics": [ "fast_is_equal" ] }, { "page": "fast_round", "title": "Fast round", "topics": [ "fast_round" ] }, { "page": "fast_scale", "title": "scale", "topics": [ "fast_scale" ] }, { "page": "find_and_transform_dates", "title": "Identify date columns", "topics": [ "find_and_transform_dates" ] }, { "page": "find_and_transform_numerics", "title": "Identify numeric columns in a data_set set", "topics": [ "find_and_transform_numerics" ] }, { "page": "generate_date_diffs", "title": "Date difference", "topics": [ "generate_date_diffs" ] }, { "page": "generate_factor_from_date", "title": "Generate factor from dates", "topics": [ "generate_factor_from_date" ] }, { "page": "generate_from_character", "title": "Recode character", "topics": [ "generate_from_character" ] }, { "page": "generate_from_factor", "title": "Recode factor", "topics": [ "generate_from_factor" ] }, { "page": "get_most_frequent_element", "title": "Get most frequent element", "topics": [ "get_most_frequent_element" ] }, { "page": "identify_dates", "title": "Identify date columns", "topics": [ "identify_dates" ] }, { "page": "messy_adult", "title": "Adult with some ugly columns added", "topics": [ "messy_adult" ] }, { "page": "one_hot_encoder", "title": "One hot encoder", "topics": [ "one_hot_encoder" ] }, { "page": "prepare_set", "title": "Preparation pipeline", "topics": [ "prepare_set" ] }, { "page": "remove_percentile_outlier", "title": "Percentile outlier filtering", "topics": [ "remove_percentile_outlier" ] }, { "page": "remove_rare_categorical", "title": "Filter rare categories", "topics": [ "remove_rare_categorical" ] }, { "page": "remove_sd_outlier", "title": "Standard deviation outlier filtering", "topics": [ "remove_sd_outlier" ] }, { "page": "same_shape", "title": "Give same shape", "topics": [ "same_shape" ] }, { "page": "set_as_numeric_matrix", "title": "Numeric matrix preparation for Machine Learning.", "topics": [ "set_as_numeric_matrix" ] }, { "page": "set_col_as_character", "title": "Set columns as character", "topics": [ "set_col_as_character" ] }, { "page": "set_col_as_date", "title": "Set columns as POSIXct", "topics": [ "set_col_as_date" ] }, { "page": "set_col_as_factor", "title": "Set columns as factor", "topics": [ "set_col_as_factor" ] }, { "page": "set_col_as_numeric", "title": "Set columns as numeric", "topics": [ "set_col_as_numeric" ] }, { "page": "shape_set", "title": "Final preparation before ML algorithm", "topics": [ "shape_set" ] }, { "page": "target_encode", "title": "Target encode", "topics": [ "target_encode" ] }, { "page": "tiny_messy_adult", "title": "First 500 rows of 'messy_adult'", "topics": [ "tiny_messy_adult" ] }, { "page": "un_factor", "title": "Unfactor factor with too many values", "topics": [ "un_factor" ] }, { "page": "which_are_bijection", "title": "Identify bijections", "topics": [ "which_are_bijection" ] }, { "page": "which_are_constant", "title": "Identify constant columns", "topics": [ "which_are_constant" ] }, { "page": "which_are_in_double", "title": "Identify double columns", "topics": [ "which_are_in_double" ] }, { "page": "which_are_included", "title": "Identify columns that are included in others", "topics": [ "which_are_included" ] } ], "_readme": "https://github.com/eltoulemonde/datapreparation/raw/HEAD/README.md", "_rundeps": [ "cli", "cpp11", "crayon", "data.table", "generics", "glue", "hms", "lattice", "lifecycle", "lubridate", "magrittr", "Matrix", "pkgconfig", "prettyunits", "progress", "R6", "rlang", "stringi", "stringr", "timechange", "vctrs" ], "_score": 5.6858312746260635, "_indexed": true, "_nocasepkg": "datapreparation", "_universes": [ "eltoulemonde" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.1.2", "date": "2026-05-20T10:28:45.000Z", "distro": "noble", "commit": "5748e2dd552e449302ada05d35e20eb6b8ac4ad8", "fileid": "895a3affb50419fda5cea90f5b8cbb762989a6545212ae1af17f868fea0ab3b7", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/eltoulemonde/actions/runs/26156499395" }, { "r": "4.6.0", "os": "linux", "version": "1.1.2", "date": "2026-05-20T10:29:00.000Z", "distro": "noble", "commit": "5748e2dd552e449302ada05d35e20eb6b8ac4ad8", "fileid": "c86dac8776d1f004743013ee6889d8751a6655d8efe10ddfe3716a070a6c9405", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/eltoulemonde/actions/runs/26156499395" }, { "r": "4.5.3", "os": "mac", "version": "1.1.2", "date": "2026-05-20T10:30:04.000Z", "commit": "5748e2dd552e449302ada05d35e20eb6b8ac4ad8", "fileid": "c9c530c9428a56576bc401b0b3dab65663541514a9408d8b9293f90fa8aac1d0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/eltoulemonde/actions/runs/26156499395" }, { "r": "4.6.0", "os": "mac", "version": "1.1.2", "date": "2026-05-20T10:29:14.000Z", "commit": "5748e2dd552e449302ada05d35e20eb6b8ac4ad8", "fileid": "88e11a5c87da7676d8bfca2efe16744ac786bf2ee0a2687b51cc44d2808b16bf", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/eltoulemonde/actions/runs/26156499395" }, { "r": "4.7.0", "os": "win", "version": "1.1.2", "date": "2026-05-20T10:28:03.000Z", "commit": "5748e2dd552e449302ada05d35e20eb6b8ac4ad8", "fileid": "cde3e06e1e85240ff41c324e9fa0dbc7698407f8d4be66051327de4a1b4c2439", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/eltoulemonde/actions/runs/26156499395" }, { "r": "4.5.3", "os": "win", "version": "1.1.2", "date": "2026-05-20T10:27:58.000Z", "commit": "5748e2dd552e449302ada05d35e20eb6b8ac4ad8", "fileid": "c4afb84bd64f1be3beccc2281f41440474668e9ce16444780da9ced739ffe6e2", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/eltoulemonde/actions/runs/26156499395" }, { "r": "4.6.0", "os": "win", "version": "1.1.2", "date": "2026-05-20T10:27:59.000Z", "commit": "5748e2dd552e449302ada05d35e20eb6b8ac4ad8", "fileid": "86d721563152f74e9aa8ef688c1fba3b89a8da7345c8a680c4b01e7135a66425", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/eltoulemonde/actions/runs/26156499395" }, { "r": "4.6.0", "os": "wasm", "version": "1.1.2", "date": "2026-06-02T13:09:24.000Z", "commit": "5748e2dd552e449302ada05d35e20eb6b8ac4ad8", "fileid": "36ebdb4626e4b26465bf7b61d1f7d57a91ea1f7eba4a2c52fba366aafe3f832e", "status": "success", "buildurl": "https://github.com/r-universe/eltoulemonde/actions/runs/26156499395" } ] }