{ "_id": "6a1b3dbf1d7bb097a0a10574", "Package": "autodb", "Title": "Automatic Database Normalisation for Data Frames", "Version": "3.2.4.9000", "Authors@R": "person(\n\"Mark\",\n\"Webster\",\nemail = \"markwebster204@yahoo.co.uk\",\nrole = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0002-3351-0686\")\n)", "Description": "Automatic normalisation of a data frame to third normal\nform, with the intention of easing the process of data\ncleaning. (Usage to design your actual database for you is not\nadvised.) Originally inspired by the 'AutoNormalize' library\nfor 'Python' by 'Alteryx'\n(), with various\nchanges and improvements. Automatic discovery of functional or\napproximate dependencies, normalisation based on those, and\nplotting of the resulting \"database\" via 'Graphviz', with\noptions to exclude some attributes at discovery time, or remove\ndiscovered dependencies at normalisation time.", "License": "BSD_3_clause + file LICENSE", "Encoding": "UTF-8", "Language": "en-GB", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.3.3", "Config/testthat/edition": "3", "VignetteBuilder": "knitr", "LazyData": "true", "URL": "https://charnelmouse.github.io/autodb/,\nhttps://github.com/CharnelMouse/autodb", "BugReports": "https://github.com/CharnelMouse/autodb/issues", "Repository": "https://charnelmouse.r-universe.dev", "Date/Publication": "2026-05-30 19:06:16 UTC", "RemoteUrl": "https://github.com/charnelmouse/autodb", "RemoteRef": "HEAD", "RemoteSha": "f79870da5b0fa44fb89ed49cb03be7d890e2060f", "NeedsCompilation": "no", "Packaged": { "Date": "2026-05-30 19:34:55 UTC", "User": "root" }, "Author": "Mark Webster [aut, cre] (ORCID:\n)", "Maintainer": "Mark Webster ", "MD5sum": "00163af12e6737d057b63a8cf6bf19ae", "_user": "charnelmouse", "_type": "src", "_file": "autodb_3.2.4.9000.tar.gz", "_fileid": "6fe4435ea7d91073a677910f4dfceaf052d791c29371c5305203623d2e0a7c9d", "_filesize": 707227, "_sha256": "6fe4435ea7d91073a677910f4dfceaf052d791c29371c5305203623d2e0a7c9d", "_created": "2026-05-30T19:34:55.000Z", "_published": "2026-05-30T19:42:55.000Z", "_distro": "noble", "_jobs": [ { "job": 78672618456, "time": 408, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "7310830805" }, { "job": 78672618447, "time": 410, "config": "linux-release-x86_64", "r": "4.6.0", "check": "NOTE", "artifact": "7310830970" }, { "job": 78672618446, "time": 282, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "NOTE", "artifact": "7310814115" }, { "job": 78672618453, "time": 295, "config": "macos-release-arm64", "r": "4.6.0", "check": "NOTE", "artifact": "7310816067" }, { "job": 78672382989, "time": 249, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7310788592" }, { "job": 78672618439, "time": 112, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7310800604" }, { "job": 78672618466, "time": 448, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "7310835125" }, { "job": 78672618467, "time": 387, "config": "windows-oldrel", "r": "4.5.3", "check": "NOTE", "artifact": "7310828585" }, { "job": 78672618492, "time": 429, "config": "windows-release", "r": "4.6.0", "check": "NOTE", "artifact": "7310833066" } ], "_buildurl": "https://github.com/r-universe/charnelmouse/actions/runs/26692904418", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/charnelmouse/autodb", "_commit": { "id": "f79870da5b0fa44fb89ed49cb03be7d890e2060f", "author": "Mark Webster ", "committer": "Mark Webster ", "message": "Update NEWS\n", "time": 1780167976 }, "_maintainer": { "name": "Mark Webster", "email": "markwebster204@yahoo.co.uk", "login": "charnelmouse", "description": "", "uuid": 58379326, "orcid": "0000-0002-3351-0686" }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.1.0", "role": "Depends" }, { "package": "rlang", "role": "Suggests" }, { "package": "spelling", "role": "Suggests" }, { "package": "DiagrammeR", "version": ">= 1.0.7", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.3.0", "role": "Suggests" }, { "package": "R.utils", "version": ">= 2.11.0", "role": "Suggests" }, { "package": "hedgehog", "version": ">= 0.1", "role": "Suggests" }, { "package": "tibble", "version": ">= 3.2.1", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" } ], "_owner": "charnelmouse", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2025-22", "n": 19 }, { "week": "2025-23", "n": 43 }, { "week": "2025-24", "n": 25 }, { "week": "2025-25", "n": 8 }, { "week": "2025-26", "n": 11 }, { "week": "2025-33", "n": 3 }, { "week": "2025-34", "n": 4 }, { "week": "2025-38", "n": 26 }, { "week": "2025-40", "n": 1 }, { "week": "2025-41", "n": 3 }, { "week": "2025-43", "n": 2 }, { "week": "2025-44", "n": 7 }, { "week": "2025-45", "n": 9 }, { "week": "2025-46", "n": 6 }, { "week": "2025-50", "n": 10 }, { "week": "2025-51", "n": 18 }, { "week": "2026-03", "n": 6 }, { "week": "2026-04", "n": 5 }, { "week": "2026-05", "n": 5 }, { "week": "2026-06", "n": 13 }, { "week": "2026-07", "n": 3 }, { "week": "2026-08", "n": 12 }, { "week": "2026-09", "n": 11 }, { "week": "2026-11", "n": 3 }, { "week": "2026-12", "n": 2 }, { "week": "2026-14", "n": 13 }, { "week": "2026-15", "n": 9 }, { "week": "2026-16", "n": 8 }, { "week": "2026-17", "n": 4 }, { "week": "2026-21", "n": 3 }, { "week": "2026-22", "n": 10 } ], "_tags": [ { "name": "v3.0.0", "date": "2025-06-25" }, { "name": "v3.1.0", "date": "2025-09-18" }, { "name": "v3.2.0", "date": "2025-11-07" }, { "name": "v3.2.1", "date": "2025-11-08" }, { "name": "v3.2.2", "date": "2025-11-08" }, { "name": "v3.2.3", "date": "2025-11-08" }, { "name": "v3.2.4", "date": "2025-11-15" } ], "_topics": [ "functional-dependency-discovery" ], "_stars": 10, "_contributors": [ { "user": "charnelmouse", "count": 1279, "uuid": 58379326 }, { "user": "hadley", "count": 1, "uuid": 4196 } ], "_userbio": { "uuid": 58379326, "type": "user", "name": "Mark Webster" }, "_downloads": { "count": 182, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/autodb" }, "_devurl": "https://github.com/charnelmouse/autodb", "_pkgdown": "https://charnelmouse.github.io/autodb/", "_searchresults": 32, "_rbuild": "4.6.0", "_assets": [ "extra/autodb.html", "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", "manual.pdf" ], "_homeurl": "https://github.com/charnelmouse/autodb", "_realowner": "charnelmouse", "_cranurl": true, "_releases": [ { "version": "2.3.1", "date": "2025-03-22" }, { "version": "3.0.0", "date": "2025-06-25" }, { "version": "3.1.0", "date": "2025-09-18" }, { "version": "3.2.4", "date": "2025-11-17" } ], "_exports": [ "attrs", "attrs_order", "attrs_order<-", "attrs<-", "autodb", "autoref", "create", "d2", "database", "database_schema", "decompose", "dependant", "dependant<-", "detset", "detset<-", "df_anyDuplicated", "df_duplicated", "df_equiv", "df_rbind", "df_records", "df_unique", "discover", "discover_keys", "functional_dependency", "gv", "insert", "keys", "keys<-", "merge_empty_keys", "merge_schemas", "normalise", "records", "records<-", "reduce", "references", "references<-", "rejoin", "relation", "relation_schema", "remove_extraneous", "rename_attrs", "subrelations", "subschemas", "synthesise" ], "_datasets": [ { "name": "nudge", "title": "Nudge meta-analysis data", "object": "nudge", "class": [ "data.frame" ], "fields": [ "publication_id", "study_id", "es_id", "reference", "title", "year", "location", "domain", "intervention_category", "intervention_technique", "type_experiment", "population", "n_study", "n_comparison", "n_control", "n_intervention", "binary_outcome", "mean_control", "sd_control", "mean_intervention", "sd_intervention", "cohens_d", "variance_d", "approximation", "wansink" ], "rows": 447, "table": true, "tojson": true } ], "_help": [ { "page": "attrs", "title": "Relational data attributes", "topics": [ "attrs", "attrs<-" ] }, { "page": "attrs_order", "title": "Relational data attribute order", "topics": [ "attrs_order", "attrs_order<-" ] }, { "page": "autodb", "title": "Create a normalised database from a data frame", "topics": [ "autodb" ] }, { "page": "autoref", "title": "Add foreign key references to a normalised database", "topics": [ "autoref" ] }, { "page": "create", "title": "Create instance of a schema", "topics": [ "create" ] }, { "page": "d2", "title": "Generate D2 input text to plot objects", "topics": [ "d2" ] }, { "page": "d2.data.frame", "title": "Generate D2 input text to plot a data frame", "topics": [ "d2.data.frame" ] }, { "page": "d2.database", "title": "Generate D2 input text to plot databases", "topics": [ "d2.database" ] }, { "page": "d2.database_schema", "title": "Generate D2 input text to plot database schemas", "topics": [ "d2.database_schema" ] }, { "page": "d2.relation", "title": "Generate D2 input text to plot relations", "topics": [ "d2.relation" ] }, { "page": "d2.relation_schema", "title": "Generate D2 input text to plot relation schemas", "topics": [ "d2.relation_schema" ] }, { "page": "database", "title": "Databases", "topics": [ "database" ] }, { "page": "database_schema", "title": "Database schemas", "topics": [ "database_schema" ] }, { "page": "decompose", "title": "Decompose a data frame based on given normalised dependencies", "topics": [ "decompose" ] }, { "page": "dependant", "title": "Dependants", "topics": [ "dependant", "dependant<-" ] }, { "page": "detset", "title": "Determinant sets", "topics": [ "detset", "detset<-" ] }, { "page": "df_duplicated", "title": "Determine Duplicate Elements", "topics": [ "df_anyDuplicated", "df_duplicated", "df_records", "df_unique" ] }, { "page": "df_equiv", "title": "Test data frames for equivalence under row reordering", "topics": [ "df_equiv" ] }, { "page": "df_rbind", "title": "Combine R Objects by Rows or Columns", "topics": [ "df_rbind" ] }, { "page": "discover", "title": "Dependency discovery with DFD", "topics": [ "discover" ] }, { "page": "discover_keys", "title": "Key discovery with MCSS", "topics": [ "discover_keys" ] }, { "page": "functional_dependency", "title": "Functional dependency vectors", "topics": [ "functional_dependency" ] }, { "page": "gv", "title": "Generate Graphviz input text to plot objects", "topics": [ "gv" ] }, { "page": "gv.data.frame", "title": "Generate Graphviz input text to plot a data frame", "topics": [ "gv.data.frame" ] }, { "page": "gv.database", "title": "Generate Graphviz input text to plot databases", "topics": [ "gv.database" ] }, { "page": "gv.database_schema", "title": "Generate Graphviz input text to plot database schemas", "topics": [ "gv.database_schema" ] }, { "page": "gv.relation", "title": "Generate Graphviz input text to plot relations", "topics": [ "gv.relation" ] }, { "page": "gv.relation_schema", "title": "Generate Graphviz input text to plot relation schemas", "topics": [ "gv.relation_schema" ] }, { "page": "insert", "title": "Insert data", "topics": [ "insert" ] }, { "page": "keys", "title": "Relational data keys", "topics": [ "keys", "keys<-" ] }, { "page": "merge_empty_keys", "title": "Merge relation schemas with empty keys", "topics": [ "merge_empty_keys" ] }, { "page": "merge_schemas", "title": "Merge relation schemas in given pairs", "topics": [ "merge_schemas" ] }, { "page": "normalise", "title": "Create normalised database schemas from functional dependencies", "topics": [ "normalise" ] }, { "page": "nudge", "title": "Nudge meta-analysis data", "topics": [ "nudge" ] }, { "page": "records", "title": "Relational data records", "topics": [ "records", "records<-" ] }, { "page": "reduce", "title": "Remove relations not linked to the main relations", "topics": [ "reduce" ] }, { "page": "reduce.database", "title": "Remove database relations not linked to the main relations", "topics": [ "reduce.database" ] }, { "page": "reduce.database_schema", "title": "Remove database schema relations not linked to the given relations", "topics": [ "reduce.database_schema" ] }, { "page": "references", "title": "Schema references", "topics": [ "references", "references<-" ] }, { "page": "rejoin", "title": "Join a database into a data frame", "topics": [ "rejoin" ] }, { "page": "relation", "title": "Relation vectors", "topics": [ "relation" ] }, { "page": "relation_schema", "title": "Relation schema vectors", "topics": [ "relation_schema" ] }, { "page": "remove_extraneous", "title": "Remove extraneous components from functional dependencies", "topics": [ "remove_extraneous" ] }, { "page": "rename_attrs", "title": "Rename relational data attributes", "topics": [ "rename_attrs" ] }, { "page": "subrelations", "title": "Database subrelations", "topics": [ "subrelations" ] }, { "page": "subschemas", "title": "Schema subschemas", "topics": [ "subschemas" ] }, { "page": "synthesise", "title": "Synthesise relation schemas from functional dependencies", "topics": [ "synthesise" ] } ], "_readme": "https://github.com/charnelmouse/autodb/raw/HEAD/README.md", "_rundeps": [], "_vignettes": [ { "source": "nudge.Rmd", "filename": "nudge.html", "title": "A larger example: the nudge dataset", "engine": "knitr::rmarkdown", "headings": [ "Initial decomposition", "Simplifying the search result", "Fixing the data", "Simplifying further with search filters", "How not to remove spurious structure", "Alternative approach: hierarchical limits" ], "created": "2025-10-10 20:59:05", "modified": "2025-11-08 00:04:44", "commits": 4 }, { "source": "null.Rmd", "filename": "null.html", "title": "Handling missing values", "engine": "knitr::rmarkdown", "headings": [ "Missing values", "Decomposing to remove missing values", "Structure conditional on value presence" ], "created": "2025-10-10 20:59:05", "modified": "2025-11-08 00:04:44", "commits": 4 }, { "source": "limits.Rmd", "filename": "limits.html", "title": "Limitations", "engine": "knitr::rmarkdown", "headings": [ "Meaningful duplicate rows / row order", "Value-based constraints", "Semantic types", "Table merges don't fix issues with merge.data.frame", "Synthesis doesn't minimise relation key count", "Normal forms are't all there is to database design" ], "created": "2025-10-10 20:59:05", "modified": "2025-11-08 00:04:44", "commits": 5 }, { "source": "nest.Rmd", "filename": "nest.html", "title": "Nested data", "engine": "knitr::rmarkdown", "headings": [], "created": "2026-03-15 10:08:15", "modified": "2026-03-15 10:08:15", "commits": 1 }, { "source": "plans.Rmd", "filename": "plans.html", "title": "Planned improvements", "engine": "knitr::rmarkdown", "headings": [ "Views for BCNF and connected reference chains", "Boyes-Codd Normal Form", "Reference chains", "Views as a solution", "Proper handling of nullable data", "Handling of duplicate records" ], "created": "2025-10-10 20:59:05", "modified": "2025-11-08 00:42:18", "commits": 6 }, { "source": "autodb.Rmd", "filename": "autodb.html", "title": "Using autodb", "engine": "knitr::rmarkdown", "headings": [ "Terminology", "Motivation", "Database normalisation", "For data cleaning", "Not for database design", "To third normal form", "Individual steps", "Finding functional dependencies", "Normalisation", "Adding foreign key references", "Decomposing the original relation", "Rejoining a database back into a data frame", "Tuning detection and normalisation", "Avoidable attributes" ], "created": "2022-11-29 23:57:05", "modified": "2025-11-08 00:23:20", "commits": 53 } ], "_score": 7.473632926873842, "_indexed": true, "_nocasepkg": "autodb", "_universes": [ "charnelmouse" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "3.2.4.9000", "date": "2026-05-30T19:37:52.000Z", "distro": "noble", "commit": "f79870da5b0fa44fb89ed49cb03be7d890e2060f", "fileid": "a5e88b226f2fcea10c8f8bf0668c8b79ebdd7b98fe694a16417ea12b9d1bc1ad", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/charnelmouse/actions/runs/26692904418" }, { "r": "4.6.0", "os": "linux", "version": "3.2.4.9000", "date": "2026-05-30T19:37:52.000Z", "distro": "noble", "commit": "f79870da5b0fa44fb89ed49cb03be7d890e2060f", "fileid": "55f933d8111592af84bd7ce574f7650d9ec33e4c6a554cf607314edcfeeede57", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/charnelmouse/actions/runs/26692904418" }, { "r": "4.5.3", "os": "mac", "version": "3.2.4.9000", "date": "2026-05-30T19:37:03.000Z", "commit": "f79870da5b0fa44fb89ed49cb03be7d890e2060f", "fileid": "99ee3bdd7f7a8e3b7302bd81f0180a61fe8aa0c40f0839cde75847cc4ff9945b", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/charnelmouse/actions/runs/26692904418" }, { "r": "4.6.0", "os": "mac", "version": "3.2.4.9000", "date": "2026-05-30T19:37:03.000Z", "commit": "f79870da5b0fa44fb89ed49cb03be7d890e2060f", "fileid": "b5e27cc99d3d20a75c87e40283a793bd95ba96a081b9c78ac08822b0c089cfe3", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/charnelmouse/actions/runs/26692904418" }, { "r": "4.6.0", "os": "wasm", "version": "3.2.4.9000", "date": "2026-05-30T19:37:06.000Z", "commit": "f79870da5b0fa44fb89ed49cb03be7d890e2060f", "fileid": "a963f0d0b0e68b34080553138925ffabb38081eabd91e821c8c9295fd12408b7", "status": "success", "buildurl": "https://github.com/r-universe/charnelmouse/actions/runs/26692904418" }, { "r": "4.7.0", "os": "win", "version": "3.2.4.9000", "date": "2026-05-30T19:36:10.000Z", "commit": "f79870da5b0fa44fb89ed49cb03be7d890e2060f", "fileid": "f44b2ee527633ddfb9d285f9efd99f8b4d4876a1c49bb1707e3fc5dec0a9583f", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/charnelmouse/actions/runs/26692904418" }, { "r": "4.5.3", "os": "win", "version": "3.2.4.9000", "date": "2026-05-30T19:36:06.000Z", "commit": "f79870da5b0fa44fb89ed49cb03be7d890e2060f", "fileid": "bf56ae80cd09420d07edea9a0fdbdf2774a6eb81cf70042097e39cf67002f2a8", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/charnelmouse/actions/runs/26692904418" }, { "r": "4.6.0", "os": "win", "version": "3.2.4.9000", "date": "2026-05-30T19:36:39.000Z", "commit": "f79870da5b0fa44fb89ed49cb03be7d890e2060f", "fileid": "2f517a75707360821b342e287169c7fcca879d0d452e22e3202a9941ab020d97", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/charnelmouse/actions/runs/26692904418" } ] }