{ "_id": "6a155d88acfb0bcc41d5fa15", "Package": "fedmatch", "Title": "Fast, Flexible, and User-Friendly Record Linkage Methods", "Version": "2.1.0", "Authors@R": "c(person(\"Melanie\", \"Friedrichs\", email = \"melanie.r.friedrichs@gmail.com\", role = c(\"aut\")),\nperson(\"Chris\", \"Webster\", email = \"chris0webster@gmail.com\", role = c(\"aut\", \"cre\")),\nperson(\"Blake\", \"Marsh\", email = \"blake.marsh@kc.frb.org\", role = c(\"aut\")),\nperson(\"Jacob\", \"Dice\", email = \"Jacob.Dice@kc.frb.org\", role = c(\"aut\")),\nperson(\"Seung\", \"Lee\", email = \"seung.j.lee@frb.gov\", role = c(\"aut\")))", "Description": "Provides a flexible set of tools for matching two\nun-linked data sets. 'fedmatch' allows for three ways to match\ndata: exact matches, fuzzy matches, and multi-variable matches.\nIt also allows an easy combination of these three matches via\nthe tier matching function.", "License": "MIT + file LICENSE", "Encoding": "UTF-8", "LazyData": "true", "RoxygenNote": "7.3.2", "VignetteBuilder": "knitr", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-05-26 08:41:08 UTC", "User": "root" }, "Author": "Melanie Friedrichs [aut], Chris Webster [aut, cre], Blake Marsh\n[aut], Jacob Dice [aut], Seung Lee [aut]", "Maintainer": "Chris Webster ", "Repository": "https://cran.r-universe.dev", "Date/Publication": "2025-01-31 22:40:02 UTC", "RemoteUrl": "https://github.com/cran/fedmatch", "RemoteRef": "HEAD", "RemoteSha": "3aae39ec12a66a5484d792e8ba1b2397a350d4f4", "MD5sum": "0f68bd94e069178934147335da5f1395", "_user": "cran", "_type": "src", "_file": "fedmatch_2.1.0.tar.gz", "_fileid": "3f020b1bb093c18ca6507332db5d5fdfcde093ad3ea1676a2e8e57e09af78cd5", "_filesize": 270029, "_sha256": "3f020b1bb093c18ca6507332db5d5fdfcde093ad3ea1676a2e8e57e09af78cd5", "_created": "2026-05-26T08:41:08.000Z", "_published": "2026-05-26T08:44:56.269Z", "_distro": "noble", "_jobs": [ { "job": 77838102056, "time": 179, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "7212620481" }, { "job": 77838102008, "time": 156, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7212612628" }, { "job": 77838101995, "time": 138, "config": "linux-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7212606944" }, { "job": 77838102028, "time": 156, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7212612304" }, { "job": 77837574555, "time": 201, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7212560754" }, { "job": 77838102009, "time": 139, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7212607362" } ], "_buildurl": "https://github.com/r-universe/cran/actions/runs/26441701572", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/cran/fedmatch", "_commit": { "id": "3aae39ec12a66a5484d792e8ba1b2397a350d4f4", "author": "Chris Webster ", "committer": "cran-robot ", "message": "version 2.1.0\n", "time": 1738363202 }, "_maintainer": { "name": "Chris Webster", "email": "chris0webster@gmail.com", "login": "c0webster", "description": "", "uuid": 68300216 }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.5.3", "role": "Depends" }, { "package": "Rcpp", "role": "LinkingTo" }, { "package": "BH", "role": "LinkingTo" }, { "package": "stringdist", "role": "Imports" }, { "package": "SnowballC", "role": "Imports" }, { "package": "stringr", "role": "Imports" }, { "package": "purrr", "role": "Imports" }, { "package": "Rcpp", "role": "Imports" }, { "package": "parallel", "role": "Imports" }, { "package": "forcats", "role": "Imports" }, { "package": "data.table", "role": "Imports" }, { "package": "magrittr", "role": "Imports" }, { "package": "scales", "role": "Imports" }, { "package": "testthat", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" } ], "_owner": "cran", "_selfowned": false, "_usedby": 1, "_updates": [], "_tags": [], "_stars": 1, "_contributors": [ { "user": "c0webster", "count": 7, "uuid": 68300216 } ], "_userbio": { "uuid": 6899542, "type": "organization", "name": "cran", "description": "Unofficial read-only mirror of all CRAN R packages" }, "_downloads": { "count": 889, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/fedmatch" }, "_searchresults": 96, "_topics": [ "cpp", "openmp" ], "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/fedmatch.html", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_realowner": "c0webster", "_cranurl": false, "_releases": [ { "version": "2.0.0", "date": "2021-07-20" }, { "version": "2.0.2", "date": "2021-08-04" }, { "version": "2.0.3", "date": "2021-09-08" }, { "version": "2.0.4", "date": "2021-10-28" }, { "version": "2.0.5", "date": "2021-11-22" }, { "version": "2.0.6", "date": "2024-05-20" }, { "version": "2.1.0", "date": "2025-01-31" } ], "_exports": [ "%>%", "build_clean_settings", "build_corpus", "build_fuzzy_settings", "build_multivar_settings", "build_score_settings", "build_tier", "calculate_weights", "clean_strings", "match_evaluate", "merge_plus", "tier_match", "wgt_jaccard_distance", "word_frequency" ], "_datasets": [ { "name": "articles", "title": "articles", "object": "articles", "class": [ "data.table", "data.frame" ], "fields": [ "article", "replacement" ], "rows": 23, "table": true, "tojson": true }, { "name": "corp_data1", "title": "corp_data1", "object": "corp_data1", "class": [ "data.table", "data.frame" ], "fields": [ "Company", "Country", "State", "SIC", "Revenue", "unique_key_1" ], "rows": 10, "table": true, "tojson": true }, { "name": "corp_data2", "title": "corp_data2", "object": "corp_data2", "class": [ "data.table", "data.frame" ], "fields": [ "Name", "country", "state_code", "SIC_code", "earnings", "unique_key_2" ], "rows": 10, "table": true, "tojson": true }, { "name": "corporate_words", "title": "corporate_words", "object": "corporate_words", "class": [ "data.table", "data.frame" ], "fields": [ "abbr", "long.names" ], "rows": 54, "table": true, "tojson": true }, { "name": "fund_words", "title": "fund_words", "object": "fund_words", "class": [ "data.frame" ], "fields": [ "abbr.", "long.name" ], "rows": 63, "table": true, "tojson": true }, { "name": "sp_char_words", "title": "sp_char_words", "object": "sp_char_words", "class": [ "data.table", "data.frame" ], "fields": [ "character", "replacement" ], "rows": 4, "table": true, "tojson": true }, { "name": "State_FIPS", "title": "State_FIPS", "object": "State_FIPS", "class": [ "data.table", "data.frame" ], "fields": [ "State", "Abbreviation", "FIPS" ], "rows": 55, "table": true, "tojson": true }, { "name": "World_Bank_Codes", "title": "World_Bank_Codes", "object": "World_Bank_Codes", "class": [ "data.table", "data.frame" ], "fields": [ "Country", "World_Bank_Code" ], "rows": 213, "table": true, "tojson": true } ], "_help": [ { "page": "articles", "title": "articles", "topics": [ "articles" ] }, { "page": "build_clean_settings", "title": "Building settings for string cleaning", "topics": [ "build_clean_settings" ] }, { "page": "build_corpus", "title": "Calculate word corpus for weighted jaccard matching", "topics": [ "build_corpus" ] }, { "page": "build_fuzzy_settings", "title": "Build settings for fuzzy matching", "topics": [ "build_fuzzy_settings" ] }, { "page": "build_multivar_settings", "title": "Build settings for multivar matching", "topics": [ "build_multivar_settings" ] }, { "page": "build_score_settings", "title": "Build settings for scoring", "topics": [ "build_score_settings" ] }, { "page": "build_tier", "title": "Build settings for a tier", "topics": [ "build_tier" ] }, { "page": "calculate_weights", "title": "Calculate weights for computing matchscore", "topics": [ "calculate_weights" ] }, { "page": "clean_strings", "title": "String cleaning for easier matching", "topics": [ "clean_strings" ] }, { "page": "corp_data1", "title": "corp_data1", "topics": [ "corp_data1" ] }, { "page": "corp_data2", "title": "corp_data2", "topics": [ "corp_data2" ] }, { "page": "corporate_words", "title": "corporate_words", "topics": [ "corporate_words" ] }, { "page": "fund_words", "title": "fund_words", "topics": [ "fund_words" ] }, { "page": "fuzzy_match", "title": "Use string distances to match on names", "topics": [ "fuzzy_match" ] }, { "page": "match_evaluate", "title": "evaluate a matched dataset", "topics": [ "match_evaluate" ] }, { "page": "merge_plus", "title": "Merge two datasets either by exact, fuzzy, or multivar-based matching", "topics": [ "merge_plus" ] }, { "page": "multivar_match", "title": "Matching by computing multivar_scores based on several variables", "topics": [ "multivar_match" ] }, { "page": "sp_char_words", "title": "sp_char_words", "topics": [ "sp_char_words" ] }, { "page": "State_FIPS", "title": "State_FIPS", "topics": [ "State_FIPS" ] }, { "page": "tier_match", "title": "Perform an iterative match by tier", "topics": [ "tier_match" ] }, { "page": "wgt_jaccard_distance", "title": "Computing Weighted Jaccard Distance", "topics": [ "wgt_jaccard_distance" ] }, { "page": "word_frequency", "title": "Compute frequency of words in a corpus", "topics": [ "word_frequency" ] }, { "page": "World_Bank_Codes", "title": "World_Bank_Codes", "topics": [ "World_Bank_Codes" ] } ], "_readme": "https://github.com/cran/fedmatch/raw/HEAD/README.md", "_rundeps": [ "BH", "cli", "data.table", "farver", "forcats", "glue", "labeling", "lifecycle", "magrittr", "pillar", "pkgconfig", "purrr", "R6", "RColorBrewer", "Rcpp", "rlang", "scales", "SnowballC", "stringdist", "stringi", "stringr", "tibble", "utf8", "vctrs", "viridisLite" ], "_sysdeps": [ { "shlib": "libstdc++", "package": "libstdc++6", "source": "gcc", "version": "14.2.0-4ubuntu2~24.04.1", "name": "c++", "homepage": "http://gcc.gnu.org/", "description": "GNU Standard C++ Library v3" }, { "shlib": "libgomp", "package": "libgomp1", "source": "gcc", "version": "14.2.0-4ubuntu2~24.04.1", "name": "openmp", "homepage": "http://gcc.gnu.org/", "description": "GCC OpenMP (GOMP) support library" } ], "_vignettes": [ { "source": "Fuzzy-matching.Rmd", "filename": "Fuzzy-matching.html", "title": "Fuzzy Matching", "engine": "knitr::rmarkdown", "headings": [ "Intro", "Fuzzy matching theory", "Jaro-Winkler", "Weighted Jaccard Similarity", "Other similarity metrics", "Using fuzzy matching in fedmatch", "Basic Syntax", "The order of which is data1 and which is data2 matters!", "An example - weighted Jaccard match", "Weighted Jaccard Match" ], "created": "2021-07-20 07:40:02", "modified": "2025-01-31 22:40:02", "commits": 7 }, { "source": "Intro-to-fedmatch.Rmd", "filename": "Intro-to-fedmatch.html", "title": "Introduction to fedmatch", "author": "Chris Webster", "engine": "knitr::rmarkdown", "headings": [ "Background", "Name cleaning", "Basics: merge_plus", "Exact matching", "Fuzzy matching", "Multivar matching", "Summary and next steps" ], "created": "2021-07-20 07:40:02", "modified": "2025-01-31 22:40:02", "commits": 3 }, { "source": "Multivar_matching.Rmd", "filename": "Multivar_matching.html", "title": "Multivar Matching", "author": "Chris Webster", "engine": "knitr::rmarkdown", "headings": [ "Background", "Syntax", "Return value", "Calculating weights from a training set", "Using a logit model instead of a linear sum", "Parallelization and saving time" ], "created": "2021-07-20 07:40:02", "modified": "2024-05-21 02:39:22", "commits": 4 }, { "source": "Using-tier-match.Rmd", "filename": "Using-tier-match.html", "title": "Tier Matching", "engine": "knitr::rmarkdown", "headings": [ "Overview", "Syntax" ], "created": "2021-07-20 07:40:02", "modified": "2025-01-31 22:40:02", "commits": 3 }, { "source": "Using-clean-strings.Rmd", "filename": "Using-clean-strings.html", "title": "Using clean_strings", "engine": "knitr::rmarkdown", "headings": [ "Using clean_strings", "sp_char_words", "common_words", "Remove characters and words", "stem" ], "created": "2021-07-20 07:40:02", "modified": "2021-07-20 07:40:02", "commits": 1 } ], "_score": 4.857332496431268, "_indexed": false, "_nocasepkg": "fedmatch", "_universes": [ "cran" ], "_indexurl": "https://c0webster.r-universe.dev/fedmatch", "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "2.1.0", "date": "2026-05-26T08:44:12.000Z", "distro": "noble", "arch": "aarch64", "commit": "3aae39ec12a66a5484d792e8ba1b2397a350d4f4", "fileid": "232583e3c664cb3b9eea8b3f019c7ee8c766e5f53e587363f705176b0980e57a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/26441701572" }, { "r": "4.7.0", "os": "linux", "version": "2.1.0", "date": "2026-05-26T08:43:42.000Z", "distro": "noble", "arch": "x86_64", "commit": "3aae39ec12a66a5484d792e8ba1b2397a350d4f4", "fileid": "c7e9f12a8828a36175c326cfabd3c1af4aac3f19805ecf79ac950d64d36c5421", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/26441701572" }, { "r": "4.6.0", "os": "linux", "version": "2.1.0", "date": "2026-05-26T08:43:31.000Z", "distro": "noble", "arch": "aarch64", "commit": "3aae39ec12a66a5484d792e8ba1b2397a350d4f4", "fileid": "3e7173813ba51d1e14d4490cfab967e15403263e88342a4973b552b4fdf77b7c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/26441701572" }, { "r": "4.6.0", "os": "linux", "version": "2.1.0", "date": "2026-05-26T08:43:42.000Z", "distro": "noble", "arch": "x86_64", "commit": "3aae39ec12a66a5484d792e8ba1b2397a350d4f4", "fileid": "d897e56239a0019250a59a6f7055e7c8ee71e0be0f8f8d225d0674feb7f5a0cd", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/26441701572" }, { "r": "4.6.0", "os": "wasm", "version": "2.1.0", "date": "2026-05-26T08:43:50.000Z", "arch": "emscripten", "commit": "3aae39ec12a66a5484d792e8ba1b2397a350d4f4", "fileid": "d3a1d8b3452bb659768b93c386265ab86dab1dd0820f2f18d8c024c3d17f62c7", "status": "success", "buildurl": "https://github.com/r-universe/cran/actions/runs/26441701572" } ] }