{ "_id": "6a1973a6acfb0bcc41defab2", "Package": "representr", "Type": "Package", "Title": "Create Representative Records After Entity Resolution", "Version": "0.1.6", "Authors@R": "c(person(\"Andee\", \"Kaplan\", email = \"andee.kaplan@colostate.edu\",\nrole = c(\"aut\", \"cre\")),\nperson(\"Brenda\", \"Betancourt\", role = \"aut\"),\nperson(\"Rebecca C.\", \"Steorts\", email = \"beka@stat.duke.edu\", role = c(\"aut\")))", "Description": "An implementation of Kaplan, Betancourt, Steorts (2022)\n that creates representative\nrecords for use in downstream tasks after entity resolution is\nperformed. Multiple methods for creating the representative\nrecords (data sets) are provided.", "License": "GPL-3", "Encoding": "UTF-8", "LazyData": "true", "RoxygenNote": "7.3.3", "VignetteBuilder": "knitr", "Repository": "https://cleanzr.r-universe.dev", "Date/Publication": "2026-01-29 17:57:31 UTC", "RemoteUrl": "https://github.com/cleanzr/representr", "RemoteRef": "HEAD", "RemoteSha": "1bce511c3944e1c02ac4224108320da7cb80f291", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-05-29 09:36:29 UTC", "User": "root" }, "Author": "Andee Kaplan [aut, cre],\nBrenda Betancourt [aut],\nRebecca C. Steorts [aut]", "Maintainer": "Andee Kaplan ", "MD5sum": "decb339cf0b60655fbedc4994052c7cd", "_user": "cleanzr", "_type": "src", "_file": "representr_0.1.6.tar.gz", "_fileid": "ddad80f69cfb001c20828734dc660f9891422dc2e5824e83e7162a438b56b13c", "_filesize": 1144777, "_sha256": "ddad80f69cfb001c20828734dc660f9891422dc2e5824e83e7162a438b56b13c", "_created": "2026-05-29T09:36:29.000Z", "_published": "2026-05-29T11:08:22.911Z", "_distro": "noble", "_jobs": [ { "job": 78475799855, "time": 176, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "7287722252" }, { "job": 78475799809, "time": 181, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7287723171" }, { "job": 78475799850, "time": 176, "config": "linux-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7287722407" }, { "job": 78475799909, "time": 171, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7287720594" }, { "job": 78475799858, "time": 149, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7289236165" }, { "job": 78475799820, "time": 411, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "7287976231" }, { "job": 78475799875, "time": 139, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7289238661" }, { "job": 78475799837, "time": 361, "config": "macos-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7287939112" }, { "job": 78475223715, "time": 229, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7287668375" }, { "job": 78475799866, "time": 113, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7287702914" }, { "job": 78475799824, "time": 162, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7287718195" }, { "job": 78475799859, "time": 145, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7287712521" }, { "job": 78475799842, "time": 255, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7287745882" } ], "_buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26629704235", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/cleanzr/representr", "_commit": { "id": "1bce511c3944e1c02ac4224108320da7cb80f291", "author": "Andee Kaplan ", "committer": "Andee Kaplan ", "message": "update news\n", "time": 1769709451 }, "_maintainer": { "name": "Andee Kaplan", "email": "andee.kaplan@colostate.edu", "login": "andeek", "description": "", "uuid": 2414427 }, "_registered": true, "_dependencies": [ { "package": "Rcpp", "role": "LinkingTo" }, { "package": "doParallel", "role": "Imports" }, { "package": "foreach", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "Rcpp", "role": "Imports" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "ggplot2", "role": "Suggests" } ], "_owner": "cleanzr", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-05", "n": 3 } ], "_tags": [ { "name": "v0.1.6", "date": "2026-01-29" } ], "_topics": [ "downstream-tasks", "post-linkage-analysis", "record-linkage", "cpp" ], "_stars": 10, "_contributors": [ { "user": "andeek", "count": 56, "uuid": 2414427 }, { "user": "resteorts", "count": 9, "uuid": 4843162 } ], "_userbio": { "uuid": 55656800, "type": "organization", "name": "cleanzr" }, "_downloads": { "count": 230, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/representr" }, "_devurl": "https://github.com/cleanzr/representr", "_searchresults": 13, "_rbuild": "4.6.0", "_assets": [ "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", "extra/representr.html", "manual.pdf" ], "_homeurl": "https://github.com/cleanzr/representr", "_realowner": "cleanzr", "_cranurl": true, "_releases": [ { "version": "0.1.0", "date": "2020-10-17" }, { "version": "0.1.1", "date": "2020-10-20" }, { "version": "0.1.2", "date": "2021-07-27" }, { "version": "0.1.3", "date": "2022-02-04" }, { "version": "0.1.4", "date": "2022-10-19" }, { "version": "0.1.5", "date": "2023-09-05" }, { "version": "0.1.6", "date": "2026-01-29" } ], "_exports": [ "clust_composite", "clust_proto_minimax", "clust_proto_random", "dist_binary", "dist_col_type", "dist_col_type_slow", "emp_kl_div", "pp_weights", "represent", "within_category_compare_cpp" ], "_datasets": [ { "name": "identity.rl_reg1", "title": "500 records suitable for record linkage with additional regression variables", "object": "identity.rl_reg1", "class": [ "integer" ], "fields": [], "table": false, "tojson": true }, { "name": "identity.rl_reg2", "title": "500 records suitable for record linkage with additional regression variables", "object": "identity.rl_reg2", "class": [ "integer" ], "fields": [], "table": false, "tojson": true }, { "name": "identity.rl_reg5", "title": "500 records suitable for record linkage with additional regression variables", "object": "identity.rl_reg5", "class": [ "integer" ], "fields": [], "table": false, "tojson": true }, { "name": "linkage.rl", "title": "500 records suitable for record linkage with additional regression variables", "object": "linkage.rl", "class": [ "matrix", "array" ], "fields": {}, "rows": 100000, "table": true, "tojson": true }, { "name": "rl_reg1", "title": "500 records suitable for record linkage with additional regression variables", "object": "rl_reg1", "class": [ "data.frame" ], "fields": [ "fname", "lname", "bm", "bd", "by", "sex", "education", "income", "bp" ], "rows": 500, "table": true, "tojson": true }, { "name": "rl_reg2", "title": "500 records suitable for record linkage with additional regression variables", "object": "rl_reg2", "class": [ "data.frame" ], "fields": [ "fname", "lname", "bm", "bd", "by", "sex", "education", "income", "bp" ], "rows": 500, "table": true, "tojson": true }, { "name": "rl_reg5", "title": "500 records suitable for record linkage with additional regression variables", "object": "rl_reg5", "class": [ "data.frame" ], "fields": [ "fname", "lname", "bm", "bd", "by", "sex", "education", "income", "bp" ], "rows": 500, "table": true, "tojson": true } ], "_help": [ { "page": "clust_composite", "title": "Composite record from a cluster using a weighted average of each column values.", "topics": [ "clust_composite" ] }, { "page": "clust_proto_random", "title": "Prototype record from a cluster.", "topics": [ "clust_proto_minimax", "clust_proto_random", "maxmin_compare", "random_compare", "within_category_compare" ] }, { "page": "dist_binary", "title": "The distance between two records", "topics": [ "dist_binary", "dist_col_type_slow" ] }, { "page": "dist_col_type", "title": "dist_col_type Inner column type record distance function", "topics": [ "dist_col_type" ] }, { "page": "emp_kl_div", "title": "Calculate the empirical KL divergence for a representative dataset as compared to the true dataset", "topics": [ "emp_kl_div" ] }, { "page": "pp_weights", "title": "Get posterior weights for each record post record-linkage using posterior prototyping.", "topics": [ "pp_weights" ] }, { "page": "represent", "title": "Create a representative dataset post record-linkage.", "topics": [ "represent" ] }, { "page": "representr", "title": "representr: A package for creating representative records post-record linkage.", "topics": [ "representr-package", "representr" ] }, { "page": "rl_reg1", "title": "500 records suitable for record linkage with additional regression variables", "topics": [ "identity.rl_reg1", "identity.rl_reg2", "identity.rl_reg5", "linkage.rl", "rl_reg1", "rl_reg2", "rl_reg5" ] }, { "page": "within_category_compare_cpp", "title": "within_category_compare_cpp Inner column type record distance function", "topics": [ "within_category_compare_cpp" ] } ], "_readme": "https://github.com/cleanzr/representr/raw/HEAD/README.md", "_rundeps": [ "cli", "codetools", "doParallel", "dplyr", "foreach", "generics", "glue", "iterators", "lifecycle", "magrittr", "pillar", "pkgconfig", "R6", "Rcpp", "rlang", "tibble", "tidyselect", "utf8", "vctrs", "withr" ], "_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" } ], "_vignettes": [ { "source": "representr.Rmd", "filename": "representr.html", "title": "Prototyping with representr", "author": "Andee Kaplan and Rebecca C. Steorts", "engine": "knitr::rmarkdown", "headings": [ "Background and Motivating Example", "Record linkage", "The Downstream Task", "Prototyping methods", "Random Prototyping", "Minimax Prototyping", "Composite Records", "Posterior Prototyping", "Evaluation", "References" ], "created": "2018-10-01 20:58:03", "modified": "2021-07-27 16:29:12", "commits": 11 } ], "_score": 4.812913356642856, "_indexed": true, "_nocasepkg": "representr", "_universes": [ "cleanzr", "andeek" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.6", "date": "2026-05-29T09:39:01.000Z", "distro": "noble", "arch": "aarch64", "commit": "1bce511c3944e1c02ac4224108320da7cb80f291", "fileid": "45a259bfefc8757e3b8bb7c1af3b24361b50ca192418796291586417d8696dda", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26629704235" }, { "r": "4.7.0", "os": "linux", "version": "0.1.6", "date": "2026-05-29T09:38:55.000Z", "distro": "noble", "arch": "x86_64", "commit": "1bce511c3944e1c02ac4224108320da7cb80f291", "fileid": "2a516077c0da449d943c4e14677044bca1de4fc36449675fd1b4a71d127aff4c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26629704235" }, { "r": "4.6.0", "os": "linux", "version": "0.1.6", "date": "2026-05-29T09:39:02.000Z", "distro": "noble", "arch": "aarch64", "commit": "1bce511c3944e1c02ac4224108320da7cb80f291", "fileid": "a7b120a459e3097735f93c4cc9bdbdb757a6ed9221936b3598750b8efc865a4e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26629704235" }, { "r": "4.6.0", "os": "linux", "version": "0.1.6", "date": "2026-05-29T09:38:47.000Z", "distro": "noble", "arch": "x86_64", "commit": "1bce511c3944e1c02ac4224108320da7cb80f291", "fileid": "f0d8b8f48f9efcdc393f3e5e1de013f841845f894fc772bcbfc71cf0fc57495c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26629704235" }, { "r": "4.5.3", "os": "mac", "version": "0.1.6", "date": "2026-05-29T11:06:47.000Z", "arch": "aarch64", "commit": "1bce511c3944e1c02ac4224108320da7cb80f291", "fileid": "d1d7a5e018a7c6f57bf8f5bc1b2dfeaa968e0541c9c1b60ecbc74106621d8c5b", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26629704235" }, { "r": "4.5.3", "os": "mac", "version": "0.1.6", "date": "2026-05-29T09:51:55.000Z", "arch": "x86_64", "commit": "1bce511c3944e1c02ac4224108320da7cb80f291", "fileid": "b6d01ebed5fefcc9e16a3a025c6c8f18f27672e5b4d04c7e7df5e45ac87aae51", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26629704235" }, { "r": "4.6.0", "os": "mac", "version": "0.1.6", "date": "2026-05-29T11:07:03.000Z", "arch": "aarch64", "commit": "1bce511c3944e1c02ac4224108320da7cb80f291", "fileid": "8d20050a7d16cc1fba2af44c8e194428b3e44e8c614546079d619a49bae4a0a0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26629704235" }, { "r": "4.6.0", "os": "mac", "version": "0.1.6", "date": "2026-05-29T09:49:51.000Z", "arch": "x86_64", "commit": "1bce511c3944e1c02ac4224108320da7cb80f291", "fileid": "07f02d371744a6ee5b6cee21fb6bdb3f576ff5135ac6d0ee5de5f8b7d6f7c595", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26629704235" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.6", "date": "2026-05-29T09:38:45.000Z", "arch": "emscripten", "commit": "1bce511c3944e1c02ac4224108320da7cb80f291", "fileid": "da94a6e85d76d16c061760db60bc51a53b2962539b10633f63d416dbe3bc52cd", "status": "success", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26629704235" }, { "r": "4.7.0", "os": "win", "version": "0.1.6", "date": "2026-05-29T09:38:13.000Z", "arch": "x86_64", "commit": "1bce511c3944e1c02ac4224108320da7cb80f291", "fileid": "8a2e1aac79c45936f24e571d16bd9c2149fdf7b311d625bd52a6b5c8b23126ef", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26629704235" }, { "r": "4.5.3", "os": "win", "version": "0.1.6", "date": "2026-05-29T09:37:58.000Z", "arch": "x86_64", "commit": "1bce511c3944e1c02ac4224108320da7cb80f291", "fileid": "9877f1e8f38f3d684092593a5bdd2d14bef54ab6c4d9ef4c5ab81387d66b3300", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26629704235" }, { "r": "4.6.0", "os": "win", "version": "0.1.6", "date": "2026-05-29T09:39:14.000Z", "arch": "x86_64", "commit": "1bce511c3944e1c02ac4224108320da7cb80f291", "fileid": "b5fe57014c75f4a5bb7d4bde619a85e5b5a1d8e1f3ca9571d2e3f83533a031e3", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26629704235" } ] }