{ "_id": "6aea31fe1e2c7b3a4f533c65", "Package": "klsh", "Type": "Package", "Title": "Blocking for Record Linkage", "Version": "0.1.0", "Authors@R": "person(\"Rebecca\", \"Steorts\", email = \"beka@stat.duke.edu\",\nrole = c(\"aut\", \"cre\"))", "VignetteBuilder": "knitr", "Description": "An implementation of the blocking algorithm KLSH in\nSteorts, Ventura, Sadinle, Fienberg (2014)\n, which is a k-means variant\nof locality sensitive hashing. The method is illustrated with\nexamples and a vignette.", "Encoding": "UTF-8", "License": "GPL-3", "RoxygenNote": "7.1.1.9000", "NeedsCompilation": "no", "Packaged": { "Date": "2026-11-03 19:09:32 UTC", "User": "root" }, "Author": "Rebecca Steorts [aut, cre]", "Maintainer": "Rebecca Steorts ", "Config/pak/sysreqs": "libicu-dev", "Repository": "https://cranhaven.r-universe.dev", "Date/Publication": "2026-11-03 06:02:00 UTC", "RemoteUrl": "https://github.com/cranhaven/cranhaven.r-universe.dev", "RemoteRef": "package/klsh", "RemoteSha": "1599ccdc715e433673b30daa846157a4d139f793", "RemoteSubdir": "klsh", "_user": "cranhaven", "_type": "src", "_file": "klsh_0.1.0.tar.gz", "_fileid": "https://r2.ropensci.org/cfad50027906e7d8e849419634582bfc99b96cb80acd7b292b632f143a28b52c", "_filesize": 198445, "_sha256": "cfad50027906e7d8e849419634582bfc99b96cb80acd7b292b632f143a28b52c", "_expires": "2027-02-11T19:11:57.000Z", "_created": "2026-11-03T19:09:32.000Z", "_published": "2026-11-03T19:11:58.839Z", "_upstream": "https://github.com/cranhaven/cranhaven.r-universe.dev", "_status": "success", "_maintainer": { "name": "Rebecca Steorts", "email": "beka@stat.duke.edu", "login": "resteorts", "description": "\n Assistant Professor, Duke University, Department of Statistical Science\n", "uuid": 4843162 }, "_jobs": [ { "job": 126142797800, "time": 115, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "13263511566" }, { "job": 126142797855, "time": 112, "config": "linux-release-x86_64", "r": "4.6.2", "check": "NOTE", "artifact": "13263675068" }, { "job": 126142797864, "time": 105, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "NOTE", "artifact": "13263540167" }, { "job": 126142797805, "time": 100, "config": "macos-release-arm64", "r": "4.6.2", "check": "NOTE", "artifact": "13261344866" }, { "job": 126139965936, "time": 304, "config": "source", "r": "4.6.2", "check": "OK", "artifact": "13261189724" }, { "job": 126142797928, "time": 92, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "13263615097" }, { "job": 126142798178, "time": 98, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "13261224935" }, { "job": 126142797898, "time": 81, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "NOTE", "artifact": "13262294728" }, { "job": 126142798025, "time": 81, "config": "windows-release-x86_64", "r": "4.6.2", "check": "NOTE", "artifact": "13262818141" } ], "_buildurl": "https://github.com/r-universe/cranhaven/actions/runs/41699785448", "_commit": { "id": "1599ccdc715e433673b30daa846157a4d139f793", "author": "GitHub Action ", "committer": "GitHub Action ", "message": "Add klsh to CRANhaven, because archived on 2026-11-03 06:02:00 +0000\n", "time": 1793685720 }, "_distro": "resolute", "_host": "GitHub-Actions", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.0.2", "role": "Depends" }, { "package": "blink", "role": "Depends" }, { "package": "stats", "role": "Depends" }, { "package": "utils", "role": "Depends" }, { "package": "plyr", "role": "Depends" }, { "package": "Rcpp", "role": "Imports" }, { "package": "stringi", "role": "Imports" }, { "package": "SnowballC", "role": "Imports" }, { "package": "knitr", "role": "Suggests" }, { "package": "ggplot2", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" } ], "_owner": "cranhaven", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-45", "n": 1 } ], "_tags": [], "_topics": [ "archived", "packages", "r-universe" ], "_stars": 5, "_contributors": [ { "user": "henrikbengtsson", "count": 183, "uuid": 1616850 } ], "_userbio": { "uuid": 161993010, "type": "organization", "name": "cranhaven", "followers": 3, "description": "CRANhaven - Repository for Recently Archived CRAN Packages" }, "_downloads": { "count": 215, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/klsh" }, "_devurl": "https://github.com/cranhaven/cranhaven.r-universe.dev", "_searchresults": 4, "_rbuild": "4.6.2", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/klsh.html", "extra/manual.pdf", "extra/readme.html", "extra/readme.md" ], "_homeurl": "https://github.com/cleanzr/klsh", "_realowner": "cleanzr", "_cranurl": false, "_releases": [ { "version": "0.1.0", "date": "2020-10-22" } ], "_exports": [ "bag_of_word_ify", "bag_signatures", "block.ids.from.blocking", "calc_idf", "confusion.from.blocking", "klsh", "reduction.ratio", "reduction.ratio.from.blocking", "rproject_bags", "sacks_of_bags_of_words", "tokenify" ], "_help": [ { "page": "bag_of_word_ify", "title": "Function to convert a record into a bag of tokens with a fieldwise flag", "topics": [ "bag_of_word_ify" ] }, { "page": "bag_signatures", "title": "Function that reduces a bag of words into a signature matrix using multiple random projections", "topics": [ "bag_signatures" ] }, { "page": "block.ids.from.blocking", "title": "Returns the block ids associated with a blocking method.", "topics": [ "block.ids.from.blocking" ] }, { "page": "calc_idf", "title": "Function to calculate the inverse document frequency given a shingled bag of words", "topics": [ "calc_idf" ] }, { "page": "confusion.from.blocking", "title": "Perform evaluations (recall) for blocking.", "topics": [ "confusion.from.blocking" ] }, { "page": "klsh", "title": "Function that reduces a bag of words into a signature matrix using multiple random projections", "topics": [ "klsh" ] }, { "page": "reduction.ratio", "title": "Returns the reduction ratio associated with a blocking method", "topics": [ "reduction.ratio" ] }, { "page": "reduction.ratio.from.blocking", "title": "Returns the reduction ratio associated with a blocking method", "topics": [ "reduction.ratio.from.blocking" ] }, { "page": "rproject_bags", "title": "Function that generates unit random vectors and takes (weighted) projections onto the random unit vectors given a bag of words", "topics": [ "rproject_bags" ] }, { "page": "sacks_of_bags_of_words", "title": "Function to convert all records into a bag of tokens", "topics": [ "sacks_of_bags_of_words" ] }, { "page": "tokenify", "title": "Function to token a string into its k components", "topics": [ "tokenify" ] } ], "_readme": "https://github.com/cranhaven/cranhaven.r-universe.dev/raw/package/klsh/klsh/README.md", "_rundeps": [ "blink", "plyr", "Rcpp", "SnowballC", "stringdist", "stringi" ], "_vignettes": [ { "source": "klsh.Rmd", "filename": "klsh.html", "title": "klsh", "author": "Rebecca C. Steorts", "engine": "knitr::rmarkdown", "headings": [ "Understanding the RLdata500 dataset", "KLSH applied to RLdata500" ], "created": "2026-11-03 06:02:00", "modified": "2026-11-03 06:02:00", "commits": 1 } ], "_score": 3.3979400086720375, "_indexed": false, "_nocasepkg": "klsh", "_universes": [ "cranhaven" ], "_indexurl": "https://cleanzr.r-universe.dev/klsh", "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.0", "date": "2026-11-03T19:11:29.000Z", "distro": "resolute", "commit": "1599ccdc715e433673b30daa846157a4d139f793", "fileid": "https://r2.ropensci.org/1f3c179bea63bffcadbac64d216e7a8cb2ac69856ecaa41d04eba3749c6b3571", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cranhaven/actions/runs/41699785448" }, { "r": "4.6.2", "os": "linux", "version": "0.1.0", "date": "2026-11-03T19:11:24.000Z", "distro": "resolute", "commit": "1599ccdc715e433673b30daa846157a4d139f793", "fileid": "https://r2.ropensci.org/1da55567998e979fa260ac978fc21864380e40c960a4118a23f1e0cd74c799f6", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cranhaven/actions/runs/41699785448" }, { "r": "4.5.3", "os": "mac", "version": "0.1.0", "date": "2026-11-03T19:11:17.000Z", "commit": "1599ccdc715e433673b30daa846157a4d139f793", "fileid": "https://r2.ropensci.org/5f4d6fcc6c26fcae1cd9065542fa4b97c7506f31e0b9b277bcd89f5684ac56f7", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cranhaven/actions/runs/41699785448" }, { "r": "4.6.2", "os": "mac", "version": "0.1.0", "date": "2026-11-03T19:11:14.000Z", "commit": "1599ccdc715e433673b30daa846157a4d139f793", "fileid": "https://r2.ropensci.org/f8e2d73f32fa360d9f536597a65972ac942769b01a93309fdc682fb4ae5e8d28", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cranhaven/actions/runs/41699785448" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.0", "date": "2026-11-03T19:11:20.000Z", "commit": "1599ccdc715e433673b30daa846157a4d139f793", "fileid": "https://r2.ropensci.org/91886f3734fa37ed407f682268580e6b738504ffb665baba349d9bb8e570fcd2", "status": "success", "buildurl": "https://github.com/r-universe/cranhaven/actions/runs/41699785448" }, { "r": "4.7.0", "os": "win", "version": "0.1.0", "date": "2026-11-03T19:10:58.000Z", "commit": "1599ccdc715e433673b30daa846157a4d139f793", "fileid": "https://r2.ropensci.org/4eced8da1826a9216880b60d9009db33d946588391bcc18d3c28957c00a5a560", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cranhaven/actions/runs/41699785448" }, { "r": "4.5.3", "os": "win", "version": "0.1.0", "date": "2026-11-03T19:10:35.000Z", "commit": "1599ccdc715e433673b30daa846157a4d139f793", "fileid": "https://r2.ropensci.org/2fc6dd240bba39530601d42d3f1afcc5c202fd3a7a7af84def38a47a56878290", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cranhaven/actions/runs/41699785448" }, { "r": "4.6.2", "os": "win", "version": "0.1.0", "date": "2026-11-03T19:10:48.000Z", "commit": "1599ccdc715e433673b30daa846157a4d139f793", "fileid": "https://r2.ropensci.org/0907b5c565346d0f81bc5f6fae60032550c072e8f026fef3464605c038fd9e45", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cranhaven/actions/runs/41699785448" } ] }