{ "_id": "6a1d38961d7bb097a0a3df31", "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", "Config/pak/sysreqs": "libicu-dev", "Repository": "https://cleanzr.r-universe.dev", "Date/Publication": "2020-10-14 10:05:44 UTC", "RemoteUrl": "https://github.com/cleanzr/klsh", "RemoteRef": "HEAD", "RemoteSha": "de9921997ec1c86044a8648899fb883c352a78b1", "NeedsCompilation": "no", "Packaged": { "Date": "2026-06-01 07:40:59 UTC", "User": "root" }, "Author": "Rebecca Steorts [aut, cre]", "Maintainer": "Rebecca Steorts ", "MD5sum": "1a5fd0c83b248ad5e2963a7a761b53fa", "_user": "cleanzr", "_type": "src", "_file": "klsh_0.1.0.tar.gz", "_fileid": "9cd4e4f5aed43646b16445a253ba98a40198752c4321d27db5c1e9de85a3f08f", "_filesize": 197508, "_sha256": "9cd4e4f5aed43646b16445a253ba98a40198752c4321d27db5c1e9de85a3f08f", "_created": "2026-06-01T07:40:59.000Z", "_published": "2026-06-01T07:45:26.169Z", "_distro": "noble", "_jobs": [ { "job": 78807344351, "time": 109, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "7325910804" }, { "job": 78807344344, "time": 112, "config": "linux-release-x86_64", "r": "4.6.0", "check": "NOTE", "artifact": "7325911547" }, { "job": 78807344368, "time": 106, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "NOTE", "artifact": "7325948387" }, { "job": 78807344316, "time": 81, "config": "macos-release-arm64", "r": "4.6.0", "check": "NOTE", "artifact": "7325925633" }, { "job": 78806858689, "time": 208, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7325877477" }, { "job": 78807344323, "time": 103, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7325909030" }, { "job": 78807344397, "time": 95, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "7325906577" }, { "job": 78807344356, "time": 95, "config": "windows-oldrel", "r": "4.5.3", "check": "NOTE", "artifact": "7325906591" }, { "job": 78807344345, "time": 74, "config": "windows-release", "r": "4.6.0", "check": "NOTE", "artifact": "7325899992" } ], "_buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26741629624", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/cleanzr/klsh", "_commit": { "id": "de9921997ec1c86044a8648899fb883c352a78b1", "author": "Rebecca Steorts ", "committer": "Rebecca Steorts ", "message": "prepare for cran.\n", "time": 1602669944 }, "_maintainer": { "name": "Rebecca Steorts", "email": "beka@stat.duke.edu", "login": "resteorts", "description": "\n Assistant Professor, Duke University, Department of Statistical Science\n", "uuid": 4843162 }, "_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": "cleanzr", "_selfowned": true, "_usedby": 0, "_updates": [], "_tags": [], "_stars": 0, "_contributors": [ { "user": "resteorts", "count": 18, "uuid": 4843162 }, { "user": "andeek", "count": 2, "uuid": 2414427 } ], "_userbio": { "uuid": 55656800, "type": "organization", "name": "cleanzr" }, "_downloads": { "count": 205, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/klsh" }, "_devurl": "https://github.com/cleanzr/klsh", "_searchresults": 3, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/klsh.html", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_homeurl": "https://github.com/cleanzr/klsh", "_realowner": "cleanzr", "_cranurl": true, "_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/cleanzr/klsh/raw/HEAD/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": "2020-10-08 15:35:54", "modified": "2020-10-12 22:02:13", "commits": 3 } ], "_score": 3.6989700043360187, "_indexed": true, "_nocasepkg": "klsh", "_universes": [ "cleanzr", "resteorts" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.0", "date": "2026-06-01T07:42:47.000Z", "distro": "noble", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "c3c22910aadaf0a19b9f216f3ecfc5ad651dc8ca28a6638c936a8f666f159725", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26741629624" }, { "r": "4.6.0", "os": "linux", "version": "0.1.0", "date": "2026-06-01T07:42:53.000Z", "distro": "noble", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "a97a2026d94c9d71c5525b5fc97c579cc8813d63605fd0861c1a65bcb79bdde6", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26741629624" }, { "r": "4.5.3", "os": "mac", "version": "0.1.0", "date": "2026-06-01T07:44:58.000Z", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "99848b42dfc7bc7f277336aaf634646f0708db83eab78d49ec3dcfc322ed2325", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26741629624" }, { "r": "4.6.0", "os": "mac", "version": "0.1.0", "date": "2026-06-01T07:43:42.000Z", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "97cffa3bb5ce8e0dde19bb84da7788f1c9606c7122cc5006f84da72e293bba8d", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26741629624" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.0", "date": "2026-06-01T07:42:57.000Z", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "3794ae1467b11b136b2507adef523cba82fddaaa9c8218cd361bd95e160ef164", "status": "success", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26741629624" }, { "r": "4.7.0", "os": "win", "version": "0.1.0", "date": "2026-06-01T07:42:28.000Z", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "d0906e8055eeaa73e4d924c5c0bf449beb7d369a28f9dfd09446f6ca5a21dc72", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26741629624" }, { "r": "4.5.3", "os": "win", "version": "0.1.0", "date": "2026-06-01T07:42:28.000Z", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "5634de736668da008ceb0ee3ed7f3c96da1e373bb59b5a14b7f39d8894d7e001", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26741629624" }, { "r": "4.6.0", "os": "win", "version": "0.1.0", "date": "2026-06-01T07:42:09.000Z", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "80b838df2952ef054b256a5528c5e4c779631a0c73e6333591871ba940d6f63c", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/26741629624" } ] }