{ "_id": "6ad1fe17fdc1a00814f1ea8f", "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": "2026-10-16 10:33:04 UTC", "User": "root" }, "Author": "Rebecca Steorts [aut, cre]", "Maintainer": "Rebecca Steorts ", "_user": "cleanzr", "_type": "src", "_file": "klsh_0.1.0.tar.gz", "_fileid": "https://r2.ropensci.org/31862d78181061d86f3eef45304475a61678764cde806632fd141f3cf5967ff2", "_filesize": 197925, "_sha256": "31862d78181061d86f3eef45304475a61678764cde806632fd141f3cf5967ff2", "_expires": "2027-01-24T10:36:05.000Z", "_created": "2026-10-16T10:33:04.000Z", "_published": "2026-10-16T10:36:07.322Z", "_buildurl": "https://github.com/r-universe/cleanzr/actions/runs/38887533837", "_status": "success", "_host": "GitHub-Actions", "_jobs": [ { "job": 116930366106, "time": 142, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "12040078506" }, { "job": 116930366117, "time": 117, "config": "linux-release-x86_64", "r": "4.6.1", "check": "NOTE", "artifact": "12040217734" }, { "job": 116930366124, "time": 84, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "NOTE", "artifact": "12041120979" }, { "job": 116930366104, "time": 118, "config": "macos-release-arm64", "r": "4.6.1", "check": "NOTE", "artifact": "12040777055" }, { "job": 116928938789, "time": 230, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "12041055993" }, { "job": 116930366276, "time": 87, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "12041086302" }, { "job": 116930366128, "time": 81, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "12040382183" }, { "job": 116930366179, "time": 62, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "NOTE", "artifact": "12039864081" }, { "job": 116930366371, "time": 105, "config": "windows-release-x86_64", "r": "4.6.1", "check": "NOTE", "artifact": "12040906873" } ], "_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 }, "_distro": "resolute", "_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", "followers": 8 }, "_downloads": { "count": 254, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/klsh" }, "_devurl": "https://github.com/cleanzr/klsh", "_searchresults": 4, "_rbuild": "4.6.1", "_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": 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": "2026-10-16T10:35:28.000Z", "distro": "resolute", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "https://r2.ropensci.org/0e51dc988fe215d071d2a10c601306fa645e8be6b31a42d189ea50e94eb4ee59", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/38887533837" }, { "r": "4.6.1", "os": "linux", "version": "0.1.0", "date": "2026-10-16T10:34:59.000Z", "distro": "resolute", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "https://r2.ropensci.org/61019d5c287b101640fc52e50dcda89ffbe85a7a5b32ad58ab2082c72dddfab6", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/38887533837" }, { "r": "4.5.3", "os": "mac", "version": "0.1.0", "date": "2026-10-16T10:34:35.000Z", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "https://r2.ropensci.org/7db3009ef93fb40fd097253772b970a6359c13d49bd1b2f2fa94c1257c318c38", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/38887533837" }, { "r": "4.6.1", "os": "mac", "version": "0.1.0", "date": "2026-10-16T10:35:07.000Z", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "https://r2.ropensci.org/829f142450f715caa2b5d9a4cf0a8c00daac15bce49e33898f03709741007a0f", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/38887533837" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.0", "date": "2026-10-16T10:34:48.000Z", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "https://r2.ropensci.org/5e232d41efd6ef22713852af3334b5f6b228a30cf8d05984c84505fb23c2e400", "status": "success", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/38887533837" }, { "r": "4.7.0", "os": "win", "version": "0.1.0", "date": "2026-10-16T10:34:19.000Z", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "https://r2.ropensci.org/203f49b9c42e441d9a97033008cc7e473654a6d4418c81216afa8321f7e2107c", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/38887533837" }, { "r": "4.5.3", "os": "win", "version": "0.1.0", "date": "2026-10-16T10:34:04.000Z", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "https://r2.ropensci.org/795e578b7cad8ab1f1b6d542bbac9c3539ef916688e8329ba92544c52b171349", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/38887533837" }, { "r": "4.6.1", "os": "win", "version": "0.1.0", "date": "2026-10-16T10:34:28.000Z", "commit": "de9921997ec1c86044a8648899fb883c352a78b1", "fileid": "https://r2.ropensci.org/40d81594b951dbd89f0d978a2a7299184c6de92943f20ad5d646f8d1b2ed8ada", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cleanzr/actions/runs/38887533837" } ] }