{ "_id": "6a49d345b48287dcb3fdaa29", "Package": "zoomerjoin", "Title": "Superlatively Fast Fuzzy Joins", "Version": "0.2.2", "Authors@R": "c(\nperson(\"Beniamino\", \"Green\", , \"beniamino.green@yale.edu\", role = c(\"aut\", \"cre\", \"cph\")),\nperson(\"Etienne\", \"Bacher\", email = \"etienne.bacher@protonmail.com\", role = \"ctb\",\ncomment = c(ORCID = \"0000-0002-9271-5075\")),\nperson(given = \"The authors of the dependency Rust crates\",\nrole = c(\"ctb\", \"cph\"),\ncomment = \"see inst/AUTHORS file for details\")\n)", "Description": "Empowers users to fuzzily-merge data frames with millions\nor tens of millions of rows in minutes with low memory usage.\nThe package uses the locality sensitive hashing algorithms\ndeveloped by Datar, Immorlica, Indyk and Mirrokni (2004)\n, and Broder (1998)\n to avoid having to compare\nevery pair of records in each dataset, resulting in\nfuzzy-merges that finish in linear time.", "License": "MIT + file LICENSE", "Encoding": "UTF-8", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.3.3", "SystemRequirements": "Cargo (>= 1.56) (Rust's package manager), rustc (>=\n1.70)", "Config/testthat/edition": "3", "URL": "https://beniamino.org/zoomerjoin/,\nhttps://github.com/beniaminogreen/zoomerjoin", "BugReports": "https://github.com/beniaminogreen/zoomerjoin/issues", "VignetteBuilder": "knitr", "LazyData": "true", "LazyDataCompression": "xz", "Config/rextendr/version": "0.4.2", "Config/pak/sysreqs": "libicu-dev libclang-dev", "Repository": "https://beniaminogreen.r-universe.dev", "Date/Publication": "2026-04-17 03:15:00 UTC", "RemoteUrl": "https://github.com/beniaminogreen/zoomerjoin", "RemoteRef": "HEAD", "RemoteSha": "d441bcdea9d4b74fa141d460e07734337c653d39", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-06-16 11:06:32 UTC", "User": "root" }, "Author": "Beniamino Green [aut, cre, cph],\nEtienne Bacher [ctb] (ORCID: ),\nThe authors of the dependency Rust crates [ctb, cph] (see inst/AUTHORS\nfile for details)", "Maintainer": "Beniamino Green ", "_user": "beniaminogreen", "_type": "src", "_file": "zoomerjoin_0.2.2.tar.gz", "_fileid": "https://r2.ropensci.org/29a65f7a193436769d700fe22f3c7cd078c1c29411d25362db9a0f18909482b4", "_filesize": 5236434, "_sha256": "29a65f7a193436769d700fe22f3c7cd078c1c29411d25362db9a0f18909482b4", "_expires": "2026-10-13T03:45:07.000Z", "_created": "2026-06-16T11:06:32.000Z", "_published": "2026-07-05T03:45:09.306Z", "_jobs": [ { "job": 85190221387, "time": 196, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "7665024995" }, { "job": 85190221363, "time": 196, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7665024850" }, { "job": 85190221568, "time": 235, "config": "linux-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7665038255" }, { "job": 85190221574, "time": 203, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7665027382" }, { "job": 85190221515, "time": 143, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7665005826" }, { "job": 85190221480, "time": 354, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "7665082390" }, { "job": 85190221454, "time": 144, "config": "macos-release-arm64", "r": "4.6.0", "check": "NOTE", "artifact": "7665006386" }, { "job": 85190221356, "time": 327, "config": "macos-release-x86_64", "r": "4.6.0", "check": "NOTE", "artifact": "7665071602" }, { "job": 85190221194, "time": 278, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7664954512" }, { "job": 85190221453, "time": 163, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7665013422" }, { "job": 85190221393, "time": 208, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "7665028824" }, { "job": 85190221548, "time": 196, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7665025849" }, { "job": 85190221398, "time": 193, "config": "windows-release", "r": "4.6.0", "check": "NOTE", "artifact": "7665023605" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/27612924087", "_status": "success", "_upstream": "https://github.com/beniaminogreen/zoomerjoin", "_commit": { "id": "d441bcdea9d4b74fa141d460e07734337c653d39", "author": "Ben Green ", "committer": "GitHub ", "message": "Merge pull request #136 from beniaminogreen/block_by_fix\n\nbugfix", "time": 1776395700 }, "_maintainer": { "name": "Beniamino Green", "email": "beniamino.green@yale.edu", "login": "beniaminogreen", "description": "\n", "uuid": 50080644 }, "_distro": "noble", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.2", "role": "Depends" }, { "package": "collapse", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "tibble", "role": "Imports" }, { "package": "tidyr", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "babynames", "role": "Suggests" }, { "package": "covr", "role": "Suggests" }, { "package": "igraph", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "microbenchmark", "role": "Suggests" }, { "package": "profmem", "role": "Suggests" }, { "package": "purrr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "stringdist", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "tidyverse", "role": "Suggests" }, { "package": "vdiffr", "role": "Suggests" } ], "_owner": "beniaminogreen", "_selfowned": true, "_usedby": 2, "_updates": [ { "week": "2025-39", "n": 1 }, { "week": "2025-46", "n": 1 }, { "week": "2026-11", "n": 1 }, { "week": "2026-16", "n": 1 } ], "_tags": [], "_topics": [ "blazinglyfast", "fuzzyjoin", "join", "rust", "zoomer", "cargo" ], "_stars": 109, "_contributors": [ { "user": "beniaminogreen", "count": 368, "uuid": 50080644 }, { "user": "etiennebacher", "count": 29, "uuid": 52219252 }, { "user": "jonddowns", "count": 2, "uuid": 110783391 }, { "user": "josiahparry", "count": 2, "uuid": 13534508 }, { "user": "floriancaro", "count": 1, "uuid": 34598596 } ], "_userbio": { "uuid": 50080644, "type": "user", "name": "Ben Green", "followers": 0 }, "_downloads": { "count": 587, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/zoomerjoin" }, "_devurl": "https://github.com/beniaminogreen/zoomerjoin", "_searchresults": 15, "_cargo": true, "_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/zoomerjoin.html", "LICENSE", "manual.pdf" ], "_homeurl": "https://github.com/beniaminogreen/zoomerjoin", "_realowner": "beniaminogreen", "_cranurl": true, "_releases": [ { "version": "0.1.4", "date": "2024-01-31" }, { "version": "0.1.5", "date": "2024-07-02" }, { "version": "0.2.0", "date": "2024-09-24" }, { "version": "0.2.1", "date": "2025-04-13" }, { "version": "0.2.2", "date": "2026-01-30" }, { "version": "0.2.3", "date": "2026-03-14" } ], "_exports": [ "em_link", "euclidean_anti_join", "euclidean_full_join", "euclidean_inner_join", "euclidean_left_join", "euclidean_probability", "euclidean_right_join", "fuzzy_join_core", "hamming_anti_join", "hamming_distance", "hamming_full_join", "hamming_inner_join", "hamming_left_join", "hamming_probability", "hamming_right_join", "jaccard_anti_join", "jaccard_curve", "jaccard_full_join", "jaccard_hyper_grid_search", "jaccard_inner_join", "jaccard_left_join", "jaccard_probability", "jaccard_right_join", "jaccard_similarity", "jaccard_string_group" ], "_datasets": [ { "name": "dime_data", "title": "Donors from DIME Database", "object": "dime_data", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "...1", "x" ], "rows": 1000, "table": true, "tojson": true } ], "_help": [ { "page": "dime_data", "title": "Donors from DIME Database", "topics": [ "dime_data" ] }, { "page": "em_link", "title": "Fit a Probabilistic Matching Model using Naive Bayes + E.M.", "topics": [ "em_link" ] }, { "page": "euclidean-joins", "title": "Fuzzy joins for Euclidean distance using Locality Sensitive Hashing", "topics": [ "euclidean_anti_join", "euclidean_full_join", "euclidean_inner_join", "euclidean_left_join", "euclidean_right_join" ] }, { "page": "euclidean_curve", "title": "Plot S-Curve for a LSH with given hyperparameters", "topics": [ "euclidean_curve" ] }, { "page": "euclidean_probability", "title": "Find Probability of Match Based on Similarity", "topics": [ "euclidean_probability" ] }, { "page": "fuzzy_join_core", "title": "Perform a Fuzzy-Join With an Arbitrary Distance Metric", "topics": [ "fuzzy_join_core" ] }, { "page": "hamming_distance", "title": "Calculate Hamming distance of two character vectors", "topics": [ "hamming_distance" ] }, { "page": "hamming-joins", "title": "Fuzzy joins for Hamming distance using Locality Sensitive Hashing", "topics": [ "hamming_anti_join", "hamming_full_join", "hamming_inner_join", "hamming_left_join", "hamming_right_join" ] }, { "page": "hamming_probability", "title": "Find Probability of Match Based on Similarity", "topics": [ "hamming_probability" ] }, { "page": "jaccard_curve", "title": "Plot S-Curve for a LSH with given hyperparameters", "topics": [ "jaccard_curve" ] }, { "page": "jaccard_hyper_grid_search", "title": "Help Choose the Appropriate LSH Hyperparameters", "topics": [ "jaccard_hyper_grid_search" ] }, { "page": "jaccard-joins", "title": "Fuzzy joins for Jaccard distance using MinHash", "topics": [ "jaccard_anti_join", "jaccard_full_join", "jaccard_inner_join", "jaccard_left_join", "jaccard_right_join" ] }, { "page": "jaccard_probability", "title": "Find Probability of Match Based on Similarity", "topics": [ "jaccard_probability" ] }, { "page": "jaccard_similarity", "title": "Calculate Jaccard Similarity of two character vectors", "topics": [ "jaccard_similarity" ] }, { "page": "jaccard_string_group", "title": "Fuzzy String Grouping Using Minhashing", "topics": [ "jaccard_string_group" ] } ], "_pkglogo": "https://github.com/beniaminogreen/zoomerjoin/raw/HEAD/logo.png", "_readme": "https://github.com/beniaminogreen/zoomerjoin/raw/HEAD/README.md", "_rundeps": [ "cli", "collapse", "cpp11", "dplyr", "generics", "glue", "lifecycle", "magrittr", "pillar", "pkgconfig", "purrr", "R6", "Rcpp", "rlang", "stringi", "stringr", "tibble", "tidyr", "tidyselect", "utf8", "vctrs", "withr" ], "_vignettes": [ { "source": "guided_tour.Rmd", "filename": "guided_tour.html", "title": "A Zoomerjoin Guided Tour", "engine": "knitr::rmarkdown", "headings": [ "Introduction:", "How Does it Work?", "Basic Syntax:", "Standardizing String Names After A Merge", "References:" ], "created": "2023-03-09 04:36:20", "modified": "2026-03-13 13:58:54", "commits": 10 }, { "source": "benchmarks.Rmd", "filename": "benchmarks.html", "title": "Benchmarks", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "Benchmarks", "Benchmarking Code:" ], "created": "2023-03-09 19:42:12", "modified": "2024-09-23 23:04:25", "commits": 6 }, { "source": "matching_vectors.Rmd", "filename": "matching_vectors.html", "title": "Matching Vectors Based on Euclidean Distance", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "Demonstration" ], "created": "2023-08-06 17:09:27", "modified": "2024-02-14 14:38:27", "commits": 5 } ], "_score": 8.371880249091555, "_indexed": true, "_nocasepkg": "zoomerjoin", "_universes": [ "beniaminogreen" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.2.2", "date": "2026-06-16T11:09:29.000Z", "distro": "noble", "arch": "aarch64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/dd0642d08ee7a7d8d92e949c35d97fbb4dc2a208e12284d8b6017c9c9b4b6cb3", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/27612924087" }, { "r": "4.7.0", "os": "linux", "version": "0.2.2", "date": "2026-06-16T11:09:30.000Z", "distro": "noble", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/7b1941a962e065169bdc8d57e4f4a15c83914c8ba72ed29090484869b910e7f0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/27612924087" }, { "r": "4.6.0", "os": "linux", "version": "0.2.2", "date": "2026-06-16T11:10:04.000Z", "distro": "noble", "arch": "aarch64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/f1930c3ccbbd65cc42e69759c279dbfeb9e57701b6414d78c205247e8cf73c9a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/27612924087" }, { "r": "4.6.0", "os": "linux", "version": "0.2.2", "date": "2026-06-16T11:09:32.000Z", "distro": "noble", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/f9f51eff02b1b4f394d887eb6cf7cc987071fb82af84f0ac60e2edd983e982ce", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/27612924087" }, { "r": "4.5.3", "os": "mac", "version": "0.2.2", "date": "2026-06-16T11:08:23.000Z", "arch": "aarch64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/97e7a1e432d88502d13ca858563ffac148e2c5a16d969059a6e390cfa0dba60c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/27612924087" }, { "r": "4.5.3", "os": "mac", "version": "0.2.2", "date": "2026-06-16T11:11:10.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/73e274eb39a65b9235abf176325b680cfa14a3c974dab2dbb9e0d1c23e24408b", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/27612924087" }, { "r": "4.6.0", "os": "mac", "version": "0.2.2", "date": "2026-06-16T11:08:30.000Z", "arch": "aarch64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/5da5fc46f403ed11d63996317f28e284562db52c4cc12317f6cf565810a72792", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/27612924087" }, { "r": "4.6.0", "os": "mac", "version": "0.2.2", "date": "2026-06-16T11:10:35.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/80b020d137b2819d3368c116d4e5cbdbfd83d0c1a8ab4b5aaff8a627e803c966", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/27612924087" }, { "r": "4.6.0", "os": "wasm", "version": "0.2.2", "date": "2026-06-16T11:09:29.000Z", "arch": "emscripten", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/45fbd47b187a03e02147d6a1834b8bf80728ad82bb9a6a36408a58de5dcc5024", "status": "success", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/27612924087" }, { "r": "4.7.0", "os": "win", "version": "0.2.2", "date": "2026-06-16T11:08:29.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/f3d170041205159bcbd1269585d548b60d042c61c192f0a729c4fdfc70be690d", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/27612924087" }, { "r": "4.5.3", "os": "win", "version": "0.2.2", "date": "2026-06-16T11:08:25.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/c44f09f3cc95e350426821570ed27e116201926200fbd69b44b8ab6f689a7adc", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/27612924087" }, { "r": "4.6.0", "os": "win", "version": "0.2.2", "date": "2026-06-16T11:08:19.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/dca24c106c9566c019d6327bd78b6d05e4a8eb031f8644b69ea7194440faa5a0", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/27612924087" } ] }