{ "_id": "6a1f1754b401979e7341ea89", "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": "2026-05-17 06:03:48 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 ", "MD5sum": "ddf5d8cebaafc61e04109f127e2edc30", "_user": "beniaminogreen", "_type": "src", "_file": "zoomerjoin_0.2.2.tar.gz", "_fileid": "42a879aa75a330ca53c40832cfb589846e37fd8d99f3d922aec05a550612c4ef", "_filesize": 5230887, "_sha256": "42a879aa75a330ca53c40832cfb589846e37fd8d99f3d922aec05a550612c4ef", "_created": "2026-05-17T06:03:48.000Z", "_published": "2026-06-02T17:48:04.825Z", "_distro": "noble", "_jobs": [ { "job": 79135473320, "time": 189, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "7039862624" }, { "job": 79135473439, "time": 195, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7039863313" }, { "job": 79135473381, "time": 183, "config": "linux-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7039862159" }, { "job": 79135473352, "time": 201, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7039863977" }, { "job": 79135473503, "time": 225, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7039863808" }, { "job": 79135473406, "time": 449, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "7039888457" }, { "job": 79135473958, "time": 191, "config": "macos-release-arm64", "r": "4.6.0", "check": "NOTE", "artifact": "7039859625" }, { "job": 79135473042, "time": 342, "config": "macos-release-x86_64", "r": "4.6.0", "check": "NOTE", "artifact": "7039878376" }, { "job": 79135472516, "time": 291, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7039842233" }, { "job": 79135472557, "time": 173, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7365550907" }, { "job": 79135473162, "time": 266, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "7039871627" }, { "job": 79135474199, "time": 196, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7039863378" }, { "job": 79135473170, "time": 276, "config": "windows-release", "r": "4.6.0", "check": "NOTE", "artifact": "7039872870" } ], "_buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/25982950879", "_status": "success", "_host": "GitHub-Actions", "_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 }, "_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": 108, "_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" }, "_downloads": { "count": 627, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/zoomerjoin" }, "_devurl": "https://github.com/beniaminogreen/zoomerjoin", "_searchresults": 12, "_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", "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": 8.270967493629824, "_indexed": true, "_nocasepkg": "zoomerjoin", "_universes": [ "beniaminogreen" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.2.2", "date": "2026-05-17T06:06:43.000Z", "distro": "noble", "arch": "aarch64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "b301705bf8b5136c5c01a1ccae7609f32c8c0283bdfdecc1399c8943e905de60", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/25982950879" }, { "r": "4.7.0", "os": "linux", "version": "0.2.2", "date": "2026-05-17T06:06:46.000Z", "distro": "noble", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "af55f16ab7fa61b05a331e795049dc2c236c73878f71a2cafd05eaf1f054a8e1", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/25982950879" }, { "r": "4.6.0", "os": "linux", "version": "0.2.2", "date": "2026-05-17T06:06:37.000Z", "distro": "noble", "arch": "aarch64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "8069c0285c9c56b9380cc710897c94af9de734b7cc0ffc47cc5d75462a6809e2", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/25982950879" }, { "r": "4.6.0", "os": "linux", "version": "0.2.2", "date": "2026-05-17T06:06:52.000Z", "distro": "noble", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "c0c499a285c0e33c7ff92a0314a17419a1593004c77a403dcbf4f7c63321c25b", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/25982950879" }, { "r": "4.5.3", "os": "mac", "version": "0.2.2", "date": "2026-05-17T06:06:36.000Z", "arch": "aarch64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "63fbcf665239785ccdb6c9b326115ef690b856a46ca827591b4841f917705c74", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/25982950879" }, { "r": "4.5.3", "os": "mac", "version": "0.2.2", "date": "2026-05-17T06:08:13.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "48137e8e39d8294cfdf721a8bf8cd70fb99225f96a6eeea7fb5a19dfaa529c22", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/25982950879" }, { "r": "4.6.0", "os": "mac", "version": "0.2.2", "date": "2026-05-17T06:06:10.000Z", "arch": "aarch64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "fc5e903a590d0c53064b38c612a7dcef7234fa68bf450679c3b7b26f6b1aa574", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/25982950879" }, { "r": "4.6.0", "os": "mac", "version": "0.2.2", "date": "2026-05-17T06:07:46.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "9157c39aebdcd4f8537c81891ac275a5ced0135c24a25ce738a0bce2ac0a50cd", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/25982950879" }, { "r": "4.7.0", "os": "win", "version": "0.2.2", "date": "2026-05-17T06:05:52.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "a5eb477ce768da3eecf71bb103d64f42f0b4d759846377aa5302e929cf1a106d", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/25982950879" }, { "r": "4.5.3", "os": "win", "version": "0.2.2", "date": "2026-05-17T06:05:37.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "d9aef797cb95fddaee2729165e0a27af0aadf21e642ce7d47953a23332635508", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/25982950879" }, { "r": "4.6.0", "os": "win", "version": "0.2.2", "date": "2026-05-17T06:06:05.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "0c39e74474356995a2d70c36cc034ee8be009eed3522712eaef067e521bb18b0", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/25982950879" }, { "r": "4.6.0", "os": "wasm", "version": "0.2.2", "date": "2026-06-02T17:47:26.000Z", "arch": "emscripten", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "f65f6f5fae64d469d04c2041f1bdac32a8040a751c97421b2d58ee400d1cebed", "status": "success", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/25982950879" } ] }