{
  "_id": "6aafae203d719c1f84080a54",
  "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<doi:10.1145/997817.997857>, and Broder (1998)\n<doi:10.1109/SEQUEN.1997.666900> 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": "2026-08-21 16:23:03 UTC",
  "RemoteUrl": "https://github.com/beniaminogreen/zoomerjoin",
  "RemoteRef": "HEAD",
  "RemoteSha": "99a9c71063bc63f91cf64a569046acc6cde506c5",
  "NeedsCompilation": "yes",
  "Packaged": {
    "Date": "2026-09-20 09:47:21 UTC",
    "User": "root"
  },
  "Author": "Beniamino Green [aut, cre, cph],\nEtienne Bacher [ctb] (ORCID: <https://orcid.org/0000-0002-9271-5075>),\nThe authors of the dependency Rust crates [ctb, cph] (see inst/AUTHORS\nfile for details)",
  "Maintainer": "Beniamino Green <beniamino.green@yale.edu>",
  "_user": "beniaminogreen",
  "_type": "src",
  "_file": "zoomerjoin_0.2.2.tar.gz",
  "_fileid": "https://r2.ropensci.org/9f3d0971e5472ce9d4b98a7493361e7547808c94928f8b6129c2bc3739941ec4",
  "_filesize": 6434278,
  "_sha256": "9f3d0971e5472ce9d4b98a7493361e7547808c94928f8b6129c2bc3739941ec4",
  "_expires": "2026-12-29T09:57:49.000Z",
  "_created": "2026-09-20T09:47:21.000Z",
  "_published": "2026-09-20T09:57:52.681Z",
  "_jobs": [
    {
      "job": 106058759463,
      "time": 171,
      "config": "linux-devel-arm64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "10603002465"
    },
    {
      "job": 106058759421,
      "time": 216,
      "config": "linux-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "10603101594"
    },
    {
      "job": 106058759447,
      "time": 178,
      "config": "linux-release-arm64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "10602658245"
    },
    {
      "job": 106058759410,
      "time": 197,
      "config": "linux-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "10601854449"
    },
    {
      "job": 106058759435,
      "time": 111,
      "config": "macos-oldrel-arm64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "10603206086"
    },
    {
      "job": 106058759437,
      "time": 275,
      "config": "macos-oldrel-x86_64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "10603206267"
    },
    {
      "job": 106058759438,
      "time": 192,
      "config": "macos-release-arm64",
      "r": "4.6.1",
      "check": "NOTE",
      "artifact": "10603395904"
    },
    {
      "job": 106058759423,
      "time": 570,
      "config": "macos-release-x86_64",
      "r": "4.6.1",
      "check": "NOTE",
      "artifact": "10603027868"
    },
    {
      "job": 106058215980,
      "time": 277,
      "config": "source",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "10603575477"
    },
    {
      "job": 106058759477,
      "time": 175,
      "config": "wasm-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "10603545704"
    },
    {
      "job": 106058759511,
      "time": 299,
      "config": "windows-devel-arm64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "10603361082"
    },
    {
      "job": 106058759521,
      "time": 236,
      "config": "windows-devel-x86_64",
      "r": "4.7.0",
      "check": "NOTE",
      "artifact": "10603470980"
    },
    {
      "job": 106058759525,
      "time": 210,
      "config": "windows-oldrel-x86_64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "10603301124"
    },
    {
      "job": 106058759500,
      "time": 344,
      "config": "windows-release-arm64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "10603151504"
    },
    {
      "job": 106058759504,
      "time": 229,
      "config": "windows-release-x86_64",
      "r": "4.6.1",
      "check": "NOTE",
      "artifact": "10603331111"
    }
  ],
  "_host": "GitHub-Actions",
  "_buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259",
  "_status": "success",
  "_upstream": "https://github.com/beniaminogreen/zoomerjoin",
  "_commit": {
    "id": "99a9c71063bc63f91cf64a569046acc6cde506c5",
    "author": "Ben Green <beniamino.green@tutanota.com>",
    "committer": "GitHub <noreply@github.com>",
    "message": "Merge pull request #137 from jeroen/main\n\nFix build on Windows ARM64",
    "time": 1787329383
  },
  "_maintainer": {
    "name": "Beniamino Green",
    "email": "beniamino.green@yale.edu",
    "login": "beniaminogreen",
    "description": "\n",
    "uuid": 50080644
  },
  "_distro": "resolute",
  "_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
    },
    {
      "week": "2026-34",
      "n": 1
    }
  ],
  "_tags": [],
  "_topics": [
    "blazinglyfast",
    "fuzzyjoin",
    "join",
    "rust",
    "zoomer",
    "cargo"
  ],
  "_stars": 110,
  "_contributors": [
    {
      "user": "beniaminogreen",
      "count": 369,
      "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
    },
    {
      "user": "jeroen",
      "count": 1,
      "uuid": 216319
    }
  ],
  "_userbio": {
    "uuid": 50080644,
    "type": "user",
    "name": "Ben Green",
    "followers": 0
  },
  "_downloads": {
    "count": 487,
    "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/zoomerjoin"
  },
  "_devurl": "https://github.com/beniaminogreen/zoomerjoin",
  "_searchresults": 15,
  "_cargo": true,
  "_rbuild": "4.6.1",
  "_assets": [
    "extra/citation.cff",
    "extra/citation.html",
    "extra/citation.json",
    "extra/citation.txt",
    "extra/contents.json",
    "extra/manual.pdf",
    "extra/NEWS.html",
    "extra/NEWS.txt",
    "extra/readme.html",
    "extra/readme.md",
    "extra/zoomerjoin.html",
    "LICENSE"
  ],
  "_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"
    },
    {
      "version": "0.2.4",
      "date": "2026-08-27"
    }
  ],
  "_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": 8.56966646232527,
  "_indexed": true,
  "_nocasepkg": "zoomerjoin",
  "_universes": [
    "beniaminogreen"
  ],
  "_binaries": [
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "0.2.2",
      "date": "2026-09-20T09:49:58.000Z",
      "distro": "resolute",
      "arch": "aarch64",
      "commit": "99a9c71063bc63f91cf64a569046acc6cde506c5",
      "fileid": "https://r2.ropensci.org/8403aef02edfe52a6f67f33eb5f4b0e1c42b2755735e178014c45a15e9b7a9d3",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259"
    },
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "0.2.2",
      "date": "2026-09-20T09:50:38.000Z",
      "distro": "resolute",
      "arch": "x86_64",
      "commit": "99a9c71063bc63f91cf64a569046acc6cde506c5",
      "fileid": "https://r2.ropensci.org/5c565badb319f95ab5aa7dac3cf3f73eca38e0d16ce7007f04a05fffe1d6a7a4",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259"
    },
    {
      "r": "4.6.1",
      "os": "linux",
      "version": "0.2.2",
      "date": "2026-09-20T09:50:06.000Z",
      "distro": "resolute",
      "arch": "aarch64",
      "commit": "99a9c71063bc63f91cf64a569046acc6cde506c5",
      "fileid": "https://r2.ropensci.org/6c5f6f7d1a1405e0cd949d499d4599b156ba34390032c52045181f41072f21be",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259"
    },
    {
      "r": "4.6.1",
      "os": "linux",
      "version": "0.2.2",
      "date": "2026-09-20T09:50:20.000Z",
      "distro": "resolute",
      "arch": "x86_64",
      "commit": "99a9c71063bc63f91cf64a569046acc6cde506c5",
      "fileid": "https://r2.ropensci.org/7c8d26b44dd689939b46eb2f75bc12afe0160854156079e108c6bfc68f841a8e",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "0.2.2",
      "date": "2026-09-20T09:49:03.000Z",
      "arch": "aarch64",
      "commit": "99a9c71063bc63f91cf64a569046acc6cde506c5",
      "fileid": "https://r2.ropensci.org/735a328def132ec8980fced8466034cf5451355574309908758e73ed5b0b4489",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "0.2.2",
      "date": "2026-09-20T09:50:53.000Z",
      "arch": "x86_64",
      "commit": "99a9c71063bc63f91cf64a569046acc6cde506c5",
      "fileid": "https://r2.ropensci.org/4c7c6547898ac575ef48938e50d645d91f62cb14f39ad6f75756ad39d6165106",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259"
    },
    {
      "r": "4.6.1",
      "os": "mac",
      "version": "0.2.2",
      "date": "2026-09-20T09:49:51.000Z",
      "arch": "aarch64",
      "commit": "99a9c71063bc63f91cf64a569046acc6cde506c5",
      "fileid": "https://r2.ropensci.org/3470545d5bd4555903771c9edd8f290a484695ac71b1b84af7caf2933c3e4d10",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259"
    },
    {
      "r": "4.6.1",
      "os": "mac",
      "version": "0.2.2",
      "date": "2026-09-20T09:52:28.000Z",
      "arch": "x86_64",
      "commit": "99a9c71063bc63f91cf64a569046acc6cde506c5",
      "fileid": "https://r2.ropensci.org/48255ee3e1c39e87443fe51fc5077a7f91bab578af75ebf5f2eb4fea033f307e",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259"
    },
    {
      "r": "4.6.0",
      "os": "wasm",
      "version": "0.2.2",
      "date": "2026-09-20T09:50:30.000Z",
      "arch": "emscripten",
      "commit": "99a9c71063bc63f91cf64a569046acc6cde506c5",
      "fileid": "https://r2.ropensci.org/32ec9296bfc95b5429fc42b175cd2e413662ebd9ef24dfe81f55bfb91062b00f",
      "status": "success",
      "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "0.2.2",
      "date": "2026-09-20T09:51:04.000Z",
      "arch": "aarch64",
      "commit": "99a9c71063bc63f91cf64a569046acc6cde506c5",
      "fileid": "https://r2.ropensci.org/0a5e177f8de4230f6ae8719859e3e795361d91be2e3c940590f4b9ee0820ed65",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "0.2.2",
      "date": "2026-09-20T09:49:08.000Z",
      "arch": "x86_64",
      "commit": "99a9c71063bc63f91cf64a569046acc6cde506c5",
      "fileid": "https://r2.ropensci.org/1b90abfcaabc75c856a7c46c0f8d92eb625ea580ab47bbc17052ce1e4332bbeb",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259"
    },
    {
      "r": "4.5.3",
      "os": "win",
      "version": "0.2.2",
      "date": "2026-09-20T09:49:19.000Z",
      "arch": "x86_64",
      "commit": "99a9c71063bc63f91cf64a569046acc6cde506c5",
      "fileid": "https://r2.ropensci.org/6dc2c572488295486ea31b9a53e2ff17ec25804b669f319c0b2d5a87b9dc5c40",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259"
    },
    {
      "r": "4.6.1",
      "os": "win",
      "version": "0.2.2",
      "date": "2026-09-20T09:51:54.000Z",
      "arch": "aarch64",
      "commit": "99a9c71063bc63f91cf64a569046acc6cde506c5",
      "fileid": "https://r2.ropensci.org/685a9b99b556e2fbc9503667f47d05239e817f477eb40038dd7828c0fa05e8fa",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259"
    },
    {
      "r": "4.6.1",
      "os": "win",
      "version": "0.2.2",
      "date": "2026-09-20T09:49:09.000Z",
      "arch": "x86_64",
      "commit": "99a9c71063bc63f91cf64a569046acc6cde506c5",
      "fileid": "https://r2.ropensci.org/460bafb89e02c7110e9f19288bcb50632ccdb507abbfa8c1b48d47de380090c2",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/35503070259"
    }
  ]
}