{ "_id": "6a589784ff0138dec5d75826", "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": "2026-07-16 08:24:10 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/86ccbe60040766f2cc705142d936172de3229fadd49b7216f377a2d667b4dc00", "_filesize": 5231031, "_sha256": "86ccbe60040766f2cc705142d936172de3229fadd49b7216f377a2d667b4dc00", "_expires": "2026-10-24T08:34:09.000Z", "_created": "2026-07-16T08:24:10.000Z", "_published": "2026-07-16T08:34:12.092Z", "_jobs": [ { "job": 87572029422, "time": 211, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "8369459868" }, { "job": 87572029342, "time": 254, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8369468877" }, { "job": 87572029426, "time": 205, "config": "linux-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8369457860" }, { "job": 87572029384, "time": 199, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8369454116" }, { "job": 87572029368, "time": 119, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "8369423519" }, { "job": 87572029378, "time": 252, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "8369474168" }, { "job": 87572029364, "time": 141, "config": "macos-release-arm64", "r": "4.6.1", "check": "NOTE", "artifact": "8369432345" }, { "job": 87572029383, "time": 328, "config": "macos-release-x86_64", "r": "4.6.1", "check": "NOTE", "artifact": "8369504821" }, { "job": 87571057489, "time": 305, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8369375175" }, { "job": 87572029328, "time": 173, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8369443893" }, { "job": 87572029449, "time": 200, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "8369454578" }, { "job": 87572029347, "time": 195, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "8369452668" }, { "job": 87572029357, "time": 535, "config": "windows-release", "r": "4.6.1", "check": "NOTE", "artifact": "8369580291" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/29483050121", "_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": "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 } ], "_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": 489, "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/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": "2026-07-16T08:27:33.000Z", "distro": "resolute", "arch": "aarch64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/73c3a4794d3c63ab8be2a474993f7d2d37b57da19bedda4ca8dd080612aa848c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/29483050121" }, { "r": "4.7.0", "os": "linux", "version": "0.2.2", "date": "2026-07-16T08:28:05.000Z", "distro": "resolute", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/f03bdc67069269fdad5fe43a4fd2a3ff3b4b5641fdcb25a12bbe49dd5806153c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/29483050121" }, { "r": "4.6.1", "os": "linux", "version": "0.2.2", "date": "2026-07-16T08:27:33.000Z", "distro": "resolute", "arch": "aarch64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/ef104a0e7a98766541203639d4b8cecd3c6353eb6b347f40825e73e43007b0bf", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/29483050121" }, { "r": "4.6.1", "os": "linux", "version": "0.2.2", "date": "2026-07-16T08:27:14.000Z", "distro": "resolute", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/4429668e7e1510fb34b6e1bac482054253cc0da82c0404e7fd687c602d8dc2c3", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/29483050121" }, { "r": "4.5.3", "os": "mac", "version": "0.2.2", "date": "2026-07-16T08:26:01.000Z", "arch": "aarch64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/fc7ca5d1aaf1a8912ce2e294704348a3ee7fcffa56d0c6e0ed7527a6b0a04f74", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/29483050121" }, { "r": "4.5.3", "os": "mac", "version": "0.2.2", "date": "2026-07-16T08:27:28.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/1a9a0b9eddd06cfad966c4e92f11a238cb1a1e24626aabe74c18d5ce66b7a56e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/29483050121" }, { "r": "4.6.1", "os": "mac", "version": "0.2.2", "date": "2026-07-16T08:26:22.000Z", "arch": "aarch64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/c503bcf29f90e90192a3e2526c0aa99abdfc9961d1604a6a865ba24c9dbc10a3", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/29483050121" }, { "r": "4.6.1", "os": "mac", "version": "0.2.2", "date": "2026-07-16T08:28:24.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/9ca8c2c105a5524a0912470fafa087f81124dca154918e59883d0ae85fbd570b", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/29483050121" }, { "r": "4.6.0", "os": "wasm", "version": "0.2.2", "date": "2026-07-16T08:27:19.000Z", "arch": "emscripten", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/b7e3811bfcf0e4919b64ed6f81c5500c83bc5307dbccb963aea63144df2947ae", "status": "success", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/29483050121" }, { "r": "4.7.0", "os": "win", "version": "0.2.2", "date": "2026-07-16T08:26:02.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/fa6cdffaadf69c888dd1c1f382c4fc214fc1d2e5ae1de98325f18882f3257163", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/29483050121" }, { "r": "4.5.3", "os": "win", "version": "0.2.2", "date": "2026-07-16T08:26:01.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/b52e633dc92f73274a415658e8aa7fd57a0832b2747fedfb9d03884eb11675d9", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/29483050121" }, { "r": "4.6.1", "os": "win", "version": "0.2.2", "date": "2026-07-16T08:26:38.000Z", "arch": "x86_64", "commit": "d441bcdea9d4b74fa141d460e07734337c653d39", "fileid": "https://r2.ropensci.org/774d513342aa3e8e3177367fc45f8800bec6e99d2cb1fcf53c7554ed5d5e32e9", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/beniaminogreen/actions/runs/29483050121" } ] }