{ "_id": "6ab27e143d719c1f8408da39", "Package": "DataSimilarity", "Type": "Package", "Title": "Quantifying Similarity of Datasets and Multivariate Two- And\nk-Sample Testing", "Version": "0.4.0", "Date": "2026-05-15", "Authors@R": "c(person(given = \"Marieke\", family = \"Stolte\", \nemail = \"marieke.stolte@ibe.med.uni-muenchen.de\", role = c(\"aut\", \"cre\", \"cph\"),\ncomment = c(ORCID = \"0009-0002-0711-6789\")),\nperson(given = \"Luca\", family = \"Sauer\", role = c(\"aut\"),\ncomment = c(ORCID = \"0009-0000-1086-023X\")),\nperson(given = \"David\", family = \"Alvarez-Melis\", role = c(\"ctb\"),\ncomment = \"Original python implementation of OTDD, \"),\nperson(given = \"Nabarun\", family = \"Deb\", role = c(\"ctb\"),\ncomment = \"Original implementation of rank-based Energy test (DS), \"),\nperson(given = \"Bodhisattva\", family = \"Sen\", role = c(\"ctb\"),\ncomment = \"Original implementation of rank-based Energy test (DS), \"))", "Description": "A collection of methods for quantifying the similarity of\ntwo or more datasets, many of which can be used for two- or\nk-sample testing. It provides newly implemented methods as well\nas wrapper functions for existing methods that enable calling\nmany different methods in a unified framework. The methods were\nselected from the review and comparison of Stolte et al. (2024)\n. An empirical comparison of the methods\nwas performed in Stolte et al. (2026)\n for categorical data and in\nStolte et al. (2026) for\nnumeric data.", "License": "GPL (>= 3)", "LazyData": "true", "NeedsCompilation": "no", "Packaged": { "Date": "2026-09-22 13:03:17 UTC", "User": "root" }, "Author": "Marieke Stolte [aut, cre, cph] (ORCID:\n), Luca Sauer [aut]\n(ORCID: ), David\nAlvarez-Melis [ctb] (Original python implementation of OTDD,\n), Nabarun Deb [ctb]\n(Original implementation of rank-based Energy test (DS),\n), Bodhisattva\nSen [ctb] (Original implementation of rank-based Energy test\n(DS), )", "Maintainer": "Marieke Stolte ", "Repository": "https://mariekestolte.r-universe.dev", "Date/Publication": "2026-05-15 08:19:19 UTC", "RemoteUrl": "https://github.com/cran/DataSimilarity", "RemoteRef": "HEAD", "RemoteSha": "b0bceebe6a415b81875365ba953c80f6b93b259c", "_user": "mariekestolte", "_type": "src", "_file": "DataSimilarity_0.4.0.tar.gz", "_fileid": "https://r2.ropensci.org/8a5bc3e98164f02c1ebf3e65ad948536b2a343e2f7ca8ba2970027ed89f09869", "_filesize": 1743159, "_sha256": "8a5bc3e98164f02c1ebf3e65ad948536b2a343e2f7ca8ba2970027ed89f09869", "_expires": "2026-12-31T13:09:37.000Z", "_created": "2026-09-22T13:03:17.000Z", "_published": "2026-09-22T13:09:40.209Z", "_jobs": [ { "job": 106756413498, "time": 321, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "10696145490" }, { "job": 106756413371, "time": 310, "config": "linux-release-x86_64", "r": "4.6.1", "check": "NOTE", "artifact": "10695443654" }, { "job": 106756411847, "time": 244, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "NOTE", "artifact": "10696090303" }, { "job": 106756411957, "time": 245, "config": "macos-release-arm64", "r": "4.6.1", "check": "NOTE", "artifact": "10694953773" }, { "job": 106737844234, "time": 3318, "config": "source", "r": "4.6.1", "check": "ERROR", "artifact": "10695597464" }, { "job": 106756411780, "time": 171, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "10695715469" }, { "job": 106756411967, "time": 204, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "10695745560" }, { "job": 106756411737, "time": 253, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "NOTE", "artifact": "10695573460" }, { "job": 106756411819, "time": 231, "config": "windows-release-x86_64", "r": "4.6.1", "check": "NOTE", "artifact": "10695548188" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/mariekestolte/actions/runs/35725413831", "_status": "failure", "_upstream": "https://github.com/cran/DataSimilarity", "_commit": { "id": "b0bceebe6a415b81875365ba953c80f6b93b259c", "author": "Marieke Stolte ", "committer": "cran-robot ", "message": "version 0.4.0\n", "time": 1778833159 }, "_maintainer": { "name": "Marieke Stolte", "email": "marieke.stolte@ibe.med.uni-muenchen.de", "login": "mariekestolte", "orcid": "0009-0002-0711-6789", "description": "", "uuid": 52041172 }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.5.0", "role": "Depends" }, { "package": "boot", "role": "Imports" }, { "package": "stats", "role": "Imports" }, { "package": "ade4", "role": "Suggests" }, { "package": "approxOT", "role": "Suggests" }, { "package": "Ball", "role": "Suggests" }, { "package": "caret", "role": "Suggests" }, { "package": "clue", "role": "Suggests" }, { "package": "cramer", "role": "Suggests" }, { "package": "crossmatch", "role": "Suggests" }, { "package": "dbscan", "role": "Suggests" }, { "package": "densratio", "role": "Suggests" }, { "package": "DWDLargeR", "role": "Suggests" }, { "package": "e1071", "role": "Suggests" }, { "package": "Ecume", "role": "Suggests" }, { "package": "energy", "role": "Suggests" }, { "package": "expm", "role": "Suggests" }, { "package": "FNN", "role": "Suggests" }, { "package": "GraphRankTest", "role": "Suggests" }, { "package": "gTests", "role": "Suggests" }, { "package": "gTestsMulti", "role": "Suggests" }, { "package": "HDLSSkST", "role": "Suggests" }, { "package": "hypoRF", "role": "Suggests" }, { "package": "kernlab", "role": "Suggests" }, { "package": "kerTests", "role": "Suggests" }, { "package": "KMD", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "LPKsample", "role": "Suggests" }, { "package": "Matrix", "role": "Suggests" }, { "package": "mvtnorm", "role": "Suggests" }, { "package": "nbpMatching", "role": "Suggests" }, { "package": "pROC", "role": "Suggests" }, { "package": "purrr", "role": "Suggests" }, { "package": "randtoolbox", "role": "Suggests" }, { "package": "rlemon", "role": "Suggests" }, { "package": "rpart", "role": "Suggests" }, { "package": "rpart.plot", "role": "Suggests" }, { "package": "testthat", "role": "Suggests" }, { "package": "nnet", "role": "Suggests" }, { "package": "synthpop", "role": "Suggests" }, { "package": "igraph", "role": "Suggests" }, { "package": "cluster", "role": "Suggests" } ], "_owner": "cran", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-09", "n": 1 }, { "week": "2026-20", "n": 1 } ], "_tags": [ { "name": "0.3.0", "date": "2026-02-27" }, { "name": "0.4.0", "date": "2026-05-15" } ], "_stars": 0, "_contributors": [ { "user": "mariekestolte", "count": 4, "uuid": 52041172 } ], "_userbio": { "uuid": 52041172, "type": "user", "name": "Marieke Stolte", "followers": 4 }, "_downloads": { "count": 425, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/DataSimilarity" }, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/DataSimilarity.html", "extra/manual.pdf" ], "_realowner": "mariekestolte", "_cranurl": false, "_releases": [ { "version": "0.1.1", "date": "2025-03-22" }, { "version": "0.2.0", "date": "2025-06-16" }, { "version": "0.3.0", "date": "2026-02-27" }, { "version": "0.4.0", "date": "2026-05-15" } ], "_exports": [ "AUC", "Bahr", "BallDivergence", "BF", "BG", "BG2", "BMG", "BQS", "C2ST", "CCS", "CCS_cat", "CF", "CF_cat", "CMDistance", "Cramer", "DataSimilarity", "DiProPerm", "DISCOB", "DISCOF", "DS", "dwdProj", "Energy", "engineerMetric", "f.a", "f.aCat", "f.s", "f.sCat", "findSigma", "findSimilarityMethod", "FR", "FR_cat", "FStest", "GGRL", "GGRLCat", "GPK", "gTests", "gTests_cat", "gTestsMulti", "HamiltonPath", "hammingDist", "HMN", "Jeffreys", "kerTests", "KMD", "knn", "knn.bf", "knn.fast", "LHZ", "LHZStatistic", "MD", "MMCM", "MMD", "MST", "MST5", "MW", "NKT", "OTDD", "Petrie", "rectPartition", "RISE", "RItest", "Rosenbaum", "SC", "SH", "svmProj", "tStat", "Wasserstein", "YMRZL", "ZC", "ZC_cat" ], "_datasets": [ { "name": "method.table", "title": "List of Methods Included in the Package", "object": "method.table", "class": [ "data.frame" ], "fields": [ "Method", "Implementation", "Target.Inclusion", "Numeric", "Categorical", "Unequal.Sample.Sizes", "p.Larger.N", "Multiple.Samples", "Without.training", "No.assumptions", "No.parameters", "Implemented", "Complexity", "Interpretable.units", "Lower.bound", "Upper.bound", "Rotation.invariant", "Location.change.invariant", "Homogeneous.scale.invariant", "Positive.definite", "Symmetric", "Triangle.inequality", "Consistency.N", "Consistency.p", "Number.Fulfilled", "Number.Cond.Fulfilled", "Number.Unfulfilled", "Number.NA", "Class", "Subclass" ], "rows": 45, "table": true, "tojson": true } ], "_help": [ { "page": "DataSimilarity-package", "title": "Quantifying Similarity of Datasets and Multivariate Two- And k-Sample Testing", "concept": [ "dataset similarity" ], "topics": [ "DataSimilarity-package" ] }, { "page": "Bahr", "title": "Bahr (1996) Multivariate Two-sample Test", "concept": [ "dataset similarity" ], "topics": [ "Bahr" ] }, { "page": "BallDivergence", "title": "Ball Divergence Based Two- or k-sample Test", "concept": [ "dataset similarity" ], "topics": [ "BallDivergence" ] }, { "page": "BF", "title": "Baringhaus and Franz (2010) Rigid Motion Invariant Multivariate Two-sample Test", "concept": [ "dataset similarity" ], "topics": [ "BF" ] }, { "page": "BG", "title": "Biau and Gyorfi (2005) Two-sample Homogeneity Test", "concept": [ "dataset similarity" ], "topics": [ "BG" ] }, { "page": "BG2", "title": "Biswas and Ghosh (2014) Two-Sample Test", "concept": [ "dataset similarity" ], "topics": [ "BG2" ] }, { "page": "BMG", "title": "Biswas et al. (2014) Two-sample Runs Test", "concept": [ "dataset similarity" ], "topics": [ "BMG" ] }, { "page": "BQS", "title": "Barakat et al. (1996) Two-Sample Test", "concept": [ "dataset similarity" ], "topics": [ "BQS" ] }, { "page": "C2ST", "title": "Classifier Two-Sample Test", "concept": [ "dataset similarity" ], "topics": [ "C2ST" ] }, { "page": "CCS", "title": "Weighted Edge-Count Two-Sample Test", "concept": [ "dataset similarity" ], "topics": [ "CCS" ] }, { "page": "CCS_cat", "title": "Weighted Edge-Count Two-Sample Test for Discrete Data", "concept": [ "dataset similarity" ], "topics": [ "CCS_cat" ] }, { "page": "CF", "title": "Generalized Edge-Count Test", "concept": [ "dataset similarity" ], "topics": [ "CF" ] }, { "page": "CF_cat", "title": "Generalized Edge-Count Test for Discrete Data", "concept": [ "dataset similarity" ], "topics": [ "CF_cat" ] }, { "page": "CMDistance", "title": "Constrained Minimum Distance", "concept": [ "dataset similarity" ], "topics": [ "CMDistance" ] }, { "page": "Cramer", "title": "Cramér Two-Sample Test", "concept": [ "dataset similarity" ], "topics": [ "Cramer" ] }, { "page": "DataSimilarity", "title": "Dataset Similarity", "concept": [ "dataset similarity" ], "topics": [ "DataSimilarity" ] }, { "page": "dipro.fun", "title": "Direction-Projection Functions for DiProPerm Test", "concept": [ "dataset similarity" ], "topics": [ "dipro.fun", "dwdProj", "svmProj" ] }, { "page": "DiProPerm", "title": "Direction-Projection-Permutation (DiProPerm) Test", "concept": [ "dataset similarity" ], "topics": [ "DiProPerm" ] }, { "page": "DISCOB", "title": "Distance Components (DISCO) Tests", "concept": [ "dataset similarity" ], "topics": [ "DISCOB" ] }, { "page": "DISCOF", "title": "Distance Components (DISCO) Tests", "concept": [ "dataset similarity" ], "topics": [ "DISCOF" ] }, { "page": "DS", "title": "Rank-Based Energy Test (Deb and Sen, 2021)", "concept": [ "dataset similarity" ], "topics": [ "DS" ] }, { "page": "Energy", "title": "Energy Statistic and Test", "concept": [ "dataset similarity" ], "topics": [ "Energy" ] }, { "page": "engineerMetric", "title": "Engineer Metric", "concept": [ "dataset similarity" ], "topics": [ "engineerMetric" ] }, { "page": "findSimilarityMethod", "title": "Selection of Appropriate Methods for Quantifying the Similarity of Datasets", "concept": [ "dataset similarity" ], "topics": [ "findSimilarityMethod" ] }, { "page": "FR", "title": "Friedman-Rafsky Test", "concept": [ "dataset similarity" ], "topics": [ "FR" ] }, { "page": "FR_cat", "title": "Friedman-Rafsky Test for Discrete Data", "concept": [ "dataset similarity" ], "topics": [ "FR_cat" ] }, { "page": "FStest", "title": "Multisample FS Test", "concept": [ "dataset similarity" ], "topics": [ "FStest" ] }, { "page": "GGRL", "title": "Decision-Tree Based Measure of Dataset Distance and Two-Sample Test", "concept": [ "dataset similarity" ], "topics": [ "f.a", "f.aCat", "f.s", "f.sCat", "GGRL", "GGRLCat" ] }, { "page": "GPK", "title": "Generalized Permutation-Based Kernel (GPK) Two-Sample Test", "concept": [ "dataset similarity" ], "topics": [ "findSigma", "GPK" ] }, { "page": "gTests", "title": "Graph-Based Tests", "concept": [ "dataset similarity" ], "topics": [ "gTests" ] }, { "page": "gTests_cat", "title": "Graph-Based Tests for Discrete Data", "concept": [ "dataset similarity" ], "topics": [ "gTests_cat" ] }, { "page": "gTestsMulti", "title": "Graph-Based Multi-Sample Test", "concept": [ "dataset similarity" ], "topics": [ "gTestsMulti" ] }, { "page": "HamiltonPath", "title": "Shortest Hamilton path", "concept": [ "dataset similarity" ], "topics": [ "HamiltonPath" ] }, { "page": "HMN", "title": "Random Forest Based Two-Sample Test", "concept": [ "dataset similarity" ], "topics": [ "HMN" ] }, { "page": "Jeffreys", "title": "Jeffreys Divergence", "concept": [ "dataset similarity" ], "topics": [ "Jeffreys" ] }, { "page": "kerTests", "title": "Generalized Permutation-Based Kernel (GPK) Two-Sample Test", "concept": [ "dataset similarity" ], "topics": [ "kerTests" ] }, { "page": "KMD", "title": "Kernel Measure of Multi-Sample Dissimilarity (KMD)", "concept": [ "dataset similarity" ], "topics": [ "KMD" ] }, { "page": "knn", "title": "K-Nearest Neighbor Graph", "topics": [ "knn", "knn.bf", "knn.fast" ] }, { "page": "LHZ", "title": "Empirical Characteristic Distance", "concept": [ "dataset similarity" ], "topics": [ "LHZ" ] }, { "page": "LHZStatistic", "title": "Calculation of the Li et al. (2022) Empirical Characteristic Distance", "concept": [ "dataset similarity" ], "topics": [ "LHZStatistic" ] }, { "page": "method.table", "title": "List of Methods Included in the Package", "topics": [ "method.table" ] }, { "page": "MMCM", "title": "Multisample Mahalanobis Crossmatch (MMCM) Test", "concept": [ "dataset similarity" ], "topics": [ "MMCM" ] }, { "page": "MMD", "title": "Maximum Mean Discrepancy (MMD) Test", "concept": [ "dataset similarity" ], "topics": [ "MMD" ] }, { "page": "MST", "title": "Minimum Spanning Tree (MST)", "topics": [ "MST", "MST5" ] }, { "page": "MW", "title": "Nonparametric Graph-Based LP (GLP) Test", "concept": [ "dataset similarity" ], "topics": [ "MW" ] }, { "page": "NKT", "title": "Decision-Tree Based Measure of Dataset Similarity ('Ntoutsi et al., 2008')", "concept": [ "dataset similarity" ], "topics": [ "NKT" ] }, { "page": "OTDD", "title": "Optimal Transport Dataset Distance", "concept": [ "dataset similarity" ], "topics": [ "hammingDist", "OTDD" ] }, { "page": "Petrie", "title": "Multisample Crossmatch (MCM) Test", "concept": [ "dataset similarity" ], "topics": [ "Petrie" ] }, { "page": "rectPartition", "title": "Calculate a Rectangular Partition", "concept": [ "dataset similarity" ], "topics": [ "rectPartition" ] }, { "page": "RISE", "title": "Rank In Similarity Graph Edge-count two-sample test (RISE)", "concept": [ "dataset similarity" ], "topics": [ "RISE" ] }, { "page": "RItest", "title": "Multisample RI Test", "concept": [ "dataset similarity" ], "topics": [ "RItest" ] }, { "page": "Rosenbaum", "title": "Rosenbaum Crossmatch Test", "concept": [ "dataset similarity" ], "topics": [ "Rosenbaum" ] }, { "page": "SC", "title": "Graph-Based Multi-Sample Test", "concept": [ "dataset similarity" ], "topics": [ "SC" ] }, { "page": "SH", "title": "Schilling-Henze Nearest Neighbor Test", "concept": [ "dataset similarity" ], "topics": [ "SH" ] }, { "page": "stat.fun", "title": "Univariate Two-Sample Statistics for DiProPerm Test", "concept": [ "dataset similarity" ], "topics": [ "AUC", "MD", "stat.fun", "tStat" ] }, { "page": "Wasserstein", "title": "Wasserstein Distance Based Test", "concept": [ "dataset similarity" ], "topics": [ "Wasserstein" ] }, { "page": "YMRZL", "title": "Yu et al. (2007) Two-Sample Test", "concept": [ "dataset similarity" ], "topics": [ "YMRZL" ] }, { "page": "ZC", "title": "Maxtype Edge-Count Test", "concept": [ "dataset similarity" ], "topics": [ "ZC" ] }, { "page": "ZC_cat", "title": "Maxtype Edge-Count Test for Discrete Data", "concept": [ "dataset similarity" ], "topics": [ "ZC_cat" ] } ], "_rundeps": [ "boot" ], "_vignettes": [ { "source": "Details.Rnw", "filename": "Details.pdf", "title": "Details on methods and implementations", "engine": "utils::Sweave", "headings": [ "Methods", "Implementation overview", "Method choice", "Implementation details" ], "created": "2025-06-16 10:20:12", "modified": "2026-05-15 08:19:19", "commits": 2 }, { "source": "GettingStarted.Rnw", "filename": "GettingStarted.pdf", "title": "Getting Started with DataSimilarity", "engine": "utils::Sweave", "headings": [ "Introduction", "Workflow", "Examples for case a): We already know which method to apply", "Examples for case b): We are looking for a method to apply" ], "created": "2025-06-16 10:20:12", "modified": "2026-05-15 08:19:19", "commits": 2 } ], "_score": 2.6020599913279625, "_indexed": true, "_nocasepkg": "datasimilarity", "_universes": [ "mariekestolte" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.4.0", "date": "2026-09-22T13:07:18.000Z", "distro": "resolute", "commit": "b0bceebe6a415b81875365ba953c80f6b93b259c", "fileid": "https://r2.ropensci.org/2e29d763f5f5894955a01576db7b174df0e2a1f7ca81292fb4fb49895fc972d5", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mariekestolte/actions/runs/35725413831" }, { "r": "4.6.1", "os": "linux", "version": "0.4.0", "date": "2026-09-22T13:07:11.000Z", "distro": "resolute", "commit": "b0bceebe6a415b81875365ba953c80f6b93b259c", "fileid": "https://r2.ropensci.org/ace57f798f956856702d71f68f71ace9a64fe07fb44f840e23203db3c4e75b1c", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mariekestolte/actions/runs/35725413831" }, { "r": "4.5.3", "os": "mac", "version": "0.4.0", "date": "2026-09-22T13:06:13.000Z", "commit": "b0bceebe6a415b81875365ba953c80f6b93b259c", "fileid": "https://r2.ropensci.org/60fbdc45e7b707ee1609a2c5e492e4ae2d0f74ac065828eac5532b78436e8327", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mariekestolte/actions/runs/35725413831" }, { "r": "4.6.1", "os": "mac", "version": "0.4.0", "date": "2026-09-22T13:05:50.000Z", "commit": "b0bceebe6a415b81875365ba953c80f6b93b259c", "fileid": "https://r2.ropensci.org/865e549108df635c70fa33ca343cb029f88b60350fc9828b40b3e231b9f9a34e", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mariekestolte/actions/runs/35725413831" }, { "r": "4.6.0", "os": "wasm", "version": "0.4.0", "date": "2026-09-22T13:06:46.000Z", "commit": "b0bceebe6a415b81875365ba953c80f6b93b259c", "fileid": "https://r2.ropensci.org/bb0ee371ff9bc5632fb25141783afccc6030b077946b523306949e0c80dc35ca", "status": "success", "buildurl": "https://github.com/r-universe/mariekestolte/actions/runs/35725413831" }, { "r": "4.7.0", "os": "win", "version": "0.4.0", "date": "2026-09-22T13:05:24.000Z", "commit": "b0bceebe6a415b81875365ba953c80f6b93b259c", "fileid": "https://r2.ropensci.org/501837ffdd71b8c5182c56d42055b1d3edbd289bd9d8c23cc0c6aaf2343f41a1", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mariekestolte/actions/runs/35725413831" }, { "r": "4.5.3", "os": "win", "version": "0.4.0", "date": "2026-09-22T13:05:51.000Z", "commit": "b0bceebe6a415b81875365ba953c80f6b93b259c", "fileid": "https://r2.ropensci.org/35639b607056158a81171e60ce76b7c8653382e8222517d57e63a38212c92e38", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mariekestolte/actions/runs/35725413831" }, { "r": "4.6.1", "os": "win", "version": "0.4.0", "date": "2026-09-22T13:05:25.000Z", "commit": "b0bceebe6a415b81875365ba953c80f6b93b259c", "fileid": "https://r2.ropensci.org/50e8fdee7b85e5f88a01d8391fb8f6739e183a656d977b0d1d4fdfdc0db7eaa7", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/mariekestolte/actions/runs/35725413831" } ] }