{
  "_id": "6a13ff5bacfb0bcc41d37a9a",
  "Package": "casimir",
  "Title": "Comparing Automated Subject Indexing Methods in R",
  "Version": "0.3.3",
  "Authors@R": "c(\nperson(\"Maximilian\", \"Kähler\", , \"m.kaehler@dnb.de\", role = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0003-4695-0565\")),\nperson(\"Markus\", \"Schumacher\", , \"m.schumacher@dnb.de\", role = c(\"aut\")),\nperson(\"Deutsche Nationalbibliothek\", , role = c(\"cph\"))\n)",
  "Description": "Perform evaluation of automatic subject indexing methods.\nThe main focus of the package is to enable efficient\ncomputation of set retrieval and ranked retrieval metrics\nacross multiple dimensions of a dataset, e.g. document strata\nor subsets of the label set. The package also provides the\npossibility of computing bootstrap confidence intervals for all\nmajor metrics, with seamless integration of parallel\ncomputation and propensity scored variants of standard metrics.",
  "License": "MIT + file LICENSE",
  "Encoding": "UTF-8",
  "Roxygen": "list(markdown = TRUE)",
  "RoxygenNote": "7.3.1",
  "Config/testthat/edition": "3",
  "LazyData": "true",
  "URL": "https://deutsche-nationalbibliothek.github.io/casimir/",
  "Config/pak/sysreqs": "libicu-dev",
  "Repository": "https://deutsche-nationalbibliothek.r-universe.dev",
  "Date/Publication": "2025-11-26 09:29:03 UTC",
  "RemoteUrl": "https://github.com/deutsche-nationalbibliothek/casimir",
  "RemoteRef": "HEAD",
  "RemoteSha": "49ff488089ebdc20811e7132d1b9b5cf882edf74",
  "NeedsCompilation": "no",
  "Packaged": {
    "Date": "2026-05-25 07:46:55 UTC",
    "User": "root"
  },
  "Author": "Maximilian Kähler [aut, cre] (ORCID:\n<https://orcid.org/0000-0003-4695-0565>),\nMarkus Schumacher [aut],\nDeutsche Nationalbibliothek [cph]",
  "Maintainer": "Maximilian Kähler <m.kaehler@dnb.de>",
  "MD5sum": "115cb69103b47e8589bf037d95754d70",
  "_user": "deutsche-nationalbibliothek",
  "_type": "src",
  "_file": "casimir_0.3.3.tar.gz",
  "_fileid": "0d5ae197a86bb6557b7f042946196c44558bba33edebb219b6e84745c55711e6",
  "_filesize": 405557,
  "_sha256": "0d5ae197a86bb6557b7f042946196c44558bba33edebb219b6e84745c55711e6",
  "_created": "2026-05-25T07:46:55.000Z",
  "_published": "2026-05-25T07:50:51.348Z",
  "_distro": "noble",
  "_jobs": [
    {
      "job": 77675909464,
      "time": 196,
      "config": "linux-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "7194011147"
    },
    {
      "job": 77675909490,
      "time": 189,
      "config": "linux-release-x86_64",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "7194009624"
    },
    {
      "job": 77675909462,
      "time": 176,
      "config": "macos-oldrel-arm64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "7193998012"
    },
    {
      "job": 77675909491,
      "time": 145,
      "config": "macos-release-arm64",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "7193993259"
    },
    {
      "job": 77675407876,
      "time": 242,
      "config": "source",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "7193959738"
    },
    {
      "job": 77675909454,
      "time": 132,
      "config": "wasm-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "7193994454"
    },
    {
      "job": 77675909473,
      "time": 158,
      "config": "windows-devel",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "7194001069"
    },
    {
      "job": 77675909542,
      "time": 127,
      "config": "windows-oldrel",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "7193993263"
    },
    {
      "job": 77675909480,
      "time": 128,
      "config": "windows-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "7193993577"
    }
  ],
  "_buildurl": "https://github.com/r-universe/deutsche-nationalbibliothek/actions/runs/26389437583",
  "_status": "success",
  "_host": "GitHub-Actions",
  "_upstream": "https://github.com/deutsche-nationalbibliothek/casimir",
  "_commit": {
    "id": "49ff488089ebdc20811e7132d1b9b5cf882edf74",
    "author": "Kähler, Maximilian <m.kaehler@dnb.de>",
    "committer": "Kähler, Maximilian <m.kaehler@dnb.de>",
    "message": "Update install instructs to include conda\n",
    "time": 1764149343
  },
  "_maintainer": {
    "name": "Maximilian Kähler",
    "email": "m.kaehler@dnb.de",
    "login": "mfakaehler",
    "mastodon": "@mfakaehler@openbiblio.social",
    "orcid": "0000-0003-4695-0565",
    "description": "Data Scientist and Research Software Engineer @deutsche-nationalbibliothek ",
    "uuid": 60214565
  },
  "_registered": true,
  "_dependencies": [
    {
      "package": "R",
      "version": ">= 4.1.0",
      "role": "Depends"
    },
    {
      "package": "dplyr",
      "version": ">= 1.1.1",
      "role": "Imports"
    },
    {
      "package": "furrr",
      "role": "Imports"
    },
    {
      "package": "purrr",
      "role": "Imports"
    },
    {
      "package": "rsample",
      "role": "Imports"
    },
    {
      "package": "tidyr",
      "role": "Imports"
    },
    {
      "package": "rlang",
      "role": "Imports"
    },
    {
      "package": "collapse",
      "version": ">= 2.1.0",
      "role": "Imports"
    },
    {
      "package": "stringr",
      "role": "Imports"
    },
    {
      "package": "options",
      "role": "Imports"
    },
    {
      "package": "withr",
      "role": "Imports"
    },
    {
      "package": "testthat",
      "version": ">= 3.0.0",
      "role": "Suggests"
    },
    {
      "package": "tibble",
      "role": "Suggests"
    },
    {
      "package": "tidyverse",
      "role": "Suggests"
    },
    {
      "package": "ggplot2",
      "role": "Suggests"
    },
    {
      "package": "future",
      "role": "Suggests"
    }
  ],
  "_owner": "deutsche-nationalbibliothek",
  "_selfowned": true,
  "_usedby": 0,
  "_updates": [
    {
      "week": "2025-39",
      "n": 10
    },
    {
      "week": "2025-41",
      "n": 17
    },
    {
      "week": "2025-42",
      "n": 5
    },
    {
      "week": "2025-45",
      "n": 5
    },
    {
      "week": "2025-46",
      "n": 1
    },
    {
      "week": "2025-47",
      "n": 1
    },
    {
      "week": "2025-48",
      "n": 1
    }
  ],
  "_tags": [
    {
      "name": "v0.1.0",
      "date": "2025-09-25"
    },
    {
      "name": "v0.2.1",
      "date": "2025-10-06"
    },
    {
      "name": "v0.2.3",
      "date": "2025-10-09"
    },
    {
      "name": "v0.3.1",
      "date": "2025-10-13"
    },
    {
      "name": "v0.3.2",
      "date": "2025-10-13"
    },
    {
      "name": "v0.3.3",
      "date": "2025-11-20"
    }
  ],
  "_topics": [
    "code4lib",
    "glam",
    "information-retrieval",
    "metrics",
    "multilabel-classification",
    "subject-indexing",
    "xmlc"
  ],
  "_stars": 0,
  "_contributors": [
    {
      "user": "mfakaehler",
      "count": 66,
      "uuid": 60214565
    },
    {
      "user": "mschumac",
      "count": 8,
      "uuid": 98738162
    }
  ],
  "_userbio": {
    "uuid": 75751762,
    "type": "organization",
    "name": "Deutsche Nationalbibliothek",
    "description": "Open Source Projekte der Deutschen Nationalbibliothek"
  },
  "_downloads": {
    "count": 169,
    "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/casimir"
  },
  "_devurl": "https://github.com/deutsche-nationalbibliothek/casimir",
  "_pkgdown": "https://deutsche-nationalbibliothek.github.io/casimir/",
  "_searchresults": 21,
  "_rbuild": "4.6.0",
  "_assets": [
    "extra/casimir.html",
    "extra/citation.cff",
    "extra/citation.html",
    "extra/citation.json",
    "extra/citation.txt",
    "extra/contents.json",
    "extra/readme.html",
    "extra/readme.md",
    "manual.pdf"
  ],
  "_homeurl": "https://github.com/deutsche-nationalbibliothek/casimir",
  "_realowner": "deutsche-nationalbibliothek",
  "_cranurl": true,
  "_releases": [
    {
      "version": "0.3.3",
      "date": "2025-11-17"
    }
  ],
  "_exports": [
    "apply_threshold",
    "compute_intermediate_results",
    "compute_intermediate_results_rr",
    "compute_pr_auc",
    "compute_pr_auc_from_curve",
    "compute_pr_curve",
    "compute_propensity_scores",
    "compute_ranked_retrieval_scores",
    "compute_set_retrieval_scores",
    "create_comparison",
    "create_rank_col",
    "join_propensity_scores",
    "summarise_intermediate_results"
  ],
  "_datasets": [
    {
      "name": "dnb_gold_standard",
      "title": "DNB gold standard data for computing evaluation metrics",
      "object": "dnb_gold_standard",
      "class": [
        "tbl_df",
        "tbl",
        "data.frame"
      ],
      "fields": [
        "doc_id",
        "label_id"
      ],
      "rows": 337,
      "table": true,
      "tojson": true
    },
    {
      "name": "dnb_label_distribution",
      "title": "DNB label distribution for computing propensity scored metrics",
      "object": "dnb_label_distribution",
      "class": [
        "tbl_df",
        "tbl",
        "data.frame"
      ],
      "fields": [
        "label_id",
        "label_freq",
        "n_docs"
      ],
      "rows": 7772,
      "table": true,
      "tojson": true
    },
    {
      "name": "dnb_test_predictions",
      "title": "DNB test predictions for computing evaluation metrics",
      "object": "dnb_test_predictions",
      "class": [
        "tbl_df",
        "tbl",
        "data.frame"
      ],
      "fields": [
        "doc_id",
        "label_id",
        "score"
      ],
      "rows": 10000,
      "table": true,
      "tojson": true
    }
  ],
  "_help": [
    {
      "page": "apply_threshold",
      "title": "Filter predictions based on score and rank",
      "topics": [
        "apply_threshold"
      ]
    },
    {
      "page": "boot_worker_fn",
      "title": "Compute bootstrap replica of pr auc",
      "topics": [
        "boot_worker_fn"
      ]
    },
    {
      "page": "check_id_vars",
      "title": "Coerce id columns to character",
      "topics": [
        "check_id_vars"
      ]
    },
    {
      "page": "check_id_vars_col",
      "title": "Coerce column to character",
      "topics": [
        "check_id_vars_col"
      ]
    },
    {
      "page": "check_repair_relevance_compare",
      "title": "Check for inconsistent relevance values",
      "topics": [
        "check_repair_relevance_compare"
      ]
    },
    {
      "page": "check_repair_relevance_pred",
      "title": "Check for inconsistent relevance values",
      "topics": [
        "check_repair_relevance_pred"
      ]
    },
    {
      "page": "compute_intermediate_results",
      "title": "Compute intermediate set retrieval results per group",
      "topics": [
        "compute_intermediate_results",
        "compute_intermediate_results_dplyr"
      ]
    },
    {
      "page": "compute_intermediate_results_rr",
      "title": "Compute intermediate ranked retrieval results per group",
      "topics": [
        "compute_intermediate_results_rr"
      ]
    },
    {
      "page": "compute_pr_auc",
      "title": "Compute area under precision-recall curve",
      "topics": [
        "compute_pr_auc"
      ]
    },
    {
      "page": "compute_pr_auc_from_curve",
      "title": "Compute area under precision-recall curve",
      "topics": [
        "compute_pr_auc_from_curve"
      ]
    },
    {
      "page": "compute_pr_curve",
      "title": "Compute precision-recall curve",
      "topics": [
        "compute_pr_curve"
      ]
    },
    {
      "page": "compute_propensity_scores",
      "title": "Compute inverse propensity scores",
      "topics": [
        "compute_propensity_scores"
      ]
    },
    {
      "page": "compute_ranked_retrieval_scores",
      "title": "Compute ranked retrieval scores",
      "topics": [
        "compute_ranked_retrieval_scores"
      ]
    },
    {
      "page": "compute_set_retrieval_scores",
      "title": "Compute multi-label metrics",
      "topics": [
        "compute_set_retrieval_scores",
        "compute_set_retrieval_scores_dplyr"
      ]
    },
    {
      "page": "create_comparison",
      "title": "Join gold standard and predicted results",
      "topics": [
        "create_comparison"
      ]
    },
    {
      "page": "create_rank_col",
      "title": "Create a rank column",
      "topics": [
        "create_rank_col",
        "create_rank_col_dplyr"
      ]
    },
    {
      "page": "dcg_score",
      "title": "Helper function for document-wise computation of ranked retrieval scores",
      "topics": [
        "dcg_score"
      ]
    },
    {
      "page": "dnb_gold_standard",
      "title": "DNB gold standard data for computing evaluation metrics",
      "topics": [
        "dnb_gold_standard"
      ]
    },
    {
      "page": "dnb_label_distribution",
      "title": "DNB label distribution for computing propensity scored metrics",
      "topics": [
        "dnb_label_distribution"
      ]
    },
    {
      "page": "dnb_test_predictions",
      "title": "DNB test predictions for computing evaluation metrics",
      "topics": [
        "dnb_test_predictions"
      ]
    },
    {
      "page": "find_ps_rprec_deno",
      "title": "Compute the denominator for R-precision",
      "topics": [
        "find_ps_rprec_deno",
        "find_ps_rprec_deno_dplyr"
      ]
    },
    {
      "page": "generate_pr_auc_replica",
      "title": "Compute bootstrap replica of pr auc",
      "topics": [
        "generate_pr_auc_replica"
      ]
    },
    {
      "page": "generate_replicate_results",
      "title": "Compute bootstrapping results",
      "topics": [
        "generate_replicate_results",
        "generate_replicate_results_dplyr"
      ]
    },
    {
      "page": "helper_f",
      "title": "Calculate bootstrapping results for one sample",
      "topics": [
        "helper_f"
      ]
    },
    {
      "page": "helper_f_dplyr",
      "title": "Calculate bootstrapping results for one sample",
      "topics": [
        "helper_f_dplyr"
      ]
    },
    {
      "page": "join_propensity_scores",
      "title": "Join propensity scores",
      "topics": [
        "join_propensity_scores",
        "join_propensity_scores_dplyr"
      ]
    },
    {
      "page": "lrap_score",
      "title": "Helper function for document-wise computation of ranked retrieval scores",
      "topics": [
        "lrap_score"
      ]
    },
    {
      "page": "ndcg_score",
      "title": "Helper function for document-wise computation of ranked retrieval scores",
      "topics": [
        "ndcg_score"
      ]
    },
    {
      "page": "option_params",
      "title": "Declaration of options to be used as identical function arguments",
      "topics": [
        "option_params"
      ]
    },
    {
      "page": "options",
      "title": "casimir Options",
      "topics": [
        "options"
      ]
    },
    {
      "page": "pr_curve_post_processing",
      "title": "Postprocessing of pr curve data",
      "topics": [
        "pr_curve_post_processing"
      ]
    },
    {
      "page": "process_cost_fp",
      "title": "Process cost for false positives",
      "topics": [
        "process_cost_fp"
      ]
    },
    {
      "page": "rename_metrics",
      "title": "Rename metrics",
      "topics": [
        "rename_metrics"
      ]
    },
    {
      "page": "set_grouping_var",
      "title": "Set grouping variables",
      "topics": [
        "set_grouping_var"
      ]
    },
    {
      "page": "set_ps_flags",
      "title": "Set flags for propensity scores",
      "topics": [
        "set_ps_flags"
      ]
    },
    {
      "page": "summarise_intermediate_results",
      "title": "Compute the mean of intermediate results",
      "topics": [
        "summarise_intermediate_results"
      ]
    },
    {
      "page": "summarise_intermediate_results_dplyr",
      "title": "Compute the mean of intermediate results",
      "topics": [
        "summarise_intermediate_results_dplyr"
      ]
    }
  ],
  "_readme": "https://github.com/deutsche-nationalbibliothek/casimir/raw/HEAD/README.md",
  "_rundeps": [
    "cli",
    "codetools",
    "collapse",
    "cpp11",
    "digest",
    "dplyr",
    "furrr",
    "future",
    "generics",
    "globals",
    "glue",
    "lifecycle",
    "listenv",
    "magrittr",
    "options",
    "parallelly",
    "pillar",
    "pkgconfig",
    "purrr",
    "R6",
    "Rcpp",
    "rlang",
    "rsample",
    "slider",
    "stringi",
    "stringr",
    "tibble",
    "tidyr",
    "tidyselect",
    "utf8",
    "vctrs",
    "warp",
    "withr"
  ],
  "_score": 3.8662873390841948,
  "_indexed": true,
  "_nocasepkg": "casimir",
  "_universes": [
    "deutsche-nationalbibliothek",
    "mfakaehler"
  ],
  "_binaries": [
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "0.3.3",
      "date": "2026-05-25T07:49:28.000Z",
      "distro": "noble",
      "commit": "49ff488089ebdc20811e7132d1b9b5cf882edf74",
      "fileid": "c9b963671acac19553198ab9d216b5c35672185e89832ac0da814fd1ed94ec09",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/deutsche-nationalbibliothek/actions/runs/26389437583"
    },
    {
      "r": "4.6.0",
      "os": "linux",
      "version": "0.3.3",
      "date": "2026-05-25T07:49:26.000Z",
      "distro": "noble",
      "commit": "49ff488089ebdc20811e7132d1b9b5cf882edf74",
      "fileid": "98cf693f75160b47335452c3882d5b16ccd55fffb95237528861236eb95413f1",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/deutsche-nationalbibliothek/actions/runs/26389437583"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "0.3.3",
      "date": "2026-05-25T07:49:03.000Z",
      "commit": "49ff488089ebdc20811e7132d1b9b5cf882edf74",
      "fileid": "40cf19e275d09cb1f7d74014e31d44b1b0f8ba4a848cd7692d778c12116a84f0",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/deutsche-nationalbibliothek/actions/runs/26389437583"
    },
    {
      "r": "4.6.0",
      "os": "mac",
      "version": "0.3.3",
      "date": "2026-05-25T07:48:49.000Z",
      "commit": "49ff488089ebdc20811e7132d1b9b5cf882edf74",
      "fileid": "0ae212f7d8ab69284d60d496a69d0bfe5259c739f080e5f1f5fb96de0e5555c1",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/deutsche-nationalbibliothek/actions/runs/26389437583"
    },
    {
      "r": "4.6.0",
      "os": "wasm",
      "version": "0.3.3",
      "date": "2026-05-25T07:49:28.000Z",
      "commit": "49ff488089ebdc20811e7132d1b9b5cf882edf74",
      "fileid": "e164079745e83a4a29ed36ce320bae53424b81114cba2d324e36a505067f3448",
      "status": "success",
      "buildurl": "https://github.com/r-universe/deutsche-nationalbibliothek/actions/runs/26389437583"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "0.3.3",
      "date": "2026-05-25T07:48:43.000Z",
      "commit": "49ff488089ebdc20811e7132d1b9b5cf882edf74",
      "fileid": "a21e8b453c1c662e1a883fdcd3aac0211bd1767e4bfb636c4cd090556ba97d72",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/deutsche-nationalbibliothek/actions/runs/26389437583"
    },
    {
      "r": "4.5.3",
      "os": "win",
      "version": "0.3.3",
      "date": "2026-05-25T07:48:23.000Z",
      "commit": "49ff488089ebdc20811e7132d1b9b5cf882edf74",
      "fileid": "df8305d19f6845548a8d256098a411d57e3dfd128270cc47c9f58ddaf9bd162b",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/deutsche-nationalbibliothek/actions/runs/26389437583"
    },
    {
      "r": "4.6.0",
      "os": "win",
      "version": "0.3.3",
      "date": "2026-05-25T07:48:16.000Z",
      "commit": "49ff488089ebdc20811e7132d1b9b5cf882edf74",
      "fileid": "e7f9d3648a764f85281fba028fb92662cf34701a1602ca546c5b3cb6253e20fc",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/deutsche-nationalbibliothek/actions/runs/26389437583"
    }
  ]
}