{ "_id": "6a215569cd65a98ecbd2e17e", "Package": "cleanNLP", "Type": "Package", "Title": "A Tidy Data Model for Natural Language Processing", "Version": "3.1.0", "Author": "Taylor B. Arnold [aut, cre]", "Maintainer": "Taylor B. Arnold ", "Description": "Provides a set of fast tools for converting a textual\ncorpus into a set of normalized tables. Users may make use of\nthe 'udpipe' back end with no external dependencies, or a\nPython back ends with 'spaCy' . Exposed\nannotation tasks include tokenization, part of speech tagging,\nnamed entity recognition, and dependency parsing.", "SystemRequirements": "Python (>= 3.7.0)", "License": "LGPL-2", "URL": "https://statsmaths.github.io/cleanNLP/", "BugReports": "https://github.com/statsmaths/cleanNLP/issues", "LazyData": "true", "Encoding": "UTF-8", "VignetteBuilder": "knitr", "RoxygenNote": "7.3.1", "Config/pak/sysreqs": "libicu-dev libpng-dev python3", "Repository": "https://taylor-arnold.r-universe.dev", "Date/Publication": "2025-06-08 14:20:56 UTC", "RemoteUrl": "https://github.com/taylor-arnold/rpkg", "RemoteRef": "HEAD", "RemoteSha": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "RemoteSubdir": "cleanNLP", "NeedsCompilation": "no", "Packaged": { "Date": "2026-06-04 10:34:43 UTC", "User": "root" }, "MD5sum": "f837ad2be524ed039f66fb87bf8fc5b8", "_user": "taylor-arnold", "_type": "src", "_file": "cleanNLP_3.1.0.tar.gz", "_fileid": "049bc8756ac6880f10fc2d5d0f3623b92ae306b65483a21979deac483b3e041b", "_filesize": 4829076, "_sha256": "049bc8756ac6880f10fc2d5d0f3623b92ae306b65483a21979deac483b3e041b", "_created": "2026-06-04T10:34:43.000Z", "_published": "2026-06-04T10:37:29.331Z", "_distro": "noble", "_jobs": [ { "job": 79500597868, "time": 132, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7409273069" }, { "job": 79500597879, "time": 135, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7409273839" }, { "job": 79500597864, "time": 121, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7409268674" }, { "job": 79500597852, "time": 98, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7409261221" }, { "job": 79500107928, "time": 189, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7409229686" }, { "job": 79500597875, "time": 107, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7409264620" }, { "job": 79500597907, "time": 72, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7409252962" }, { "job": 79500597888, "time": 87, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7409258089" }, { "job": 79500597890, "time": 76, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7409254287" } ], "_buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/26946312608", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/taylor-arnold/rpkg", "_commit": { "id": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "author": "taylor-arnold ", "committer": "taylor-arnold ", "message": "auto update\n", "time": 1749392456 }, "_maintainer": { "name": "Taylor B. Arnold", "email": "tarnold2@richmond.edu", "login": "taylor-arnold", "description": "Professor, Data Science & Statistics Faculty in Linguistics and Cognitive Sci. Director, @distant-viewing ", "uuid": 5752184 }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.5.0", "role": "Depends" }, { "package": "Matrix", "version": ">= 1.2", "role": "Imports" }, { "package": "udpipe", "role": "Imports" }, { "package": "reticulate", "role": "Imports" }, { "package": "stringi", "role": "Imports" }, { "package": "stats", "role": "Imports" }, { "package": "methods", "role": "Imports" }, { "package": "knitr", "version": ">= 1.15", "role": "Suggests" }, { "package": "rmarkdown", "version": ">= 1.4", "role": "Suggests" }, { "package": "testthat", "version": ">= 1.0.1", "role": "Suggests" }, { "package": "covr", "version": ">= 2.2.2", "role": "Suggests" } ], "_owner": "taylor-arnold", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2025-23", "n": 6 } ], "_tags": [], "_topics": [ "algorithms", "spatial-analysis", "text-analysis" ], "_stars": 218, "_contributors": [ { "user": "taylor-arnold", "count": 6, "uuid": 5752184 }, { "user": "dselivanov", "count": 1, "uuid": 5123805 }, { "user": "emilhvitfeldt", "count": 1, "uuid": 14034784 }, { "user": "joshuaulrich", "count": 1, "uuid": 1023193 }, { "user": "batpigandme", "count": 1, "uuid": 831732 }, { "user": "reisner", "count": 1, "uuid": 490216 } ], "_userbio": { "uuid": 5752184, "type": "user", "name": "Taylor Arnold", "description": "Professor, Data Science & Statistics Faculty in Linguistics and Cognitive Sci. Director, @distant-viewing " }, "_downloads": { "count": 558, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/cleanNLP" }, "_devurl": "https://github.com/statsmaths/cleannlp", "_searchresults": 267, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/cleanNLP.html", "extra/contents.json", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_homeurl": "https://github.com/taylor-arnold/rpkg", "_realowner": "taylor-arnold", "_cranurl": true, "_releases": [ { "version": "0.24", "date": "2016-11-11" }, { "version": "1.5.2", "date": "2017-04-12" }, { "version": "1.9.0", "date": "2017-05-27" }, { "version": "1.10.0", "date": "2017-07-01" }, { "version": "2.0.3", "date": "2018-01-22" }, { "version": "2.3.0", "date": "2018-11-18" }, { "version": "3.0.0", "date": "2019-10-22" }, { "version": "3.0.2", "date": "2020-03-08" }, { "version": "3.0.3", "date": "2020-10-13" }, { "version": "3.0.4", "date": "2022-08-15" }, { "version": "3.0.7", "date": "2023-11-16" }, { "version": "3.1.0", "date": "2024-05-20" } ], "_exports": [ "cnlp_annotate", "cnlp_download_spacy", "cnlp_init_spacy", "cnlp_init_stringi", "cnlp_init_udpipe", "cnlp_utils_pca", "cnlp_utils_tf", "cnlp_utils_tfidf" ], "_datasets": [ { "name": "un", "title": "Universal Declaration of Human Rights", "object": "un", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "doc_id", "text" ], "rows": 30, "table": true, "tojson": true }, { "name": "word_frequency", "title": "Most frequent English words", "object": "word_frequency", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "language", "word", "frequency" ], "rows": 150000, "table": true, "tojson": true } ], "_help": [ { "page": "cleanNLP-package", "title": "cleanNLP: A Tidy Data Model for Natural Language Processing", "topics": [ "cleanNLP-package", "cleanNLP" ] }, { "page": "cnlp_annotate", "title": "Run the annotation pipeline on a set of documents", "topics": [ "cnlp_annotate" ] }, { "page": "cnlp_download_spacy", "title": "Download model files needed for spacy", "topics": [ "cnlp_download_spacy" ] }, { "page": "cnlp_init_spacy", "title": "Interface for initializing the spacy backend", "topics": [ "cnlp_init_spacy" ] }, { "page": "cnlp_init_stringi", "title": "Interface for initializing the standard R backend", "topics": [ "cnlp_init_stringi" ] }, { "page": "cnlp_init_udpipe", "title": "Interface for initializing the udpipe backend", "topics": [ "cnlp_init_udpipe" ] }, { "page": "cnlp_utils_pca", "title": "Compute Principal Components and store as a Data Frame", "topics": [ "cnlp_utils_pca" ] }, { "page": "cnlp_utils_tfidf", "title": "Construct the TF-IDF Matrix from Annotation or Data Frame", "topics": [ "cnlp_utils_tf", "cnlp_utils_tfidf" ] }, { "page": "un", "title": "Universal Declaration of Human Rights", "topics": [ "un" ] }, { "page": "word_frequency", "title": "Most frequent English words", "topics": [ "word_frequency" ] } ], "_readme": "https://github.com/taylor-arnold/rpkg/raw/HEAD/cleanNLP/README.md", "_rundeps": [ "data.table", "here", "jsonlite", "lattice", "Matrix", "png", "rappdirs", "Rcpp", "RcppTOML", "reticulate", "rlang", "rprojroot", "stringi", "udpipe", "withr" ], "_vignettes": [ { "source": "wikipedia.Rmd", "filename": "wikipedia.html", "title": "Creating Text Visualizations with Wikipedia Data", "author": "Taylor Arnold", "engine": "knitr::rmarkdown", "headings": [ "Grabbing the data", "Running the cleanNLP annotation", "Reconstructing the text" ], "created": "2025-06-08 13:15:30", "modified": "2025-06-08 13:15:30", "commits": 1 }, { "source": "state-of-union.Rmd", "filename": "state-of-union.html", "title": "Exploring the State of the Union Addresses: A Case Study with cleanNLP", "author": "Taylor Arnold", "engine": "knitr::rmarkdown", "headings": [ "Running the cleanNLP annotation", "Exploratory Analysis", "Models", "Principal Component Analysis (PCA)", "Topic Models (LDA)", "Predictive Models" ], "created": "2025-06-08 13:15:30", "modified": "2025-06-08 13:15:30", "commits": 1 } ], "_score": 8.4639377593052, "_indexed": true, "_nocasepkg": "cleannlp", "_universes": [ "taylor-arnold", "statsmaths" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "3.1.0", "date": "2026-06-04T10:36:58.000Z", "distro": "noble", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "4f6a7ce5176f7dbd077eb9679fd6090c98958ff9dc5004737740122b49c1468a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/26946312608" }, { "r": "4.6.0", "os": "linux", "version": "3.1.0", "date": "2026-06-04T10:37:00.000Z", "distro": "noble", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "d8b5effd7998a14bcfc2c18b6f9d80b1aca9611e4baccf0b20b3b24043aa6c9b", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/26946312608" }, { "r": "4.5.3", "os": "mac", "version": "3.1.0", "date": "2026-06-04T10:36:44.000Z", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "34afad477a68875a4b70a0d97858af2b15543905f540988efea39356b69a205b", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/26946312608" }, { "r": "4.6.0", "os": "mac", "version": "3.1.0", "date": "2026-06-04T10:36:26.000Z", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "ef77654b45c0d7f60afd08f22060984c8d143ee67c474504d06a84b175a11de3", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/26946312608" }, { "r": "4.6.0", "os": "wasm", "version": "3.1.0", "date": "2026-06-04T10:36:48.000Z", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "736cc7054037493d5408b24b5cc251c62850083208e4976e0202b50f6ff983dc", "status": "success", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/26946312608" }, { "r": "4.7.0", "os": "win", "version": "3.1.0", "date": "2026-06-04T10:35:55.000Z", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "8b85c0616f1058517e28f04237abe81918808b57e9bfa6163b80f4e578ffe53c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/26946312608" }, { "r": "4.5.3", "os": "win", "version": "3.1.0", "date": "2026-06-04T10:36:08.000Z", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "6b7c15d8bde8c9eab1562b1605ca796c2c0a4797844f8ebe317fce01f8f267d8", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/26946312608" }, { "r": "4.6.0", "os": "win", "version": "3.1.0", "date": "2026-06-04T10:35:58.000Z", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "e3cd79183280af4c705389c510047cc37688c511a079e9629afa54351c8c00ba", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/26946312608" } ] }