{ "_id": "6aca574cfe5cc25786e8790a", "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": "2026-10-10 14:36:02 UTC", "User": "root" }, "_user": "taylor-arnold", "_type": "src", "_file": "cleanNLP_3.1.0.tar.gz", "_fileid": "https://r2.ropensci.org/de4db912f73986cb547b7989be7f6d05da1b5c5327d0dab9b4c32d1d6e9959f0", "_filesize": 4826932, "_sha256": "de4db912f73986cb547b7989be7f6d05da1b5c5327d0dab9b4c32d1d6e9959f0", "_expires": "2027-01-18T15:18:34.000Z", "_created": "2026-10-10T14:36:02.000Z", "_published": "2026-10-10T15:18:35.977Z", "_buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/38060054502", "_status": "success", "_host": "GitHub-Actions", "_jobs": [ { "job": 114236969754, "time": 121, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "11672778345" }, { "job": 114236969672, "time": 105, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "11672338924" }, { "job": 114236969668, "time": 71, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "11673438319" }, { "job": 114236969694, "time": 95, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "11673907884" }, { "job": 114236385238, "time": 172, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "11672956151" }, { "job": 114236969724, "time": 141, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "11672738428" }, { "job": 114236969753, "time": 72, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "11672278892" }, { "job": 114236969734, "time": 70, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "11673091166" }, { "job": 114236969737, "time": 56, "config": "windows-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "11672498586" } ], "_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 }, "_distro": "resolute", "_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": [], "_tags": [], "_topics": [ "algorithms", "spatial-analysis", "text-analysis" ], "_stars": 219, "_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", "followers": 337, "description": "Professor, Data Science & Statistics Faculty in Linguistics and Cognitive Sci. Director, @distant-viewing " }, "_downloads": { "count": 683, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/cleanNLP" }, "_devurl": "https://github.com/statsmaths/cleannlp", "_searchresults": 315, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/cleanNLP.html", "extra/contents.json", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md" ], "_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": 8.537724672965737, "_indexed": true, "_nocasepkg": "cleannlp", "_universes": [ "taylor-arnold", "statsmaths" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "3.1.0", "date": "2026-10-10T14:38:08.000Z", "distro": "resolute", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "https://r2.ropensci.org/df4f4140ffac945069b4172a16817123190b1440bed825712051426ed5de0830", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/38060054502" }, { "r": "4.6.1", "os": "linux", "version": "3.1.0", "date": "2026-10-10T14:38:00.000Z", "distro": "resolute", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "https://r2.ropensci.org/fe9bbe6bf185fcd7eec470fc20735d7e0c6b884090241d8f4a0e451188462bd0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/38060054502" }, { "r": "4.5.3", "os": "mac", "version": "3.1.0", "date": "2026-10-10T15:15:24.000Z", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "https://r2.ropensci.org/e225328edc41f9ed9c3a5c87dadfc334fda92b4ef47a05197c933ca5ea39a1c2", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/38060054502" }, { "r": "4.6.1", "os": "mac", "version": "3.1.0", "date": "2026-10-10T15:18:00.000Z", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "https://r2.ropensci.org/8f5ad02ac0738a657804e60e9a72d276133ed0561dc1bf44da19477d5aa4ac63", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/38060054502" }, { "r": "4.6.0", "os": "wasm", "version": "3.1.0", "date": "2026-10-10T14:38:43.000Z", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "https://r2.ropensci.org/053eb237d470f0c1341792136bf9dd2e72ce4fe247077a6992653b03a3219ec7", "status": "success", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/38060054502" }, { "r": "4.7.0", "os": "win", "version": "3.1.0", "date": "2026-10-10T14:37:15.000Z", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "https://r2.ropensci.org/c4a7799af2f2ce6ee7e66f1189413b56c23cadd214286674cd087237e192debe", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/38060054502" }, { "r": "4.5.3", "os": "win", "version": "3.1.0", "date": "2026-10-10T14:37:14.000Z", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "https://r2.ropensci.org/c6134e7bbb7435c06a8b9787f618800df5701eae9aad6d365add90f529618752", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/38060054502" }, { "r": "4.6.1", "os": "win", "version": "3.1.0", "date": "2026-10-10T14:37:07.000Z", "commit": "fef7c1b376e204f78d8b21e59fa70171e30e7e48", "fileid": "https://r2.ropensci.org/cdbc219af171fdc2f7c6e652d8ed2f10000dce212b565a03a9b4c36c2521c4da", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/taylor-arnold/actions/runs/38060054502" } ] }