{ "_id": "6a1f18c0b401979e7341edc9", "Package": "textdata", "Title": "Download and Load Various Text Datasets", "Version": "0.4.5.9000", "Authors@R": "c(\nperson(\"Emil\", \"Hvitfeldt\", , \"emilhhvitfeldt@gmail.com\", role = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0002-0679-1945\")),\nperson(\"Julia\", \"Silge\", , \"julia.silge@gmail.com\", role = \"ctb\",\ncomment = c(ORCID = \"0000-0002-3671-836X\"))\n)", "Description": "Provides a framework to download, parse, and store text\ndatasets on the disk and load them when needed. Includes\nvarious sentiment lexicons and labeled text data sets for\nclassification and analysis.", "License": "MIT + file LICENSE", "URL": "https://emilhvitfeldt.github.io/textdata/,\nhttps://github.com/EmilHvitfeldt/textdata", "BugReports": "https://github.com/EmilHvitfeldt/textdata/issues", "VignetteBuilder": "knitr", "Encoding": "UTF-8", "RoxygenNote": "7.3.1.9000", "Collate": "'cache_info.R' 'dataset_ag_news.R' 'dataset_dbpedia.R'\n'dataset_imdb.R' 'dataset_sentence_polarity.R' 'dataset_trec.R'\n'embedding_glove.R' 'lexicon_nrc_vad.R' 'lexicon_nrc_eil.R'\n'lexicon_nrc.R' 'lexicon_bing.R' 'lexicon_loughran.R'\n'lexicon_afinn.R' 'download_functions.R' 'info.R'\n'load_dataset.R' 'printer.R' 'process_functions.R'\n'textdata-package.R'", "Config/pak/sysreqs": "cmake make libuv1-dev libx11-dev", "Repository": "https://emilhvitfeldt.r-universe.dev", "Date/Publication": "2024-05-28 22:00:24 UTC", "RemoteUrl": "https://github.com/emilhvitfeldt/textdata", "RemoteRef": "HEAD", "RemoteSha": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "NeedsCompilation": "no", "Packaged": { "Date": "2026-05-17 05:36:04 UTC", "User": "root" }, "Author": "Emil Hvitfeldt [aut, cre] (ORCID:\n),\nJulia Silge [ctb] (ORCID: )", "Maintainer": "Emil Hvitfeldt ", "MD5sum": "7a398e203f59164de3bc69b3a59285e4", "_user": "emilhvitfeldt", "_type": "src", "_file": "textdata_0.4.5.9000.tar.gz", "_fileid": "7da8d4ec58c9180f1f8d1c1e5deb720691e3f130bfa24635bfe338851c63f448", "_filesize": 4776216, "_sha256": "7da8d4ec58c9180f1f8d1c1e5deb720691e3f130bfa24635bfe338851c63f448", "_created": "2026-05-17T05:36:04.000Z", "_published": "2026-06-02T17:54:08.848Z", "_distro": "noble", "_jobs": [ { "job": 79136804262, "time": 135, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7039673610" }, { "job": 79136804242, "time": 136, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7039674009" }, { "job": 79136804307, "time": 78, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7039667827" }, { "job": 79136804423, "time": 104, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7039670558" }, { "job": 79136803275, "time": 184, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7039659808" }, { "job": 79136803377, "time": 112, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7365687393" }, { "job": 79136804013, "time": 86, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7039668689" }, { "job": 79136804709, "time": 69, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7039666899" }, { "job": 79136804107, "time": 76, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7039667665" } ], "_buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/25982468383", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/emilhvitfeldt/textdata", "_commit": { "id": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "author": "Emil Hvitfeldt ", "committer": "GitHub ", "message": "Merge pull request #58 from EmilHvitfeldt/PC-0.4.5\n\nRelease Candidate 0.4.5", "time": 1716933624 }, "_maintainer": { "name": "Emil Hvitfeldt", "email": "emilhhvitfeldt@gmail.com", "login": "emilhvitfeldt", "bluesky": "@emilhvitfeldt.bsky.social", "description": "All things @tidymodels", "uuid": 14034784, "orcid": "0000-0002-0679-1945" }, "_registered": true, "_dependencies": [ { "package": "fs", "role": "Imports" }, { "package": "rappdirs", "role": "Imports" }, { "package": "readr", "role": "Imports" }, { "package": "tibble", "role": "Imports" }, { "package": "covr", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "testthat", "version": ">= 2.1.0", "role": "Suggests" } ], "_owner": "emilhvitfeldt", "_selfowned": true, "_usedby": 3, "_updates": [], "_tags": [], "_topics": [ "text-datasets" ], "_stars": 78, "_contributors": [ { "user": "emilhvitfeldt", "count": 134, "uuid": 14034784 }, { "user": "juliasilge", "count": 5, "uuid": 12505835 }, { "user": "ellisvalentiner", "count": 1, "uuid": 9932219 }, { "user": "jmclawson", "count": 1, "uuid": 3894072 }, { "user": "jonthegeek", "count": 1, "uuid": 33983824 }, { "user": "olivroy", "count": 1, "uuid": 52606734 } ], "_userbio": { "uuid": 14034784, "type": "user", "name": "Emil Hvitfeldt", "description": "All things @tidymodels" }, "_downloads": { "count": 9059, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/textdata" }, "_devurl": "https://github.com/emilhvitfeldt/textdata", "_pkgdown": "https://emilhvitfeldt.github.io/textdata/", "_searchresults": 1548, "_rbuild": "4.6.0", "_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/textdata.html", "manual.pdf" ], "_homeurl": "https://github.com/emilhvitfeldt/textdata", "_realowner": "emilhvitfeldt", "_cranurl": true, "_releases": [ { "version": "0.1.0", "date": "2019-06-12" }, { "version": "0.2.0", "date": "2019-07-22" }, { "version": "0.3.0", "date": "2019-08-28" }, { "version": "0.4.0", "date": "2020-03-06" }, { "version": "0.4.1", "date": "2020-05-04" }, { "version": "0.4.2", "date": "2022-05-02" }, { "version": "0.4.3", "date": "2022-08-15" }, { "version": "0.4.4", "date": "2022-09-02" }, { "version": "0.4.5", "date": "2024-05-28" } ], "_exports": [ "cache_info", "catalogue", "dataset_ag_news", "dataset_dbpedia", "dataset_imdb", "dataset_sentence_polarity", "dataset_trec", "embedding_glove27b", "embedding_glove42b", "embedding_glove6b", "embedding_glove840b", "lexicon_afinn", "lexicon_bing", "lexicon_loughran", "lexicon_nrc", "lexicon_nrc_eil", "lexicon_nrc_vad", "load_dataset" ], "_help": [ { "page": "cache_info", "title": "List folders and their sizes in cache", "topics": [ "cache_info" ] }, { "page": "catalogue", "title": "Catalogue of all available data sources", "topics": [ "catalogue" ] }, { "page": "dataset_ag_news", "title": "AG's News Topic Classification Dataset", "concept": [ "topic" ], "topics": [ "dataset_ag_news" ] }, { "page": "dataset_dbpedia", "title": "DBpedia Ontology Dataset", "concept": [ "topic" ], "topics": [ "dataset_dbpedia" ] }, { "page": "dataset_imdb", "title": "IMDB Large Movie Review Dataset", "concept": [ "topic sentiment" ], "topics": [ "dataset_imdb" ] }, { "page": "dataset_sentence_polarity", "title": "v1.0 sentence polarity dataset", "concept": [ "sentiment" ], "topics": [ "dataset_sentence_polarity" ] }, { "page": "dataset_trec", "title": "TREC dataset", "concept": [ "topic" ], "topics": [ "dataset_trec" ] }, { "page": "embedding_glove", "title": "Global Vectors for Word Representation", "concept": [ "embeddings" ], "topics": [ "embedding_glove", "embedding_glove27b", "embedding_glove42b", "embedding_glove6b", "embedding_glove840b" ] }, { "page": "lexicon_afinn", "title": "AFINN-111 dataset", "concept": [ "lexicon" ], "topics": [ "lexicon_afinn" ] }, { "page": "lexicon_bing", "title": "Bing sentiment lexicon", "concept": [ "lexicon" ], "topics": [ "lexicon_bing" ] }, { "page": "lexicon_loughran", "title": "Loughran-McDonald sentiment lexicon", "concept": [ "lexicon" ], "topics": [ "lexicon_loughran" ] }, { "page": "lexicon_nrc", "title": "NRC word-emotion association lexicon", "concept": [ "lexicon" ], "topics": [ "lexicon_nrc" ] }, { "page": "lexicon_nrc_eil", "title": "NRC Emotion Intensity Lexicon (aka Affect Intensity Lexicon) v0.5", "concept": [ "lexicon" ], "topics": [ "lexicon_nrc_eil" ] }, { "page": "lexicon_nrc_vad", "title": "The NRC Valence, Arousal, and Dominance Lexicon", "concept": [ "lexicon" ], "topics": [ "lexicon_nrc_vad" ] } ], "_pkglogo": "https://github.com/emilhvitfeldt/textdata/raw/HEAD/man/figures/logo.png", "_readme": "https://github.com/emilhvitfeldt/textdata/raw/HEAD/README.md", "_rundeps": [ "bit", "bit64", "cli", "clipr", "cpp11", "crayon", "fs", "glue", "hms", "lifecycle", "magrittr", "pillar", "pkgconfig", "prettyunits", "progress", "R6", "rappdirs", "readr", "rlang", "tibble", "tidyselect", "tzdb", "utf8", "vctrs", "vroom", "withr" ], "_vignettes": [ { "source": "How-to-add-a-data-set.Rmd", "filename": "How-to-add-a-data-set.html", "title": "How to add a data set", "engine": "knitr::rmarkdown", "headings": [ "Guidelines for textdata datasets", "Classification datasets" ], "created": "2019-06-08 22:16:31", "modified": "2022-05-02 16:30:06", "commits": 8 } ], "_score": 10.391128336806617, "_indexed": true, "_nocasepkg": "textdata", "_universes": [ "emilhvitfeldt" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.4.5.9000", "date": "2026-05-17T05:38:16.000Z", "distro": "noble", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "1c624413cde5e20957657efeca2572db5533990c37c76f3d69037bddacbb4ef3", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/25982468383" }, { "r": "4.6.0", "os": "linux", "version": "0.4.5.9000", "date": "2026-05-17T05:38:16.000Z", "distro": "noble", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "0e394b973b3968bd6bed6430e8e91f5a288c8dee7e3dede2995c057ca553cf86", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/25982468383" }, { "r": "4.5.3", "os": "mac", "version": "0.4.5.9000", "date": "2026-05-17T05:37:27.000Z", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "93852c491341395a9fe24adbf85d665a705d235a0bf7dce0c8202b53d39c86dd", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/25982468383" }, { "r": "4.6.0", "os": "mac", "version": "0.4.5.9000", "date": "2026-05-17T05:37:48.000Z", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "f7f2b492a35fb470b54cb3fa06ff2f8195894e0ba9c933ab491e41ef9b6a0fdd", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/25982468383" }, { "r": "4.7.0", "os": "win", "version": "0.4.5.9000", "date": "2026-05-17T05:37:19.000Z", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "7bfdb7574b038072b278255d383f4b876b42589b671a24922e1ec5ef5283e293", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/25982468383" }, { "r": "4.5.3", "os": "win", "version": "0.4.5.9000", "date": "2026-05-17T05:37:06.000Z", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "ff1113e7926e4c1a55d93fff670bf8ad7156089e83241e3bb355d7419ae5111f", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/25982468383" }, { "r": "4.6.0", "os": "win", "version": "0.4.5.9000", "date": "2026-05-17T05:37:12.000Z", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "8f21c62725ef027c81a794c3f525ff691cb4f99d93bf8bff3bd04dea8b6658fa", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/25982468383" }, { "r": "4.6.0", "os": "wasm", "version": "0.4.5.9000", "date": "2026-06-02T17:53:51.000Z", "commit": "7a99a97b4e7f30927bc5509d5dfaafd2aa8b58d6", "fileid": "d59d9403c931bc21eda88eac55732b1d765013919c2adbe2120a6cacc48619ba", "status": "success", "buildurl": "https://github.com/r-universe/emilhvitfeldt/actions/runs/25982468383" } ] }