{ "_id": "6a13ee48acfb0bcc41d2f7bd", "Package": "text2vec", "Type": "Package", "Version": "0.6.6", "Title": "Modern Text Mining Framework for R", "License": "GPL (>= 2) | file LICENSE", "Description": "Fast and memory-friendly tools for text vectorization,\ntopic modeling (LDA, LSA), word embeddings (GloVe),\nsimilarities. This package provides a source-agnostic streaming\nAPI, which allows researchers to perform analysis of\ncollections of documents which are larger than available RAM.\nAll core functions are parallelized to benefit from multicore\nmachines.", "Authors@R": "c(\nperson(\"Dmitriy\", \"Selivanov\", role = c(\"aut\", \"cre\", \"cph\"),\nemail = \"selivanov.dmitriy@gmail.com\"),\nperson(\"Manuel\", \"Bickel\", role = c(\"aut\", \"cph\"),\ncomment = \"Coherence measures for topic models\"),\nperson(\"Qing\", \"Wang\", role = c(\"aut\", \"cph\"),\ncomment = \"Author of the WaprLDA C++ code\"))", "Maintainer": "Dmitriy Selivanov ", "Encoding": "UTF-8", "URL": "http://text2vec.org", "BugReports": "https://github.com/dselivanov/text2vec/issues", "VignetteBuilder": "knitr", "LazyData": "true", "RoxygenNote": "7.3.2", "Config/pak/sysreqs": "libicu-dev", "Repository": "https://dselivanov.r-universe.dev", "Date/Publication": "2025-12-01 09:36:22 UTC", "RemoteUrl": "https://github.com/dselivanov/text2vec", "RemoteRef": "HEAD", "RemoteSha": "0b31bdd81f37baaf0bd2c8113cbaa578450c8730", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-05-25 06:29:51 UTC", "User": "root" }, "Author": "Dmitriy Selivanov [aut, cre, cph],\nManuel Bickel [aut, cph] (Coherence measures for topic models),\nQing Wang [aut, cph] (Author of the WaprLDA C++ code)", "MD5sum": "b5dbdc7c681badad57f1628dc5ee43f0", "_user": "dselivanov", "_type": "src", "_file": "text2vec_0.6.6.tar.gz", "_fileid": "f019a0c0c8455b407a8940a55103626385c007135c86de34615a52ec67abe6e9", "_filesize": 2602365, "_sha256": "f019a0c0c8455b407a8940a55103626385c007135c86de34615a52ec67abe6e9", "_created": "2026-05-25T06:29:51.000Z", "_published": "2026-05-25T06:38:00.926Z", "_distro": "noble", "_jobs": [ { "job": 77667157098, "time": 249, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "7192931026" }, { "job": 77667157079, "time": 204, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7192920162" }, { "job": 77667157108, "time": 176, "config": "linux-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7192913591" }, { "job": 77667157090, "time": 242, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7192929250" }, { "job": 77667157091, "time": 115, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7192900043" }, { "job": 77667157076, "time": 230, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "7192926431" }, { "job": 77667157084, "time": 115, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7192900429" }, { "job": 77667157083, "time": 426, "config": "macos-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7192974067" }, { "job": 77666671641, "time": 269, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7192874636" }, { "job": 77667157056, "time": 118, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7192900980" }, { "job": 77667157071, "time": 205, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7192920229" }, { "job": 77667157070, "time": 188, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7192916343" }, { "job": 77667157085, "time": 170, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7192911553" } ], "_buildurl": "https://github.com/r-universe/dselivanov/actions/runs/26386681354", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/dselivanov/text2vec", "_commit": { "id": "0b31bdd81f37baaf0bd2c8113cbaa578450c8730", "author": "Dmitry Selivanov ", "committer": "GitHub ", "message": "Merge pull request #352 from dselivanov/dev\n\n0.6.6", "time": 1764581782 }, "_maintainer": { "name": "Dmitriy Selivanov", "email": "selivanov.dmitriy@gmail.com", "login": "dselivanov", "twitter": "@rexyai", "description": "", "uuid": 5123805 }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.6.0", "role": "Depends" }, { "package": "methods", "role": "Depends" }, { "package": "Rcpp", "role": "LinkingTo" }, { "package": "digest", "version": ">= 0.6.8", "role": "LinkingTo" }, { "package": "Matrix", "version": ">= 1.5-2", "role": "Imports" }, { "package": "Rcpp", "version": ">= 1.0.3", "role": "Imports" }, { "package": "R6", "version": ">= 2.3.0", "role": "Imports" }, { "package": "data.table", "version": ">= 1.9.6", "role": "Imports" }, { "package": "rsparse", "version": ">= 0.3.3.4", "role": "Imports" }, { "package": "stringi", "version": ">= 1.1.5", "role": "Imports" }, { "package": "mlapi", "version": ">= 0.1.0", "role": "Imports" }, { "package": "lgr", "version": ">= 0.2", "role": "Imports" }, { "package": "digest", "version": ">= 0.6.8", "role": "Imports" }, { "package": "magrittr", "role": "Suggests" }, { "package": "udpipe", "version": ">= 0.6", "role": "Suggests" }, { "package": "glmnet", "role": "Suggests" }, { "package": "testthat", "role": "Suggests" }, { "package": "covr", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "proxy", "role": "Suggests" }, { "package": "LDAvis", "role": "Suggests" } ], "_owner": "dselivanov", "_selfowned": true, "_usedby": 27, "_updates": [ { "week": "2025-49", "n": 1 } ], "_tags": [ { "name": "v0.6.6", "date": "2025-12-01" } ], "_topics": [ "glove", "latent-dirichlet-allocation", "natural-language-processing", "text-mining", "topic-modeling", "vectorization", "word-embeddings", "word2vec", "cpp" ], "_stars": 870, "_contributors": [ { "user": "dselivanov", "count": 416, "uuid": 5123805 }, { "user": "lmullen", "count": 32, "uuid": 183672 }, { "user": "y-he2", "count": 2, "uuid": 62895281 }, { "user": "chrisss93", "count": 1, "uuid": 5660300 }, { "user": "dfalbel", "count": 1, "uuid": 4706822 }, { "user": "jwijffels", "count": 1, "uuid": 1710810 }, { "user": "kbenoit", "count": 1, "uuid": 2182246 }, { "user": "manuelbickel", "count": 1, "uuid": 19306666 }, { "user": "michaelchirico", "count": 1, "uuid": 7606389 }, { "user": "michaelpaulhirsch", "count": 1, "uuid": 32165250 }, { "user": "mtoto", "count": 1, "uuid": 10297043 }, { "user": "tylerlittlefield", "count": 1, "uuid": 35909636 }, { "user": "chainsawriot", "count": 1, "uuid": 637269 }, { "user": "pshashk", "count": 1, "uuid": 10852024 } ], "_userbio": { "uuid": 5123805, "type": "user", "name": "Dmitry Selivanov" }, "_downloads": { "count": 8438, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/text2vec" }, "_mentions": 4, "_devurl": "https://github.com/dselivanov/text2vec", "_searchresults": 1596, "_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/text2vec.html", "manual.pdf" ], "_homeurl": "https://github.com/dselivanov/text2vec", "_realowner": "dselivanov", "_cranurl": true, "_releases": [ { "version": "0.2.0", "date": "2016-01-10" }, { "version": "0.3.0", "date": "2016-03-31" }, { "version": "0.4.0", "date": "2016-10-07" }, { "version": "0.5.0", "date": "2017-08-08" }, { "version": "0.5.1", "date": "2018-01-11" }, { "version": "0.6", "date": "2020-02-18" }, { "version": "0.6.1", "date": "2022-04-21" }, { "version": "0.6.2", "date": "2022-09-11" }, { "version": "0.6.3", "date": "2022-11-30" }, { "version": "0.6.4", "date": "2023-11-09" }, { "version": "0.6.6", "date": "2025-12-01" } ], "_exports": [ "as.lda_c", "BNS", "char_tokenizer", "check_analogy_accuracy", "coherence", "Collocations", "combine_vocabularies", "create_dtm", "create_tcm", "create_vocabulary", "dist2", "fit", "fit_transform", "GlobalVectors", "GloVe", "hash_vectorizer", "idir", "ifiles", "ifiles_parallel", "itoken", "itoken_parallel", "jsPCA_robust", "LatentDirichletAllocation", "LatentSemanticAnalysis", "LDA", "LSA", "normalize", "pdist2", "perplexity", "postag_lemma_tokenizer", "prepare_analogy_questions", "prune_vocabulary", "psim2", "RelaxedWordMoversDistance", "RWMD", "sim2", "space_tokenizer", "split_into", "TfIdf", "vocab_vectorizer", "vocabulary", "word_tokenizer" ], "_datasets": [ { "name": "movie_review", "title": "IMDB movie reviews", "object": "movie_review", "class": [ "data.frame" ], "fields": [ "id", "sentiment", "review" ], "rows": 5000, "table": true, "tojson": true } ], "_help": [ { "page": "as.lda_c", "title": "Converts document-term matrix sparse matrix to 'lda_c' format", "topics": [ "as.lda_c" ] }, { "page": "BNS", "title": "BNS", "topics": [ "BNS" ] }, { "page": "check_analogy_accuracy", "title": "Checks accuracy of word embeddings on the analogy task", "topics": [ "check_analogy_accuracy" ] }, { "page": "coherence", "title": "Coherence metrics for topic models", "topics": [ "coherence" ] }, { "page": "Collocations", "title": "Collocations model.", "topics": [ "Collocations" ] }, { "page": "combine_vocabularies", "title": "Combines multiple vocabularies into one", "topics": [ "combine_vocabularies" ] }, { "page": "create_dtm", "title": "Document-term matrix construction", "topics": [ "create_dtm", "create_dtm.itoken", "create_dtm.itoken_parallel" ] }, { "page": "create_tcm", "title": "Term-co-occurence matrix construction", "topics": [ "create_tcm", "create_tcm.itoken", "create_tcm.itoken_parallel" ] }, { "page": "create_vocabulary", "title": "Creates a vocabulary of unique terms", "topics": [ "create_vocabulary", "create_vocabulary.character", "create_vocabulary.itoken", "create_vocabulary.itoken_parallel", "vocabulary" ] }, { "page": "distances", "title": "Pairwise Distance Matrix Computation", "topics": [ "dist2", "distances", "pdist2" ] }, { "page": "GloVe", "title": "re-export rsparse::GloVe", "topics": [ "GlobalVectors", "GloVe" ] }, { "page": "ifiles", "title": "Creates iterator over text files from the disk", "topics": [ "idir", "ifiles", "ifiles_parallel" ] }, { "page": "itoken", "title": "Iterators (and parallel iterators) over input objects", "topics": [ "itoken", "itoken.character", "itoken.iterator", "itoken.list", "itoken_parallel", "itoken_parallel.character", "itoken_parallel.iterator", "itoken_parallel.list" ] }, { "page": "jsPCA_robust", "title": "(numerically robust) Dimension reduction via Jensen-Shannon Divergence & Principal Components", "topics": [ "jsPCA_robust" ] }, { "page": "LatentDirichletAllocation", "title": "Creates Latent Dirichlet Allocation model.", "topics": [ "LatentDirichletAllocation", "LDA" ] }, { "page": "LatentSemanticAnalysis", "title": "Latent Semantic Analysis model", "topics": [ "LatentSemanticAnalysis", "LSA" ] }, { "page": "movie_review", "title": "IMDB movie reviews", "topics": [ "movie_review" ] }, { "page": "normalize", "title": "Matrix normalization", "topics": [ "normalize" ] }, { "page": "perplexity", "title": "Perplexity of a topic model", "topics": [ "perplexity" ] }, { "page": "prepare_analogy_questions", "title": "Prepares list of analogy questions", "topics": [ "prepare_analogy_questions" ] }, { "page": "print.text2vec_vocabulary", "title": "Printing Vocabulary", "topics": [ "print.text2vec_vocabulary" ] }, { "page": "prune_vocabulary", "title": "Prune vocabulary", "topics": [ "prune_vocabulary" ] }, { "page": "RelaxedWordMoversDistance", "title": "Creates Relaxed Word Movers Distance (RWMD) model", "topics": [ "RelaxedWordMoversDistance", "RWMD" ] }, { "page": "similarities", "title": "Pairwise Similarity Matrix Computation", "topics": [ "psim2", "sim2", "similarities" ] }, { "page": "split_into", "title": "Split a vector for parallel processing", "topics": [ "split_into" ] }, { "page": "text2vec", "title": "text2vec", "topics": [ "text2vec-package", "text2vec" ] }, { "page": "TfIdf", "title": "TfIdf", "topics": [ "TfIdf" ] }, { "page": "tokenizers", "title": "Simple tokenization functions for string splitting", "topics": [ "char_tokenizer", "postag_lemma_tokenizer", "space_tokenizer", "tokenizers", "word_tokenizer" ] }, { "page": "vectorizers", "title": "Vocabulary and hash vectorizers", "topics": [ "hash_vectorizer", "vectorizers", "vocab_vectorizer" ] } ], "_readme": "https://github.com/dselivanov/text2vec/raw/HEAD/README.md", "_rundeps": [ "data.table", "digest", "float", "lattice", "lgr", "Matrix", "MatrixExtra", "mlapi", "R6", "Rcpp", "RcppArmadillo", "RhpcBLASctl", "rsparse", "stringi" ], "_sysdeps": [ { "shlib": "libstdc++", "package": "libstdc++6", "source": "gcc", "version": "14.2.0-4ubuntu2~24.04.1", "name": "c++", "homepage": "http://gcc.gnu.org/", "description": "GNU Standard C++ Library v3" } ], "_vignettes": [ { "source": "text-vectorization.Rmd", "filename": "text-vectorization.html", "title": "Analyzing Texts with the text2vec package", "author": "Dmitriy Selivanov", "engine": "knitr::knitr", "headings": [ "Text analysis pipeline", "Vectorization", "Vocabulary-based vectorization", "Pruning vocabulary", "N-grams", "Feature hashing", "Basic transformations", "Normalization", "TF-IDF" ], "created": "2016-01-10 12:35:22", "modified": "2023-11-13 02:24:59", "commits": 12 }, { "source": "glove.Rmd", "filename": "glove.html", "title": "GloVe Word Embeddings", "author": "Dmitriy Selivanov", "engine": "knitr::knitr", "headings": [ "Word embeddings", "GloVe algorithm", "Linguistic regularities" ], "created": "2016-01-10 12:35:22", "modified": "2023-11-13 02:24:59", "commits": 15 } ], "_score": 13.693280023192642, "_indexed": true, "_nocasepkg": "text2vec", "_universes": [ "dselivanov" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.6.6", "date": "2026-05-25T06:33:29.000Z", "distro": "noble", "arch": "aarch64", "commit": "0b31bdd81f37baaf0bd2c8113cbaa578450c8730", "fileid": "8e03fb88e33ca0c39d2d5cb5f0d15bdaf096bcc685ab7b71d7d1e6209ed3c50d", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/dselivanov/actions/runs/26386681354" }, { "r": "4.7.0", "os": "linux", "version": "0.6.6", "date": "2026-05-25T06:32:36.000Z", "distro": "noble", "arch": "x86_64", "commit": "0b31bdd81f37baaf0bd2c8113cbaa578450c8730", "fileid": "bc8399b79c1710daddd8acc5fa032175592d5aa2b71fc909046042994031e340", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/dselivanov/actions/runs/26386681354" }, { "r": "4.6.0", "os": "linux", "version": "0.6.6", "date": "2026-05-25T06:32:24.000Z", "distro": "noble", "arch": "aarch64", "commit": "0b31bdd81f37baaf0bd2c8113cbaa578450c8730", "fileid": "e0dd227dcf9c90418f42b8f12abc6212e9cecb1f63d9358becd69d882fb6c24a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/dselivanov/actions/runs/26386681354" }, { "r": "4.6.0", "os": "linux", "version": "0.6.6", "date": "2026-05-25T06:33:12.000Z", "distro": "noble", "arch": "x86_64", "commit": "0b31bdd81f37baaf0bd2c8113cbaa578450c8730", "fileid": "86d9b5adc9fdcb02fb14dc744a34480ffb5c2341b03316d2b62ee07e6a5c8b31", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/dselivanov/actions/runs/26386681354" }, { "r": "4.5.3", "os": "mac", "version": "0.6.6", "date": "2026-05-25T06:31:41.000Z", "arch": "aarch64", "commit": "0b31bdd81f37baaf0bd2c8113cbaa578450c8730", "fileid": "df3dba26f3541fbc8e103c029c819686d145fd3dfa7b34562b86d8df165601ab", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/dselivanov/actions/runs/26386681354" }, { "r": "4.5.3", "os": "mac", "version": "0.6.6", "date": "2026-05-25T06:32:37.000Z", "arch": "x86_64", "commit": "0b31bdd81f37baaf0bd2c8113cbaa578450c8730", "fileid": "c71fc388e5fc6419ccd8e4098259ba0230df4683de30e34cd4bb67841f6e5713", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/dselivanov/actions/runs/26386681354" }, { "r": "4.6.0", "os": "mac", "version": "0.6.6", "date": "2026-05-25T06:31:41.000Z", "arch": "aarch64", "commit": "0b31bdd81f37baaf0bd2c8113cbaa578450c8730", "fileid": "fcfae1a2a9445e46552684b6129291b65cd75f08f232cf451bc2bce389e95be3", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/dselivanov/actions/runs/26386681354" }, { "r": "4.6.0", "os": "mac", "version": "0.6.6", "date": "2026-05-25T06:34:12.000Z", "arch": "x86_64", "commit": "0b31bdd81f37baaf0bd2c8113cbaa578450c8730", "fileid": "9ce7bdbbe38d489b674610c3cd360f2640eaabb337f6e216d6a75f935a780727", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/dselivanov/actions/runs/26386681354" }, { "r": "4.6.0", "os": "wasm", "version": "0.6.6", "date": "2026-05-25T06:32:20.000Z", "arch": "emscripten", "commit": "0b31bdd81f37baaf0bd2c8113cbaa578450c8730", "fileid": "b52e6a5986db558ee0f2ca208cd4e3dd480f98f10ea6ca27e63c2cab975ee82e", "status": "success", "buildurl": "https://github.com/r-universe/dselivanov/actions/runs/26386681354" }, { "r": "4.7.0", "os": "win", "version": "0.6.6", "date": "2026-05-25T06:31:58.000Z", "arch": "x86_64", "commit": "0b31bdd81f37baaf0bd2c8113cbaa578450c8730", "fileid": "8895cb8b2f09893acb150b52ddc8dc223f45d20a413f1fe3665681a203961e2f", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/dselivanov/actions/runs/26386681354" }, { "r": "4.5.3", "os": "win", "version": "0.6.6", "date": "2026-05-25T06:31:37.000Z", "arch": "x86_64", "commit": "0b31bdd81f37baaf0bd2c8113cbaa578450c8730", "fileid": "b8ac479df235196852dfb2ccab4e66f7b04b8c57ddc380fd5dac142cd476c419", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/dselivanov/actions/runs/26386681354" }, { "r": "4.6.0", "os": "win", "version": "0.6.6", "date": "2026-05-25T06:31:42.000Z", "arch": "x86_64", "commit": "0b31bdd81f37baaf0bd2c8113cbaa578450c8730", "fileid": "93660ffde1e16b1717e9b0842ba3ac16f0ace015aea1f2df4fd0cc5b7eef8ae4", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/dselivanov/actions/runs/26386681354" } ] }