{ "_id": "6a1693efacfb0bcc41d79a18", "Package": "sbo", "Type": "Package", "Title": "Text Prediction via Stupid Back-Off N-Gram Models", "Version": "0.5.0", "Author": "Valerio Gherardi", "Maintainer": "Valerio Gherardi ", "Description": "Utilities for training and evaluating text predictors\nbased on Stupid Back-Off N-gram models (Brants et al., 2007,\n).", "License": "GPL-3", "Encoding": "UTF-8", "LazyData": "true", "RoxygenNote": "7.1.1.9000", "SystemRequirements": "C++11", "URL": "https://vgherard.github.io/sbo/, https://github.com/vgherard/sbo", "BugReports": "https://github.com/vgherard/sbo/issues", "VignetteBuilder": "knitr", "Config/pak/sysreqs": "cmake make libicu-dev libuv1-dev", "Repository": "https://vgherard.r-universe.dev", "Date/Publication": "2020-12-05 14:59:11 UTC", "RemoteUrl": "https://github.com/vgherard/sbo", "RemoteRef": "v0.5.0", "RemoteSha": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-05-27 06:43:27 UTC", "User": "root" }, "MD5sum": "3d6c1ce723a23ab62aeabb486161ca36", "_user": "vgherard", "_type": "src", "_file": "sbo_0.5.0.tar.gz", "_fileid": "b3480c3d105d4fa0e8debf38e2d3a45d0191afe651a899692e4c9217488458e4", "_filesize": 3233051, "_sha256": "b3480c3d105d4fa0e8debf38e2d3a45d0191afe651a899692e4c9217488458e4", "_created": "2026-05-27T06:43:27.000Z", "_published": "2026-05-27T06:49:19.547Z", "_distro": "noble", "_jobs": [ { "job": 78022364275, "time": 206, "config": "linux-devel-arm64", "r": "4.7.0", "check": "ERROR", "artifact": "7233703838" }, { "job": 78022364335, "time": 203, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "ERROR", "artifact": "7233703104" }, { "job": 78022364271, "time": 184, "config": "linux-release-arm64", "r": "4.6.0", "check": "ERROR", "artifact": "7233698104" }, { "job": 78022364280, "time": 178, "config": "linux-release-x86_64", "r": "4.6.0", "check": "ERROR", "artifact": "7233696897" }, { "job": 78022364297, "time": 113, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "ERROR", "artifact": "7233680099" }, { "job": 78022364298, "time": 215, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "ERROR", "artifact": "7233706393" }, { "job": 78022364266, "time": 117, "config": "macos-release-arm64", "r": "4.6.0", "check": "ERROR", "artifact": "7233680928" }, { "job": 78022364256, "time": 289, "config": "macos-release-x86_64", "r": "4.6.0", "check": "ERROR", "artifact": "7233725873" }, { "job": 78021787680, "time": 258, "config": "source", "r": "4.6.0", "check": "ERROR", "artifact": "7233650529" }, { "job": 78022364234, "time": 133, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7233685306" }, { "job": 78022364269, "time": 205, "config": "windows-devel", "r": "4.7.0", "check": "ERROR", "artifact": "7233703541" }, { "job": 78022364268, "time": 144, "config": "windows-oldrel", "r": "4.5.3", "check": "ERROR", "artifact": "7233687989" }, { "job": 78022364296, "time": 172, "config": "windows-release", "r": "4.6.0", "check": "ERROR", "artifact": "7233695012" } ], "_buildurl": "https://github.com/r-universe/vgherard/actions/runs/26495227520", "_status": "failure", "_host": "GitHub-Actions", "_upstream": "https://github.com/vgherard/sbo", "_commit": { "id": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "author": "vgherard ", "committer": "vgherard ", "message": "CRAN comments for v0.5.0\n", "time": 1607180351 }, "_maintainer": { "name": "Valerio Gherardi", "email": "vgherard@sissa.it" }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.5.0", "role": "Depends" }, { "package": "Rcpp", "role": "LinkingTo" }, { "package": "testthat", "role": "LinkingTo" }, { "package": "Rcpp", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "tidyr", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "stats", "role": "Imports" }, { "package": "graphics", "role": "Imports" }, { "package": "ggplot2", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "cli", "role": "Suggests" }, { "package": "testthat", "role": "Suggests" }, { "package": "covr", "role": "Suggests" } ], "_owner": "vgherard", "_selfowned": true, "_usedby": 0, "_updates": [], "_tags": [], "_topics": [ "natural-language-processing", "ngram-models", "predictive-text", "sbo", "cpp" ], "_stars": 10, "_userbio": { "uuid": 62836440, "type": "user", "name": "Valerio Gherardi", "description": "|physicist> + |data scientist>" }, "_downloads": { "count": 33, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/sbo" }, "_devurl": "https://github.com/vgherard/sbo", "_pkgdown": "https://vgherard.github.io/sbo/", "_searchresults": 11, "_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/sbo.html", "manual.pdf" ], "_cranurl": false, "_releases": [ { "version": "0.3.0", "date": "2020-11-04" }, { "version": "0.3.2", "date": "2020-11-09" }, { "version": "0.5.0", "date": "2020-12-05" } ], "_exports": [ "as_sbo_dictionary", "babble", "dictionary", "eval_sbo_predictor", "kgram_freqs", "kgram_freqs_fast", "predictor", "predtable", "preprocess", "prune", "sbo_dictionary", "sbo_kgram_freqs", "sbo_kgram_freqs_fast", "sbo_predictor", "sbo_predtable", "tokenize_sentences", "word_coverage" ], "_datasets": [ { "name": "twitter_dict", "title": "Top 1000 dictionary from Twitter training set", "object": "twitter_dict", "class": [ "sbo_dictionary" ], "fields": [], "table": false, "tojson": false }, { "name": "twitter_freqs", "title": "k-gram frequencies from Twitter training set", "object": "twitter_freqs", "class": [ "sbo_kgram_freqs" ], "fields": [], "table": false, "tojson": false }, { "name": "twitter_predtable", "title": "Next-word prediction tables from 3-gram model trained on Twitter training set", "object": "twitter_predtable", "class": [ "sbo_predtable", "sbo_predictions" ], "fields": [], "table": false, "tojson": false }, { "name": "twitter_test", "title": "Twitter test set", "object": "twitter_test", "class": [ "character" ], "fields": [], "table": false, "tojson": true }, { "name": "twitter_train", "title": "Twitter training set", "object": "twitter_train", "class": [ "character" ], "fields": [], "table": false, "tojson": true } ], "_help": [ { "page": "as_sbo_dictionary", "title": "Coerce to dictionary", "topics": [ "as_sbo_dictionary", "as_sbo_dictionary.character" ] }, { "page": "babble", "title": "Babble!", "topics": [ "babble" ] }, { "page": "eval_sbo_predictor", "title": "Evaluate Stupid Back-off next-word predictions", "topics": [ "eval_sbo_predictor" ] }, { "page": "kgram_freqs", "title": "k-gram frequency tables", "topics": [ "kgram_freqs", "kgram_freqs_fast", "sbo_kgram_freqs", "sbo_kgram_freqs_fast" ] }, { "page": "plot.word_coverage", "title": "Plot method for word_coverage objects", "topics": [ "plot.word_coverage" ] }, { "page": "predict.sbo_kgram_freqs", "title": "Predict method for k-gram frequency tables", "topics": [ "predict.sbo_kgram_freqs" ] }, { "page": "predict.sbo_predictor", "title": "Predict method for Stupid Back-off text predictor", "topics": [ "predict.sbo_predictor" ] }, { "page": "preprocess", "title": "Preprocess text corpus", "topics": [ "preprocess" ] }, { "page": "prune", "title": "Prune k-gram objects", "topics": [ "prune", "prune.sbo_kgram_freqs", "prune.sbo_predtable" ] }, { "page": "sbo_dictionary", "title": "Dictionaries", "topics": [ "dictionary", "sbo_dictionary" ] }, { "page": "sbo_predictions", "title": "Stupid Back-off text predictions", "topics": [ "predictor", "predtable", "sbo_predictions", "sbo_predictor", "sbo_predictor.character", "sbo_predictor.sbo_kgram_freqs", "sbo_predictor.sbo_predtable", "sbo_predtable", "sbo_predtable.character", "sbo_predtable.sbo_kgram_freqs" ] }, { "page": "tokenize_sentences", "title": "Sentence tokenizer", "topics": [ "tokenize_sentences" ] }, { "page": "twitter_dict", "title": "Top 1000 dictionary from Twitter training set", "topics": [ "twitter_dict" ] }, { "page": "twitter_freqs", "title": "k-gram frequencies from Twitter training set", "topics": [ "twitter_freqs" ] }, { "page": "twitter_predtable", "title": "Next-word prediction tables from 3-gram model trained on Twitter training set", "topics": [ "twitter_predtable" ] }, { "page": "twitter_test", "title": "Twitter test set", "topics": [ "twitter_test" ] }, { "page": "twitter_train", "title": "Twitter training set", "topics": [ "twitter_train" ] }, { "page": "word_coverage", "title": "Word coverage fraction", "topics": [ "word_coverage", "word_coverage.character", "word_coverage.sbo_dictionary", "word_coverage.sbo_kgram_freqs", "word_coverage.sbo_predictions" ] } ], "_readme": "https://github.com/vgherard/sbo/raw/v0.5.0/README.md", "_rundeps": [ "brio", "callr", "cli", "cpp11", "crayon", "desc", "diffobj", "dplyr", "evaluate", "fs", "generics", "glue", "jsonlite", "lifecycle", "magrittr", "pillar", "pkgbuild", "pkgconfig", "pkgload", "praise", "processx", "ps", "purrr", "R6", "Rcpp", "rlang", "rprojroot", "stringi", "stringr", "testthat", "tibble", "tidyr", "tidyselect", "utf8", "vctrs", "waldo", "withr" ], "_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" } ], "_score": 2.7403626894942437, "_indexed": true, "_nocasepkg": "sbo", "_universes": [ "vgherard" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.5.0", "date": "2026-05-27T06:46:34.000Z", "distro": "noble", "arch": "aarch64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "4354a4b7e1f2d6af0c80eea071994b15065f08aa6f62208d97906a101d857b43", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/26495227520" }, { "r": "4.7.0", "os": "linux", "version": "0.5.0", "date": "2026-05-27T06:46:26.000Z", "distro": "noble", "arch": "x86_64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "59217001f915d8913446df74464ce46de07d79007b9731bed48db23e404fba7d", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/26495227520" }, { "r": "4.6.0", "os": "linux", "version": "0.5.0", "date": "2026-05-27T06:46:10.000Z", "distro": "noble", "arch": "aarch64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "821c70d60390f1b4ff05637cd03f0ca498fc813b12a03eb466fb049d2b48ac98", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/26495227520" }, { "r": "4.6.0", "os": "linux", "version": "0.5.0", "date": "2026-05-27T06:46:11.000Z", "distro": "noble", "arch": "x86_64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "71d7ca4cbd5ff6ed59817e639c67e1fd3b8aaa7b5ccb276e567c73d0fe405e41", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/26495227520" }, { "r": "4.5.3", "os": "mac", "version": "0.5.0", "date": "2026-05-27T06:45:21.000Z", "arch": "aarch64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "34185897cd776c232e9de71ad934f78bf1b1a0c37ace8177abe33fdc8e5eab4f", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/26495227520" }, { "r": "4.5.3", "os": "mac", "version": "0.5.0", "date": "2026-05-27T06:46:21.000Z", "arch": "x86_64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "41b5e7f37cc094ef671111779ff0590b97f48f82b9898ea75b53e051eb3c4cbe", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/26495227520" }, { "r": "4.6.0", "os": "mac", "version": "0.5.0", "date": "2026-05-27T06:45:23.000Z", "arch": "aarch64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "d82f50ca9d7144075eeddc061de3c64fe11220b61ec9e45e0cad47b0809c551f", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/26495227520" }, { "r": "4.6.0", "os": "mac", "version": "0.5.0", "date": "2026-05-27T06:46:51.000Z", "arch": "x86_64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "fdf3b6b3baa3d332892e8e50046ed6930aa78cabafa13dcb4342364214db4017", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/26495227520" }, { "r": "4.6.0", "os": "wasm", "version": "0.5.0", "date": "2026-05-27T06:46:00.000Z", "arch": "emscripten", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "4de1f96ee241823de10c5b3fd78b17b5ff13d57ea310dea22f97ca39d7ae3883", "status": "success", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/26495227520" }, { "r": "4.7.0", "os": "win", "version": "0.5.0", "date": "2026-05-27T06:45:34.000Z", "arch": "x86_64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "7053574ea5ef43e5d9ffbd9deb2214c10c965238ada7ae7316f4834bcda0c190", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/26495227520" }, { "r": "4.5.3", "os": "win", "version": "0.5.0", "date": "2026-05-27T06:45:05.000Z", "arch": "x86_64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "b27c28f65fbfe3dd343166fec0fd650bc2ac9c905b1d560589bad63b9cfe92ad", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/26495227520" }, { "r": "4.6.0", "os": "win", "version": "0.5.0", "date": "2026-05-27T06:45:08.000Z", "arch": "x86_64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "6d9e3d27ab675c00975ba904582de474480c1435e580916737d4ed4979f3b983", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/26495227520" } ] }