{ "_id": "6a493c4ca19c9318096e70a4", "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": "2026-07-04 16:51:35 UTC", "User": "root" }, "_user": "vgherard", "_type": "src", "_file": "sbo_0.5.0.tar.gz", "_fileid": "https://r2.ropensci.org/3e99d5ce0b157ff1fb9076de3fe47607ac158ddf82435dfcf565112a952babec", "_filesize": 3236288, "_sha256": "3e99d5ce0b157ff1fb9076de3fe47607ac158ddf82435dfcf565112a952babec", "_expires": "2026-10-12T17:00:58.000Z", "_created": "2026-07-04T16:51:35.000Z", "_published": "2026-07-04T17:01:00.625Z", "_jobs": [ { "job": 85149788183, "time": 183, "config": "linux-devel-arm64", "r": "4.7.0", "check": "ERROR", "artifact": "8083616298" }, { "job": 85149788173, "time": 190, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "ERROR", "artifact": "8083616725" }, { "job": 85149788169, "time": 190, "config": "linux-release-arm64", "r": "4.6.1", "check": "ERROR", "artifact": "8083617199" }, { "job": 85149788174, "time": 183, "config": "linux-release-x86_64", "r": "4.6.1", "check": "ERROR", "artifact": "8083615770" }, { "job": 85149788176, "time": 100, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "ERROR", "artifact": "8083605601" }, { "job": 85149788177, "time": 499, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "ERROR", "artifact": "8083654893" }, { "job": 85149788172, "time": 148, "config": "macos-release-arm64", "r": "4.6.1", "check": "ERROR", "artifact": "8083611362" }, { "job": 85149788187, "time": 289, "config": "macos-release-x86_64", "r": "4.6.1", "check": "ERROR", "artifact": "8083629248" }, { "job": 85149481430, "time": 263, "config": "source", "r": "4.6.1", "check": "ERROR", "artifact": "8083592564" }, { "job": 85149788157, "time": 183, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8083615812" }, { "job": 85149788161, "time": 181, "config": "windows-devel", "r": "4.7.0", "check": "ERROR", "artifact": "8083615500" }, { "job": 85149788156, "time": 169, "config": "windows-oldrel", "r": "4.5.3", "check": "ERROR", "artifact": "8083613964" }, { "job": 85149788162, "time": 166, "config": "windows-release", "r": "4.6.1", "check": "ERROR", "artifact": "8083613810" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/vgherard/actions/runs/28712973376", "_status": "failure", "_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" }, "_distro": "resolute", "_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", "followers": 14, "description": "|physicist> + |data scientist>" }, "_downloads": { "count": 59, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/sbo" }, "_devurl": "https://github.com/vgherard/sbo", "_pkgdown": "https://vgherard.github.io/sbo/", "_searchresults": 17, "_rbuild": "4.6.1", "_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", "otel", "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": "16-20260322-1ubuntu1", "name": "c++", "homepage": "http://gcc.gnu.org/", "description": "GNU Standard C++ Library v3" } ], "_score": 2.929418925714293, "_indexed": true, "_nocasepkg": "sbo", "_universes": [ "vgherard" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.5.0", "date": "2026-07-04T16:54:28.000Z", "distro": "resolute", "arch": "aarch64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "https://r2.ropensci.org/c7d6a4592fe3ed1486429c0c973e91adf12da93bbde8fc3d4cc59b02cbf6dd1d", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/28712973376" }, { "r": "4.7.0", "os": "linux", "version": "0.5.0", "date": "2026-07-04T16:54:21.000Z", "distro": "resolute", "arch": "x86_64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "https://r2.ropensci.org/8f41596ef065f5b1abd83207f155acc046e63b57dbf6bf8ce19beb558bd80c41", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/28712973376" }, { "r": "4.6.1", "os": "linux", "version": "0.5.0", "date": "2026-07-04T16:54:33.000Z", "distro": "resolute", "arch": "aarch64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "https://r2.ropensci.org/cca9fd8ea65c23e47387d6801fa501c44f1e7528a68937687be7acbc54ade03f", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/28712973376" }, { "r": "4.6.1", "os": "linux", "version": "0.5.0", "date": "2026-07-04T16:54:16.000Z", "distro": "resolute", "arch": "x86_64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "https://r2.ropensci.org/4f7312251a41cc8bc884b2ba21b8b358088196ffac73a5427416bdeea79c38c8", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/28712973376" }, { "r": "4.5.3", "os": "mac", "version": "0.5.0", "date": "2026-07-04T16:53:23.000Z", "arch": "aarch64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "https://r2.ropensci.org/7ac4fd305b2ea5a4c5639f200ebdc4d5cf1008f597b14124857aa2c98ff0cfdf", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/28712973376" }, { "r": "4.5.3", "os": "mac", "version": "0.5.0", "date": "2026-07-04T16:56:44.000Z", "arch": "x86_64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "https://r2.ropensci.org/8ed4c8589954b95052b9494125e612d2930d46949b18a4c45d4ece3051446af1", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/28712973376" }, { "r": "4.6.1", "os": "mac", "version": "0.5.0", "date": "2026-07-04T16:53:54.000Z", "arch": "aarch64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "https://r2.ropensci.org/f149921a01274d038c4309e01a42a100858c11ac86a9abc6a8ef95567f97693e", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/28712973376" }, { "r": "4.6.1", "os": "mac", "version": "0.5.0", "date": "2026-07-04T16:55:21.000Z", "arch": "x86_64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "https://r2.ropensci.org/2824448695415f999c36311913006761970846c1584c565b91553b1f5ed99539", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/28712973376" }, { "r": "4.6.0", "os": "wasm", "version": "0.5.0", "date": "2026-07-04T16:54:57.000Z", "arch": "emscripten", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "https://r2.ropensci.org/3786a13931422331578c85c68396e3fac9547df5110c06a255181c3b89fd6823", "status": "success", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/28712973376" }, { "r": "4.7.0", "os": "win", "version": "0.5.0", "date": "2026-07-04T16:53:19.000Z", "arch": "x86_64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "https://r2.ropensci.org/861dfaa89f955c1fd6615fef4a750402adc18cb049e2e6ea46a2b777c6164a01", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/28712973376" }, { "r": "4.5.3", "os": "win", "version": "0.5.0", "date": "2026-07-04T16:53:26.000Z", "arch": "x86_64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "https://r2.ropensci.org/622b615536c66cdd356a2d59c91605ea54984ba9fdb88afa62479d69c21b7442", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/28712973376" }, { "r": "4.6.1", "os": "win", "version": "0.5.0", "date": "2026-07-04T16:53:21.000Z", "arch": "x86_64", "commit": "75374a5bf57709fae780207fa1f93b8e86d7c6c4", "fileid": "https://r2.ropensci.org/9d69ecba5d4f422bee3f53372cae2278789f42b5a9bccbd164fb7c5636b27f74", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/vgherard/actions/runs/28712973376" } ] }