{ "_id": "6a1c06721d7bb097a0a2b2fb", "Package": "textreg", "Type": "Package", "Title": "n-Gram Text Regression, aka Concise Comparative Summarization", "Version": "0.1.5", "Date": "2018-09-01", "Author": "Luke Miratrix", "Maintainer": "Luke Miratrix ", "Description": "Function for sparse regression on raw text, regressing a\nlabeling vector onto a feature space consisting of all possible\nphrases.", "License": "MIT + file LICENSE", "VignetteBuilder": "knitr", "RoxygenNote": "6.1.0", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-05-31 09:56:01 UTC", "User": "root" }, "Repository": "https://cran.r-universe.dev", "Date/Publication": "2018-10-04 10:00:03 UTC", "RemoteUrl": "https://github.com/cran/textreg", "RemoteRef": "HEAD", "RemoteSha": "e6960e5cdb3a90233f9421a8ff31b82953de35cc", "MD5sum": "e585536dc14f57165122f9c4bc436333", "_user": "cran", "_type": "src", "_file": "textreg_0.1.5.tar.gz", "_fileid": "53f582cc38ab933e55f012b22979b35fb705bd33513aef7b341ff76bed9f2ef2", "_filesize": 1801689, "_sha256": "53f582cc38ab933e55f012b22979b35fb705bd33513aef7b341ff76bed9f2ef2", "_created": "2026-05-31T09:56:01.000Z", "_published": "2026-05-31T09:59:14.007Z", "_distro": "noble", "_jobs": [ { "job": 78716879616, "time": 135, "config": "linux-devel-arm64", "r": "4.7.0", "check": "WARNING", "artifact": "7315783183" }, { "job": 78716879613, "time": 140, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "WARNING", "artifact": "7315783893" }, { "job": 78716879637, "time": 138, "config": "linux-release-arm64", "r": "4.6.0", "check": "WARNING", "artifact": "7315783592" }, { "job": 78716879627, "time": 145, "config": "linux-release-x86_64", "r": "4.6.0", "check": "WARNING", "artifact": "7315784464" }, { "job": 78716648345, "time": 241, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7315767749" }, { "job": 78716879603, "time": 140, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7315783739" } ], "_buildurl": "https://github.com/r-universe/cran/actions/runs/26709385373", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/cran/textreg", "_commit": { "id": "e6960e5cdb3a90233f9421a8ff31b82953de35cc", "author": "Luke Miratrix ", "committer": "cran-robot ", "message": "version 0.1.5\n", "time": 1538647203 }, "_maintainer": { "name": "Luke Miratrix", "email": "lmiratrix@stat.harvard.edu" }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 2.10", "role": "Depends" }, { "package": "Rcpp", "role": "LinkingTo" }, { "package": "tm", "version": ">= 0.7", "role": "Imports" }, { "package": "NLP", "version": ">= 0.1-10", "role": "Imports" }, { "package": "Rcpp", "version": ">= 0.12.9", "role": "Imports" }, { "package": "stats", "role": "Imports" }, { "package": "graphics", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "corrplot", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "SnowballC", "version": ">= 0.5.1", "role": "Suggests" }, { "package": "xtable", "role": "Suggests" }, { "package": "testthat", "role": "Suggests" }, { "package": "plyr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" } ], "_owner": "cran", "_selfowned": false, "_usedby": 0, "_updates": [], "_tags": [], "_stars": 1, "_userbio": { "uuid": 6899542, "type": "organization", "name": "cran", "description": "Unofficial read-only mirror of all CRAN R packages" }, "_downloads": { "count": 488, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/textreg" }, "_searchresults": 80, "_topics": [ "cpp" ], "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/readme.html", "extra/readme.md", "extra/textreg.html", "manual.pdf" ], "_realowner": "cran", "_cranurl": false, "_releases": [ { "version": "0.1", "date": "2014-12-04" }, { "version": "0.1.1", "date": "2015-02-02" }, { "version": "0.1.2", "date": "2015-02-06" }, { "version": "0.1.3", "date": "2015-11-11" }, { "version": "0.1.4", "date": "2017-03-17" }, { "version": "0.1.5", "date": "2018-10-04" } ], "_exports": [ "build.corpus", "calc.loss", "clean.text", "cluster.phrases", "convert.tm.to.character", "find.CV.C", "find.threshold.C", "grab.fragments", "is.fragment.sample", "is.textreg.corpus", "is.textreg.result", "list.table.chart", "make.appearance.matrix", "make.count.table", "make.CV.chart", "make.list.table", "make.path.matrix", "make.phrase.correlation.chart", "make.phrase.matrix", "make.similarity.matrix", "path.matrix.chart", "phrase.count", "phrase.matrix", "phrases", "reformat.textreg.model", "sample.fragments", "save.corpus.to.files", "stem.corpus", "textreg" ], "_datasets": [ { "name": "bathtub", "title": "Sample of cleaned OSHA accident summaries.", "object": "bathtub", "file": "bathtub.RData", "class": [ "VCorpus", "Corpus" ], "fields": [], "table": false, "tojson": false }, { "name": "dirtyBathtub", "title": "Sample of raw-text OSHA accident summaries.", "object": "dirtyBathtub", "file": "dirtyBathtub.RData", "class": [ "data.frame" ], "fields": [ "summary_nr", "event_date", "event_desc", "event_keyword", "sic_list", "fatality", "year", "text", "DOOR", "LOST BALANCE", "FALL", "STUCK", "WORK RULES", "INDUSTRIAL TRUCK", "UNSTABLE POSITION", "LEG", "CONSTRUCTION", "UNSTABLE LOAD", "STRUCK BY", "UNSECURED", "FALLING OBJECT", "IRON WORKER", "SCAFFOLD", "ELEVATED WORK PLAT", "FALL PROTECTION", "WELDING", "PERIMETER GUARDING", "GUARDRAIL", "TABLE SAW", "SAW", "STRUCK AGAINST", "FINGER", "UNGUARDED", "KICK BACK", "SLIPPERY SURFACE", "ROOF", "SLIP", "PALLET", "EQUIPMENT FAILURE", "KNEE", "CONTUSION", "INSTALLING", "TREE", "GRINDER", "WHEEL", "HAND", "STEEL PLATE", "LACERATION", "WRIST", "CAUGHT BY", "FRACTURE", "BACK", "MOBILE SCAFFOLD", "NOSE", "EYE", "GAS", "ABRASION", "TRENCH", "COLLAPSE", "HIP", "PELVIS", "MANUAL MAT HANDLING", "FACE", "LIFELINE", "PINNED", "EARTHMOVING EQUIP", "INATTENTION", "MECH MAT HANDLING", "CAUGHT BETWEEN", "JAMMED", "WORK SURFACE", "CLEARANCE", "ELECTRIC SHOCK", "ROOFER", "DRIVER", "VEHICLE", "ROOF OPENING", "DECKING", "LOGGING", "CHEMICAL VAPOR", "TOXIC ATMOSPHERE", "TOXIC FUMES", "TANK", "LOG", "SPINE", "SHOULDER", "HEART ATTACK", "TANK TRUCK", "CLEANING", "VAPOR", "OVEREXPOSURE", "INHALATION", "TRUCK", "CONVEYOR", "CRUSHED", "TRAILER", "CHEST", "CRANE", "MOLD", "BURN", "FIRE", "EQUIPMENT OPERATOR", "SMOKE", "MOTOR VEHICLE", "NECK", "RUN OVER", "BACKING UP", "DUMP TRUCK", "HEAD", "STEAM", "ELECTROCUTED", "AERIAL LIFT", "REPAIR", "ELEC CIRC PART--MISC", "LOCKOUT", "ARM", "LADDER", "LEAK", "FOOD PREPARATION", "GUARD", "AMPUTATED", "FLAMMABLE VAPORS", "ASPHYXIATED", "CARBON MONOXIDE", "PROPANE", "CARDIOVASC DISEASE", "HEART", "EXPLOSION", "STORAGE TANK", "ELECTRICAL", "ELEC UTILITY WORK", "IND TRK OPERATOR", "SKYLIGHT", "SKIDDER", "LOADER", "TELECOM WORK", "TOWER", "BACKHOE", "TRAFFIC CONTROL", "FLAGMAN", "TRIPPED", "TIRE", "CONCUSSION", "MAINTENANCE", "ROLL-OVER", "UNCONSCIOUSNESS", "SKULL", "ROOF OPENING COVER", "MECH MALFUNCTION", "BOLT", "CARPENTER", "CONCRETE", "BRAIN", "CAVE-IN", "SHORING", "NAIL", "CARDIAC ARREST", "PIPE", "LOST CONTROL", "MACHINE OPERATOR", "ENGINE", "UNTRAINED", "STEEL", "PAINTER", "STAIR", "FOOT", "ANKLE", "LIGHTING CIRCUIT", "TRAIN", "BRIDGE", "PPE", "FLYING OBJECT", "HEAT", "TRACTOR", "UTILITY POLE", "UNSTABLE SURFACE", "TORSO", "ALCOHOL", "ROLLER--CONST EQUIP", "DROWN", "WORK STATION", "CONFINED SPACE", "ELECTRICAL FAULT", "ELECTRIC ARC", "CPR", "BRAKE", "VEHICLE IN GEAR", "CHOCK", "EJECTED", "GRADER", "WATER", "ELECTRIC CONDUCTOR", "HAND TOOL", "TRUCK DRIVER", "BEAM", "RAIL", "PLATFORM", "METAL POLE", "LIGHTING", "E C", "CONCRETE FORM WORK", "PUMP", "CHEMICAL BURN", "WALKING SURFACE", "TRAFFIC ACCIDENT", "RESTRAINING DEVICE", "DUCT", "GARBAGE TRUCK", "HIGH TEMPERATURE", "BURIED", "HANDRAIL", "DEMOLITION", "SPRAY PAINTING", "PAINT SOLVENT", "RESPIRATOR", "HIGHWAY", "ROLLER--MACH/PART", "NIP POINT", "GLOVE", "E GI IV", "ROTATING PARTS", "RIB", "PRESSURE RELEASE", "EXTENSION LADDER", "EAR", "HEATER", "GRINDING MACHINE", "PRESSURE PIPING", "FOREHEAD", "BELT", "CHAIN", "HATCH", "COMPRESSOR", "PLUMBING", "BLADE", "FLAMMABLE LIQUID", "AUTOMOBILE", "PLASTIC MFG", "SILO", "LUNG", "AIR CONDITIONER", "HIGH WIND", "SKIN", "INFECTIOUS DISEASE", "MOBILE CRANE", "BARRIER GUARD", "COVER", "GUNSHOT", "DESCENDING", "SHOCK", "VENTILATION", "CHEMICAL", "LUMBER", "RIVER", "POISONING", "RING", "PAINT", "INADEQUATE MAINT", "PRESS", "THUMB", "STORAGE RACK", "PUNCTURE", "UNGUARDED LIVE PARTS", "SPILL", "LIVER", "HOT WATER", "CLOGGED", "PRESS BRAKE", "SEVERED", "INTOXICATED", "IMPALED", "HOT COOKING OIL", "REFINERY", "RIP", "HEAT EXHAUSTION", "DISLOCATED", "FOOD PACKAGING MACH", "KNIFE", "INFECTION", "STEAM CLEANER", "DELIVERY WORK", "HOSE", "MEAT BLENDING MACH", "DRAIN PIPE", "INSULATOR", "PAPER", "MANHOLE", "METAL SHEET", "FIXED LADDER", "GEAR", "LAWN MOWER", "WALKING ON BEAM", "TENDON", "HEMORRHAGE", "DUST", "IGNITION SYSTEM", "HYDRAULIC FLUID", "FENCE", "PIN", "POOL", "METAL PIPE", "IRON", "ATTACHMENT HOOK", "PALLETIZED CARGO", "STOP SWITCH", "THIGH", "SAFETY CONTROL LINE", "STORAGE ROOM", "NURSERY", "NAUSEA", "OFFICE AREA", "BROKEN CABLE", "WATER HEATER", "VOMIT", "CARBOXYHEMOGLOBIN", "METAL SHOP", "TRACTOR--TRUCK", "HYDROGEN SULFIDE", "ENCLOSED SPACE", "LEGIONNAIRES DISEASE", "PAPER ROLL", "METHYL ALCOHOL", "SAFETY BLOCK", "WALK PLATFORM", "XYLENE", "HYDROGEN", "NAPHTHA", "FRYER", "DRILL PRESS", "METHYLENE CHLORIDE", "E M", "SAFE", "MEK", "DEBONING", "ISOPROPANOL" ], "rows": 127, "table": true, "tojson": true }, { "name": "testCorpora", "title": "Some small, fake test corpora.", "object": "testCorpora", "file": "testCorpora.RData", "class": [ "list" ], "fields": [], "table": false, "tojson": true } ], "_help": [ { "page": "textreg-package", "title": "Sparse regression package for text that allows for multiple word phrases.", "topics": [ "textreg-package" ] }, { "page": "bathtub", "title": "Sample of cleaned OSHA accident summaries.", "concept": [ "bathtub" ], "topics": [ "bathtub" ] }, { "page": "build.corpus", "title": "Build a corpus that can be used in the textreg call.", "topics": [ "build.corpus" ] }, { "page": "calc.loss", "title": "Calculate total loss of model (Squared hinge loss).", "topics": [ "calc.loss" ] }, { "page": "clean.text", "title": "Clean text and get it ready for textreg.", "topics": [ "clean.text" ] }, { "page": "cluster.phrases", "title": "Cluster phrases based on similarity of appearance.", "concept": [ "Phrase Vizualization" ], "topics": [ "cluster.phrases" ] }, { "page": "convert.tm.to.character", "title": "Convert tm corpus to vector of strings.", "topics": [ "convert.tm.to.character" ] }, { "page": "cpp_build.corpus", "title": "Driver function for the C++ function.", "topics": [ "cpp_build.corpus" ] }, { "page": "cpp_textreg", "title": "Driver function for the C++ function.", "topics": [ "cpp_textreg" ] }, { "page": "dirtyBathtub", "title": "Sample of raw-text OSHA accident summaries.", "concept": [ "bathtub" ], "topics": [ "dirtyBathtub" ] }, { "page": "find.CV.C", "title": "K-fold cross-validation to determine optimal tuning parameter", "topics": [ "find.CV.C" ] }, { "page": "find.threshold.C", "title": "Conduct permutation test on labeling to get null distribution of regularization parameter.", "topics": [ "find.threshold.C" ] }, { "page": "grab.fragments", "title": "Grab all fragments in a corpus with given phrase.", "topics": [ "grab.fragments" ] }, { "page": "is.fragment.sample", "title": "Is object a fragment.sample object?", "concept": [ "sample.fragments" ], "topics": [ "fragment.sample", "is.fragment.sample" ] }, { "page": "is.textreg.corpus", "title": "Is object a textreg.corpus object?", "concept": [ "textreg.corpus" ], "topics": [ "is.textreg.corpus", "textreg.corpus" ] }, { "page": "is.textreg.result", "title": "Is object a textreg.result object?", "concept": [ "textreg.result" ], "topics": [ "is.textreg.result", "textreg.result" ] }, { "page": "list.table.chart", "title": "Graphic showing multiple word lists side-by-side.", "topics": [ "list.table.chart" ] }, { "page": "make_search_phrases", "title": "Convert phrases to appropriate search string.", "topics": [ "make_search_phrases" ] }, { "page": "make.appearance.matrix", "title": "Make phrase appearance matrix from textreg result.", "concept": [ "Phrase Vizualization" ], "topics": [ "make.appearance.matrix" ] }, { "page": "make.count.table", "title": "Count number of times documents have a given phrase.", "concept": [ "textregCounting" ], "topics": [ "make.count.table" ] }, { "page": "make.CV.chart", "title": "Plot K-fold cross validation curves", "topics": [ "make.CV.chart" ] }, { "page": "make.list.table", "title": "Collate multiple regression runs.", "topics": [ "make.list.table" ] }, { "page": "make.path.matrix", "title": "Generate matrix describing gradient descent path of textreg.", "concept": [ "plot.path.matrix" ], "topics": [ "make.path.matrix" ] }, { "page": "make.phrase.correlation.chart", "title": "Generate visualization of phrase overlap.", "concept": [ "Phrase Vizualization" ], "topics": [ "make.phrase.correlation.chart" ] }, { "page": "make.phrase.matrix", "title": "Make a table of where phrases appear in a corpus", "concept": [ "textregCounting" ], "topics": [ "make.phrase.matrix" ] }, { "page": "make.similarity.matrix", "title": "Calculate similarity matrix for set of phrases.", "concept": [ "Phrase Vizualization" ], "topics": [ "make.similarity.matrix" ] }, { "page": "path.matrix.chart", "title": "Plot optimization path of textreg.", "concept": [ "plot.path.matrix" ], "topics": [ "path.matrix.chart" ] }, { "page": "phrase.count", "title": "Count phrase appearance.", "concept": [ "textregCounting" ], "topics": [ "phrase.count" ] }, { "page": "phrase.matrix", "title": "Make matrix of where phrases appear in corpus.", "topics": [ "phrase.matrix" ] }, { "page": "phrases", "title": "Get the phrases from the textreg.result object?", "concept": [ "textreg.result" ], "topics": [ "phrases" ] }, { "page": "plot.textreg.result", "title": "Plot the sequence of features as they are introduced with the textreg gradient descent program.", "concept": [ "plot.path.matrix" ], "topics": [ "plot.textreg.result" ] }, { "page": "predict.textreg.result", "title": "Predict labeling with the selected phrases.", "topics": [ "predict.textreg.result" ] }, { "page": "print.fragment.sample", "title": "Pretty print results of phrase sampling object.", "concept": [ "sample.fragments" ], "topics": [ "print.fragment.sample" ] }, { "page": "print.textreg.corpus", "title": "Pretty print textreg corpus object", "concept": [ "textreg.corpus" ], "topics": [ "print.textreg.corpus" ] }, { "page": "print.textreg.result", "title": "Pretty print results of textreg regression.", "concept": [ "textreg.result" ], "topics": [ "print.textreg.result" ] }, { "page": "reformat.textreg.model", "title": "Clean up output from textreg.", "concept": [ "textreg.result" ], "topics": [ "reformat.textreg.model" ] }, { "page": "sample.fragments", "title": "Sample fragments of text to contextualize a phrase.", "concept": [ "sample.fragments" ], "topics": [ "sample.fragments" ] }, { "page": "save.corpus.to.files", "title": "Save corpus to text (and RData) file.", "topics": [ "save.corpus.to.files" ] }, { "page": "stem.corpus", "title": "Step corpus with annotation.", "topics": [ "stem.corpus" ] }, { "page": "testCorpora", "title": "Some small, fake test corpora.", "topics": [ "testCorpora" ] }, { "page": "textreg", "title": "Sparse regression of labeling vector onto all phrases in a corpus.", "topics": [ "textreg" ] }, { "page": "tm_gregexpr", "title": "Call gregexpr on the content of a tm Corpus.", "topics": [ "tm_gregexpr" ] } ], "_readme": "https://github.com/cran/textreg/raw/HEAD/README.md", "_rundeps": [ "BH", "cli", "NLP", "Rcpp", "rlang", "slam", "tm", "xml2" ], "_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": "bathtub_vignette.Rmd", "filename": "bathtub_vignette.html", "title": "Using the textreg package", "author": "Miratrix", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "Installing the textreg package", "Getting ready to regress", "Obtaining the Summary", "Tuning the Summary", "Selecting C", "Dropping documents", "Exploring the Text", "Finding Where Phrases Appear", "Independent Search Methods", "Finding Phrases' Contexts", "Relationships between phrases", "Prediction", "Out of Sample Prediction", "Cross Validation", "Cleaning Text and Stemming" ], "created": "2018-10-04 10:00:03", "modified": "2018-10-04 10:00:03", "commits": 1 } ], "_score": 3.6020599913279625, "_indexed": true, "_nocasepkg": "textreg", "_universes": [ "cran" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.5", "date": "2026-05-31T09:58:23.000Z", "distro": "noble", "arch": "aarch64", "commit": "e6960e5cdb3a90233f9421a8ff31b82953de35cc", "fileid": "ba03e3b01d0ec2ac044b4f740437dc0ed57c60a8e6ff8ed6b83ce3342d1e4253", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/cran/actions/runs/26709385373" }, { "r": "4.7.0", "os": "linux", "version": "0.1.5", "date": "2026-05-31T09:58:25.000Z", "distro": "noble", "arch": "x86_64", "commit": "e6960e5cdb3a90233f9421a8ff31b82953de35cc", "fileid": "902e9f2adcbb801002315494172c3ed1af075969d73c16251f0053a9cbc7bc5c", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/cran/actions/runs/26709385373" }, { "r": "4.6.0", "os": "linux", "version": "0.1.5", "date": "2026-05-31T09:58:25.000Z", "distro": "noble", "arch": "aarch64", "commit": "e6960e5cdb3a90233f9421a8ff31b82953de35cc", "fileid": "856a429f2193e24db25c4f4616715351e020b2750fbe93282b353ee369cf60ac", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/cran/actions/runs/26709385373" }, { "r": "4.6.0", "os": "linux", "version": "0.1.5", "date": "2026-05-31T09:58:29.000Z", "distro": "noble", "arch": "x86_64", "commit": "e6960e5cdb3a90233f9421a8ff31b82953de35cc", "fileid": "bfa9f477cac2d4aec71a50a0d0d5f1a5f5432aa6d6fdb1aaafc6079f42509b6a", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/cran/actions/runs/26709385373" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.5", "date": "2026-05-31T09:58:37.000Z", "arch": "emscripten", "commit": "e6960e5cdb3a90233f9421a8ff31b82953de35cc", "fileid": "9dd1c882b69cfd0e5daf38040408dc8b70bfcfcb128ea1f7abbaead086f1b7bd", "status": "success", "buildurl": "https://github.com/r-universe/cran/actions/runs/26709385373" } ] }