R/stylest_select_vocab.R
stylest_terms.RdThe same text, speaker, and filter should be used in this model
as in fit_speaker to select the terms for the latter function.
stylest_terms(x, speaker, vocab_cutoff, filter = NULL)
| x | Corpus as text vector. May be a |
|---|---|
| speaker | Vector of speaker labels. Should be the same length as
|
| vocab_cutoff | Quantile cutoff for the vocabulary in (0, 100] |
| filter | if not |
list of terms
data(novels_excerpts) stylest_terms(novels_excerpts$text, novels_excerpts$author, vocab_cutoff = 50)#> [1] "," "the" "of" "." #> [5] "and" "in" "to" "a" #> [9] "for" ";" "as" "that" #> [13] "i" "with" "it" "had" #> [17] "be" "on" "was" "my" #> [21] "or" "but" "his" "have" #> [25] "when" "been" "not" "who" #> [29] "at" "by" "he" "is" #> [33] "one" "so" "there" "from" #> [37] "very" "all" "-" "her" #> [41] "their" "me" "which" "an" #> [45] "little" "into" "this" "even" #> [49] "she" "them" "years" "mr" #> [53] "any" "are" "day" "has" #> [57] "if" "may" "some" "they" #> [61] "do" "long" "many" "only" #> [65] "up" "will" "great" "where" #> [69] "more" "you" "were" "life" #> [73] "men" "about" "own" "what" #> [77] "ago" "can" "just" "lady" #> [81] "most" "say" "we" "before" #> [85] "well" "am" "days" "him" #> [89] "man" "must" "never" "no" #> [93] "should" "than" "young" "few" #> [97] "good" "know" "like" "made" #> [101] "much" "perhaps" "three" "too" #> [105] "\"" "!" "shall" "?" #> [109] "mother" ":" "among" "came" #> [113] "certain" "county" "dear" "died" #> [117] "family" "father" "himself" "interest" #> [121] "lived" "present" "spoke" "these" #> [125] "upon" "wife" "after" "age" #> [129] "down" "end" "every" "existence" #> [133] "first" "house" "indeed" "known" #> [137] "land" "last" "nothing" "other" #> [141] "park" "people" "position" "short" #> [145] "single" "surrounding" "tell" "think" #> [149] "time" "two" "under" "whom" #> [153] "without" "world" "your" "miss" #> [157] "our" "girl" "how" "now" #> [161] "then" "daughters" "death" "handsome" #> [165] "kind" "large" "mistress" "old" #> [169] "principal" "small" "subject" "thousand" #> [173] "town" "travelled" "'" "(" #> [177] ")" "acquaintance" "acquainted" "affairs" #> [181] "affectionate" "afternoon" "almost" "appeared" #> [185] "barely" "beginning" "between" "bred" #> [189] "cease" "centuries" "child" "connection" #> [193] "considered" "course" "dark" "deep" #> [197] "desire" "did" "early" "enough" #> [201] "enter" "entering" "eyes" "families" #> [205] "far" "fond" "fortune" "four" #> [209] "friend" "friends" "given" "grandfather" #> [213] "half" "heard" "here" "history" #> [217] "home" "hope" "hour" "hours" #> [221] "impatiently" "inhabitants" "invitation" "journey" #> [225] "lad" "lawyer" "legal" "line" #> [229] "longer" "look" "make" "might" #> [233] "mrs" "myself" "nearly" "once" #> [237] "over" "point" "poor" "pretty" #> [241] "property" "proud" "quite" "read" #> [245] "receive" "remembrance" "respect" "respectable" #> [249] "saying" "sea-coast" "seen" "seventeen" #> [253] "sir" "sister" "sisters" "situation" #> [257] "sixteen" "such" "sure" "taken" #> [261] "things" "though" "thought" "towards" #> [265] "turned" "twenty" "twice" "unless" #> [269] "village" "whose" "woman" "would" #> [273] "year" "same" "saw" "above" #> [277] "bennet" "estate" "god" "letters" #> [281] "vernon" "want" "—" "back" #> [285] "broad" "christmas" "consumption" "cursed" #> [289] "dashwood" "dog" "drop" "eltham" #> [293] "emma" "england" "events" "exceptional" #> [297] "farm" "forgive" "glendwr" "governess" #> [301] "huntingdon" "ink" "knew" "make-believe" #> [305] "maria" "married" "miseries" "national" #> [309] "norland" "occurred" "oh" "owain" #> [313] "post" "pounds" "prejudices" "shire" #> [317] "spinning-wheels" "to-day" "truth" "ward" #> [321] "welsh" "wilkins" "1492" "1799" #> [325] "1836" "_angina" "_them_" "_you_" #> [329] "able" "abroad" "abrupt" "acknowledged" #> [333] "across" "actors" "add" "admiration" #> [337] "admitted" "advanced" "advantage" "affection" #> [341] "affectionately" "against" "alien" "alien-looking" #> [345] "allowed" "almonds" "alpine" "already" #> [349] "alteration" "always" "ambition" "amusement" #> [353] "angel" "annie" "announced" "another" #> [357] "answer" "anyhow" "approaches" "arising" #> [361] "arrange" "ask" "assertion" "attacks" #> [365] "attending" "attorney" "aware" "away" #> [369] "baby" "bad" "bag" "barked" #> [373] "baronet's" "baronetage" "became" "begin" #> [377] "being" "believe" "bells" "benefited" #> [381] "bent" "bequeath" "bertram" "best" #> [385] "better" "blankness" "bless" "blessings" #> [389] "blindly" "blood" "bloom" "blushing" #> [393] "book" "books" "born" "bosom" #> [397] "both" "bound" "branch" "brawny" #> [401] "breakfasts" "bringing" "british" "broken" #> [405] "brother" "builder" "burden" "burge" #> [409] "burnt" "burthen" "busily" "business" #> [413] "busy" "buy" "called" "calling" #> [417] "captivate" "career" "caresses" "carpenter" #> [421] "carrying" "case" "catholics" "cattle" #> [425] "caucasus" "caught" "centre" "century" #> [429] "certainly" "chance" "changed" "character" #> [433] "charge" "cheerful" "chieftain" "children" #> [437] "church" "churchhill" "cities" "claim" #> [441] "clear" "clergyman" "clerk" "clever" #> [445] "clock" "close" "clothed" "coaches" #> [449] "come" "comer" "comes" "comfortable" #> [453] "comforts" "coming" "companion" "conceal" #> [457] "conduct" "confectioner" "confectioner's" "confectionery" #> [461] "confidential" "connected" "consequence" "consequences" #> [465] "considerable" "consideration" "consolation" "consolidated" #> [469] "constant" "constitution" "contained" "contemplating" #> [473] "contempt" "continental" "contrast" "convenient" #> [477] "conveyancing" "corn" "could" "country" #> [481] "country-folk" "countrymen" "couple" "creations" #> [485] "cried" "cumberland" "dare" "daresay" #> [489] "daughter" "dawn" "dead" "deafen" #> [493] "dears" "debts" "dec" "degree" #> [497] "delightful" "delivering" "delusive" "deserve" #> [501] "desired" "desolation" "different" "dines" #> [505] "discern" "discretion" "disinherited" "disposition" #> [509] "dispositions" "distinction" "distress" "distressed" #> [513] "districts" "domes" "domestic" "doors" #> [517] "dressed-up" "driven" "dumplings" "eager" #> [521] "earliest" "earthly" "egyptian" "eighteenth" #> [525] "elevation" "elliot" "else" "endless" #> [529] "endured" "engage" "engineer" "enlightenment" #> [533] "envy" "equal" "equally" "equitable" #> [537] "established" "ever" "excellent" "excitement" #> [541] "exclaimed" "expectation" "experience" "expressed" #> [545] "extraordinary" "faculties" "failed" "faint" #> [549] "fairly" "fallen" "famous" "far-away" #> [553] "far-reaching" "farmhouses" "fatalities" "favourable" #> [557] "fed" "feeling" "feelings" "fell" #> [561] "fiercely" "fifteen" "figure" "fills" #> [565] "firm" "five" "fix" "fixed" #> [569] "flash" "folks" "foresee" "forests" #> [573] "fortitude" "forty" "forward" "found" #> [577] "frances" "free" "full" "fully" #> [581] "general" "generality" "generations" "gentry" #> [585] "get" "gives" "glass" "glazing" #> [589] "glendower" "go" "got" "grandmother" #> [593] "grass" "greatness" "green" "groan" #> [597] "guidance" "guys" "hall" "hamley" #> [601] "hands" "happened" "happy" "hayslope" #> [605] "health" "hearing" "hearts" "heaven" #> [609] "heavy" "henry" "hercules" "hero" #> [613] "hills" "honest" "hornby" "hospitable" #> [617] "household" "housekeeper" "however" "human" #> [621] "hummed" "husband" "idle" "ill" #> [625] "illiterate" "immediately" "improvements" "incidents" #> [629] "income" "independence" "indistinct" "indulgent" #> [633] "inexperienced" "influential" "inheritor" "inroads" #> [637] "inside" "insular" "intended" "interested" #> [641] "intermediate" "intimacy" "introduced" "invited" #> [645] "isles" "james" "jars" "jerky" #> [649] "jews" "jonathan" "joy" "june" #> [653] "kellynch" "kept" "knowledge" "ladies" #> [657] "lanes" "langford" "late" "lately" #> [661] "lead" "leaf" "learnt" "lease" #> [665] "least" "leaving" "left" "leigh" #> [669] "less" "let" "levant" "likes" #> [673] "limited" "lips" "live" "lodgings" #> [677] "looked" "looking" "lord" "loss" #> [681] "love" "lozenges" "luck" "lucy" #> [685] "ludlow" "macaroons" "magical" "makes" #> [689] "making" "manner" "mansfield" "many-curved" #> [693] "marriage" "marrying" "masts" "match" #> [697] "measurer" "meet" "men's" "mental" #> [701] "meringues" "mid" "mighty" "miles" #> [705] "mind" "minds" "mingled" "minutes" #> [709] "mirror" "modify" "money" "month" #> [713] "months" "morning" "motion" "mountain" #> [717] "mounts" "multitude" "mysterious" "nakedness" #> [721] "name" "natives" "naturally" "need" #> [725] "needed" "needle" "neighbourhood" "nephew" #> [729] "netherfield" "new" "north" "northampton" #> [733] "notes" "nought" "nurse-maid" "oak" #> [737] "objection" "obliged" "obtained" "occupation" #> [741] "off" "offends" "offer" "often" #> [745] "olive" "one-and-twenty" "opened" "opinion" #> [749] "order" "ordinary" "orphan" "otherwise" #> [753] "out" "outline" "outweigh" "owen" #> [757] "owner" "oxford" "pains" "pale" #> [761] "pallid" "paradise" "parents" "parted" #> [765] "particularly" "passing" "past" "pastry-cook's" #> [769] "patents" "patriotism" "pay" "peasant" #> [773] "pectoris_" "pen" "peppermint" "period" #> [777] "person" "physical" "physician" "pillars" #> [781] "pine" "pink" "pitch" "pity" #> [785] "place" "places" "plain" "plains" #> [789] "pleasure" "plum-buns" "poem" "poignancy" #> [793] "polished" "pork" "possession" "powerless" #> [797] "powers" "precepts" "predict" "presence" #> [801] "pressing" "pretend" "prince" "principality" #> [805] "principally" "prize" "prizes" "produced" #> [809] "professional" "profiting" "prolong" "prosper" #> [813] "protestants" "protracted" "proudly" "provide" #> [817] "provision" "provisions" "purchase" "pure" #> [821] "puritans" "race" "races" "rain-freshened" #> [825] "raised" "raising" "rank" "rarely" #> [829] "rather" "rattling" "reach" "reader" #> [833] "readers" "received" "redoubted" "refuge" #> [837] "refuse" "relating" "remnant" "remnants" #> [841] "rented" "replied" "repugnance" "residence" #> [845] "restless" "retirement" "returned" "reveal" #> [849] "rich" "ridges" "rightful" "ringing" #> [853] "rise" "rising" "river-sides" "rochdale" #> [857] "room" "roomy" "round" "roused" #> [861] "sad" "said" "salt" "sate" #> [865] "satiety" "satirized" "satisfied" "scarcely" #> [869] "scattered" "scholar" "school" "science" #> [873] "scotland" "screaming" "scruple" "sea" #> [877] "secure" "sedge-like" "seemed" "seems" #> [881] "sensations" "sentence" "separation" "serve" #> [885] "service" "settled" "seven" "shadows" #> [889] "sharp" "shepherd's" "shop" "show" #> [893] "showing" "side" "sidereal" "sign" #> [897] "silk" "sister's" "six" "skill" #> [901] "slightest" "slow" "snowy" "soaring" #> [905] "socially" "society" "sold" "somersetshire" #> [909] "something" "somewhere" "son" "soon" #> [913] "sorcerer" "sorrow" "spelling" "spending" #> [917] "spires" "spoken" "spots" "spring-time" #> [921] "standing" "stars" "start" "state" #> [925] "station" "stay" "stayed" "steady" #> [929] "steal" "still" "stirred" "stock" #> [933] "stomach" "stooped" "story" "strange" #> [937] "strangely" "strengthened" "strict" "strongly" #> [941] "studied" "sufficiently" "sugar-candy" "sugared" #> [945] "summits" "sun" "sunset" "supplied" #> [949] "supply" "suppose" "sups" "susan" #> [953] "sussex" "taking" "tale" "taylor" #> [957] "tedium" "tells" "ten" "tender" #> [961] "thanks" "thee" "thereby" "therefore" #> [965] "thing" "thirty" "thomas" "those" #> [969] "thou'rt" "thread-lace" "three-cornered" "times" #> [973] "told" "took" "tortured" "toy" #> [977] "traditions" "transacted" "true" "try" #> [981] "twelfth-cake" "twenty-one" "unceasing" "uncle" #> [985] "undersized" "undertake" "undertaken" "undertakes" #> [989] "unit" "unite" "universally" "unstable" #> [993] "unwelcome" "unwilling" "upland" "upright" #> [997] "urgent" "us" "utter" "valleys" #> [1001] "vex" "views" "visions" "wainscoting" #> [1005] "wales" "walk" "walter" "warm" #> [1009] "watching" "way" "wearisome" "week" #> [1013] "weeks" "western" "westmoreland" "whether" #> [1017] "while" "whisper" "whistle" "whizz" #> [1021] "widow" "window-frames" "wing" "winter" #> [1025] "wisdom" "wise" "witches" "within" #> [1029] "wizards" "women" "woodhouse" "woodhouse's" #> [1033] "words" "workmen" "workshop" "ye" #> [1037] "yeast" "yeoman" "yet" "youngest" #> [1041] "youth" "“" "”"