Repositories (1)

kaggle-insults
1 snippets stored for this repo
stemmer = nltk.stem.PorterStemmer()

curse_words = set(['dickless', 'moron', 'batard', 'dumb', 'stupid', 'twit', 'jrk', 'sht', 'fucku', 'anus', 'arse', 'arsehole', 'ass', 'assbag', 'assbandit', 'assbanger', 'assbite', 'assclown', 'asscock', 'asscracker', 'asses', 'assface', 'assfuck', 'assfucker', 'assgoblin', 'asshat', 'asshead', 'asshole', 'asshopper', 'assjacker', 'asslick', 'asslicker', 'assmonkey', 'assmunch', 'assmuncher', 'assnigger', 'asspirate', 'assshit', 'assshole', 'asssucker', 'asswad', 'asswipe', 'axwound', 'bampot', 'bastard', 'beaner', 'bitch', 'bitchass', 'bitches', 'bitchtits', 'bitchy', 'blowjob', 'bollocks', 'bollox', 'boner', 'brotherfucker', 'bullshit', 'bumblefuck', 'buttfucka', 'buttfucker', 'carpetmuncher', 'chesticle', 'chinc', 'chink', 'choad', 'chode', 'clit', 'clitface', 'clitfuck', 'clusterfuck', 'cock', 'cockass', 'cockbite', 'cockburger', 'cockface', 'cockfucker', 'cockhead', 'cockjockey', 'cockknoker', 'cockmaster', 'cockmongler', 'cockmongruel', 'cockmonkey', 'cockmuncher', 'cocknose', 'cocknugget', 'cockshit', 'cocksmith', 'cocksmoke', 'cocksmoker', 'cocksniffer', 'cocksucker', 'cockwaffle', 'coochie', 'coochy', 'coon', 'cooter', 'cracker', 'cum', 'cumbubble', 'cumdumpster', 'cumguzzler', 'cumjockey', 'cumslut', 'cumtart', 'cunnie', 'cunnilingus', 'cunt', 'cuntass', 'cuntface', 'cunthole', 'cuntlicker', 'cuntrag', 'cuntslut', 'dago', 'damn', 'deggo', 'dick', 'dickbag', 'dickbeaters', 'dickface', 'dickfuck', 'dickfucker', 'dickhead', 'dickhole', 'dickjuice', 'dickmilk', 'dickmonger', 'dicks', 'dickslap', 'dicksucker', 'dicksucking', 'dicktickler', 'dickwad', 'dickweasel', 'dickweed', 'dickwod', 'dike', 'dildo', 'dipshit', 'doochbag', 'dookie', 'douche', 'douchebag', 'douchewaffle', 'dumass', 'dumbass', 'dumbfuck', 'dumbshit', 'dumshit', 'dyke', 'fag', 'fagbag', 'fagfucker', 'faggit', 'faggot', 'faggotcock', 'fagtard', 'fatass', 'fellatio', 'feltch', 'flamer', 'fuck', 'fuckass', 'fuckbag', 'fuckboy', 'fuckbrain', 'fuckbutt', 'fuckbutter', 'fucked', 'fucker', 'fuckersucker', 'fuckface', 'fuckhead', 'fuckhole', 'fuckin', 'fucking', 'fucknut', 'fucknutt', 'fuckoff', 'fucks', 'fuckstick', 'fucktard', 'fucktart', 'fuckup', 'fuckwad', 'fuckwit', 'fuckwitt', 'fudgepacker', 'gay', 'gayass', 'gaybob', 'gaydo', 'gayfuck', 'gayfuckist', 'gaylord', 'gaytard', 'gaywad', 'goddamn', 'goddamnit', 'gooch', 'gook', 'gringo', 'guido', 'handjob', 'heeb', 'hell', 'ho', 'hoe', 'homo', 'homodumbshit', 'honkey', 'humping', 'jackass', 'jagoff', 'jap', 'jerkass', 'jigaboo', 'jizz', 'junglebunny', 'kike', 'kooch', 'kootch', 'kraut', 'kunt', 'kyke', 'lameass', 'lardass', 'lesbian', 'lesbo', 'lezzie', 'mcfagget', 'mick', 'minge', 'mothafucka', 'motherfucker', 'motherfucking', 'muff', 'muffdiver', 'munging', 'negro', 'nigaboo', 'nigga', 'nigger', 'niggers', 'niglet', 'nutsack', 'paki', 'panooch', 'pecker', 'peckerhead', 'penis', 'penisbanger', 'penisfucker', 'penispuffer', 'piss', 'pissed', 'pissflaps', 'polesmoker', 'pollock', 'poon', 'poonani', 'poonany', 'poontang', 'porchmonkey', 'prick', 'punanny', 'punta', 'pussies', 'pussy', 'pussylicking', 'puto', 'queef', 'queer', 'queerbait', 'queerhole', 'renob', 'rimjob', 'ruski', 'sandnigger', 'schlong', 'scrote', 'shit', 'shitass', 'shitbag', 'shitbagger', 'shitbrains', 'shitbreath', 'shitcanned', 'shitcunt', 'shitdick', 'shitface', 'shitfaced', 'shithead', 'shithole', 'shithouse', 'shitspitter', 'shitstain', 'shitter', 'shittiest', 'shitting', 'shitty', 'shiz', 'shiznit', 'skank', 'skeet', 'skullfuck', 'slut', 'slutbag', 'smeg', 'snatch', 'spic', 'spick', 'splooge', 'spook', 'suckass', 'tard', 'testicle', 'thundercunt', 'tit', 'titfuck', 'tits', 'tittyfuck', 'twat', 'twatlips', 'twats', 'twatwaffle', 'unclefucker', 'vag', 'vagina', 'vajayjay', 'vjayjay', 'wank', 'wankjob', 'wetback', 'whore', 'whorebag', 'whoreface', 'wop', 'assh*le', 'azz', 'basturd', 'turd', 'loser', 'moronic', 'black', 'ch*t', 'd**kless', 'd**k', 'd*ck', 'd1ck', 'dik', 'dumb***', 'dumbsh*t', 'dumbs**t', 'f', 'f*ck', 'f**k', 'f*&k', 'f*cking', 'f#cking', 'f***ing', 'fake', 'fcuk', 'fok', 'fu', 'fuk', 'lame', 'libtard', 'lynch', 'monkey', 'negro', 'nigg*r', 'parasite', 'phuck', 'phuckface', 'pr1ck', 'pieceofch*t', 'sh#t', 'sh*t', 'sh1t', 'sh1thead', 'stfu', 'stupidity', 'troll', 'crap', 'crappy', 'coward', 'azzhole', 'bigot', 'racist', 'libturd', 'toad', 'sucker', '@$$', 'a$$', 'as$hole', 'asshoIe', 'asstard', 'asz', 'b!tch', 'b1tch', 'baloney', 'bastard', 'beeoch', 'beoch', 'bitch', 'blow', 'bludger', 'brainless', 'bs', 'buffoon', 'bullshit', 'bushfucker', 'bytch', 'c0ward', 'caveman', 'clueless', 'cooch', 'crap', 'cretin', 'desperate', 'dic', 'disgrace', 'disgusting', 'dolt', 'douchebag', 'dumb', 'fagget', 'faggot', 'faggott', 'failure', 'fat', 'fuckin', 'fucko', 'fuckoff', 'fucktard', 'fuk', 'fuka', 'fukka', 'fuktard', 'garbage', 'h#ll', 'horrible', 'horrid', 'hypocrit', 'idiocy', 'idiot', 'ignorance', 'ignorant', 'inbred', 'inferior', 'jerk', 'jimdog', 'joker', 'jurk', 'knucklefuck', 'liar', 'lousy', 'lying', 'mentalcase', 'minion', 'miserable', 'mofo', 'moron', 'moronic', 'muthafucka', 'nazi', 'neanderthal', 'nerd', 'p*ssy', 'pathetic', 'pedo', 'pedophile', 'penis', 'perv', 'pervert', 'pig', 'prick', 'prostitute', 'psychotic', 'pussie', 'rectum', 'retard', 'retarded', 'schlong', 'schmuck', 'screw', 'scum', 'scum', 'scumbag', 'shame', 'sheet', 'shyt', 'sh|t', 'slime', 'snob', 'stank', 'stoopid', 'stupid', 'sucker', 'sukin', 'tinkerbell', 'trash', 'troglodytes', 'turd', 'ugly', 'wack', 'wh0re', 'whine', 'whore', 'faagg', 'fagg', 'faag', '$tupid', '@$$', 'Knucklefuck', 'adolf', 'ahole', 'annoying', 'arrogant', 'as$hole', 'asstard', 'beeoch', 'beoch', 'blind', 'bludger', 'bottomfeeder', 'brain', 'bully', 'butt', 'cabbage', 'coloured', 'commie', 'commy', 'coon', 'coward', 'crackpot', 'crybaby', 'dbag', 'diarrhea', 'dikhead', 'dim', 'dolt', 'dopey', 'douche', 'dramaqueen', 'dumbfuck', 'excrement', 'fart', 'fck', 'filth', 'fleabagger', 'fool', 'fraud', 'freak', 'fucko', 'fuckstick', 'fuuck', 'gullible', 'herpes', 'hoodrat', 'horrible', 'hos', 'hypocrisy', 'idi0t', 'idiocy', 'incest', 'intelligence', 'intelligent', 'iq', 'jackoff', 'jacksquat', 'klan', 'klaner', 'klavern', 'knucklehead', 'lame', 'lazy', 'leech', 'lesbo', 'lib', 'libidiot', 'libturd', 'libturdz', 'lyin', 'mad', 'maggot', 'mental', 'mercyless', 'mf', 'mindless', 'monster', 'mufucker', 'muthafucka', 'naive', 'neanderthal', 'ni@@er', 'nieve', 'nutjuice', 'p*ssy', 'parasite', 'peabrain', 'pig', 'pms', 'ponyfag', 'prick', 'psycho', 'psychopath', 'puerile', 'puke', 'queer', 'racist', 'raunchy', 'rectum', 'reject', 's%#t', 's***', 'savage', 'senile', 'shitt', 'simpleton', 'slob', 'sodomite', 'sow', 'spam', 'stoopid', 'stupidest', 'stupidly', 'sux', 'tampon', 'tard', 'trash', 'troglodyte', 'trollbitch', 'twat', 'ugly', 'unaccomplished', 'unintelligent', 'vile', 'wackoff', 'whitepower', 'worthless', 'xenophobic'])
stemmed_curse_words = set([stemmer.stem(word) for word in curse_words])
you_words = set(['you', 'your', 'ya', 'u', 'ur', 'yourself', 'yo', 'yours']) 
stopwords = set(['all', 'just', 'being', 'over', 'both', 'through', 'yourselves', 'its', 'before', 'herself', 'had', 'should', 'to', 'only', 'under', 'ours', 'has', 'do', 'them', 'his', 'very', 'they', 'not', 'during', 'now', 'him', 'nor', 'did', 'this', 'she', 'each', 'further', 'where', 'few', 'because', 'doing', 'some', 'are', 'our', 'ourselves', 'out', 'what', 'for', 'while', 'does', 'above', 'between', 't', 'be', 'we', 'who', 'were', 'here', 'hers', 'by', 'on', 'about', 'of', 'against', 's', 'or', 'own', 'into', 'down', 'from', 'her', 'their', 'there', 'been', 'whom', 'too', 'themselves', 'was', 'until', 'more', 'himself', 'that', 'but', 'don', 'with', 'than', 'those', 'he', 'me', 'myself', 'these', 'up', 'will', 'below', 'can', 'theirs', 'my', 'and', 'then', 'is', 'am', 'it', 'an', 'as', 'itself', 'at', 'have', 'in', 'any', 'if', 'again', 'no', 'when', 'same', 'how', 'other', 'which', 'after', 'most', 'such', 'why', 'a', 'off', 'i', 'yours', 'so', 'the', 'having', 'once'])