NgRdZddlZddlZddlZddlmZddlZddlm Z GddZ GddZ Gd d Z dS) a If you use the VADER sentiment analysis tools, please cite: Hutto, C.J. & Gilbert, E.E. (2014). VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text. Eighth International Conference on Weblogs and Social Media (ICWSM-14). Ann Arbor, MI, June 2014. N)product)pairwiseceZdZdZdZdZdZdZhdZideded ed ed ed ed ededededededededededeidedededededededed ed!ed"ed#ed$ed%ed&ed'ed(eid)ed*ed+ed,ed-ed.ed/ed0ed1ed2ed3ed4ed5ed6ed7ed8ed9eeeeeeeeeeeeeeeed:Z d;d;dd?d=d@Z e j dAe j ejdBZgdCZdDZdKdFZdLdHZdIZdJS)MVaderConstantsz8 A class to keep the Vader lists and constants. gn?gnҿg~jt?gGz>;ain'tcan'tdon'tisn'tuh-uhwon'taren'tdidn'thadn'thasn'tshan'twasn'tdaren'tdoesn'thaven'tmustn'tneedn'tweren'tcouldn'tmightn'toughtn'twouldn't shouldn'tnornotaintcantdontisntnonenopeuhuhwontarentdidnthadnthasntnevershantwasntcannotdarentdoesnthaventmustntneedntrarelyseldomwerentcouldntdespitemightntneithernothingnowhereoughtntwithoutwouldntshouldnt absolutely amazinglyawfully completely considerably decidedlydeeplyeffing enormouslyentirely especially exceptionally extremely fabulouslyflippingflippinfrickingfrickinfriggingfrigginfullyfuckinggreatlyhellahighlyhugely incredibly intenselymajorlymoremost particularlypurelyquitereally remarkablyso substantially thoroughlytotally tremendouslyuber unbelievably unusuallyutterlyveryalmostbarelyhardlyz just enoughzkind of)kindakindofzkind-oflesslittle marginally occasionallypartlyscarcelyslightlysomewhatzsort ofsortasortofzsort-of?g)zthe shitzthe bombzbad assz yeah rightzcut the mustardz kiss of deathz hand to mouth[]).!?,;:-'"z!!z!!!z??z???z?!?z!?!z?!?!z!?!?cdSN)selfs P/var/www/html/ai-engine/env/lib/python3.11/site-packages/nltk/sentiment/vader.py__init__zVaderConstants.__init__s Tc|jtfd|DrdS|rtd|DrdSt|D]8\}}|dkr|dkrdS9dS)z< Determine if input contains negation words c3DK|]}|vVdSrlower).0word neg_wordss r z)VaderConstants.negated..s0AATtzz||y(AAAAAArTc3BK|]}d|vVdS)zn'tNr)rrs rrz)VaderConstants.negated..s/AAT5DJJLL(AAAAAArleastatF)NEGATEanyrr)r input_words include_ntfirstsecondrs @rnegatedzVaderConstants.negatedsK AAAA[AAA A A 4  AA[AAAAA t%k22  ME6||~~((U[[]]d-B-Btturc@|tj||z|zz }|S)z| Normalize the score to be between -1 and 1 using an alpha that approximates the max expected value )mathsqrt)rscorealpha norm_scores r normalizezVaderConstants.normalizes' TY '>??? rcd}|}||jvrI|j|}|dkr|dz}|r|r|dkr ||jz }n ||jz}|S)zh Check if the preceding words increase, decrease, or negate/nullify the valence r)r BOOSTER_DICTisupperC_INCR)rrvalence is_cap_diffscalar word_lowers rscalar_inc_deczVaderConstants.scalar_inc_decs ZZ\\ * * *&z2F{{" ||~~ *+ *Q;;dk)FFdk)F rN)T)r)__name__ __module__ __qualname____doc__B_INCRB_DECRrN_SCALARrrSPECIAL_CASE_IDIOMSrecompileescapestring punctuationREGEX_REMOVE_PUNCTUATION PUNC_LISTrrrrrrrrr!s F FFH<<<FBCfCVC 6C f C  C V C &C &C fC FC fC C VC fC FC 6!C" F#CC$ 6%C& F'C( 6)C* +C, 6-C. 6/C0 1C2 &3C4 &5C6 f7C8 V9C: 6;C< =C> ?C@ ACB &CCD ECCCF &GCH fICJ fKCL MCN fOCP 6QCR SCT UCV WCX VYCZ 6[C\ ]C^ &_C` &aCb &cCd veCf 6gCChECCCLN *rz*Nibi8J.K.K*N*N*NOOI(       rrc*eZdZdZdZdZdZdZdS) SentiTextzL Identify sentiment-relevant string-level properties of input text. ct|ts"t|d}||_||_||_||_||j|_ dS)Nzutf-8) isinstancestrencodetextrr_words_and_emoticonswords_and_emoticonsallcap_differentialr)rr punc_listregex_remove_punctuations rrzSentiText.__init__ sx$$$ -t{{7++,,D "(@%#'#<#<#>#>  33D4LMMrc0|jd|j}|}d|D}dt |j|D}dt ||jD}|}|||S)zt Returns mapping of form: { 'cat,': 'cat', ',cat': 'cat', } c8h|]}t|dk|Slen)rws r z-SentiText._words_plus_punc..#s#:::As1vvzzazzzrcFi|]}d||dS)rrjoinrps r z.SentiText._words_plus_punc..%s(UUUArwwqzz1Q4UUUrcFi|]}d||dS)rrrrs rrz.SentiText._words_plus_punc..&s(TTT1bggajj!A$TTTr)rsubrsplitrrupdate)r no_punc_text words_only punc_before punc_afterwords_punc_dicts r_words_plus_punczSentiText._words_plus_puncs488TYGG !'')) ::::: UU1T1TUUU TT DN0S0STTT %z***rc|j}|}d|D}t|D]\}}||vr ||||<|S)z Removes leading and trailing puncutation Leaves contractions and most emoticons Does not preserve punc-plus-letter emoticons (e.g. :D) c8g|]}t|dk|Srr)rwes r z2SentiText._words_and_emoticons..3s#///b3r77Q;;r;;;r)rrr enumerate)rwesrirs rrzSentiText._words_and_emoticons+sq ioo//11//C///s^^ - -EAr_$$(,A rcd}d}|D]}|r|dz }t||z }d|cxkrt|krnnd}|S)z Check whether just some words in the input are ALL CAPS :param list words: The words to inspect :returns: `True` if some but not all items in `words` are ALL CAPS FrrT)rr)rwords is_different allcap_wordsrcap_differentials rrzSentiText.allcap_differential9s}   " "D||~~ "! u:: 4  , , , ,#e** , , , , ,LrN)rrrrrrrrrrrrrs] N N N(   rrcdeZdZdZ ddZdZdZdZdZdZ d Z d Z d Z d Z d ZdZdZdS)SentimentIntensityAnalyzerz8 Give a sentiment intensity score to sentences. ;sentiment/vader_lexicon.zip/vader_lexicon/vader_lexicon.txtctj||_||_t |_dSr)nltkdataload lexicon_file make_lex_dictlexiconr constants)rrs rrz#SentimentIntensityAnalyzer.__init__Ps>!INN<88))++ '))rci}|jdD]F}|ddd\}}t|||<G|S)z6 Convert lexicon file to a dictionary   rr)rrstripfloat)rlex_dictlinermeasures rrz(SentimentIntensityAnalyzer.make_lex_dictXsg%++D11 , ,D"jjll0066qs;OT7"7^^HTNNrc*t||jj|jj}g}|j}|D]}d}||}|t |dz kr9|dkr!||dzdks ||jjvr| || |||||}| ||}| ||S)a Return a float for sentiment strength based on the input text. Positive values are positive valence, negative value are negative valence. :note: Hashtags are not taken into consideration (e.g. #BAD is neutral). If you are interested in processing the text in the hashtags too, then we recommend preprocessing your data to remove the #, after which the hashtag text may be matched as if it was a normal word in the sentence. rrkindof) rrrrrindexrrrappendsentiment_valence _but_check score_valence)rr sentitext sentimentsritemrrs rpolarity_scoresz*SentimentIntensityAnalyzer.polarity_scoresbs $.*DN,S   ';' Y YDG#))$//AC+,,q000JJLLF**'A.4466$>>!<<<!!'***//D!ZXXJJ__%8*EE !!*d333rc|j}|j}|}||jvr#|j|}|r'|r%|dkr||jjz }n||jjz}tddD]} || kr||| dzz |jvr|j||| dzz ||} | dkr | dkr| dz} | dkr | dkr| dz} || z}| ||| |}| dkr| |||}| |||}| ||S)Nrrrgffffff?rg?) rrrrrrrranger _never_check _idioms_check _least_checkr) rrrrrrrritem_lowercasestart_iss rrz,SentimentIntensityAnalyzer.sentiment_valences+ '; T\ ) )l>2G||~~ 5+ 5Q;;t~44GGt~44G A;; V VKK+A1,=>DDFF<(( 55+A1,=>A!||QH!||QG%kG"//!4gqG!||"&"4"4W>QST"U"U''1DaHHG'"""rc|dkr||dz |jvrs||dz dkrR||dz dkr0||dz dkr||jjz}nZ|dkrT||dz |jvr0||dz dkr||jjz}|S)Nrrrrror)rrrr)rrrrs rrz'SentimentIntensityAnalyzer._least_checks EE#AE*0022$,FF#AE*0022g==$AE*0022d::'A.4466&@@!DN$;; EE#AE*0022$,FF#AE*0022g== 77Grc d|D}dht|z}|ra|tt|}t |D]"\}}||kr |dz||<||kr|dz||<#|S)Nc6g|]}|Srr)rw_es rrz9SentimentIntensityAnalyzer._but_check..s JJJssyy{{JJJrbutg?r)setrnextiterr)rrrr%bisidx sentiments rrz%SentimentIntensityAnalyzer._but_checksJJ6IJJJg/000  7$**4S ??;;B#,Z#8#8 7 7i"99'03Jt$$BYY'03Jt$rc||dz d||}d||dz ||dz ||}||dz d||dz }d||dz ||dz ||dz }d||dz ||dz }|||||g} | D]$} | |jjvr|jj| }n%t|dz |kr6||d||dz} | |jjvr|jj| }t|dz |dzkrOd||||dz||dz} | |jjvr|jj| }||jjvs||jjvr||jjz}|S)Nr z{} {} {}rrz{} {})formatrrrrr) rrrronezero twoonezerotwoone threetwoonethreetwo sequencesseqzeroone zeroonetwos rrz(SentimentIntensityAnalyzer._idioms_checks6(Q/JJ2Ea2HJJ&& A & A &  "  (A.MM1DQU1KMM '' A & A & A &  >> A &(;AE(B  j&+xH   Cdn888.s rr;z&SentimentIntensityAnalyzer._amplify_ep+s1::c?? a<<H %' rc\|d}d}|dkr|dkr|dz}nd}|S)Nrrrrg ףp= ?gQ?rD)rrqm_countr?s rr<z&SentimentIntensityAnalyzer._amplify_qm5s@::c?? a<<1}} ($ # rcd}d}d}|D]C}|dkr|t|dzz }|dkr|t|dz z }|dkr|dz }D|||fS)Nrrr)r )rrpos_sumneg_sum neu_countsentiment_scores r_sift_sentiment_scoresz1SentimentIntensityAnalyzer._sift_sentiment_scoresBs )  O""/**Q.""/**Q.!##Q **rc|rtt|}|||}|dkr||z }n |dkr||z}|j|}||\}}}|t j|kr||z }n|t j|kr||z}|t j|z|z} t j|| z } t j|| z } t j|| z } nd}d} d} d} t| dt| dt| dt|dd} | S)NrrrrC)negneuposcompound) r sumrArrrNrfabsround)rrrr=r@rSrJrKrLtotalrRrPrQsentiment_dicts rrz(SentimentIntensityAnalyzer.score_valenceTs}  #j//**E#'#=#=eT#J#J qyy----~//66H*.*E*Ej*Q*Q 'GWi7++++//49W----//di0009r\s  ccccccccLAAAAAAAAHnnnnnnnnnnr