o iR@sjdZddlZddlZddlZddlmZddlZddlm Z GdddZ GdddZ Gd d 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)pairwisec@seZdZdZdZdZdZdZhdZideded 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 dAe ejdBZgdCZdDdEZdOdGdHZdPdJdKZdLdMZdNS)QVaderConstantsz8 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!?!?cCsdSN)selfrrO/var/www/edux/Edux_v2/venv/lib/python3.10/site-packages/nltk/sentiment/vader.py__init__szVaderConstants.__init__Tcsn|jtfdd|DrdS|rtdd|DrdSt|D]\}}|dkr4|dkr4dSq!dS)z< Determine if input contains negation words c3s|] }|vVqdSrlower.0word neg_wordsrr z)VaderConstants.negated..Tcss|] }d|vVqdS)zn'tNrrrrrrrleastatF)NEGATEanyrr)r input_words include_ntfirstsecondrrrnegatedszVaderConstants.negatedcCs|t|||}|S)z| Normalize the score to be between -1 and 1 using an alpha that approximates the max expected value )mathsqrt)rscorealpha norm_scorerrr normalizeszVaderConstants.normalizecCs`d}|}||jvr.|j|}|dkr|d9}|r.|r.|dkr)||j7}|S||j8}|S)zh Check if the preceding words increase, decrease, or negate/nullify the valence r)r BOOSTER_DICTisupperC_INCR)rrvalence is_cap_diffscalar word_lowerrrrscalar_inc_decs     zVaderConstants.scalar_inc_decN)T)r)__name__ __module__ __qualname____doc__B_INCRB_DECRrN_SCALARrrSPECIAL_CASE_IDIOMSrecompileescapestring punctuationREGEX_REMOVE_PUNCTUATION PUNC_LISTrrrrrrrrr!sA      !"#$%&'()*+,-./01234G    rc@s0eZdZdZddZddZddZdd Zd S) SentiTextzL Identify sentiment-relevant string-level properties of input text. cCsFt|ts t|d}||_||_||_||_||j|_ dS)Nzutf-8) isinstancestrencodetextrr_words_and_emoticonswords_and_emoticonsallcap_differentialr)rr punc_listregex_remove_punctuationrrrr s  zSentiText.__init__cCsd|jd|j}|}dd|D}ddt|j|D}ddt||jD}|}|||S)zt Returns mapping of form: { 'cat,': 'cat', ',cat': 'cat', } cSsh|] }t|dkr|qSlen)rwrrr #z-SentiText._words_plus_punc..cSi|] }d||dqS)rrjoinrprrr %rz.SentiText._words_plus_punc..cSr)rrrrrrrr&r)rsubrsplitrrupdate)r no_punc_text words_only punc_before punc_afterwords_punc_dictrrr_words_plus_puncs zSentiText._words_plus_punccCsJ|j}|}dd|D}t|D]\}}||vr"||||<q|S)z Removes leading and trailing puncutation Leaves contractions and most emoticons Does not preserve punc-plus-letter emoticons (e.g. :D) cSsg|] }t|dkr|qSrr)rwerrr 3rz2SentiText._words_and_emoticons..)rrr enumerate)rwesrirrrrr+s  zSentiText._words_and_emoticonscCsTd}d}|D] }|r|d7}qt||}d|kr#t|kr(n|Sd}|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_differentialrrrr9s zSentiText.allcap_differentialN)rrrrrrrrrrrrrs   rc@s|eZdZdZ dddZddZddZd d Zd d Zd dZ ddZ ddZ ddZ ddZ ddZddZddZdS)SentimentIntensityAnalyzerz8 Give a sentiment intensity score to sentences. ;sentiment/vader_lexicon.zip/vader_lexicon/vader_lexicon.txtcCs$tj||_||_t|_dSr)nltkdataload lexicon_file make_lex_dictlexiconr constants)rrrrrrPs  z#SentimentIntensityAnalyzer.__init__cCs@i}|jdD]}|ddd\}}t|||<q|S)z6 Convert lexicon file to a dictionary   rr)rrstripfloat)rlex_dictlinermeasurerrrrXs z(SentimentIntensityAnalyzer.make_lex_dictcCst||jj|jj}g}|j}|D]8}d}||}|t|dkr2|dkr2||ddks:||jjvr@| |q| |||||}q| ||}| ||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 sentimentsritemrrrrrpolarity_scoresbs"      z*SentimentIntensityAnalyzer.polarity_scoresc Cs|j}|j}|}||jvr|j|}|r+|r+|dkr%||jj7}n||jj8}tddD]P} || kr||| d|jvr|j||| d||} | dkr]| dkr]| d} | dkri| dkri| d} || }| ||| |}| dkr| |||}q0| |||}| ||S)Nrr}rgffffff?rg?) rrrrrrrranger _never_check _idioms_check _least_checkr) rrrrrrrritem_lowercasestart_isrrrrs>     z,SentimentIntensityAnalyzer.sentiment_valencecCs|dkr5||d|jvr5||ddkr5||ddkr3||ddkr3||jj}|S|dkrT||d|jvrT||ddkrT||jj}|S)Nrrrrrmr)rrrr)rrrrrrrr s  z'SentimentIntensityAnalyzer._least_checkcCsrdd|D}dht|@}|r7|tt|}t|D]\}}||kr,|d||<q||kr6|d||<q|S)NcSsg|]}|qSrr)rw_errrrsz9SentimentIntensityAnalyzer._but_check..butg?r~)setrnextiterr)rrrrbisidx sentimentrrrrs z%SentimentIntensityAnalyzer._but_checkc Cs||dd||}d||d||d||}||dd||d}d||d||d||d}d||d||d}|||||g} | D]} | |jjvrg|jj| }nqWt|d|kr||d||d} | |jjvr|jj| }t|d|dkrd||||d||d} | |jjvr|jj| }||jjvs||jjvr||jj}|S)Nr z{} {} {}rr}z{} {})formatrrrrr) rrrronezero twoonezerotwoone threetwoonethreetwo sequencesseqzeroone zeroonetworrrr sJ                z(SentimentIntensityAnalyzer._idioms_checkcCs |dkr|j||dgr||jj}|dkrI||ddkr6||ddks1||ddkr6|d}n|j|||dgrI||jj}|dkr||ddkre||ddksu||ddksu||ddksu||ddkr{|d }|S|j|||dgr||jj}|S) Nrrrr*rdthisr~r}g?)rrr)rrrr rrrrr s*    z'SentimentIntensityAnalyzer._never_checkcCs ||}||}||}|Sr) _amplify_ep _amplify_qm)rsum_sr ep_amplifier qm_amplifierpunct_emph_amplifierrrr_punctuation_emphasis$s  z0SentimentIntensityAnalyzer._punctuation_emphasiscCs"|d}|dkr d}|d}|S)Nrg㥛 ?count)rrep_countr&rrrr#+s z&SentimentIntensityAnalyzer._amplify_epcCs2|d}d}|dkr|dkr|d}|Sd}|S)Nrrrr}g ףp= ?gQ?r+)rrqm_countr'rrrr$5s z&SentimentIntensityAnalyzer._amplify_qmcCs`d}d}d}|D]"}|dkr|t|d7}|dkr"|t|d7}|dkr*|d7}q|||fS)Nrrr)r)rrpos_sumneg_sum neu_countsentiment_scorerrr_sift_sentiment_scoresBs    z1SentimentIntensityAnalyzer._sift_sentiment_scorescCs|rctt|}|||}|dkr||7}n|dkr||8}|j|}||\}}}|t|kr9||7}n |t|krD||8}|t||} t|| } t|| } t|| } nd}d} d} d} t| dt| dt| dt|dd} | S)Nrrr}r*)negneuposcompound) rsumr)rrr3rfabsround)rrrr%r(r7r/r0r1totalr6r4r5sentiment_dictrrrrTs6     z(SentimentIntensityAnalyzer.score_valenceN)r)rrrrrrrrr rr r r)r#r$r3rrrrrrKs   "2 1  r) rrrr itertoolsr nltk.datar nltk.utilrrrrrrrrs  gD