+ h.Rt^RIt^RI5^RI5]P!R4t]P!R4t]P!R4t]P!R4t!RR4t !R R 4t !R R ] 4t R#) a CorpusReader for reviews corpora (syntax based on Customer Review Corpus). Customer Review Corpus information ================================== Annotated by: Minqing Hu and Bing Liu, 2004. Department of Computer Science University of Illinois at Chicago Contact: Bing Liu, liub@cs.uic.edu https://www.cs.uic.edu/~liub Distributed with permission. The "product_reviews_1" and "product_reviews_2" datasets respectively contain annotated customer reviews of 5 and 9 products from amazon.com. Related papers: - Minqing Hu and Bing Liu. "Mining and summarizing customer reviews". Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD-04), 2004. - Minqing Hu and Bing Liu. "Mining Opinion Features in Customer Reviews". Proceedings of Nineteeth National Conference on Artificial Intelligence (AAAI-2004), 2004. - Xiaowen Ding, Bing Liu and Philip S. Yu. "A Holistic Lexicon-Based Appraoch to Opinion Mining." Proceedings of First ACM International Conference on Web Search and Data Mining (WSDM-2008), Feb 11-12, 2008, Stanford University, Stanford, California, USA. Symbols used in the annotated reviews: :[t]: the title of the review: Each [t] tag starts a review. :xxxx[+|-n]: xxxx is a product feature. :[+n]: Positive opinion, n is the opinion strength: 3 strongest, and 1 weakest. Note that the strength is quite subjective. You may want ignore it, but only considering + and - :[-n]: Negative opinion :##: start of each sentence. Each line is a sentence. :[u]: feature not appeared in the sentence. :[p]: feature not appeared in the sentence. Pronoun resolution is needed. :[s]: suggestion or recommendation. :[cc]: comparison with a competing product from a different brand. :[cs]: comparison with a competing product from the same brand. Note: Some of the files (e.g. "ipod.txt", "Canon PowerShot SD500.txt") do not provide separation between different reviews. This is due to the fact that the dataset was specifically designed for aspect/feature-based sentiment analysis, for which sentence-level annotation is sufficient. For document- level classification and analysis, this peculiarity should be taken into consideration. N)*z ^\[t\](.*)$z%((?:(?:\w+\s)+)?\w+)\[((?:\+|\-)\d)\]z\[(?!t)(p|u|s|cc|cs)\]z##(.*)$cFa]tRt^MtoRtR RltRtRtRtRt Rt Vt R#) Reviewz6 A Review is the main block of a ReviewsCorpusReader. Nc 8WnVf .VnR#W nR#)zt :param title: the title of the review. :param review_lines: the list of the ReviewLines that belong to the Review. N)title review_lines)selfrrs&&&>> from nltk.corpus import product_reviews_1 >>> camera_reviews = product_reviews_1.reviews('Canon_G3.txt') >>> review = camera_reviews[0] >>> review.sents()[0] # doctest: +NORMALIZE_WHITESPACE ['i', 'recently', 'purchased', 'the', 'canon', 'powershot', 'g3', 'and', 'am', 'extremely', 'satisfied', 'with', 'the', 'purchase', '.'] >>> review.features() # doctest: +NORMALIZE_WHITESPACE [('canon powershot g3', '+3'), ('use', '+2'), ('picture', '+2'), ('picture quality', '+1'), ('picture quality', '+1'), ('camera', '+2'), ('use', '+2'), ('feature', '+1'), ('picture quality', '+3'), ('use', '+1'), ('option', '+1')] We can also reach the same information directly from the stream: >>> product_reviews_1.features('Canon_G3.txt') [('canon powershot g3', '+3'), ('use', '+2'), ...] We can compute stats for specific product features: >>> n_reviews = len([(feat,score) for (feat,score) in product_reviews_1.features('Canon_G3.txt') if feat=='picture']) >>> tot = sum([int(score) for (feat,score) in product_reviews_1.features('Canon_G3.txt') if feat=='picture']) >>> mean = tot / n_reviews >>> print(n_reviews, tot, mean) 15 24 1.6 utf8c L\PWW$4W0nRVnR#)a4 :param root: The root directory for the corpus. :param fileids: a list or regexp specifying the fileids in the corpus. :param word_tokenizer: a tokenizer for breaking sentences or paragraphs into words. Default: `WordPunctTokenizer` :param encoding: the encoding that should be used to read the corpus. z README.txtN) CorpusReaderr _word_tokenizer_readme)rrootfileidsword_tokenizerencodings&&&&&r r ReviewsCorpusReader.__init__s! d'<-# r Nc  VfVPpM\V\4'dV.p\VP VR4UUu.uF"wr#VP W P VR7NK$ upp4#uuppi)a= Return a list of features. Each feature is a tuple made of the specific item feature and the opinion strength about that feature. :param fileids: a list or regexp specifying the ids of the files whose features have to be returned. :return: all features for the item(s) in the given file(s). :rtype: list(tuple) Tr>)_fileidsrstrconcatabspaths CorpusView_read_featuresrr<fileidencs&& r rReviewsCorpusReader.featuressu ?mmG  % %iG&*]]7D%A %AMV(;(;cJ%A    s(A5 c  Vf VPp\VPVR4UUu.uF"wr#VPW PVR7NK$ upp4#uuppi)a# Return all the reviews as a list of Review objects. If `fileids` is specified, return all the reviews from each of the specified files. :param fileids: a list or regexp specifying the ids of the files whose reviews have to be returned. :return: the given file(s) as a list of reviews. TrA)rBrDrErF_read_review_blockrHs&& r reviewsReviewsCorpusReader.reviewssa ?mmG&*]]7D%A %AMV(?(?#N%A    s(A c  \VPVRR4UUUu.uF#wr#pVPW PVR7NK% uppp4#uupppi)a! Return all sentences in the corpus or in the specified files. :param fileids: a list or regexp specifying the ids of the files whose sentences have to be returned. :return: the given file(s) as a list of sentences, each encoded as a list of word strings. :rtype: list(list(str)) TrA)rDrErF_read_sent_blockrr<pathrJrIs&& r rReviewsCorpusReader.sentsX,0==$+M +M'T&;&;cJ+M    )A c  \VPVRR4UUUu.uF#wr#pVPW PVR7NK% uppp4#uupppi)a Return all words and punctuation symbols in the corpus or in the specified files. :param fileids: a list or regexp specifying the ids of the files whose words have to be returned. :return: the given file(s) as a list of words and punctuation symbols. :rtype: list(str) TrA)rDrErF_read_word_blockrRs&& r wordsReviewsCorpusReader.wordsrUrVc.p\^4FIpVP4pV'gVu#VP\P!\ V44KK V#)rangereadlinerrefindallFEATURES)rstreamrilines&& r rG"ReviewsCorpusReader._read_featuressGrA??$D OOBJJx6 7  r cVP4pV'g.#\P!\V4pV'gK@\ VP ^4P 4R7pTP4pTP4pT'gT.#\P!\T4'dTPT4T.#\P!\T4p\P!\T4p\P!\T4pT'd#TPPT^,4p\YTR7p TP!T 4K)T)rr/)r_r`matchTITLErgroupstriptellseekrarbNOTESSENTr9tokenizerr) rrcre title_matchreviewoldposfeatsr0rrs && r rM&ReviewsCorpusReader._read_review_blocks??$D ((5$/K{%++A.446[[]F??$Dxxxt$$ F#xJJx.EJJud+E::dD)D++44T!W=$$eLK OOK (r c.pVPV4F1pTPVP4Uu.uFqDNK up4K3 V#uupir.)rMrr)rrcrrrrs&& r rQ$ReviewsCorpusReader._read_sent_block>sG--f5F LL6<<>:>4$>: ;6 ;s A c.p\^4FipVP4p\P!\V4pV'gK8VP VP PV^,44Kk V#r\)r^r_r`rarorr9rp)rrcrYrdrers&& r rX$ReviewsCorpusReader._read_word_blockDs^rA??$D::dD)Dt T11::47CD   r )r:r9r.)r#r$r%r&r'StreamBackedCorpusViewrFWordPunctTokenizerr rrNrrYrGrMrQrXr(r)r*s@r r5r5sN>(J-?,@6 $ * $ " ")B r r5) r'r`nltk.corpus.reader.api nltk.tokenizecompilerirbrnrorrr8r5r r rsw6p $ >" ::,  ,- zz*2 2 j  0q,qr