Python LazyCorpusLoader.fileids方法代码示例

# 需要导入模块: from nltk.corpus.util import LazyCorpusLoader [as 别名]
# 或者: from nltk.corpus.util.LazyCorpusLoader import fileids [as 别名]
def demo():

    import nltk
    from nltk.corpus.util import LazyCorpusLoader

    root = nltk.data.find("corpora/knbc/corpus1")
    fileids = [
        f for f in find_corpus_fileids(FileSystemPathPointer(root), ".*") if re.search(r"\d\-\d\-[\d]+\-[\d]+", f)
    ]

    def _knbc_fileids_sort(x):
        cells = x.split("-")
        return (cells[0], int(cells[1]), int(cells[2]), int(cells[3]))

    knbc = LazyCorpusLoader("knbc/corpus1", KNBCorpusReader, sorted(fileids, key=_knbc_fileids_sort), encoding="euc-jp")

    print knbc.fileids()[:10]
    print "".join(knbc.words()[:100])

    print "\n\n".join("%s" % tree for tree in knbc.parsed_sents()[:2])

    knbc.morphs2str = lambda morphs: "/".join(
        "%s(%s)" % (m[0], m[1].split(" ")[2]) for m in morphs if m[0] != "EOS"
    ).encode("utf-8")

    print "\n\n".join("%s" % tree for tree in knbc.parsed_sents()[:2])

    print "\n".join(" ".join("%s/%s" % (w[0], w[1].split(" ")[2]) for w in sent) for sent in knbc.tagged_sents()[0:2])

# 需要导入模块: from nltk.corpus.util import LazyCorpusLoader [as 别名]
# 或者: from nltk.corpus.util.LazyCorpusLoader import fileids [as 别名]
def demo():

    import nltk
    from nltk.corpus.util import LazyCorpusLoader

    root = nltk.data.find('corpora/knbc/corpus1')
    fileids = [f for f in find_corpus_fileids(FileSystemPathPointer(root), ".*")
               if re.search(r"\d\-\d\-[\d]+\-[\d]+", f)]

    def _knbc_fileids_sort(x):
        cells = x.split('-')
        return (cells[0], int(cells[1]), int(cells[2]), int(cells[3]))

    knbc = LazyCorpusLoader('knbc/corpus1', KNBCorpusReader,
                            sorted(fileids, key=_knbc_fileids_sort), encoding='euc-jp')

    print knbc.fileids()[:10]
    print ''.join( knbc.words()[:100] )

    print '\n\n'.join( '%s' % tree for tree in knbc.parsed_sents()[:2] )

    knbc.morphs2str = lambda morphs: '/'.join(
        "%s(%s)"%(m[0], m[1].split(' ')[2]) for m in morphs if m[0] != 'EOS'
        ).encode('utf-8')

    print '\n\n'.join( '%s' % tree for tree in knbc.parsed_sents()[:2] )

    print '\n'.join( ' '.join("%s/%s"%(w[0], w[1].split(' ')[2]) for w in sent)
                     for sent in knbc.tagged_sents()[0:2] )

# 需要导入模块: from nltk.corpus.util import LazyCorpusLoader [as 别名]
# 或者: from nltk.corpus.util.LazyCorpusLoader import fileids [as 别名]
def parse_wsj(processes=8):
    ptb = LazyCorpusLoader( # Penn Treebank v3: WSJ portions
        'ptb', CategorizedBracketParseCorpusReader, r'wsj/\d\d/wsj_\d\d\d\d.mrg',
        cat_file='allcats.txt', tagset='wsj')

    fileids = ptb.fileids()
    params = []
    for f in fileids:
        corpus = zip(ptb.parsed_sents(f), ptb.tagged_sents(f))
        for i, (parsed, tagged) in enumerate(corpus):
            params.append((f, i, parsed, tagged))

    p = Pool(processes)
    p.starmap(get_best_parse, sorted(params, key=lambda x: (x[0], x[1])))

# 需要导入模块: from nltk.corpus.util import LazyCorpusLoader [as 别名]
# 或者: from nltk.corpus.util.LazyCorpusLoader import fileids [as 别名]
wordlist = LazyCorpusLoader(
        'bamana/wordlist', PlaintextCorpusReader, r'bailleul.clean.wordlist', word_tokenizer=orthographic_word, encoding='utf-8')

properlist = LazyCorpusLoader(
        'bamana/propernames', PlaintextCorpusReader, r'.*\.clean\.wordlist', word_tokenizer=orthographic_word, encoding='utf-8')

propernames = LazyCorpusLoader(
        'bamana/propernames', ToolboxCorpusReader, '.*\.txt', encoding='utf-8')

bailleul = LazyCorpusLoader(
        'bamana/bailleul', ToolboxCorpusReader, r'bailleul.txt', encoding='utf-8')

lexicon = ElementTree(bailleul.xml('bailleul.txt'))

for file in propernames.fileids():
    for e in ElementTree(propernames.xml(file)).findall('record'):
        ge = Element('ge')
        ge.text = e.find('lx').text
        e.append(ge)
        ps = Element('ps')
        ps.text = 'n.prop'
        e.append(ps)
        lexicon.getroot().append(e)

wl = {}
wl_detone = {}

def normalize_bailleul(word):
    return u''.join([c for c in word if c not in u'.-'])

# 需要导入模块: from nltk.corpus.util import LazyCorpusLoader [as 别名]
# 或者: from nltk.corpus.util.LazyCorpusLoader import fileids [as 别名]
def loadClassifier(outputdir):
    classifier_filename = os.path.join("pickled_algos", "voted_classifier.pickle") 
    word_features_filename = os.path.join("pickled_algos", "word_features.pickle")
    if os.path.exists(classifier_filename) and os.path.exists(word_features_filename):
        word_features = pickleLoad("word_features.pickle")
#        classifier = pickleLoad("originalnaivebayes.pickle")
#        MNB_classifier = pickleLoad("MNB_classifier.pickle")
#        BernoulliNB_classifier = pickleLoad("BernoulliNB_classifier.pickle")
#        LogisticRegression_classifier = pickleLoad("LogisticRegression_classifier.pickle")
#        SGDClassifier_classifier = pickleLoad("SGDClassifier_classifier.pickle")
#        LinearSVC_classifier = pickleLoad("LinearSVC_classifier.pickle")
#        
#        voted_classifier = VoteClassifier(classifier,
##                                  NuSVC_classifier,
#                                  LinearSVC_classifier,
#                                  SGDClassifier_classifier,
#                                  MNB_classifier,
#                                  BernoulliNB_classifier,
#                                  LogisticRegression_classifier)
        voted_classifier= pickleLoad("voted_classifier.pickle")
        return voted_classifier, word_features
    else:
        criticas_cine = LazyCorpusLoader(
                'criticas_cine', CategorizedPlaintextCorpusReader,
                r'(?!\.).*\.txt', cat_pattern=r'(neg|pos)/.*',
                encoding='utf-8')
#        criticas_cine = LazyCorpusLoader(
#                'criticas_cine_neu', CategorizedPlaintextCorpusReader,
#                r'(?!\.).*\.txt', cat_pattern=r'(neg|neu|pos)/.*',
#                encoding='utf-8')
            
        documents = [(list(criticas_cine.words(fileid)), category)
                     for category in criticas_cine.categories()
                     for fileid in criticas_cine.fileids(category)]
#            
#        document_pos = [(list(criticas_cine.words(fileid)), "pos")
#                        for fileid in criticas_cine.fileids("pos")]
#        document_neg = [(list(criticas_cine.words(fileid)), "neg")
#                        for fileid in criticas_cine.fileids("neg")]
#        document_neu = [(list(criticas_cine.words(fileid)), "neu")
#                        for fileid in criticas_cine.fileids("neu")]
        
        random.shuffle(documents)
        
#        random.shuffle(document_pos)
#        random.shuffle(document_neg)
#        random.shuffle(document_neu)
        
        all_words = []
        
        for w in criticas_cine.words():
            all_words.append(w.lower())
        
#        for w in criticas_cine.words():
#            if not is_filtered(w.lower()):
#                all_words.append(w.lower())
#        
        all_words = nltk.FreqDist(all_words)
        
        #print (all_words.most_common(50))
        
        # Filtering by type of word
        
#        for sample in all_words:
                    
        
        word_features = list(all_words.keys())[:3000]
        pickleDump(word_features, "word_features.pickle")
        
        featuresets = [(find_features(rev, word_features), category) for (rev, category) in documents]
        
#        featuresetpos = [(find_features(rev, word_features), category) for (rev, category) in document_pos]
#        featuresetneg = [(find_features(rev, word_features), category) for (rev, category) in document_neg]
#        featuresetneu = [(find_features(rev, word_features), category) for (rev, category) in document_neu]
        
#        training_set = featuresetpos[:1000]
#        training_set.extend(featuresetneg[:1000])
#        training_set.extend(featuresetneu[:1000])
#        testing_set = featuresetpos[1000:1273]
#        testing_set.extend(featuresetneg[1000:])
#        testing_set.extend(featuresetneu[1000:])

#        pos_feat = [(featuresSet, category) for (featuresSet, category) in featuresets if category == "pos"]
#        neu_feat = [(featuresSet, category) for (featuresSet, category) in featuresets if category == "neu"]
#        neg_feat = [(featuresSet, category) for (featuresSet, category) in featuresets if category == "neg"]
                
        training_set = featuresets[:2000]
        testing_set =  featuresets[2000:]
        classifier = nltk.NaiveBayesClassifier.train(training_set)
#        pickleDump(classifier, "originalnaivebayes.pickle")
    
        NaiveBayesClassifierAccuracy = nltk.classify.accuracy(classifier, testing_set)
        
        print("Original Naive Bayes Algo accuracy percent:", (NaiveBayesClassifierAccuracy)*100)
        
        accuracy = Accuracy(classifier,testing_set)
        print(accuracy)
        # order: neu, neg, pos
#        print("Accuracy: ", (accuracy["neg"][0]+accuracy["pos"][2])/3)
#        print("Discarded: ", (accuracy["neu"][0]+accuracy["neg"][1]+accuracy["pos"][0])/3)
#.........这里部分代码省略.........

# 需要导入模块: from nltk.corpus.util import LazyCorpusLoader [as 别名]
# 或者: from nltk.corpus.util.LazyCorpusLoader import fileids [as 别名]
interrogazioni = LazyCorpusLoader(
    'opp_interrogazioni_macro',
    CategorizedPlaintextCorpusReader,
    r'\d*', cat_file='cats.txt', cat_delimiter=','
)

print "computing FreqDist over all words"
all_words = nltk.FreqDist(w.lower() for w in interrogazioni.words())
top_words = all_words.keys()[:2000]


print "generating list of documents for each category"
documents = [
    (list(interrogazioni.words(fileid)), category)
    for category in interrogazioni.categories()
    for fileid in interrogazioni.fileids(category)
]
random.shuffle(documents)

print "building the classifier"
featuresets = [(document_features(d, top_words), c) for (d,c) in documents]
train_set, test_set = featuresets[1000:], featuresets[:1000]
classifier = nltk.NaiveBayesClassifier.train(train_set)

print "classifier accuracy: ", nltk.classify.accuracy(classifier, test_set)

# 需要导入模块: from nltk.corpus.util import LazyCorpusLoader [as 别名]
# 或者: from nltk.corpus.util.LazyCorpusLoader import fileids [as 别名]
train_test_ratio = 2.0/3



def pickleObject():
	obj = classifier
	savefile = open('classifier.pickle', 'w')
	cPickle.dump(obj, savefile, cPickle.HIGHEST_PROTOCOL)

def pickleFeats():
	obj = words_in_sentence
	savefile = open('feats.pickle', 'w')
	cPickle.dump(obj, savefile, cPickle.HIGHEST_PROTOCOL)

files_in_neg = movie_reviews.fileids('neg')
files_in_pos = movie_reviews.fileids('pos')

neg_data = [(words_in_sentence(movie_reviews.words(fileids=[f])), 'neg') for f in files_in_neg]
pos_data = [(words_in_sentence(movie_reviews.words(fileids=[f])), 'pos') for f in files_in_pos]

negative_first_test_pos = int(len(neg_data)*train_test_ratio)
positive_first_test_pos = int(len(pos_data)*train_test_ratio)

train_data = neg_data[:negative_first_test_pos] + pos_data[:positive_first_test_pos]
test_data = neg_data[negative_first_test_pos:] + pos_data[positive_first_test_pos:]
print 'training on %d paragraphs and testing on %d paragraphs' % (len(train_data), len(test_data))

classifier = NaiveBayesClassifier.train(train_data)
print 'accuracy:', nltk.classify.util.accuracy(classifier, test_data)
classifier.show_most_informative_features(20)

# 需要导入模块: from nltk.corpus.util import LazyCorpusLoader [as 别名]
# 或者: from nltk.corpus.util.LazyCorpusLoader import fileids [as 别名]
from nltk.corpus.util import LazyCorpusLoader
from nltk.corpus.reader import WordListCorpusReader

reader = LazyCorpusLoader('cookbook', WordListCorpusReader, ['wordlist.txt'])
print(isinstance(reader, LazyCorpusLoader))

print(reader.fileids())
print(isinstance(reader, LazyCorpusLoader))
print(isinstance(reader, WordListCorpusReader))

# 需要导入模块: from nltk.corpus.util import LazyCorpusLoader [as 别名]
# 或者: from nltk.corpus.util.LazyCorpusLoader import fileids [as 别名]
def summarize_cisco_support_forum_texts():
    # cisco_plain_text = LazyCorpusLoader(
    #    'content', PlaintextCorpusReader, r'(?!\.).*\.txt', encoding='latin_1')
    cisco_plain_text = LazyCorpusLoader(
        "cisco_forum_subset", PlaintextCorpusReader, r"(?!\.).*\.txt", encoding="latin_1"
    )
    token_dict = {}
    for article in cisco_plain_text.fileids():
        token_dict[article] = cisco_plain_text.raw(article)

    tfidf = TfidfVectorizer(tokenizer=tokenize_and_stem, stop_words="english", decode_error="ignore")

    sys.stdout.flush()

    # creates Compressed Sparse Row format numpy matrix
    tdm = tfidf.fit_transform(token_dict.values())
    feature_names = tfidf.get_feature_names()

    # problem_statement_#1 - summarize support_forum articles automatically
    for article_id in range(0, tdm.shape[0] - 2):
        article_text = cisco_plain_text.raw(cisco_plain_text.fileids()[article_id])
        sent_scores = []
        for sentence in nltk.sent_tokenize(article_text):
            score = 0
            sent_tokens = tokenize_and_stem(sentence)
            for token in (t for t in sent_tokens if t in feature_names):
                score += tdm[article_id, feature_names.index(token)]
            sent_scores.append((score / len(sent_tokens), sentence))
        summary_length = int(math.ceil(len(sent_scores) / 5))
        sent_scores.sort(key=lambda sent: sent[0])
        print "\n*** SUMMARY ***"
        for summary_sentence in sent_scores[:summary_length]:
            print summary_sentence[1]
        print "\n*** ORIGINAL ***"
        print article_text

    # problem_statement_#2 - automatically categorize forum posts by tags into various groups
    reduce_dimensionality_and_cluster_docs(tfidf, tdm, num_features=200)

    # problem_statement_#3 - find similar documents to a current document (that user is reading) automatically
    # eg - quora: find similar questions, find similar answers
    cosine_similarity(tdm[0:1], tdm)
    """
    output looks like this
    array([[ 1.        ,  0.22185251,  0.0215558 ,  0.03805012,  0.04796646,
         0.05069365,  0.05507056,  0.03374501,  0.03643342,  0.05308392,
         0.06002623,  0.0298806 ,  0.04177088,  0.0844478 ,  0.07951179,
         0.02822186,  0.03036787,  0.11022385,  0.0535391 ,  0.10009412,
         0.07432719,  0.03753424,  0.06596462,  0.01256566,  0.02135591,
         0.13931643,  0.03062681,  0.02595649,  0.04897851,  0.06276997,
         0.03173952,  0.01822134,  0.04043555,  0.06629454,  0.05436211,
         0.0549144 ,  0.04400169,  0.05157118,  0.05409632,  0.09541703,
         0.02473209,  0.05646599,  0.05728387,  0.04672681,  0.04519217,
         0.04126276,  0.06289187,  0.03116767,  0.04828476,  0.04745193,
         0.01404426,  0.04201325,  0.023492  ,  0.07138136,  0.03778315,
         0.03677206,  0.02553581]])
    The first document is compared to the rest, with the most similar to it being itself with score of 1, next most similar to it is document with score 0.22185251
    """

    cosine_similarities = linear_kernel(tdm[0:1], tdm).flatten()

    # mapping back to document_name space
    related_docs_indices = cosine_similarities.argsort()
    """
    document_ids
    array([23, 50, 31, 24,  2, 52, 40, 56, 27, 15, 11, 16, 26, 47, 30,  7,  8,
       55, 21, 54,  3, 32, 45, 12, 51, 36, 44, 43, 49,  4, 48, 28,  5, 37,
        9, 18, 38, 34, 35,  6, 41, 42, 10, 29, 46, 22, 33, 53, 20, 14, 13,
       39, 19, 17, 25,  1,  0])

       docs 0 and 1 are very similar which are the following posts (last 2 array elements above when sorted)
        https://supportforums.cisco.com/discussion/11469881/aniserver-failed-run-lms-40
        and
        supportforums.cisco.com/discussion/11469606/eos-lms-31-support-quest
    """

    cosine_similarities[related_docs_indices]
    for key, value in token_dict.iteritems():
        print key, value
    # find the actual posts which are the most similar
    tfidf.inverse_transform(tdm)[0]
    tfidf.inverse_transform(tdm)[1]

# 需要导入模块: from nltk.corpus.util import LazyCorpusLoader [as 别名]
# 或者: from nltk.corpus.util.LazyCorpusLoader import fileids [as 别名]
        return source


connection = pyodbc.connect("Driver={Microsoft Access Driver (*.mdb, *.accdb)};DBQ=E:\\farsnettest.mdb")
c = connection.cursor()
#c.execute("select number,example from shir")
corpus = LazyCorpusLoader('hamshahricorpus',XMLCorpusReader, r'(?!\.).*\.xml')
word=u'شیر'
targ = 0
c.execute("select * from shir")
for row in c:
    print row

#out = codecs.open('d:\\shirham.txt','w','utf-8')
for file in corpus.fileids():
#
#   #if num==1000: break
   for doc in  corpus.xml(file).getchildren():
#
          cat=doc.getchildren()[3].text#
          text=doc.getchildren()[5].text
          newtext=correctPersianString(text)
          allwords=text.split()
          sents=newtext.split('.')

          for sent in sents:


             if word in sent.split():
                 targ+=1