Python data.find函数代码示例

    def test_corpus_bleu(self):
        ref_file = find('models/wmt15_eval/ref.ru')
        hyp_file = find('models/wmt15_eval/google.ru')
        mteval_output_file = find('models/wmt15_eval/mteval-13a.output')

        # Reads the BLEU scores from the `mteval-13a.output` file.
        # The order of the list corresponds to the order of the ngrams.
        with open(mteval_output_file, 'r') as mteval_fin:
            # The numbers are located in the last 2nd line of the file.
            # The first and 2nd item in the list are the score and system names.
            mteval_bleu_scores = map(float, mteval_fin.readlines()[-2].split()[1:-1])

        with io.open(ref_file, 'r', encoding='utf8') as ref_fin:
            with io.open(hyp_file, 'r', encoding='utf8') as hyp_fin:
                # Whitespace tokenize the file.
                # Note: split() automatically strip().
                hypothesis = list(map(lambda x: x.split(), hyp_fin))
                # Note that the corpus_bleu input is list of list of references.
                references = list(map(lambda x: [x.split()],ref_fin))
                # Without smoothing.
                for i, mteval_bleu in zip(range(1,10), mteval_bleu_scores):
                    nltk_bleu = corpus_bleu(references, hypothesis, weights=(1.0/i,)*i)
                    # Check that the BLEU scores difference is less than 0.005 .
                    # Note: This is an approximate comparison; as much as
                    #       +/- 0.01 BLEU might be "statistically significant",
                    #       the actual translation quality might not be.
                    assert abs(mteval_bleu - nltk_bleu) < 0.005

                # With the same smoothing method used in mteval-v13a.pl
                chencherry = SmoothingFunction()
                for i, mteval_bleu in zip(range(1,10), mteval_bleu_scores):
                    nltk_bleu = corpus_bleu(references, hypothesis,
                                            weights=(1.0/i,)*i,
                                            smoothing_function=chencherry.method3)
                    assert abs(mteval_bleu - nltk_bleu) < 0.005

def demo():
    from itertools import islice

#    zip_path = find('corpora/toolbox.zip')
#    lexicon = ToolboxData(ZipFilePathPointer(zip_path, 'toolbox/rotokas.dic')).parse()
    file_path = find('corpora/toolbox/rotokas.dic')
    lexicon = ToolboxData(file_path).parse()
    print('first field in fourth record:')
    print(lexicon[3][0].tag)
    print(lexicon[3][0].text)

    print('\nfields in sequential order:')
    for field in islice(lexicon.find('record'), 10):
        print(field.tag, field.text)

    print('\nlx fields:')
    for field in islice(lexicon.findall('record/lx'), 10):
        print(field.text)

    settings = ToolboxSettings()
    file_path = find('corpora/toolbox/MDF/MDF_AltH.typ')
    settings.open(file_path)
#    settings.open(ZipFilePathPointer(zip_path, entry='toolbox/MDF/MDF_AltH.typ'))
    tree = settings.parse(unwrap=False, encoding='cp1252')
    print(tree.find('expset/expMDF/rtfPageSetup/paperSize').text)
    settings_tree = ElementTree(tree)
    print(to_settings_string(settings_tree).encode('utf8'))

def build_model(fmt="binary"):
    print("Loading training data...")
    train_paths = [
        find("corpora/ace_data/ace.dev"),
        find("corpora/ace_data/ace.heldout"),
        find("corpora/ace_data/bbn.dev"),
        find("corpora/ace_data/muc.dev"),
    ]
    train_trees = load_ace_data(train_paths, fmt)
    train_data = [postag_tree(t) for t in train_trees]
    print("Training...")
    cp = NEChunkParser(train_data)
    del train_data

    print("Loading eval data...")
    eval_paths = [find("corpora/ace_data/ace.eval")]
    eval_trees = load_ace_data(eval_paths, fmt)
    eval_data = [postag_tree(t) for t in eval_trees]

    print("Evaluating...")
    chunkscore = ChunkScore()
    for i, correct in enumerate(eval_data):
        guess = cp.parse(correct.leaves())
        chunkscore.score(correct, guess)
        if i < 3:
            cmp_chunks(correct, guess)
    print(chunkscore)

    outfilename = "/tmp/ne_chunker_%s.pickle" % fmt
    print("Saving chunker to %s..." % outfilename)

    with open(outfilename, "wb") as out:
        pickle.dump(cp, out, -1)

    return cp

def nltk_download_corpus(resource_path):
    """
    Download the specified NLTK corpus file
    unless it has already been downloaded.

    Returns True if the corpus needed to be downloaded.
    """
    from nltk.data import find
    from nltk import download
    from os.path import split

    # Download the wordnet data only if it is not already downloaded
    _, corpus_name = split(resource_path)

    ## From http://www.nltk.org/api/nltk.html ##
    # When using find() to locate a directory contained in a zipfile,
    # the resource name must end with the forward slash character.
    # Otherwise, find() will not locate the directory.
    ####
    # Helps when resource_path=='sentiment/vader_lexicon''
    if not resource_path.endswith('/'):
        resource_path = resource_path + '/'

    downloaded = False

    try:
        find(resource_path)
    except LookupError:
        download(corpus_name)
        downloaded = True

    return downloaded

def build_model(fmt='binary'):
    print('Loading training data...')
    train_paths = [find('corpora/ace_data/ace.dev'),
                   find('corpora/ace_data/ace.heldout'),
                   find('corpora/ace_data/bbn.dev'),
                   find('corpora/ace_data/muc.dev')]
    train_trees = load_ace_data(train_paths, fmt)
    train_data = [postag_tree(t) for t in train_trees]
    print('Training...')
    cp = NEChunkParser(train_data)
    del train_data

    print('Loading eval data...')
    eval_paths = [find('corpora/ace_data/ace.eval')]
    eval_trees = load_ace_data(eval_paths, fmt)
    eval_data = [postag_tree(t) for t in eval_trees]

    print('Evaluating...')
    chunkscore = ChunkScore()
    for i, correct in enumerate(eval_data):
        guess = cp.parse(correct.leaves())
        chunkscore.score(correct, guess)
        if i < 3: cmp_chunks(correct, guess)
    print(chunkscore)

    outfilename = '/tmp/ne_chunker_%s.pickle' % fmt
    print('Saving chunker to %s...' % outfilename)

    with open(outfilename, 'wb') as outfile:
        pickle.dump(cp, outfile, -1)

    return cp

    def __init__(self):
        from nltk.data import find
        from nltk import download

        try:
            find('wordnet.zip')
        except LookupError:
            download('wordnet')

def namedEntityRecognizer():
    echo2("Performing NER on incoming stream")
    content = request.stream.read()
    #print content

    if Verbose:
        echo2("Incoming content is "+content)
    PICKLE = "averaged_perceptron_tagger.pickle"
    AP_MODEL_LOC = 'file:'+str(find('taggers/averaged_perceptron_tagger/'+PICKLE))
    tagger = PerceptronTagger(load=False)
    tagger.load(AP_MODEL_LOC)
    pos_tag = tagger.tag
    start = time.time()
    #date_time = timex.tag(content)
    tokenized = nltk.word_tokenize(content)
    tagged = pos_tag(tokenized)
    namedEnt = nltk.ne_chunk(tagged, binary=True)
    names = extract_entity_names(namedEnt, 'NE')
    #names.extend(date_time)
    result = {"result" : "success", "names" : names}
    if Units:
        grammar = '''unit: {<CD><NNS>?<NN.*>?},
                     unit: {<CD><JJ>?<NN.*>}
                  '''
        parser = nltk.RegexpParser(grammar)
        units = extract_entity_names(parser.parse(tagged),'unit')
        result['units'] = units
    jsonDoc = json.dumps(result, sort_keys=True, indent=4, separators=(',', ': '))
    end = time.time()
    print "NER took "+str(end - start)+" seconds"
    return jsonDoc

 def _vocabulary(self):
     return (
         data.find('stemmers/porter_test/porter_vocabulary.txt')
             .open(encoding='utf-8')
             .read()
             .splitlines()
     )

 def _vocabulary(self):
     with closing(
         data.find('stemmers/porter_test/porter_vocabulary.txt').open(
             encoding='utf-8'
         )
     ) as fp:
         return fp.read().splitlines()

def demo():
    from nltk.data import find
    corpus_root = find('corpora/childes/data-xml/Eng-USA/')
    childes = CHILDESCorpusReader(corpus_root, u'.*.xml')

    # describe all corpus
    for file in childes.fileids()[:5]:
        corpus = ''
        corpus_id = ''
        for (key,value) in childes.corpus(file)[0].items():
            if key == "Corpus": corpus = value
            if key == "Id": corpus_id = value
        print 'Reading', corpus,corpus_id,' .....'
        print "words:", childes.words(file)[:7],"..."
        print "words with replaced words:", childes.words(file, replace=True)[:7]," ..."
        print "words with pos tags:", childes.words(file, pos=True)[:7]," ..."
        print "words (only MOT):", childes.words(file, speaker='MOT')[:7], "..."
        print "words (only CHI):", childes.words(file, speaker='CHI')[:7], "..."
        print "stemmed words:", childes.words(file, stem=True)[:7]," ..."
        print "words with relations and pos-tag:", childes.words(file, relation=True)[:5]," ..."
        print "sentence:", childes.sents(file)[:2]," ..."
        for (participant, values) in childes.participants(file)[0].items():
                for (key, value) in values.items():
                    print "\tparticipant", participant, key, ":", value
        print "num of sent:", len(childes.sents(file))
        print "num of morphemes:", len(childes.words(file, stem=True))
        print "age:", childes.age(file)    
        print "age in month:", childes.age(file, month=True)    
        print "MLU:", childes.MLU(file)
        print '\r'

 def test_vocabulary_nltk_mode(self):
     self._test_against_expected_output(
         PorterStemmer.NLTK_EXTENSIONS,
         data.find('stemmers/porter_test/porter_nltk_output.txt')
             .open(encoding='utf-8')
             .read()
             .splitlines()
     )

def _get_tagger(lang=None):
    if lang == 'rus':
        tagger = PerceptronTagger(False)
        ap_russian_model_loc = 'file:' + str(find(RUS_PICKLE))
        tagger.load(ap_russian_model_loc)
    else:
        tagger = PerceptronTagger()
    return tagger

 def __init__(self):
     from nltk.data import find
     from nltk import download
     import os
     
     # Download the wordnet data only if it is not already downloaded
     wordnet_path = None
     if os.name == 'nt':
         wordnet_path = os.path.join(os.getenv('APPDATA'), 'nltk_data',
                                             'corpora', 'wordnet.zip')
     else:
         wordnet_path = os.path.join(os.path.expanduser('~'), 'nltk_data',
                                             'corpora', 'wordnet.zip')
     try:
         if not os.path.isfile(wordnet_path):
             find('wordnet.zip')
     except LookupError:
         download('wordnet')

def demo(corpus_root=None):
    """
    The CHILDES corpus should be manually downloaded and saved
    to ``[NLTK_Data_Dir]/corpora/childes/``
    """
    if not corpus_root:
        from nltk.data import find

        corpus_root = find('corpora/childes/data-xml/Eng-USA/')

    try:
        childes = CHILDESCorpusReader(corpus_root, '.*.xml')
        # describe all corpus
        for file in childes.fileids()[:5]:
            corpus = ''
            corpus_id = ''
            for (key, value) in childes.corpus(file)[0].items():
                if key == "Corpus":
                    corpus = value
                if key == "Id":
                    corpus_id = value
            print('Reading', corpus, corpus_id, ' .....')
            print("words:", childes.words(file)[:7], "...")
            print(
                "words with replaced words:",
                childes.words(file, replace=True)[:7],
                " ...",
            )
            print("words with pos tags:", childes.tagged_words(file)[:7], " ...")
            print("words (only MOT):", childes.words(file, speaker='MOT')[:7], "...")
            print("words (only CHI):", childes.words(file, speaker='CHI')[:7], "...")
            print("stemmed words:", childes.words(file, stem=True)[:7], " ...")
            print(
                "words with relations and pos-tag:",
                childes.words(file, relation=True)[:5],
                " ...",
            )
            print("sentence:", childes.sents(file)[:2], " ...")
            for (participant, values) in childes.participants(file)[0].items():
                for (key, value) in values.items():
                    print("\tparticipant", participant, key, ":", value)
            print("num of sent:", len(childes.sents(file)))
            print("num of morphemes:", len(childes.words(file, stem=True)))
            print("age:", childes.age(file))
            print("age in month:", childes.age(file, month=True))
            print("MLU:", childes.MLU(file))
            print()

    except LookupError as e:
        print(
            """The CHILDES corpus, or the parts you need, should be manually
        downloaded from https://childes.talkbank.org/data-xml/ and saved at
        [NLTK_Data_Dir]/corpora/childes/
            Alternately, you can call the demo with the path to a portion of the CHILDES corpus, e.g.:
        demo('/path/to/childes/data-xml/Eng-USA/")
        """
        )

    def __init__(self):
        from nltk.data import find
        from nltk import download
        import os

        # Download the punkt data only if it is not already downloaded
        punkt_path = None
        if os.name == 'nt':
            punkt_path = os.path.join(os.getenv('APPDATA'), 'nltk_data',
                                                'tokenizers', 'punkt.zip')
        else:
            punkt_path = os.path.join(os.path.expanduser('~'), 'nltk_data',
                                                'tokenizers', 'punkt.zip')
        try:
            if not os.path.isfile(punkt_path):
                find('punkt.zip')
        except LookupError:
            download('punkt')