本文整理汇总了Python中nltk.tag.StanfordPOSTagger方法的典型用法代码示例。如果您正苦于以下问题：Python tag.StanfordPOSTagger方法的具体用法？Python tag.StanfordPOSTagger怎么用？Python tag.StanfordPOSTagger使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类nltk.tag的用法示例。
在下文中一共展示了tag.StanfordPOSTagger方法的6个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: get_postag_with_record
# 需要导入模块: from nltk import tag [as 别名]
# 或者: from nltk.tag import StanfordPOSTagger [as 别名]
def get_postag_with_record(records, pairs):
path = os.path.dirname(__file__)
path = path[:path.rfind(os.sep, 0, len(path)-10)+1] + 'stanford-postagger/'
print(path)
# jar = '/Users/memray/Project/stanford/stanford-postagger/stanford-postagger.jar'
jar = path + '/stanford-postagger.jar'
model = path + '/models/english-bidirectional-distsim.tagger'
pos_tagger = StanfordPOSTagger(model, jar)
# model = '/Users/memray/Project/stanford/stanford-postagger/models/english-left3words-distsim.tagger'
# model = '/Users/memray/Project/stanford/stanford-postagger/models/english-bidirectional-distsim.tagger'
stanford_dir = jar.rpartition('/')[0]
stanford_jars = find_jars_within_path(stanford_dir)
pos_tagger._stanford_jar = ':'.join(stanford_jars)
tagged_source = []
# Predict on testing data
for idx, (record, pair) in enumerate(zip(records, pairs)): # len(test_data_plain)
print('*' * 100)
print('File: ' + record['name'])
print('Input: ' + str(pair[0]))
text = pos_tagger.tag(pair[0])
print('[%d/%d][%d] : %s' % (idx, len(records) , len(pair[0]), str(text)))
tagged_source.append(text)
return tagged_source 示例2: get_postag_with_index
# 需要导入模块: from nltk import tag [as 别名]
# 或者: from nltk.tag import StanfordPOSTagger [as 别名]
def get_postag_with_index(sources, idx2word, word2idx):
path = os.path.dirname(__file__)
path = path[:path.rfind(os.sep, 0, len(path)-10)+1] + 'stanford-postagger/'
print(path)
# jar = '/Users/memray/Project/stanford/stanford-postagger/stanford-postagger.jar'
jar = path + '/stanford-postagger.jar'
model = path + '/models/english-bidirectional-distsim.tagger'
pos_tagger = StanfordPOSTagger(model, jar)
# model = '/Users/memray/Project/stanford/stanford-postagger/models/english-left3words-distsim.tagger'
# model = '/Users/memray/Project/stanford/stanford-postagger/models/english-bidirectional-distsim.tagger'
stanford_dir = jar.rpartition('/')[0]
stanford_jars = find_jars_within_path(stanford_dir)
pos_tagger._stanford_jar = ':'.join(stanford_jars)
tagged_source = []
# Predict on testing data
for idx in xrange(len(sources)): # len(test_data_plain)
test_s_o = sources[idx]
source_text = keyphrase_utils.cut_zero(test_s_o, idx2word)
text = pos_tagger.tag(source_text)
print('[%d/%d] : %s' % (idx, len(sources), str(text)))
tagged_source.append(text)
return tagged_source 示例3: load_pos_tagger
# 需要导入模块: from nltk import tag [as 别名]
# 或者: from nltk.tag import StanfordPOSTagger [as 别名]
def load_pos_tagger():
path = os.path.dirname(__file__)
path = os.path.join(file_dir[: file_dir.rfind('pykp') + 4], 'stanford-postagger')
print(path)
# jar = '/Users/memray/Project/stanford/stanford-postagger/stanford-postagger.jar'
jar = path + '/stanford-postagger.jar'
model = path + '/models/english-bidirectional-distsim.tagger'
pos_tagger = StanfordPOSTagger(model, jar)
stanford_dir = jar.rpartition('/')[0]
stanford_jars = find_jars_within_path(stanford_dir)
pos_tagger._stanford_jar = ':'.join(stanford_jars)
return pos_tagger 示例4: __init__
# 需要导入模块: from nltk import tag [as 别名]
# 或者: from nltk.tag import StanfordPOSTagger [as 别名]
def __init__(self, model_type='english-bidirectional-distsim.tagger'):
"""
Args:
model: model available in $STANFORD_MODELS:
english-bidirectional-distsim.tagger
english-caseless-left3words-distsim.tagger
english-left3words-distsim.tagger
"""
#self.eng_tagger = StanfordPOSTagger(model_type, java_options='-mx16000m')
self.eng_tagger = PerceptronTagger() 示例5: load_pos_tagger
# 需要导入模块: from nltk import tag [as 别名]
# 或者: from nltk.tag import StanfordPOSTagger [as 别名]
def load_pos_tagger(stanford_base_dir):
# path = os.path.dirname(__file__)
# path = os.path.join(file_dir[: file_dir.rfind('pykp') + 4], 'stanford-postagger')
# print(path)
# jar = '/Users/memray/Project/stanford/stanford-postagger/stanford-postagger.jar'
jar = stanford_base_dir + '/stanford-postagger.jar'
model = stanford_base_dir + '/models/english-bidirectional-distsim.tagger'
pos_tagger = StanfordPOSTagger(model_filename=model, path_to_jar=jar)
stanford_base_dir = jar.rpartition('/')[0]
stanford_jars = find_jars_within_path(stanford_base_dir)
pos_tagger._stanford_jar = ':'.join(stanford_jars)
return pos_tagger 示例6: check_postag
# 需要导入模块: from nltk import tag [as 别名]
# 或者: from nltk.tag import StanfordPOSTagger [as 别名]
def check_postag(config):
train_set, validation_set, test_set, idx2word, word2idx = deserialize_from_file(config['dataset'])
path = os.path.dirname(__file__)
path = path[:path.rfind(os.sep, 0, len(path)-10)+1] + 'stanford-postagger/'
jar = path + '/stanford-postagger.jar'
model = path + '/models/english-bidirectional-distsim.tagger'
pos_tagger = StanfordPOSTagger(model, jar)
for dataset_name in config['testing_datasets']:
# override the original test_set
# test_set = load_testing_data(dataset_name, kwargs=dict(basedir=config['path']))(idx2word, word2idx, config['preprocess_type'])
test_sets = load_additional_testing_data(config['testing_datasets'], idx2word, word2idx, config)
test_set = test_sets[dataset_name]
# print(dataset_name)
# print('Avg length=%d, Max length=%d' % (np.average([len(s) for s in test_set['source']]), np.max([len(s) for s in test_set['source']])))
test_data_plain = zip(*(test_set['source'], test_set['target']))
test_size = len(test_data_plain)
# Alternatively to setting the CLASSPATH add the jar and model via their path:
jar = '/Users/memray/Project/stanford/stanford-postagger/stanford-postagger.jar'
# model = '/Users/memray/Project/stanford/stanford-postagger/models/english-left3words-distsim.tagger'
model = '/Users/memray/Project/stanford/stanford-postagger/models/english-bidirectional-distsim.tagger'
pos_tagger = StanfordPOSTagger(model, jar)
for idx in xrange(len(test_data_plain)): # len(test_data_plain)
test_s_o, test_t_o = test_data_plain[idx]
source = keyphrase_utils.cut_zero(test_s_o, idx2word)
print(source)
# Add other jars from Stanford directory
stanford_dir = jar.rpartition('/')[0]
stanford_jars = find_jars_within_path(stanford_dir)
pos_tagger._stanford_jar = ':'.join(stanford_jars)
text = pos_tagger.tag(source)
print(text)