def parse_worker(q):
""""""
parser = DependencyTreeParser(model_path='StanfordLibrary/stanford-parser-full-%s/edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz' % DATE)
parser = MetricalTreeParser(parser)
for filename in iter(q.get, 'STOP'):
print 'Working on %s...' % filename
sents = []
with codecs.open(filename, encoding='utf-8') as f:
for line in f:
sents.extend(pause_splitter(line))
df = parser.stats_raw_parse_sents(sents, arto=True)
df.to_csv(codecs.open('%s.csv' % filename, 'w', encoding='utf-8'), index=False)
print 'Finished with %s.' % filename
return True
def parse_worker(q):
""""""
parser = DependencyTreeParser(model_path='Stanford Library/stanford-parser-full-%s/edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz' % DATE)
parser = MetricalTreeParser(parser)
for filename in iter(q.get, 'STOP'):
print('Working on %s...' % filename)
sents = []
with codecs.open(filename, encoding='utf-8') as f:
for line in f:
sents.extend(pause_splitter(line))
df = parser.stats_raw_parse_sents(sents, arto=True)
df.to_csv(codecs.open('%s.csv' % filename, 'w', encoding='utf-8'), index=False)
print('Finished with %s.' % filename)
return True
def __init__(self, deptreeParser=None):
""""""
if deptreeParser is None:
sys.stderr.write('No deptreeParser provided, defaulting to PCFG\n')
deptreeParser = 'PCFG'
if isinstance(deptreeParser, compat.string_types):
deptreeParser = DependencyTreeParser(model_path='stanford-parser-full-%s/edu/stanford/nlp/models/lexparser/english%s.ser.gz' % (DATE, deptreeParser))
elif not isinstance(deptreeParser, DependencyTreeParser):
raise ValueError('Provided an invalid dependency tree parser')
self.deptreeParser = deptreeParser
def return_parser(dir_root):
model_path = 'Stanford Library/stanford-parser-full-%s/edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz' % DATE
fnfn = os.path.join(dir_root, model_path)
parser = DependencyTreeParser(model_path=fnfn)
parser = MetricalTreeParser(parser)
return parser