def __init__(self,
extractors,
iob_directories=[],
iob_file=None,
label_index=-1):
"""
Args:
extractors:
the list of canonical citation extractors to evaluate
iob_test_file:
the file in IOB format to be used for testing and evaluating the extactors
"""
# read the test instances from a list of directories containing the test data
import logging
self.logger = logging.getLogger("CREX.SIMPLEVAL")
if (iob_file is None):
self.logger.debug(iob_directories)
data = []
for directory in iob_directories:
data += IO.read_iob_files(directory, ".txt")
self.test_instances = data
else:
self.test_instances = IO.file_to_instances(iob_file)
self.logger.debug("Found %i instances for test" %
len(self.test_instances))
self.extractors = extractors
self.output = {}
self.error_matrix = None
self.label_index = label_index
return
def __init__(self,extractors,iob_directories=[],iob_file=None,label_index=-1):
"""
Args:
extractors:
the list of canonical citation extractors to evaluate
iob_test_file:
the file in IOB format to be used for testing and evaluating the extactors
"""
# read the test instances from a list of directories containing the test data
import logging
self.logger = logging.getLogger("CREX.SIMPLEVAL")
if(iob_file is None):
self.logger.debug(iob_directories)
data = []
for directory in iob_directories:
data += IO.read_iob_files(directory,".txt")
self.test_instances = data
else:
self.test_instances = IO.file_to_instances(iob_file)
self.logger.debug("Found %i instances for test"%len(self.test_instances))
self.extractors = extractors
self.output = {}
self.error_matrix = None
self.label_index = label_index
return
def get_extractor(settings):
"""
Instantiate, train and return a Citation_Extractor.
"""
import sys
import citation_extractor as citation_extractor_module
from citation_extractor.core import citation_extractor
from citation_extractor.Utils import IO
ce = None
try:
logger.info("Using CitationExtractor v. %s" %
citation_extractor_module.__version__)
train_instances = []
for directory in settings.DATA_DIRS:
train_instances += IO.read_iob_files(directory, extension=".txt")
logger.info(
"Training data: found %i directories containing %i sentences and %i tokens"
% (len(settings.DATA_DIRS), len(train_instances),
IO.count_tokens(train_instances)))
if (settings.CLASSIFIER is None):
ce = citation_extractor(settings)
else:
ce = citation_extractor(settings, settings.CLASSIFIER)
except Exception, e:
print e
def get_extractor(settings):
"""
Instantiate, train and return a Citation_Extractor.
"""
import sys
import citation_extractor as citation_extractor_module
from citation_extractor.core import citation_extractor
from citation_extractor.eval import IO
ce = None
try:
logger.info("Using CitationExtractor v. %s"%citation_extractor_module.__version__)
train_instances = []
for directory in settings.DATA_DIRS:
train_instances += IO.read_iob_files(directory,extension=".txt")
logger.info("Training data: found %i directories containing %i sentences and %i tokens"%(len(settings.DATA_DIRS),len(train_instances),IO.count_tokens(train_instances)))
ce = citation_extractor(settings)
except Exception, e:
print e
def read_instances(directories):
result = []
for d in directories:
result += IO.read_iob_files(d)
return result
def read_instances(directories):
result = []
for d in directories:
result += IO.read_iob_files(d)
return result