def test_extract_(self):
feature_accumulator = extract_features.make_feature_accumulator()
article = corenlp_xml_reader.AnnotatedText(
open('test/corenlp1.xml').read()
)
feature_accumulator.extract(article)
article = corenlp_xml_reader.AnnotatedText(
open('test/corenlp2.xml').read()
)
feature_accumulator.extract(article)
feature_accumulator.write('test/merged-extracted')
def corenlp(self):
if self.is_parc_or_annotator_training():
raise ArticleError(
'Sorry, no corenlp file available for annotator-training files '
'and parc3-replication files.\n\nTry this instead:\n\n'
'>>> polnear.data.train()[0].corenlp()')
return corenlp_xml_reader.AnnotatedText(
open(self.path('corenlp')).read())
def test_extract(self):
article = corenlp_xml_reader.AnnotatedText(
open('test/corenlp1.xml').read()
)
feature_accumulator = extract_features.make_feature_accumulator()
feature_accumulator.extract(article)
# Test that the features extracted are the ones expected
self.assert_feature_like_on_disc(feature_accumulator, 'test/extracted1')
def test_merge_load(self):
article = corenlp_xml_reader.AnnotatedText(
open('test/corenlp1.xml').read()
)
feature_accumulator = extract_features.make_feature_accumulator()
feature_accumulator.extract(article)
feature_accumulator.merge_load('test/extracted2')
self.assert_feature_like_on_disc(
feature_accumulator, 'test/merged-extracted')
def test_normalized(self):
feature_accumulator = extract_features.make_feature_accumulator()
article = corenlp_xml_reader.AnnotatedText(
open('test/corenlp1.xml').read()
)
feature_accumulator.extract(article)
normalized_features = {
token : feature_accumulator.get_features(token, ['dependency'])
for token in feature_accumulator.dictionary.get_token_list()
}
open('test/normalized1.json', 'w').write(
json.dumps(normalized_features)
)
def corenlp(self):
if self.is_parc_or_annotator_training():
raise ArticleError('No corenlp file available.')
return corenlp_xml_reader.AnnotatedText(
open(self.path('corenlp')).read())