def markup(text_path, ann_path, html_path):
"""Markup text in file `text_path` with annotations in file `ann_path` as HTML and write to
file `html_path`
"""
text, ann = get_entities_from_brat(text_path, ann_path)
# print('&' * 80)
print(len(ann), text_path, html_path)
if not ann:
return
# for i, a in enumerate(ann[:5]):
# s = text[a['start']:a['end']]
# # print('%3d: %10s %s %s' % (i, a['type'], a['text'], s))
gaps = [text[a['end']:b['start']] for a, b in zip(ann[:-1], ann[1:])]
gaps = [text[:ann[0]['start']]] + gaps + [text[ann[-1]['end']:]]
gaps = [abridge(g) for g in gaps]
words = ['<b>%s</b> [%s] ' % (a['text'], a['type']) for a in ann]
# for i, (g, w) in enumerate(list(zip(gaps, words))[:5]):
# print('%3d: "%s" -- "%s"' % (i, g, w))
# print(text[:ann[5]['end']])
gw = [g + w for g, w in zip(gaps, words)]
gw.append(gaps[-1])
body = '<body>%s</body>' % ''.join(gw)
marked = '<html>%s</html>' % body
write_file(html_path, marked)
def predict(self, text):
assert False
self.prediction_count += 1
if self.prediction_count == 1:
self.parameters['dataset_text_folder'] = os.path.join('..', 'data', 'temp')
self.stats_graph_folder, _ = self._create_stats_graph_folder(self.parameters)
# Update the deploy folder, file, and dataset
dataset_type = 'deploy'
### Delete all deployment data
for filepath in glob.glob(os.path.join(self.parameters['dataset_text_folder'], '{0}*'.format(dataset_type))):
if os.path.isdir(filepath):
shutil.rmtree(filepath)
else:
os.remove(filepath)
### Create brat folder and file
dataset_brat_deploy_folder = os.path.join(self.parameters['dataset_text_folder'], dataset_type)
utils.create_folder_if_not_exists(dataset_brat_deploy_folder)
dataset_brat_deploy_filepath = os.path.join(dataset_brat_deploy_folder,
'temp_{0}.txt'.format(str(self.prediction_count).zfill(5)))
with codecs.open(dataset_brat_deploy_filepath, 'w', 'UTF-8') as f:
f.write(text)
### Update deploy filepaths
dataset_filepaths, dataset_brat_folders = self._get_valid_dataset_filepaths(self.parameters,
dataset_types=[dataset_type])
self.dataset_filepaths.update(dataset_filepaths)
self.dataset_brat_folders.update(dataset_brat_folders)
### Update the dataset for the new deploy set
self.dataset.update_dataset(self.dataset_filepaths, [dataset_type])
# Predict labels and output brat
output_filepaths = {}
prediction_output = train.prediction_step(self.sess, self.dataset, dataset_type, self.model,
self.transition_params_trained, self.stats_graph_folder, self.prediction_count,
self.parameters, self.dataset_filepaths)
_, _, output_filepaths[dataset_type] = prediction_output
conll_to_brat.output_brat(output_filepaths, self.dataset_brat_folders, self.stats_graph_folder,
overwrite=True)
# Print and output result
text_filepath = os.path.join(self.stats_graph_folder, 'brat', 'deploy',
os.path.basename(dataset_brat_deploy_filepath))
annotation_filepath = os.path.join(self.stats_graph_folder, 'brat', 'deploy',
'{0}.ann'.format(utils.get_basename_without_extension(dataset_brat_deploy_filepath)))
text2, entities = brat_to_conll.get_entities_from_brat(text_filepath, annotation_filepath,
verbose=True)
assert(text == text2)
return entities
