def __init__(self, note_path, overwrite=False):
print "processing file...", note_path
self.source_file = note_path
self.overwrite = overwrite
_Note = Note.__init__(self, note_path, note_path)
self.raw_text = []
self.text = []
self.relations = []
# read data, save text and relations
self.load_data()
print "data loaded"
# send body of document to NewsReader pipeline.
tokenized_text, token_to_offset, sentence_features, dependency_paths, id_to_tok = \
pre_processing.pre_process('\n'.join(self.text), note_path, overwrite=self.overwrite)
# chunks = self.split_text(200)
# for i, chunk in enumerate(chunks):
# tokenized_text, token_to_offset, sentence_features, dependency_paths, id_to_tok = \
# pre_processing.pre_process('\n'.join(self.text), note_path+str(i), overwrite=self.overwrite)
#
# self.pre_processed_text.update(tokenized_text)
# self.token_to_offset.update(token_to_offset)
# self.sentence_features.update(sentence_features)
# self.dependency_paths.update(dependency_paths)
# self.id_to_tok.update(id_to_tok)
# {sentence_num: [{token},...], ...}
self.pre_processed_text = tokenized_text
# contains the char based offsets generated by tokenizer, used for asserting char offsets are correct
# {'token':[(start, end),...],...}
self.token_to_offset = token_to_offset
# contains sentence level information extracted by newsreader
self.sentence_features = sentence_features
# dependency paths for sentences in the document
self.dependency_paths = dependency_paths
# map token ids to tokens within self.tokenized_text
# {'wid':'token'}
self.id_to_tok = id_to_tok
self.discourse_connectives = {}
self.iob_labels = []
self.semLinks = []
# get list of [{'entity_id': 10002, 'entity_label': 'Component-Whole(e2,e1)', 'entity_type': 'e2'}, ...]
self.get_labels()
"""
def __init__(self, string, fret, interval=c.INTVL_ROOT):
self.set_string(string)
self.set_fret(fret)
note = string.get_note_at_fret(fret)
Note.__init__(self, note.get_name(), note.get_accidental(), interval)
def __init__(self, timeml_note_path, annotated_timeml_path=None, verbose=False):
if verbose: print "called TimeNote constructor"
_Note = Note.__init__(self, timeml_note_path, annotated_timeml_path)
# get body of document
data = get_text(timeml_note_path)
# original text body of timeml doc
self.original_text = data
# send body of document to NewsReader pipeline.
tokenized_text, token_to_offset, sentence_features, dependency_paths, id_to_tok = pre_processing.pre_process(data, timeml_note_path)
# {sentence_num: [{token},...], ...}
self.pre_processed_text = tokenized_text
# contains the char based offsets generated by tokenizer, used for asserting char offsets are correct
# {'token':[(start, end),...],...}
self.token_to_offset = token_to_offset
# contains sentence level information extracted by newsreader
self.sentence_features = sentence_features
# dependency paths for sentences in the document
self.dependency_paths = dependency_paths
# map token ids to tokens within self.tokenized_text
# {'wid':'token'}
self.id_to_tok = id_to_tok
self.discourse_connectives = {}
self.iob_labels = []
"""
print "\n\nself.original_text:\n\n"
print self.original_text
print "\n\n"
print "self.pre_processed_text:\n\n"
print tokenized_text
print "\n\n"
print "self.token_to_offset:\n\n"
print self.token_to_offset
print "\n\n"
print "self.sentence_features:\n\n"
print self.sentence_features
print "\n\n"
"""
self.tlinks = []
if self.annotated_note_path is not None:
self.get_tlinked_entities()
# will store labels in self.iob_labels
self.get_labels()
