def process_training_fragments(self):
"""Retrieve the TRAINING XmlDocument and hand it to the feature extracter for processing.
Features file will be used for training"""
os.chdir(self.DIR_CLASSIFIER)
perl = self.tarsqi_instance.getopt_perl()
fragment_count = 0
for fragment in self.fragments:
base = fragment[0]
fragment_count += 1
fin = os.path.join(self.DIR_DATA,
base + '.' + self.CREATION_EXTENSION)
ee_vectors = fin + '.EE'
et_vectors = fin + '.ET'
# tt_vectors = fin + '.TT'
ee_train_vectors = fin + '.train.EE'
et_train_vectors = fin + '.train.ET'
# tt_train_vectors = fin + '.train.TT'
fragment_doc = Parser().parse_file(open(fin, "r"))
fragment_doc.set_dct_timex(self.document.get_dct())
# vectors.create_vectors(fragment_doc, ee_vectors, et_vectors, tt_vectors)
# vectors.create_vectors(fragment_doc, ee_vectors, et_vectors)
"""
Without narrative scheme
"""
dictionary_file = os.path.join(self.DICT_DATA,
'feature_index.dict')
"""
With narrative scheme
"""
# dictionary_file = os.path.join( self.DICT_DATA,
# 'feature_index_with_narrative_scheme.dict' )
feature_index_dict = Feature_Index_Dict()
feature_index_dict.load_from_file(dictionary_file)
"""
Without narrative scheme
"""
tree_vectors.create_vectors(fragment_doc,
self.auxillary[PARSED_DOCUMENT],
feature_index_dict, ee_vectors,
et_vectors)
"""
With narrative scheme
"""
# tree_vectors_with_narrative.create_vectors(fragment_doc, self.auxillary[PARSED_DOCUMENT],
# feature_index_dict, ee_vectors, et_vectors)
feature_index_dict.dump_to_file(dictionary_file)
print 'done create vectors'
# feature_recollect( self.document, ee_vectors, et_vectors, tt_vectors,
# ee_train_vectors, et_train_vectors, tt_train_vectors)
feature_recollect(self.document, ee_vectors, et_vectors,
ee_train_vectors, et_train_vectors)
print 'done collect training label and features'
print '======================================================'
