def generate(self, parsers, database, is_test):
level_db = LevelDBCreator(database)
window_slider = SlidingWindow()
nr_instances = 0
if is_test:
plain_text_instances_file = open(
database + "/../test_instances.txt", "w")
else:
plain_text_instances_file = open(
database + "/../train_instances.txt", "w")
for i, talk_parser in enumerate(parsers):
talks = talk_parser.parse()
prev_progress = 0
print("")
print("Processing file %s ..." % talk_parser.get_file_name())
for talk in talks:
progress = int(talk_parser.progress() * 100)
if progress > prev_progress:
sys.stdout.write(str(progress) + "% ")
sys.stdout.flush()
prev_progress = progress
talk.build_interval_tree()
base_dir = os.path.dirname(talk_parser.get_file_name())
# get pitch feature values
pitch_level_file = base_dir + "/" + talk.group_name + "_talkid" + str(
talk.talk_id) + ".pitch"
talk.parse_pitch_feature(pitch_level_file)
# get energy feature values
energy_level_file = base_dir + "/" + talk.group_name + "_talkid" + str(
talk.talk_id) + ".energy"
talk.parse_energy_feature(energy_level_file)
# normalize features
talk.normalize()
# get the training instances
training_instances = window_slider.list_windows(talk)
# write training instances to level db
for training_instance in training_instances:
nr_instances += 1
# write instance to file
s = unicode(training_instance) + "\n"
s += "\n"
plain_text_instances_file.write(s.encode('utf8'))
# write to level db
level_db.write_training_instance(training_instance)
plain_text_instances_file.close()
