def predict_text(self, text):
input_text = InputText(text)
for token in input_text.gold_tokens:
if not token.is_punctuation():
token.word_vec = self.word2vec.get_vector(token.word.lower())
slidingWindow = SlidingWindow()
instances = slidingWindow.list_windows(input_text)
punctuations = []
for instance in instances:
probs = self.predict_caffe(instance)
#print instance
#self.show_probs(probs)
punctuations.append(numpy.argmax(probs))
#print punctuations
print(">>> Sentence with boundaries:")
for i in range(len(punctuations) - 1, -1, -1):
input_text.gold_tokens.insert(i + PUNCTUATION_POS, classes_as_string[punctuations[i]])
print "{",
for t in input_text.gold_tokens:
print t,
print "}"
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()
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()
def predict(self, input_audio):
sliding_window = SlidingWindow()
instances = sliding_window.list_windows(input_audio)
# get caffe predictions
punctuation_probs = []
for instance in instances:
probs = self._predict_caffe(instance)
punctuation_probs.extend(numpy.copy(probs))
return punctuation_probs
def predict(self, input_text):
for token in input_text.tokens:
if not token.is_punctuation():
if not self.word2vec:
token.word_vec = numpy.random.rand(300)
else:
token.word_vec = self.word2vec.get_vector(token.word.lower())
sliding_window = SlidingWindow()
instances = sliding_window.list_windows(input_text)
# get caffe predictions
punctuation_probs = []
for instance in instances:
probs = self._predict_caffe(instance)
punctuation_probs.extend(numpy.copy(probs))
return punctuation_probs
def predict(self, input_text):
for token in input_text.tokens:
if not token.is_punctuation():
if not self.word2vec:
token.word_vec = numpy.random.rand(300)
else:
token.word_vec = self.word2vec.get_vector(
token.word.lower())
sliding_window = SlidingWindow()
instances = sliding_window.list_windows(input_text)
# get caffe predictions
punctuation_probs = []
for instance in instances:
probs = self._predict_caffe(instance)
punctuation_probs.extend(numpy.copy(probs))
return punctuation_probs
def generate(self, parsers, database, is_test):
level_db = LevelDBCreator(database)
window_slider = SlidingWindow()
# count how often each type (COMMA, PERIOD etc.) is in the instances
class_distribution = dict()
nr_instances = 0
nr_instances_used = 0
label_nr = len(Punctuation)
if not self.USE_QUESTION_MARK:
label_nr -= 1
perfect_distribution = 1.0 / label_nr
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, text_parser in enumerate(parsers):
texts = text_parser.parse()
prev_progress = 0
print("")
print("Processing file %s ..." % text_parser.get_file_name())
foo = open("lineparsing", "w")
for text in texts:
progress = int(text_parser.progress() * 100)
if progress > prev_progress:
sys.stdout.write(str(progress) + "% ")
sys.stdout.flush()
prev_progress = progress
for sentence in text.sentences:
tokens = sentence.get_tokens()
# get the word vectors for all tokens in the sentence
for i in range(len(tokens)):
token = tokens[i]
if not token.is_punctuation():
if i == len(tokens) - 1:
punctuation_string = "PERIOD"
else:
next_token = tokens[i + 1]
if next_token.is_punctuation():
punctuation_string = str(next_token.punctuation_type)
punctuation_string = punctuation_string[12:]
else:
punctuation_string = "O"
foo.write(token.word.lower() + "\t" + punctuation_string + "\n")
token.word_vec = self.word2vec.get_vector(token.word.lower())
# get the training instances
training_instances = window_slider.list_windows(text)
# write training instances to level db
for training_instance in training_instances:
nr_instances += 1
class_variation = (class_distribution.get(training_instance.label, 0) / float(max(nr_instances_used, 1))) - perfect_distribution
if is_test or (not self.CLASS_DISTRIBUTION_NORMALIZATION) or (class_variation <= self.CLASS_DISTRIBUTION_VARIATION):
# write instance to file
s = unicode(training_instance) + "\n"
s += "\n"
plain_text_instances_file.write(s.encode('utf8'))
# adapt class distribution
nr_instances_used += 1
class_distribution[training_instance.label] = class_distribution.get(training_instance.label, 0) + 1
# write to level db
level_db.write_training_instance(training_instance)
foo.close()
plain_text_instances_file.close()
print("")
print("Originally " + str(nr_instances) + " instances.")
print("Created " + str(nr_instances_used) + " instances." )
print("Class distribution:")
print(class_distribution)