def test_corpus_token_counts_split_with_max_lines(self):
token_counts = tokenizer.corpus_token_counts(self.corpus_path,
corpus_max_lines=5,
split_on_newlines=True)
self.assertIn(u"slept", token_counts)
self.assertNotIn(u"Mitch", token_counts)
def test_corpus_token_counts_no_split_with_max_lines(self):
token_counts = tokenizer.corpus_token_counts(
self.corpus_path, corpus_max_lines=5, split_on_newlines=False)
self.assertIn(u"slept", token_counts)
self.assertNotIn(u"Mitch", token_counts)
self.assertDictContainsSubset({
u".\n\n": 1,
u"\n": 2,
u".\n": 1
}, token_counts)
def test_corpus_token_counts_no_split_with_max_lines(self):
token_counts = tokenizer.corpus_token_counts(
self.corpus_path, corpus_max_lines=5, split_on_newlines=False)
self.assertIn(u"slept", token_counts)
self.assertNotIn(u"Mitch", token_counts)
self.assertDictContainsSubset({
u".\n\n": 1,
u"\n": 2,
u".\n": 1
}, token_counts)
def main(unused_argv):
gs = text_encoder.SubwordTextEncoder()
if not FLAGS.corpus_filepattern:
raise ValueError('Must provide --corpus_filepattern')
token_counts = tokenizer.corpus_token_counts(
FLAGS.corpus_filepattern,
FLAGS.corpus_max_lines,
split_on_newlines=FLAGS.split_on_newlines)
gs.build_from_token_counts(token_counts, FLAGS.min_count,
FLAGS.num_iterations)
gs.store_to_file(FLAGS.output_fn)
def _get_or_generate_vocab(tmp_dir, vocab_filename, vocab_size):
"""Read or create vocabulary."""
vocab_filepath = os.path.join(tmp_dir, vocab_filename)
print('Vocab file written to: ' + vocab_filepath)
if tf.gfile.Exists(vocab_filepath):
gs = text_encoder.SubwordTextEncoder(vocab_filepath)
return gs
example_file = os.path.join(tmp_dir, _EXAMPLES_FILE)
gs = text_encoder.SubwordTextEncoder()
token_counts = tokenizer.corpus_token_counts(
example_file, corpus_max_lines=1000000)
gs = gs.build_to_target_size(
vocab_size, token_counts, min_val=1, max_val=1e3)
gs.store_to_file(vocab_filepath)
return gs
def _get_or_generate_vocab(tmp_dir, vocab_filename, vocab_size):
"""Read or create vocabulary."""
vocab_filepath = os.path.join(tmp_dir, vocab_filename)
print('Vocab file written to: ' + vocab_filepath)
if tf.gfile.Exists(vocab_filepath):
gs = text_encoder.SubwordTextEncoder(vocab_filepath)
return gs
example_file = os.path.join(tmp_dir, _EXAMPLES_FILE)
gs = text_encoder.SubwordTextEncoder()
token_counts = tokenizer.corpus_token_counts(
example_file, corpus_max_lines=1000000)
gs = gs.build_to_target_size(
vocab_size, token_counts, min_val=1, max_val=1e3)
gs.store_to_file(vocab_filepath)
return gs
def test_corpus_token_counts_split_on_newlines(self):
token_counts = tokenizer.corpus_token_counts(
self.corpus_path, corpus_max_lines=0, split_on_newlines=True)
expected = {
u"'": 2,
u".": 2,
u". ": 1,
u"... ": 1,
u"Groucho": 1,
u"Marx": 1,
u"Mitch": 1,
u"Hedberg": 1,
u"I": 3,
u"in": 2,
u"my": 2,
u"pajamas": 2,
}
self.assertDictContainsSubset(expected, token_counts)
self.assertNotIn(u".\n\n", token_counts)
self.assertNotIn(u"\n", token_counts)
def test_corpus_token_counts_split_on_newlines(self):
token_counts = tokenizer.corpus_token_counts(
self.corpus_path, corpus_max_lines=0, split_on_newlines=True)
expected = {
u"'": 2,
u".": 2,
u". ": 1,
u"... ": 1,
u"Groucho": 1,
u"Marx": 1,
u"Mitch": 1,
u"Hedberg": 1,
u"I": 3,
u"in": 2,
u"my": 2,
u"pajamas": 2,
}
self.assertDictContainsSubset(expected, token_counts)
self.assertNotIn(u".\n\n", token_counts)
self.assertNotIn(u"\n", token_counts)
def main(unused_argv):
if FLAGS.corpus_filepattern and FLAGS.vocab_filepattern:
raise ValueError(
'Must only provide one of --corpus_filepattern or --vocab_filepattern')
elif FLAGS.corpus_filepattern:
token_counts = tokenizer.corpus_token_counts(
FLAGS.corpus_filepattern,
FLAGS.corpus_max_lines,
split_on_newlines=FLAGS.split_on_newlines)
elif FLAGS.vocab_filepattern:
token_counts = tokenizer.vocab_token_counts(FLAGS.vocab_filepattern,
FLAGS.corpus_max_lines)
else:
raise ValueError(
'Must provide one of --corpus_filepattern or --vocab_filepattern')
encoder = text_encoder.SubwordTextEncoder()
encoder.build_from_token_counts(token_counts, FLAGS.min_count,
FLAGS.num_iterations)
encoder.store_to_file(FLAGS.output_filename)
def main(unused_argv):
if FLAGS.corpus_filepattern and FLAGS.vocab_filepattern:
raise ValueError(
'Must only provide one of --corpus_filepattern or --vocab_filepattern')
elif FLAGS.corpus_filepattern:
token_counts = tokenizer.corpus_token_counts(
FLAGS.corpus_filepattern,
FLAGS.corpus_max_lines,
split_on_newlines=FLAGS.split_on_newlines)
elif FLAGS.vocab_filepattern:
token_counts = tokenizer.vocab_token_counts(FLAGS.vocab_filepattern,
FLAGS.corpus_max_lines)
else:
raise ValueError(
'Must provide one of --corpus_filepattern or --vocab_filepattern')
encoder = text_encoder.SubwordTextEncoder()
encoder.build_from_token_counts(token_counts, FLAGS.min_count,
FLAGS.num_iterations)
encoder.store_to_file(FLAGS.output_filename)
def test_corpus_token_counts_no_split_on_newlines(self):
token_counts = tokenizer.corpus_token_counts(self.corpus_path,
corpus_max_lines=0,
split_on_newlines=False)
self.assertDictContainsSubset({u".\n\n": 2, u"\n": 3}, token_counts)
def test_corpus_token_counts_split_with_max_lines(self):
token_counts = tokenizer.corpus_token_counts(
self.corpus_path, corpus_max_lines=5, split_on_newlines=True)
self.assertIn(u"slept", token_counts)
self.assertNotIn(u"Mitch", token_counts)
def test_corpus_token_counts_no_split_on_newlines(self):
token_counts = tokenizer.corpus_token_counts(
self.corpus_path, corpus_max_lines=0, split_on_newlines=False)
self.assertDictContainsSubset({u".\n\n": 2, u"\n": 3}, token_counts)
