You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2018/03/12 17:58:16 UTC
[GitHub] marcoabreu commented on a change in pull request #10074: Add vocabulary and embedding
marcoabreu commented on a change in pull request #10074: Add vocabulary and embedding
URL: https://github.com/apache/incubator-mxnet/pull/10074#discussion_r173891556
##########
File path: tests/python/unittest/test_text.py
##########
@@ -0,0 +1,675 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements. See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership. The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# 'License'); you may not use this file except in compliance
+# with the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# 'AS IS' BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied. See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+# coding: utf-8
+
+from __future__ import absolute_import
+from __future__ import print_function
+
+from collections import Counter
+
+from common import assertRaises
+from mxnet import ndarray as nd
+from mxnet.test_utils import *
+from mxnet import text
+
+
+def _get_test_str_of_tokens(token_delim, seq_delim):
+ seq1 = token_delim + token_delim.join(['Life', 'is', 'great', '!']) + token_delim + seq_delim
+ seq2 = token_delim + token_delim.join(['life', 'is', 'good', '.']) + token_delim + seq_delim
+ seq3 = token_delim + token_delim.join(['life', "isn't", 'bad', '.']) + token_delim + seq_delim
+ seqs = seq1 + seq2 + seq3
+ return seqs
+
+
+def _test_count_tokens_from_str_with_delims(token_delim, seq_delim):
+ source_str = _get_test_str_of_tokens(token_delim, seq_delim)
+
+ cnt1 = text.count_tokens_from_str(source_str, token_delim, seq_delim, to_lower=False)
+ assert cnt1 == Counter(
+ {'is': 2, 'life': 2, '.': 2, 'Life': 1, 'great': 1, '!': 1, 'good': 1, "isn't": 1,
+ 'bad': 1})
+
+ cnt2 = text.count_tokens_from_str(source_str, token_delim, seq_delim, to_lower=True)
+ assert cnt2 == Counter(
+ {'life': 3, 'is': 2, '.': 2, 'great': 1, '!': 1, 'good': 1, "isn't": 1, 'bad': 1})
+
+ counter_to_update = Counter({'life': 2})
+
+ cnt3 = text.utils.count_tokens_from_str(source_str, token_delim, seq_delim, to_lower=False,
+ counter_to_update=counter_to_update.copy())
+ assert cnt3 == Counter(
+ {'is': 2, 'life': 4, '.': 2, 'Life': 1, 'great': 1, '!': 1, 'good': 1, "isn't": 1,
+ 'bad': 1})
+
+ cnt4 = text.count_tokens_from_str(source_str, token_delim, seq_delim, to_lower=True,
+ counter_to_update=counter_to_update.copy())
+ assert cnt4 == Counter(
+ {'life': 5, 'is': 2, '.': 2, 'great': 1, '!': 1, 'good': 1, "isn't": 1, 'bad': 1})
+
+
+def test_count_tokens_from_str():
+ _test_count_tokens_from_str_with_delims(' ', '\n')
+ _test_count_tokens_from_str_with_delims('IS', 'LIFE')
+
+
+def test_vocabulary_getitem():
+ counter = Counter(['a', 'b', 'b', 'c', 'c', 'c', 'some_word$'])
+
+ vocab = text.Vocabulary(counter, max_size=None, min_freq=1, unknown_token='<unk>',
+ reserved_tokens=None)
+
+ i1 = vocab['c']
+ assert i1 == 1
+
+ i2 = vocab[['c']]
+ assert i2 == [1]
+
+ i3 = vocab[['<unk>', 'non-exist']]
+ assert i3 == [0, 0]
+
+ i4 = vocab[['a', 'non-exist', 'a', 'b']]
+ assert i4 == [3, 0, 3, 2]
+
+
+def test_vocabulary_to_tokens():
+ counter = Counter(['a', 'b', 'b', 'c', 'c', 'c', 'some_word$'])
+
+ vocab = text.Vocabulary(counter, max_size=None, min_freq=1,
+ unknown_token='<unknown>', reserved_tokens=None)
+ i1 = vocab.to_tokens(1)
+ assert i1 == 'c'
+
+ i2 = vocab.to_tokens([1])
+ assert i2 == ['c']
+
+ i3 = vocab.to_tokens([0, 0])
+ assert i3 == ['<unknown>', '<unknown>']
+
+ i4 = vocab.to_tokens([3, 0, 3, 2])
+ assert i4 == ['a', '<unknown>', 'a', 'b']
+
+ assertRaises(ValueError, vocab.to_tokens, 5)
+ assertRaises(ValueError, vocab.to_tokens, [5, 6])
+
+
+def test_vocabulary():
+ counter = Counter(['a', 'b', 'b', 'c', 'c', 'c', 'some_word$'])
+
+ v1 = text.Vocabulary(counter, max_size=None, min_freq=1, unknown_token='<unk>',
+ reserved_tokens=None)
+ assert len(v1) == 5
+ assert v1.token_to_idx == {'<unk>': 0, 'c': 1, 'b': 2, 'a': 3, 'some_word$': 4}
+ assert v1.idx_to_token[1] == 'c'
+ assert v1.unknown_token == '<unk>'
+ assert v1.reserved_tokens is None
+ assert v1.embedding is None
+ assert 'a' in v1
+ assert v1.unknown_token in v1
+
+ v2 = text.Vocabulary(counter, max_size=None, min_freq=2, unknown_token='<unk>',
+ reserved_tokens=None)
+ assert len(v2) == 3
+ assert v2.token_to_idx == {'<unk>': 0, 'c': 1, 'b': 2}
+ assert v2.idx_to_token[1] == 'c'
+ assert v2.unknown_token == '<unk>'
+ assert v2.reserved_tokens is None
+ assert v2.embedding is None
+ assert 'a' not in v2
+ assert v2.unknown_token in v2
+
+ v3 = text.Vocabulary(counter, max_size=None, min_freq=100, unknown_token='<unk>',
+ reserved_tokens=None)
+ assert len(v3) == 1
+ assert v3.token_to_idx == {'<unk>': 0}
+ assert v3.idx_to_token[0] == '<unk>'
+ assert v3.unknown_token == '<unk>'
+ assert v3.reserved_tokens is None
+ assert v3.embedding is None
+ assert 'a' not in v3
+
+ v4 = text.Vocabulary(counter, max_size=2, min_freq=1, unknown_token='<unk>',
+ reserved_tokens=None)
+ assert len(v4) == 3
+ assert v4.token_to_idx == {'<unk>': 0, 'c': 1, 'b': 2}
+ assert v4.idx_to_token[1] == 'c'
+ assert v4.unknown_token == '<unk>'
+ assert v4.reserved_tokens is None
+ assert v4.embedding is None
+ assert 'a' not in v4
+
+ v5 = text.Vocabulary(counter, max_size=3, min_freq=1, unknown_token='<unk>',
+ reserved_tokens=None)
+ assert len(v5) == 4
+ assert v5.token_to_idx == {'<unk>': 0, 'c': 1, 'b': 2, 'a': 3}
+ assert v5.idx_to_token[1] == 'c'
+ assert v5.unknown_token == '<unk>'
+ assert v5.reserved_tokens is None
+ assert v5.embedding is None
+ assert 'a' in v5
+
+ v6 = text.Vocabulary(counter, max_size=100, min_freq=1, unknown_token='<unk>',
+ reserved_tokens=None)
+ assert len(v6) == 5
+ assert v6.token_to_idx == {'<unk>': 0, 'c': 1, 'b': 2, 'a': 3,
+ 'some_word$': 4}
+ assert v6.idx_to_token[1] == 'c'
+ assert v6.unknown_token == '<unk>'
+ assert v6.reserved_tokens is None
+ assert v6.embedding is None
+ assert 'a' in v6
+
+ v7 = text.Vocabulary(counter, max_size=1, min_freq=2, unknown_token='<unk>',
+ reserved_tokens=None)
+ assert len(v7) == 2
+ assert v7.token_to_idx == {'<unk>': 0, 'c': 1}
+ assert v7.idx_to_token[1] == 'c'
+ assert v7.unknown_token == '<unk>'
+ assert v7.reserved_tokens is None
+ assert v7.embedding is None
+ assert 'a' not in v7
+
+ assertRaises(AssertionError, text.Vocabulary, counter, max_size=None,
+ min_freq=0, unknown_token='<unknown>', reserved_tokens=['b'])
+
+ assertRaises(AssertionError, text.Vocabulary, counter, max_size=None,
+ min_freq=1, unknown_token='<unknown>', reserved_tokens=['b', 'b'])
+
+ assertRaises(AssertionError, text.Vocabulary, counter, max_size=None,
+ min_freq=1, unknown_token='<unknown>', reserved_tokens=['b', '<unknown>'])
+
+ v8 = text.Vocabulary(counter, max_size=None, min_freq=1, unknown_token='<unknown>',
+ reserved_tokens=['b'])
+ assert len(v8) == 5
+ assert v8.token_to_idx == {'<unknown>': 0, 'b': 1, 'c': 2, 'a': 3, 'some_word$': 4}
+ assert v8.idx_to_token[1] == 'b'
+ assert v8.unknown_token == '<unknown>'
+ assert v8.reserved_tokens == ['b']
+ assert v8.embedding is None
+ assert 'a' in v8
+
+ v9 = text.Vocabulary(counter, max_size=None, min_freq=2, unknown_token='<unk>',
+ reserved_tokens=['b', 'a'])
+ assert len(v9) == 4
+ assert v9.token_to_idx == {'<unk>': 0, 'b': 1, 'a': 2, 'c': 3}
+ assert v9.idx_to_token[1] == 'b'
+ assert v9.unknown_token == '<unk>'
+ assert v9.reserved_tokens == ['b', 'a']
+ assert v9.embedding is None
+ assert 'a' in v9
+
+ v10 = text.Vocabulary(counter, max_size=None, min_freq=100, unknown_token='<unk>',
+ reserved_tokens=['b', 'c'])
+ assert len(v10) == 3
+ assert v10.token_to_idx == {'<unk>': 0, 'b': 1, 'c': 2}
+ assert v10.idx_to_token[1] == 'b'
+ assert v10.unknown_token == '<unk>'
+ assert v10.reserved_tokens == ['b', 'c']
+ assert v10.embedding is None
+ assert 'a' not in v10
+
+ v11 = text.Vocabulary(counter, max_size=1, min_freq=2, unknown_token='<unk>',
+ reserved_tokens=['<pad>', 'b'])
+ assert len(v11) == 4
+ assert v11.token_to_idx == {'<unk>': 0, '<pad>': 1, 'b': 2, 'c': 3}
+ assert v11.idx_to_token[1] == '<pad>'
+ assert v11.unknown_token == '<unk>'
+ assert v11.reserved_tokens == ['<pad>', 'b']
+ assert v11.embedding is None
+ assert 'a' not in v11
+
+ v12 = text.Vocabulary(counter, max_size=None, min_freq=2, unknown_token='b',
+ reserved_tokens=['<pad>'])
+ assert len(v12) == 3
+ assert v12.token_to_idx == {'b': 0, '<pad>': 1, 'c': 2}
+ assert v12.idx_to_token[1] == '<pad>'
+ assert v12.unknown_token == 'b'
+ assert v12.reserved_tokens == ['<pad>']
+ assert v12.embedding is None
+ assert 'a' not in v12
+
+ v13 = text.Vocabulary(counter, max_size=None, min_freq=2, unknown_token='a',
+ reserved_tokens=['<pad>'])
+ assert len(v13) == 4
+ assert v13.token_to_idx == {'a': 0, '<pad>': 1, 'c': 2, 'b': 3}
+ assert v13.idx_to_token[1] == '<pad>'
+ assert v13.unknown_token == 'a'
+ assert v13.reserved_tokens == ['<pad>']
+ assert v13.embedding is None
+ assert 'a' in v13
+
+ counter_tuple = Counter([('a', 'a'), ('b', 'b'), ('b', 'b'), ('c', 'c'), ('c', 'c'), ('c', 'c'),
+ ('some_word$', 'some_word$')])
+
+ v14 = text.Vocabulary(counter_tuple, max_size=None, min_freq=1,
+ unknown_token=('<unk>', '<unk>'), reserved_tokens=None)
+ assert len(v14) == 5
+ assert v14.token_to_idx == {('<unk>', '<unk>'): 0, ('c', 'c'): 1, ('b', 'b'): 2, ('a', 'a'): 3,
+ ('some_word$', 'some_word$'): 4}
+ assert v14.idx_to_token[1] == ('c', 'c')
+ assert v14.unknown_token == ('<unk>', '<unk>')
+ assert v14.reserved_tokens is None
+ assert v14.embedding is None
+ assert ('a', 'a') in v14
+ assert ('<unk>', '<unk>') in v14
+
+
+def _mk_my_pretrain_file(path, token_delim, pretrain_file):
+ path = os.path.expanduser(path)
+ if not os.path.exists(path):
+ os.makedirs(path)
+ seq1 = token_delim.join(['a', '0.1', '0.2', '0.3', '0.4', '0.5']) + '\n'
+ seq2 = token_delim.join(['b', '0.6', '0.7', '0.8', '0.9', '1.0']) + '\n'
+ seqs = seq1 + seq2
+ with open(os.path.join(path, pretrain_file), 'w') as fout:
+ fout.write(seqs)
+
+
+def _mk_my_pretrain_file2(path, token_delim, pretrain_file):
+ path = os.path.expanduser(path)
+ if not os.path.exists(path):
+ os.makedirs(path)
+ seq1 = token_delim.join(['a', '0.01', '0.02', '0.03', '0.04', '0.05']) + '\n'
+ seq2 = token_delim.join(['c', '0.06', '0.07', '0.08', '0.09', '0.1']) + '\n'
+ seqs = seq1 + seq2
+ with open(os.path.join(path, pretrain_file), 'w') as fout:
+ fout.write(seqs)
+
+
+def _mk_my_pretrain_file3(path, token_delim, pretrain_file):
+ path = os.path.expanduser(path)
+ if not os.path.exists(path):
+ os.makedirs(path)
+ seq1 = token_delim.join(['a', '0.1', '0.2', '0.3', '0.4', '0.5']) + '\n'
+ seq2 = token_delim.join(['b', '0.6', '0.7', '0.8', '0.9', '1.0']) + '\n'
+ seq3 = token_delim.join(['<unk1>', '1.1', '1.2', '1.3', '1.4',
+ '1.5']) + '\n'
+ seqs = seq1 + seq2 + seq3
+ with open(os.path.join(path, pretrain_file), 'w') as fout:
+ fout.write(seqs)
+
+
+def _mk_my_pretrain_file4(path, token_delim, pretrain_file):
+ path = os.path.expanduser(path)
+ if not os.path.exists(path):
+ os.makedirs(path)
+ seq1 = token_delim.join(['a', '0.01', '0.02', '0.03', '0.04', '0.05']) + '\n'
+ seq2 = token_delim.join(['c', '0.06', '0.07', '0.08', '0.09', '0.1']) + '\n'
+ seq3 = token_delim.join(['<unk2>', '0.11', '0.12', '0.13', '0.14', '0.15']) + '\n'
+ seqs = seq1 + seq2 + seq3
+ with open(os.path.join(path, pretrain_file), 'w') as fout:
+ fout.write(seqs)
+
+
+def _mk_my_invalid_pretrain_file(path, token_delim, pretrain_file):
+ path = os.path.expanduser(path)
+ if not os.path.exists(path):
+ os.makedirs(path)
+ seq1 = token_delim.join(['a', '0.1', '0.2', '0.3', '0.4', '0.5']) + '\n'
+ seq2 = token_delim.join(['b', '0.6', '0.7', '0.8', '0.9', '1.0']) + '\n'
+ seq3 = token_delim.join(['c']) + '\n'
+ seqs = seq1 + seq2 + seq3
+ with open(os.path.join(path, pretrain_file), 'w') as fout:
+ fout.write(seqs)
+
+
+def _mk_my_invalid_pretrain_file2(path, token_delim, pretrain_file):
+ path = os.path.expanduser(path)
+ if not os.path.exists(path):
+ os.makedirs(path)
+ seq1 = token_delim.join(['a', '0.1', '0.2', '0.3', '0.4', '0.5']) + '\n'
+ seq2 = token_delim.join(['b', '0.6', '0.7', '0.8', '0.9', '1.0']) + '\n'
+ seq3 = token_delim.join(['c', '0.6', '0.7', '0.8']) + '\n'
+ seqs = seq1 + seq2 + seq3
+ with open(os.path.join(path, pretrain_file), 'w') as fout:
+ fout.write(seqs)
+
+
+def test_token_embedding_from_file():
+ embed_root = 'embedding'
Review comment:
Please use a tempfile instead
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services