Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Save nesting_field.vocab.freqs #403

Merged
merged 7 commits into from
Sep 24, 2018
Merged

Save nesting_field.vocab.freqs #403

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
90df0e8
Save nested.vocab.freq
nzw0301 Sep 21, 2018
6f0b3fa
Add tests for freqs attribute in NestedFiled
nzw0301 Sep 24, 2018
0697751
Merge branch 'master' of github.com:pytorch/text
nzw0301 Sep 24, 2018
a77ec87
Break lines
nzw0301 Sep 24, 2018
69ac69f
Use variable for pep 8
nzw0301 Sep 24, 2018
50566e6
Merge branch 'master' into master
mttk Sep 24, 2018
ad8459e
Merge branch 'master' into master
mttk Sep 24, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions test/data/test_field.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -514,6 +514,9 @@ def test_build_vocab_from_dataset(self):
for c in expected:
assert c in CHARS.vocab.stoi

expected_freqs = Counter({"a": 6, "b": 6, "c": 1})
assert CHARS.vocab.freqs == CHARS.nesting_field.vocab.freqs == expected_freqs

def test_build_vocab_from_iterable(self):
nesting_field = data.Field(unk_token="<cunk>", pad_token="<cpad>")
CHARS = data.NestedField(nesting_field)
Expand All @@ -527,6 +530,9 @@ def test_build_vocab_from_iterable(self):
for c in expected:
assert c in CHARS.vocab.stoi

expected_freqs = Counter({"a": 6, "b": 12, "c": 4})
assert CHARS.vocab.freqs == CHARS.nesting_field.vocab.freqs == expected_freqs

def test_pad(self):
nesting_field = data.Field(tokenize=list, unk_token="<cunk>", pad_token="<cpad>",
init_token="<w>", eos_token="</w>")
Expand Down
1 change: 1 addition & 0 deletions torchtext/data/field.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -644,6 +644,7 @@ def build_vocab(self, *args, **kwargs):
self.nesting_field.build_vocab(*flattened, **kwargs)
super(NestedField, self).build_vocab()
self.vocab.extend(self.nesting_field.vocab)
self.vocab.freqs = self.nesting_field.vocab.freqs.copy()
if old_vectors is not None:
self.vocab.load_vectors(old_vectors,
unk_init=old_unk_init, cache=old_vectors_cache)
Expand Down