Skip to content

fix(document): fix feature hash mixin #85

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

Merged
hanxiao merged 1 commit into from
Jan 27, 2022
Merged

fix(document): fix feature hash mixin #85

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
36 changes: 19 additions & 17 deletions docarray/document/mixins/featurehash.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,22 +64,24 @@ def _hash_column(col_name, col_val, n_dim, max_value, idxs, data, table):


def _any_hash(v):
try:
return int(v) # parse int parameter
except ValueError:
if not v:
# ignore it when the parameter is empty
return 0
elif isinstance(v, (tuple, dict, list, str)):
if isinstance(v, str):
v = v.strip()
if v.lower() in {'true', 'yes'}: # parse boolean parameter
return 1
if v.lower() in {'false', 'no'}:
return 0
else:
v = json.dumps(v, sort_keys=True)
return int(hashlib.md5(str(v).encode('utf-8')).hexdigest(), base=16)
else:
try:
return float(v) # parse float parameter
return int(v) # parse int parameter
except ValueError:
if not v:
# ignore it when the parameter is empty
return 0
if isinstance(v, str):
v = v.strip()
if v.lower() in {'true', 'yes'}: # parse boolean parameter
return 1
if v.lower() in {'false', 'no'}:
return 0
if isinstance(v, (tuple, dict, list)):
v = json.dumps(v, sort_keys=True)

return int(hashlib.md5(str(v).encode('utf-8')).hexdigest(), base=16)
try:
return float(v) # parse float parameter
except ValueError:
return 0 # unable to hash
13 changes: 10 additions & 3 deletions tests/unit/document/test_feature_hashing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,10 +8,17 @@
@pytest.mark.parametrize('sparse', [True, False])
@pytest.mark.parametrize('metric', ['jaccard', 'cosine'])
def test_feature_hashing(n_dim, sparse, metric):
da = DocumentArray.empty(3)
da.texts = ['hello world', 'world, bye', 'hello bye']
da = DocumentArray.empty(6)
da.texts = [
'hello world',
'world, bye',
'hello bye',
'infinity test',
'nan test',
'2.3 test',
]
da.apply(lambda d: d.embed_feature_hashing(n_dim=n_dim, sparse=sparse))
assert da.embeddings.shape == (3, n_dim)
assert da.embeddings.shape == (6, n_dim)
da.embeddings = to_numpy_array(da.embeddings)
da.match(da, metric=metric, use_scipy=True)
result = da['@m', ('id', f'scores__{metric}__value')]
Expand Down