explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 09:26:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix Vectors.n_keys for floret vectors (#10394)

Browse Source 
Fix `Vectors.n_keys` for floret vectors to match docstring description
and avoid W007 warnings in similarity methods.
This commit is contained in:
Adriane Boyd 2022-03-01 09:21:25 +01:00 committed by GitHub
parent 3f68bbcfec
commit 8e93fa8507
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 11 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/tests/vocab_vectors/test_vectors.py
View File

@ -535,6 +535,10 @@ def test_floret_vectors(floret_vectors_vec_str, floret_vectors_hashvec_str):
# every word has a vector # every word has a vector
assert nlp.vocab[word * 5].has_vector assert nlp.vocab[word * 5].has_vector
# n_keys is -1 for floret
assert nlp_plain.vocab.vectors.n_keys > 0
assert nlp.vocab.vectors.n_keys == -1
# check that single and batched vector lookups are identical # check that single and batched vector lookups are identical
words = [s for s in nlp_plain.vocab.vectors] words = [s for s in nlp_plain.vocab.vectors]
single_vecs = OPS.to_numpy(OPS.asarray([nlp.vocab[word].vector for word in words])) single_vecs = OPS.to_numpy(OPS.asarray([nlp.vocab[word].vector for word in words]))

2
spacy/vectors.pyx
View File

@ -170,6 +170,8 @@ cdef class Vectors:
DOCS: https://spacy.io/api/vectors#n_keys DOCS: https://spacy.io/api/vectors#n_keys
""" """
if self.mode == Mode.floret:
return -1
return len(self.key2row) return len(self.key2row)
def __reduce__(self): def __reduce__(self):

8
website/docs/api/vectors.md
View File

@ -328,8 +328,8 @@ will be counted individually. In `floret` mode, the keys table is not used.
> ``` > ```
| Name | Description | | Name | Description |
| ----------- | -------------------------------------------- | | ----------- | ----------------------------------------------------------------------------- |
| **RETURNS** | The number of all keys in the table. ~~int~~ | | **RETURNS** | The number of all keys in the table. Returns `-1` for floret vectors. ~~int~~ |
## Vectors.most_similar {#most_similar tag="method"} ## Vectors.most_similar {#most_similar tag="method"}
@ -348,7 +348,7 @@ supported for `floret` mode.
> ``` > ```
| Name | Description | | Name | Description |
| -------------- | --------------------------------------------------------------------------- | | -------------- | --------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
| `queries` | An array with one or more vectors. ~~numpy.ndarray~~ | | `queries` | An array with one or more vectors. ~~numpy.ndarray~~ |
| _keyword-only_ | | | _keyword-only_ | |
| `batch_size` | The batch size to use. Default to `1024`. ~~int~~ | | `batch_size` | The batch size to use. Default to `1024`. ~~int~~ |
@ -385,7 +385,7 @@ Change the embedding matrix to use different Thinc ops.
> ``` > ```
| Name | Description | | Name | Description |
|-------|----------------------------------------------------------| | ----- | -------------------------------------------------------- |
| `ops` | The Thinc ops to switch the embedding matrix to. ~~Ops~~ | | `ops` | The Thinc ops to switch the embedding matrix to. ~~Ops~~ |
## Vectors.to_disk {#to_disk tag="method"} ## Vectors.to_disk {#to_disk tag="method"}