spaCy/spacy/tests/pipeline/test_lemmatizer.py
Adriane Boyd e962784531
Add Lemmatizer and simplify related components (#5848)
* Add Lemmatizer and simplify related components

* Add `Lemmatizer` pipe with `lookup` and `rule` modes using the
`Lookups` tables.
* Reduce `Tagger` to a simple tagger that sets `Token.tag` (no pos or lemma)
* Reduce `Morphology` to only keep track of morph tags (no tag map, lemmatizer,
or morph rules)
* Remove lemmatizer from `Vocab`
* Adjust many many tests

Differences:

* No default lookup lemmas
* No special treatment of TAG in `from_array` and similar required
* Easier to modify labels in a `Tagger`
* No extra strings added from morphology / tag map

* Fix test

* Initial fix for Lemmatizer config/serialization

* Adjust init test to be more generic

* Adjust init test to force empty Lookups

* Add simple cache to rule-based lemmatizer

* Convert language-specific lemmatizers

Convert language-specific lemmatizers to component lemmatizers. Remove
previous lemmatizer class.

* Fix French and Polish lemmatizers

* Remove outdated UPOS conversions

* Update Russian lemmatizer init in tests

* Add minimal init/run tests for custom lemmatizers

* Add option to overwrite existing lemmas

* Update mode setting, lookup loading, and caching

* Make `mode` an immutable property
* Only enforce strict `load_lookups` for known supported modes
* Move caching into individual `_lemmatize` methods

* Implement strict when lang is not found in lookups

* Fix tables/lookups in make_lemmatizer

* Reallow provided lookups and allow for stricter checks

* Add lookups asset to all Lemmatizer pipe tests

* Rename lookups in lemmatizer init test

* Clean up merge

* Refactor lookup table loading

* Add helper from `load_lemmatizer_lookups` that loads required and
optional lookups tables based on settings provided by a config.

Additional slight refactor of lookups:

* Add `Lookups.set_table` to set a table from a provided `Table`
* Reorder class definitions to be able to specify type as `Table`

* Move registry assets into test methods

* Refactor lookups tables config

Use class methods within `Lemmatizer` to provide the config for
particular modes and to load the lookups from a config.

* Add pipe and score to lemmatizer

* Simplify Tagger.score

* Add missing import

* Clean up imports and auto-format

* Remove unused kwarg

* Tidy up and auto-format

* Update docstrings for Lemmatizer

Update docstrings for Lemmatizer.

Additionally modify `is_base_form` API to take `Token` instead of
individual features.

* Update docstrings

* Remove tag map values from Tagger.add_label

* Update API docs

* Fix relative link in Lemmatizer API docs
2020-08-07 15:27:13 +02:00

110 lines
3.4 KiB
Python

import pytest
from spacy import util, registry
from spacy.lang.en import English
from spacy.lookups import Lookups, load_lookups
from ..util import make_tempdir
@pytest.fixture
def nlp():
return English()
@pytest.fixture
def lemmatizer(nlp):
@registry.assets("cope_lookups")
def cope_lookups():
lookups = Lookups()
lookups.add_table("lemma_lookup", {"cope": "cope"})
lookups.add_table("lemma_index", {"verb": ("cope", "cop")})
lookups.add_table("lemma_exc", {"verb": {"coping": ("cope",)}})
lookups.add_table("lemma_rules", {"verb": [["ing", ""]]})
return lookups
lemmatizer = nlp.add_pipe(
"lemmatizer", config={"mode": "rule", "lookups": {"@assets": "cope_lookups"}}
)
return lemmatizer
def test_lemmatizer_init(nlp):
@registry.assets("cope_lookups")
def cope_lookups():
lookups = Lookups()
lookups.add_table("lemma_lookup", {"cope": "cope"})
lookups.add_table("lemma_index", {"verb": ("cope", "cop")})
lookups.add_table("lemma_exc", {"verb": {"coping": ("cope",)}})
lookups.add_table("lemma_rules", {"verb": [["ing", ""]]})
return lookups
lemmatizer = nlp.add_pipe(
"lemmatizer", config={"mode": "lookup", "lookups": {"@assets": "cope_lookups"}}
)
assert isinstance(lemmatizer.lookups, Lookups)
assert lemmatizer.mode == "lookup"
# replace any tables from spacy-lookups-data
lemmatizer.lookups = Lookups()
doc = nlp("coping")
# lookup with no tables sets text as lemma
assert doc[0].lemma_ == "coping"
nlp.remove_pipe("lemmatizer")
@registry.assets("empty_lookups")
def empty_lookups():
return Lookups()
with pytest.raises(ValueError):
nlp.add_pipe(
"lemmatizer",
config={"mode": "lookup", "lookups": {"@assets": "empty_lookups"}},
)
def test_lemmatizer_config(nlp, lemmatizer):
doc = nlp.make_doc("coping")
doc[0].pos_ = "VERB"
assert doc[0].lemma_ == ""
doc = lemmatizer(doc)
assert doc[0].text == "coping"
assert doc[0].lemma_ == "cope"
doc = nlp.make_doc("coping")
doc[0].pos_ = "VERB"
assert doc[0].lemma_ == ""
doc = lemmatizer(doc)
assert doc[0].text == "coping"
assert doc[0].lemma_ == "cope"
def test_lemmatizer_serialize(nlp, lemmatizer):
@registry.assets("cope_lookups")
def cope_lookups():
lookups = Lookups()
lookups.add_table("lemma_lookup", {"cope": "cope"})
lookups.add_table("lemma_index", {"verb": ("cope", "cop")})
lookups.add_table("lemma_exc", {"verb": {"coping": ("cope",)}})
lookups.add_table("lemma_rules", {"verb": [["ing", ""]]})
return lookups
nlp2 = English()
lemmatizer2 = nlp2.add_pipe(
"lemmatizer", config={"mode": "rule", "lookups": {"@assets": "cope_lookups"}}
)
lemmatizer2.from_bytes(lemmatizer.to_bytes())
assert lemmatizer.to_bytes() == lemmatizer2.to_bytes()
assert lemmatizer.lookups.tables == lemmatizer2.lookups.tables
# Also test the results are still the same after IO
with make_tempdir() as tmp_dir:
nlp.to_disk(tmp_dir)
nlp2 = util.load_model_from_path(tmp_dir)
doc2 = nlp2.make_doc("coping")
doc2[0].pos_ = "VERB"
assert doc2[0].lemma_ == ""
doc2 = lemmatizer(doc2)
assert doc2[0].text == "coping"
assert doc2[0].lemma_ == "cope"