mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 09:56:28 +03:00
43b960c01b
* Update with WIP * Update with WIP * Update with pipeline serialization * Update types and pipe factories * Add deep merge, tidy up and add tests * Fix pipe creation from config * Don't validate default configs on load * Update spacy/language.py Co-authored-by: Ines Montani <ines@ines.io> * Adjust factory/component meta error * Clean up factory args and remove defaults * Add test for failing empty dict defaults * Update pipeline handling and methods * provide KB as registry function instead of as object * small change in test to make functionality more clear * update example script for EL configuration * Fix typo * Simplify test * Simplify test * splitting pipes.pyx into separate files * moving default configs to each component file * fix batch_size type * removing default values from component constructors where possible (TODO: test 4725) * skip instead of xfail * Add test for config -> nlp with multiple instances * pipeline.pipes -> pipeline.pipe * Tidy up, document, remove kwargs * small cleanup/generalization for Tok2VecListener * use DEFAULT_UPSTREAM field * revert to avoid circular imports * Fix tests * Replace deprecated arg * Make model dirs require config * fix pickling of keyword-only arguments in constructor * WIP: clean up and integrate full config * Add helper to handle function args more reliably Now also includes keyword-only args * Fix config composition and serialization * Improve config debugging and add visual diff * Remove unused defaults and fix type * Remove pipeline and factories from meta * Update spacy/default_config.cfg Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/default_config.cfg * small UX edits * avoid printing stack trace for debug CLI commands * Add support for language-specific factories * specify the section of the config which holds the model to debug * WIP: add Language.from_config * Update with language data refactor WIP * Auto-format * Add backwards-compat handling for Language.factories * Update morphologizer.pyx * Fix morphologizer * Update and simplify lemmatizers * Fix Japanese tests * Port over tagger changes * Fix Chinese and tests * Update to latest Thinc * WIP: xfail first Russian lemmatizer test * Fix component-specific overrides * fix nO for output layers in debug_model * Fix default value * Fix tests and don't pass objects in config * Fix deep merging * Fix lemma lookup data registry Only load the lookups if an entry is available in the registry (and if spacy-lookups-data is installed) * Add types * Add Vocab.from_config * Fix typo * Fix tests * Make config copying more elegant * Fix pipe analysis * Fix lemmatizers and is_base_form * WIP: move language defaults to config * Fix morphology type * Fix vocab * Remove comment * Update to latest Thinc * Add morph rules to config * Tidy up * Remove set_morphology option from tagger factory * Hack use_gpu * Move [pipeline] to top-level block and make [nlp.pipeline] list Allows separating component blocks from component order – otherwise, ordering the config would mean a changed component order, which is bad. Also allows initial config to define more components and not use all of them * Fix use_gpu and resume in CLI * Auto-format * Remove resume from config * Fix formatting and error * [pipeline] -> [components] * Fix types * Fix tagger test: requires set_morphology? Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
236 lines
7.3 KiB
Python
236 lines
7.3 KiB
Python
import pytest
|
|
from spacy.language import Language
|
|
|
|
|
|
@pytest.fixture
|
|
def nlp():
|
|
return Language()
|
|
|
|
|
|
@Language.component("new_pipe")
|
|
def new_pipe(doc):
|
|
return doc
|
|
|
|
|
|
@Language.component("other_pipe")
|
|
def other_pipe(doc):
|
|
return doc
|
|
|
|
|
|
def test_add_pipe_no_name(nlp):
|
|
nlp.add_pipe("new_pipe")
|
|
assert "new_pipe" in nlp.pipe_names
|
|
|
|
|
|
def test_add_pipe_duplicate_name(nlp):
|
|
nlp.add_pipe("new_pipe", name="duplicate_name")
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("new_pipe", name="duplicate_name")
|
|
|
|
|
|
@pytest.mark.parametrize("name", ["parser"])
|
|
def test_add_pipe_first(nlp, name):
|
|
nlp.add_pipe("new_pipe", name=name, first=True)
|
|
assert nlp.pipeline[0][0] == name
|
|
|
|
|
|
@pytest.mark.parametrize("name1,name2", [("parser", "lambda_pipe")])
|
|
def test_add_pipe_last(nlp, name1, name2):
|
|
Language.component("new_pipe2", func=lambda doc: doc)
|
|
nlp.add_pipe("new_pipe2", name=name2)
|
|
nlp.add_pipe("new_pipe", name=name1, last=True)
|
|
assert nlp.pipeline[0][0] != name1
|
|
assert nlp.pipeline[-1][0] == name1
|
|
|
|
|
|
def test_cant_add_pipe_first_and_last(nlp):
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("new_pipe", first=True, last=True)
|
|
|
|
|
|
@pytest.mark.parametrize("name", ["my_component"])
|
|
def test_get_pipe(nlp, name):
|
|
with pytest.raises(KeyError):
|
|
nlp.get_pipe(name)
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
assert nlp.get_pipe(name) == new_pipe
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"name,replacement,invalid_replacement",
|
|
[("my_component", "other_pipe", lambda doc: doc)],
|
|
)
|
|
def test_replace_pipe(nlp, name, replacement, invalid_replacement):
|
|
with pytest.raises(ValueError):
|
|
nlp.replace_pipe(name, new_pipe)
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
with pytest.raises(ValueError):
|
|
nlp.replace_pipe(name, invalid_replacement)
|
|
nlp.replace_pipe(name, replacement)
|
|
assert nlp.get_pipe(name) == nlp.create_pipe(replacement)
|
|
|
|
|
|
@pytest.mark.parametrize("old_name,new_name", [("old_pipe", "new_pipe")])
|
|
def test_rename_pipe(nlp, old_name, new_name):
|
|
with pytest.raises(ValueError):
|
|
nlp.rename_pipe(old_name, new_name)
|
|
nlp.add_pipe("new_pipe", name=old_name)
|
|
nlp.rename_pipe(old_name, new_name)
|
|
assert nlp.pipeline[0][0] == new_name
|
|
|
|
|
|
@pytest.mark.parametrize("name", ["my_component"])
|
|
def test_remove_pipe(nlp, name):
|
|
with pytest.raises(ValueError):
|
|
nlp.remove_pipe(name)
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
assert len(nlp.pipeline) == 1
|
|
removed_name, removed_component = nlp.remove_pipe(name)
|
|
assert not len(nlp.pipeline)
|
|
assert removed_name == name
|
|
assert removed_component == new_pipe
|
|
|
|
|
|
@pytest.mark.parametrize("name", ["my_component"])
|
|
def test_disable_pipes_method(nlp, name):
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
assert nlp.has_pipe(name)
|
|
disabled = nlp.select_pipes(disable=name)
|
|
assert not nlp.has_pipe(name)
|
|
disabled.restore()
|
|
|
|
|
|
@pytest.mark.parametrize("name", ["my_component"])
|
|
def test_enable_pipes_method(nlp, name):
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
assert nlp.has_pipe(name)
|
|
disabled = nlp.select_pipes(enable=[])
|
|
assert not nlp.has_pipe(name)
|
|
disabled.restore()
|
|
|
|
|
|
@pytest.mark.parametrize("name", ["my_component"])
|
|
def test_disable_pipes_context(nlp, name):
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
assert nlp.has_pipe(name)
|
|
with nlp.select_pipes(disable=name):
|
|
assert not nlp.has_pipe(name)
|
|
assert nlp.has_pipe(name)
|
|
|
|
|
|
def test_select_pipes_list_arg(nlp):
|
|
for name in ["c1", "c2", "c3"]:
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
assert nlp.has_pipe(name)
|
|
with nlp.select_pipes(disable=["c1", "c2"]):
|
|
assert not nlp.has_pipe("c1")
|
|
assert not nlp.has_pipe("c2")
|
|
assert nlp.has_pipe("c3")
|
|
with nlp.select_pipes(enable="c3"):
|
|
assert not nlp.has_pipe("c1")
|
|
assert not nlp.has_pipe("c2")
|
|
assert nlp.has_pipe("c3")
|
|
with nlp.select_pipes(enable=["c1", "c2"], disable="c3"):
|
|
assert nlp.has_pipe("c1")
|
|
assert nlp.has_pipe("c2")
|
|
assert not nlp.has_pipe("c3")
|
|
with nlp.select_pipes(enable=[]):
|
|
assert not nlp.has_pipe("c1")
|
|
assert not nlp.has_pipe("c2")
|
|
assert not nlp.has_pipe("c3")
|
|
with nlp.select_pipes(enable=["c1", "c2", "c3"], disable=[]):
|
|
assert nlp.has_pipe("c1")
|
|
assert nlp.has_pipe("c2")
|
|
assert nlp.has_pipe("c3")
|
|
with nlp.select_pipes(disable=["c1", "c2", "c3"], enable=[]):
|
|
assert not nlp.has_pipe("c1")
|
|
assert not nlp.has_pipe("c2")
|
|
assert not nlp.has_pipe("c3")
|
|
|
|
|
|
def test_select_pipes_errors(nlp):
|
|
for name in ["c1", "c2", "c3"]:
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
assert nlp.has_pipe(name)
|
|
|
|
with pytest.raises(ValueError):
|
|
nlp.select_pipes()
|
|
|
|
with pytest.raises(ValueError):
|
|
nlp.select_pipes(enable=["c1", "c2"], disable=["c1"])
|
|
|
|
with pytest.raises(ValueError):
|
|
nlp.select_pipes(enable=["c1", "c2"], disable=[])
|
|
|
|
with pytest.raises(ValueError):
|
|
nlp.select_pipes(enable=[], disable=["c3"])
|
|
|
|
|
|
@pytest.mark.parametrize("n_pipes", [100])
|
|
def test_add_lots_of_pipes(nlp, n_pipes):
|
|
Language.component("n_pipes", func=lambda doc: doc)
|
|
for i in range(n_pipes):
|
|
nlp.add_pipe("n_pipes", name=f"pipe_{i}")
|
|
assert len(nlp.pipe_names) == n_pipes
|
|
|
|
|
|
@pytest.mark.parametrize("component", [lambda doc: doc, {"hello": "world"}])
|
|
def test_raise_for_invalid_components(nlp, component):
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe(component)
|
|
|
|
|
|
@pytest.mark.parametrize("component", ["ner", "tagger", "parser", "textcat"])
|
|
def test_pipe_base_class_add_label(nlp, component):
|
|
label = "TEST"
|
|
pipe = nlp.create_pipe(component)
|
|
pipe.add_label(label)
|
|
if component == "tagger":
|
|
# Tagger always has the default coarse-grained label scheme
|
|
assert label in pipe.labels
|
|
else:
|
|
assert pipe.labels == (label,)
|
|
|
|
|
|
def test_pipe_labels(nlp):
|
|
input_labels = {
|
|
"ner": ["PERSON", "ORG", "GPE"],
|
|
"textcat": ["POSITIVE", "NEGATIVE"],
|
|
}
|
|
for name, labels in input_labels.items():
|
|
nlp.add_pipe(name)
|
|
pipe = nlp.get_pipe(name)
|
|
for label in labels:
|
|
pipe.add_label(label)
|
|
assert len(pipe.labels) == len(labels)
|
|
|
|
assert len(nlp.pipe_labels) == len(input_labels)
|
|
for name, labels in nlp.pipe_labels.items():
|
|
assert sorted(input_labels[name]) == sorted(labels)
|
|
|
|
|
|
def test_add_pipe_before_after():
|
|
"""Test that before/after works with strings and ints."""
|
|
nlp = Language()
|
|
nlp.add_pipe("ner")
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("textcat", before="parser")
|
|
nlp.add_pipe("textcat", before="ner")
|
|
assert nlp.pipe_names == ["textcat", "ner"]
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("parser", before=3)
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("parser", after=3)
|
|
nlp.add_pipe("parser", after=0)
|
|
assert nlp.pipe_names == ["textcat", "parser", "ner"]
|
|
nlp.add_pipe("tagger", before=2)
|
|
assert nlp.pipe_names == ["textcat", "parser", "tagger", "ner"]
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("entity_ruler", after=1, first=True)
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("entity_ruler", before="ner", after=2)
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("entity_ruler", before=True)
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("entity_ruler", first=False)
|