spaCy/spacy/tests/pipeline/test_morphologizer.py

139 lines
4.6 KiB
Python
Raw Normal View History

import pytest
from numpy.testing import assert_equal
from spacy import util
from spacy.training import Example
from spacy.lang.en import English
from spacy.language import Language
from spacy.tests.util import make_tempdir
from spacy.morphology import Morphology
from spacy.attrs import MORPH
def test_label_types():
nlp = Language()
Refactor pipeline components, config and language data (#5759) * 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>
2020-07-22 14:42:59 +03:00
morphologizer = nlp.add_pipe("morphologizer")
morphologizer.add_label("Feat=A")
with pytest.raises(ValueError):
Refactor pipeline components, config and language data (#5759) * 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>
2020-07-22 14:42:59 +03:00
morphologizer.add_label(9)
TRAIN_DATA = [
2020-06-20 15:15:04 +03:00
(
"I like green eggs",
{
"morphs": ["Feat=N", "Feat=V", "Feat=J", "Feat=N"],
"pos": ["NOUN", "VERB", "ADJ", "NOUN"],
},
),
# test combinations of morph+POS
("Eat blue ham", {"morphs": ["Feat=V", "", ""], "pos": ["", "ADJ", ""]}),
]
def test_no_label():
nlp = Language()
nlp.add_pipe("morphologizer")
with pytest.raises(ValueError):
2020-09-28 22:35:09 +03:00
nlp.initialize()
def test_implicit_label():
nlp = Language()
nlp.add_pipe("morphologizer")
train_examples = []
for t in TRAIN_DATA:
train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
2020-09-28 22:35:09 +03:00
nlp.initialize(get_examples=lambda: train_examples)
def test_no_resize():
nlp = Language()
morphologizer = nlp.add_pipe("morphologizer")
morphologizer.add_label("POS" + Morphology.FIELD_SEP + "NOUN")
morphologizer.add_label("POS" + Morphology.FIELD_SEP + "VERB")
2020-09-28 22:35:09 +03:00
nlp.initialize()
# this throws an error because the morphologizer can't be resized after initialization
with pytest.raises(ValueError):
morphologizer.add_label("POS" + Morphology.FIELD_SEP + "ADJ")
2020-09-28 22:35:09 +03:00
def test_initialize_examples():
nlp = Language()
morphologizer = nlp.add_pipe("morphologizer")
morphologizer.add_label("POS" + Morphology.FIELD_SEP + "NOUN")
train_examples = []
for t in TRAIN_DATA:
train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
# you shouldn't really call this more than once, but for testing it should be fine
2020-09-28 22:35:09 +03:00
nlp.initialize()
nlp.initialize(get_examples=lambda: train_examples)
with pytest.raises(TypeError):
2020-09-28 22:35:09 +03:00
nlp.initialize(get_examples=lambda: None)
with pytest.raises(TypeError):
2020-09-28 22:35:09 +03:00
nlp.initialize(get_examples=train_examples)
def test_overfitting_IO():
# Simple test to try and quickly overfit the morphologizer - ensuring the ML models work correctly
nlp = English()
nlp.add_pipe("morphologizer")
train_examples = []
for inst in TRAIN_DATA:
train_examples.append(Example.from_dict(nlp.make_doc(inst[0]), inst[1]))
2020-09-28 22:35:09 +03:00
optimizer = nlp.initialize(get_examples=lambda: train_examples)
for i in range(50):
losses = {}
nlp.update(train_examples, sgd=optimizer, losses=losses)
assert losses["morphologizer"] < 0.00001
# test the trained model
test_text = "I like blue ham"
doc = nlp(test_text)
gold_morphs = ["Feat=N", "Feat=V", "", ""]
gold_pos_tags = ["NOUN", "VERB", "ADJ", ""]
assert [str(t.morph) for t in doc] == gold_morphs
assert [t.pos_ for t in doc] == gold_pos_tags
# 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(test_text)
assert [str(t.morph) for t in doc2] == gold_morphs
assert [t.pos_ for t in doc2] == gold_pos_tags
# Make sure that running pipe twice, or comparing to call, always amounts to the same predictions
texts = [
"Just a sentence.",
"Then one more sentence about London.",
"Here is another one.",
"I like London.",
]
batch_deps_1 = [doc.to_array([MORPH]) for doc in nlp.pipe(texts)]
batch_deps_2 = [doc.to_array([MORPH]) for doc in nlp.pipe(texts)]
no_batch_deps = [doc.to_array([MORPH]) for doc in [nlp(text) for text in texts]]
assert_equal(batch_deps_1, batch_deps_2)
assert_equal(batch_deps_1, no_batch_deps)
# Test without POS
nlp.remove_pipe("morphologizer")
nlp.add_pipe("morphologizer")
for example in train_examples:
for token in example.reference:
token.pos_ = ""
optimizer = nlp.initialize(get_examples=lambda: train_examples)
for i in range(50):
losses = {}
nlp.update(train_examples, sgd=optimizer, losses=losses)
assert losses["morphologizer"] < 0.00001
# Test the trained model
test_text = "I like blue ham"
doc = nlp(test_text)
gold_morphs = ["Feat=N", "Feat=V", "", ""]
gold_pos_tags = ["", "", "", ""]
assert [str(t.morph) for t in doc] == gold_morphs
assert [t.pos_ for t in doc] == gold_pos_tags