spaCy/spacy/tests/parser/test_nn_beam.py

143 lines
3.5 KiB
Python
Raw Normal View History

Add beam_parser and beam_ner components for v3 (#6369) * Get basic beam tests working * Get basic beam tests working * Compile _beam_utils * Remove prints * Test beam density * Beam parser seems to train * Draft beam NER * Upd beam * Add hypothesis as dev dependency * Implement missing is-gold-parse method * Implement early update * Fix state hashing * Fix test * Fix test * Default to non-beam in parser constructor * Improve oracle for beam * Start refactoring beam * Update test * Refactor beam * Update nn * Refactor beam and weight by cost * Update ner beam settings * Update test * Add __init__.pxd * Upd test * Fix test * Upd test * Fix test * Remove ring buffer history from StateC * WIP change arc-eager transitions * Add state tests * Support ternary sent start values * Fix arc eager * Fix NER * Pass oracle cut size for beam * Fix ner test * Fix beam * Improve StateC.clone * Improve StateClass.borrow * Work directly with StateC, not StateClass * Remove print statements * Fix state copy * Improve state class * Refactor parser oracles * Fix arc eager oracle * Fix arc eager oracle * Use a vector to implement the stack * Refactor state data structure * Fix alignment of sent start * Add get_aligned_sent_starts method * Add test for ae oracle when bad sentence starts * Fix sentence segment handling * Avoid Reduce that inserts illegal sentence * Update preset SBD test * Fix test * Remove prints * Fix sent starts in Example * Improve python API of StateClass * Tweak comments and debug output of arc eager * Upd test * Fix state test * Fix state test
2020-12-13 04:08:32 +03:00
import pytest
import hypothesis
import hypothesis.strategies
import numpy
from spacy.vocab import Vocab
from spacy.language import Language
from spacy.pipeline._parser_internals.arc_eager import ArcEager
from spacy.tokens import Doc
from spacy.pipeline._parser_internals._beam_utils import BeamBatch
from spacy.pipeline._parser_internals.stateclass import StateClass
from spacy.training import Example
from thinc.tests.strategies import ndarrays_of_shape
@pytest.fixture(scope="module")
def vocab():
return Vocab()
@pytest.fixture(scope="module")
def moves(vocab):
aeager = ArcEager(vocab.strings, {})
aeager.add_action(0, "")
aeager.add_action(1, "")
aeager.add_action(2, "nsubj")
aeager.add_action(2, "punct")
aeager.add_action(2, "aux")
aeager.add_action(2, "nsubjpass")
aeager.add_action(3, "dobj")
aeager.add_action(2, "aux")
aeager.add_action(4, "ROOT")
return aeager
@pytest.fixture(scope="module")
def docs(vocab):
return [
Doc(
vocab,
words=["Rats", "bite", "things"],
heads=[1, 1, 1],
deps=["nsubj", "ROOT", "dobj"],
2021-01-05 05:41:53 +03:00
sent_starts=[True, False, False],
Add beam_parser and beam_ner components for v3 (#6369) * Get basic beam tests working * Get basic beam tests working * Compile _beam_utils * Remove prints * Test beam density * Beam parser seems to train * Draft beam NER * Upd beam * Add hypothesis as dev dependency * Implement missing is-gold-parse method * Implement early update * Fix state hashing * Fix test * Fix test * Default to non-beam in parser constructor * Improve oracle for beam * Start refactoring beam * Update test * Refactor beam * Update nn * Refactor beam and weight by cost * Update ner beam settings * Update test * Add __init__.pxd * Upd test * Fix test * Upd test * Fix test * Remove ring buffer history from StateC * WIP change arc-eager transitions * Add state tests * Support ternary sent start values * Fix arc eager * Fix NER * Pass oracle cut size for beam * Fix ner test * Fix beam * Improve StateC.clone * Improve StateClass.borrow * Work directly with StateC, not StateClass * Remove print statements * Fix state copy * Improve state class * Refactor parser oracles * Fix arc eager oracle * Fix arc eager oracle * Use a vector to implement the stack * Refactor state data structure * Fix alignment of sent start * Add get_aligned_sent_starts method * Add test for ae oracle when bad sentence starts * Fix sentence segment handling * Avoid Reduce that inserts illegal sentence * Update preset SBD test * Fix test * Remove prints * Fix sent starts in Example * Improve python API of StateClass * Tweak comments and debug output of arc eager * Upd test * Fix state test * Fix state test
2020-12-13 04:08:32 +03:00
)
]
@pytest.fixture(scope="module")
def examples(docs):
return [Example(doc, doc.copy()) for doc in docs]
@pytest.fixture
def states(docs):
return [StateClass(doc) for doc in docs]
@pytest.fixture
def tokvecs(docs, vector_size):
output = []
for doc in docs:
vec = numpy.random.uniform(-0.1, 0.1, (len(doc), vector_size))
output.append(numpy.asarray(vec))
return output
@pytest.fixture(scope="module")
def batch_size(docs):
return len(docs)
@pytest.fixture(scope="module")
def beam_width():
return 4
2021-01-05 05:41:53 +03:00
Add beam_parser and beam_ner components for v3 (#6369) * Get basic beam tests working * Get basic beam tests working * Compile _beam_utils * Remove prints * Test beam density * Beam parser seems to train * Draft beam NER * Upd beam * Add hypothesis as dev dependency * Implement missing is-gold-parse method * Implement early update * Fix state hashing * Fix test * Fix test * Default to non-beam in parser constructor * Improve oracle for beam * Start refactoring beam * Update test * Refactor beam * Update nn * Refactor beam and weight by cost * Update ner beam settings * Update test * Add __init__.pxd * Upd test * Fix test * Upd test * Fix test * Remove ring buffer history from StateC * WIP change arc-eager transitions * Add state tests * Support ternary sent start values * Fix arc eager * Fix NER * Pass oracle cut size for beam * Fix ner test * Fix beam * Improve StateC.clone * Improve StateClass.borrow * Work directly with StateC, not StateClass * Remove print statements * Fix state copy * Improve state class * Refactor parser oracles * Fix arc eager oracle * Fix arc eager oracle * Use a vector to implement the stack * Refactor state data structure * Fix alignment of sent start * Add get_aligned_sent_starts method * Add test for ae oracle when bad sentence starts * Fix sentence segment handling * Avoid Reduce that inserts illegal sentence * Update preset SBD test * Fix test * Remove prints * Fix sent starts in Example * Improve python API of StateClass * Tweak comments and debug output of arc eager * Upd test * Fix state test * Fix state test
2020-12-13 04:08:32 +03:00
@pytest.fixture(params=[0.0, 0.5, 1.0])
def beam_density(request):
return request.param
2021-01-05 05:41:53 +03:00
Add beam_parser and beam_ner components for v3 (#6369) * Get basic beam tests working * Get basic beam tests working * Compile _beam_utils * Remove prints * Test beam density * Beam parser seems to train * Draft beam NER * Upd beam * Add hypothesis as dev dependency * Implement missing is-gold-parse method * Implement early update * Fix state hashing * Fix test * Fix test * Default to non-beam in parser constructor * Improve oracle for beam * Start refactoring beam * Update test * Refactor beam * Update nn * Refactor beam and weight by cost * Update ner beam settings * Update test * Add __init__.pxd * Upd test * Fix test * Upd test * Fix test * Remove ring buffer history from StateC * WIP change arc-eager transitions * Add state tests * Support ternary sent start values * Fix arc eager * Fix NER * Pass oracle cut size for beam * Fix ner test * Fix beam * Improve StateC.clone * Improve StateClass.borrow * Work directly with StateC, not StateClass * Remove print statements * Fix state copy * Improve state class * Refactor parser oracles * Fix arc eager oracle * Fix arc eager oracle * Use a vector to implement the stack * Refactor state data structure * Fix alignment of sent start * Add get_aligned_sent_starts method * Add test for ae oracle when bad sentence starts * Fix sentence segment handling * Avoid Reduce that inserts illegal sentence * Update preset SBD test * Fix test * Remove prints * Fix sent starts in Example * Improve python API of StateClass * Tweak comments and debug output of arc eager * Upd test * Fix state test * Fix state test
2020-12-13 04:08:32 +03:00
@pytest.fixture
def vector_size():
return 6
@pytest.fixture
def beam(moves, examples, beam_width):
states, golds, _ = moves.init_gold_batch(examples)
return BeamBatch(moves, states, golds, width=beam_width, density=0.0)
@pytest.fixture
def scores(moves, batch_size, beam_width):
return numpy.asarray(
numpy.concatenate(
[
numpy.random.uniform(-0.1, 0.1, (beam_width, moves.n_moves))
for _ in range(batch_size)
]
2021-01-05 05:41:53 +03:00
),
dtype="float32",
)
Add beam_parser and beam_ner components for v3 (#6369) * Get basic beam tests working * Get basic beam tests working * Compile _beam_utils * Remove prints * Test beam density * Beam parser seems to train * Draft beam NER * Upd beam * Add hypothesis as dev dependency * Implement missing is-gold-parse method * Implement early update * Fix state hashing * Fix test * Fix test * Default to non-beam in parser constructor * Improve oracle for beam * Start refactoring beam * Update test * Refactor beam * Update nn * Refactor beam and weight by cost * Update ner beam settings * Update test * Add __init__.pxd * Upd test * Fix test * Upd test * Fix test * Remove ring buffer history from StateC * WIP change arc-eager transitions * Add state tests * Support ternary sent start values * Fix arc eager * Fix NER * Pass oracle cut size for beam * Fix ner test * Fix beam * Improve StateC.clone * Improve StateClass.borrow * Work directly with StateC, not StateClass * Remove print statements * Fix state copy * Improve state class * Refactor parser oracles * Fix arc eager oracle * Fix arc eager oracle * Use a vector to implement the stack * Refactor state data structure * Fix alignment of sent start * Add get_aligned_sent_starts method * Add test for ae oracle when bad sentence starts * Fix sentence segment handling * Avoid Reduce that inserts illegal sentence * Update preset SBD test * Fix test * Remove prints * Fix sent starts in Example * Improve python API of StateClass * Tweak comments and debug output of arc eager * Upd test * Fix state test * Fix state test
2020-12-13 04:08:32 +03:00
def test_create_beam(beam):
pass
def test_beam_advance(beam, scores):
beam.advance(scores)
def test_beam_advance_too_few_scores(beam, scores):
n_state = sum(len(beam) for beam in beam)
scores = scores[:n_state]
with pytest.raises(IndexError):
beam.advance(scores[:-1])
def test_beam_parse(examples, beam_width):
nlp = Language()
parser = nlp.add_pipe("beam_parser")
parser.cfg["beam_width"] = beam_width
parser.add_label("nsubj")
parser.initialize(lambda: examples)
doc = nlp.make_doc("Australia is a country")
parser(doc)
@hypothesis.given(hyp=hypothesis.strategies.data())
def test_beam_density(moves, examples, beam_width, hyp):
beam_density = float(hyp.draw(hypothesis.strategies.floats(0.0, 1.0, width=32)))
states, golds, _ = moves.init_gold_batch(examples)
beam = BeamBatch(moves, states, golds, width=beam_width, density=beam_density)
n_state = sum(len(beam) for beam in beam)
scores = hyp.draw(ndarrays_of_shape((n_state, moves.n_moves)))
beam.advance(scores)
for b in beam:
beam_probs = b.probs
assert b.min_density == beam_density
assert beam_probs[-1] >= beam_probs[0] * beam_density