mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
569cc98982
* Add load_from_config function * Add train_from_config script * Merge configs and expose via spacy.config * Fix script * Suggest create_evaluation_callback * Hard-code for NER * Fix errors * Register command * Add TODO * Update train-from-config todos * Fix imports * Allow delayed setting of parser model nr_class * Get train-from-config working * Tidy up and fix scores and printing * Hide traceback if cancelled * Fix weighted score formatting * Fix score formatting * Make output_path optional * Add Tok2Vec component * Tidy up and add tok2vec_tensors * Add option to copy docs in nlp.update * Copy docs in nlp.update * Adjust nlp.update() for set_annotations * Don't shuffle pipes in nlp.update, decruft * Support set_annotations arg in component update * Support set_annotations in parser update * Add get_gradients method * Add get_gradients to parser * Update errors.py * Fix problems caused by merge * Add _link_components method in nlp * Add concept of 'listeners' and ControlledModel * Support optional attributes arg in ControlledModel * Try having tok2vec component in pipeline * Fix tok2vec component * Fix config * Fix tok2vec * Update for Example * Update for Example * Update config * Add eg2doc util * Update and add schemas/types * Update schemas * Fix nlp.update * Fix tagger * Remove hacks from train-from-config * Remove hard-coded config str * Calculate loss in tok2vec component * Tidy up and use function signatures instead of models * Support union types for registry models * Minor cleaning in Language.update * Make ControlledModel specifically Tok2VecListener * Fix train_from_config * Fix tok2vec * Tidy up * Add function for bilstm tok2vec * Fix type * Fix syntax * Fix pytorch optimizer * Add example configs * Update for thinc describe changes * Update for Thinc changes * Update for dropout/sgd changes * Update for dropout/sgd changes * Unhack gradient update * Work on refactoring _ml * Remove _ml.py module * WIP upgrade cli scripts for thinc * Move some _ml stuff to util * Import link_vectors from util * Update train_from_config * Import from util * Import from util * Temporarily add ml.component_models module * Move ml methods * Move typedefs * Update load vectors * Update gitignore * Move imports * Add PrecomputableAffine * Fix imports * Fix imports * Fix imports * Fix missing imports * Update CLI scripts * Update spacy.language * Add stubs for building the models * Update model definition * Update create_default_optimizer * Fix import * Fix comment * Update imports in tests * Update imports in spacy.cli * Fix import * fix obsolete thinc imports * update srsly pin * from thinc to ml_datasets for example data such as imdb * update ml_datasets pin * using STATE.vectors * small fix * fix Sentencizer.pipe * black formatting * rename Affine to Linear as in thinc * set validate explicitely to True * rename with_square_sequences to with_list2padded * rename with_flatten to with_list2array * chaining layernorm * small fixes * revert Optimizer import * build_nel_encoder with new thinc style * fixes using model's get and set methods * Tok2Vec in component models, various fixes * fix up legacy tok2vec code * add model initialize calls * add in build_tagger_model * small fixes * setting model dims * fixes for ParserModel * various small fixes * initialize thinc Models * fixes * consistent naming of window_size * fixes, removing set_dropout * work around Iterable issue * remove legacy tok2vec * util fix * fix forward function of tok2vec listener * more fixes * trying to fix PrecomputableAffine (not succesful yet) * alloc instead of allocate * add morphologizer * rename residual * rename fixes * Fix predict function * Update parser and parser model * fixing few more tests * Fix precomputable affine * Update component model * Update parser model * Move backprop padding to own function, for test * Update test * Fix p. affine * Update NEL * build_bow_text_classifier and extract_ngrams * Fix parser init * Fix test add label * add build_simple_cnn_text_classifier * Fix parser init * Set gpu off by default in example * Fix tok2vec listener * Fix parser model * Small fixes * small fix for PyTorchLSTM parameters * revert my_compounding hack (iterable fixed now) * fix biLSTM * Fix uniqued * PyTorchRNNWrapper fix * small fixes * use helper function to calculate cosine loss * small fixes for build_simple_cnn_text_classifier * putting dropout default at 0.0 to ensure the layer gets built * using thinc util's set_dropout_rate * moving layer normalization inside of maxout definition to optimize dropout * temp debugging in NEL * fixed NEL model by using init defaults ! * fixing after set_dropout_rate refactor * proper fix * fix test_update_doc after refactoring optimizers in thinc * Add CharacterEmbed layer * Construct tagger Model * Add missing import * Remove unused stuff * Work on textcat * fix test (again :)) after optimizer refactor * fixes to allow reading Tagger from_disk without overwriting dimensions * don't build the tok2vec prematuraly * fix CharachterEmbed init * CharacterEmbed fixes * Fix CharacterEmbed architecture * fix imports * renames from latest thinc update * one more rename * add initialize calls where appropriate * fix parser initialization * Update Thinc version * Fix errors, auto-format and tidy up imports * Fix validation * fix if bias is cupy array * revert for now * ensure it's a numpy array before running bp in ParserStepModel * no reason to call require_gpu twice * use CupyOps.to_numpy instead of cupy directly * fix initialize of ParserModel * remove unnecessary import * fixes for CosineDistance * fix device renaming * use refactored loss functions (Thinc PR 251) * overfitting test for tagger * experimental settings for the tagger: avoid zero-init and subword normalization * clean up tagger overfitting test * use previous default value for nP * remove toy config * bringing layernorm back (had a bug - fixed in thinc) * revert setting nP explicitly * remove setting default in constructor * restore values as they used to be * add overfitting test for NER * add overfitting test for dep parser * add overfitting test for textcat * fixing init for linear (previously affine) * larger eps window for textcat * ensure doc is not None * Require newer thinc * Make float check vaguer * Slop the textcat overfit test more * Fix textcat test * Fix exclusive classes for textcat * fix after renaming of alloc methods * fixing renames and mandatory arguments (staticvectors WIP) * upgrade to thinc==8.0.0.dev3 * refer to vocab.vectors directly instead of its name * rename alpha to learn_rate * adding hashembed and staticvectors dropout * upgrade to thinc 8.0.0.dev4 * add name back to avoid warning W020 * thinc dev4 * update srsly * using thinc 8.0.0a0 ! Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com> Co-authored-by: Ines Montani <ines@ines.io>
252 lines
9.0 KiB
Cython
252 lines
9.0 KiB
Cython
# cython: infer_types=True
|
|
from cpython.ref cimport Py_INCREF
|
|
from cymem.cymem cimport Pool
|
|
from ..typedefs cimport weight_t
|
|
from thinc.extra.search cimport Beam
|
|
from collections import Counter
|
|
import srsly
|
|
|
|
from . cimport _beam_utils
|
|
from ..tokens.doc cimport Doc
|
|
from ..structs cimport TokenC
|
|
from .stateclass cimport StateClass
|
|
from ..typedefs cimport attr_t
|
|
from ..errors import Errors
|
|
from .. import util
|
|
|
|
|
|
cdef weight_t MIN_SCORE = -90000
|
|
|
|
|
|
class OracleError(Exception):
|
|
pass
|
|
|
|
|
|
cdef void* _init_state(Pool mem, int length, void* tokens) except NULL:
|
|
cdef StateC* st = new StateC(<const TokenC*>tokens, length)
|
|
return <void*>st
|
|
|
|
|
|
cdef int _del_state(Pool mem, void* state, void* x) except -1:
|
|
cdef StateC* st = <StateC*>state
|
|
del st
|
|
|
|
|
|
cdef class TransitionSystem:
|
|
def __init__(self, StringStore string_table, labels_by_action=None, min_freq=None):
|
|
self.mem = Pool()
|
|
self.strings = string_table
|
|
self.n_moves = 0
|
|
self._size = 100
|
|
|
|
self.c = <Transition*>self.mem.alloc(self._size, sizeof(Transition))
|
|
|
|
self.labels = {}
|
|
if labels_by_action:
|
|
self.initialize_actions(labels_by_action, min_freq=min_freq)
|
|
self.root_label = self.strings.add('ROOT')
|
|
self.init_beam_state = _init_state
|
|
self.del_beam_state = _del_state
|
|
|
|
def __reduce__(self):
|
|
return (self.__class__, (self.strings, self.labels), None, None)
|
|
|
|
def init_batch(self, docs):
|
|
cdef StateClass state
|
|
states = []
|
|
offset = 0
|
|
for doc in docs:
|
|
state = StateClass(doc, offset=offset)
|
|
self.initialize_state(state.c)
|
|
states.append(state)
|
|
offset += len(doc)
|
|
return states
|
|
|
|
def init_beams(self, docs, beam_width, beam_density=0.):
|
|
cdef Doc doc
|
|
beams = []
|
|
cdef int offset = 0
|
|
|
|
# Doc objects might contain labels that we need to register actions for. We need to check for that
|
|
# *before* we create any Beam objects, because the Beam object needs the correct number of
|
|
# actions. It's sort of dumb, but the best way is to just call init_batch() -- that triggers the additions,
|
|
# and it doesn't matter that we create and discard the state objects.
|
|
self.init_batch(docs)
|
|
|
|
for doc in docs:
|
|
beam = Beam(self.n_moves, beam_width, min_density=beam_density)
|
|
beam.initialize(self.init_beam_state, self.del_beam_state,
|
|
doc.length, doc.c)
|
|
for i in range(beam.width):
|
|
state = <StateC*>beam.at(i)
|
|
state.offset = offset
|
|
offset += len(doc)
|
|
beam.check_done(_beam_utils.check_final_state, NULL)
|
|
beams.append(beam)
|
|
return beams
|
|
|
|
def get_oracle_sequence(self, doc, GoldParse gold):
|
|
cdef Pool mem = Pool()
|
|
# n_moves should not be zero at this point, but make sure to avoid zero-length mem alloc
|
|
assert self.n_moves > 0
|
|
costs = <float*>mem.alloc(self.n_moves, sizeof(float))
|
|
is_valid = <int*>mem.alloc(self.n_moves, sizeof(int))
|
|
|
|
cdef StateClass state = StateClass(doc, offset=0)
|
|
self.initialize_state(state.c)
|
|
history = []
|
|
while not state.is_final():
|
|
self.set_costs(is_valid, costs, state, gold)
|
|
for i in range(self.n_moves):
|
|
if is_valid[i] and costs[i] <= 0:
|
|
action = self.c[i]
|
|
history.append(i)
|
|
action.do(state.c, action.label)
|
|
break
|
|
else:
|
|
raise ValueError(Errors.E024)
|
|
return history
|
|
|
|
def apply_transition(self, StateClass state, name):
|
|
if not self.is_valid(state, name):
|
|
raise ValueError(Errors.E170.format(name=name))
|
|
action = self.lookup_transition(name)
|
|
action.do(state.c, action.label)
|
|
|
|
cdef int initialize_state(self, StateC* state) nogil:
|
|
pass
|
|
|
|
cdef int finalize_state(self, StateC* state) nogil:
|
|
pass
|
|
|
|
def finalize_doc(self, doc):
|
|
pass
|
|
|
|
def preprocess_gold(self, GoldParse gold):
|
|
raise NotImplementedError
|
|
|
|
def is_gold_parse(self, StateClass state, GoldParse gold):
|
|
raise NotImplementedError
|
|
|
|
cdef Transition lookup_transition(self, object name) except *:
|
|
raise NotImplementedError
|
|
|
|
cdef Transition init_transition(self, int clas, int move, attr_t label) except *:
|
|
raise NotImplementedError
|
|
|
|
def is_valid(self, StateClass stcls, move_name):
|
|
action = self.lookup_transition(move_name)
|
|
if action.move == 0:
|
|
return False
|
|
return action.is_valid(stcls.c, action.label)
|
|
|
|
cdef int set_valid(self, int* is_valid, const StateC* st) nogil:
|
|
cdef int i
|
|
for i in range(self.n_moves):
|
|
is_valid[i] = self.c[i].is_valid(st, self.c[i].label)
|
|
|
|
cdef int set_costs(self, int* is_valid, weight_t* costs,
|
|
StateClass stcls, GoldParse gold) except -1:
|
|
cdef int i
|
|
self.set_valid(is_valid, stcls.c)
|
|
cdef int n_gold = 0
|
|
for i in range(self.n_moves):
|
|
if is_valid[i]:
|
|
costs[i] = self.c[i].get_cost(stcls, &gold.c, self.c[i].label)
|
|
n_gold += costs[i] <= 0
|
|
else:
|
|
costs[i] = 9000
|
|
if n_gold <= 0:
|
|
raise ValueError(Errors.E024)
|
|
|
|
def get_class_name(self, int clas):
|
|
act = self.c[clas]
|
|
return self.move_name(act.move, act.label)
|
|
|
|
def initialize_actions(self, labels_by_action, min_freq=None):
|
|
self.labels = {}
|
|
self.n_moves = 0
|
|
added_labels = []
|
|
added_actions = {}
|
|
for action, label_freqs in sorted(labels_by_action.items()):
|
|
action = int(action)
|
|
# Make sure we take a copy here, and that we get a Counter
|
|
self.labels[action] = Counter()
|
|
# Have to be careful here: Sorting must be stable, or our model
|
|
# won't be read back in correctly.
|
|
sorted_labels = [(f, L) for L, f in label_freqs.items()]
|
|
sorted_labels.sort()
|
|
sorted_labels.reverse()
|
|
for freq, label_str in sorted_labels:
|
|
if freq < 0:
|
|
added_labels.append((freq, label_str))
|
|
added_actions.setdefault(label_str, []).append(action)
|
|
else:
|
|
self.add_action(int(action), label_str)
|
|
self.labels[action][label_str] = freq
|
|
added_labels.sort(reverse=True)
|
|
for freq, label_str in added_labels:
|
|
for action in added_actions[label_str]:
|
|
self.add_action(int(action), label_str)
|
|
self.labels[action][label_str] = freq
|
|
|
|
def add_action(self, int action, label_name):
|
|
cdef attr_t label_id
|
|
if not isinstance(label_name, int) and \
|
|
not isinstance(label_name, long):
|
|
label_id = self.strings.add(label_name)
|
|
else:
|
|
label_id = label_name
|
|
# Check we're not creating a move we already have, so that this is
|
|
# idempotent
|
|
for trans in self.c[:self.n_moves]:
|
|
if trans.move == action and trans.label == label_id:
|
|
return 0
|
|
if self.n_moves >= self._size:
|
|
self._size *= 2
|
|
self.c = <Transition*>self.mem.realloc(self.c, self._size * sizeof(self.c[0]))
|
|
self.c[self.n_moves] = self.init_transition(self.n_moves, action, label_id)
|
|
self.n_moves += 1
|
|
# Add the new (action, label) pair, making up a frequency for it if
|
|
# necessary. To preserve sort order, the frequency needs to be lower
|
|
# than previous frequencies.
|
|
if self.labels.get(action, []):
|
|
new_freq = min(self.labels[action].values())
|
|
else:
|
|
self.labels[action] = Counter()
|
|
new_freq = -1
|
|
if new_freq > 0:
|
|
new_freq = 0
|
|
self.labels[action][label_name] = new_freq-1
|
|
return 1
|
|
|
|
def to_disk(self, path, **kwargs):
|
|
with path.open('wb') as file_:
|
|
file_.write(self.to_bytes(**kwargs))
|
|
|
|
def from_disk(self, path, **kwargs):
|
|
with path.open('rb') as file_:
|
|
byte_data = file_.read()
|
|
self.from_bytes(byte_data, **kwargs)
|
|
return self
|
|
|
|
def to_bytes(self, exclude=tuple(), **kwargs):
|
|
transitions = []
|
|
serializers = {
|
|
'moves': lambda: srsly.json_dumps(self.labels),
|
|
'strings': lambda: self.strings.to_bytes()
|
|
}
|
|
exclude = util.get_serialization_exclude(serializers, exclude, kwargs)
|
|
return util.to_bytes(serializers, exclude)
|
|
|
|
def from_bytes(self, bytes_data, exclude=tuple(), **kwargs):
|
|
labels = {}
|
|
deserializers = {
|
|
'moves': lambda b: labels.update(srsly.json_loads(b)),
|
|
'strings': lambda b: self.strings.from_bytes(b)
|
|
}
|
|
exclude = util.get_serialization_exclude(deserializers, exclude, kwargs)
|
|
msg = util.from_bytes(bytes_data, deserializers, exclude)
|
|
self.initialize_actions(labels)
|
|
return self
|