def test_readers():
config_string = """
[training]
[corpora]
@readers = "myreader.v1"
[nlp]
lang = "en"
pipeline = ["tok2vec", "textcat"]
[components]
[components.tok2vec]
factory = "tok2vec"
[components.textcat]
factory = "textcat"
"""
@registry.readers.register("myreader.v1")
def myreader() -> Dict[str, Callable[[Language, str], Iterable[Example]]]:
annots = {"cats": {"POS": 1.0, "NEG": 0.0}}
def reader(nlp: Language):
doc = nlp.make_doc(f"This is an example")
return [Example.from_dict(doc, annots)]
return {
"train": reader,
"dev": reader,
"extra": reader,
"something": reader
}
config = Config().from_str(config_string)
nlp = load_model_from_config(config, auto_fill=True)
T = registry.resolve(nlp.config.interpolate()["training"],
schema=ConfigSchemaTraining)
dot_names = [T["train_corpus"], T["dev_corpus"]]
train_corpus, dev_corpus = resolve_dot_names(nlp.config, dot_names)
assert isinstance(train_corpus, Callable)
optimizer = T["optimizer"]
# simulate a training loop
nlp.initialize(lambda: train_corpus(nlp), sgd=optimizer)
for example in train_corpus(nlp):
nlp.update([example], sgd=optimizer)
scores = nlp.evaluate(list(dev_corpus(nlp)))
assert scores["cats_macro_auc"] == 0.0
# ensure the pipeline runs
doc = nlp("Quick test")
assert doc.cats
corpora = {"corpora": nlp.config.interpolate()["corpora"]}
extra_corpus = registry.resolve(corpora)["corpora"]["extra"]
assert isinstance(extra_corpus, Callable)
def __init__(
self,
config: Config,
*,
rank: int = 0,
num_workers: int = 1,
use_gpu: int = 0,
ray=None,
):
if ray is None:
# Avoid importing ray in the module. This allows a test-ray to
# be passed in, and speeds up the CLI.
import ray # type: ignore
self.ray = ray
self.rank = rank
self.num_workers = num_workers
self.gpu_id = self._resolve_gpu(use_gpu)
self.nlp = init_nlp(Config(config), use_gpu=self.gpu_id)
config = self.nlp.config.interpolate()
self.T = registry.resolve(config["training"], schema=ConfigSchemaTraining)
dot_names = [self.T["train_corpus"], self.T["dev_corpus"]]
self.train_corpus, self.dev_corpus = resolve_dot_names(config, dot_names)
self.before_to_disk = create_before_to_disk_callback(self.T["before_to_disk"])
allocator = self.T["gpu_allocator"]
if use_gpu >= 0 and allocator:
set_gpu_allocator(allocator)
self._evaluation_callback = lambda: {}
self._results = []
self._has_evaluation_callback = False
self.thread = None
self.proxy = None
self.n_grads_used = 0
self.n_grads_discarded = 0
def test_cat_readers(reader, additional_config):
nlp_config_string = """
[training]
seed = 0
[training.score_weights]
cats_macro_auc = 1.0
[corpora]
@readers = "PLACEHOLDER"
[nlp]
lang = "en"
pipeline = ["tok2vec", "textcat_multilabel"]
[components]
[components.tok2vec]
factory = "tok2vec"
[components.textcat_multilabel]
factory = "textcat_multilabel"
"""
config = Config().from_str(nlp_config_string)
fix_random_seed(config["training"]["seed"])
config["corpora"]["@readers"] = reader
config["corpora"].update(additional_config)
nlp = load_model_from_config(config, auto_fill=True)
T = registry.resolve(nlp.config["training"], schema=ConfigSchemaTraining)
dot_names = [T["train_corpus"], T["dev_corpus"]]
train_corpus, dev_corpus = resolve_dot_names(nlp.config, dot_names)
optimizer = T["optimizer"]
# simulate a training loop
nlp.initialize(lambda: train_corpus(nlp), sgd=optimizer)
for example in train_corpus(nlp):
assert example.y.cats
# this shouldn't fail if each training example has at least one positive label
assert sorted(list(set(example.y.cats.values()))) == [0.0, 1.0]
nlp.update([example], sgd=optimizer)
# simulate performance benchmark on dev corpus
dev_examples = list(dev_corpus(nlp))
for example in dev_examples:
# this shouldn't fail if each dev example has at least one positive label
assert sorted(list(set(example.y.cats.values()))) == [0.0, 1.0]
scores = nlp.evaluate(dev_examples)
assert scores["cats_score"]
# ensure the pipeline runs
doc = nlp("Quick test")
assert doc.cats
def test_create_nlp_from_pretraining_config():
"""Test that the default pretraining config validates properly"""
config = Config().from_str(pretrain_config_string)
pretrain_config = load_config(DEFAULT_CONFIG_PRETRAIN_PATH)
filled = config.merge(pretrain_config)
registry.resolve(filled["pretraining"], schema=ConfigSchemaPretrain)