# Note that the input and output types here are defined to match the problem statement,
# i.e., entity recognition.
classifier = AutoML(
search_algorithm=PESearch,
input=(Seq[Seq[Word]], Supervised[Seq[Seq[Label]]]),
output=Seq[Seq[Label]],
score_metric=meddocan.F1_beta,
cross_validation_steps=1,
# Since we only want to try neural networks, we restrict
# the contrib registry to algorithms matching with `Keras`.
registry=find_classes("Keras|Bert"),
# We need to give some extra time because neural networks are slow
evaluation_timeout=300,
search_timeout=1800,
)
# Basic logging configuration.
loggers = [RichLogger()]
# Finally, loading the MEDDOCAN dataset, running the `AutoML` instance,
# and printing the results.
X_train, y_train, X_test, y_test = meddocan.load()
classifier.fit(X_train, y_train, logger=loggers)
score = classifier.score(X_test, y_test)
print(score)
output=Seq[Seq[Label]],
registry=find_classes(exclude="Keras|Bert"),
search_iterations=args.iterations,
score_metric=meddocan.F1_beta,
cross_validation_steps=1,
pop_size=args.popsize,
search_timeout=args.global_timeout,
evaluation_timeout=args.timeout,
memory_limit=args.memory * 1024 ** 3,
)
# Basic logging configuration.
loggers = [RichLogger()]
if args.token:
from autogoal.contrib.telegram import TelegramLogger
telegram = TelegramLogger(token=args.token, name=f"MEDDOCAN", channel=args.channel,)
loggers.append(telegram)
# Finally, loading the MEDDOCAN dataset, running the `AutoML` instance,
# and printing the results.
X_train, y_train, X_test, y_test = meddocan.load(max_examples=args.examples)
classifier.fit(X_train, y_train, logger=loggers)
score = classifier.score(X_test, y_test)
print(score)
from autogoal.contrib.nltk._generated import AffixTagger
from autogoal.datasets.meddocan import load
X, _, y, _ = load()
# for sent in X:
# print(repr(sent))
X = X[:10]
y = y[:10]
tagger = AffixTagger(-3, 2, 0)
tagger.run((X, y))
tagger.eval()
ypred = tagger.run((X, None))
print("ypred", ypred)
print("ytrue", y)