def test_intent_classifier_config(self):
# Given
config_dict = {
"unit_name": LogRegIntentClassifier.unit_name,
"data_augmentation_config":
IntentClassifierDataAugmentationConfig().to_dict(),
"featurizer_config": FeaturizerConfig().to_dict(),
"random_seed": 42
}
# When
config = LogRegIntentClassifierConfig.from_dict(config_dict)
serialized_config = config.to_dict()
# Then
self.assertDictEqual(config_dict, serialized_config)
def from_path(cls, path, **shared):
"""Loads a :class:`LogRegIntentClassifier` instance from a path
The data at the given path must have been generated using
:func:`~LogRegIntentClassifier.persist`
"""
import numpy as np
from sklearn.linear_model import SGDClassifier
path = Path(path)
model_path = path / "intent_classifier.json"
if not model_path.exists():
raise LoadingError("Missing intent classifier model file: %s"
% model_path.name)
with model_path.open(encoding="utf8") as f:
model_dict = json.load(f)
# Create the classifier
config = LogRegIntentClassifierConfig.from_dict(model_dict["config"])
intent_classifier = cls(config=config, **shared)
intent_classifier.intent_list = model_dict['intent_list']
# Create the underlying SGD classifier
sgd_classifier = None
coeffs = model_dict['coeffs']
intercept = model_dict['intercept']
t_ = model_dict["t_"]
if coeffs is not None and intercept is not None:
sgd_classifier = SGDClassifier(**LOG_REG_ARGS)
sgd_classifier.coef_ = np.array(coeffs)
sgd_classifier.intercept_ = np.array(intercept)
sgd_classifier.t_ = t_
intent_classifier.classifier = sgd_classifier
# Add the featurizer
featurizer = model_dict['featurizer']
if featurizer is not None:
featurizer_path = path / featurizer
intent_classifier.featurizer = Featurizer.from_path(
featurizer_path, **shared)
return intent_classifier
def from_dict(cls, unit_dict):
"""Creates a :class:`LogRegIntentClassifier` instance from a dict
The dict must have been generated with
:func:`~LogRegIntentClassifier.to_dict`
"""
config = LogRegIntentClassifierConfig.from_dict(unit_dict["config"])
intent_classifier = cls(config=config)
sgd_classifier = None
coeffs = unit_dict['coeffs']
intercept = unit_dict['intercept']
t_ = unit_dict["t_"]
if coeffs is not None and intercept is not None:
sgd_classifier = SGDClassifier(**LOG_REG_ARGS)
sgd_classifier.coef_ = np.array(coeffs)
sgd_classifier.intercept_ = np.array(intercept)
sgd_classifier.t_ = t_
intent_classifier.classifier = sgd_classifier
intent_classifier.intent_list = unit_dict['intent_list']
featurizer = unit_dict['featurizer']
if featurizer is not None:
intent_classifier.featurizer = Featurizer.from_dict(featurizer)
return intent_classifier