def test_intializing_embeds_from_config(self):
feature_config = FeatureConfig(
word_feat=WordFeatConfig(
embedding_init_strategy=EmbedInitStrategy.RANDOM,
embed_dim=5,
pretrained_embeddings_path=tests_module.TEST_BASE_DIR,
)
)
data_handler = JointModelDataHandler.from_config(
JointModelDataHandler.Config(),
feature_config,
[DocLabelConfig(), WordLabelConfig()],
featurizer=SimpleFeaturizer.from_config(
SimpleFeaturizer.Config(), feature_config
),
)
data_handler.init_metadata_from_path(TRAIN_FILE, EVAL_FILE, TEST_FILE)
pretrained_embeds = data_handler.metadata.features[
DatasetFieldName.TEXT_FIELD
].pretrained_embeds_weight
# test random initialization (values should be non-0)
np.testing.assert_array_less(
[0, 0, 0, 0, 0], np.absolute(pretrained_embeds[11].numpy())
)
feature_config = FeatureConfig(
word_feat=WordFeatConfig(
embedding_init_strategy=EmbedInitStrategy.ZERO,
embed_dim=5,
pretrained_embeddings_path=tests_module.TEST_BASE_DIR,
)
)
data_handler = JointModelDataHandler.from_config(
JointModelDataHandler.Config(),
feature_config,
[DocLabelConfig(), WordLabelConfig()],
featurizer=SimpleFeaturizer.from_config(
SimpleFeaturizer.Config(), feature_config
),
)
data_handler.init_metadata_from_path(TRAIN_FILE, EVAL_FILE, TEST_FILE)
pretrained_embeds = data_handler.metadata.features[
DatasetFieldName.TEXT_FIELD
].pretrained_embeds_weight
# test zero initialization (values should all be 0)
np.testing.assert_array_equal([0, 0, 0, 0, 0], pretrained_embeds[11].numpy())
class Config(Task.Config):
model: SeqNNModel.Config = SeqNNModel.Config()
trainer: Trainer.Config = Trainer.Config()
labels: DocLabelConfig = DocLabelConfig()
data_handler: SeqModelDataHandler.Config = SeqModelDataHandler.Config()
metric_reporter: ClassificationMetricReporter.Config = (
ClassificationMetricReporter.Config())
def example_config(cls):
return cls.Config(
labels=[DocLabelConfig(), WordLabelConfig()],
model=BaggingDocEnsemble_Deprecated.Config(
models=[DocModel_Deprecated.Config()]
),
)
def setUp(self):
self.data_handler = JointModelDataHandler.from_config(
JointModelDataHandler.Config(),
FeatureConfig(),
[DocLabelConfig(), WordLabelConfig()],
featurizer=SimpleFeaturizer.from_config(SimpleFeaturizer.Config(),
FeatureConfig()),
)
class Config(Task_Deprecated.Config):
model: SeqNNModel_Deprecated.Config = SeqNNModel_Deprecated.Config()
trainer: Trainer.Config = Trainer.Config()
labels: DocLabelConfig = DocLabelConfig()
data_handler: SeqModelDataHandler.Config = SeqModelDataHandler.Config()
metric_reporter: ClassificationMetricReporter.Config = (
ClassificationMetricReporter.Config())
exporter: Optional[DenseFeatureExporter.Config] = None
def setUp(self):
file_name = tests_module.test_file(
"contextual_intent_slot_train_tiny.tsv")
self.dh = ContextualIntentSlotModelDataHandler.from_config(
ContextualIntentSlotModelDataHandler.Config(),
ModelInputConfig(),
[DocLabelConfig(), WordLabelConfig()],
featurizer=SimpleFeaturizer(SimpleFeaturizer.Config(),
ModelInputConfig()),
)
self.data = self.dh.read_from_file(file_name, self.dh.raw_columns)
def test_read_file_with_dense_features(self):
data_handler_config = ContextualIntentSlotModelDataHandler.Config()
data_handler_config.columns_to_read.append(ModelInput.DENSE)
dense_file_name = tests_module.test_file(
"contextual_intent_slot_train_tiny_dense.tsv")
data_handler = ContextualIntentSlotModelDataHandler.from_config(
data_handler_config,
ModelInputConfig(),
[DocLabelConfig(), WordLabelConfig()],
featurizer=SimpleFeaturizer(SimpleFeaturizer.Config(),
ModelInputConfig()),
)
dense_data = list(
data_handler.read_from_file(dense_file_name,
data_handler.raw_columns))
self.assertEqual(dense_data[0][ModelInput.DENSE], "[0,1,2,3,4]")
def setUp(self):
self.train_data = [{
DFColumn.DOC_LABEL:
"cu:discuss_where",
DFColumn.UTTERANCE:
'["where do you wanna meet?", "MPK"]',
}]
self.eval_data = [
{
DFColumn.DOC_LABEL: "cu:discuss_where",
DFColumn.UTTERANCE: '["how about SF?", "sounds good"]',
},
{
DFColumn.DOC_LABEL: "cu:other",
DFColumn.UTTERANCE: '["lol"]'
},
]
self.test_data = [
{
DFColumn.DOC_LABEL: "cu:discuss_where",
DFColumn.UTTERANCE: '["MPK sounds good to me"]',
},
{
DFColumn.DOC_LABEL: "cu:other",
DFColumn.UTTERANCE: '["great", "awesome"]',
},
]
self.dh = SeqModelDataHandler.from_config(
SeqModelDataHandler.Config(),
FeatureConfig(),
DocLabelConfig(),
featurizer=SimpleFeaturizer.from_config(SimpleFeaturizer.Config(),
FeatureConfig()),
)
def example_config(cls):
return cls.Config(labels=[DocLabelConfig(), WordLabelConfig()])