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())
def example_config(cls):
return cls.Config(
labels=[DocLabelConfig(), WordLabelConfig()],
model=BaggingDocEnsemble_Deprecated.Config(
models=[DocModel_Deprecated.Config()]
),
)
class Config(Task.Config):
model: WordTaggingModel.Config = WordTaggingModel.Config()
trainer: Trainer.Config = Trainer.Config()
labels: WordLabelConfig = WordLabelConfig()
data_handler: JointModelDataHandler.Config = JointModelDataHandler.Config(
)
metric_reporter: WordTaggingMetricReporter.Config = (
WordTaggingMetricReporter.Config())
def setUp(self):
self.data_handler = JointModelDataHandler.from_config(
JointModelDataHandler.Config(),
FeatureConfig(),
[DocLabelConfig(), WordLabelConfig()],
featurizer=SimpleFeaturizer.from_config(SimpleFeaturizer.Config(),
FeatureConfig()),
)
def _init_data_handler(self):
data_handler = LanguageModelDataHandler.from_config(
LanguageModelDataHandler.Config(),
FeatureConfig(),
WordLabelConfig(),
featurizer=create_featurizer(SimpleFeaturizer.Config(), FeatureConfig()),
shuffle=False,
)
data_handler.init_metadata_from_path(FILE_NAME, FILE_NAME, FILE_NAME)
return data_handler
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 test_data_handler(self):
data_handler = BPTTLanguageModelDataHandler.from_config(
BPTTLanguageModelDataHandler.Config(bptt_len=4),
FeatureConfig(),
WordLabelConfig(),
featurizer=SimpleFeaturizer.from_config(
SimpleFeaturizer.Config(), FeatureConfig()
),
)
data_handler.init_metadata_from_path(FILE_NAME, FILE_NAME, FILE_NAME)
train_iter = data_handler.get_train_iter_from_path(FILE_NAME, BATCH_SIZE)
batches = [t for t in train_iter]
# There are two batches in the tiny dataset
self.assertEqual(len(batches), 2)
# batches of tuple(input, target, context)
# input -> tuple(input_sequences, sequence_length)
# input_sequence -> tensor of dim (bsize, max_seq_length)
np.testing.assert_array_equal(
batches[0][0][0],
[[15, 19, 12, 16], [3, 13, 21, 8], [20, 7, 23, 4], [6, 5, 7, 22]],
)
# sequence_length -> tensor of dim (bsize)
np.testing.assert_array_equal(batches[0][0][1], [4, 4, 4, 4])
# target -> tensor of same dim as input_sequences (bsize, max_seq_length)
np.testing.assert_array_equal(
batches[0][1][0],
[[19, 12, 16, 14], [13, 21, 8, 3], [7, 23, 4, 3], [5, 7, 22, 10]],
)
np.testing.assert_array_equal(
batches[1][0][0], [[14, 17, 11], [3, 5, 18], [3, 8, 4], [10, 4, 9]]
)
np.testing.assert_array_equal(batches[1][0][1], [3, 3, 3, 3])
np.testing.assert_array_equal(
batches[1][1][0], [[17, 11, 4], [5, 18, 6], [8, 4, 3], [4, 9, 1]]
)
def example_config(cls):
return cls.Config(labels=[DocLabelConfig(), WordLabelConfig()])
