def test_should_be_deserializable_before_fit(self):
# Given
features_factories = [
{
"factory_name": ShapeNgramFactory.name,
"args": {"n": 1},
"offsets": [0]
},
{
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}
]
slot_filler_config = CRFSlotFillerConfig(
feature_factory_configs=features_factories)
slot_filler_dict = {
"unit_name": "crf_slot_filler",
"crf_model_file": None,
"language_code": None,
"intent": None,
"slot_name_mapping": None,
"config": slot_filler_config.to_dict()
}
metadata = {"unit_name": "crf_slot_filler"}
self.tmp_file_path.mkdir()
self.writeJsonContent(self.tmp_file_path / "metadata.json", metadata)
self.writeJsonContent(self.tmp_file_path / "slot_filler.json",
slot_filler_dict)
# When
slot_filler = CRFSlotFiller.from_path(self.tmp_file_path)
# Then
expected_features_factories = [
{
"factory_name": ShapeNgramFactory.name,
"args": {"n": 1},
"offsets": [0]
},
{
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}
]
expected_language = None
expected_config = CRFSlotFillerConfig(
feature_factory_configs=expected_features_factories)
expected_intent = None
expected_slot_name_mapping = None
expected_crf_model = None
self.assertEqual(slot_filler.crf_model, expected_crf_model)
self.assertEqual(slot_filler.language, expected_language)
self.assertEqual(slot_filler.intent, expected_intent)
self.assertEqual(slot_filler.slot_name_mapping,
expected_slot_name_mapping)
self.assertDictEqual(expected_config.to_dict(),
slot_filler.config.to_dict())
def test_should_be_deserializable_before_fit(self,
mock_deserialize_crf_model):
# Given
mock_deserialize_crf_model.return_value = None
features_factories = [
{
"factory_name": ShapeNgramFactory.name,
"args": {"n": 1},
"offsets": [0]
},
{
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}
]
slot_filler_config = CRFSlotFillerConfig(
feature_factory_configs=features_factories)
slot_filler_dict = {
"unit_name": "crf_slot_filler",
"crf_model_data": None,
"language_code": None,
"intent": None,
"slot_name_mapping": None,
"config": slot_filler_config.to_dict()
}
# When
slot_filler = CRFSlotFiller.from_dict(slot_filler_dict)
# Then
expected_features_factories = [
{
"factory_name": ShapeNgramFactory.name,
"args": {"n": 1},
"offsets": [0]
},
{
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}
]
expected_language = None
expected_config = CRFSlotFillerConfig(
feature_factory_configs=expected_features_factories)
expected_intent = None
expected_slot_name_mapping = None
expected_crf_model = None
self.assertEqual(slot_filler.crf_model, expected_crf_model)
self.assertEqual(slot_filler.language, expected_language)
self.assertEqual(slot_filler.intent, expected_intent)
self.assertEqual(slot_filler.slot_name_mapping,
expected_slot_name_mapping)
self.assertDictEqual(expected_config.to_dict(),
slot_filler.config.to_dict())
def test_should_be_serializable_before_fit(self):
# Given
features_factories = [{
"factory_name": ShapeNgramFactory.name,
"args": {
"n": 1
},
"offsets": [0]
}, {
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}]
config = CRFSlotFillerConfig(
tagging_scheme=TaggingScheme.BILOU,
feature_factory_configs=features_factories)
slot_filler = CRFSlotFiller(config)
# When
slot_filler.persist(self.tmp_file_path)
# Then
metadata_path = self.tmp_file_path / "metadata.json"
self.assertJsonContent(metadata_path, {"unit_name": "crf_slot_filler"})
expected_slot_filler_dict = {
"crf_model_file": None,
"language_code": None,
"config": config.to_dict(),
"intent": None,
"slot_name_mapping": None,
}
slot_filler_path = self.tmp_file_path / "slot_filler.json"
self.assertJsonContent(slot_filler_path, expected_slot_filler_dict)
def test_should_be_serializable_before_fit(self):
# Given
features_factories = [
{
"factory_name": ShapeNgramFactory.name,
"args": {"n": 1},
"offsets": [0]
},
{
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}
]
config = CRFSlotFillerConfig(
tagging_scheme=TaggingScheme.BILOU,
feature_factory_configs=features_factories)
slot_filler = CRFSlotFiller(config)
# When
actual_slot_filler_dict = slot_filler.to_dict()
# Then
expected_slot_filler_dict = {
"unit_name": "crf_slot_filler",
"crf_model_data": None,
"language_code": None,
"config": config.to_dict(),
"intent": None,
"slot_name_mapping": None,
}
self.assertDictEqual(actual_slot_filler_dict,
expected_slot_filler_dict)
def test_should_be_serializable(self):
# Given
features_factories = [{
"factory_name": ShapeNgramFactory.name,
"args": {
"n": 1
},
"offsets": [0]
}, {
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}]
config = CRFSlotFillerConfig(
tagging_scheme=TaggingScheme.BILOU,
feature_factory_configs=features_factories)
dataset = SAMPLE_DATASET
slot_filler = CRFSlotFiller(config)
intent = "dummy_intent_1"
slot_filler.fit(dataset, intent=intent)
# When
slot_filler.persist(self.tmp_file_path)
# Then
metadata_path = self.tmp_file_path / "metadata.json"
self.assertJsonContent(metadata_path, {"unit_name": "crf_slot_filler"})
expected_crf_file = Path(slot_filler.crf_model.modelfile.name).name
self.assertTrue((self.tmp_file_path / expected_crf_file).exists())
expected_feature_factories = [{
"factory_name": ShapeNgramFactory.name,
"args": {
"n": 1,
"language_code": "en"
},
"offsets": [0]
}, {
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}]
expected_config = CRFSlotFillerConfig(
tagging_scheme=TaggingScheme.BILOU,
feature_factory_configs=expected_feature_factories)
expected_slot_filler_dict = {
"crf_model_file": expected_crf_file,
"language_code": "en",
"config": expected_config.to_dict(),
"intent": intent,
"slot_name_mapping": {
"dummy_slot_name": "dummy_entity_1",
"dummy_slot_name2": "dummy_entity_2",
"dummy_slot_name3": "dummy_entity_2",
}
}
slot_filler_path = self.tmp_file_path / "slot_filler.json"
self.assertJsonContent(slot_filler_path, expected_slot_filler_dict)
def test_should_be_serializable(self, mock_serialize_crf_model):
# Given
mock_serialize_crf_model.return_value = "mocked_crf_model_data"
features_factories = [
{
"factory_name": ShapeNgramFactory.name,
"args": {"n": 1},
"offsets": [0]
},
{
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}
]
config = CRFSlotFillerConfig(
tagging_scheme=TaggingScheme.BILOU,
feature_factory_configs=features_factories)
dataset = validate_and_format_dataset(SAMPLE_DATASET)
slot_filler = CRFSlotFiller(config)
intent = "dummy_intent_1"
slot_filler.fit(dataset, intent=intent)
# When
actual_slot_filler_dict = slot_filler.to_dict()
# Then
expected_feature_factories = [
{
"factory_name": ShapeNgramFactory.name,
"args": {"n": 1, "language_code": "en"},
"offsets": [0]
},
{
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}
]
expected_config = CRFSlotFillerConfig(
tagging_scheme=TaggingScheme.BILOU,
feature_factory_configs=expected_feature_factories)
expected_slot_filler_dict = {
"unit_name": "crf_slot_filler",
"crf_model_data": "mocked_crf_model_data",
"language_code": "en",
"config": expected_config.to_dict(),
"intent": intent,
"slot_name_mapping": {
"dummy_slot_name": "dummy_entity_1",
"dummy_slot_name2": "dummy_entity_2",
"dummy_slot_name3": "dummy_entity_2",
}
}
self.assertDictEqual(actual_slot_filler_dict,
expected_slot_filler_dict)
def test_should_be_deserializable(self):
# Given
language = LANGUAGE_EN
feature_factories = [{
"factory_name": ShapeNgramFactory.name,
"args": {
"n": 1,
"language_code": language
},
"offsets": [0]
}, {
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}]
slot_filler_config = CRFSlotFillerConfig(
feature_factory_configs=feature_factories)
slot_filler_dict = {
"unit_name": "crf_slot_filler",
"crf_model_file": "foobar.crfsuite",
"language_code": "en",
"intent": "dummy_intent_1",
"slot_name_mapping": {
"dummy_intent_1": {
"dummy_slot_name": "dummy_entity_1",
}
},
"config": slot_filler_config.to_dict()
}
metadata = {"unit_name": "crf_slot_filler"}
self.tmp_file_path.mkdir()
self.writeJsonContent(self.tmp_file_path / "metadata.json", metadata)
self.writeJsonContent(self.tmp_file_path / "slot_filler.json",
slot_filler_dict)
self.writeFileContent(self.tmp_file_path / "foobar.crfsuite",
"foo bar")
# When
slot_filler = CRFSlotFiller.from_path(self.tmp_file_path)
# Then
expected_language = LANGUAGE_EN
expected_feature_factories = [{
"factory_name": ShapeNgramFactory.name,
"args": {
"n": 1,
"language_code": language
},
"offsets": [0]
}, {
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}]
expected_config = CRFSlotFillerConfig(
feature_factory_configs=expected_feature_factories)
expected_intent = "dummy_intent_1"
expected_slot_name_mapping = {
"dummy_intent_1": {
"dummy_slot_name": "dummy_entity_1",
}
}
self.assertEqual(slot_filler.language, expected_language)
self.assertEqual(slot_filler.intent, expected_intent)
self.assertEqual(slot_filler.slot_name_mapping,
expected_slot_name_mapping)
self.assertDictEqual(expected_config.to_dict(),
slot_filler.config.to_dict())
crf_path = Path(slot_filler.crf_model.modelfile.name)
self.assertFileContent(crf_path, "foo bar")
def test_should_be_serializable(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: my_intent
utterances:
- this is [slot1:entity1](my first entity)
- this is [slot2:entity2](second_entity)""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
features_factories = [{
"factory_name": ShapeNgramFactory.name,
"args": {
"n": 1
},
"offsets": [0]
}, {
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}]
config = CRFSlotFillerConfig(
tagging_scheme=TaggingScheme.BILOU,
feature_factory_configs=features_factories)
shared = self.get_shared_data(dataset)
slot_filler = CRFSlotFiller(config, **shared)
intent = "my_intent"
slot_filler.fit(dataset, intent=intent)
# When
slot_filler.persist(self.tmp_file_path)
# Then
metadata_path = self.tmp_file_path / "metadata.json"
self.assertJsonContent(metadata_path, {"unit_name": "crf_slot_filler"})
self.assertTrue((self.tmp_file_path / CRF_MODEL_FILENAME).exists())
expected_feature_factories = [{
"factory_name": ShapeNgramFactory.name,
"args": {
"n": 1,
"language_code": "en"
},
"offsets": [0]
}, {
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}]
expected_config = CRFSlotFillerConfig(
tagging_scheme=TaggingScheme.BILOU,
feature_factory_configs=expected_feature_factories)
expected_slot_filler_dict = {
"crf_model_file": CRF_MODEL_FILENAME,
"language_code": "en",
"config": expected_config.to_dict(),
"intent": intent,
"slot_name_mapping": {
"slot1": "entity1",
"slot2": "entity2",
}
}
slot_filler_path = self.tmp_file_path / "slot_filler.json"
self.assertJsonContent(slot_filler_path, expected_slot_filler_dict)
def test_should_be_deserializable(self, mock_deserialize_crf_model):
# Given
language = LANGUAGE_EN
mock_deserialize_crf_model.return_value = None
feature_factories = [
{
"factory_name": ShapeNgramFactory.name,
"args": {"n": 1, "language_code": language},
"offsets": [0]
},
{
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}
]
slot_filler_config = CRFSlotFillerConfig(
feature_factory_configs=feature_factories)
slot_filler_dict = {
"unit_name": "crf_slot_filler",
"crf_model_data": "mocked_crf_model_data",
"language_code": "en",
"intent": "dummy_intent_1",
"slot_name_mapping": {
"dummy_intent_1": {
"dummy_slot_name": "dummy_entity_1",
}
},
"config": slot_filler_config.to_dict()
}
# When
slot_filler = CRFSlotFiller.from_dict(slot_filler_dict)
# Then
mock_deserialize_crf_model.assert_called_once_with(
"mocked_crf_model_data")
expected_language = LANGUAGE_EN
expected_feature_factories = [
{
"factory_name": ShapeNgramFactory.name,
"args": {"n": 1, "language_code": language},
"offsets": [0]
},
{
"factory_name": IsDigitFactory.name,
"args": {},
"offsets": [-1, 0]
}
]
expected_config = CRFSlotFillerConfig(
feature_factory_configs=expected_feature_factories)
expected_intent = "dummy_intent_1"
expected_slot_name_mapping = {
"dummy_intent_1": {
"dummy_slot_name": "dummy_entity_1",
}
}
self.assertEqual(slot_filler.language, expected_language)
self.assertEqual(slot_filler.intent, expected_intent)
self.assertEqual(slot_filler.slot_name_mapping,
expected_slot_name_mapping)
self.assertDictEqual(expected_config.to_dict(),
slot_filler.config.to_dict())