def test_nlu_engine_should_raise_error_with_bytes_input(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: MakeTea
utterances:
- make me a [beverage_temperature:Temperature](hot) cup of tea
- make me [number_of_cups:snips/number](five) tea cups
---
type: intent
name: MakeCoffee
utterances:
- make me [number_of_cups:snips/number](one) cup of coffee please
- brew [number_of_cups] cups of coffee""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
bytes_input = b"brew me an espresso"
# pylint:disable=unused-variable
@IntentParser.register("my_intent_parser", True)
class MyIntentParser(MockIntentParser):
pass
# pylint:enable=unused-variable
config = NLUEngineConfig(["my_intent_parser"])
engine = SnipsNLUEngine(config).fit(dataset)
# When / Then
with self.assertRaises(InvalidInputError) as cm:
engine.parse(bytes_input)
message = str(cm.exception.args[0])
self.assertTrue("Expected unicode but received" in message)
def test_should_fit_and_parse_empty_intent(self):
# Given
dataset = {
"intents": {
"dummy_intent": {
"utterances": [
{
"data": [
{
"text": " "
}
]
}
]
}
},
"language": "en",
"entities": dict()
}
engine = SnipsNLUEngine()
# When / Then
engine.fit(dataset)
engine.parse("ya", intents=["dummy_intent"])
def test_should_not_parse_slots_when_not_fitted(self):
# Given
engine = SnipsNLUEngine()
# When / Then
self.assertFalse(engine.fitted)
with self.assertRaises(NotTrained):
engine.parse("foobar")
def test_nlu_engine_should_raise_error_with_bytes_input(self):
# Given
bytes_input = b"brew me an espresso"
engine = SnipsNLUEngine().fit(BEVERAGE_DATASET)
# When / Then
with self.assertRaises(TypeError) as cm:
engine.parse(bytes_input)
message = str(cm.exception.args[0])
self.assertTrue("Expected unicode but received" in message)
def test_nlu_engine_should_raise_error_with_bytes_input(self):
# Given
bytes_input = b"brew me an espresso"
engine = SnipsNLUEngine().fit(BEVERAGE_DATASET)
# When / Then
with self.assertRaises(TypeError) as cm:
engine.parse(bytes_input)
message = str(cm.exception.args[0])
self.assertTrue("Expected unicode but received" in message)
def test_nlu_engine_should_train_and_parse_in_all_languages(self):
# Given
text = "brew me an espresso"
for language in get_all_languages():
dataset = deepcopy(BEVERAGE_DATASET)
dataset[LANGUAGE] = language
engine = SnipsNLUEngine()
# When / Then
msg = "Could not fit engine in '%s'" % language
with self.fail_if_exception(msg):
engine = engine.fit(dataset)
msg = "Could not parse in '%s'" % language
with self.fail_if_exception(msg):
engine.parse(text)
def test_nlu_engine_should_train_and_parse_in_all_languages(self):
# Given
text = "brew me an espresso"
for language in get_all_languages():
dataset = deepcopy(BEVERAGE_DATASET)
dataset[LANGUAGE] = language
engine = SnipsNLUEngine()
# When / Then
msg = "Could not fit engine in '%s'" % language
with self.fail_if_exception(msg):
engine = engine.fit(dataset)
msg = "Could not parse in '%s'" % language
with self.fail_if_exception(msg):
engine.parse(text)
def test_nlu_engine_should_train_and_parse_in_all_languages(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: MakeTea
utterances:
- make me a [beverage_temperature:Temperature](hot) cup of tea
- make me [number_of_cups:snips/number](five) tea cups
- i want [number_of_cups] cups of [beverage_temperature](boiling hot) tea pls
- can you prepare [number_of_cups] cup of [beverage_temperature](cold) tea ?
---
type: intent
name: MakeCoffee
utterances:
- make me [number_of_cups:snips/number](one) cup of coffee please
- brew [number_of_cups] cups of coffee
- can you prepare [number_of_cups] cup of coffee""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
text = "please brew me a cup of coffee"
for language in get_all_languages():
dataset[LANGUAGE] = language
engine = SnipsNLUEngine()
# When / Then
msg = "Could not fit engine in '%s'" % language
with self.fail_if_exception(msg):
engine = engine.fit(dataset)
msg = "Could not parse in '%s'" % language
with self.fail_if_exception(msg):
res = engine.parse(text)
self.assertEqual("MakeCoffee", res[RES_INTENT][RES_INTENT_NAME])
def test_should_handle_empty_dataset(self):
# Given
dataset = validate_and_format_dataset(get_empty_dataset(LANGUAGE_EN))
engine = SnipsNLUEngine().fit(dataset)
# When
result = engine.parse("hello world")
# Then
self.assertEqual(empty_result("hello world"), result)
def test_should_handle_empty_dataset(self):
# Given
dataset = validate_and_format_dataset(get_empty_dataset(LANGUAGE_EN))
engine = SnipsNLUEngine().fit(dataset)
# When
result = engine.parse("hello world")
# Then
self.assertEqual(empty_result("hello world"), result)
def test_should_handle_empty_dataset(self):
# Given
dataset = get_empty_dataset(LANGUAGE_EN)
shared = self.get_shared_data(dataset)
engine = SnipsNLUEngine(**shared).fit(dataset)
# When
result = engine.parse("hello world")
# Then
self.assertEqual(empty_result("hello world", 1.0), result)
def test_should_use_parsers_sequentially(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: greeting1
utterances:
- hello [greeted:name](john)""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
input_text = "hello snips"
intent = intent_classification_result(intent_name='greeting1',
probability=0.7)
slots = [
unresolved_slot(match_range=(6, 11),
value='snips',
entity='name',
slot_name='greeted')
]
# pylint:disable=unused-variable
@IntentParser.register("first_intent_parser", True)
class FirstIntentParser(MockIntentParser):
pass
@IntentParser.register("second_intent_parser", True)
class SecondIntentParser(MockIntentParser):
def parse(self, text, intents=None, top_n=None):
if text == input_text:
return parsing_result(text, intent, slots)
return empty_result(text, 1.0)
# pylint:enable=unused-variable
config = NLUEngineConfig(
["first_intent_parser", "second_intent_parser"])
engine = SnipsNLUEngine(config).fit(dataset)
# When
parse = engine.parse(input_text)
# Then
expected_slots = [custom_slot(s) for s in slots]
expected_parse = parsing_result(input_text, intent, expected_slots)
self.assertDictEqual(expected_parse, parse)
def test_should_use_parsers_sequentially(self):
# Given
input_text = "hello world"
intent = intent_classification_result(intent_name='dummy_intent_1',
probability=0.7)
slots = [
unresolved_slot(match_range=(6, 11),
value='world',
entity='mocked_entity',
slot_name='mocked_slot_name')
]
class TestIntentParser1Config(ProcessingUnitConfig):
unit_name = "test_intent_parser1"
def to_dict(self):
return {"unit_name": self.unit_name}
@classmethod
def from_dict(cls, obj_dict):
return TestIntentParser1Config()
class TestIntentParser1(IntentParser):
unit_name = "test_intent_parser1"
config_type = TestIntentParser1Config
def fit(self, dataset, force_retrain):
self._fitted = True
return self
@property
def fitted(self):
return hasattr(self, '_fitted') and self._fitted
def parse(self, text, intents):
return empty_result(text)
def to_dict(self):
return {
"unit_name": self.unit_name,
}
@classmethod
def from_dict(cls, unit_dict):
conf = cls.config_type()
return TestIntentParser1(conf)
class TestIntentParser2Config(ProcessingUnitConfig):
unit_name = "test_intent_parser2"
def to_dict(self):
return {"unit_name": self.unit_name}
@classmethod
def from_dict(cls, obj_dict):
return TestIntentParser2Config()
class TestIntentParser2(IntentParser):
unit_name = "test_intent_parser2"
config_type = TestIntentParser2Config
def fit(self, dataset, force_retrain):
self._fitted = True
return self
@property
def fitted(self):
return hasattr(self, '_fitted') and self._fitted
def parse(self, text, intents):
if text == input_text:
return parsing_result(text, intent, slots)
return empty_result(text)
def to_dict(self):
return {
"unit_name": self.unit_name,
}
@classmethod
def from_dict(cls, unit_dict):
conf = cls.config_type()
return TestIntentParser2(conf)
register_processing_unit(TestIntentParser1)
register_processing_unit(TestIntentParser2)
mocked_dataset_metadata = {
"language_code": "en",
"entities": {
"mocked_entity": {
"automatically_extensible": True,
"utterances": dict()
}
},
"slot_name_mappings": {
"dummy_intent_1": {
"mocked_slot_name": "mocked_entity"
}
}
}
config = NLUEngineConfig(
[TestIntentParser1Config(),
TestIntentParser2Config()])
engine = SnipsNLUEngine(config).fit(SAMPLE_DATASET)
# pylint:disable=protected-access
engine._dataset_metadata = mocked_dataset_metadata
# pylint:enable=protected-access
# When
parse = engine.parse(input_text)
# Then
expected_slots = [custom_slot(s) for s in slots]
expected_parse = parsing_result(input_text, intent, expected_slots)
self.assertDictEqual(expected_parse, parse)
def test_synonyms_should_point_to_base_value(self):
# Given
dataset = {
"intents": {
"dummy_intent_1": {
"utterances": [
{
"data": [
{
"text": "dummy_1",
"entity": "dummy_entity_1",
"slot_name": "dummy_slot_name"
}
]
}
]
}
},
"entities": {
"dummy_entity_1": {
"use_synonyms": True,
"automatically_extensible": False,
"data": [
{
"value": "dummy1",
"synonyms": [
"dummy1",
"dummy1_bis"
]
}
],
"matching_strictness": 1.0
}
},
"language": "en"
}
mocked_intent = intent_classification_result("dummy_intent_1", 1.0)
mocked_slots = [
unresolved_slot(match_range=(0, 10), value="dummy1_bis",
entity="dummy_entity_1",
slot_name="dummy_slot_name")]
# pylint:disable=unused-variable
@IntentParser.register("my_intent_parser", True)
class MyIntentParser(MockIntentParser):
def parse(self, text, intents=None, top_n=None):
return parsing_result(text, mocked_intent, mocked_slots)
# pylint:enable=unused-variable
input_ = "dummy1_bis"
config = NLUEngineConfig(["my_intent_parser"])
engine = SnipsNLUEngine(config).fit(dataset)
# When
result = engine.parse(input_)
# Then
expected_slot = {
RES_MATCH_RANGE: {
"start": 0,
"end": 10
},
RES_RAW_VALUE: "dummy1_bis",
RES_VALUE: {
"kind": "Custom",
"value": "dummy1"
},
RES_ENTITY: "dummy_entity_1",
RES_SLOT_NAME: "dummy_slot_name"
}
expected_result = parsing_result(
input_, mocked_intent, slots=[expected_slot])
self.assertEqual(expected_result, result)
def test_should_use_parsers_sequentially(self):
# Given
input_text = "hello world"
intent = intent_classification_result(
intent_name='dummy_intent_1', probability=0.7)
slots = [unresolved_slot(match_range=(6, 11),
value='world',
entity='mocked_entity',
slot_name='mocked_slot_name')]
class TestIntentParser1Config(ProcessingUnitConfig):
unit_name = "test_intent_parser1"
def to_dict(self):
return {"unit_name": self.unit_name}
@classmethod
def from_dict(cls, obj_dict):
return TestIntentParser1Config()
class TestIntentParser1(IntentParser):
unit_name = "test_intent_parser1"
config_type = TestIntentParser1Config
def fit(self, dataset, force_retrain):
self._fitted = True
return self
@property
def fitted(self):
return hasattr(self, '_fitted') and self._fitted
def parse(self, text, intents):
return empty_result(text)
def to_dict(self):
return {
"unit_name": self.unit_name,
}
@classmethod
def from_dict(cls, unit_dict):
conf = cls.config_type()
return TestIntentParser1(conf)
class TestIntentParser2Config(ProcessingUnitConfig):
unit_name = "test_intent_parser2"
def to_dict(self):
return {"unit_name": self.unit_name}
@classmethod
def from_dict(cls, obj_dict):
return TestIntentParser2Config()
class TestIntentParser2(IntentParser):
unit_name = "test_intent_parser2"
config_type = TestIntentParser2Config
def fit(self, dataset, force_retrain):
self._fitted = True
return self
@property
def fitted(self):
return hasattr(self, '_fitted') and self._fitted
def parse(self, text, intents):
if text == input_text:
return parsing_result(text, intent, slots)
return empty_result(text)
def to_dict(self):
return {
"unit_name": self.unit_name,
}
@classmethod
def from_dict(cls, unit_dict):
conf = cls.config_type()
return TestIntentParser2(conf)
register_processing_unit(TestIntentParser1)
register_processing_unit(TestIntentParser2)
mocked_dataset_metadata = {
"language_code": "en",
"entities": {
"mocked_entity": {
"automatically_extensible": True,
"utterances": dict()
}
},
"slot_name_mappings": {
"dummy_intent_1": {
"mocked_slot_name": "mocked_entity"
}
}
}
config = NLUEngineConfig([TestIntentParser1Config(),
TestIntentParser2Config()])
engine = SnipsNLUEngine(config).fit(SAMPLE_DATASET)
# pylint:disable=protected-access
engine._dataset_metadata = mocked_dataset_metadata
# pylint:enable=protected-access
# When
parse = engine.parse(input_text)
# Then
expected_slots = [custom_slot(s) for s in slots]
expected_parse = parsing_result(input_text, intent, expected_slots)
self.assertDictEqual(expected_parse, parse)
def test_synonyms_should_not_collide_when_remapped_to_base_value(
self, mocked_proba_parse):
# Given
# Given
dataset = {
"intents": {
"intent1": {
"utterances": [{
"data": [{
"text": "value",
"entity": "entity1",
"slot_name": "slot1"
}]
}]
}
},
"entities": {
"entity1": {
"data": [{
"value": "a",
"synonyms": ["favorïte"]
}, {
"value": "b",
"synonyms": ["favorite"]
}],
"use_synonyms":
True,
"automatically_extensible":
False
}
},
"language": "en",
}
mocked_proba_parser_intent = intent_classification_result(
"intent1", 1.0)
def mock_proba_parse(text, intents):
slots = [
unresolved_slot(match_range=(0, len(text)),
value=text,
entity="entity1",
slot_name="slot1")
]
return parsing_result(text, mocked_proba_parser_intent, slots)
mocked_proba_parse.side_effect = mock_proba_parse
config = NLUEngineConfig([ProbabilisticIntentParserConfig()])
engine = SnipsNLUEngine(config).fit(dataset)
# When
result1 = engine.parse("favorite")
result2 = engine.parse("favorïte")
# Then
expected_slot1 = {
RES_MATCH_RANGE: {
"start": 0,
"end": 8
},
RES_RAW_VALUE: "favorite",
RES_VALUE: {
"kind": "Custom",
"value": "b"
},
RES_ENTITY: "entity1",
RES_SLOT_NAME: "slot1"
}
expected_slot2 = {
RES_MATCH_RANGE: {
"start": 0,
"end": 8
},
RES_RAW_VALUE: "favorïte",
RES_VALUE: {
"kind": "Custom",
"value": "a"
},
RES_ENTITY: "entity1",
RES_SLOT_NAME: "slot1"
}
expected_result1 = parsing_result("favorite",
intent=mocked_proba_parser_intent,
slots=[expected_slot1])
expected_result2 = parsing_result("favorïte",
intent=mocked_proba_parser_intent,
slots=[expected_slot2])
self.assertEqual(expected_result1, result1)
self.assertEqual(expected_result2, result2)
def test_should_use_parsers_sequentially(self):
# Given
input_text = "hello world"
intent = intent_classification_result(intent_name='dummy_intent_1',
probability=0.7)
slots = [
unresolved_slot(match_range=(6, 11),
value='world',
entity='mocked_entity',
slot_name='mocked_slot_name')
]
class FirstIntentParserConfig(ProcessingUnitConfig):
unit_name = "first_intent_parser"
def to_dict(self):
return {"unit_name": self.unit_name}
@classmethod
def from_dict(cls, obj_dict):
return FirstIntentParserConfig()
def get_required_resources(self):
return None
class FirstIntentParser(IntentParser):
unit_name = "first_intent_parser"
config_type = FirstIntentParserConfig
def fit(self, dataset, force_retrain):
self._fitted = True
return self
@property
def fitted(self):
return hasattr(self, '_fitted') and self._fitted
def parse(self, text, intents):
return empty_result(text)
def persist(self, path):
path = Path(path)
path.mkdir()
with (path / "metadata.json").open(mode="w") as f:
f.write(json_string({"unit_name": self.unit_name}))
@classmethod
def from_path(cls, path):
cfg = cls.config_type()
return cls(cfg)
class SecondIntentParserConfig(ProcessingUnitConfig):
unit_name = "second_intent_parser"
def to_dict(self):
return {"unit_name": self.unit_name}
@classmethod
def from_dict(cls, obj_dict):
return SecondIntentParserConfig()
def get_required_resources(self):
return None
class SecondIntentParser(IntentParser):
unit_name = "second_intent_parser"
config_type = SecondIntentParserConfig
def fit(self, dataset, force_retrain):
self._fitted = True
return self
@property
def fitted(self):
return hasattr(self, '_fitted') and self._fitted
def parse(self, text, intents):
if text == input_text:
return parsing_result(text, intent, slots)
return empty_result(text)
def persist(self, path):
path = Path(path)
path.mkdir()
with (path / "metadata.json").open(mode="w") as f:
f.write(json_string({"unit_name": self.unit_name}))
@classmethod
def from_path(cls, path):
cfg = cls.config_type()
return cls(cfg)
register_processing_unit(FirstIntentParser)
register_processing_unit(SecondIntentParser)
mocked_dataset_metadata = {
"language_code": "en",
"entities": {
"mocked_entity": {
"automatically_extensible": True,
"utterances": dict()
}
},
"slot_name_mappings": {
"dummy_intent_1": {
"mocked_slot_name": "mocked_entity"
}
}
}
config = NLUEngineConfig(
[FirstIntentParserConfig(),
SecondIntentParserConfig()])
engine = SnipsNLUEngine(config).fit(SAMPLE_DATASET)
# pylint:disable=protected-access
engine._dataset_metadata = mocked_dataset_metadata
# pylint:enable=protected-access
# When
parse = engine.parse(input_text)
# Then
expected_slots = [custom_slot(s) for s in slots]
expected_parse = parsing_result(input_text, intent, expected_slots)
self.assertDictEqual(expected_parse, parse)
def test_should_handle_keyword_entities(self, mocked_regex_parse,
mocked_crf_parse):
# Given
dataset = {
"snips_nlu_version": "1.1.1",
"intents": {
"dummy_intent_1": {
"utterances": [
{
"data": [
{
"text": "dummy_1",
"entity": "dummy_entity_1",
"slot_name": "dummy_slot_name"
},
{
"text": " dummy_2",
"entity": "dummy_entity_2",
"slot_name": "other_dummy_slot_name"
}
]
}
]
}
},
"entities": {
"dummy_entity_1": {
"use_synonyms": True,
"automatically_extensible": False,
"data": [
{
"value": "dummy1",
"synonyms": [
"dummy1",
"dummy1_bis"
]
},
{
"value": "dummy2",
"synonyms": [
"dummy2",
"dummy2_bis"
]
}
]
},
"dummy_entity_2": {
"use_synonyms": False,
"automatically_extensible": True,
"data": [
{
"value": "dummy2",
"synonyms": [
"dummy2"
]
}
]
}
},
"language": "en"
}
text = "dummy_3 dummy_4"
mocked_crf_intent = intent_classification_result("dummy_intent_1", 1.0)
mocked_crf_slots = [unresolved_slot(match_range=(0, 7),
value="dummy_3",
entity="dummy_entity_1",
slot_name="dummy_slot_name"),
unresolved_slot(match_range=(8, 15),
value="dummy_4",
entity="dummy_entity_2",
slot_name="other_dummy_slot_name")]
mocked_regex_parse.return_value = empty_result(text)
mocked_crf_parse.return_value = parsing_result(
text, mocked_crf_intent, mocked_crf_slots)
engine = SnipsNLUEngine()
# When
engine = engine.fit(dataset)
result = engine.parse(text)
# Then
expected_slot = custom_slot(unresolved_slot(
match_range=(8, 15), value="dummy_4", entity="dummy_entity_2",
slot_name="other_dummy_slot_name"))
expected_result = parsing_result(text, intent=mocked_crf_intent,
slots=[expected_slot])
self.assertEqual(expected_result, result)
def test_should_handle_keyword_entities(self, mocked_regex_parse,
mocked_crf_parse):
# Given
dataset = {
"snips_nlu_version": "1.1.1",
"intents": {
"dummy_intent_1": {
"utterances": [{
"data": [{
"text": "dummy_1",
"entity": "dummy_entity_1",
"slot_name": "dummy_slot_name"
}, {
"text": " dummy_2",
"entity": "dummy_entity_2",
"slot_name": "other_dummy_slot_name"
}]
}]
}
},
"entities": {
"dummy_entity_1": {
"use_synonyms":
True,
"automatically_extensible":
False,
"data": [{
"value": "dummy1",
"synonyms": ["dummy1", "dummy1_bis"]
}, {
"value": "dummy2",
"synonyms": ["dummy2", "dummy2_bis"]
}]
},
"dummy_entity_2": {
"use_synonyms": False,
"automatically_extensible": True,
"data": [{
"value": "dummy2",
"synonyms": ["dummy2"]
}]
}
},
"language": "en"
}
text = "dummy_3 dummy_4"
mocked_crf_intent = intent_classification_result("dummy_intent_1", 1.0)
mocked_crf_slots = [
unresolved_slot(match_range=(0, 7),
value="dummy_3",
entity="dummy_entity_1",
slot_name="dummy_slot_name"),
unresolved_slot(match_range=(8, 15),
value="dummy_4",
entity="dummy_entity_2",
slot_name="other_dummy_slot_name")
]
mocked_regex_parse.return_value = empty_result(text)
mocked_crf_parse.return_value = parsing_result(text, mocked_crf_intent,
mocked_crf_slots)
engine = SnipsNLUEngine()
# When
engine = engine.fit(dataset)
result = engine.parse(text)
# Then
expected_slot = custom_slot(
unresolved_slot(match_range=(8, 15),
value="dummy_4",
entity="dummy_entity_2",
slot_name="other_dummy_slot_name"))
expected_result = parsing_result(text,
intent=mocked_crf_intent,
slots=[expected_slot])
self.assertEqual(expected_result, result)
def test_synonyms_should_point_to_base_value(self, mocked_deter_parse,
mocked_proba_parse):
# Given
dataset = {
"snips_nlu_version": "1.1.1",
"intents": {
"dummy_intent_1": {
"utterances": [{
"data": [{
"text": "dummy_1",
"entity": "dummy_entity_1",
"slot_name": "dummy_slot_name"
}]
}]
}
},
"entities": {
"dummy_entity_1": {
"use_synonyms":
True,
"automatically_extensible":
False,
"data": [{
"value": "dummy1",
"synonyms": ["dummy1", "dummy1_bis"]
}]
}
},
"language": "en"
}
text = "dummy1_bis"
mocked_proba_parser_intent = intent_classification_result(
"dummy_intent_1", 1.0)
mocked_proba_parser_slots = [
unresolved_slot(match_range=(0, 10),
value="dummy1_bis",
entity="dummy_entity_1",
slot_name="dummy_slot_name")
]
mocked_deter_parse.return_value = empty_result(text)
mocked_proba_parse.return_value = parsing_result(
text, mocked_proba_parser_intent, mocked_proba_parser_slots)
engine = SnipsNLUEngine().fit(dataset)
# When
result = engine.parse(text)
# Then
expected_slot = {
RES_MATCH_RANGE: {
"start": 0,
"end": 10
},
RES_RAW_VALUE: "dummy1_bis",
RES_VALUE: {
"kind": "Custom",
"value": "dummy1"
},
RES_ENTITY: "dummy_entity_1",
RES_SLOT_NAME: "dummy_slot_name"
}
expected_result = parsing_result(text,
intent=mocked_proba_parser_intent,
slots=[expected_slot])
self.assertEqual(expected_result, result)
def test_should_parse_top_intents(self):
# Given
text = "foo bar ban"
dataset_stream = io.StringIO("""
---
type: intent
name: intent1
utterances:
- foo [slot1:entity1](bak)
---
type: intent
name: intent2
utterances:
- '[slot2:entity2](foo) baz'
---
type: intent
name: intent3
utterances:
- foo bap""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
# pylint:disable=unused-variable
@IntentParser.register("first_intent_parser", True)
class FirstIntentParser(MockIntentParser):
def get_intents(self, text):
return [
intent_classification_result("intent1", 0.5),
intent_classification_result("intent2", 0.3),
intent_classification_result(None, 0.15),
intent_classification_result("intent3", 0.05)
]
def get_slots(self, text, intent):
if intent == "intent1":
return []
if intent == "intent2":
return [
unresolved_slot((0, 3), "foo", "entity2", "slot2")
]
return []
@IntentParser.register("second_intent_parser", True)
class SecondIntentParser(MockIntentParser):
def get_intents(self, text):
return [
intent_classification_result("intent2", 0.6),
intent_classification_result("intent1", 0.2),
intent_classification_result(None, 0.15),
intent_classification_result("intent3", 0.05)
]
def get_slots(self, text, intent):
if intent == "intent1":
return [
unresolved_slot((0, 3), "foo", "entity1", "slot1")
]
if intent == "intent2":
return [
unresolved_slot((8, 11), "ban", "entity2", "slot2")
]
return []
# pylint:enable=unused-variable
config = NLUEngineConfig(
["first_intent_parser", "second_intent_parser"])
nlu_engine = SnipsNLUEngine(config).fit(dataset)
# When
results = nlu_engine.parse(text, top_n=3)
results_with_filter = nlu_engine.parse(
text, intents=["intent1", "intent3"], top_n=3)
# Then
expected_results = [
extraction_result(
intent_classification_result("intent2", 0.6),
[custom_slot(
unresolved_slot((0, 3), "foo", "entity2", "slot2"))]
),
extraction_result(
intent_classification_result("intent1", 0.5),
[custom_slot(
unresolved_slot((0, 3), "foo", "entity1", "slot1"))]
),
extraction_result(
intent_classification_result(None, 0.15),
[]
),
]
expected_results_with_filter = [
extraction_result(
intent_classification_result("intent1", 0.5),
[custom_slot(
unresolved_slot((0, 3), "foo", "entity1", "slot1"))]
),
extraction_result(
intent_classification_result(None, 0.15),
[]
),
extraction_result(
intent_classification_result("intent3", 0.05),
[]
),
]
self.assertListEqual(expected_results, results)
self.assertListEqual(expected_results_with_filter, results_with_filter)
def test_synonyms_should_not_collide_when_remapped_to_base_value(self):
# Given
dataset = {
"intents": {
"intent1": {
"utterances": [
{
"data": [
{
"text": "value",
"entity": "entity1",
"slot_name": "slot1"
}
]
}
]
}
},
"entities": {
"entity1": {
"data": [
{
"value": "a",
"synonyms": [
"favorïte"
]
},
{
"value": "b",
"synonyms": [
"favorite"
]
}
],
"use_synonyms": True,
"automatically_extensible": False,
"matching_strictness": 1.0
}
},
"language": "en",
}
mocked_intent = intent_classification_result("intent1", 1.0)
# pylint:disable=unused-variable
@IntentParser.register("my_intent_parser", True)
class MyIntentParser(MockIntentParser):
def parse(self, text, intents=None, top_n=None):
slots = [
unresolved_slot(match_range=(0, len(text)), value=text,
entity="entity1", slot_name="slot1")]
return parsing_result(text, mocked_intent, slots)
# pylint:enable=unused-variable
config = NLUEngineConfig(["my_intent_parser"])
engine = SnipsNLUEngine(config).fit(dataset)
# When
result1 = engine.parse("favorite")
result2 = engine.parse("favorïte")
# Then
expected_slot1 = {
RES_MATCH_RANGE: {
"start": 0,
"end": 8
},
RES_RAW_VALUE: "favorite",
RES_VALUE: {
"kind": "Custom",
"value": "b"
},
RES_ENTITY: "entity1",
RES_SLOT_NAME: "slot1"
}
expected_slot2 = {
RES_MATCH_RANGE: {
"start": 0,
"end": 8
},
RES_RAW_VALUE: "favorïte",
RES_VALUE: {
"kind": "Custom",
"value": "a"
},
RES_ENTITY: "entity1",
RES_SLOT_NAME: "slot1"
}
expected_result1 = parsing_result("favorite", intent=mocked_intent,
slots=[expected_slot1])
expected_result2 = parsing_result("favorïte", intent=mocked_intent,
slots=[expected_slot2])
self.assertEqual(expected_result1, result1)
self.assertEqual(expected_result2, result2)
def test_synonyms_should_point_to_base_value(self, mocked_deter_parse,
mocked_proba_parse):
# Given
dataset = {
"snips_nlu_version": "1.1.1",
"intents": {
"dummy_intent_1": {
"utterances": [
{
"data": [
{
"text": "dummy_1",
"entity": "dummy_entity_1",
"slot_name": "dummy_slot_name"
}
]
}
]
}
},
"entities": {
"dummy_entity_1": {
"use_synonyms": True,
"automatically_extensible": False,
"data": [
{
"value": "dummy1",
"synonyms": [
"dummy1",
"dummy1_bis"
]
}
]
}
},
"language": "en"
}
text = "dummy1_bis"
mocked_proba_parser_intent = intent_classification_result(
"dummy_intent_1", 1.0)
mocked_proba_parser_slots = [
unresolved_slot(match_range=(0, 10), value="dummy1_bis",
entity="dummy_entity_1",
slot_name="dummy_slot_name")]
mocked_deter_parse.return_value = empty_result(text)
mocked_proba_parse.return_value = parsing_result(
text, mocked_proba_parser_intent, mocked_proba_parser_slots)
engine = SnipsNLUEngine().fit(dataset)
# When
result = engine.parse(text)
# Then
expected_slot = {
RES_MATCH_RANGE: {
"start": 0,
"end": 10
},
RES_RAW_VALUE: "dummy1_bis",
RES_VALUE: {
"kind": "Custom",
"value": "dummy1"
},
RES_ENTITY: "dummy_entity_1",
RES_SLOT_NAME: "dummy_slot_name"
}
expected_result = parsing_result(
text, intent=mocked_proba_parser_intent, slots=[expected_slot])
self.assertEqual(expected_result, result)
