def generate_dataset(language, *files):
"""Create a Snips NLU dataset from text friendly files"""
if any(f.endswith(".yml") or f.endswith(".yaml") for f in files):
dataset = Dataset.from_yaml_files(language, list(files))
else:
dataset = Dataset.from_files(language, list(files))
print(json.dumps(dataset.json, indent=2, sort_keys=True))
def test_should_parse_with_filter(self):
dataset_stream = io.StringIO("""
---
type: intent
name: intent1
utterances:
- "[slot1:entity1](foo) bar"
---
type: intent
name: intent2
utterances:
- foo bar [slot2:entity2](baz)
---
type: intent
name: intent3
utterances:
- foz for [slot3:entity3](baz)""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
shared = self.get_shared_data(dataset)
shared[RANDOM_STATE] = 42
parser = ProbabilisticIntentParser(**shared)
parser.fit(dataset)
text = "foo bar baz"
# When
result = parser.parse(text, intents=["intent1", "intent3"])
# Then
expected_slots = [unresolved_slot((0, 3), "foo", "entity1", "slot1")]
self.assertEqual("intent1", result[RES_INTENT][RES_INTENT_NAME])
self.assertEqual(expected_slots, result[RES_SLOTS])
def test_should_get_slots_after_deserialization(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: MakeTea
utterances:
- make me [number_of_cups:snips/number](one) cup of tea
- i want [number_of_cups] cups of tea please
- can you prepare [number_of_cups] cups of tea ?""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
intent = "MakeTea"
shared = self.get_shared_data(dataset)
shared[RANDOM_STATE] = 42
slot_filler = CRFSlotFiller(**shared)
slot_filler.fit(dataset, intent)
slot_filler.persist(self.tmp_file_path)
deserialized_slot_filler = CRFSlotFiller.from_path(
self.tmp_file_path, **shared)
# When
slots = deserialized_slot_filler.get_slots("make me two cups of tea")
# Then
expected_slots = [
unresolved_slot(match_range={
START: 8,
END: 11
},
value='two',
entity='snips/number',
slot_name='number_of_cups')
]
self.assertListEqual(expected_slots, slots)
def test_should_get_intents(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: intent1
utterances:
- yala yili
---
type: intent
name: intent2
utterances:
- yala yili yulu
---
type: intent
name: intent3
utterances:
- yili yulu yele""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
classifier_config = LogRegIntentClassifierConfig(random_seed=42)
parser_config = ProbabilisticIntentParserConfig(classifier_config)
parser = ProbabilisticIntentParser(parser_config).fit(dataset)
text = "yala yili yulu"
# When
results = parser.get_intents(text)
intents = [res[RES_INTENT_NAME] for res in results]
# Then
expected_intents = ["intent2", "intent1", "intent3", None]
self.assertEqual(expected_intents, intents)
def test_get_slots_should_raise_with_unknown_intent(self):
# Given
slots_dataset_stream = io.StringIO("""
---
type: intent
name: greeting1
utterances:
- Hello [name1](John)
---
type: intent
name: goodbye
utterances:
- Goodbye [name](Eric)""")
dataset = Dataset.from_yaml_files("en", [slots_dataset_stream]).json
# pylint:disable=unused-variable
@IntentClassifier.register("my_intent_classifier", True)
class MyIntentClassifier(MockIntentClassifier):
pass
@SlotFiller.register("my_slot_filler", True)
class MySlotFiller(MockSlotFiller):
pass
# pylint:enable=unused-variable
config = ProbabilisticIntentParserConfig(
intent_classifier_config="my_intent_classifier",
slot_filler_config="my_slot_filler")
parser = ProbabilisticIntentParser(config).fit(dataset)
# When / Then
with self.assertRaises(IntentNotFoundError):
parser.get_slots("Hello John", "greeting3")
def test_parse_should_raise_with_unknown_intent_in_filter(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: greeting1
utterances:
- Hello [name1](John)
---
type: intent
name: goodbye
utterances:
- Goodbye [name](Eric)""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
# pylint:disable=unused-variable
@IntentParser.register("my_intent_parser", True)
class FirstIntentParser(MockIntentParser):
pass
# pylint:enable=unused-variable
config = NLUEngineConfig(["my_intent_parser"])
nlu_engine = SnipsNLUEngine(config).fit(dataset)
# When / Then
with self.assertRaises(IntentNotFoundError):
nlu_engine.parse("Hello John", intents="greeting3")
with self.assertRaises(IntentNotFoundError):
nlu_engine.parse("Hello John", intents=["greeting3"])
def test_should_persist_resources_from_memory(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
shared = self.get_shared_data(dataset)
engine = SnipsNLUEngine(**shared).fit(dataset)
dir_temp_engine = self.fixture_dir / "temp_engine"
engine.persist(dir_temp_engine)
# When
loaded_engine = SnipsNLUEngine.from_path(dir_temp_engine)
shutil.rmtree(str(dir_temp_engine))
# Then
loaded_engine.to_byte_array()
def test_should_limit_nb_queries(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: my_first_intent
utterances:
- this is [slot1:entity1](my first entity)
- this is [slot2:entity2](my second entity)
- this is [slot3:entity3](my third entity)
---
type: intent
name: my_second_intent
utterances:
- this is [slot4:entity4](my fourth entity)""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
config = DeterministicIntentParserConfig(max_queries=2,
max_pattern_length=1000)
# When
parser = DeterministicIntentParser(config=config).fit(dataset)
# Then
self.assertEqual(len(parser.regexes_per_intent["my_first_intent"]), 2)
self.assertEqual(len(parser.regexes_per_intent["my_second_intent"]), 1)
def test_should_limit_patterns_length(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: my_first_intent
utterances:
- how are you
- hello how are you?
- what's up
---
type: intent
name: my_second_intent
utterances:
- what is the weather today ?
- does it rain
- will it rain tomorrow""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
config = DeterministicIntentParserConfig(max_queries=1000,
max_pattern_length=25,
ignore_stop_words=False)
# When
parser = DeterministicIntentParser(config=config).fit(dataset)
# Then
self.assertEqual(2, len(parser.regexes_per_intent["my_first_intent"]))
self.assertEqual(1, len(parser.regexes_per_intent["my_second_intent"]))
def test_should_get_builtin_slots(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: GetWeather
utterances:
- what is the weather [datetime:snips/datetime](at 9pm)
- what's the weather in [location:weather_location](berlin)
- What's the weather in [location](tokyo) [datetime](this weekend)?
- Can you tell me the weather [datetime] please ?
- what is the weather forecast [datetime] in [location](paris)""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
config = CRFSlotFillerConfig(random_seed=42)
intent = "GetWeather"
slot_filler = CRFSlotFiller(config, **self.get_shared_data(dataset))
slot_filler.fit(dataset, intent)
# When
slots = slot_filler.get_slots("Give me the weather at 9pm in Paris")
# Then
expected_slots = [
unresolved_slot(match_range={START: 20, END: 26},
value='at 9pm',
entity='snips/datetime',
slot_name='datetime'),
unresolved_slot(match_range={START: 30, END: 35},
value='Paris',
entity='weather_location',
slot_name='location')
]
self.assertListEqual(expected_slots, slots)
def test_should_get_sub_builtin_slots(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: PlanBreak
utterances:
- 'I want to leave from [start:snips/datetime](tomorrow) until
[end:snips/datetime](next thursday)'
- find me something from [start](9am) to [end](12pm)
- I need a break from [start](2pm) until [end](4pm)
- Can you suggest something from [start](april 4th) until [end](april 6th) ?
- Book me a trip from [start](this friday) to [end](next tuesday)""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
config = CRFSlotFillerConfig(random_seed=42)
intent = "PlanBreak"
slot_filler = CRFSlotFiller(config,
**self.get_shared_data(dataset))
slot_filler.fit(dataset, intent)
# When
slots = slot_filler.get_slots("Find me a plan from 5pm to 6pm")
# Then
expected_slots = [
unresolved_slot(match_range={START: 20, END: 23},
value="5pm",
entity="snips/datetime",
slot_name="start"),
unresolved_slot(match_range={START: 27, END: 30},
value="6pm",
entity="snips/datetime",
slot_name="end")
]
self.assertListEqual(expected_slots, slots)
def test_should_parse_top_intents(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: intent1
utterances:
- hello world
---
type: intent
name: intent2
utterances:
- foo bar""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
parser = DeterministicIntentParser().fit(dataset)
text = "hello world"
# When
results = parser.parse(text, top_n=3)
# Then
expected_intent = intent_classification_result(intent_name="intent1",
probability=1.0)
expected_results = [extraction_result(expected_intent, [])]
self.assertEqual(expected_results, results)
def setUp(self):
super(TestCLI, self).setUp()
if not self.fixture_dir.exists():
self.fixture_dir.mkdir()
dataset_stream = io.StringIO(u"""
---
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""")
beverage_dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
self.beverage_dataset_path = self.fixture_dir / "beverage_dataset.json"
if self.beverage_dataset_path.exists():
self.beverage_dataset_path.unlink()
with self.beverage_dataset_path.open(mode="w") as f:
f.write(json_string(beverage_dataset))
self.tmp_file_path = self.fixture_dir / next(
tempfile._get_candidate_names())
while self.tmp_file_path.exists():
self.tmp_file_path = self.fixture_dir / next(
tempfile._get_candidate_names())
def test_training_should_be_reproducible(self):
# Given
random_state = 42
dataset_stream = io.StringIO("""
---
type: intent
name: MakeTea
utterances:
- make me a hot cup of tea
- make me five tea cups
---
type: intent
name: MakeCoffee
utterances:
- make me one cup of coffee please
- brew two cups of coffee""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
# When
engine1 = SnipsNLUEngine(random_state=random_state)
engine1.fit(dataset)
engine2 = SnipsNLUEngine(random_state=random_state)
engine2.fit(dataset)
# Then
with temp_dir() as tmp_dir:
dir_engine1 = tmp_dir / "engine1"
dir_engine2 = tmp_dir / "engine2"
engine1.persist(dir_engine1)
engine2.persist(dir_engine2)
hash1 = dirhash(str(dir_engine1), 'sha256')
hash2 = dirhash(str(dir_engine2), 'sha256')
self.assertEqual(hash1, hash2)
def test_should_not_build_builtin_parser_when_provided(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
dataset = validate_and_format_dataset(dataset)
builtin_entity_parser = BuiltinEntityParser.build(language="en")
# When
with patch("snips_nlu.entity_parser.builtin_entity_parser"
".BuiltinEntityParser.build") as mocked_build_parser:
engine = SnipsNLUEngine(
builtin_entity_parser=builtin_entity_parser)
engine.fit(dataset)
# Then
mocked_build_parser.assert_not_called()
def test_should_ignore_very_ambiguous_utterances(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: intent_1
utterances:
- "[event_type](meeting) tomorrow"
---
type: intent
name: intent_2
utterances:
- call [time:snips/datetime](today)
---
type: entity
name: event_type
values:
- call
- diner""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
parser = DeterministicIntentParser().fit(dataset)
text = "call tomorrow"
# When
res = parser.parse(text)
# Then
self.assertEqual(empty_result(text, 1.0), res)
def test_should_not_build_custom_parser_when_provided(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
resources = load_resources("en")
custom_entity_parser = CustomEntityParser.build(
dataset, CustomEntityParserUsage.WITH_AND_WITHOUT_STEMS, resources)
# When
with patch("snips_nlu.entity_parser.custom_entity_parser"
".CustomEntityParser.build") as mocked_build_parser:
engine = SnipsNLUEngine(
custom_entity_parser=custom_entity_parser)
engine.fit(dataset)
# Then
mocked_build_parser.assert_not_called()
def test_should_parse_slightly_ambiguous_utterances(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: intent_1
utterances:
- call tomorrow
---
type: intent
name: intent_2
utterances:
- call [time:snips/datetime](today)""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
parser = DeterministicIntentParser().fit(dataset)
text = "call tomorrow"
# When
res = parser.parse(text)
# Then
expected_intent = intent_classification_result(intent_name="intent_1",
probability=2. / 3.)
expected_result = parsing_result(text, expected_intent, [])
self.assertEqual(expected_result, res)
def test_should_be_serializable_into_bytearray(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
shared = self.get_shared_data(dataset)
engine = SnipsNLUEngine(**shared).fit(dataset)
# When
engine_bytes = engine.to_byte_array()
loaded_engine = SnipsNLUEngine.from_byte_array(engine_bytes)
result = loaded_engine.parse("Make me two cups of coffee")
# Then
self.assertEqual(result[RES_INTENT][RES_INTENT_NAME], "MakeCoffee")
def test_should_parse_intent(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: intent1
utterances:
- foo bar baz
---
type: intent
name: intent2
utterances:
- foo bar ban""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
parser = DeterministicIntentParser().fit(dataset)
text = "foo bar ban"
# When
parsing = parser.parse(text)
# Then
probability = 1.0
expected_intent = intent_classification_result(intent_name="intent2",
probability=probability)
self.assertEqual(expected_intent, parsing[RES_INTENT])
def test_validate_should_accept_dataset_object(self):
# Given
dataset_stream = io.StringIO("""
# getWeather Intent
---
type: intent
name: getWeather
utterances:
- what is the weather in [weatherLocation:location](Paris)?
- is it raining in [weatherLocation] [weatherDate:snips/datetime]
# Location Entity
---
type: entity
name: location
automatically_extensible: true
values:
- [new york, big apple]
- london
""")
dataset = Dataset.from_yaml_files("en", [dataset_stream])
# When
validated_dataset = validate_and_format_dataset(dataset)
# Then
self.assertTrue(validated_dataset.get(VALIDATED, False))
def test_should_be_serializable_into_bytearray(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: MakeTea
utterances:
- make me [number_of_cups:snips/number](one) cup of tea
- i want [number_of_cups] cups of tea please
- can you prepare [number_of_cups] cup of tea ?
---
type: intent
name: MakeCoffee
utterances:
- make me [number_of_cups:snips/number](two) cups of coffee
- 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
shared = self.get_shared_data(dataset)
intent_parser = DeterministicIntentParser(**shared).fit(dataset)
# When
intent_parser_bytes = intent_parser.to_byte_array()
loaded_intent_parser = DeterministicIntentParser.from_byte_array(
intent_parser_bytes, **shared)
result = loaded_intent_parser.parse("make me two cups of coffee")
# Then
self.assertEqual("MakeCoffee", result[RES_INTENT][RES_INTENT_NAME])
def test_should_get_intents(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: intent1
utterances:
- yala yili
---
type: intent
name: intent2
utterances:
- yala yili yulu
---
type: intent
name: intent3
utterances:
- yili yulu yele""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
shared = self.get_shared_data(dataset)
shared[RANDOM_STATE] = 42
parser = ProbabilisticIntentParser(**shared).fit(dataset)
text = "yala yili yulu"
# When
results = parser.get_intents(text)
intents = [res[RES_INTENT_NAME] for res in results]
# Then
expected_intents = ["intent2", "intent1", "intent3", None]
self.assertEqual(expected_intents, intents)
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_not_retrain_intent_classifier_when_no_force_retrain(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
parser = ProbabilisticIntentParser()
intent_classifier = LogRegIntentClassifier()
intent_classifier.fit(dataset)
parser.intent_classifier = intent_classifier
# When / Then
with patch("snips_nlu.intent_classifier.log_reg_classifier"
".LogRegIntentClassifier.fit") as mock_fit:
parser.fit(dataset, force_retrain=False)
mock_fit.assert_not_called()
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_get_slots(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: MakeTea
utterances:
- make me [number_of_cups:snips/number](five) cups of tea
- please I want [number_of_cups](two) cups of tea""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
shared = self.get_shared_data(dataset)
shared[RANDOM_STATE] = 42
slot_filler = CRFSlotFiller(**shared)
intent = "MakeTea"
slot_filler.fit(dataset, intent)
# When
slots = slot_filler.get_slots("make me two cups of tea")
# Then
expected_slots = [
unresolved_slot(match_range={
START: 8,
END: 11
},
value='two',
entity='snips/number',
slot_name='number_of_cups')
]
self.assertListEqual(slots, expected_slots)
def test_should_not_load_resources_when_provided(
self, mocked_load_resources):
# 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
resources = load_resources("en")
# When
engine = SnipsNLUEngine(resources=resources)
engine.fit(dataset)
# Then
mocked_load_resources.assert_not_called()
def test_should_be_serializable_into_bytearray(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: MakeTea
utterances:
- make me [number_of_cups:snips/number](one) cup of tea
- i want [number_of_cups] cups of tea please
- can you prepare [number_of_cups] cups of tea ?""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
shared = self.get_shared_data(dataset)
slot_filler = CRFSlotFiller(**shared).fit(dataset, "MakeTea")
# When
slot_filler_bytes = slot_filler.to_byte_array()
loaded_slot_filler = CRFSlotFiller.from_byte_array(
slot_filler_bytes, **shared)
slots = loaded_slot_filler.get_slots("make me two cups of tea")
# Then
expected_slots = [
unresolved_slot(match_range={
START: 8,
END: 11
},
value='two',
entity='snips/number',
slot_name='number_of_cups')
]
self.assertListEqual(expected_slots, slots)
def test_should_get_intent_when_filter(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: MakeTea
utterances:
- make me a cup of tea
- i want two cups of tea please
- can you prepare one cup of tea ?
---
type: intent
name: MakeCoffee
utterances:
- make me a cup of coffee please
- brew two cups of coffee
- can you prepare one cup of coffee""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
classifier = LogRegIntentClassifier(random_state=42).fit(dataset)
# When
text1 = "Make me two cups of tea"
res1 = classifier.get_intent(text1, ["MakeCoffee", "MakeTea"])
text2 = "Make me two cups of tea"
res2 = classifier.get_intent(text2, ["MakeCoffee"])
text3 = "bla bla bla"
res3 = classifier.get_intent(text3, ["MakeCoffee"])
# Then
self.assertEqual("MakeTea", res1[RES_INTENT_NAME])
self.assertEqual("MakeCoffee", res2[RES_INTENT_NAME])
self.assertEqual(None, res3[RES_INTENT_NAME])
