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_intents(self, text, intents_filter):
if isinstance(intents_filter, str):
intents_filter = {intents_filter}
elif isinstance(intents_filter, list):
intents_filter = set(intents_filter)
if not text or not self.intent_list or not self.featurizer:
results = [intent_classification_result(None, 1.0)]
results += [intent_classification_result(i, 0.0)
for i in self.intent_list if i is not None]
return results
if len(self.intent_list) == 1:
return [intent_classification_result(self.intent_list[0], 1.0)]
# pylint: disable=C0103
X = self.featurizer.transform([text_to_utterance(text)])
# pylint: enable=C0103
proba_vec = self._predict_proba(X)
logger.debug(
"%s", DifferedLoggingMessage(self.log_activation_weights, text, X))
results = [
intent_classification_result(i, proba)
for i, proba in zip(self.intent_list, proba_vec[0])
if intents_filter is None or i is None or i in intents_filter]
return sorted(results, key=lambda res: -res[RES_PROBA])
def test_should_get_intents(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: greeting1
utterances:
- hello
---
type: intent
name: greeting2
utterances:
- how are you""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
input_text = "hello world"
# pylint:disable=unused-variable
@IntentParser.register("first_intent_parser", True)
class FirstIntentParser(MockIntentParser):
def get_intents(self, text):
return [
intent_classification_result("greeting1", 0.5),
intent_classification_result("greeting2", 0.3),
intent_classification_result(None, 0.2)
]
@IntentParser.register("second_intent_parser", True)
class SecondIntentParser(MockIntentParser):
def get_intents(self, text):
return [
intent_classification_result("greeting2", 0.6),
intent_classification_result("greeting1", 0.2),
intent_classification_result(None, 0.1)
]
# pylint:enable=unused-variable
config = NLUEngineConfig(["first_intent_parser",
"second_intent_parser"])
engine = SnipsNLUEngine(config).fit(dataset)
# When
res_intents = engine.get_intents(input_text)
# Then
expected_intents = [
intent_classification_result("greeting2", 0.6),
intent_classification_result("greeting1", 0.5),
intent_classification_result(None, 0.2)
]
self.assertListEqual(expected_intents, res_intents)
def test_should_parse_intent_with_ambivalent_words(self):
# Given
slots_dataset_stream = io.StringIO("""
---
type: intent
name: give_flower
utterances:
- give a rose to [name](emily)
- give a daisy to [name](tom)
- give a tulip to [name](daisy)
""")
dataset = Dataset.from_yaml_files("en",
[slots_dataset_stream]).json
parser = LookupIntentParser().fit(dataset)
text = "give a daisy to emily"
# When
parsing = parser.parse(text)
# Then
expected_intent = intent_classification_result(
intent_name="give_flower", probability=1.0)
expected_slots = [
{
"entity": "name",
"range": {"end": 21, "start": 16},
"slotName": "name",
"value": "emily"
}
]
self.assertDictEqual(expected_intent, parsing[RES_INTENT])
self.assertListEqual(expected_slots, parsing[RES_SLOTS])
def test_should_serialize_results(self):
# Given
input_ = "hello world"
intent = intent_classification_result("world", 0.5)
slots = [unresolved_slot([3, 5],
"slot_value",
"slot_entity",
"slot_name")]
# When
result = parsing_result(input=input_, intent=intent, slots=slots)
# Then
msg = "Result dict should be json serializable"
with self.fail_if_exception(msg):
json.dumps(result)
expected_result = {
RES_INTENT: {RES_INTENT_NAME: 'world', RES_PROBABILITY: 0.5},
RES_SLOTS: [{RES_MATCH_RANGE: {"start": 3, "end": 5},
RES_ENTITY: 'slot_entity',
RES_SLOT_NAME: 'slot_name',
RES_VALUE: 'slot_value'}],
RES_INPUT: input_}
self.assertDictEqual(expected_result, result)
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_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_should_serialize_results(self):
# Given
input_ = "hello world"
intent = intent_classification_result("world", 0.5)
slots = [
unresolved_slot([3, 5], "slot_value", "slot_entity", "slot_name")
]
# When
result = parsing_result(input=input_, intent=intent, slots=slots)
# Then
msg = "Result dict should be json serializable"
with self.fail_if_exception(msg):
json.dumps(result)
expected_result = {
RES_INTENT: {
RES_INTENT_NAME: 'world',
RES_PROBA: 0.5
},
RES_SLOTS: [{
RES_MATCH_RANGE: {
"start": 3,
"end": 5
},
RES_ENTITY: 'slot_entity',
RES_SLOT_NAME: 'slot_name',
RES_VALUE: 'slot_value'
}],
RES_INPUT:
input_
}
self.assertDictEqual(expected_result, result)
def test_empty_vocabulary_should_fit_and_return_none_intent(
self, mocked_build_training):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: dummy_intent_1
utterances:
- "[dummy_slot_name:dummy_entity_1](...)"
---
type: entity
name: dummy_entity_1
automatically_extensible: true
use_synonyms: false
matching_strictness: 1.0
values:
- ...
""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
text = " "
noise_size = 6
utterances = [text] + [text] * noise_size
utterances = [text_to_utterance(t) for t in utterances]
labels = [0] + [1] * noise_size
intent_list = ["dummy_intent_1", None]
mocked_build_training.return_value = utterances, labels, intent_list
# When / Then
intent_classifier = LogRegIntentClassifier().fit(dataset)
intent = intent_classifier.get_intent("no intent there")
self.assertEqual(intent_classification_result(None, 1.0), intent)
def test_should_get_none_intent_when_empty_input(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
classifier = LogRegIntentClassifier().fit(dataset)
text = ""
# When
result = classifier.get_intent(text)
# Then
self.assertEqual(intent_classification_result(None, 1.0), result)
def _get_matching_result(self, text, processed_text, regex, intent,
builtin_entities_ranges_mapping=None):
found_result = regex.match(processed_text)
if found_result is None:
return None
parsed_intent = intent_classification_result(intent_name=intent,
probability=1.0)
slots = []
for group_name in found_result.groupdict():
slot_name = self.group_names_to_slot_names[group_name]
entity = self.slot_names_to_entities[intent][slot_name]
rng = (found_result.start(group_name),
found_result.end(group_name))
if builtin_entities_ranges_mapping is not None:
if rng in builtin_entities_ranges_mapping:
rng = builtin_entities_ranges_mapping[rng]
else:
shift = _get_range_shift(
rng, builtin_entities_ranges_mapping)
rng = {START: rng[0] + shift, END: rng[1] + shift}
else:
rng = {START: rng[0], END: rng[1]}
value = text[rng[START]:rng[END]]
parsed_slot = unresolved_slot(
match_range=rng, value=value, entity=entity,
slot_name=slot_name)
slots.append(parsed_slot)
parsed_slots = _deduplicate_overlapping_slots(
slots, self.language)
parsed_slots = sorted(parsed_slots,
key=lambda s: s[RES_MATCH_RANGE][START])
return parsing_result(text, parsed_intent, parsed_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 parse(self, text, intents=None):
"""Performs intent parsing on the provided *text*
Intent and slots are extracted simultaneously through pattern matching
Args:
text (str): Input
intents (str or list of str): If provided, reduces the scope of
intent parsing to the provided list of intents
Returns:
dict: The matched intent, if any, along with the extracted slots.
See :func:`.parsing_result` for the output format.
Raises:
NotTrained: When the intent parser is not fitted
"""
if not self.fitted:
raise NotTrained("DeterministicIntentParser must be fitted")
if isinstance(intents, str):
intents = [intents]
ranges_mapping, processed_text = _replace_builtin_entities(
text, self.language)
for intent, regexes in iteritems(self.regexes_per_intent):
if intents is not None and intent not in intents:
continue
for regex in regexes:
match = regex.match(processed_text)
if match is None:
continue
parsed_intent = intent_classification_result(
intent_name=intent, probability=1.0)
slots = []
for group_name in match.groupdict():
slot_name = self.group_names_to_slot_names[group_name]
entity = self.slot_names_to_entities[slot_name]
rng = (match.start(group_name), match.end(group_name))
value = match.group(group_name)
if rng in ranges_mapping:
rng = ranges_mapping[rng]
value = text[rng[START]:rng[END]]
else:
rng = {START: rng[0], END: rng[1]}
parsed_slot = unresolved_slot(match_range=rng,
value=value,
entity=entity,
slot_name=slot_name)
slots.append(parsed_slot)
parsed_slots = _deduplicate_overlapping_slots(
slots, self.language)
parsed_slots = sorted(parsed_slots,
key=lambda s: s[RES_MATCH_RANGE][START])
return parsing_result(text, parsed_intent, parsed_slots)
return empty_result(text)
def get_intents(self, text):
"""Returns the list of intents ordered by decreasing probability
The length of the returned list is exactly the number of intents in the
dataset + 1 for the None intent
"""
nb_intents = len(self.regexes_per_intent)
top_intents = [intent_result[RES_INTENT] for intent_result in
self._parse_top_intents(text, top_n=nb_intents)]
matched_intents = {res[RES_INTENT_NAME] for res in top_intents}
for intent in self.regexes_per_intent:
if intent not in matched_intents:
top_intents.append(intent_classification_result(intent, 0.0))
# The None intent is not included in the regex patterns and is thus
# never matched by the deterministic parser
top_intents.append(intent_classification_result(None, 0.0))
return top_intents
def get_intent(self, text, intents_filter=None):
"""Performs intent classification on the provided *text*
Args:
text (str): Input
intents_filter (str or list of str): When defined, it will find
the most likely intent among the list, otherwise it will use
the whole list of intents defined in the dataset
Returns:
dict or None: The most likely intent along with its probability or
*None* if no intent was found
Raises:
NotTrained: When the intent classifier is not fitted
"""
if not self.fitted:
raise NotTrained('LogRegIntentClassifier must be fitted')
if isinstance(intents_filter, str):
intents_filter = [intents_filter]
if not text or not self.intent_list \
or self.featurizer is None or self.classifier is None:
return None
if len(self.intent_list) == 1:
if self.intent_list[0] is None:
return None
return intent_classification_result(self.intent_list[0], 1.0)
# pylint: disable=C0103
X = self.featurizer.transform([text_to_utterance(text)])
# pylint: enable=C0103
proba_vec = self._predict_proba(X, intents_filter=intents_filter)
intents_probas = sorted(zip(self.intent_list, proba_vec[0]),
key=lambda p: -p[1])
for intent, proba in intents_probas:
if intent is None:
return None
if intents_filter is None or intent in intents_filter:
return intent_classification_result(intent, proba)
return None
def parse(self, text, intents=None):
"""Performs intent parsing on the provided *text*
Intent and slots are extracted simultaneously through pattern matching
Args:
text (str): Input
intents (str or list of str): If provided, reduces the scope of
intent parsing to the provided list of intents
Returns:
dict: The matched intent, if any, along with the extracted slots.
See :func:`.parsing_result` for the output format.
Raises:
NotTrained: When the intent parser is not fitted
"""
if not self.fitted:
raise NotTrained("DeterministicIntentParser must be fitted")
if isinstance(intents, str):
intents = [intents]
ranges_mapping, processed_text = _replace_builtin_entities(
text, self.language)
for intent, regexes in iteritems(self.regexes_per_intent):
if intents is not None and intent not in intents:
continue
for regex in regexes:
match = regex.match(processed_text)
if match is None:
continue
parsed_intent = intent_classification_result(
intent_name=intent, probability=1.0)
slots = []
for group_name in match.groupdict():
slot_name = self.group_names_to_slot_names[group_name]
entity = self.slot_names_to_entities[slot_name]
rng = (match.start(group_name), match.end(group_name))
value = match.group(group_name)
if rng in ranges_mapping:
rng = ranges_mapping[rng]
value = text[rng[START]:rng[END]]
else:
rng = {START: rng[0], END: rng[1]}
parsed_slot = unresolved_slot(
match_range=rng, value=value, entity=entity,
slot_name=slot_name)
slots.append(parsed_slot)
parsed_slots = _deduplicate_overlapping_slots(
slots, self.language)
parsed_slots = sorted(parsed_slots,
key=lambda s: s[RES_MATCH_RANGE][START])
return parsing_result(text, parsed_intent, parsed_slots)
return empty_result(text)
def test_should_parse_top_intents(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: intent1
utterances:
- meeting tomorrow
---
type: intent
name: intent2
utterances:
- meeting [time:snips/datetime](today)""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
parser = DeterministicIntentParser().fit(dataset)
text = "meeting tomorrow"
# When
results = parser.parse(text, top_n=3)
# Then
slot = {
"entity": "snips/datetime",
"range": {
"end": 16,
"start": 8
},
"slotName": "time",
"value": "tomorrow"
}
expected_results = [
extraction_result(
intent_classification_result(intent_name="intent1",
probability=0.5), []),
extraction_result(
intent_classification_result(intent_name="intent2",
probability=0.5), [slot])
]
results = sorted(results, key=lambda r: r[RES_INTENT][RES_INTENT_NAME])
self.assertEqual(expected_results, results)
def test_should_get_none_intent_when_empty_dataset(self):
# Given
dataset = get_empty_dataset(LANGUAGE_EN)
classifier = LogRegIntentClassifier().fit(dataset)
text = "this is a dummy query"
# When
intent = classifier.get_intent(text)
# Then
expected_intent = intent_classification_result(None, 1.0)
self.assertEqual(intent, expected_intent)
def test_should_parse_stop_words_slots(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: search
utterances:
- search
- search [search_object](this)
- search [search_object](a cat)
---
type: entity
name: search_object
values:
- [this thing, that]
""")
resources = self.get_resources("en")
resources[STOP_WORDS] = {"a", "this", "that"}
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
parser_config = DeterministicIntentParserConfig(ignore_stop_words=True)
parser = DeterministicIntentParser(config=parser_config,
resources=resources)
parser.fit(dataset)
# When
res_1 = parser.parse("search this")
res_2 = parser.parse("search that")
# Then
expected_intent = intent_classification_result(intent_name="search",
probability=1.0)
expected_slots_1 = [
unresolved_slot(match_range=(7, 11),
value="this",
entity="search_object",
slot_name="search_object")
]
expected_slots_2 = [
unresolved_slot(match_range=(7, 11),
value="that",
entity="search_object",
slot_name="search_object")
]
self.assertEqual(expected_intent, res_1[RES_INTENT])
self.assertEqual(expected_intent, res_2[RES_INTENT])
self.assertListEqual(expected_slots_1, res_1[RES_SLOTS])
self.assertListEqual(expected_slots_2, res_2[RES_SLOTS])
def test_should_get_intent(self):
# Given
dataset = validate_and_format_dataset(self.slots_dataset)
parser = DeterministicIntentParser().fit(dataset)
text = "this is a dummy_a query with another dummy_c at 10p.m. or " \
"at 12p.m."
# When
parsing = parser.parse(text)
# Then
probability = 1.0
expected_intent = intent_classification_result(
intent_name="dummy_intent_1", probability=probability)
self.assertEqual(expected_intent, parsing[RES_INTENT])
def test_should_parse_intent_with_stop_words(self, mock_get_stop_words):
# Given
mock_get_stop_words.return_value = {"a", "hey"}
dataset = self.slots_dataset
config = DeterministicIntentParserConfig(ignore_stop_words=True)
parser = DeterministicIntentParser(config).fit(dataset)
text = "Hey this is dummy_a query with another dummy_c at 10p.m. or " \
"at 12p.m."
# When
parsing = parser.parse(text)
# Then
probability = 1.0
expected_intent = intent_classification_result(
intent_name="dummy_intent_1", probability=probability)
self.assertEqual(expected_intent, parsing[RES_INTENT])
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_parse_intent_after_deserialization(self):
# Given
dataset = self.slots_dataset
shared = self.get_shared_data(dataset)
parser = DeterministicIntentParser(**shared).fit(dataset)
parser.persist(self.tmp_file_path)
deserialized_parser = DeterministicIntentParser.from_path(
self.tmp_file_path, **shared)
text = "this is a dummy_a query with another dummy_c at 10p.m. or " \
"at 12p.m."
# When
parsing = deserialized_parser.parse(text)
# Then
probability = 1.0
expected_intent = intent_classification_result(
intent_name="dummy_intent_1", probability=probability)
self.assertEqual(expected_intent, parsing[RES_INTENT])
def test_should_parse_intent_with_duplicated_slot_names(self):
# Given
slots_dataset_stream = io.StringIO("""
---
type: intent
name: math_operation
slots:
- name: number
entity: snips/number
utterances:
- what is [number](one) plus [number](one)""")
dataset = Dataset.from_yaml_files("en", [slots_dataset_stream]).json
parser = DeterministicIntentParser().fit(dataset)
text = "what is one plus one"
# When
parsing = parser.parse(text)
# Then
probability = 1.0
expected_intent = intent_classification_result(
intent_name="math_operation", probability=probability)
expected_slots = [{
"entity": "snips/number",
"range": {
"end": 11,
"start": 8
},
"slotName": "number",
"value": "one"
}, {
"entity": "snips/number",
"range": {
"end": 20,
"start": 17
},
"slotName": "number",
"value": "one"
}]
self.assertDictEqual(expected_intent, parsing[RES_INTENT])
self.assertListEqual(expected_slots, parsing[RES_SLOTS])
def test_should_get_intent_after_deserialization(self):
# Given
dataset = validate_and_format_dataset(self.slots_dataset)
parser = DeterministicIntentParser().fit(dataset)
custom_entity_parser = parser.custom_entity_parser
parser.persist(self.tmp_file_path)
deserialized_parser = DeterministicIntentParser.from_path(
self.tmp_file_path,
builtin_entity_parser=BuiltinEntityParser.build(language="en"),
custom_entity_parser=custom_entity_parser)
text = "this is a dummy_a query with another dummy_c at 10p.m. or " \
"at 12p.m."
# When
parsing = deserialized_parser.parse(text)
# Then
probability = 1.0
expected_intent = intent_classification_result(
intent_name="dummy_intent_1", probability=probability)
self.assertEqual(expected_intent, parsing[RES_INTENT])
def _parse_map_output(self, text, output, entities, intents):
"""Parse the map output to the parser's result format"""
intent_id, slot_ids = output
intent_name = self._intents_names[intent_id]
if intents is not None and intent_name not in intents:
return None
parsed_intent = intent_classification_result(
intent_name=intent_name, probability=1.0)
slots = []
# assert invariant
assert len(slot_ids) == len(entities)
for slot_id, entity in zip(slot_ids, entities):
slot_name = self._slots_names[slot_id]
rng_start = entity[RES_MATCH_RANGE][START]
rng_end = entity[RES_MATCH_RANGE][END]
slot_value = text[rng_start:rng_end]
entity_name = entity[ENTITY_KIND]
slot = unresolved_slot(
[rng_start, rng_end], slot_value, entity_name, slot_name)
slots.append(slot)
return extraction_result(parsed_intent, slots)
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, 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_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_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 get_intent(self, text, intents_filter):
if "tea" in text:
return intent_classification_result("MakeTea", 1.0)
elif "coffee" in text:
return intent_classification_result("MakeCoffee", 1.0)
return intent_classification_result(None, 1.0)
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_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_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_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)
