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])
def test_should_not_get_intent_when_not_fitted(self):
# Given
intent_classifier = LogRegIntentClassifier()
# When / Then
self.assertFalse(intent_classifier.fitted)
with self.assertRaises(NotTrained):
intent_classifier.get_intent("foobar")
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 test_should_get_intent(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(random_state=42).fit(dataset)
text = "hey how are you doing ?"
# When
res = classifier.get_intent(text)
intent = res[RES_INTENT_NAME]
# Then
self.assertEqual("my_first_intent", intent)
def test_intent_classifier_should_get_intent_when_filter(self):
# Given
dataset = validate_and_format_dataset(BEVERAGE_DATASET)
classifier = LogRegIntentClassifier().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)
def test_intent_classifier_should_get_intent_when_filter(self):
# Given
dataset = validate_and_format_dataset(BEVERAGE_DATASET)
classifier = LogRegIntentClassifier().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)
def test_should_get_none_if_empty_dataset(self):
# Given
dataset = validate_and_format_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 = None
self.assertEqual(intent, expected_intent)
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_get_none_if_empty_dataset(self):
# Given
dataset = validate_and_format_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 = None
self.assertEqual(intent, expected_intent)
def test_intent_classifier_should_get_intent(self):
# Given
dataset = validate_and_format_dataset(SAMPLE_DATASET)
classifier = LogRegIntentClassifier().fit(dataset)
text = "This is a dummy_3 query from another intent"
# When
res = classifier.get_intent(text)
intent = res[RES_INTENT_NAME]
# Then
expected_intent = "dummy_intent_2"
self.assertEqual(intent, expected_intent)
def test_intent_classifier_should_get_intent(self):
# Given
dataset = validate_and_format_dataset(SAMPLE_DATASET)
classifier = LogRegIntentClassifier().fit(dataset)
text = "This is a dummy_3 query from another intent"
# When
res = classifier.get_intent(text)
intent = res[RES_INTENT_NAME]
# Then
expected_intent = "dummy_intent_2"
self.assertEqual(intent, expected_intent)
def test_empty_vocabulary_should_fit_and_return_none_intent(
self, mocked_build_training):
# Given
language = LANGUAGE_EN
dataset = {
"entities": {
"dummy_entity_1": {
"automatically_extensible": True,
"use_synonyms": False,
"data": [
{
"value": "...",
"synonyms": [],
}
],
"matching_strictness": 1.0
}
},
"intents": {
"dummy_intent_1": {
"utterances": [
{
"data": [
{
"text": "...",
"slot_name": "dummy_slot_name",
"entity": "dummy_entity_1"
}
]
}
]
}
},
"language": language
}
dataset = validate_and_format_dataset(dataset)
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(None, intent)
def test_empty_vocabulary_should_fit_and_return_none_intent(
self, mocked_build_training):
# Given
language = LANGUAGE_EN
dataset = {
"snips_nlu_version": "0.0.1",
"entities": {
"dummy_entity_1": {
"automatically_extensible": True,
"use_synonyms": False,
"data": [
{
"value": "...",
"synonyms": [],
}
]
}
},
"intents": {
"dummy_intent_1": {
"utterances": [
{
"data": [
{
"text": "...",
"slot_name": "dummy_slot_name",
"entity": "dummy_entity_1"
}
]
}
]
}
},
"language": language
}
dataset = validate_and_format_dataset(dataset)
text = " "
noise_size = 6
utterance = [text] + [text] * noise_size
labels = [1] + [None] * noise_size
intent_list = ["dummy_intent_1", None]
mocked_build_training.return_value = utterance, labels, intent_list
# When / Then
intent_classifier = LogRegIntentClassifier().fit(dataset)
intent = intent_classifier.get_intent("no intent there")
self.assertEqual(intent, None)
