def test_should_not_parse_when_not_fitted(self):
# Given
parser = ProbabilisticIntentParser()
# When / Then
self.assertFalse(parser.fitted)
with self.assertRaises(NotTrained):
parser.parse("foobar")
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_parse_top_intents(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: intent1
utterances:
- "[entity1](foo) bar"
---
type: intent
name: intent2
utterances:
- foo bar [entity2](baz)
---
type: intent
name: intent3
utterances:
- foz for [entity3](baz)""")
dataset = Dataset.from_yaml_files("en", [dataset_stream]).json
classifier_config = LogRegIntentClassifierConfig(random_seed=42)
slot_filler_config = CRFSlotFillerConfig(random_seed=42)
parser_config = ProbabilisticIntentParserConfig(
classifier_config, slot_filler_config)
parser = ProbabilisticIntentParser(parser_config)
parser.fit(dataset)
text = "foo bar baz"
# When
results = parser.parse(text, top_n=2)
intents = [res[RES_INTENT][RES_INTENT_NAME] for res in results]
entities = [[s[RES_VALUE] for s in res[RES_SLOTS]] for res in results]
# Then
expected_intents = ["intent2", "intent1"]
expected_entities = [["baz"], ["foo"]]
self.assertListEqual(expected_intents, intents)
self.assertListEqual(expected_entities, entities)
def test_should_parse_top_intents(self):
# Given
dataset_stream = io.StringIO("""
---
type: intent
name: intent1
utterances:
- "[entity1](foo) bar"
---
type: intent
name: intent2
utterances:
- foo bar [entity2](baz)
---
type: intent
name: intent3
utterances:
- foz for [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
results = parser.parse(text, top_n=2)
intents = [res[RES_INTENT][RES_INTENT_NAME] for res in results]
entities = [[s[RES_VALUE] for s in res[RES_SLOTS]] for res in results]
# Then
expected_intents = ["intent2", "intent1"]
expected_entities = [["baz"], ["foo"]]
self.assertListEqual(expected_intents, intents)
self.assertListEqual(expected_entities, entities)
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
classifier_config = LogRegIntentClassifierConfig(random_seed=42)
slot_filler_config = CRFSlotFillerConfig(random_seed=42)
parser_config = ProbabilisticIntentParserConfig(
classifier_config, slot_filler_config)
parser = ProbabilisticIntentParser(parser_config)
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])