def test_spacy_ner_extractor(spacy_nlp):
example = Message(
data={
TEXT: "anywhere in the U.K.",
"intent": "restaurant_search",
"entities": [],
"text_spacy_doc": spacy_nlp("anywhere in the west"),
})
component = SpacyEntityExtractor(SpacyEntityExtractor.get_default_config())
component.process([example],
model=SpacyModel(model=spacy_nlp, model_name=""))
assert len(example.get("entities", [])) == 1
assert example.get("entities")[0] == {
"start": 16,
"extractor": "SpacyEntityExtractor",
"end": 20,
"value": "U.K.",
"entity": "GPE",
"confidence": None,
}
# Test dimension filtering includes only specified dimensions
example = Message(
data={
TEXT:
"anywhere in the West with Sebastian Thrun",
"intent":
"example_intent",
"entities": [],
"text_spacy_doc":
spacy_nlp("anywhere in the West with Sebastian Thrun"),
})
component = SpacyEntityExtractor({"dimensions": ["PERSON"]})
component.process([example],
model=SpacyModel(model=spacy_nlp, model_name=""))
assert len(example.get("entities", [])) == 1
assert example.get("entities")[0] == {
"start": 26,
"extractor": "SpacyEntityExtractor",
"end": 41,
"value": "Sebastian Thrun",
"entity": "PERSON",
"confidence": None,
}
assert os.path.exists(
os.path.join(report_folder, "response_selection_histogram.png"))
assert not os.path.exists(
os.path.join(report_folder, "response_selection_errors.json"))
assert os.path.exists(
os.path.join(report_folder, "response_selection_successes.json"))
@pytest.mark.parametrize(
"components, expected_extractors",
[
([DIETClassifier({ENTITY_RECOGNITION: False})], set()),
([DIETClassifier({ENTITY_RECOGNITION: True})], {"DIETClassifier"}),
([CRFEntityExtractor()], {"CRFEntityExtractor"}),
(
[SpacyEntityExtractor(),
CRFEntityExtractor()],
{"SpacyEntityExtractor", "CRFEntityExtractor"},
),
([ResponseSelector()], set()),
],
)
def test_get_entity_extractors(components, expected_extractors):
mock_interpreter = Interpreter(components, None)
extractors = get_entity_extractors(mock_interpreter)
assert extractors == expected_extractors
def test_entity_evaluation_report(tmpdir_factory):
class EntityExtractorA(EntityExtractor):
assert not os.path.exists(
os.path.join(report_folder, "response_selection_errors.json")
)
assert os.path.exists(
os.path.join(report_folder, "response_selection_successes.json")
)
@pytest.mark.parametrize(
"components, expected_extractors",
[
([DIETClassifier({ENTITY_RECOGNITION: False})], set()),
([DIETClassifier({ENTITY_RECOGNITION: True})], {"DIETClassifier"}),
([CRFEntityExtractor()], {"CRFEntityExtractor"}),
(
[SpacyEntityExtractor(), CRFEntityExtractor()],
{"SpacyEntityExtractor", "CRFEntityExtractor"},
),
([ResponseSelector()], set()),
],
)
def test_get_entity_extractors(
components: List[Component], expected_extractors: Set[Text]
):
mock_interpreter = Interpreter(components, None)
extractors = get_entity_extractors(mock_interpreter)
assert extractors == expected_extractors
def test_entity_evaluation_report(tmp_path: Path):
