def test_evaluate_sample_wrong_entities_to_keep_correct_statistics():
prediction = ["O", "O", "O", "U-ANIMAL"]
model = MockTokensModel(prediction=prediction,
entities_to_keep=['SPACESHIP'])
sample = InputSample(full_text="I am the walrus",
masked="I am the [ANIMAL]",
spans=None)
sample.tokens = ["I", "am", "the", "walrus"]
sample.tags = ["O", "O", "O", "U-ANIMAL"]
evaluated = model.evaluate_sample(sample)
assert evaluated.results[("O", "O")] == 4
def test_evaluate_same_entity_correct_statistics():
prediction = ["O", "U-ANIMAL", "O", "U-ANIMAL"]
model = MockTokensModel(prediction=prediction, entities_to_keep=['ANIMAL'])
sample = InputSample(full_text="I dog the walrus",
masked="I [ANIMAL] the [ANIMAL]",
spans=None)
sample.tokens = ["I", "am", "the", "walrus"]
sample.tags = ["O", "O", "O", "U-ANIMAL"]
evaluation_result = model.evaluate_sample(sample)
assert evaluation_result.results[("O", "O")] == 2
assert evaluation_result.results[("ANIMAL", "ANIMAL")] == 1
assert evaluation_result.results[("O", "ANIMAL")] == 1
def test_evaluate_multiple_tokens_partial_match_correct_statistics():
prediction = ["O", "O", "O", "B-ANIMAL", "L-ANIMAL", "O"]
model = MockTokensModel(prediction=prediction, entities_to_keep=['ANIMAL'])
sample = InputSample("I am the walrus amaericanus magnifico",
masked=None,
spans=None)
sample.tokens = ["I", "am", "the", "walrus", "americanus", "magnifico"]
sample.tags = ["O", "O", "O", "B-ANIMAL", "I-ANIMAL", "L-ANIMAL"]
evaluated = model.evaluate_sample(sample)
evaluation = model.calculate_score([evaluated])
assert evaluation.pii_precision == 1
assert evaluation.pii_recall == 4 / 6
def test_evaluator_simple():
prediction = ["O", "O", "O", "U-ANIMAL"]
model = MockTokensModel(prediction=prediction, entities_to_keep=['ANIMAL'])
sample = InputSample(full_text="I am the walrus",
masked="I am the [ANIMAL]",
spans=None)
sample.tokens = ["I", "am", "the", "walrus"]
sample.tags = ["O", "O", "O", "U-ANIMAL"]
evaluated = model.evaluate_sample(sample)
final_evaluation = model.calculate_score([evaluated])
assert final_evaluation.pii_precision == 1
assert final_evaluation.pii_recall == 1