def test_credit_card_recognizer_with_template(pii_csv, utterances,
num_of_examples,
acceptance_threshold):
"""
Test credit card recognizer with a dataset generated from
template and a CSV values file
:param pii_csv: input csv file location
:param utterances: template file location
:param num_of_examples: number of samples to be used from dataset
to test
:param acceptance_threshold: minimum precision/recall
allowed for tests to pass
"""
# read template and CSV files
import os
dir_path = os.path.dirname(os.path.realpath(__file__))
# generate examples
generator = PresidioDataGenerator()
templates = utterances.format(dir_path)
examples = generator.generate_fake_data(templates=templates,
n_samples=num_of_examples)
input_samples = [
InputSample.from_faker_spans_result(example) for example in examples
]
scores = score_presidio_recognizer(
recognizer=CreditCardRecognizer(),
entities_to_keep=["CREDIT_CARD"],
input_samples=input_samples,
)
if not np.isnan(scores.pii_f):
assert acceptance_threshold <= scores.pii_f
def test_faker_spans_result_to_input_sample(faker_span_result):
input_sample = InputSample.from_faker_spans_result(
faker_span_result, create_tags_from_span=False)
assert input_sample.full_text == "Dan is my name."
assert input_sample.masked == "{{name}} is my name."
assert input_sample.spans[0] == Span("name", "Dan", 0, 3)
assert input_sample.spans[0] == Span("name", "Dan", 0, 3)
def test_faker_spans_to_input_sample_with_tags(faker_span_result):
input_sample = InputSample.from_faker_spans_result(
faker_span_result, create_tags_from_span=True, scheme="BILUO")
assert input_sample.tags
assert input_sample.tokens
assert any(["U-name" in tag for tag in input_sample.tags])
def test_pattern_recognizer(
pii_csv,
ext_csv,
utterances,
entity_name,
pattern,
score,
num_of_examples,
acceptance_threshold,
max_mistakes_number,
):
"""
Test generic pattern recognizer with a dataset generated from template, a CSV values file with common entities
and another CSV values file with a custom entity
:param pii_csv: input csv file location with the common entities
:param ext_csv: input csv file location with custom entities
:param utterances: template file location
:param entity_name: custom entity name
:param pattern: recognizer pattern
:param num_of_examples: number of samples to be used from dataset to test
:param acceptance_threshold: minimum precision/recall
allowed for tests to pass
"""
import os
dir_path = os.path.dirname(os.path.realpath(__file__))
dfpii = pd.read_csv(pii_csv.format(dir_path), encoding="utf-8")
dfext = pd.read_csv(ext_csv.format(dir_path), encoding="utf-8")
ext_column_name = dfext.columns[0]
def get_from_ext(i):
index = i % dfext.shape[0]
return dfext.iat[index, 0]
# extend pii with ext data
dfpii[ext_column_name] = [
get_from_ext(i) for i in range(0, dfpii.shape[0])
]
# generate examples
generator = PresidioDataGenerator()
templates = utterances.format(dir_path)
examples = generator.generate_fake_data(templates=templates,
n_samples=num_of_examples)
input_samples = [
InputSample.from_faker_spans_result(example) for example in examples
]
pattern = Pattern("test pattern", pattern, score)
pattern_recognizer = PatternRecognizer(entity_name,
name="test recognizer",
patterns=[pattern])
scores = score_presidio_recognizer(
recognizer=pattern_recognizer,
entities_to_keep=[entity_name],
input_samples=input_samples,
)
if not np.isnan(scores.pii_f):
assert acceptance_threshold <= scores.pii_f
assert max_mistakes_number >= len(scores.model_errors)