def test_record_generation_catches_invalid_profiles(self):
with self.assertRaises(ValueError):
record = gen_record({'forename': 'Joe'})
with self.assertRaises(ValueError):
record = gen_record({'birth_surname': 'Smith'})
with self.assertRaises(ValueError):
record = gen_record({'test': 'test'})
def setUp(self):
# Female profile with different birth surname and current surname
female = {
'forename': 'Adelyn',
'mid_forename': 'Heidenreich',
'current_surname': 'Bartell',
'birth_surname': 'Gerlach'
}
self.female_record = gen_record(female)
# Male profile with some missing name fields
male = {
'forename': 'Oliver',
'current_surname': 'Nader'
}
self.male_record = gen_record(male)
def setUp(self):
data_path = os.path.join(os.path.dirname(__file__), 'profiles_100.json')
with open(data_path, 'r') as data_file:
population = tuple(json.load(data_file))
records = [gen_record(profile) for profile in population]
self.herd = Herd()
self.herd.populate(records)
def setUp(self):
population = (
{
'forename': 'Adelyn',
'mid_forename': 'Heidenreich',
'current_surname': 'Bartell',
'birth_surname': 'Gerlach'
},
{
'forename': 'John',
'mid_forename': 'Frederich',
'current_surname': 'Sanders'
},
{
'forename': 'Joseph',
'current_surname': 'Smith'
},
{
'forename': 'John',
'mid_forename': 'Heidenreich',
'current_surname': 'Smith',
'birth_surname': 'Gerlach'
}
)
records = [gen_record(profile) for profile in population]
self.herd = Herd()
self.herd.populate(records)
self.herd.corral()
def test_no_errors(self):
"""See how the probability matrix looks with no textual errors."""
herd = Herd()
data_path = os.path.join(os.path.dirname(__file__),
'error_free_3x2.json')
with open(data_path, 'r') as data_file:
population = tuple(json.load(data_file))
records = [gen_record(profile) for profile in population]
herd = Herd()
herd.populate(records)
herd.corral()
print()
print(herd.similarity_matrix)
def test_gender_misclassification(self):
"""See how gender misclassification impacts probability matrix.
"""
herd = Herd()
data_path = os.path.join(os.path.dirname(__file__),
'gender_misclassification_3x2.json')
with open(data_path, 'r') as data_file:
population = tuple(json.load(data_file))
records = [gen_record(profile) for profile in population]
herd = Herd()
herd.populate(records)
herd.corral()
print()
print(herd.similarity_matrix)
def test_character_transposition(self):
"""See how character transposition in someone's name impacts probability
matrix.
"""
herd = Herd()
data_path = os.path.join(os.path.dirname(__file__),
'character_transposition_3x2.json')
with open(data_path, 'r') as data_file:
population = tuple(json.load(data_file))
records = [gen_record(profile) for profile in population]
herd = Herd()
herd.populate(records)
herd.corral()
print()
print(herd.similarity_matrix)
def setUp(self):
population = (
{
'forename': 'Adelyn',
'mid_forename': 'Heidenreich',
'current_surname': 'Bartell',
'birth_surname': 'Gerlach',
'address1': '448 Jones Street',
'postal_code': '95786',
'sex': 'F',
'birth_year': '1977',
'birth_month': '08',
'birth_day': '27'
},
{
'forename': 'Jane',
'current_surname': 'Doe',
'address1': '448 Jones Street',
'postal_code': '95786',
'sex': 'F',
'birth_year': '1977',
'birth_month': '08',
'birth_day': '27'
},
{
'forename': 'Adelyn',
'current_surname': 'Bartell',
'address1': '612 Johson Ave',
'postal_code': '92436',
'sex': 'F',
'birth_year': '1977',
'birth_month': '08',
'birth_day': '27'
}
)
records = [gen_record(profile) for profile in population]
self.herd = Herd()
self.herd.populate(records)
self.herd.corral()
def test_populating_herd(self):
records = [gen_record(profile) for profile in self.profiles]
herd = Herd()
herd.populate(records)
self.assertEqual(herd.size, 100)
def setUp(self):
population = (
{
'forename': 'Adelyn',
'mid_forename': 'Heidenreich',
'current_surname': 'Bartell',
'birth_surname': 'Gerlach',
'address1': '448 Jones Street',
'postal_code': '95786',
'sex': 'M',
'national_id1': 'D599776',
'birth_year': '1977',
'birth_month': '08',
'birth_day': '27'
},
{
'forename': 'Adelyn',
'mid_forename': 'Frederich',
'current_surname': 'Gerlach'
},
{
'forename': 'Joseph',
'current_surname': 'Smith',
'address1': '448 Jones Street',
'postal_code': '95786',
'sex': 'M',
'national_id1': 'D599776',
'birth_year': '1977',
'birth_month': '08',
'birth_day': '27'
},
{
'forename': 'John',
'mid_forename': 'Heidenreich',
'current_surname': 'Smith',
'birth_surname': 'Gerlach',
'address1': '448 Jones Avenue',
'postal_code': '97856',
'sex': 'F',
'national_id1': 'D599886',
'birth_year': '1986',
'birth_month': '10',
'birth_day': '27'
},
{
'forename': 'Jason',
'current_surname': 'Sanders',
'address1': '448 Jones Street',
'address2': 'Apt. A',
'postal_code': '97586',
'sex': 'F',
'national_id1': 'D597976',
'birth_year': '1977',
'birth_month': '10',
'birth_day': '27'
}
)
records = [gen_record(profile) for profile in population]
self.herd = Herd()
self.herd.populate(records)
self.herd.corral()
def test_record_generation_from_fake_profiles(self):
records = [gen_record(profile) for profile in self.profiles]
self.assertEqual(len(records), 100)