def test___init___copies_metadata():
"""Test the ``__init__`` method.
This test assures that the metadata provided to the model is copied,
so that any modifications don't change the input.
Setup:
- Initialize two models with the same metadata and data.
Expected behavior:
- The metadata for each model and the provided metadata should all be different.
"""
# Setup
metadata, data = load_tabular_demo('student_placements', metadata=True)
# Run
model = GaussianCopula(table_metadata=metadata,
categorical_transformer='label_encoding',
default_distribution='gamma')
model.fit(data)
model2 = GaussianCopula(table_metadata=metadata,
categorical_transformer='label_encoding',
default_distribution='beta')
model2.fit(data)
# Assert
assert model._metadata != metadata
assert model._metadata != model2._metadata
assert model2._metadata != metadata
gamma = 'copulas.univariate.gamma.GammaUnivariate'
beta = 'copulas.univariate.beta.BetaUnivariate'
assert all(distribution == gamma
for distribution in model.get_distributions().values())
assert all(distribution == beta
for distribution in model2.get_distributions().values())
def test_constraints(tmpdir):
# Setup
employees = load_tabular_demo()
fixed_company_department_constraint = FixedCombinations(
column_names=['company', 'department'])
age_gt_age_when_joined_constraint = Inequality(
low_column_name='age_when_joined', high_column_name='age')
age_range_constraint = ScalarRange('age', 29, 50)
constraints = [
fixed_company_department_constraint, age_gt_age_when_joined_constraint,
age_range_constraint
]
# Run
gc = GaussianCopula(constraints=constraints,
min_value=None,
max_value=None)
gc.fit(employees)
gc.save(tmpdir / 'test.pkl')
gc = gc.load(tmpdir / 'test.pkl')
sampled = gc.sample(10)
# Assert
assert all(age_gt_age_when_joined_constraint.is_valid(sampled))
assert all(age_range_constraint.is_valid(sampled))
assert all(fixed_company_department_constraint.is_valid(sampled))
def test_unique_combination_constraint():
employees = load_tabular_demo()
unique_company_department_constraint = UniqueCombinations(
columns=['company', 'department'], handling_strategy='transform')
model = CopulaGAN(constraints=[unique_company_department_constraint])
model.fit(employees)
model.sample(10)
def test_fixed_combination_constraint():
# Setup
employees = load_tabular_demo()
fixed_company_department_constraint = FixedCombinations(
column_names=['company', 'department'])
model = CTGAN(constraints=[fixed_company_department_constraint])
# Run
model.fit(employees)
sampled = model.sample(10)
# Assert
assert all(fixed_company_department_constraint.is_valid(sampled))
def test_constraints_reject_sampling_zero_valid():
"""Ensure everything works if no rows are valid on the first try.
See https://github.com/sdv-dev/SDV/issues/285
"""
employees = load_tabular_demo()
_IS_VALID_CALLED.clear()
constraint = CustomConstraint(is_valid=_is_valid)
gc = GaussianCopula(constraints=[constraint])
gc.fit(employees)
gc.sample(10)
def __init__(self, separation_char, input_data="", input_path=""):
self.input_data = input_data
if input_data == "demo":
self.data = load_tabular_demo('student_placements') # demo data
elif input_data == "ml-100k" or input_data == "own" or input_data == "amazon":
#self.data_dir = f"{conf.DATA_DIR}/ml-100k/"
if input_data == "own":
self.input_path = input_path
elif input_data == "amazon":
self.input_data = f"{conf.DATA_DIR}/amazon/amazon_ratings.csv"
self.sparse_data = self.load_sparse_data(separation_char)
else:
print(
"Dataset was not provided or implementation is not yet prepared to handle this dataset.\nPlease try ml-100k or demo dataset."
)
def __init__(self, input_data="", input_path=""):
self.max_active = 1000 # 30 for "own" dataset
self.min_active = 350 # only 33 users # 5 for "own dataset"
self.input_data = input_data
if input_data == "demo":
self.data = load_tabular_demo('student_placements') # demo data
elif input_data == "ml-100k" or input_data == "own":
#self.data_dir = f"{conf.DATA_DIR}/ml-100k/"
if input_data == "own":
self.input_path = input_path
self.active_data_dense, self.inactive_data_dense, self.active_data_sparse, self.inactive_data_sparse = self.load_data(
)
else:
print(
"Dataset was not provided or implementation is not yet prepared to handle this dataset.\nPlease try ml-100k or demo dataset."
)
def test_constraints():
employees = load_tabular_demo()
unique_company_department_constraint = UniqueCombinations(
columns=['company', 'department'], handling_strategy='transform')
age_gt_age_when_joined_constraint = GreaterThan(
low='age_when_joined', high='age', handling_strategy='reject_sampling')
years_in_the_company_constraint = ColumnFormula(
column='years_in_the_company',
formula=years_in_the_company,
handling_strategy='transform')
constraints = [
unique_company_department_constraint,
age_gt_age_when_joined_constraint, years_in_the_company_constraint
]
gc = GaussianCopula(constraints=constraints)
gc.fit(employees)
gc.sample(10)