def test_fit_sample_distribution_dict(self):
data = sample_trivariate_xyz()
model = GaussianMultivariate(distribution={'x': GaussianKDE()})
model.fit(data)
sampled_data = model.sample(10)
assert sampled_data.shape == (10, 3)
def test_fit_sample_center(self):
data = sample_trivariate_xyz()
model = VineCopula('center')
model.fit(data)
sampled_data = model.sample(10)
assert sampled_data.shape == (10, 3)
def test_cdf(self):
data = sample_trivariate_xyz()
model = GaussianMultivariate()
model.fit(data)
sampled_data = model.sample(10)
# Test CDF
cdf = model.cumulative_distribution(sampled_data)
assert (0 <= cdf).all() and (cdf <= 1).all()
# Test CDF increasing function
for column in sampled_data.columns:
sorted_data = sampled_data.sort_values(column)
other_columns = data.columns.to_list()
other_columns.remove(column)
row = sorted_data.sample(1).iloc[0]
for column in other_columns:
sorted_data[column] = row[column]
cdf = model.cumulative_distribution(sorted_data)
diffs = np.diff(
cdf
) + 0.001 # Add tolerance to avoid floating precision issues.
assert (diffs >= 0).all()
def test_fit_sample_distribution_name(self):
data = sample_trivariate_xyz()
model = GaussianMultivariate(
'copulas.univariate.gaussian_kde.GaussianKDE')
model.fit(data)
sampled_data = model.sample(10)
assert sampled_data.shape == (10, 3)
def test_pdf(self):
data = sample_trivariate_xyz()
model = GaussianMultivariate()
model.fit(data)
sampled_data = model.sample(10)
# Test PDF
pdf = model.probability_density(sampled_data)
assert (0 < pdf).all()
def test_to_dict_from_dict(self):
data = sample_trivariate_xyz()
model = VineCopula('direct')
model.fit(data)
sampled_data = model.sample(10)
params = model.to_dict()
model2 = VineCopula.from_dict(params)
sampled_data = model2.sample(10)
assert sampled_data.shape == (10, 3)
def test_fit_sample_distribution_dict_multiple(self):
data = sample_trivariate_xyz()
model = GaussianMultivariate(
distribution={
'x': Univariate(parametric=ParametricType.PARAMETRIC),
'y': BetaUnivariate(),
'z': GaussianKDE()
})
model.fit(data)
sampled_data = model.sample(10)
assert sampled_data.shape == (10, 3)
def test_save_load(self):
data = sample_trivariate_xyz()
model = VineCopula('direct')
model.fit(data)
sampled_data = model.sample(10)
path_to_model = os.path.join(self.test_dir.name, "model.pkl")
model.save(path_to_model)
model2 = VineCopula.load(path_to_model)
sampled_data = model2.sample(10)
assert sampled_data.shape == (10, 3)
def test_fit_sample_direct(self):
data = sample_trivariate_xyz()
model = VineCopula('direct')
model.fit(data)
for N in [10, 50, 100]:
assert len(model.sample(N)) == N
sampled_data = model.sample(10)
assert sampled_data.shape == (10, 3)
for column in data.columns:
assert column in sampled_data
def test_fit_sample(self):
data = sample_trivariate_xyz()
model = GaussianMultivariate()
model.fit(data)
for N in [10, 50, 100]:
assert len(model.sample(N)) == N
sampled_data = model.sample(10)
assert sampled_data.shape == (10, 3)
for column in data.columns:
assert column in sampled_data
def test_to_dict_from_dict(self):
data = sample_trivariate_xyz()
model = GaussianMultivariate()
model.fit(data)
sampled_data = model.sample(10)
params = model.to_dict()
model2 = GaussianMultivariate.from_dict(params)
pdf = model.probability_density(sampled_data)
pdf2 = model2.probability_density(sampled_data)
assert np.all(np.isclose(pdf, pdf2, atol=0.01))
cdf = model.cumulative_distribution(sampled_data)
cdf2 = model2.cumulative_distribution(sampled_data)
assert np.all(np.isclose(cdf, cdf2, atol=0.01))
def test_save_load(self):
data = sample_trivariate_xyz()
model = GaussianMultivariate()
model.fit(data)
sampled_data = model.sample(10)
path_to_model = os.path.join(self.test_dir.name, "model.pkl")
model.save(path_to_model)
model2 = GaussianMultivariate.load(path_to_model)
pdf = model.probability_density(sampled_data)
pdf2 = model2.probability_density(sampled_data)
assert np.all(np.isclose(pdf, pdf2, atol=0.01))
cdf = model.cumulative_distribution(sampled_data)
cdf2 = model2.cumulative_distribution(sampled_data)
assert np.all(np.isclose(cdf, cdf2, atol=0.01))
def testMITCopulas():
import warnings
warnings.filterwarnings('ignore')
from copulas.datasets import sample_trivariate_xyz
from copulas.multivariate import GaussianMultivariate
from copulas.visualization import compare_3d
# Load a dataset with 3 columns that are not independent
real_data = sample_trivariate_xyz()
# Fit a gaussian copula to the data
copula = GaussianMultivariate()
copula.fit(real_data)
# Sample synthetic data
synthetic_data = copula.sample(len(real_data))
# Plot the real and the synthetic data to compare
compare_3d(real_data, synthetic_data)
return True
def test_cdf(self):
data = sample_trivariate_xyz()
model = GaussianMultivariate()
model.fit(data)
sampled_data = model.sample(10)
# Test CDF
cdf = model.cumulative_distribution(sampled_data)
assert (0 < cdf).all() and (cdf < 1).all()
# Test CDF increasing function
for column in sampled_data.columns:
sorted_data = sampled_data.sort_values(column)
other_columns = data.columns.to_list()
other_columns.remove(column)
row = sorted_data.sample(1).iloc[0]
for column in other_columns:
sorted_data[column] = row[column]
cdf = model.cumulative_distribution(sorted_data)
assert (np.diff(cdf) >= 0).all()
def test_compare_3d():
data = sample_trivariate_xyz()
compare_3d(data, data)
