def test_cdf(self):
model = GaussianKDE()
model.fit(self.data)
sampled_data = model.sample(50)
# Test the CDF
cdf = model.cumulative_distribution(sampled_data)
assert (0 <= cdf).all() and (cdf <= 1).all()
# Test CDF increasing function
sorted_data = sorted(sampled_data)
cdf = model.cumulative_distribution(sorted_data)
assert (np.diff(cdf) >= 0).all()
def test_second_tree_likelihood(self):
"""Assert second tree likelihood is correct."""
# Setup
# Build first tree
data = pd.read_csv('data/iris.data.csv')
tau_mat = data.corr(method='kendall').values
u_matrix = np.empty(data.shape)
for index, col in enumerate(data):
uni = GaussianKDE()
uni.fit(data[col])
u_matrix[:, index] = uni.cumulative_distribution(data[col])
first_tree = get_tree(TreeTypes.CENTER)
first_tree.fit(0, 4, tau_mat, u_matrix)
uni_matrix = np.array([[0.1, 0.2, 0.3, 0.4]])
likelihood_first_tree, conditional_uni_first = first_tree.get_likelihood(uni_matrix)
tau = first_tree.get_tau_matrix()
# Build second tree
second_tree = get_tree(TreeTypes.CENTER)
second_tree.fit(1, 3, tau, first_tree)
expected_likelihood_second_tree = 0.4888802429313932
# Run
likelihood_second_tree, out_u = second_tree.get_likelihood(conditional_uni_first)
# Check
assert compare_values_epsilon(likelihood_second_tree, expected_likelihood_second_tree)
def test_serialization_fit_model(self):
# Setup
instance = get_tree(TreeTypes.REGULAR)
X = pd.DataFrame(data=[
[1, 0, 0],
[0, 1, 0],
[0, 0, 1]
])
index = 0
n_nodes = X.shape[1]
tau_matrix = X.corr(method='kendall').values
univariates_matrix = np.empty(X.shape)
for i, column in enumerate(X):
distribution = GaussianKDE()
distribution.fit(X[column])
univariates_matrix[:, i] = distribution.cumulative_distribution(X[column])
instance.fit(index, n_nodes, tau_matrix, univariates_matrix)
# Run
result = Tree.from_dict(instance.to_dict())
# Check
assert result.to_dict() == instance.to_dict()
def test_cumulative_distribution(self, kde_mock):
"""cumulative_distribution evaluates with the model."""
# Setup
model_mock = kde_mock.return_value
model_mock.integrate_box_1d.side_effect = [0.0, 0.5, 1.0]
model_mock.dataset = MagicMock()
model_mock.dataset.mean.return_value = 1
model_mock.dataset.std.return_value = 0.1
fit_data = np.array([1, 2, 3, 4, 5])
instance = GaussianKDE()
instance.fit(fit_data)
call_data = np.array([-10, 0, 10])
expected_result = np.array([0.0, 0.5, 1.0])
expected_integrate_1d_box_call_args_list = [
((0.5, -10),
{}), # The first argument is the lower_bound (1 - 0.1*5)
((0.5, 0), {}),
((0.5, 10), {}),
]
# Run
result = instance.cumulative_distribution(call_data)
# Check
compare_nested_iterables(result, expected_result)
kde_mock.assert_called_once_with(fit_data)
assert (model_mock.integrate_box_1d.call_args_list ==
expected_integrate_1d_box_call_args_list)
def setUp(self):
self.data = pd.read_csv('data/iris.data.csv')
self.tau_mat = self.data.corr(method='kendall').values
self.u_matrix = np.empty(self.data.shape)
count = 0
for col in self.data:
uni = GaussianKDE()
uni.fit(self.data[col])
self.u_matrix[:, count] = uni.cumulative_distribution(self.data[col])
count += 1
self.tree = Tree(TreeTypes.DIRECT)
self.tree.fit(0, 4, self.tau_mat, self.u_matrix)
def test_cumulative_distribution(self):
"""cumulative_distribution evaluates with the model."""
instance = GaussianKDE()
instance.fit(np.array([0.9, 1.0, 1.1]))
cdf = instance.cumulative_distribution(np.array([
0.0, # There is no data below this (cdf = 0.0).
1.0, # Half the data is below this (cdf = 0.5).
2.0, # All the data is below this (cdf = 1.0).
-1.0 # There is no data below this (cdf = 0).
]))
assert np.all(np.isclose(cdf, np.array([0.0, 0.5, 1.0, 0.0]), atol=1e-3))
def test_to_dict_from_dict(self):
model = GaussianKDE()
model.fit(self.data)
sampled_data = model.sample(50)
params = model.to_dict()
model2 = GaussianKDE.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):
model = GaussianKDE()
model.fit(self.data)
sampled_data = model.sample(50)
path_to_model = os.path.join(self.test_dir.name, "model.pkl")
model.save(path_to_model)
model2 = GaussianKDE.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 test_to_dict_from_dict_constant(self):
model = GaussianKDE()
model.fit(self.constant)
sampled_data = model.sample(50)
pdf = model.probability_density(sampled_data)
cdf = model.cumulative_distribution(sampled_data)
params = model.to_dict()
model2 = GaussianKDE.from_dict(params)
np.testing.assert_equal(np.full(50, 5), sampled_data)
np.testing.assert_equal(np.full(50, 5), model2.sample(50))
np.testing.assert_equal(np.full(50, 1), pdf)
np.testing.assert_equal(np.full(50, 1), model2.probability_density(sampled_data))
np.testing.assert_equal(np.full(50, 1), cdf)
np.testing.assert_equal(np.full(50, 1), model2.cumulative_distribution(sampled_data))
def test_to_dict_fit_model(self):
# Setup
instance = get_tree(TreeTypes.REGULAR)
X = pd.DataFrame(data=[
[1, 0, 0],
[0, 1, 0],
[0, 0, 1]
])
index = 0
n_nodes = X.shape[1]
tau_matrix = X.corr(method='kendall').values
univariates_matrix = np.empty(X.shape)
for i, column in enumerate(X):
distribution = GaussianKDE()
distribution.fit(X[column])
univariates_matrix[:, i] = distribution.cumulative_distribution(X[column])
instance.fit(index, n_nodes, tau_matrix, univariates_matrix)
expected_result = {
'type': 'copulas.multivariate.tree.RegularTree',
'fitted': True,
'level': 1,
'n_nodes': 3,
'previous_tree': [
[0.8230112726144534, 0.3384880496294825, 0.3384880496294825],
[0.3384880496294825, 0.8230112726144534, 0.3384880496294825],
[0.3384880496294825, 0.3384880496294825, 0.8230112726144534]
],
'tau_matrix': [
[1.0, -0.49999999999999994, -0.49999999999999994],
[-0.49999999999999994, 1.0, -0.49999999999999994],
[-0.49999999999999994, -0.49999999999999994, 1.0]
],
'tree_type': TreeTypes.REGULAR,
'edges': [
{
'index': 0,
'D': set(),
'L': 0,
'R': 1,
'U': [
[0.7969636014074211, 0.6887638642325501, 0.12078520049364487],
[0.6887638642325501, 0.7969636014074211, 0.12078520049364487]
],
'likelihood': None,
'name': CopulaTypes.FRANK,
'neighbors': [],
'parents': None,
'tau': -0.49999999999999994,
'theta': -5.736282443655552
},
{
'index': 1,
'D': set(),
'L': 1,
'R': 2,
'U': [
[0.12078520049364491, 0.7969636014074213, 0.6887638642325501],
[0.12078520049364491, 0.6887638642325503, 0.7969636014074211]
],
'likelihood': None,
'name': CopulaTypes.FRANK,
'neighbors': [],
'parents': None,
'tau': -0.49999999999999994,
'theta': -5.736282443655552
}
],
}
# Run
result = instance.to_dict()
# Check
compare_nested_dicts(result, expected_result)
def test_percent_point_invertibility(self):
instance = GaussianKDE()
instance.fit(sample_univariate_bimodal())
cdf = np.random.random(size=1000)
x = instance.percent_point(cdf)
assert np.abs(instance.cumulative_distribution(x) - cdf).max() < 1e-6
