def test_fit_sample_constant(self):
model = GaussianKDE()
model.fit(self.constant)
sampled_data = model.sample(50)
assert isinstance(sampled_data, np.ndarray)
assert sampled_data.shape == (50, )
assert model._constant_value == 5
np.testing.assert_equal(np.full(50, 5), model.sample(50))
def test_fit_sample(self):
model = GaussianKDE()
model.fit(self.data)
sampled_data = model.sample(50)
assert isinstance(sampled_data, np.ndarray)
assert sampled_data.shape == (50, )
def test_pdf(self):
model = GaussianKDE()
model.fit(self.data)
sampled_data = model.sample(50)
# Test PDF
pdf = model.probability_density(sampled_data)
assert (0 < pdf).all()
def test_sample(self, kde_mock):
"""Sample calls the gaussian_kde.resample method."""
instance = GaussianKDE()
instance.fit(np.array([1, 2, 3, 4]))
model = kde_mock.return_value
model.resample.return_value = np.array([[1, 2, 3]])
samples = instance.sample(3)
instance._model.resample.assert_called_once_with(3)
np.testing.assert_equal(samples, np.array([1, 2, 3]))
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_sample_constant(self):
"""If constant_value is set, all the sample have the same value."""
# Setup
instance = GaussianKDE()
instance.fitted = True
instance.constant_value = 3
instance._replace_constant_methods()
expected_result = np.array([3, 3, 3, 3, 3])
# Run
result = instance.sample(5)
# Check
compare_nested_iterables(result, expected_result)
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_sample(self, kde_mock):
"""When fitted, we are able to use the model to get samples."""
# Setup
model_mock = kde_mock.return_value
model_mock.resample.return_value = np.array([[0, 1, 0, 1, 0]])
instance = GaussianKDE()
X = np.array([1, 2, 3, 4, 5])
instance.fit(X)
expected_result = np.array([0, 1, 0, 1, 0])
# Run
result = instance.sample(5)
# Check
compare_nested_iterables(result, expected_result)
assert instance.model == model_mock
kde_mock.assert_called_once_with(X)
model_mock.resample.assert_called_once_with(5)