def test_not_implemented_error(self):
# Convert data to list
values = self.data_single.tolist()
# Create an object with links to the model and time series
problem = pints.SingleOutputProblem(self.model_single, self.times,
values)
# Create error measure
error = pints.NormalisedRootMeanSquaredError(problem)
# Check that not implemented error is raised for evaluateS1
self.assertRaisesRegex(NotImplementedError, '', error.evaluateS1, 1)
def test_call_two_dim_array_single(self):
# Convert data to array of shape (n_times, 1)
values = np.reshape(self.data_single, (self.n_times, 1))
# Create an object with links to the model and time series
problem = pints.SingleOutputProblem(self.model_single, self.times,
values)
# Create error measure
error = pints.NormalisedRootMeanSquaredError(problem)
# Evaluate likelihood for test parameters
test_parameters = [3]
score = error(test_parameters)
# Check that error returns expected value
# Expected = sqrt(mean((input - 1) ** 2)) / sqrt(mean(2 ** 2))
self.assertEqual(score, 0.5)
def test_normalised_root_mean_squared_error(self):
# Tests :class:`pints.NormalisedRootMeanSquaredError`.
p = MiniProblem()
e = pints.NormalisedRootMeanSquaredError(p)
self.assertEqual(e.n_parameters(), 3)
float(e([1, 2, 3]))
self.assertEqual(e([-1, 2, 3]), 0)
self.assertNotEqual(np.all(e([1, 2, 3])), 0)
x = [0, 0, 0]
y = 1.0
self.assertEqual(e(x), y)
x = [1, 1, 1]
y = np.sqrt((4 + 1 + 4) / 3) / np.sqrt((1 + 4 + 9) / 3)
self.assertAlmostEqual(e(x), y)
p = MultiMiniProblem()
self.assertRaisesRegex(
ValueError,
'This measure is only defined for single output problems.',
pints.NormalisedRootMeanSquaredError, p)