def test_assemble_config_not_existing_obs():
with pytest.raises(ValidationError) as ve:
assemble_config(
{"observations": ["not_an_observation"]},
["a", "list", "of", "existing", "observations"],
)
expected_err_msg = (
"Invalid configuration of misfit preprocessor\n"
" - Found no match for observation not_an_observation (observations.0)\n"
)
assert expected_err_msg == str(ve.value)
def test_assemble_config(input_observations, expected_result):
config = assemble_config(
{"observations": input_observations},
["a", "list", "of", "existing", "observations"],
)
assert expected_result == sorted(config.observations)
def test_misfit_preprocessor_n_polynomials_w_correlation(num_polynomials):
state_size = 3
poly_states = [range(1, state_size + 1) for _ in range(num_polynomials)]
observations, simulated = generate_measurements(
num_polynomials,
poly_states=poly_states,
ensemble_size=10000,
)
measured_data = MockedMeasuredData(observations, simulated)
# We add a correlation:
measured_data.data["poly_0"] = measured_data.data["poly_1"] * 2.0
config = assemble_config(
{
"clustering": {
"method": "spearman_correlation"
},
"scaling": {
"threshold": 0.99
},
},
list(measured_data.data.columns.get_level_values(0)),
).snapshot
reporter_mock = Mock()
configs = misfit_preprocessor.run(config, measured_data, reporter_mock)
assert num_polynomials == len(configs) - 1, configs
def test_misfit_preprocessor_state_uneven_size(state_size):
num_polynomials = len(state_size)
poly_states = [range(1, size + 1) for size in state_size]
observations, simulated = generate_measurements(
num_polynomials,
poly_states=poly_states,
ensemble_size=30000,
)
measured_data = MockedMeasuredData(observations, simulated)
obs_keys = measured_data.data.columns.get_level_values(0)
config = assemble_config(
{
"clustering": {
"method": "spearman_correlation",
"spearman_correlation": {
"fcluster": {
"t": num_polynomials + 1,
"criterion": "maxclust"
}
},
}
},
obs_keys,
).snapshot
reporter_mock = Mock()
configs = misfit_preprocessor.run(config, measured_data, reporter_mock)
assert num_polynomials == len(configs), configs
assert_homogen_clusters(configs)
def test_misfit_preprocessor_n_polynomials(num_polynomials, method):
"""
The goal of this test is to create a data set of uncorrelated polynomials,
meaning that there should be as many clusters as there are input polynomials.
"""
state_size = 3
poly_states = [range(1, state_size + 1) for _ in range(num_polynomials)]
observations, simulated = generate_measurements(
num_polynomials,
poly_states=poly_states,
ensemble_size=10000,
)
measured_data = MockedMeasuredData(observations, simulated)
# We set the PCA threshold to 0.99 so a high degree of correlation is required
# to have an impact. Setting it this way only has an impact for "auto_scale"
obs_keys = measured_data.data.columns.get_level_values(0)
config = assemble_config(
{
"clustering": {
"method": method
},
"scaling": {
"threshold": 0.99
}
},
obs_keys,
)
reporter_mock = Mock()
configs = misfit_preprocessor.run(config.snapshot, measured_data,
reporter_mock)
assert_homogen_clusters(configs)
assert num_polynomials == len(configs), configs
def test_assemble_config_default_observations():
config = assemble_config(
{},
["a", "list", "of", "existing", "observations"],
).snapshot
assert sorted(["a", "list", "of", "existing",
"observations"]) == sorted(config.observations)
def _fetch_scaling_parameters(config_record, observations):
config = misfit_preprocessor.assemble_config(
config_record,
observations,
)
if not config.valid:
# The config is loaded by misfit_preprocessor.run first. The
# second time should never fail!
raise ValueError("Misfit preprocessor config not valid on second load")
scale_conf = config.snapshot.scaling
return {
"threshold": scale_conf.threshold,
}
def test_misfit_preprocessor_configuration_errors():
with pytest.raises(misfit_preprocessor.ValidationError) as ve:
assemble_config(
{
"unknown_key": ["not in set"],
"clustering": {
"method": "spearman_correlation",
"spearman_correlation": {
"fcluster": {
"threshold": 1.0
}
},
},
},
["a", "list", "of", "observations"],
)
expected_err_msg = (
"Invalid configuration of misfit preprocessor\n"
" - Unknown key: unknown_key (root level)\n"
" - Unknown key: threshold (clustering.spearman_correlation.fcluster)\n"
)
assert expected_err_msg == str(ve.value)
def test_misfit_preprocessor_state_size(state_size, method, linkage):
if state_size == [5, 5, 5, 5, 100]:
if linkage == "average":
pytest.skip("Produces wrong number of clusters")
elif method == "auto_scale":
pytest.skip(
"Produces not homogeneous clusters due to PCA analysis")
num_polynomials = 5
poly_states = [range(1, size + 1) for size in state_size]
observations, simulated = generate_measurements(
num_polynomials,
poly_states=poly_states,
ensemble_size=30000,
)
measured_data = MockedMeasuredData(observations, simulated)
obs_keys = measured_data.data.columns.get_level_values(0)
config = assemble_config(
{
"clustering": {
"method": method,
method: {
"linkage": {
"method": linkage
}
}
},
"scaling": {
"threshold": 0.99
},
},
obs_keys,
).snapshot
reporter_mock = Mock()
configs = misfit_preprocessor.run(config, measured_data, reporter_mock)
assert_homogen_clusters(configs)
assert num_polynomials == len(configs), configs