def test_grid_search_single_sample_multivariate_normal():
"""
Supposed to run into problems b/c nr splits > then nr_samples
"""
cv = 5
m = MultivariateNormalTransition()
m_grid = GridSearchCV(m, {"scaling": np.logspace(-5, 1.5, 5)}, cv=cv)
df, w = data(1)
m_grid.fit(df, w)
assert m_grid.cv == cv
def test_gaussian_multiple_populations_crossval_kde(db_path, sampler):
sigma_x = 1
sigma_y = 0.5
y_observed = 2
def model(args):
return {"y": st.norm(args['x'], sigma_y).rvs()}
models = [model]
models = list(map(FunctionModel, models))
nr_populations = 4
population_size = ConstantPopulationSize(600)
parameter_given_model_prior_distribution = [
Distribution(x=st.norm(0, sigma_x))
]
parameter_perturbation_kernels = [
GridSearchCV(
MultivariateNormalTransition(),
{"scaling": np.logspace(-1, 1.5, 5)},
)
]
abc = ABCSMC(
models,
parameter_given_model_prior_distribution,
MinMaxDistance(measures_to_use=["y"]),
population_size,
transitions=parameter_perturbation_kernels,
eps=MedianEpsilon(0.2),
sampler=sampler,
)
abc.new(db_path, {"y": y_observed})
minimum_epsilon = -1
abc.do_not_stop_when_only_single_model_alive()
history = abc.run(minimum_epsilon, max_nr_populations=nr_populations)
posterior_x, posterior_weight = history.get_distribution(0, None)
posterior_x = posterior_x["x"].values
sort_indices = np.argsort(posterior_x)
f_empirical = sp.interpolate.interp1d(
np.hstack((-200, posterior_x[sort_indices], 200)),
np.hstack((0, np.cumsum(posterior_weight[sort_indices]), 1)),
)
sigma_x_given_y = 1 / np.sqrt(1 / sigma_x**2 + 1 / sigma_y**2)
mu_x_given_y = sigma_x_given_y**2 * y_observed / sigma_y**2
expected_posterior_x = st.norm(mu_x_given_y, sigma_x_given_y)
x = np.linspace(-8, 8)
max_distribution_difference = np.absolute(
f_empirical(x) - expected_posterior_x.cdf(x)).max()
assert max_distribution_difference < 0.052
assert history.max_t == nr_populations - 1
mean_emp, std_emp = mean_and_std(posterior_x, posterior_weight)
assert abs(mean_emp - mu_x_given_y) < 0.07
assert abs(std_emp - sigma_x_given_y) < 0.12
def test_grid_search_multivariate_normal():
m = MultivariateNormalTransition()
m_grid = GridSearchCV(m, {"scaling": np.logspace(-5, 1.5, 5)}, n_jobs=1)
df, w = data(20)
m_grid.fit(df, w)
