def test_logpdf_differentiable():
reg = GPARRegressor(replace=False, impute=False,
linear=True, linear_scale=1., nonlinear=False,
noise=1e-8, normalise_y=False)
x = np.linspace(0, 5, 10)
y = reg.sample(x, p=2, latent=True)
# Test that gradient calculation works.
reg.vs.requires_grad(True)
for var in reg.vs.get_vars():
assert var.grad is None
reg.logpdf(torch.tensor(x), torch.tensor(y)).backward()
for var in reg.vs.get_vars():
assert var.grad is not None
def test_logpdf(x, w):
# Sample some data from a "sensitive" GPAR.
reg = GPARRegressor(
replace=False,
impute=False,
nonlinear=True,
nonlinear_scale=0.1,
linear=True,
linear_scale=10.0,
noise=1e-2,
normalise_y=False,
)
y = reg.sample(x, w, p=2, latent=True)
# Extract models.
gpar = _construct_gpar(reg, reg.vs, B.shape(B.uprank(x))[1], 2)
f1, e1 = gpar.layers[0]()
f2, e2 = gpar.layers[1]()
# Test computation under prior.
x1 = x
x2 = B.concat(B.uprank(x), y[:, 0:1], axis=1)
if w is not None:
x1 = WeightedUnique(x1, w[:, 0])
x2 = WeightedUnique(x2, w[:, 1])
logpdf1 = (f1 + e1)(x1).logpdf(y[:, 0])
logpdf2 = (f2 + e2)(x2).logpdf(y[:, 1])
approx(reg.logpdf(x, y, w), logpdf1 + logpdf2, atol=1e-6)
# Test computation under posterior.
post1 = f1.measure | ((f1 + e1)(x1), y[:, 0])
post2 = f2.measure | ((f2 + e2)(x2), y[:, 1])
e1_post = GP(e1.mean, e1.kernel, measure=post1)
e2_post = GP(e2.mean, e2.kernel, measure=post2)
logpdf1 = (post1(f1) + e1_post)(x1).logpdf(y[:, 0])
logpdf2 = (post2(f2) + e2_post)(x2).logpdf(y[:, 1])
with pytest.raises(RuntimeError):
reg.logpdf(x, y, w, posterior=True)
reg.condition(x, y, w)
approx(reg.logpdf(x, y, w, posterior=True), logpdf1 + logpdf2, atol=1e-6)
# Test that sampling missing gives a stochastic estimate.
y[::2, 0] = np.nan
all_different(
reg.logpdf(x, y, w, sample_missing=True),
reg.logpdf(x, y, w, sample_missing=True),
)
def test_logpdf(x, w):
# Sample some data from a "sensitive" GPAR.
reg = GPARRegressor(
replace=False,
impute=False,
nonlinear=True,
nonlinear_scale=0.1,
linear=True,
linear_scale=10.0,
noise=1e-2,
normalise_y=False,
)
y = reg.sample(x, w, p=2, latent=True)
# Extract models.
gpar = _construct_gpar(reg, reg.vs, B.shape(B.uprank(x))[1], 2)
f1, noise1 = gpar.layers[0]()
f2, noise2 = gpar.layers[1]()
if w is not None:
noise1 = noise1 / w[:, 0]
noise2 = noise2 / w[:, 1]
# Test computation under prior.
x1 = x
x2 = B.concat(B.uprank(x), y[:, 0:1], axis=1)
logpdf1 = f1(x1, noise1).logpdf(y[:, 0])
logpdf2 = f2(x2, noise2).logpdf(y[:, 1])
approx(reg.logpdf(x, y, w), logpdf1 + logpdf2, atol=1e-6)
# Test computation under posterior.
f1_post = f1 | (f1(x1, noise1), y[:, 0])
f2_post = f2 | (f2(x2, noise2), y[:, 1])
logpdf1 = f1_post(x1, noise1).logpdf(y[:, 0])
logpdf2 = f2_post(x2, noise2).logpdf(y[:, 1])
with pytest.raises(RuntimeError):
reg.logpdf(x, y, w, posterior=True)
reg.condition(x, y, w)
approx(reg.logpdf(x, y, w, posterior=True), logpdf1 + logpdf2, atol=1e-6)
# Test that sampling missing gives a stochastic estimate.
y[::2, 0] = np.nan
all_different(
reg.logpdf(x, y, w, sample_missing=True),
reg.logpdf(x, y, w, sample_missing=True),
)
def test_logpdf():
# Sample some data from a "sensitive" GPAR.
reg = GPARRegressor(replace=False,
impute=False,
nonlinear=True,
nonlinear_scale=0.1,
linear=True,
linear_scale=10.,
noise=1e-4,
normalise_y=False)
x = np.linspace(0, 5, 10)
y = reg.sample(x, p=2, latent=True)
# Extract models.
gpar = _construct_gpar(reg, reg.vs, 1, 2)
f1, e1 = gpar.layers[0]()
f2, e2 = gpar.layers[1]()
# Test computation under prior.
logpdf1 = (f1 + e1)(B.array(x)).logpdf(B.array(y[:, 0]))
x_stack = np.concatenate([x[:, None], y[:, 0:1]], axis=1)
logpdf2 = (f2 + e2)(B.array(x_stack)).logpdf(B.array(y[:, 1]))
yield approx, reg.logpdf(x, y), logpdf1 + logpdf2, 6
# Test computation under posterior.
e1_post = GP(e1.kernel, e1.mean, graph=e1.graph)
e2_post = GP(e2.kernel, e2.mean, graph=e2.graph)
f1_post = f1 | ((f1 + e1)(B.array(x)), B.array(y[:, 0]))
f2_post = f2 | ((f2 + e2)(B.array(x_stack)), B.array(y[:, 1]))
logpdf1 = (f1_post + e1_post)(B.array(x)).logpdf(B.array(y[:, 0]))
logpdf2 = (f2_post + e2_post)(B.array(x_stack)).logpdf(B.array(y[:, 1]))
yield raises, RuntimeError, lambda: reg.logpdf(x, y, posterior=True)
reg.fit(x, y, iters=0)
yield approx, reg.logpdf(x, y, posterior=True), logpdf1 + logpdf2, 6
# Test that sampling missing gives a stochastic estimate.
y[::2, 0] = np.nan
yield ge, \
np.abs(reg.logpdf(x, y, sample_missing=True) -
reg.logpdf(x, y, sample_missing=True)), \
1e-3
for sample in samples]
# Compute metrics of training
if x_valid is not None:
print('Predicting validation points')
samples = unnormalise(
model.sample(transform_x(x_valid),
num_samples=50,
latent=True,
posterior=True))
means = np.mean(samples, axis=0)
stds = np.std(samples, axis=0)
valid_rmse = np.mean((y_valid - means)**2)**0.5
valid_loglik = model.logpdf(transform_x(x_valid), y_valid) / len(x_valid)
else:
valid_rmse = 0
valid_loglik = 0
print('Predicting training points')
samples = unnormalise(
model.sample(transform_x(x), num_samples=50, latent=True, posterior=True))
means = np.mean(samples, axis=0)
stds = np.std(samples, axis=0)
train_rmse = np.mean((y - means)**2)**0.5
train_loglik = model.logpdf(transform_x(x), y) / len(x)
# Plot the result.