def test_sample_and_predict(x, w):
# Use output transform to ensure that is handled correctly.
reg = GPARRegressor(
replace=False,
impute=False,
linear=True,
linear_scale=1.0,
nonlinear=False,
noise=1e-8,
normalise_y=False,
transform_y=squishing_transform,
)
# Test checks.
with pytest.raises(ValueError):
reg.sample(x, w)
with pytest.raises(RuntimeError):
reg.sample(x, w, posterior=True)
# Test that output is simplified correctly.
assert isinstance(reg.sample(x, w, p=2), np.ndarray)
assert isinstance(reg.sample(x, w, p=2, num_samples=2), list)
# Test that it produces random samples. Not sure how to test correctness.
all_different(reg.sample(x, w, p=2), reg.sample(x, w, p=2))
all_different(reg.sample(x, w, p=2, latent=True),
reg.sample(x, w, p=2, latent=True))
# Test that mean of posterior samples are around the data.
y = reg.sample(x, w, p=2)
reg.condition(x, y, w)
approx(y,
np.mean(reg.sample(x, w, posterior=True, num_samples=100), axis=0),
atol=5e-2)
approx(
y,
np.mean(reg.sample(x, w, latent=True, posterior=True, num_samples=100),
axis=0),
atol=5e-2,
)
# Test that prediction is around the data.
approx(y, reg.predict(x, w, num_samples=100), atol=5e-2)
approx(y, reg.predict(x, w, latent=True, num_samples=100), atol=5e-2)
# Test that prediction is confident.
_, lowers, uppers = reg.predict(x,
w,
num_samples=100,
credible_bounds=True)
approx(uppers, lowers, atol=5e-2)
def test_sample_and_predict():
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)
# Test checks.
yield raises, ValueError, lambda: reg.sample(x)
yield raises, RuntimeError, lambda: reg.sample(x, posterior=True)
# Test that output is simplified correctly.
yield isinstance, reg.sample(x, p=2), np.ndarray
yield isinstance, reg.sample(x, p=2, num_samples=2), list
# Test that it produces random samples. Not sure how to test correctness.
yield ge, np.sum(np.abs(reg.sample(x, p=2) - reg.sample(x, p=2))), 1e-2
yield ge, np.sum(
np.abs(
reg.sample(x, p=2, latent=True) -
reg.sample(x, p=2, latent=True))), 1e-3
# Test that mean of posterior samples are around the data.
y = reg.sample(x, p=2)
reg.fit(x, y, iters=0)
yield approx, y, np.mean(reg.sample(x, posterior=True, num_samples=20),
axis=0), 4
yield approx, y, np.mean(reg.sample(x,
latent=True,
posterior=True,
num_samples=20),
axis=0), 4
# Test that prediction is around the data.
yield approx, y, reg.predict(x, num_samples=20), 4
yield approx, y, reg.predict(x, latent=True, num_samples=20), 4
# Test that prediction is confident.
_, lowers, uppers = reg.predict(x, num_samples=10, credible_bounds=True)
yield ok, np.less_equal(uppers - lowers, 1e-3).all()
def test_sample_and_predict():
# Use output transform to ensure that is handled correctly.
reg = GPARRegressor(replace=False, impute=False,
linear=True, linear_scale=1., nonlinear=False,
noise=1e-8, normalise_y=False,
transform_y=squishing_transform)
x = np.linspace(0, 5, 5)
# Test checks.
with pytest.raises(ValueError):
reg.sample(x)
with pytest.raises(RuntimeError):
reg.sample(x, posterior=True)
# Test that output is simplified correctly.
assert isinstance(reg.sample(x, p=2), np.ndarray)
assert isinstance(reg.sample(x, p=2, num_samples=2), list)
# Test that it produces random samples. Not sure how to test correctness.
assert np.sum(np.abs(reg.sample(x, p=2) - reg.sample(x, p=2))) >= 1e-2
assert np.sum(np.abs(reg.sample(x, p=2, latent=True) -
reg.sample(x, p=2, latent=True))) >= 1e-3
# Test that mean of posterior samples are around the data.
y = reg.sample(x, p=2)
reg.condition(x, y)
approx(y, np.mean(reg.sample(x,
posterior=True,
num_samples=100), axis=0), digits=3)
approx(y, np.mean(reg.sample(x,
latent=True,
posterior=True,
num_samples=100), axis=0), digits=3)
# Test that prediction is around the data.
approx(y, reg.predict(x, num_samples=100), digits=3)
approx(y, reg.predict(x, latent=True, num_samples=100), digits=3)
# Test that prediction is confident.
_, lowers, uppers = reg.predict(x, num_samples=100, credible_bounds=True)
assert np.less_equal(uppers - lowers, 1e-2).all()
y = f + noise * np.random.randn(n, 3)
x_obs, y_obs = x[::8], y[::8]
# Fit and predict GPAR.
model = GPARRegressor(scale=0.1,
linear=True,
linear_scale=10.,
nonlinear=True,
nonlinear_scale=0.1,
noise=0.1,
impute=True,
replace=False,
normalise_y=False)
model.fit(x_obs, y_obs)
means, lowers, uppers = \
model.predict(x, num_samples=100, credible_bounds=True, latent=True)
# Fit and predict independent GPs: set markov=0.
igp = GPARRegressor(scale=0.1,
linear=True,
linear_scale=10.,
nonlinear=True,
nonlinear_scale=0.1,
noise=0.1,
markov=0,
normalise_y=False)
igp.fit(x_obs, y_obs)
igp_means, igp_lowers, igp_uppers = \
igp.predict(x, num_samples=100, credible_bounds=True, latent=True)
# Plot the result.
model = GPARRegressor(scale=0.1,
linear=False, nonlinear=True, nonlinear_scale=0.5,
impute=True, replace=True,
noise=0.1, normalise_y=True)
# Sample observations and discard some.
y = model.sample(x, p=3)
y_obs = y.copy()
y_obs[np.random.permutation(100)[:25], 0] = np.nan
y_obs[np.random.permutation(100)[:50], 1] = np.nan
y_obs[np.random.permutation(100)[:75], 2] = np.nan
# Fit model and predict.
model.fit(x, y)
means, lowers, uppers = \
model.predict(x, num_samples=200, latent=False, credible_bounds=True)
# Plot the result.
plt.figure(figsize=(8, 6))
for i in range(3):
plt.subplot(3, 1, i + 1)
plt.plot(x, means[:, i], label='Prediction', style='pred')
plt.fill_between(x, lowers[:, i], uppers[:, i], style='pred')
plt.scatter(x, y[:, i], label='Truth', style='test')
plt.scatter(x, y_obs[:, i], label='Observations', style='train')
plt.ylabel(f'Output {i + 1}')
wbml.plot.tweak(legend=i == 0)
plt.tight_layout()
plt.show()
replace=True,
noise=0.1,
normalise_y=True,
)
# Sample observations and discard some.
y = model.sample(x, p=3)
y_obs = y.copy()
y_obs[np.random.permutation(100)[:25], 0] = np.nan
y_obs[np.random.permutation(100)[:50], 1] = np.nan
y_obs[np.random.permutation(100)[:75], 2] = np.nan
# Fit model and predict.
model.fit(x, y)
means, lowers, uppers = model.predict(x,
num_samples=200,
latent=False,
credible_bounds=True)
# Plot the result.
plt.figure(figsize=(8, 6))
for i in range(3):
plt.subplot(3, 1, i + 1)
plt.plot(x, means[:, i], label="Prediction", style="pred")
plt.fill_between(x, lowers[:, i], uppers[:, i], style="pred")
plt.scatter(x, y[:, i], label="Truth", style="test")
plt.scatter(x, y_obs[:, i], label="Observations", style="train")
plt.ylabel(f"Output {i + 1}")
wbml.plot.tweak(legend=i == 0)
plt.tight_layout()
# Fit and predict GPAR.
model = GPARRegressor(
scale=0.1,
linear=True,
linear_scale=10.0,
nonlinear=True,
nonlinear_scale=0.1,
noise=0.1,
impute=True,
replace=False,
normalise_y=False,
)
model.fit(x_obs, y_obs)
means, lowers, uppers = model.predict(x,
num_samples=200,
credible_bounds=True,
latent=True)
# Fit and predict independent GPs: set `markov=0` in GPAR.
igp = GPARRegressor(
scale=0.1,
linear=True,
linear_scale=10.0,
nonlinear=True,
nonlinear_scale=0.1,
noise=0.1,
markov=0,
normalise_y=False,
)
igp.fit(x_obs, y_obs)
igp_means, igp_lowers, igp_uppers = igp.predict(x,