def test_conditioning():
graph = Graph()
f1, e1 = GP(EQ(), graph=graph), GP(1e-8 * Delta(), graph=graph)
f2, e2 = GP(EQ(), graph=graph), GP(2e-8 * Delta(), graph=graph)
gpar = GPAR().add_layer(lambda: (f1, e1)).add_layer(lambda: (f2, e2))
x = array([[1], [2], [3]])
y = array([[4, 5], [6, 7], [8, 9]])
gpar = gpar | (x, y)
# Extract posterior processes.
f1_post, e1_post = gpar.layers[0]()
f2_post, e2_post = gpar.layers[1]()
# Test independence of noises.
yield eq, graph.kernels[f1_post, e1_post], ZeroKernel()
yield eq, graph.kernels[f2_post, e2_post], ZeroKernel()
# Test form of noises.
yield eq, e1.mean, e1_post.mean
yield eq, e1.kernel, e1_post.kernel
yield eq, e2.mean, e2_post.mean
yield eq, e2.kernel, e2_post.kernel
# Test posteriors.
yield approx, f1_post.mean(x), y[:, 0:1]
yield approx, f2_post.mean(B.concat([x, y[:, 0:1]], axis=1)), y[:, 1:2]
def objective(vs, m, x_data, y_data, locs):
"""NLML objective.
Args:
vs (:class:`varz.Vars`): Variable container.
m (int): Number of latent processes.
x_data (tensor): Time stamps of the observations.
y_data (tensor): Observations.
locs (tensor): Spatial locations of observations.
Returns:
scalar: Negative log-marginal likelihood.
"""
y_proj, _, S, noises_obs = project(vs, m, y_data, locs)
xs, noise_obs, noises_latent = model(vs, m)
# Add contribution of latent processes.
lml = 0
for i, (x, y) in enumerate(zip(xs, y_proj)):
e_signal = GP((noise_obs / S[i] + noises_latent[i]) * Delta(),
graph=x.graph)
lml += (x + e_signal)(x_data).logpdf(y)
e_noise = GP(noise_obs / S[i] * Delta(), graph=x.graph)
lml -= e_noise(x_data).logpdf(y)
# Add regularisation contribution.
lml += B.sum(Normal(Diagonal(noises_obs)).logpdf(B.transpose(y_data)))
# Return negative the evidence, normalised by the number of data points.
n, p = B.shape(y_data)
return -lml / (n * p)
def test_conditioning():
graph = Graph()
f1, e1 = GP(EQ(), graph=graph), GP(1e-8 * Delta(), graph=graph)
f2, e2 = GP(EQ(), graph=graph), GP(2e-8 * Delta(), graph=graph)
gpar = GPAR().add_layer(lambda: (f1, e1)).add_layer(lambda: (f2, e2))
x = tensor([[1], [2], [3]])
y = tensor([[4, 5],
[6, 7],
[8, 9]])
gpar = gpar | (x, y)
# Extract posterior processes.
f1_post, e1_post = gpar.layers[0]()
f2_post, e2_post = gpar.layers[1]()
# Test independence of noises.
assert graph.kernels[f1_post, e1_post] == ZeroKernel()
assert graph.kernels[f2_post, e2_post] == ZeroKernel()
# Test form of noises.
assert e1.mean == e1_post.mean
assert e1.kernel == e1_post.kernel
assert e2.mean == e2_post.mean
assert e2.kernel == e2_post.kernel
# Test posteriors.
approx(f1_post.mean(x), y[:, 0:1])
approx(f2_post.mean(B.concat(x, y[:, 0:1], axis=1)), y[:, 1:2])
def test_logpdf():
graph = Graph()
f1, e1 = GP(EQ(), graph=graph), GP(2e-1 * Delta(), graph=graph)
f2, e2 = GP(Linear(), graph=graph), GP(1e-1 * Delta(), graph=graph)
gpar = GPAR().add_layer(lambda: (f1, e1)).add_layer(lambda: (f2, e2))
# Sample some data from GPAR.
x = B.linspace(0, 2, 10, dtype=torch.float64)[:, None]
y = gpar.sample(x, latent=True)
# Compute logpdf.
logpdf1 = (f1 + e1)(x).logpdf(y[:, 0])
logpdf2 = (f2 + e2)(B.concat([x, y[:, 0:1]], axis=1)).logpdf(y[:, 1])
# Test computation of GPAR.
yield eq, gpar.logpdf(x, y), logpdf1 + logpdf2
yield eq, gpar.logpdf(x, y, only_last_layer=True), logpdf2
# Test resuming computation.
x_int, x_ind_int = gpar.logpdf(x, y, return_inputs=True, outputs=[0])
yield eq, gpar.logpdf(x_int, y, x_ind=x_ind_int, outputs=[1]), logpdf2
# Test that sampling missing gives a stochastic estimate.
y[1, 0] = np.nan
yield ge, \
B.abs(gpar.logpdf(x, y, sample_missing=True) -
gpar.logpdf(x, y, sample_missing=True)).numpy(), \
1e-3
def __init__(
self,
measure: Measure,
xs: List[GP],
h: AbstractMatrix,
noise_obs: B.Numeric,
noises_latent: B.Numeric,
):
self.measure = measure
self.xs = xs
self.h = h
self.noise_obs = noise_obs
self.noises_latent = noises_latent
# Create noisy latent processes.
xs_noisy = [
x + GP(self.noises_latent[i] * Delta(), measure=self.measure)
for i, x in enumerate(xs)
]
# Create noiseless observed processes.
self.fs = _matmul(self.h, self.xs)
# Create observed processes.
fs_noisy = _matmul(self.h, xs_noisy)
self.ys = [
f + GP(self.noise_obs * Delta(), measure=self.measure) for f in fs_noisy
]
def test_sample():
graph = Graph()
x = array([1, 2, 3])[:, None]
# Test that it produces random samples. Not sure how to test for
# correctness.
f1, e1 = GP(EQ(), graph=graph), GP(1e-1 * Delta(), graph=graph)
f2, e2 = GP(EQ(), graph=graph), GP(1e-1 * Delta(), graph=graph)
gpar = GPAR().add_layer(lambda: (f1, e1)).add_layer(lambda: (f2, e2))
yield ge, B.sum(B.abs(gpar.sample(x) - gpar.sample(x))), 1e-3
yield ge, \
B.sum(B.abs(gpar.sample(x, latent=True) -
gpar.sample(x, latent=True))), \
1e-3
# Test that posterior latent samples are around the data that is
# conditioned on.
graph = Graph()
f1, e1 = GP(EQ(), graph=graph), GP(1e-8 * Delta(), graph=graph)
f2, e2 = GP(EQ(), graph=graph), GP(1e-8 * Delta(), graph=graph)
gpar = GPAR().add_layer(lambda: (f1, e1)).add_layer(lambda: (f2, e2))
y = gpar.sample(x, latent=True)
gpar = gpar | (x, y)
yield approx, gpar.sample(x), y, 3
yield approx, gpar.sample(x, latent=True), y, 3
def test_conditioning(x, w):
prior = Measure()
f1, e1 = GP(EQ(), measure=prior), GP(1e-10 * Delta(), measure=prior)
f2, e2 = GP(EQ(), measure=prior), GP(2e-10 * Delta(), measure=prior)
gpar = GPAR().add_layer(lambda: (f1, e1)).add_layer(lambda: (f2, e2))
# Generate some data.
y = B.concat((f1 + e1)(x).sample(), (f2 + e2)(x).sample(), axis=1)
# Extract posterior processes.
gpar = gpar | (x, y, w)
f1_post, e1_post = gpar.layers[0]()
f2_post, e2_post = gpar.layers[1]()
# Test independence of noises.
assert f1_post.measure.kernels[f1_post, e1_post] == ZeroKernel()
assert f2_post.measure.kernels[f2_post, e2_post] == ZeroKernel()
# Test form of noises.
assert e1.mean == e1_post.mean
assert e1.kernel == e1_post.kernel
assert e2.mean == e2_post.mean
assert e2.kernel == e2_post.kernel
# Test posteriors.
approx(f1_post.mean(x), y[:, 0:1], atol=1e-3)
approx(f2_post.mean(B.concat(x, y[:, 0:1], axis=1)), y[:, 1:2], atol=1e-3)
def test_logpdf(x, w):
prior = Measure()
f1, e1 = GP(EQ(), measure=prior), GP(2e-1 * Delta(), measure=prior)
f2, e2 = GP(Linear(), measure=prior), GP(1e-1 * Delta(), measure=prior)
gpar = GPAR().add_layer(lambda: (f1, e1)).add_layer(lambda: (f2, e2))
# Generate some data.
y = gpar.sample(x, w, latent=True)
# Compute logpdf.
x1 = WeightedUnique(x, w[:, 0])
x2 = WeightedUnique(B.concat(x, y[:, 0:1], axis=1), w[:, 1])
logpdf1 = (f1 + e1)(x1).logpdf(y[:, 0])
logpdf2 = (f2 + e2)(x2).logpdf(y[:, 1])
# Test computation of GPAR.
assert gpar.logpdf(x, y, w) == logpdf1 + logpdf2
assert gpar.logpdf(x, y, w, only_last_layer=True) == logpdf2
# Test resuming computation.
x_partial, x_ind_partial = gpar.logpdf(x,
y,
w,
return_inputs=True,
outputs=[0])
assert gpar.logpdf(x_partial, y, w, x_ind=x_ind_partial,
outputs=[1]) == logpdf2
# Test that sampling missing gives a stochastic estimate.
y[1, 0] = np.nan
all_different(
gpar.logpdf(x, y, w, sample_missing=True),
gpar.logpdf(x, y, w, sample_missing=True),
)
def test_obs(x):
prior = Measure()
f = GP(EQ(), measure=prior)
e = GP(1e-1 * Delta(), measure=prior)
# Generate some data.
w = B.rand(B.shape(x)[0]) + 1e-2
y = f(x).sample()
# Set some observations to be missing.
y_missing = y.copy()
y_missing[::2] = np.nan
# Check dense case.
gpar = GPAR()
obs = gpar._obs(x, None, y_missing, w, f, e)
assert isinstance(obs, Obs)
approx(
prior.logpdf(obs),
(f + e)(WeightedUnique(x[1::2], w[1::2])).logpdf(y[1::2]),
atol=1e-6,
)
# Check sparse case.
gpar = GPAR(x_ind=x)
obs = gpar._obs(x, x, y_missing, w, f, e)
assert isinstance(obs, SparseObs)
approx(
prior.logpdf(obs),
(f + e)(WeightedUnique(x[1::2], w[1::2])).logpdf(y[1::2]),
atol=1e-6,
)
def test_sample(x, w):
prior = Measure()
# Test that it produces random samples.
f1, e1 = GP(EQ(), measure=prior), GP(1e-1 * Delta(), measure=prior)
f2, e2 = GP(EQ(), measure=prior), GP(2e-1 * Delta(), measure=prior)
gpar = GPAR().add_layer(lambda: (f1, e1)).add_layer(lambda: (f2, e2))
all_different(gpar.sample(x, w), gpar.sample(x, w))
all_different(gpar.sample(x, w, latent=True), gpar.sample(x,
w,
latent=True))
# Test that posterior latent samples are around the data that is conditioned on.
prior = Measure()
f1, e1 = GP(EQ(), measure=prior), GP(1e-10 * Delta(), measure=prior)
f2, e2 = GP(EQ(), measure=prior), GP(2e-10 * Delta(), measure=prior)
gpar = GPAR().add_layer(lambda: (f1, e1)).add_layer(lambda: (f2, e2))
y = gpar.sample(x, w, latent=True)
gpar = gpar | (x, y, w)
approx(gpar.sample(x, w), y, atol=1e-3)
approx(gpar.sample(x, w, latent=True), y, atol=1e-3)
def predict(vs, m, x_data, y_data, locs, x_pred):
"""Make predictions.
Args:
vs (:class:`varz.Vars`): Variable container.
m (int): Number of latent processes.
x_data (tensor): Time stamps of the observations.
y_data (tensor): Observations.
locs (tensor): Spatial locations of observations.
x_pred (tensor): Time stamps to predict at.
Returns:
tuple: Tuple containing the predictions for the latent processes and
predictions for the observations.
"""
# Construct model and project data for prediction.
xs, noise_obs, noises_latent = model(vs, m)
y_proj, H, S, noises_obs = project(vs, m, y_data, locs)
L = noise_obs / S + noises_latent
# Condition latent processes.
xs_posterior = []
for x, noise, y in zip(xs, L, y_proj):
e = GP(noise * Delta(), graph=x.graph)
xs_posterior.append(x | ((x + e)(x_data), y))
xs = xs_posterior
# Extract posterior means and variances of the latent processes.
x_means, x_vars = zip(*[(x.mean(x_pred)[:, 0], x.kernel.elwise(x_pred)[:,
0])
for x in xs])
# Construct predictions for latent processes.
lat_preds = [
B.to_numpy(mean, mean - 2 * (var + L[i])**.5,
mean + 2 * (var + L[i])**.5)
for i, (mean, var) in enumerate(zip(x_means, x_vars))
]
# Pull means through mixing matrix.
x_means = B.stack(*x_means, axis=0)
y_means = B.matmul(H, x_means)
# Pull variances through mixing matrix and add noise.
x_vars = B.stack(*x_vars, axis=0)
y_vars = B.matmul(H**2, x_vars + noises_latent[:, None]) + noise_obs
# Construct predictions for observations.
obs_preds = [(mean, mean - 2 * var**.5, mean + 2 * var**.5)
for mean, var in zip(y_means, y_vars)]
return lat_preds, obs_preds
def test_obs():
graph = Graph()
f = GP(EQ(), graph=graph)
e = GP(1e-8 * Delta(), graph=graph)
# Check that it produces the correct observations.
x = B.linspace(0, 0.1, 10, dtype=torch.float64)
y = f(x).sample()
# Set some observations to be missing.
y_missing = y.clone()
y_missing[::2] = np.nan
# Check dense case.
gpar = GPAR()
obs = gpar._obs(x, None, y_missing, f, e)
yield eq, type(obs), Obs
yield approx, y, (f | obs).mean(x)
# Check sparse case.
gpar = GPAR(x_ind=x)
obs = gpar._obs(x, x, y_missing, f, e)
yield eq, type(obs), SparseObs
yield approx, y, (f | obs).mean(x)
import matplotlib.pyplot as plt
from wbml.plot import tweak
from stheno import B, Measure, GP, EQ, Delta
# Define points to predict at.
x = B.linspace(0, 10, 100)
x_obs = B.linspace(0, 10, 20)
# Constuct a prior:
prior = Measure()
w = lambda x: B.exp(-(x**2) / 0.5) # Window
b = [(w * GP(EQ(), measure=prior)).shift(xi)
for xi in x_obs] # Weighted basis funs
f = sum(b) # Latent function
e = GP(Delta(), measure=prior) # Noise
y = f + 0.2 * e # Observation model
# Sample a true, underlying function and observations.
f_true, y_obs = prior.sample(f(x), y(x_obs))
# Condition on the observations to make predictions.
post = prior | (y(x_obs), y_obs)
# Plot result.
for i, bi in enumerate(b):
mean, lower, upper = post(bi(x)).marginals()
kw_args = {"label": "Basis functions"} if i == 0 else {}
plt.plot(x, mean, style="pred2", **kw_args)
plt.plot(x, f_true, label="True", style="test")
plt.scatter(x_obs, y_obs, label="Observations", style="train", s=20)
import matplotlib.pyplot as plt
import numpy as np
import wbml.plot
from stheno import GP, EQ, Delta, model
# Define points to predict at.
x = np.linspace(0, 10, 100)
x_obs = np.linspace(0, 7, 20)
# Construct a prior.
f = GP(EQ().periodic(5.)) # Latent function.
e = GP(Delta()) # Noise.
y = f + .5 * e
# Sample a true, underlying function and observations.
f_true, y_obs = model.sample(f(x), y(x_obs))
# Now condition on the observations to make predictions.
mean, lower, upper = (f | (y(x_obs), y_obs))(x).marginals()
# Plot result.
plt.plot(x, f_true, label='True', c='tab:blue')
plt.scatter(x_obs, y_obs, label='Observations', c='tab:red')
plt.plot(x, mean, label='Prediction', c='tab:green')
plt.plot(x, lower, ls='--', c='tab:green')
plt.plot(x, upper, ls='--', c='tab:green')
wbml.plot.tweak()
plt.savefig('readme_example1_simple_regression.png')
plt.show()
(
Exp(),
lambda scheme: RGPCM(
scheme=scheme,
window=window,
scale=scale,
noise=noise,
n_u=n_u,
m_max=n_z // 2,
t=t,
),
),
]:
# Sample data.
gp_f = GP(kernel)
gp_y = gp_f + GP(noise * Delta(), measure=gp_f.measure)
f, y = gp_f.measure.sample(gp_f(t), gp_y(t))
f, y = B.flatten(f), B.flatten(y)
wd.save(
{
"t": t,
"f": f,
"k": B.flatten(kernel(t_k, 0)),
"y": y,
"true_logpdf": gp_y(t).logpdf(y),
},
slugify(str(kernel)),
"data.pickle",
)
for scheme in ["mean-field", "structured"]:
n = 881 # Add last one for `linspace`.
noise = 0.1
t = B.linspace(-44, 44, n)
t_plot = B.linspace(44, 44, 500)
# Setup true model and GPCM models.
kernel = EQ()
window = 2
scale = 1
n_u = 40
n_z = 88
# Sample data.
m = Measure()
gp_f = GP(kernel, measure=m)
gp_y = gp_f + GP(noise * Delta(), measure=m)
truth, y = map(B.flatten, m.sample(gp_f(t_plot), gp_y(t)))
# Remove region [-8.8, 8.8].
inds = ~((t >= -8.8) & (t <= 8.8))
t = t[inds]
y = y[inds]
def comparative_kernel(vs_):
return vs_.pos(1) * kernel.stretch(vs_.pos(1.0)) + vs_.pos(noise) * Delta()
run(
args=args,
wd=wd,
# Define points to predict at.
x = np.linspace(0, 10, 100)
x_obs = np.linspace(0, 10, 10)
# Model parameters:
m = 2
p = 4
H = np.random.randn(p, m)
# Construct latent functions
us = VGP(m, EQ())
fs = us.lmatmul(H)
# Construct noise.
e = VGP(p, 0.5 * Delta())
# Construct observation model.
ys = e + fs
# Sample a true, underlying function and observations.
fs_true = fs.sample(x)
ys_obs = (ys | fs.obs(x, fs_true)).sample(x_obs)
# Condition the model on the observations to make predictions.
preds = (fs | ys.obs(x_obs, ys_obs)).marginals(x)
# Plot results.
def plot_prediction(x, f, pred, x_obs=None, y_obs=None):
plt.plot(x, f, label='True', c='tab:blue')
import matplotlib.pyplot as plt
import numpy as np
from stheno import GP, Delta, model, Obs, dense
# Define points to predict at.
x = np.linspace(0, 10, 200)
x_obs = np.linspace(0, 10, 10)
# Construct the model.
slope = GP(1)
intercept = GP(5)
f = slope * (lambda x: x) + intercept
e = 0.2 * GP(Delta()) # Noise model
y = f + e # Observation model
# Sample a slope, intercept, underlying function, and observations.
true_slope, true_intercept, f_true, y_obs = \
model.sample(slope(0), intercept(0), f(x), y(x_obs))
# Condition on the observations to make predictions.
slope, intercept, f = (slope, intercept, f) | Obs(y(x_obs), y_obs)
mean, lower, upper = f(x).marginals()
print('true slope', true_slope)
print('predicted slope', slope(0).mean)
print('true intercept', true_intercept)
print('predicted intercept', intercept(0).mean)
B.epsilon = 1e-10
# Define points to predict at.
x = B.linspace(0, 10, 200)
x_obs = B.linspace(0, 7, 50)
with Measure() as prior:
# Construct a latent function consisting of four different components.
f_smooth = GP(EQ())
f_wiggly = GP(RQ(1e-1).stretch(0.5))
f_periodic = GP(EQ().periodic(1.0))
f_linear = GP(Linear())
f = f_smooth + f_wiggly + f_periodic + 0.2 * f_linear
# Let the observation noise consist of a bit of exponential noise.
e_indep = GP(Delta())
e_exp = GP(Exp())
e = e_indep + 0.3 * e_exp
# Sum the latent function and observation noise to get a model for the observations.
y = f + 0.5 * e
# Sample a true, underlying function and observations.
(
f_true_smooth,
f_true_wiggly,
f_true_periodic,
f_true_linear,
f_true,
y_obs,
) = prior.sample(f_smooth(x), f_wiggly(x), f_periodic(x), f_linear(x), f(x),
# Define points to predict at.
x = B.linspace(0, 10, 200)
x_obs = B.linspace(0, 7, 50)
# Construct a latent function consisting of four different components.
prior = Measure()
f_smooth = GP(EQ(), measure=prior)
f_wiggly = GP(RQ(1e-1).stretch(0.5), measure=prior)
f_periodic = GP(EQ().periodic(1.0), measure=prior)
f_linear = GP(Linear(), measure=prior)
f = f_smooth + f_wiggly + f_periodic + 0.2 * f_linear
# Let the observation noise consist of a bit of exponential noise.
e_indep = GP(Delta(), measure=prior)
e_exp = GP(Exp(), measure=prior)
e = e_indep + 0.3 * e_exp
# Sum the latent function and observation noise to get a model for the observations.
y = f + 0.5 * e
# Sample a true, underlying function and observations.
(
f_true_smooth,
f_true_wiggly,
f_true_periodic,
f_true_linear,
f_true,
y_obs,
def root(a):
u, s_diag, _ = np.linalg.svd(a)
return u.dot(np.diag(s_diag**.5)).dot(u.T)
def fp_difference(K, *Ks):
root_K = root(K)
return K - np.mean([root(root_K @ Ki @ root_K) for Ki in Ks], axis=0)
t_max = 5
n = 400
# k1 = EQ().stretch(t_max / 2) * EQ().periodic(1) + 1e-6 * Delta()
# k2 = EQ().stretch(t_max / 2) * EQ().periodic(1.8) + 1e-6 * Delta()
k1 = EQ().periodic(0.8) + 1e-6 * Delta()
k2 = EQ().periodic(0.85) + 1e-6 * Delta()
k3 = EQ().periodic(0.9) + 1e-6 * Delta()
x = np.linspace(0, t_max, n)
K1 = random_K(n)
K2 = random_K(n)
K3 = random_K(n)
# K1, K2, K3 = random_K(n), random_K(n), random_K(n)
# Solve.
print('Computing...')
C1 = spa.solve_continuous_are(np.zeros((n, n)), np.linalg.cholesky(K1), K3,
np.eye(n))
def comparative_kernel(vs_):
return vs_.pos(1) * kernel.stretch(vs_.pos(1.0)) + vs_.pos(noise) * Delta()
# Define points to predict at. x = B.linspace(0, 10, 100) x_obs = B.linspace(0, 10, 10) # Model parameters: m = 2 p = 4 H = B.randn(p, m) # Construct latent functions. prior = Measure() us = VGP([GP(EQ(), measure=prior) for _ in range(m)]) fs = us.lmatmul(H) # Construct noise. e = VGP([GP(0.5 * Delta(), measure=prior) for _ in range(p)]) # Construct observation model. ys = e + fs # Sample a true, underlying function and observations. samples = prior.sample(*(p(x) for p in fs.ps), *(p(x_obs) for p in ys.ps)) fs_true, ys_obs = samples[:p], samples[p:] # Compute the posterior and make predictions. post = prior | (*((p(x_obs), y_obs) for p, y_obs in zip(ys.ps, ys_obs)), ) preds = [post(p(x)).marginals() for p in fs.ps] # Plot results. def plot_prediction(x, f, pred, x_obs=None, y_obs=None):
import matplotlib.pyplot as plt
import numpy as np
from stheno import GP, EQ, Delta, Obs
# Define points to predict at.
x = np.linspace(0, 10, 200)
x_obs = np.linspace(0, 10, 10)
# Construct the model.
f = 0.7 * GP(EQ()).stretch(1.5)
e = 0.2 * GP(Delta())
# Construct derivatives via finite differences.
df = f.diff_approx(1)
ddf = f.diff_approx(2)
dddf = f.diff_approx(3) + e
# Fix the integration constants.
f, df, ddf, dddf = (f, df, ddf, dddf) | Obs((f(0), 1), (df(0), 0),
(ddf(0), -1))
# Sample observations.
y_obs = np.sin(x_obs) + 0.2 * np.random.randn(*x_obs.shape)
# Condition on the observations to make predictions.
f, df, ddf, dddf = (f, df, ddf, dddf) | Obs(dddf(x_obs), y_obs)
# And make predictions.
pred_iiif = f(x).marginals()
pred_iif = df(x).marginals()
import wbml.out as out
from wbml.plot import tweak
from stheno import B, Measure, GP, Delta
# Define points to predict at.
x = B.linspace(0, 10, 200)
x_obs = B.linspace(0, 10, 10)
# Construct the model.
prior = Measure()
slope = GP(1, measure=prior)
intercept = GP(5, measure=prior)
f = slope * (lambda x: x) + intercept
e = 0.2 * GP(Delta(), measure=prior) # Noise model
y = f + e # Observation model
# Sample a slope, intercept, underlying function, and observations.
true_slope, true_intercept, f_true, y_obs = prior.sample(
slope(0), intercept(0), f(x), y(x_obs))
# Condition on the observations to make predictions.
post = prior | (y(x_obs), y_obs)
mean, lower, upper = post(f(x)).marginals()
out.kv("True slope", true_slope[0, 0])
out.kv("Predicted slope", post(slope(0)).mean[0, 0])
out.kv("True intercept", true_intercept[0, 0])
out.kv("Predicted intercept", post(intercept(0)).mean[0, 0])
