def create_slice_1d(i: int, experiment: bopt.Experiment, resolution: int,
n_dims: int, x_slice: List[float],
model: GPy.models.GPRegression, sample: bopt.Sample,
show_marginal: int) -> Slice1D:
param = experiment.hyperparameters[i]
grid = param.range.grid(resolution)
X_plot = np.zeros([resolution, n_dims], dtype=np.float32)
for dim in range(n_dims):
if dim == i:
X_plot[:, dim] = grid
else:
X_plot[:, dim] = np.full([resolution],
x_slice[dim],
dtype=np.float32)
X_plot_marginal = grid.reshape(-1, 1)
if show_marginal == 1:
others = experiment.predictive_samples_before(sample)
X_m, Y_m = bopt.SampleCollection(others).to_xy()
X_m = X_m[:, i].reshape(-1, 1)
model = create_gp_for_data(experiment, [param], X_m, Y_m)
mu, var = model.predict(X_plot_marginal)
else:
mu, var = model.predict(X_plot)
mu = mu.reshape(-1)
sigma = np.sqrt(var).reshape(-1)
acq = bopt.ExpectedImprovement().raw_call(mu, sigma, model.Y.max())\
.reshape(-1)
other_samples: Dict[str, List[float]] = defaultdict(list)
for other in experiment.predictive_samples_before(sample) + [sample]:
other_x, other_y = other.to_xy()
other_x = float(other_x.tolist()[i])
if param.range.is_logscale():
other_x = 10.0**other_x
other_samples["x"].append(other_x)
other_samples["y"].append(other_y)
if param.range.is_logscale():
x_slice_at = 10.0**x_slice[i]
x = 10.0**grid
else:
x_slice_at = x_slice[i]
x = grid
return Slice1D(param, x.tolist(), x_slice_at, mu.tolist(), sigma.tolist(),
acq.tolist(), other_samples, model)
def predict(model: GPy.models.GPRegression, X: np.array) -> Tuple[np.array, np.array]:
"""Wrapper function for the prediction method of a GPy regression model.
It return the standard deviation instead of the variance"""
assert isinstance(
model, GPy.models.GPRegression
), "This wrapper function is written for GPy.models.GPRegression"
mu, var = model.predict(X)
return mu, np.sqrt(var)
def test_gp(gpy_gp: GPy.models.GPRegression,
data_X: np.ndarray,
data_Y: np.ndarray,
display_model: bool = False) -> float:
"""
Evaluate the goodness of the model fit by RMSE value
:param gpy_gp: the GPy regression model
:param data_X: the query data points. Typically of x of validation data-set
:param data_Y: the labeels. Typically of the y of validation data-set
:param display_model: bool
:return:
"""
assert data_X.shape[0] == data_Y.shape[
0], "Lengths of x and labels mismatch"
assert data_X.shape[
1] == gpy_gp.input_dim, "Dimension of x and the model dimension mismatch"
mean_pred, var_pred = gpy_gp.predict(Xnew=data_X)
rmse = np.sqrt(((mean_pred - np.squeeze(data_Y, -1))**2).mean())
if display_model is True:
print("Root Mean Squared Error (RMSE): ", str(rmse))
return rmse
def create_slice_2d(i: int, j: int, experiment: bopt.Experiment,
resolution: int, n_dims: int, x_slice: List[float],
model: GPy.models.GPRegression, sample: bopt.Sample,
show_marginal: int) -> Slice2D:
p1 = experiment.hyperparameters[i]
p2 = experiment.hyperparameters[j]
d1 = p1.range.grid(resolution)
d2 = p2.range.grid(resolution)
g1, g2 = np.meshgrid(d1, d2)
gs = [0.0] * len(x_slice)
gs[i] = g1
gs[j] = g2
for dim in range(len(x_slice)):
if dim not in [i, j]:
gs[dim] = np.full(g1.shape, x_slice[dim])
grid = np.stack(gs, axis=-1)
X_pred = grid.reshape(resolution * resolution, -1)
if show_marginal == 1:
others = experiment.predictive_samples_before(sample)
X_m, Y_m = bopt.SampleCollection(others).to_xy()
X_m = X_m[:, [i, j]].reshape(-1, 2)
model = create_gp_for_data(experiment, [p1, p2], X_m, Y_m)
mu, var = model.predict(X_pred[:, [i, j]])
else:
mu, var = model.predict(X_pred)
mu = mu.reshape(-1)
sigma = np.sqrt(var).reshape(-1)
acq = bopt.ExpectedImprovement().raw_call(mu, sigma, model.Y.max())\
.reshape(-1)
mu = mu.reshape(resolution, resolution)
sigma = sigma.reshape(resolution, resolution)
acq = acq.reshape(resolution, resolution)
other_samples: Dict[str, List[float]] = defaultdict(list)
for other in experiment.predictive_samples_before(sample) + [sample]:
other_x, other_y = other.to_xy()
other_x1 = float(other_x.tolist()[i])
other_x2 = float(other_x.tolist()[j])
if p1.range.is_logscale():
other_x1 = 10.0**other_x1
if p2.range.is_logscale():
other_x2 = 10.0**other_x2
other_samples["x1"].append(other_x1)
other_samples["x2"].append(other_x2)
other_samples["y"].append(other_y)
if p1.range.is_logscale():
x1 = (10.0**d1).tolist()
x1_slice_at = 10.0**x_slice[i]
else:
x1 = d1.tolist()
x1_slice_at = x_slice[i]
if p2.range.is_logscale():
x2 = (10.0**d2).tolist()
x2_slice_at = 10.0**x_slice[j]
else:
x2 = d2.tolist()
x2_slice_at = x_slice[j]
return Slice2D(p1, p2, x1, x2, x1_slice_at, x2_slice_at, mu.tolist(),
other_samples, model)