def testMatchCIWidth(self):
Ys = get_data([self.obsd1, self.obsd2, self.obsd3], ["m2"])
pt = _compute_power_transforms(Ys)
pt["m2"].lambdas_.fill(-3.0)
bounds = _compute_inverse_bounds(pt)["m2"]
# Both will be NaN since we are far outside the bounds
new_mean_1, new_var_1 = match_ci_width_truncated(
mean=bounds[1] + 2.0,
variance=0.1,
transform=lambda y: pt["m2"].inverse_transform(np.array(y, ndmin=2)),
lower_bound=bounds[0],
upper_bound=bounds[1],
margin=0.001,
clip_mean=False,
)
# This will be finite since we clip
new_mean_2, new_var_2 = match_ci_width_truncated(
mean=bounds[1] + 2.0,
variance=0.1,
transform=lambda y: pt["m2"].inverse_transform(np.array(y, ndmin=2)),
lower_bound=bounds[0],
upper_bound=bounds[1],
margin=0.001,
clip_mean=True,
)
self.assertTrue(isnan(new_mean_1) and isnan(new_var_1))
self.assertTrue(isfinite(new_mean_2) and isfinite(new_var_2))
def transform_observation_data(
self,
observation_data: List[ObservationData],
observation_features: List[ObservationFeatures],
) -> List[ObservationData]:
"""Winsorize observation data in place."""
for obsd in observation_data:
for i, m in enumerate(obsd.metric_names):
if m in self.metric_names:
transform = self.power_transforms[m].transform
obsd.means[i], obsd.covariance[i, i] = match_ci_width_truncated(
mean=obsd.means[i],
variance=obsd.covariance[i, i],
transform=lambda y: transform(np.array(y, ndmin=2)),
lower_bound=-np.inf,
upper_bound=np.inf,
)
return observation_data
def transform_observation_data(
self,
observation_data: List[ObservationData],
observation_features: List[ObservationFeatures],
) -> List[ObservationData]:
"""Map to inverse Gaussian CDF in place."""
# TODO (jej): Transform covariances.
for obsd in observation_data:
for idx, _ in enumerate(obsd.metric_names):
mean = float(obsd.means[idx])
# Error on out-of-domain values.
if mean <= 0.0 or mean >= 1.0:
raise ValueError(
f"Inverse CDF cannot transform value: {mean} outside (0, 1)"
)
var = float(obsd.covariance[idx, idx])
transformed_mean, transformed_var = match_ci_width_truncated(
mean, var, self._map, lower_bound=0.0, upper_bound=1.0)
obsd.means[idx] = transformed_mean
obsd.covariance[idx, idx] = transformed_var
return observation_data
def untransform_observation_data(
self,
observation_data: List[ObservationData],
observation_features: List[ObservationFeatures],
) -> List[ObservationData]:
"""Winsorize observation data in place."""
for obsd in observation_data:
for i, m in enumerate(obsd.metric_names):
if m in self.metric_names:
l, u = self.inv_bounds[m]
transform = self.power_transforms[m].inverse_transform
if not self.clip_mean and (obsd.means[i] < l or obsd.means[i] > u):
raise ValueError(
"Can't untransform mean outside the bounds without clipping"
)
obsd.means[i], obsd.covariance[i, i] = match_ci_width_truncated(
mean=obsd.means[i],
variance=obsd.covariance[i, i],
transform=lambda y: transform(np.array(y, ndmin=2)),
lower_bound=l,
upper_bound=u,
clip_mean=True,
)
return observation_data