def testTransform(self):
obsd1_0 = ObservationData(
metric_names=["m1", "m2", "m2"],
means=np.array([1.0, 2.0, 1.0]),
covariance=np.array([[1.0, 0.2, 0.4], [0.2, 2.0, 0.8],
[0.4, 0.8, 3.0]]),
)
obsd1_1 = ObservationData(
metric_names=["m1", "m1", "m2", "m2"],
means=np.array([1.0, 1.0, 2.0, 1.0]),
covariance=np.array([
[1.0, 0.0, 0.0, 0.0],
[0.0, 1.0, 0.2, 0.4],
[0.0, 0.2, 2.0, 0.8],
[0.0, 0.4, 0.8, 3.0],
]),
)
obsd2_0 = ObservationData(
metric_names=["m1", "m2"],
means=np.array([1.0, 1.6]),
covariance=np.array([[1.0, 0.28], [0.28, 1.584]]),
)
obsd2_1 = ObservationData(
metric_names=["m1", "m2"],
means=np.array([1.0, 1.6]),
covariance=np.array([[0.5, 0.14], [0.14, 1.584]]),
)
observation_data = [obsd1_0, obsd1_1]
t = IVW(None, None, None)
observation_data2 = t.transform_observation_data(observation_data, [])
observation_data2_true = [obsd2_0, obsd2_1]
for i, obsd in enumerate(observation_data2_true):
self.assertEqual(observation_data2[i].metric_names,
obsd.metric_names)
self.assertTrue(
np.array_equal(observation_data2[i].means, obsd.means))
discrep = np.max(
np.abs(observation_data2[i].covariance - obsd.covariance))
self.assertTrue(discrep < 1e-8)
def _get_in_sample_arms(
model: ModelBridge,
metric_names: Set[str],
fixed_features: Optional[ObservationFeatures] = None,
) -> Tuple[Dict[str, PlotInSampleArm], RawData, Dict[str, TParameterization]]:
"""Get in-sample arms from a model with observed and predicted values
for specified metrics.
Returns a PlotInSampleArm object in which repeated observations are merged
with IVW, and a RawData object in which every observation is listed.
Fixed features input can be used to override fields of the insample arms
when making model predictions.
Args:
model: An instance of the model bridge.
metric_names: Restrict predictions to these metrics. If None, uses all
metrics in the model.
fixed_features: Features that should be fixed in the arms this function
will obtain predictions for.
Returns:
A tuple containing
- Map from arm name to PlotInSampleArm.
- List of the data for each observation like::
{'metric_name': 'likes', 'arm_name': '0_0', 'mean': 1., 'sem': 0.1}
- Map from arm name to parameters
"""
observations = model.get_training_data()
# Calculate raw data
raw_data = []
arm_name_to_parameters = {}
for obs in observations:
arm_name_to_parameters[obs.arm_name] = obs.features.parameters
for j, metric_name in enumerate(obs.data.metric_names):
if metric_name in metric_names:
raw_data.append({
"metric_name": metric_name,
"arm_name": obs.arm_name,
"mean": obs.data.means[j],
"sem": np.sqrt(obs.data.covariance[j, j]),
})
# Check that we have one ObservationFeatures per arm name since we
# key by arm name and the model is not Multi-task.
# If "TrialAsTask" is present, one of the arms is also chosen.
if ("TrialAsTask" not in model.transforms.keys()) and (
len(arm_name_to_parameters) != len(observations)):
logger.error(
"Have observations of arms with different features but same"
" name. Arbitrary one will be plotted.")
# Merge multiple measurements within each Observation with IVW to get
# un-modeled prediction
t = IVW(None, [], [])
obs_data = t.transform_observation_data([obs.data for obs in observations],
[])
# Start filling in plot data
in_sample_plot: Dict[str, PlotInSampleArm] = {}
for i, obs in enumerate(observations):
if obs.arm_name is None:
raise ValueError("Observation must have arm name for plotting.")
# Extract raw measurement
obs_y = {} # Observed metric means.
obs_se = {} # Observed metric standard errors.
# Use the IVW data, not obs.data
for j, metric_name in enumerate(obs_data[i].metric_names):
if metric_name in metric_names:
obs_y[metric_name] = obs_data[i].means[j]
obs_se[metric_name] = np.sqrt(obs_data[i].covariance[j, j])
# Make a prediction.
if model.training_in_design[i]:
features = obs.features
if fixed_features is not None:
features.update_features(fixed_features)
pred_y, pred_se = _predict_at_point(model, features, metric_names)
else:
# Use raw data for out-of-design points
pred_y = obs_y
pred_se = obs_se
in_sample_plot[not_none(obs.arm_name)] = PlotInSampleArm(
name=not_none(obs.arm_name),
y=obs_y,
se=obs_se,
parameters=obs.features.parameters,
y_hat=pred_y,
se_hat=pred_se,
context_stratum=None,
)
return in_sample_plot, raw_data, arm_name_to_parameters
def _get_in_sample_arms(
model: ModelBridge, metric_names: Set[str]
) -> Tuple[Dict[str, PlotInSampleArm], RawData, Dict[str, TParameterization]]:
"""Get in-sample arms from a model with observed and predicted values
for specified metrics.
Returns a PlotInSampleArm object in which repeated observations are merged
with IVW, and a RawData object in which every observation is listed.
Args:
model: An instance of the model bridge.
metric_names: Restrict predictions to these metrics. If None, uses all
metrics in the model.
Returns:
A tuple containing
- Map from arm name to PlotInSampleArm.
- List of the data for each observation like::
{'metric_name': 'likes', 'arm_name': '0_0', 'mean': 1., 'sem': 0.1}
- Map from arm name to parameters
"""
observations = model.get_training_data()
# Calculate raw data
raw_data = []
cond_name_to_parameters = {}
for obs in observations:
cond_name_to_parameters[obs.arm_name] = obs.features.parameters
for j, metric_name in enumerate(obs.data.metric_names):
if metric_name in metric_names:
raw_data.append({
"metric_name": metric_name,
"arm_name": obs.arm_name,
"mean": obs.data.means[j],
"sem": np.sqrt(obs.data.covariance[j, j]),
})
# Check that we have one ObservationFeatures per arm name since we
# key by arm name.
if len(cond_name_to_parameters) != len(observations):
logger.error(
"Have observations of arms with different features but same"
" name. Arbitrary one will be plotted.")
# Merge multiple measurements within each Observation with IVW to get
# un-modeled prediction
t = IVW(None, [], [])
obs_data = t.transform_observation_data([obs.data for obs in observations],
[])
# Start filling in plot data
in_sample_plot: Dict[str, PlotInSampleArm] = {}
for i, obs in enumerate(observations):
if obs.arm_name is None:
raise ValueError("Observation must have arm name for plotting.")
# Extract raw measurement
obs_y = {}
obs_se = {}
# Use the IVW data, not obs.data
for j, metric_name in enumerate(obs_data[i].metric_names):
if metric_name in metric_names:
obs_y[metric_name] = obs_data[i].means[j]
obs_se[metric_name] = np.sqrt(obs_data[i].covariance[j, j])
# Make a prediction.
if model.training_in_design[i]:
pred_y, pred_se = _predict_at_point(model, obs.features,
metric_names)
else:
# Use raw data for out-of-design points
pred_y = obs_y
pred_se = obs_se
in_sample_plot[obs.arm_name] = PlotInSampleArm(
name=obs.arm_name,
y=obs_y,
se=obs_se,
parameters=obs.features.parameters,
y_hat=pred_y,
se_hat=pred_se,
context_stratum=None,
)
return in_sample_plot, raw_data, cond_name_to_parameters