def create_transformation(self) -> Transformation:
return Chain([
AsNumpyArray(
field=FieldName.TARGET,
expected_ndim=1 + len(self.distr_output.event_shape),
),
# maps the target to (1, T) if the target data is uni
# dimensional
ExpandDimArray(
field=FieldName.TARGET,
axis=0 if self.distr_output.event_shape[0] == 1 else None,
),
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
),
AddTimeFeatures(
start_field=FieldName.START,
target_field=FieldName.TARGET,
output_field=FieldName.FEAT_TIME,
time_features=self.time_features,
pred_length=self.prediction_length,
),
VstackFeatures(
output_field=FieldName.FEAT_TIME,
input_fields=[FieldName.FEAT_TIME],
),
SetFieldIfNotPresent(field=FieldName.FEAT_STATIC_CAT, value=[0.0]),
TargetDimIndicator(
field_name=FieldName.TARGET_DIM_INDICATOR,
target_field=FieldName.TARGET,
),
AsNumpyArray(field=FieldName.FEAT_STATIC_CAT, expected_ndim=1),
])
def create_transformation(self) -> Transformation:
return Chain(
trans=[
AsNumpyArray(field=FieldName.TARGET, expected_ndim=1),
AddTimeFeatures(
start_field=FieldName.START,
target_field=FieldName.TARGET,
output_field=FieldName.FEAT_TIME,
time_features=time_features_from_frequency_str(self.freq),
pred_length=self.prediction_length,
),
SetFieldIfNotPresent(
field=FieldName.FEAT_STATIC_CAT, value=[0.0]
),
AsNumpyArray(field=FieldName.FEAT_STATIC_CAT, expected_ndim=1),
transform.InstanceSplitter(
target_field=transform.FieldName.TARGET,
is_pad_field=transform.FieldName.IS_PAD,
start_field=transform.FieldName.START,
forecast_start_field=transform.FieldName.FORECAST_START,
train_sampler=TestSplitSampler(),
time_series_fields=[FieldName.FEAT_TIME],
past_length=self.context_length,
future_length=self.prediction_length,
),
]
)
def create_transformation(self) -> Transformation:
return Chain(
[
AsNumpyArray(field=FieldName.TARGET, expected_ndim=1),
AddTimeFeatures(
start_field=FieldName.START,
target_field=FieldName.TARGET,
output_field=FieldName.FEAT_TIME,
time_features=self.time_features,
pred_length=self.prediction_length,
),
SetFieldIfNotPresent(
field=FieldName.FEAT_STATIC_CAT, value=[0.0]
),
AsNumpyArray(field=FieldName.FEAT_STATIC_CAT, expected_ndim=1),
CanonicalInstanceSplitter(
target_field=FieldName.TARGET,
is_pad_field=FieldName.IS_PAD,
start_field=FieldName.START,
forecast_start_field=FieldName.FORECAST_START,
instance_sampler=TestSplitSampler(),
time_series_fields=[FieldName.FEAT_TIME],
instance_length=self.context_length,
use_prediction_features=True,
prediction_length=self.prediction_length,
),
]
)
def create_transformation(self) -> transform.Transformation:
return Chain(
[
AsNumpyArray(field=FieldName.TARGET, expected_ndim=1),
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
),
AddTimeFeatures(
start_field=FieldName.START,
target_field=FieldName.TARGET,
output_field=FieldName.FEAT_TIME,
time_features=time_features_from_frequency_str(self.freq),
pred_length=self.prediction_length,
),
AddAgeFeature(
target_field=FieldName.TARGET,
output_field=FieldName.FEAT_AGE,
pred_length=self.prediction_length,
),
VstackFeatures(
output_field=FieldName.FEAT_TIME,
input_fields=[FieldName.FEAT_TIME, FieldName.FEAT_AGE],
),
SetFieldIfNotPresent(
field=FieldName.FEAT_STATIC_CAT, value=[0.0]
),
AsNumpyArray(field=FieldName.FEAT_STATIC_CAT, expected_ndim=1),
]
)
def create_transformation(self) -> Transformation:
return (AsNumpyArray(field=FieldName.TARGET, expected_ndim=1) +
AddTimeFeatures(
start_field=FieldName.START,
target_field=FieldName.TARGET,
output_field=FieldName.FEAT_TIME,
time_features=time_features_from_frequency_str(self.freq),
pred_length=self.prediction_length,
) + SetFieldIfNotPresent(field=FieldName.FEAT_STATIC_CAT,
value=[0.0]) +
AsNumpyArray(field=FieldName.FEAT_STATIC_CAT, expected_ndim=1))
def create_transformation(
self, bin_edges: np.ndarray, pred_length: int
) -> transform.Transformation:
return Chain(
[
AsNumpyArray(field=FieldName.TARGET, expected_ndim=1),
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
),
AddTimeFeatures(
start_field=FieldName.START,
target_field=FieldName.TARGET,
output_field=FieldName.FEAT_TIME,
time_features=time_features_from_frequency_str(self.freq),
pred_length=self.prediction_length,
),
AddAgeFeature(
target_field=FieldName.TARGET,
output_field=FieldName.FEAT_AGE,
pred_length=self.prediction_length,
),
VstackFeatures(
output_field=FieldName.FEAT_TIME,
input_fields=[FieldName.FEAT_TIME, FieldName.FEAT_AGE],
),
SetFieldIfNotPresent(
field=FieldName.FEAT_STATIC_CAT, value=[0.0]
),
AsNumpyArray(field=FieldName.FEAT_STATIC_CAT, expected_ndim=1),
InstanceSplitter(
target_field=FieldName.TARGET,
is_pad_field=FieldName.IS_PAD,
start_field=FieldName.START,
forecast_start_field=FieldName.FORECAST_START,
train_sampler=ExpectedNumInstanceSampler(num_instances=1),
past_length=self.context_length,
future_length=pred_length,
output_NTC=False,
time_series_fields=[
FieldName.FEAT_TIME,
FieldName.OBSERVED_VALUES,
],
),
QuantizeScaled(
bin_edges=bin_edges.tolist(),
future_target="future_target",
past_target="past_target",
),
]
)
def create_transformation(self) -> Transformation:
return Chain([
AsNumpyArray(
field=FieldName.TARGET,
# in the following line, we add 1 for the time dimension
expected_ndim=1 + len(self.distr_output.event_shape),
),
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
),
AddTimeFeatures(
start_field=FieldName.START,
target_field=FieldName.TARGET,
output_field=FieldName.FEAT_TIME,
time_features=self.time_features,
pred_length=self.prediction_length,
),
AddAgeFeature(
target_field=FieldName.TARGET,
output_field=FieldName.FEAT_AGE,
pred_length=self.prediction_length,
log_scale=True,
),
VstackFeatures(
output_field=FieldName.FEAT_TIME,
input_fields=[FieldName.FEAT_TIME, FieldName.FEAT_AGE],
),
SetFieldIfNotPresent(field=FieldName.FEAT_STATIC_CAT, value=[0.0]),
AsNumpyArray(field=FieldName.FEAT_STATIC_CAT, expected_ndim=1),
InstanceSplitter(
target_field=FieldName.TARGET,
is_pad_field=FieldName.IS_PAD,
start_field=FieldName.START,
forecast_start_field=FieldName.FORECAST_START,
train_sampler=ExpectedNumInstanceSampler(num_instances=1),
past_length=self.history_length,
future_length=self.prediction_length,
time_series_fields=[
FieldName.FEAT_TIME,
FieldName.OBSERVED_VALUES,
],
),
])
def create_transformation(self) -> Transformation:
remove_field_names = [FieldName.FEAT_DYNAMIC_CAT]
if not self.use_feat_dynamic_real:
remove_field_names.append(FieldName.FEAT_DYNAMIC_REAL)
return Chain([
RemoveFields(field_names=remove_field_names),
AsNumpyArray(
field=FieldName.TARGET,
expected_ndim=2,
),
# maps the target to (1, T)
# if the target data is uni dimensional
ExpandDimArray(
field=FieldName.TARGET,
axis=None,
),
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
),
AddTimeFeatures(
start_field=FieldName.START,
target_field=FieldName.TARGET,
output_field=FieldName.FEAT_TIME,
time_features=self.time_features,
pred_length=self.prediction_length,
),
VstackFeatures(
output_field=FieldName.FEAT_TIME,
input_fields=[FieldName.FEAT_TIME] +
([FieldName.FEAT_DYNAMIC_REAL]
if self.use_feat_dynamic_real else []),
),
SetFieldIfNotPresent(field=FieldName.FEAT_STATIC_CAT, value=[0]),
TargetDimIndicator(
field_name="target_dimension_indicator",
target_field=FieldName.TARGET,
),
AsNumpyArray(field=FieldName.FEAT_STATIC_CAT, expected_ndim=1),
])
def create_transformation(self) -> Transformation:
def use_marginal_transformation(
marginal_transformation: bool, ) -> Transformation:
if marginal_transformation:
return CDFtoGaussianTransform(
target_field=FieldName.TARGET,
observed_values_field=FieldName.OBSERVED_VALUES,
max_context_length=self.conditioning_length,
target_dim=self.target_dim,
)
else:
return RenameFields({
f"past_{FieldName.TARGET}":
f"past_{FieldName.TARGET}_cdf",
f"future_{FieldName.TARGET}":
f"future_{FieldName.TARGET}_cdf",
})
return Chain([
AsNumpyArray(
field=FieldName.TARGET,
expected_ndim=1 + len(self.distr_output.event_shape),
),
# maps the target to (1, T) if the target data is uni
# dimensional
ExpandDimArray(
field=FieldName.TARGET,
axis=0 if self.distr_output.event_shape[0] == 1 else None,
),
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
),
AddTimeFeatures(
start_field=FieldName.START,
target_field=FieldName.TARGET,
output_field=FieldName.FEAT_TIME,
time_features=self.time_features,
pred_length=self.prediction_length,
),
VstackFeatures(
output_field=FieldName.FEAT_TIME,
input_fields=[FieldName.FEAT_TIME],
),
SetFieldIfNotPresent(field=FieldName.FEAT_STATIC_CAT, value=[0.0]),
TargetDimIndicator(
field_name=FieldName.TARGET_DIM_INDICATOR,
target_field=FieldName.TARGET,
),
AsNumpyArray(field=FieldName.FEAT_STATIC_CAT, expected_ndim=1),
InstanceSplitter(
target_field=FieldName.TARGET,
is_pad_field=FieldName.IS_PAD,
start_field=FieldName.START,
forecast_start_field=FieldName.FORECAST_START,
train_sampler=ExpectedNumInstanceSampler(num_instances=1),
past_length=self.history_length,
future_length=self.prediction_length,
time_series_fields=[
FieldName.FEAT_TIME,
FieldName.OBSERVED_VALUES,
],
pick_incomplete=self.pick_incomplete,
),
use_marginal_transformation(self.use_marginal_transformation),
SampleTargetDim(
field_name=FieldName.TARGET_DIM_INDICATOR,
target_field=FieldName.TARGET + "_cdf",
observed_values_field=FieldName.OBSERVED_VALUES,
num_samples=self.target_dim_sample,
shuffle=self.shuffle_target_dim,
),
])