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 Chain(
trans=[
AsNumpyArray(
field=FieldName.TARGET, expected_ndim=2, dtype=self.dtype
),
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
dtype=self.dtype,
),
InstanceSplitter(
target_field=FieldName.TARGET,
is_pad_field=FieldName.IS_PAD,
start_field=FieldName.START,
forecast_start_field=FieldName.FORECAST_START,
train_sampler=self.train_sampler,
time_series_fields=[FieldName.OBSERVED_VALUES],
past_length=self.context_length,
future_length=self.prediction_length,
lead_time=self.lead_time,
output_NTC=False, # output NCT for first layer conv2d
),
]
)
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(freq, context_length, prediction_length): return Chain( [ AddObservedValuesIndicator( target_field=FieldName.TARGET, output_field=FieldName.OBSERVED_VALUES, ), AddAgeFeature( target_field=FieldName.TARGET, output_field=FieldName.FEAT_AGE, pred_length=prediction_length, log_scale=True, ), InstanceSplitter( target_field=FieldName.TARGET, is_pad_field=FieldName.IS_PAD, start_field=FieldName.START, forecast_start_field=FieldName.FORECAST_START, instance_sampler=ExpectedNumInstanceSampler( num_instances=1, min_future=prediction_length, ), past_length=context_length, future_length=prediction_length, time_series_fields=[ FieldName.FEAT_AGE, FieldName.FEAT_DYNAMIC_REAL, FieldName.OBSERVED_VALUES, ], ), ] )
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:
remove_field_names = []
if not self.use_feat_static_real:
remove_field_names.append(FieldName.FEAT_STATIC_REAL)
if not self.use_feat_dynamic_real:
remove_field_names.append(FieldName.FEAT_DYNAMIC_REAL)
if not self.use_feat_dynamic_cat:
remove_field_names.append(FieldName.FEAT_DYNAMIC_CAT)
return Chain(
[RemoveFields(field_names=remove_field_names)] +
([SetField(output_field=FieldName.FEAT_STATIC_CAT, value=[0]
)] if not self.use_feat_static_cat else []) +
([SetField(output_field=FieldName.FEAT_STATIC_REAL, value=[0.0]
)] if not self.use_feat_static_real else []) +
[
AsNumpyArray(
field=FieldName.FEAT_STATIC_CAT,
expected_ndim=1,
dtype=np.long,
),
AsNumpyArray(
field=FieldName.FEAT_STATIC_REAL,
expected_ndim=1,
dtype=self.dtype,
),
AsNumpyArray(
field=FieldName.TARGET,
# in the following line, we add 1 for the time dimension
expected_ndim=1 + len(self.distr_output.event_shape),
dtype=self.dtype,
),
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
dtype=self.dtype,
),
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,
dtype=self.dtype,
),
VstackFeatures(
output_field=FieldName.FEAT_TIME,
input_fields=[FieldName.FEAT_TIME, FieldName.FEAT_AGE] +
([FieldName.FEAT_DYNAMIC_REAL] if self.
use_feat_dynamic_real else []) +
([FieldName.FEAT_DYNAMIC_CAT] if self.
use_feat_dynamic_cat else []),
),
])
def create_transformation(self) -> Transformation:
remove_field_names = [FieldName.FEAT_DYNAMIC_CAT]
if not self.use_feat_static_real:
remove_field_names.append(FieldName.FEAT_STATIC_REAL)
if not self.use_feat_dynamic_real:
remove_field_names.append(FieldName.FEAT_DYNAMIC_REAL)
return Chain(
[RemoveFields(field_names=remove_field_names)] +
([SetField(output_field=FieldName.FEAT_STATIC_CAT, value=[0.0]
)] if not self.use_feat_static_cat else []) +
([SetField(output_field=FieldName.FEAT_STATIC_REAL, value=[0.0]
)] if not self.use_feat_static_real else []) +
[
AsNumpyArray(field=FieldName.FEAT_STATIC_CAT, expected_ndim=1),
AsNumpyArray(field=FieldName.FEAT_STATIC_REAL,
expected_ndim=1),
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] +
([FieldName.FEAT_DYNAMIC_REAL] if self.
use_feat_dynamic_real else []),
),
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)
if not self.use_feat_static_real:
remove_field_names.append(FieldName.FEAT_STATIC_REAL)
return Chain([RemoveFields(field_names=remove_field_names)] + (
[SetField(output_field=FieldName.FEAT_STATIC_CAT, value=[0]
)] if not self.use_feat_static_cat else []
) + ([SetField(
output_field=FieldName.FEAT_STATIC_REAL, value=[0.0]
)] if not self.use_feat_static_real else []) + [
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,
),
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] +
([FieldName.FEAT_DYNAMIC_REAL] if self.
use_feat_dynamic_real else []),
),
TargetDimIndicator(
field_name="target_dimension_indicator",
target_field=FieldName.TARGET,
),
AsNumpyArray(field=FieldName.FEAT_STATIC_CAT,
expected_ndim=1,
dtype=np.long),
AsNumpyArray(field=FieldName.FEAT_STATIC_REAL, expected_ndim=1),
])
def get_dataset_and_transformation():
# dont recompute, since expensive
global _data_cache
if _data_cache is not None:
return _data_cache
# create constant dataset with each time series having
# variable length and unique constant integer entries
dataset = ConstantDataset(
num_steps=CD_NUM_STEPS, num_timeseries=CD_NUM_TIME_SERIES
)
list_dataset = list(dataset.train)
for i, ts in enumerate(list_dataset):
ts["start"] = pd.Timestamp(ts_input=ts["start"], freq=dataset.freq)
# get randomness in the ts lengths
ts["target"] = np.array(
ts["target"] * random.randint(1, CD_MAX_LEN_MULTIPLICATION_FACTOR)
)
list_dataset = ListDataset(data_iter=list_dataset, freq=dataset.freq)
list_dataset_pred_length = dataset.prediction_length
# use every possible time point to split the time series
transformation = Chain(
[
InstanceSplitter(
target_field=FieldName.TARGET,
is_pad_field=FieldName.IS_PAD,
start_field=FieldName.START,
forecast_start_field=FieldName.FORECAST_START,
train_sampler=UniformSplitSampler(
p=SPLITTING_SAMPLE_PROBABILITY # THIS IS IMPORTANT FOR THE TEST
),
past_length=CONTEXT_LEN,
future_length=list_dataset_pred_length,
dummy_value=1.0,
),
]
)
# original no multiprocessing processed validation dataset
train_data_transformed_original = list(
ValidationDataLoader(
dataset=list_dataset,
transform=transformation,
batch_size=BATCH_SIZE,
num_workers=0, # This is the crucial difference
ctx=current_context(),
)
)
_data_cache = (
list_dataset,
transformation,
list_dataset_pred_length,
train_data_transformed_original,
)
return _data_cache
def create_transformation(self) -> Transformation:
return Chain(trans=[
AsNumpyArray(field=FieldName.TARGET, expected_ndim=1),
ForkingSequenceSplitter(
train_sampler=TestSplitSampler(),
enc_len=self.context_length,
dec_len=self.prediction_length,
),
])
def test_simple_model():
dsinfo, training_data, test_data = default_synthetic()
freq = dsinfo.metadata.freq
prediction_length = dsinfo.prediction_length
context_length = 2 * prediction_length
hidden_dimensions = [10, 10]
net = LightningFeedForwardNetwork(
freq=freq,
prediction_length=prediction_length,
context_length=context_length,
hidden_dimensions=hidden_dimensions,
distr_output=NormalOutput(),
batch_norm=True,
scaling=mean_abs_scaling,
)
transformation = Chain([
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
),
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=context_length,
future_length=prediction_length,
time_series_fields=[FieldName.OBSERVED_VALUES],
),
])
data_loader = TrainDataLoader(
training_data,
batch_size=8,
stack_fn=batchify,
transform=transformation,
num_batches_per_epoch=5,
)
trainer = pl.Trainer(max_epochs=3, callbacks=[], weights_summary=None)
trainer.fit(net, train_dataloader=data_loader)
predictor = net.get_predictor(transformation)
forecast_it, ts_it = make_evaluation_predictions(
dataset=test_data,
predictor=predictor,
num_samples=100,
)
evaluator = Evaluator(quantiles=[0.5, 0.9], num_workers=None)
agg_metrics, _ = evaluator(ts_it, forecast_it)
def create_transformation(self) -> Transformation:
remove_field_names = [
FieldName.FEAT_DYNAMIC_CAT,
FieldName.FEAT_STATIC_REAL,
]
if not self.use_feat_dynamic_real:
remove_field_names.append(FieldName.FEAT_DYNAMIC_REAL)
return Chain(
[RemoveFields(field_names=remove_field_names)]
+ (
[SetField(output_field=FieldName.FEAT_STATIC_CAT, value=[0.0])]
if not self.use_feat_static_cat
else []
)
+ [
AsNumpyArray(field=FieldName.FEAT_STATIC_CAT, expected_ndim=1),
AsNumpyArray(field=FieldName.TARGET, expected_ndim=1),
# gives target the (1, T) layout
ExpandDimArray(field=FieldName.TARGET, axis=0),
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
),
# Unnormalized seasonal features
AddTimeFeatures(
time_features=self.issm.time_features(),
pred_length=self.prediction_length,
start_field=FieldName.START,
target_field=FieldName.TARGET,
output_field=SEASON_INDICATORS_FIELD,
),
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]
+ (
[FieldName.FEAT_DYNAMIC_REAL]
if self.use_feat_dynamic_real
else []
),
),
]
)
def create_transformation(self) -> Transformation:
return Chain(
trans=[
AsNumpyArray(field=FieldName.TARGET, expected_ndim=2, dtype=self.dtype),
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
dtype=self.dtype,
),
]
)
def create_transformation(self) -> Transformation:
return Chain([
InstanceSplitter(
target_field=FieldName.TARGET,
is_pad_field=FieldName.IS_PAD,
start_field=FieldName.START,
forecast_start_field=FieldName.FORECAST_START,
train_sampler=self.train_sampler,
past_length=self.context_length,
future_length=self.prediction_length,
time_series_fields=[],
)
])
def create_transformation(self) -> Transformation:
return Chain([
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=self.prediction_length,
time_series_fields=[], # [FieldName.FEAT_DYNAMIC_REAL]
)
])
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),
])
def create_transformation(self) -> Transformation:
return Chain([
ContinuousTimeInstanceSplitter(
past_interval_length=self.context_interval_length,
future_interval_length=self.prediction_interval_length,
train_sampler=ContinuousTimeUniformSampler(
num_instances=self.num_training_instances),
),
RenameFields({
"past_target": "target",
"past_valid_length": "valid_length",
}),
])
def create_transformation(self) -> Transformation:
return Chain([
RemoveFields(field_names=[
FieldName.FEAT_STATIC_REAL,
FieldName.FEAT_DYNAMIC_REAL,
FieldName.FEAT_DYNAMIC_CAT,
]),
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
dtype=self.dtype,
),
])
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_post_split_transform():
return Chain([
CountTrailingZeros(
new_field="time_remaining",
target_field="past_target",
as_array=True,
),
ToIntervalSizeFormat(target_field="past_target",
discard_first=True),
RenameFields({"future_target": "sparse_future"}),
AsNumpyArray(field="past_target", expected_ndim=2),
SwapAxes(input_fields=["past_target"], axes=(0, 1)),
AddAxisLength(target_field="past_target", axis=0),
])
def create_transformation(self) -> Transformation:
return Chain([
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
dtype=self.dtype,
),
InstanceSplitter(
target_field=FieldName.TARGET,
is_pad_field=FieldName.IS_PAD,
start_field=FieldName.START,
forecast_start_field=FieldName.FORECAST_START,
train_sampler=self.train_sampler,
past_length=self.context_length,
future_length=self.prediction_length,
time_series_fields=[FieldName.OBSERVED_VALUES],
),
])
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_instance_splitter(self, mode: str):
assert mode in ["training", "validation", "test"]
instance_sampler = {
"training": ContinuousTimeUniformSampler(
num_instances=self.num_training_instances,
min_past=self.context_interval_length,
min_future=self.prediction_interval_length,
),
"validation": ContinuousTimePredictionSampler(
allow_empty_interval=True,
min_past=self.context_interval_length,
min_future=self.prediction_interval_length,
),
"test": ContinuousTimePredictionSampler(
min_past=self.context_interval_length,
allow_empty_interval=False,
),
}[mode]
assert isinstance(instance_sampler, ContinuousTimePointSampler)
return Chain(
[
ContinuousTimeInstanceSplitter(
past_interval_length=self.context_interval_length,
future_interval_length=self.prediction_interval_length,
instance_sampler=instance_sampler,
),
RenameFields(
{
"past_target": "target",
"past_valid_length": "valid_length",
}
),
]
)
def create_transformation(self) -> Transformation:
return Chain([])
def create_transformation(self) -> Transformation:
remove_field_names = [
FieldName.FEAT_DYNAMIC_CAT,
FieldName.FEAT_STATIC_REAL,
]
if not self.use_feat_dynamic_real:
remove_field_names.append(FieldName.FEAT_DYNAMIC_REAL)
return Chain(
[RemoveFields(field_names=remove_field_names)]
+ (
[SetField(output_field=FieldName.FEAT_STATIC_CAT, value=[0.0])]
if not self.use_feat_static_cat
else []
)
+ [
AsNumpyArray(field=FieldName.FEAT_STATIC_CAT, expected_ndim=1),
AsNumpyArray(field=FieldName.TARGET, expected_ndim=1),
# gives target the (1, T) layout
ExpandDimArray(field=FieldName.TARGET, axis=0),
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
),
# Unnormalized seasonal features
AddTimeFeatures(
time_features=CompositeISSM.seasonal_features(self.freq),
pred_length=self.prediction_length,
start_field=FieldName.START,
target_field=FieldName.TARGET,
output_field=SEASON_INDICATORS_FIELD,
),
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]
+ (
[FieldName.FEAT_DYNAMIC_REAL]
if self.use_feat_dynamic_real
else []
),
),
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,
SEASON_INDICATORS_FIELD,
FieldName.OBSERVED_VALUES,
],
allow_target_padding=True,
instance_length=self.past_length,
use_prediction_features=True,
prediction_length=self.prediction_length,
),
]
)
def create_transformation(self) -> Transformation:
transforms = ([AsNumpyArray(field=FieldName.TARGET, expected_ndim=1)] +
([
AsNumpyArray(field=name, expected_ndim=1)
for name in self.static_cardinalities.keys()
]) + [
AsNumpyArray(field=name, expected_ndim=1)
for name in chain(
self.static_feature_dims.keys(),
self.dynamic_cardinalities.keys(),
)
] + [
AsNumpyArray(field=name, expected_ndim=2)
for name in self.dynamic_feature_dims.keys()
] + [
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,
),
])
if self.static_cardinalities:
transforms.append(
VstackFeatures(
output_field=FieldName.FEAT_STATIC_CAT,
input_fields=list(self.static_cardinalities.keys()),
h_stack=True,
))
else:
transforms.extend([
SetField(
output_field=FieldName.FEAT_STATIC_CAT,
value=[0.0],
),
AsNumpyArray(field=FieldName.FEAT_STATIC_CAT, expected_ndim=1),
])
if self.static_feature_dims:
transforms.append(
VstackFeatures(
output_field=FieldName.FEAT_STATIC_REAL,
input_fields=list(self.static_feature_dims.keys()),
h_stack=True,
))
else:
transforms.extend([
SetField(
output_field=FieldName.FEAT_STATIC_REAL,
value=[0.0],
),
AsNumpyArray(field=FieldName.FEAT_STATIC_REAL,
expected_ndim=1),
])
if self.dynamic_cardinalities:
transforms.append(
VstackFeatures(
output_field=FieldName.FEAT_DYNAMIC_CAT,
input_fields=list(self.dynamic_cardinalities.keys()),
))
else:
transforms.extend([
SetField(
output_field=FieldName.FEAT_DYNAMIC_CAT,
value=[[0.0]],
),
AsNumpyArray(
field=FieldName.FEAT_DYNAMIC_CAT,
expected_ndim=2,
),
BroadcastTo(
field=FieldName.FEAT_DYNAMIC_CAT,
ext_length=self.prediction_length,
),
])
input_fields = [FieldName.FEAT_TIME]
if self.dynamic_feature_dims:
input_fields += list(self.dynamic_feature_dims.keys())
transforms.append(
VstackFeatures(
input_fields=input_fields,
output_field=FieldName.FEAT_DYNAMIC_REAL,
))
if self.past_dynamic_cardinalities:
transforms.append(
VstackFeatures(
output_field=FieldName.PAST_FEAT_DYNAMIC + "_cat",
input_fields=list(self.past_dynamic_cardinalities.keys()),
))
else:
transforms.extend([
SetField(
output_field=FieldName.PAST_FEAT_DYNAMIC + "_cat",
value=[[0.0]],
),
AsNumpyArray(
field=FieldName.PAST_FEAT_DYNAMIC + "_cat",
expected_ndim=2,
),
BroadcastTo(field=FieldName.PAST_FEAT_DYNAMIC + "_cat"),
])
if self.past_dynamic_feature_dims:
transforms.append(
VstackFeatures(
output_field=FieldName.PAST_FEAT_DYNAMIC_REAL,
input_fields=list(self.past_dynamic_feature_dims.keys()),
))
else:
transforms.extend([
SetField(
output_field=FieldName.PAST_FEAT_DYNAMIC_REAL,
value=[[0.0]],
),
AsNumpyArray(field=FieldName.PAST_FEAT_DYNAMIC_REAL,
expected_ndim=2),
BroadcastTo(field=FieldName.PAST_FEAT_DYNAMIC_REAL),
])
return Chain(transforms)
def _create_instance_splitter(self, mode: str):
assert mode in ["training", "validation", "test"]
instance_sampler = {
"training": self.train_sampler,
"validation": self.validation_sampler,
"test": TestSplitSampler(),
}[mode]
chain = []
chain.append(
# because of how the forking decoder works, every time step
# in context is used for splitting, which is why we use the TestSplitSampler
ForkingSequenceSplitter(
instance_sampler=instance_sampler,
enc_len=self.context_length,
dec_len=self.prediction_length,
num_forking=self.num_forking,
encoder_series_fields=[
FieldName.OBSERVED_VALUES,
# RTS with past and future values which is never empty because added dummy constant variable
FieldName.FEAT_DYNAMIC,
]
+ (
# RTS with only past values are only used by the encoder
[FieldName.PAST_FEAT_DYNAMIC_REAL]
if self.use_past_feat_dynamic_real
else []
),
encoder_disabled_fields=(
[FieldName.FEAT_DYNAMIC]
if not self.enable_encoder_dynamic_feature
else []
)
+ (
[FieldName.PAST_FEAT_DYNAMIC_REAL]
if not self.enable_encoder_dynamic_feature
and self.use_past_feat_dynamic_real
else []
),
decoder_series_fields=[
# Decoder will use all fields under FEAT_DYNAMIC which are the RTS with past and future values
FieldName.FEAT_DYNAMIC,
]
+ ([FieldName.OBSERVED_VALUES] if mode is not "test" else []),
decoder_disabled_fields=(
[FieldName.FEAT_DYNAMIC]
if not self.enable_decoder_dynamic_feature
else []
),
)
)
# past_feat_dynamic features generated above in ForkingSequenceSplitter from those under feat_dynamic - we need
# to stack with the other short related time series from the system labeled as past_past_feat_dynamic_real.
# The system labels them as past_feat_dynamic_real and the additional past_ is added to the string
# in the ForkingSequenceSplitter
if self.use_past_feat_dynamic_real:
# Stack features from ForkingSequenceSplitter horizontally since they were transposed
# so shape is now (enc_len, num_past_feature_dynamic)
chain.append(
VstackFeatures(
output_field=FieldName.PAST_FEAT_DYNAMIC,
input_fields=[
"past_" + FieldName.PAST_FEAT_DYNAMIC_REAL,
FieldName.PAST_FEAT_DYNAMIC,
],
h_stack=True,
)
)
return Chain(chain)
def create_transformation(self) -> Transformation:
chain = []
dynamic_feat_fields = []
remove_field_names = [
FieldName.FEAT_DYNAMIC_CAT,
FieldName.FEAT_STATIC_REAL,
]
# --- GENERAL TRANSFORMATION CHAIN ---
# determine unused input
if not self.use_past_feat_dynamic_real:
remove_field_names.append(FieldName.PAST_FEAT_DYNAMIC_REAL)
if not self.use_feat_dynamic_real:
remove_field_names.append(FieldName.FEAT_DYNAMIC_REAL)
if not self.use_feat_static_cat:
remove_field_names.append(FieldName.FEAT_STATIC_CAT)
chain.extend(
[
RemoveFields(field_names=remove_field_names),
AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
dtype=self.dtype,
),
]
)
# --- TRANSFORMATION CHAIN FOR DYNAMIC FEATURES ---
if self.add_time_feature:
chain.append(
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,
dtype=self.dtype,
)
)
dynamic_feat_fields.append(FieldName.FEAT_TIME)
if self.add_age_feature:
chain.append(
AddAgeFeature(
target_field=FieldName.TARGET,
output_field=FieldName.FEAT_AGE,
pred_length=self.prediction_length,
dtype=self.dtype,
)
)
dynamic_feat_fields.append(FieldName.FEAT_AGE)
if self.use_feat_dynamic_real:
# Backwards compatibility:
chain.append(
RenameFields({"dynamic_feat": FieldName.FEAT_DYNAMIC_REAL})
)
dynamic_feat_fields.append(FieldName.FEAT_DYNAMIC_REAL)
# we need to make sure that there is always some dynamic input
# we will however disregard it in the hybrid forward.
# the time feature is empty for yearly freq so also adding a dummy feature
# in the case that the time feature is the only one on
if len(dynamic_feat_fields) == 0 or (
not self.add_age_feature
and not self.use_feat_dynamic_real
and self.freq == "Y"
):
chain.append(
AddConstFeature(
target_field=FieldName.TARGET,
output_field=FieldName.FEAT_CONST,
pred_length=self.prediction_length,
const=0.0, # For consistency in case with no dynamic features
dtype=self.dtype,
)
)
dynamic_feat_fields.append(FieldName.FEAT_CONST)
# now we map all the dynamic input of length context_length + prediction_length onto FieldName.FEAT_DYNAMIC
# we exclude past_feat_dynamic_real since its length is only context_length
if len(dynamic_feat_fields) > 1:
chain.append(
VstackFeatures(
output_field=FieldName.FEAT_DYNAMIC,
input_fields=dynamic_feat_fields,
)
)
elif len(dynamic_feat_fields) == 1:
chain.append(
RenameFields({dynamic_feat_fields[0]: FieldName.FEAT_DYNAMIC})
)
# --- TRANSFORMATION CHAIN FOR STATIC FEATURES ---
if not self.use_feat_static_cat:
chain.append(
SetField(
output_field=FieldName.FEAT_STATIC_CAT,
value=np.array([0], dtype=np.int32),
)
)
# --- SAMPLE AND CUT THE TIME-SERIES ---
chain.append(
# because of how the forking decoder works, every time step
# in context is used for splitting, which is why we use the TestSplitSampler
ForkingSequenceSplitter(
train_sampler=TestSplitSampler(),
enc_len=self.context_length,
dec_len=self.prediction_length,
num_forking=self.num_forking,
encoder_series_fields=[
FieldName.OBSERVED_VALUES,
# RTS with past and future values which is never empty because added dummy constant variable
FieldName.FEAT_DYNAMIC,
]
+ (
# RTS with only past values are only used by the encoder
[FieldName.PAST_FEAT_DYNAMIC_REAL]
if self.use_past_feat_dynamic_real
else []
),
encoder_disabled_fields=(
[FieldName.FEAT_DYNAMIC]
if not self.enable_encoder_dynamic_feature
else []
)
+ (
[FieldName.PAST_FEAT_DYNAMIC_REAL]
if not self.enable_encoder_dynamic_feature
and self.use_past_feat_dynamic_real
else []
),
decoder_series_fields=[
FieldName.OBSERVED_VALUES,
# Decoder will use all fields under FEAT_DYNAMIC which are the RTS with past and future values
FieldName.FEAT_DYNAMIC,
],
decoder_disabled_fields=(
[FieldName.FEAT_DYNAMIC]
if not self.enable_decoder_dynamic_feature
else []
),
prediction_time_decoder_exclude=[FieldName.OBSERVED_VALUES],
)
)
# past_feat_dynamic features generated above in ForkingSequenceSplitter from those under feat_dynamic - we need
# to stack with the other short related time series from the system labeled as past_past_feat_dynamic_real.
# The system labels them as past_feat_dynamic_real and the additional past_ is added to the string
# in the ForkingSequenceSplitter
if self.use_past_feat_dynamic_real:
# Stack features from ForkingSequenceSplitter horizontally since they were transposed
# so shape is now (enc_len, num_past_feature_dynamic)
chain.append(
VstackFeatures(
output_field=FieldName.PAST_FEAT_DYNAMIC,
input_fields=[
"past_" + FieldName.PAST_FEAT_DYNAMIC_REAL,
FieldName.PAST_FEAT_DYNAMIC,
],
h_stack=True,
)
)
return Chain(chain)
