def create_transformation(self) -> transform.Transformation:
return transform.Chain(trans=[
transform.AsNumpyArray(field=FieldName.TARGET, expected_ndim=1),
transform.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,
),
transform.VstackFeatures(
output_field=FieldName.FEAT_DYNAMIC_REAL,
input_fields=[FieldName.FEAT_TIME],
),
transform.SetFieldIfNotPresent(field=FieldName.FEAT_STATIC_CAT,
value=[0.0]),
transform.AsNumpyArray(field=FieldName.FEAT_STATIC_CAT,
expected_ndim=1),
transform.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),
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 __init__(
self,
freq: str,
prediction_length: int,
trainer: Trainer = Trainer(),
context_length: Optional[int] = None,
num_layers: int = 2,
num_cells: int = 40,
cell_type: str = 'lstm',
num_eval_samples: int = 100,
dropout_rate: float = 0.1,
use_feat_dynamic_real: bool = False,
use_feat_static_cat: bool = False,
cardinality: Optional[List[int]] = None,
embedding_dimension: int = 20,
distr_output: DistributionOutput = StudentTOutput(),
scaling: bool = True,
lags_seq: Optional[List[int]] = None,
time_features: Optional[List[TimeFeature]] = None,
) -> None:
super().__init__(trainer=trainer)
assert (prediction_length >
0), "The value of `prediction_length` should be > 0"
assert (context_length is None or context_length > 0
), "The value of `context_length` should be > 0"
assert num_layers > 0, "The value of `num_layers` should be > 0"
assert num_cells > 0, "The value of `num_cells` should be > 0"
assert (num_eval_samples >
0), "The value of `num_eval_samples` should be > 0"
assert dropout_rate >= 0, "The value of `dropout_rate` should be >= 0"
assert (cardinality is not None or not use_feat_static_cat
), "You must set `cardinality` if `use_feat_static_cat=True`"
assert cardinality is None or [
c > 0 for c in cardinality
], "Elements of `cardinality` should be > 0"
assert (embedding_dimension >
0), "The value of `embedding_dimension` should be > 0"
self.freq = freq
self.context_length = (context_length if context_length is not None
else prediction_length)
self.prediction_length = prediction_length
self.distr_output = distr_output
self.num_layers = num_layers
self.num_cells = num_cells
self.cell_type = cell_type
self.num_sample_paths = num_eval_samples
self.dropout_rate = dropout_rate
self.use_feat_dynamic_real = use_feat_dynamic_real
self.use_feat_static_cat = use_feat_static_cat
self.cardinality = cardinality if use_feat_static_cat else [1]
self.embedding_dimension = embedding_dimension
self.scaling = scaling
self.lags_seq = (lags_seq if lags_seq is not None else
get_lags_for_frequency(freq_str=freq))
self.time_features = (time_features if time_features is not None else
time_features_from_frequency_str(self.freq))
self.history_length = self.context_length + max(self.lags_seq)
def create_transformation(
self, bin_edges: np.ndarray
) -> 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=self.prediction_length,
output_NTC=False,
time_series_fields=[
FieldName.FEAT_TIME,
FieldName.OBSERVED_VALUES,
],
),
QuantizeScaled(
bin_edges=bin_edges,
future_target="future_target",
past_target="past_target",
),
]
)
def __init__(
self,
freq: str,
prediction_length: int,
cardinality: int,
trainer: Trainer = Trainer(),
context_length: Optional[int] = None,
kernel_output: KernelOutput = RBFKernelOutput(),
params_scaling: bool = True,
float_type: DType = np.float64,
max_iter_jitter: int = 10,
jitter_method: str = "iter",
sample_noise: bool = True,
time_features: Optional[List[TimeFeature]] = None,
num_parallel_samples: int = 100,
) -> None:
self.float_type = float_type
super().__init__(trainer=trainer, float_type=self.float_type)
assert (
prediction_length > 0
), "The value of `prediction_length` should be > 0"
assert cardinality > 0, "The value of `cardinality` should be > 0"
assert (
context_length is None or context_length > 0
), "The value of `context_length` should be > 0"
assert (
num_parallel_samples > 0
), "The value of `num_parallel_samples` should be > 0"
self.freq = freq
self.prediction_length = prediction_length
self.context_length = (
context_length if context_length is not None else prediction_length
)
self.cardinality = cardinality
self.kernel_output = kernel_output
self.params_scaling = params_scaling
self.max_iter_jitter = max_iter_jitter
self.jitter_method = jitter_method
self.sample_noise = sample_noise
self.time_features = (
time_features
if time_features is not None
else time_features_from_frequency_str(self.freq)
)
self.num_parallel_samples = num_parallel_samples
def __init__(
self,
freq: str,
prediction_length: int,
add_trend: bool = False,
past_length: Optional[int] = None,
num_periods_to_train: int = 4,
trainer: Trainer = Trainer(epochs=25, hybridize=False),
num_layers: int = 2,
num_cells: int = 40,
cell_type: str = "lstm",
num_eval_samples: int = 100,
dropout_rate: float = 0.1,
use_feat_dynamic_real: bool = False,
use_feat_static_cat: bool = False,
cardinality: Optional[List[int]] = None,
embedding_dimension: int = 20,
issm: Optional[ISSM] = None,
scaling: bool = True,
time_features: Optional[List[TimeFeature]] = None,
) -> None:
super().__init__(trainer=trainer)
assert (
prediction_length > 0
), "The value of `prediction_length` should be > 0"
assert (
past_length is None or past_length > 0
), "The value of `past_length` should be > 0"
assert num_layers > 0, "The value of `num_layers` should be > 0"
assert num_cells > 0, "The value of `num_cells` should be > 0"
assert (
num_eval_samples > 0
), "The value of `num_eval_samples` should be > 0"
assert dropout_rate >= 0, "The value of `dropout_rate` should be >= 0"
assert (
cardinality is not None or not use_feat_static_cat
), "You must set `cardinality` if `use_feat_static_cat=True`"
assert cardinality is None or [
c > 0 for c in cardinality
], "Elements of `cardinality` should be > 0"
assert (
embedding_dimension > 0
), "The value of `embedding_dimension` should be > 0"
self.freq = freq
self.past_length = (
past_length
if past_length is not None
else num_periods_to_train * longest_period_from_frequency_str(freq)
)
self.prediction_length = prediction_length
self.add_trend = add_trend
self.num_layers = num_layers
self.num_cells = num_cells
self.cell_type = cell_type
self.num_sample_paths = num_eval_samples
self.scaling = scaling
self.dropout_rate = dropout_rate
self.use_feat_dynamic_real = use_feat_dynamic_real
self.use_feat_static_cat = use_feat_static_cat
self.cardinality = cardinality if use_feat_static_cat else [1]
self.embedding_dimension = embedding_dimension
self.issm = (
issm
if issm is not None
else CompositeISSM.get_from_freq(freq, add_trend)
)
self.time_features = (
time_features
if time_features is not None
else time_features_from_frequency_str(self.freq)
)
def _get_features(
self,
train_index: pd.DatetimeIndex,
prediction_length: int,
custom_features: np.ndarray = None,
) -> Tuple[np.ndarray, np.ndarray]:
"""
Internal method for computing default, (optional) seasonal features
for the training and prediction ranges given time index for the
training range and the prediction length.
Appends `custom_features` if provided.
Parameters
----------
train_index
Pandas DatetimeIndex
prediction_length
prediction length
custom_features
shape: (num_custom_features, train_length + pred_length)
Returns
-------
a tuple of (training, prediction) feature tensors
shape: (num_features, train_length/pred_length)
"""
train_length = len(train_index)
full_time_index = pd.date_range(
train_index.min(),
periods=train_length + prediction_length,
freq=train_index.freq,
)
# Default feature map for both seasonal and non-seasonal models.
if self._is_exp_kernel():
# Default time index features: index of the time point
# [0, train_length + pred_length - 1]
features = np.expand_dims(np.array(range(len(full_time_index))),
axis=0)
# Rescale time index features into the range: [-0.5, 0.5]
# similar to the seasonal features
# (see gluonts.time_feature)
features = features / (train_length + prediction_length - 1) - 0.5
else:
# For uniform seasonal model we do not add time index features
features = np.empty((0, len(full_time_index)))
# Add more features for seasonal variant
if self.use_seasonal_model:
if custom_features is not None:
total_length = train_length + prediction_length
assert len(custom_features.shape) == 2, (
"Custom features should be 2D-array where the rows "
"represent features and columns the time points.")
assert custom_features.shape[1] == total_length, (
f"For a seasonal model, feat_dynamic_real must be defined "
f"for both training and prediction ranges. They are only "
f"provided for {custom_features.shape[1]} time steps "
f"instead of {train_length + prediction_length} steps.")
features = np.vstack(
[features, self.feature_scale * custom_features])
if self.use_default_time_features or custom_features is None:
# construct seasonal features
seasonal_features_gen = time_features_from_frequency_str(
full_time_index.freqstr)
seasonal_features = [
self.feature_scale * gen(full_time_index) for gen in
seasonal_features_gen[:self.num_default_time_features]
]
features = np.vstack([features, *seasonal_features])
train_features = features[:, :train_length]
pred_features = features[:, train_length:]
return train_features, pred_features
def __init__(
self,
freq: str,
prediction_length: int,
context_length: Optional[int] = None,
trainer: Trainer = Trainer(),
dropout_rate: float = 0.1,
cardinality: Optional[List[int]] = None,
embedding_dimension: int = 20,
distr_output: DistributionOutput = StudentTOutput(),
model_dim: int = 32,
inner_ff_dim_scale: int = 4,
pre_seq: str = "dn",
post_seq: str = "drn",
act_type: str = "softrelu",
num_heads: int = 8,
scaling: bool = True,
lags_seq: Optional[List[int]] = None,
time_features: Optional[List[TimeFeature]] = None,
use_feat_dynamic_real: bool = False,
use_feat_static_cat: bool = False,
num_parallel_samples: int = 100,
) -> None:
super().__init__(trainer=trainer)
assert (
prediction_length > 0
), "The value of `prediction_length` should be > 0"
assert (
context_length is None or context_length > 0
), "The value of `context_length` should be > 0"
assert dropout_rate >= 0, "The value of `dropout_rate` should be >= 0"
assert (
cardinality is not None or not use_feat_static_cat
), "You must set `cardinality` if `use_feat_static_cat=True`"
assert cardinality is None or [
c > 0 for c in cardinality
], "Elements of `cardinality` should be > 0"
assert (
embedding_dimension > 0
), "The value of `embedding_dimension` should be > 0"
assert (
num_parallel_samples > 0
), "The value of `num_parallel_samples` should be > 0"
self.freq = freq
self.prediction_length = prediction_length
self.context_length = (
context_length if context_length is not None else prediction_length
)
self.distr_output = distr_output
self.dropout_rate = dropout_rate
self.use_feat_dynamic_real = use_feat_dynamic_real
self.use_feat_static_cat = use_feat_static_cat
self.cardinality = cardinality if use_feat_static_cat else [1]
self.embedding_dimension = embedding_dimension
self.num_parallel_samples = num_parallel_samples
self.lags_seq = (
lags_seq
if lags_seq is not None
else get_lags_for_frequency(freq_str=freq)
)
self.time_features = (
time_features
if time_features is not None
else time_features_from_frequency_str(self.freq)
)
self.history_length = self.context_length + max(self.lags_seq)
self.scaling = scaling
self.config = {
"model_dim": model_dim,
"pre_seq": pre_seq,
"post_seq": post_seq,
"dropout_rate": dropout_rate,
"inner_ff_dim_scale": inner_ff_dim_scale,
"act_type": act_type,
"num_heads": num_heads,
}
self.encoder = TransformerEncoder(
self.context_length, self.config, prefix="enc_"
)
self.decoder = TransformerDecoder(
self.prediction_length, self.config, prefix="dec_"
)
