def __init__(
self,
prediction_length: int,
freq: str,
context_length: Optional[int] = None,
# FIXME: prefix those so clients know that these are decoder params
mlp_final_dim: int = 20,
mlp_hidden_dimension_seq: List[int] = list(),
trainer: Trainer = Trainer(),
quantiles: List[float] = list([0.1, 0.5, 0.9]),
) -> None:
encoder = RNNEncoder(
mode="gru",
hidden_size=50,
num_layers=1,
bidirectional=True,
prefix="encoder_",
)
super(MQRNNEstimator, self).__init__(
encoder=encoder,
mlp_final_dim=mlp_final_dim,
mlp_hidden_dimension_seq=mlp_hidden_dimension_seq,
freq=freq,
prediction_length=prediction_length,
trainer=trainer,
context_length=context_length,
quantiles=quantiles,
)
def __init__(
self,
prediction_length: int,
freq: str,
context_length: Optional[int] = None,
decoder_mlp_dim_seq: List[int] = None,
trainer: Trainer = Trainer(),
quantiles: List[float] = None,
scaling: bool = True,
) -> None:
assert (prediction_length >
0), f"Invalid prediction length: {prediction_length}."
assert decoder_mlp_dim_seq is None or all(
d > 0 for d in decoder_mlp_dim_seq
), "Elements of `mlp_hidden_dimension_seq` should be > 0"
assert quantiles is None or all(
0 <= d <= 1 for d in
quantiles), "Elements of `quantiles` should be >= 0 and <= 1"
self.decoder_mlp_dim_seq = (decoder_mlp_dim_seq if decoder_mlp_dim_seq
is not None else [30])
self.quantiles = (quantiles if quantiles is not None else
[0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9])
# `use_static_feat` and `use_dynamic_feat` always True because network
# always receives input; either from the input data or constants
encoder = RNNEncoder(
mode="gru",
hidden_size=50,
num_layers=1,
bidirectional=True,
prefix="encoder_",
use_static_feat=True,
use_dynamic_feat=True,
)
decoder = ForkingMLPDecoder(
dec_len=prediction_length,
final_dim=self.decoder_mlp_dim_seq[-1],
hidden_dimension_sequence=self.decoder_mlp_dim_seq[:-1],
prefix="decoder_",
)
quantile_output = QuantileOutput(self.quantiles)
super().__init__(
encoder=encoder,
decoder=decoder,
quantile_output=quantile_output,
freq=freq,
prediction_length=prediction_length,
context_length=context_length,
trainer=trainer,
scaling=scaling,
)
def __init__(
self,
freq: str,
prediction_length: int,
cardinality: List[int],
embedding_dimension: int,
encoder_rnn_layer: int,
encoder_rnn_num_hidden: int,
decoder_mlp_layer: List[int],
decoder_mlp_static_dim: int,
encoder_rnn_model: str = "lstm",
encoder_rnn_bidirectional: bool = True,
scaler: Scaler = NOPScaler(),
context_length: Optional[int] = None,
quantiles: Optional[List[float]] = None,
trainer: Trainer = Trainer(),
num_parallel_samples: int = 100,
) -> None:
encoder = RNNEncoder(
mode=encoder_rnn_model,
hidden_size=encoder_rnn_num_hidden,
num_layers=encoder_rnn_layer,
bidirectional=encoder_rnn_bidirectional,
use_static_feat=True,
use_dynamic_feat=True,
)
super(RNN2QRForecaster, self).__init__(
freq=freq,
prediction_length=prediction_length,
encoder=encoder,
cardinality=cardinality,
embedding_dimension=embedding_dimension,
decoder_mlp_layer=decoder_mlp_layer,
decoder_mlp_static_dim=decoder_mlp_static_dim,
context_length=context_length,
scaler=scaler,
quantiles=quantiles,
trainer=trainer,
num_parallel_samples=num_parallel_samples,
)