def test_smoke(
hybridize: bool, target_dim_sample: int, use_marginal_transformation: bool
):
num_batches_per_epoch = 1
estimator = GPVAREstimator(
distr_output=LowrankGPOutput(rank=2),
num_cells=1,
num_layers=1,
pick_incomplete=True,
prediction_length=metadata.prediction_length,
target_dim=target_dim,
target_dim_sample=target_dim_sample,
freq=metadata.freq,
use_marginal_transformation=use_marginal_transformation,
trainer=Trainer(
epochs=2,
batch_size=10,
learning_rate=1e-4,
num_batches_per_epoch=num_batches_per_epoch,
hybridize=hybridize,
),
)
predictor = estimator.train(training_data=dataset.train)
agg_metrics, _ = backtest_metrics(
test_dataset=dataset.test,
predictor=predictor,
num_samples=10,
evaluator=MultivariateEvaluator(
quantiles=(0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9)
),
)
assert agg_metrics["ND"] < 2.5
def test_gp_output():
# test that gp output gives expected shapes
batch = 1
hidden_size = 3
dim = 4
rank = 2
states = mx.ndarray.ones(shape=(batch, dim, hidden_size))
lowrank_gp_output = LowrankGPOutput(dim=dim, rank=rank)
proj = lowrank_gp_output.get_args_proj()
proj.initialize()
distr_args = proj(states)
mu, D, W = distr_args
assert mu.shape == (batch, dim)
assert D.shape == (batch, dim)
assert W.shape == (batch, dim, rank)
def __init__(
self,
freq: str,
prediction_length: int,
target_dim: int,
trainer: Trainer = Trainer(),
# number of dimension to sample at training time
context_length: Optional[int] = None,
num_layers: int = 2,
num_cells: int = 40,
cell_type: str = "lstm",
num_parallel_samples: int = 100,
dropout_rate: float = 0.1,
target_dim_sample: Optional[int] = None,
distr_output: Optional[DistributionOutput] = None,
rank: Optional[int] = 2,
scaling: bool = True,
pick_incomplete: bool = False,
lags_seq: Optional[List[int]] = None,
shuffle_target_dim: bool = True,
time_features: Optional[List[TimeFeature]] = None,
conditioning_length: int = 100,
use_marginal_transformation: bool = False,
train_sampler: Optional[InstanceSampler] = None,
validation_sampler: Optional[InstanceSampler] = None,
batch_size: int = 32,
) -> None:
super().__init__(trainer=trainer, batch_size=batch_size)
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_parallel_samples > 0
), "The value of `num_eval_samples` should be > 0"
assert dropout_rate >= 0, "The value of `dropout_rate` should be >= 0"
if distr_output is not None:
self.distr_output = distr_output
else:
self.distr_output = LowrankGPOutput(rank=rank)
self.freq = freq
self.context_length = (
context_length if context_length is not None else prediction_length
)
self.prediction_length = prediction_length
self.target_dim = target_dim
self.target_dim_sample = (
target_dim
if target_dim_sample is None
else min(target_dim_sample, target_dim)
)
self.shuffle_target_dim = shuffle_target_dim
self.num_layers = num_layers
self.num_cells = num_cells
self.cell_type = cell_type
self.num_parallel_samples = num_parallel_samples
self.dropout_rate = dropout_rate
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.pick_incomplete = pick_incomplete
self.scaling = scaling
self.conditioning_length = conditioning_length
self.use_marginal_transformation = use_marginal_transformation
self.output_transform = (
cdf_to_gaussian_forward_transform
if self.use_marginal_transformation
else None
)
self.train_sampler = (
train_sampler
if train_sampler is not None
else ExpectedNumInstanceSampler(
num_instances=1.0,
min_past=0 if pick_incomplete else self.history_length,
min_future=prediction_length,
)
)
self.validation_sampler = (
validation_sampler
if validation_sampler is not None
else ValidationSplitSampler(
min_past=0 if pick_incomplete else self.history_length,
min_future=prediction_length,
)
)
