def compute_data_from_recipe(
self,
num_steps: int,
constant: Optional[float] = None,
one_to_zero: float = 0.1,
zero_to_one: float = 0.1,
scale_features: float = 200,
) -> TrainDatasets:
recipe = []
recipe_type = Constant(constant)
if self.is_noise:
recipe_type += RandomGaussian() # Use default stddev = 1.0
if self.is_trend:
recipe_type += LinearTrend()
if self.is_promotions:
recipe.append(
("binary_causal", BinaryMarkovChain(one_to_zero, zero_to_one))
)
recipe.append(
(FieldName.FEAT_DYNAMIC_REAL, Stack(["binary_causal"]))
)
recipe_type += scale_features * Lag("binary_causal", lag=0)
if self.holidays:
# Compute dates array
dates = list(
pd.period_range(self.start, periods=num_steps, freq=self.freq)
)
recipe.append(
("binary_holidays", BinaryHolidays(dates, self.holidays))
)
recipe.append(
(FieldName.FEAT_DYNAMIC_REAL, Stack(["binary_holidays"]))
)
recipe_type += scale_features * Lag("binary_holidays", lag=0)
recipe.append((FieldName.TARGET, recipe_type))
max_train_length = num_steps - self.prediction_length
data = RecipeDataset(
recipe=recipe,
metadata=self.metadata,
max_train_length=max_train_length,
prediction_length=self.prediction_length,
# Add 1 time series at a time in the loop for different constant
# valus per time series
num_timeseries=1,
)
generated = data.generate()
return generated
def default_synthetic() -> Tuple[DatasetInfo, Dataset, Dataset]:
recipe = [
(FieldName.TARGET, LinearTrend() + RandomGaussian()),
(FieldName.FEAT_STATIC_CAT, RandomCat([10])),
(
FieldName.FEAT_STATIC_REAL,
ForEachCat(RandomGaussian(1, (10,)), FieldName.FEAT_STATIC_CAT)
+ RandomGaussian(0.1, (10,)),
),
]
data = RecipeDataset(
recipe=recipe,
metadata=MetaData(
freq="D",
feat_static_real=[
BasicFeatureInfo(name=FieldName.FEAT_STATIC_REAL)
],
feat_static_cat=[
CategoricalFeatureInfo(
name=FieldName.FEAT_STATIC_CAT, cardinality=10
)
],
feat_dynamic_real=[
BasicFeatureInfo(name=FieldName.FEAT_DYNAMIC_REAL)
],
),
max_train_length=20,
prediction_length=10,
num_timeseries=10,
trim_length_fun=lambda x, **kwargs: np.minimum(
int(np.random.geometric(1 / (kwargs["train_length"] / 2))),
kwargs["train_length"],
),
)
generated = data.generate()
assert generated.test is not None
info = data.dataset_info(generated.train, generated.test)
return info, generated.train, generated.test
def compute_data_from_recipe(
self,
num_steps: int,
constant: Optional[float] = None,
one_to_zero: float = 0.1,
zero_to_one: float = 0.1,
scale_features: float = 200,
) -> TrainDatasets:
recipe = []
recipe_type = Constant(constant)
if self.is_noise:
recipe_type += RandomGaussian() # Use default stddev = 1.0
if self.is_trend:
recipe_type += LinearTrend()
if self.is_promotions:
recipe.append(
('binary_causal', BinaryMarkovChain(one_to_zero, zero_to_one)))
recipe.append(('feat_dynamic_real', Stack(['binary_causal'])))
recipe_type += scale_features * Lag('binary_causal', lag=0)
if self.holidays:
timestamp = self.init_date()
# Compute dates array
dates = []
for i in range(num_steps):
dates.append(timestamp)
timestamp += 1
recipe.append(('binary_holidays', Binary(dates, self.holidays)))
recipe.append(('feat_dynamic_real', Stack(['binary_holidays'])))
recipe_type += scale_features * Lag('binary_holidays', lag=0)
recipe.append(('target', recipe_type))
max_train_length = num_steps - self.prediction_length
data = RecipeDataset(
recipe=recipe,
metadata=self.metadata,
max_train_length=max_train_length,
prediction_length=self.prediction_length,
num_timeseries=
1, # Add 1 time series at a time in the loop for different constant valus per time series
)
generated = data.generate()
return generated
def default_synthetic() -> Tuple[DatasetInfo, Dataset, Dataset]:
recipe = [
('target', LinearTrend() + RandomGaussian()),
('feat_static_cat', RandomCat([10])),
(
'feat_static_real',
ForEachCat(RandomGaussian(1, 10), 'feat_static_cat') +
RandomGaussian(0.1, 10),
),
]
data = RecipeDataset(
recipe=recipe,
metadata=MetaData(
time_granularity='D',
feat_static_real=[BasicFeatureInfo(name='feat_static_real')],
feat_static_cat=[
CategoricalFeatureInfo(name='feat_static_cat', cardinality=10)
],
feat_dynamic_real=[BasicFeatureInfo(name='feat_dynamic_real')],
),
max_train_length=20,
prediction_length=10,
num_timeseries=10,
trim_length_fun=lambda x, **kwargs: np.minimum(
int(np.random.geometric(1 / (kwargs['train_length'] / 2))),
kwargs['train_length'],
),
)
generated = data.generate()
assert generated.test is not None
info = data.dataset_info(generated.train, generated.test)
return info, generated.train, generated.test
Env,
)
BASE_RECIPE = [("foo", ConstantVec(1.0)), ("cat", RandomCat([10]))]
@pytest.mark.parametrize(
"func",
[
Debug(),
RandomGaussian(),
RandomBinary(),
RandomSymmetricDirichlet(),
BinaryMarkovChain(0.1, 0.1),
Constant(1),
LinearTrend(),
RandomCat([10]),
Lag("foo", 1),
ForEachCat(RandomGaussian()),
Eval("np.random.rand(length)"),
SmoothSeasonality(Constant(12), Constant(0)),
Add(["foo", "foo"]),
Mul(["foo", "foo"]),
NanWhere("foo", "foo"),
Stack([Ref("foo"), Ref("foo")]),
RandomGaussian() + RandomGaussian(),
RandomGaussian() * RandomGaussian(),
RandomGaussian() / RandomGaussian(),
],
)
def test_call_and_repr(func) -> None:
take_as_list,
)
BASE_RECIPE = [('foo', ConstantVec(1.0)), ('cat', RandomCat([10]))]
@pytest.mark.parametrize(
"func",
[
Debug(),
RandomGaussian(),
RandomBinary(),
RandomSymmetricDirichlet(),
BinaryMarkovChain(0.1, 0.1),
Constant(1),
LinearTrend(),
RandomCat([10]),
Lag("foo", 1),
ForEachCat(RandomGaussian()),
Expr("np.random.rand(length)"),
SmoothSeasonality(Constant(12), Constant(0)),
Add(['foo', 'foo']),
Mul(['foo', 'foo']),
NanWhere('foo', 'foo'),
NanWhereNot('foo', 'foo'),
Stack(['foo', 'foo']),
RandomGaussian() + RandomGaussian(),
RandomGaussian() * RandomGaussian(),
RandomGaussian() / RandomGaussian(),
],
)