def test_recipe_dataset(recipe) -> None:
data = RecipeDataset(
recipe=recipe,
metadata=MetaData(
freq="D",
feat_static_real=[BasicFeatureInfo(name="feat_static_real_000")],
feat_static_cat=[
CategoricalFeatureInfo(name="foo", cardinality=10)
],
feat_dynamic_real=[BasicFeatureInfo(name="binary_causal")],
),
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()
generated_train = list(generated.train)
generated_test = list(generated.test)
train_lengths = np.array([len(x["target"]) for x in generated_train])
test_lengths = np.array([len(x["target"]) for x in generated_test])
assert np.all(test_lengths >= 10)
assert np.all(test_lengths - train_lengths >= 10)
assert len(list(generated.train)) == 10
def constant_dataset() -> Tuple[DatasetInfo, Dataset, Dataset]:
metadata = MetaData(
freq='1H',
feat_static_cat=[
CategoricalFeatureInfo(
name='feat_static_cat_000', cardinality='10'
)
],
feat_static_real=[BasicFeatureInfo(name='feat_static_real_000')],
)
start_date = '2000-01-01 00:00:00'
train_ds = ListDataset(
data_iter=[
{
'item': str(i),
'start': start_date,
'target': [float(i)] * 24,
'feat_static_cat': [i],
'feat_static_real': [float(i)],
}
for i in range(10)
],
freq=metadata.freq,
)
test_ds = ListDataset(
data_iter=[
{
'item': str(i),
'start': start_date,
'target': [float(i)] * 30,
'feat_static_cat': [i],
'feat_static_real': [float(i)],
}
for i in range(10)
],
freq=metadata.freq,
)
info = DatasetInfo(
name='constant_dataset',
metadata=metadata,
prediction_length=2,
train_statistics=calculate_dataset_statistics(train_ds),
test_statistics=calculate_dataset_statistics(test_ds),
)
return info, train_ds, test_ds
def constant_dataset() -> Tuple[DatasetInfo, Dataset, Dataset]:
metadata = MetaData(
freq="1H",
feat_static_cat=[
CategoricalFeatureInfo(
name="feat_static_cat_000", cardinality="10"
)
],
feat_static_real=[BasicFeatureInfo(name="feat_static_real_000")],
)
start_date = "2000-01-01 00:00:00"
train_ds = ListDataset(
data_iter=[
{
"item": str(i),
"start": start_date,
"target": [float(i)] * 24,
"feat_static_cat": [i],
"feat_static_real": [float(i)],
}
for i in range(10)
],
freq=metadata.freq,
)
test_ds = ListDataset(
data_iter=[
{
"item": str(i),
"start": start_date,
"target": [float(i)] * 30,
"feat_static_cat": [i],
"feat_static_real": [float(i)],
}
for i in range(10)
],
freq=metadata.freq,
)
info = DatasetInfo(
name="constant_dataset",
metadata=metadata,
prediction_length=2,
train_statistics=calculate_dataset_statistics(train_ds),
test_statistics=calculate_dataset_statistics(test_ds),
)
return info, train_ds, test_ds
def constant_dataset() -> Tuple[DatasetInfo, Dataset, Dataset]:
metadata = MetaData(
freq="1H",
feat_static_cat=[
CategoricalFeatureInfo(
name="feat_static_cat_000", cardinality="10"
)
],
feat_static_real=[BasicFeatureInfo(name="feat_static_real_000")],
)
start_date = "2000-01-01 00:00:00"
train_ds = ListDataset(
data_iter=[
{
FieldName.ITEM_ID: str(i),
FieldName.START: start_date,
FieldName.TARGET: [float(i)] * 24,
FieldName.FEAT_STATIC_CAT: [i],
FieldName.FEAT_STATIC_REAL: [float(i)],
}
for i in range(10)
],
freq=metadata.freq,
)
test_ds = ListDataset(
data_iter=[
{
FieldName.ITEM_ID: str(i),
FieldName.START: start_date,
FieldName.TARGET: [float(i)] * 30,
FieldName.FEAT_STATIC_CAT: [i],
FieldName.FEAT_STATIC_REAL: [float(i)],
}
for i in range(10)
],
freq=metadata.freq,
)
info = DatasetInfo(
name="constant_dataset",
metadata=metadata,
prediction_length=2,
train_statistics=calculate_dataset_statistics(train_ds),
test_statistics=calculate_dataset_statistics(test_ds),
)
return info, train_ds, test_ds
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 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
# Test data include fcast_length which are ground truths.
test_data = df2gluonts(processed_df_fill,
cat_inverted_idx,
fcast_len=0,
freq=freq,
ts_id=['sku', 'Label', 'Custname'],
static_cat=['sku', 'Label', 'Custname'])
gluonts_datasets = TrainDatasets(
metadata=MetaData(
freq=freq,
target={'name': 'quantity'},
feat_static_cat=[
# Add 'unknown'.
CategoricalFeatureInfo(name=k, cardinality=len(v) + 1)
for k, v in cat_inverted_idx.items()
],
prediction_length=fcast_length),
train=train_data,
test=test_data)
# %%
epochs = 20
metric = [
{
"Name": "train:loss",
"Regex": r"Epoch\[\d+\] Evaluation metric 'epoch_loss'=(\S+)"
},
{
