def test_chain():
chain = transform.Chain(trans=[
transform.AddTimeFeatures(
start_field=FieldName.START,
target_field=FieldName.TARGET,
output_field="time_feat",
time_features=[
time_feature.DayOfWeek(),
time_feature.DayOfMonth(),
time_feature.MonthOfYear(),
],
pred_length=10,
),
transform.AddAgeFeature(
target_field=FieldName.TARGET,
output_field="age",
pred_length=10,
log_scale=True,
),
transform.AddObservedValuesIndicator(target_field=FieldName.TARGET,
output_field="observed_values"),
])
assert equals(chain, clone(chain))
assert not equals(chain, clone(chain, {"trans": []}))
another_chain = transform.Chain(trans=[
transform.AddTimeFeatures(
start_field=FieldName.START,
target_field=FieldName.TARGET,
output_field="time_feat",
time_features=[
time_feature.DayOfWeek(),
time_feature.DayOfMonth(),
time_feature.MonthOfYear(),
],
pred_length=10,
),
transform.AddAgeFeature(
target_field=FieldName.TARGET,
output_field="age",
pred_length=10,
log_scale=False,
),
transform.AddObservedValuesIndicator(target_field=FieldName.TARGET,
output_field="observed_values"),
])
assert not equals(chain, another_chain)
def test_Transformation():
train_length = 100
ds = gluonts.dataset.common.ListDataset(
[{"start": "2012-01-01", "target": [0.2] * train_length}], freq="1D"
)
pred_length = 10
t = transform.Chain(
trans=[
transform.AddTimeFeatures(
start_field=transform.FieldName.START,
target_field=transform.FieldName.TARGET,
output_field="time_feat",
time_features=[
time_feature.DayOfWeek(),
time_feature.DayOfMonth(),
time_feature.MonthOfYear(),
],
pred_length=pred_length,
),
transform.AddAgeFeature(
target_field=transform.FieldName.TARGET,
output_field="age",
pred_length=pred_length,
log_scale=True,
),
transform.AddObservedValuesIndicator(
target_field=transform.FieldName.TARGET,
output_field="observed_values",
),
transform.VstackFeatures(
output_field="dynamic_feat",
input_fields=["age", "time_feat"],
drop_inputs=True,
),
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=transform.ExpectedNumInstanceSampler(
num_instances=4
),
past_length=train_length,
future_length=pred_length,
time_series_fields=["dynamic_feat", "observed_values"],
),
]
)
assert_serializable(t)
for u in t(iter(ds), is_train=True):
print(u)
def test_AddObservedIndicator():
"""
Tests the different methods to impute missing values.
"""
array_value = np.array(
[np.nan, 1.0, 1.0, np.nan, 2.0, np.nan, 1.0, np.nan])
l_methods = [
"dummy_value",
"mean",
"causal_mean",
"last_value",
"rolling_mean1",
"rolling_mean10",
]
d_method_instances = {
"dummy_value": DummyValueImputation(),
"mean": MeanValueImputation(),
"causal_mean": CausalMeanValueImputation(),
"last_value": LastValueImputation(),
"rolling_mean1": RollingMeanValueImputation(1),
"rolling_mean10": RollingMeanValueImputation(10),
}
d_expected_result = {
"dummy_value": np.array([0.0, 1.0, 1.0, 0.0, 2.0, 0.0, 1.0, 0.0]),
"mean": np.array([1.25, 1.0, 1.0, 1.25, 2.0, 1.25, 1.0, 1.25]),
"causal_mean": np.array([1.0, 1.0, 1.0, 1.0, 2.0, 1.2, 1.0, 9 / 7]),
"last_value": np.array([1.0, 1.0, 1.0, 1.0, 2.0, 2.0, 1.0, 1.0]),
"rolling_mean10": np.array([1.0, 1.0, 1.0, 1.0, 2.0, 1.1, 1.0, 1.2]),
"rolling_mean1": np.array([1.0, 1.0, 1.0, 1.0, 2.0, 2.0, 1.0, 1.0]),
}
expected_missindicator = np.array([0.0, 1.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0])
for method in l_methods:
transfo = transform.AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field=FieldName.OBSERVED_VALUES,
imputation_method=d_method_instances[method],
)
d = {"target": array_value.copy()}
res = transfo.transform(d)
assert np.array_equal(d_expected_result[method], res["target"])
assert np.array_equal(expected_missindicator,
res[FieldName.OBSERVED_VALUES])
def test_multi_dim_transformation(is_train):
train_length = 10
first_dim = np.arange(1, 11, 1).tolist()
first_dim[-1] = "NaN"
second_dim = np.arange(11, 21, 1).tolist()
second_dim[0] = "NaN"
ds = gluonts.dataset.common.ListDataset(
data_iter=[{"start": "2012-01-01", "target": [first_dim, second_dim]}],
freq="1D",
one_dim_target=False,
)
pred_length = 2
# Looks weird - but this is necessary to assert the nan entries correctly.
first_dim[-1] = np.nan
second_dim[0] = np.nan
t = transform.Chain(
trans=[
transform.AddTimeFeatures(
start_field=transform.FieldName.START,
target_field=transform.FieldName.TARGET,
output_field="time_feat",
time_features=[
time_feature.DayOfWeek(),
time_feature.DayOfMonth(),
time_feature.MonthOfYear(),
],
pred_length=pred_length,
),
transform.AddAgeFeature(
target_field=transform.FieldName.TARGET,
output_field="age",
pred_length=pred_length,
log_scale=True,
),
transform.AddObservedValuesIndicator(
target_field=transform.FieldName.TARGET,
output_field="observed_values",
convert_nans=False,
),
transform.VstackFeatures(
output_field="dynamic_feat",
input_fields=["age", "time_feat"],
drop_inputs=True,
),
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=transform.ExpectedNumInstanceSampler(
num_instances=4
),
past_length=train_length,
future_length=pred_length,
time_series_fields=["dynamic_feat", "observed_values"],
output_NTC=False,
),
]
)
assert_serializable(t)
if is_train:
for u in t(iter(ds), is_train=True):
assert_shape(u["past_target"], (2, 10))
assert_shape(u["past_dynamic_feat"], (4, 10))
assert_shape(u["past_observed_values"], (2, 10))
assert_shape(u["future_target"], (2, 2))
assert_padded_array(
u["past_observed_values"],
np.array([[1.0] * 9 + [0.0], [0.0] + [1.0] * 9]),
u["past_is_pad"],
)
assert_padded_array(
u["past_target"],
np.array([first_dim, second_dim]),
u["past_is_pad"],
)
else:
for u in t(iter(ds), is_train=False):
assert_shape(u["past_target"], (2, 10))
assert_shape(u["past_dynamic_feat"], (4, 10))
assert_shape(u["past_observed_values"], (2, 10))
assert_shape(u["future_target"], (2, 0))
assert_padded_array(
u["past_observed_values"],
np.array([[1.0] * 9 + [0.0], [0.0] + [1.0] * 9]),
u["past_is_pad"],
)
assert_padded_array(
u["past_target"],
np.array([first_dim, second_dim]),
u["past_is_pad"],
)
