def test_faked_DataLakeBackedDataset(MockDataset):
provider = DataLakeProvider(storename="dataplatformdlsprod", interactive=True)
dataset = TimeSeriesDataset(data_provider=provider, **CONFIG)
# Should be able to call get_data without being asked to authenticate in tests
X, y = dataset.get_data()
def test_timeseries_target_tags(tag_list, target_tag_list):
start = dateutil.parser.isoparse("2017-12-25 06:00:00Z")
end = dateutil.parser.isoparse("2017-12-29 06:00:00Z")
tsd = TimeSeriesDataset(
start,
end,
tag_list=tag_list,
target_tag_list=target_tag_list,
data_provider=MockDataProvider(),
)
X, y = tsd.get_data()
assert len(X) == len(y)
# If target_tag_list is empty, it defaults to tag_list
if target_tag_list:
assert y.shape[1] == len(target_tag_list)
else:
assert y.shape[1] == len(tag_list)
# Ensure the order in maintained
assert [tag.name for tag in target_tag_list or tag_list] == y.columns.tolist()
# Features should match the tag_list
assert X.shape[1] == len(tag_list)
# Ensure the order in maintained
assert [tag.name for tag in tag_list] == X.columns.tolist()
def test_trigger_tags(mock_tag_normalizer):
data_provider = MockDataProvider()
dataset = TimeSeriesDataset(
data_provider=data_provider,
tag_list=[
SensorTag("Tag 1", None),
SensorTag("Tag 2", None),
],
target_tag_list=[
SensorTag("Tag 5", None),
],
train_start_date=dateutil.parser.isoparse("2017-12-25 06:00:00Z"),
train_end_date=dateutil.parser.isoparse("2017-12-29 06:00:00Z"),
row_filter="`Tag 3` > 0 & `Tag 4` > 1",
tag_normalizer=mock_tag_normalizer,
)
X, y = dataset.get_data()
assert X is not None
assert y is not None
assert set(data_provider.last_tag_list) == {
SensorTag("Tag 1", None),
SensorTag("Tag 2", None),
SensorTag("Tag 3", None),
SensorTag("Tag 4", None),
SensorTag("Tag 5", None),
}
assert set(X.columns.values) == {"Tag 1", "Tag 2"}
assert set(y.columns.values) == {"Tag 5"}
def test_metadata_statistics():
"""Tests that it works to set aggregation method(s)"""
kwargs = dict(
data_provider=MockDataProvider(),
tag_list=[
SensorTag("Tag 1", None),
SensorTag("Tag 2", None),
SensorTag("Tag 3", None),
],
train_start_date=dateutil.parser.isoparse("2017-12-25 06:00:00Z"),
train_end_date=dateutil.parser.isoparse("2017-12-29 06:00:00Z"),
)
# Default aggregation gives no extra columns
dataset = TimeSeriesDataset(**kwargs)
X, _ = dataset.get_data()
assert (83, 3) == X.shape
metadata = dataset.get_metadata()
assert isinstance(metadata["x_hist"], dict)
assert len(metadata["x_hist"].keys()) == 3
