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_insufficient_data_after_automatic_filtering():
"""
Test that dataframe after row_filter scenarios raise appropriate
InsufficientDataError
"""
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"),
n_samples_threshold=84,
filter_periods={"filter_method": "median"},
)
with pytest.raises(InsufficientDataError):
TimeSeriesDataset(**kwargs).get_data()
def test_insufficient_data_after_known_filter_periods_filtering():
"""
Test that dataframe after row_filter scenarios raise appropriate
InsufficientDataError
"""
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"),
n_samples_threshold=10,
known_filter_periods=[
"~('2017-12-25 07:00:00+00:00' <= index <= '2017-12-29 06:00:00+00:00')"
],
)
with pytest.raises(InsufficientDataError):
TimeSeriesDataset(**kwargs).get_data()
