def test_parallelized_predictor():
dataset = ListDataset(
data_iter=[{
"start": "2012-01-01",
"target": (np.zeros(20) + i).tolist()
} for i in range(300)],
freq="1H",
)
base_predictor = IdentityPredictor(freq="1H",
prediction_length=10,
num_samples=100)
predictor = ParallelizedPredictor(base_predictor=base_predictor,
num_workers=10,
chunk_size=2)
predictions = list(base_predictor.predict(dataset))
parallel_predictions = list(predictor.predict(dataset))
assert len(predictions) == len(parallel_predictions)
for p, pp in zip(predictions, parallel_predictions):
assert np.all(p.samples == pp.samples)
assert np.all(p.index == pp.index)
def setup_class(self):
self.frequency = "D"
self.prediction_length = 2
timeseries_0 = {
TIMESERIES_KEYS.START:
"2018-01-01",
TIMESERIES_KEYS.TARGET:
np.array([12, 13, 14, 15]),
TIMESERIES_KEYS.TARGET_NAME:
"sales",
TIMESERIES_KEYS.TIME_COLUMN_NAME:
"date",
TIMESERIES_KEYS.FEAT_DYNAMIC_REAL:
np.array([[1, 0, 0, 0, 0, 1], [0, 0, 0, 1, 1, 0]]),
TIMESERIES_KEYS.FEAT_DYNAMIC_REAL_COLUMNS_NAMES:
["is_holiday", "is_weekend"],
TIMESERIES_KEYS.IDENTIFIERS: {
"store": 1,
"item": 1
},
}
timeseries_1 = {
TIMESERIES_KEYS.START:
"2018-01-01",
TIMESERIES_KEYS.TARGET:
np.array([2, 3, 4, 5]),
TIMESERIES_KEYS.TARGET_NAME:
"sales",
TIMESERIES_KEYS.TIME_COLUMN_NAME:
"date",
TIMESERIES_KEYS.FEAT_DYNAMIC_REAL:
np.array([[1, 0, 0, 0, 0, 1], [0, 0, 0, 1, 1, 0]]),
TIMESERIES_KEYS.FEAT_DYNAMIC_REAL_COLUMNS_NAMES:
["is_holiday", "is_weekend"],
TIMESERIES_KEYS.IDENTIFIERS: {
"store": 1,
"item": 2
},
}
self.gluon_dataset = ListDataset([timeseries_0, timeseries_1],
freq=self.frequency)
self.predictor = IdentityPredictor(prediction_length=2,
freq="D",
num_samples=100)