def evaluate(self,
data,
metrics=['mse'],
multioutput="uniform_average",
batch_size=32):
'''
Evaluate the time series pipeline.
:param data: data can be a TSDataset or data creator(will be supported).
The TSDataset should follow the same operations as the training
TSDataset used in AutoTSEstimator.fit.
:param metrics: list. The evaluation metric name to optimize. e.g. ["mse"]
:param multioutput: Defines aggregating of multiple output values.
String in ['raw_values', 'uniform_average']. The value defaults to
'uniform_average'.
:param batch_size: predict batch_size, the process will cost more time
if batch_size is small while cost less memory. The param is only
effective when data is a TSDataset. The values defaults to 32.
'''
_, y = self._tsdataset_to_numpy(data, is_predict=False)
yhat = self.predict(data, batch_size=batch_size)
if self._scaler:
from zoo.chronos.data.utils.scale import unscale_timeseries_numpy
y = unscale_timeseries_numpy(y, self._scaler, self._scaler_index)
eval_result = [
Evaluator.evaluate(m,
y_true=y,
y_pred=yhat[:y.shape[0]],
multioutput=multioutput) for m in metrics
]
return eval_result
def unscale_numpy(self, data):
'''
Unscale the time series forecaster's numpy prediction result/ground truth.
:param data: a numpy ndarray with 3 dim whose shape should be exactly the
same with self.numpy_y.
:return: the unscaled numpy ndarray.
'''
return unscale_timeseries_numpy(data, self.scaler, self.scaler_index)
def _unscale_numpy(self, data):
'''
unscale the time series forecastor's numpy prediction result/ground truth.
:param data: a numpy ndarray with 3 dim whose shape should be exactly the
same with self.numpy_y.
:return: the unscaled numpy ndarray
'''
num_roll_target = len(self.roll_target)
repeat_factor = len(self._id_list) if self.id_sensitive else 1
scaler_index = [self.target_col.index(self.roll_target[i])
for i in range(num_roll_target)] * repeat_factor
return unscale_timeseries_numpy(data, self.scaler, scaler_index)
def predict(self, data, batch_size=32):
'''
Rolling predict with time series pipeline.
:param data: data can be a TSDataset or data creator(will be supported).
The TSDataset should follow the same operations as the training
TSDataset used in AutoTSTrainer.fit.
:param batch_size: predict batch_size, the process will cost more time
if batch_size is small while cost less memory. The param is only
effective when data is a TSDataset. The values defaults to 32.
'''
x, _ = self._tsdataset_to_numpy(data, is_predict=True)
yhat = self._best_model.predict(x, batch_size=batch_size)
if self._scaler:
from zoo.chronos.data.utils.scale import unscale_timeseries_numpy
yhat = unscale_timeseries_numpy(yhat, self._scaler, self._scaler_index)
return yhat
def _tsdataset_unscale(self, y):
if self._scaler:
from zoo.chronos.data.utils.scale import unscale_timeseries_numpy
y = unscale_timeseries_numpy(y, self._scaler, self._scaler_index)
return y
