make_pipeline

make_pipeline(*steps)

Create a pipeline from aeon and sklearn estimators.

Currently available for:

forecasters, classifiers, regressors, clusterers, and transformers.

Parameters:

stepslist or tuple of aeon and/or sklearn estimators

This should be provided in same order as the required pipeline construction

Returns:

pipeaeon pipeline containing steps, in order

always a descendant of BaseObject, precise object determined by equivalent to result of step[0] * step[1] * … * step[-1]

Examples

Example 1: forecaster pipeline >>> from aeon.datasets import load_airline >>> from aeon.forecasting.trend import PolynomialTrendForecaster >>> from aeon.pipeline import make_pipeline >>> from aeon.transformations.exponent import ExponentTransformer >>> pipe = make_pipeline(ExponentTransformer(), PolynomialTrendForecaster()) >>> type(pipe).__name__ ‘TransformedTargetForecaster’

Example 2: classifier pipeline >>> from aeon.classification.feature_based import Catch22Classifier >>> from aeon.pipeline import make_pipeline >>> from aeon.transformations.exponent import ExponentTransformer >>> pipe = make_pipeline(ExponentTransformer(), Catch22Classifier()) >>> type(pipe).__name__ ‘ClassifierPipeline’

Example 3: transformer pipeline >>> from aeon.pipeline import make_pipeline >>> from aeon.transformations.exponent import ExponentTransformer >>> pipe = make_pipeline(ExponentTransformer(), ExponentTransformer()) >>> type(pipe).__name__ ‘TransformerPipeline’