Regression

The aeon.regression module contains algorithms and composition tools for time series regression.

All regressors in aeon``can be listed using the ``aeon.registry.all_estimators utility, using estimator_types="regressor", optionally filtered by tags. Valid tags can be listed using aeon.registry.all_tags.

Convolution-based

RocketRegressor([num_kernels, ...])

Regressor wrapped for the Rocket transformer using RidgeCV regressor.

Deep learning

CNNRegressor([n_layers, kernel_size, ...])	Time Series Convolutional Neural Network (CNN).
FCNRegressor([n_layers, n_filters, ...])	Fully Convolutional Network (FCN).
TapNetRegressor([n_epochs, batch_size, ...])	Time series attentional prototype network (TapNet).
InceptionTimeRegressor([n_regressors, ...])	InceptionTime ensemble regressor.
IndividualInceptionRegressor([nb_filters, ...])	Single Inception regressor.
ResNetRegressor([n_residual_blocks, ...])	Residual Neural Network.

Distance-based

KNeighborsTimeSeriesRegressor([distance, ...])

K-Nearest Neighbour Time Series Regressor.

Dummy

DummyRegressor([strategy, constant, quantile])

DummyRegressor makes predictions that ignore the input features.

Feature-based

FreshPRINCERegressor([...])

Fresh Pipeline with RotatIoN forest Regressor.

Interval-based

TimeSeriesForestRegressor([base_estimator, ...])

Time series forest (TSF) regressor.

sklearn

RotationForestRegressor([n_estimators, ...])

A Rotation Forest (RotF) vector regressor.

Base

BaseRegressor()

Abstract base class for time series regressors.

BaseDeepRegressor([batch_size, last_file_name])

Abstract base class for deep learning time series regression.