Time series regression

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

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

A full table with tag based search is also available on the Estimator Search Page (select “regresser” in the “Estimator type” dropdown).

Composition

RegressorPipeline(regressor, transformers)	Pipeline of transformers and a regressor.
SklearnRegressorPipeline(regressor, transformers)	Pipeline of transformers and a regressor.
MultiplexRegressor(regressors[, ...])	MultiplexRegressor for selecting among different models.

Model selection and tuning

TSRGridSearchCV(estimator, param_grid[, ...])

Exhaustive search over specified parameter values for an estimator.

Ensembles

ComposableTimeSeriesForestRegressor([...])

Time-Series Forest Regressor.

Deep learning

CNNRegressor([n_epochs, batch_size, ...])	Time Series Convolutional Neural Network (CNN), as described in [1].
CNTCRegressor([n_epochs, batch_size, ...])	Contextual Time-series Neural Regressor (CNTC), as described in [1].
FCNRegressor([n_epochs, batch_size, ...])	Fully Connected Neural Network (FCN), as described in [Rea5a1664c466-1].
InceptionTimeRegressor([n_epochs, ...])	InceptionTime Deep Learning Regressor.
LSTMFCNRegressor([n_epochs, batch_size, ...])	Implementation of LSTMFCNRegressor from Karim et al (2019) [1].
MACNNRegressor([n_epochs, batch_size, ...])	Multi-Scale Attention Convolutional Neural Regressor, as described in [R360bad5d0241-1].
MCDCNNRegressor([n_epochs, batch_size, ...])	Multi Channel Deep Convolutional Neural Regressor, adopted from [R244bb0d4e2ae-1].
MLPRegressor([n_epochs, batch_size, ...])	Multi Layer Perceptron Network (MLP), as described in [R15a0eceb2106-1].
SimpleRNNRegressor([n_epochs, batch_size, ...])	Simple recurrent neural network.
ResNetRegressor([n_epochs, callbacks, ...])	Residual Neural Network Regressor adopted from [1].
TapNetRegressor([n_epochs, batch_size, ...])	Time series attentional prototype network (TapNet), as described in [1].

Distance-based

KNeighborsTimeSeriesRegressor([n_neighbors, ...])

K-nearest neighbours Time Series Regressor.

Dummy

DummyRegressor([strategy, constant, quantile])

DummyRegressor makes predictions that ignore the input features.

Interval-based

TimeSeriesForestRegressor([min_interval, ...])

Time series forest regressor.

Kernel-based

TimeSeriesSVRTslearn([C, kernel, degree, ...])	Time Series Suppoer Vector Regressor, from tslearn.
RocketRegressor([num_kernels, ...])	Regressor wrapped for the Rocket transformer using RidgeCV regressor.

Base

BaseRegressor()

Abstract base class for time series regressors.

BaseDeepRegressor()

Abstract base class for deep learning time series regression.