Classification

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

All classifiers in aeon can be listed using the aeon.registry.all_estimators utility, using estimator_types="classifier", optionally filtered by tags. Valid tags can be listed by calling the function aeon.registry.all_tags.

Convolution-based

Arsenal([num_kernels, n_estimators, ...])

Arsenal ensemble.

HydraClassifier([n_kernels, n_groups, ...])

Hydra Classifier.

MultiRocketHydraClassifier([n_kernels, ...])

MultiRocket-Hydra Classifier.

RocketClassifier([num_kernels, ...])

Classifier wrapped for the Rocket transformer using RidgeClassifierCV.

Deep learning

CNNClassifier([n_layers, kernel_size, ...])

Time Convolutional Neural Network (CNN).

EncoderClassifier([n_epochs, batch_size, ...])

Establish the network structure for an Encoder.

FCNClassifier([n_layers, n_filters, ...])

Fully Convolutional Network (FCN).

InceptionTimeClassifier([n_classifiers, ...])

InceptionTime ensemble classifier.

IndividualInceptionClassifier([n_filters, ...])

Single InceptionTime classifier.

IndividualLITEClassifier([n_filters, ...])

Single LITETime classifier.

LITETimeClassifier([n_classifiers, ...])

LITETime ensemble classifier.

MLPClassifier([n_epochs, batch_size, ...])

Multi Layer Perceptron Network (MLP).

ResNetClassifier([n_residual_blocks, ...])

Residual Neural Network (RNN).

TapNetClassifier([n_epochs, batch_size, ...])

Time series attentional prototype network (TapNet).

Dictionary-based

BOSSEnsemble([threshold, max_ensemble_size, ...])

Ensemble of Bag of Symbolic Fourier Approximation Symbols (BOSS).

ContractableBOSS([n_parameter_samples, ...])

Contractable Bag of Symbolic Fourier Approximation Symbols (cBOSS).

IndividualBOSS([window_size, word_length, ...])

Single bag of Symbolic Fourier Approximation Symbols (IndividualBOSS).

IndividualTDE([window_size, word_length, ...])

Single TDE classifier, an extension of the Bag of SFA Symbols (BOSS) model.

MUSE([anova, variance, bigrams, window_inc, ...])

MUSE (MUltivariate Symbolic Extension).

REDCOMETS([variant, perc_length, n_trees, ...])

Random EnhanceD Co-eye for Multivariate Time Series (RED CoMETS).

TemporalDictionaryEnsemble([...])

Temporal Dictionary Ensemble (TDE).

WEASEL([anova, bigrams, binning_strategy, ...])

Word Extraction for Time Series Classification (WEASEL).

WEASEL_V2([min_window, norm_options, ...])

Word Extraction for Time Series Classification (WEASEL) v2.0.

Distance-based

ElasticEnsemble([distance_measures, ...])

The Elastic Ensemble (EE) of time series distance measures.

KNeighborsTimeSeriesClassifier([distance, ...])

K-Nearest Neighbour Time Series Classifier.

Feature-based

Catch22Classifier([features, catch24, ...])

Canonical Time-series Characteristics (catch22) classifier.

FreshPRINCEClassifier([...])

Fresh Pipeline with RotatIoN forest Classifier.

SignatureClassifier([estimator, ...])

Classification module using signature-based features.

SummaryClassifier([summary_stats, ...])

Summary statistic classifier.

TSFreshClassifier([default_fc_parameters, ...])

Time Series Feature Extraction based on Scalable Hypothesis Tests classifier.

Hybrid

HIVECOTEV1([stc_params, tsf_params, ...])

Hierarchical Vote Collective of Transformation-based Ensembles (HIVE-COTE) V1.

HIVECOTEV2([stc_params, drcif_params, ...])

Hierarchical Vote Collective of Transformation-based Ensembles (HIVE-COTE) V2.

RISTClassifier([n_intervals, n_shapelets, ...])

Randomised Interval-Shapelet Transformation (RIST) pipeline classifier.

Interval-based

CanonicalIntervalForestClassifier([...])

Canonical Interval Forest Classifier (CIF).

DrCIFClassifier([base_estimator, ...])

Diverse Representation Canonical Interval Forest Classifier (DrCIF).

IntervalForestClassifier([base_estimator, ...])

Configurable interval extracting forest classifier.

QUANTClassifier([interval_depth, ...])

QUANT interval classifier.

RandomIntervalClassifier([n_intervals, ...])

Random Interval Classifier.

RandomIntervalSpectralEnsembleClassifier([...])

Random Interval Spectral Ensemble (RISE) classifier.

RSTSF([n_estimators, n_intervals, ...])

Random Supervised Time Series Forest (RSTSF) Classifier.

SupervisedIntervalClassifier([n_intervals, ...])

Supervised Interval Classifier.

SupervisedTimeSeriesForest([base_estimator, ...])

Supervised Time Series Forest (STSF).

TimeSeriesForestClassifier([base_estimator, ...])

Time series forest (TSF) classifier.

Shapelet-based

LearningShapeletClassifier([...])

Learning Shapelet classifier.

MrSQMClassifier([strat, features_per_rep, ...])

Multiple Representations Sequence Miner (MrSQM) classifier.

RDSTClassifier([max_shapelets, ...])

A random dilated shapelet transform (RDST) classifier.

SASTClassifier([length_list, stride, ...])

Classification pipeline using SAST [1]_ transformer and an sklean classifier.

ShapeletTransformClassifier([...])

A shapelet transform classifier (STC).

sklearn

ContinuousIntervalTree([max_depth, ...])

Continuous interval tree (CIT) vector classifier (aka Time Series Tree).

RotationForestClassifier([n_estimators, ...])

A rotation forest (RotF) vector classifier.

Early classification

ProbabilityThresholdEarlyClassifier([...])

Probability Threshold Early Classifier.

TEASER([estimator, one_class_classifier, ...])

Two-tier Early and Accurate Series Classifier (TEASER).

Ordinal classification

IndividualOrdinalTDE([window_size, ...])

Single O-TDE classifier.

OrdinalTDE([n_parameter_samples, ...])

Ordinal Temporal Dictionary Ensemble (O-TDE).

histogram_intersection(first, second)

Find the distance between two histograms using the histogram intersection.

Composition

ClassifierPipeline(transformers, classifier)

Pipeline of transformers and a classifier.

ChannelEnsembleClassifier(estimators[, ...])

Applies estimators to channels of an array.

WeightedEnsembleClassifier(classifiers[, ...])

Weighted ensemble of classifiers with fittable ensemble weight.

Base

BaseClassifier()

Abstract base class for time series classifiers.

DummyClassifier([strategy, random_state, ...])

DummyClassifier makes predictions that ignore the input features.

BaseDeepClassifier([batch_size, ...])

Abstract base class for deep learning time series classifiers.

BaseEarlyClassifier()

Abstract base class for early time series classifiers.