def test_hivecote_v1_on_unit_test_data(): """Test of HIVECOTEV1 on unit test data.""" # load unit test data X_train, y_train = load_unit_test(split="train", return_X_y=True) X_test, y_test = load_unit_test(split="test", return_X_y=True) indices = np.random.RandomState(0).choice(len(y_train), 10, replace=False) # train HIVE-COTE v1 hc1 = HIVECOTEV1( random_state=0, stc_params={ "estimator": RotationForest(n_estimators=3), "n_shapelet_samples": 500, "max_shapelets": 20, "batch_size": 100, }, tsf_params={"n_estimators": 10}, rise_params={"n_estimators": 10}, cboss_params={ "n_parameter_samples": 25, "max_ensemble_size": 5 }, ) hc1.fit(X_train.iloc[indices], y_train[indices]) # assert probabilities are the same probas = hc1.predict_proba(X_test.iloc[indices]) testing.assert_array_almost_equal(probas, hivecote_v1_unit_test_probas, decimal=2)
def test_hivecote_v1_on_power_demand(): """Test of HIVE-COTEv1 on italy power demand.""" # load power demand data X_train, y_train = load_italy_power_demand(split="train", return_X_y=True) X_test, y_test = load_italy_power_demand(split="test", return_X_y=True) indices = np.random.RandomState(0).permutation(100) # train HIVE-COTE v1 hc1 = HIVECOTEV1( random_state=0, stc_params={ "n_estimators": 10, "transform_contract_in_mins": 0.1 }, tsf_params={"n_estimators": 10}, rise_params={"n_estimators": 10}, cboss_params={ "n_parameter_samples": 25, "max_ensemble_size": 5 }, ) hc1.fit(X_train, y_train) score = hc1.score(X_test.iloc[indices], y_test[indices]) assert score >= 0.92
def set_classifier(cls, resampleId=None): """ Basic way of creating the classifier to build using the default settings. This set up is to help with batch jobs for multiple problems to facilitate easy reproducability. You can set up bespoke classifier in many other ways. :param cls: String indicating which classifier you want :param resampleId: classifier random seed :return: A classifier. """ name = cls.lower() # Distance based if name == "pf" or name == "proximityforest": return ProximityForest(random_state=resampleId) elif name == "pt" or name == "proximitytree": return ProximityTree(random_state=resampleId) elif name == "ps" or name == "proximityStump": return ProximityStump(random_state=resampleId) elif name == "dtwcv" or name == "kneighborstimeseriesclassifier": return KNeighborsTimeSeriesClassifier(distance="dtwcv") elif name == "dtw" or name == "1nn-dtw": return KNeighborsTimeSeriesClassifier(distance="dtw") elif name == "msm" or name == "1nn-msm": return KNeighborsTimeSeriesClassifier(distance="msm") elif name == "ee" or name == "elasticensemble": return ElasticEnsemble() elif name == "shapedtw": return ShapeDTW() # Dictionary based elif name == "boss" or name == "bossensemble": return BOSSEnsemble(random_state=resampleId) elif name == "cboss" or name == "contractableboss": return ContractableBOSS(random_state=resampleId) elif name == "tde" or name == "temporaldictionaryensemble": return TemporalDictionaryEnsemble(random_state=resampleId) elif name == "weasel": return WEASEL(random_state=resampleId) elif name == "muse": return MUSE(random_state=resampleId) # Interval based elif name == "rise" or name == "randomintervalspectralforest": return RandomIntervalSpectralForest(random_state=resampleId) elif name == "tsf" or name == "timeseriesforestclassifier": return TimeSeriesForestClassifier(random_state=resampleId) elif name == "cif" or name == "canonicalintervalforest": return CanonicalIntervalForest(random_state=resampleId) elif name == "drcif": return DrCIF(random_state=resampleId) # Shapelet based elif name == "stc" or name == "shapelettransformclassifier": return ShapeletTransformClassifier( random_state=resampleId, time_contract_in_mins=1 ) elif name == "mrseql" or name == "mrseqlclassifier": return MrSEQLClassifier(seql_mode="fs", symrep=["sax", "sfa"]) elif name == "rocket": return ROCKETClassifier(random_state=resampleId) elif name == "arsenal": return Arsenal(random_state=resampleId) # Hybrid elif name == "catch22": return Catch22ForestClassifier(random_state=resampleId) elif name == "hivecotev1": return HIVECOTEV1(random_state=resampleId) else: raise Exception("UNKNOWN CLASSIFIER")
def set_classifier(cls, resample_id=None, train_file=False): """Construct a classifier. Basic way of creating the classifier to build using the default settings. This set up is to help with batch jobs for multiple problems to facilitate easy reproducibility for use with load_and_run_classification_experiment. You can pass a classifier object instead to run_classification_experiment. Parameters ---------- cls : str String indicating which classifier you want. resample_id : int or None, default=None Classifier random seed. train_file : bool, default=False Whether a train file is being produced. Return ------ classifier : A BaseClassifier. The classifier matching the input classifier name. """ name = cls.lower() # Dictionary based if name == "boss" or name == "bossensemble": return BOSSEnsemble(random_state=resample_id) elif name == "cboss" or name == "contractableboss": return ContractableBOSS(random_state=resample_id) elif name == "tde" or name == "temporaldictionaryensemble": return TemporalDictionaryEnsemble( random_state=resample_id, save_train_predictions=train_file ) elif name == "weasel": return WEASEL(random_state=resample_id) elif name == "muse": return MUSE(random_state=resample_id) # Distance based elif name == "pf" or name == "proximityforest": return ProximityForest(random_state=resample_id) elif name == "pt" or name == "proximitytree": return ProximityTree(random_state=resample_id) elif name == "ps" or name == "proximityStump": return ProximityStump(random_state=resample_id) elif name == "dtwcv" or name == "kneighborstimeseriesclassifier": return KNeighborsTimeSeriesClassifier(distance="dtwcv") elif name == "dtw" or name == "1nn-dtw": return KNeighborsTimeSeriesClassifier(distance="dtw") elif name == "msm" or name == "1nn-msm": return KNeighborsTimeSeriesClassifier(distance="msm") elif name == "ee" or name == "elasticensemble": return ElasticEnsemble(random_state=resample_id) elif name == "shapedtw": return ShapeDTW() # Feature based elif name == "catch22": return Catch22Classifier( random_state=resample_id, estimator=RandomForestClassifier(n_estimators=500) ) elif name == "matrixprofile": return MatrixProfileClassifier(random_state=resample_id) elif name == "signature": return SignatureClassifier( random_state=resample_id, estimator=RandomForestClassifier(n_estimators=500), ) elif name == "tsfresh": return TSFreshClassifier( random_state=resample_id, estimator=RandomForestClassifier(n_estimators=500) ) elif name == "tsfresh-r": return TSFreshClassifier( random_state=resample_id, estimator=RandomForestClassifier(n_estimators=500), relevant_feature_extractor=True, ) # Hybrid elif name == "hc1" or name == "hivecotev1": return HIVECOTEV1(random_state=resample_id) elif name == "hc2" or name == "hivecotev2": return HIVECOTEV2(random_state=resample_id) # Interval based elif name == "rise" or name == "randomintervalspectralforest": return RandomIntervalSpectralEnsemble( random_state=resample_id, n_estimators=500 ) elif name == "tsf" or name == "timeseriesforestclassifier": return TimeSeriesForestClassifier(random_state=resample_id, n_estimators=500) elif name == "cif" or name == "canonicalintervalforest": return CanonicalIntervalForest(random_state=resample_id, n_estimators=500) elif name == "stsf" or name == "supervisedtimeseriesforest": return SupervisedTimeSeriesForest(random_state=resample_id, n_estimators=500) elif name == "drcif": return DrCIF( random_state=resample_id, n_estimators=500, save_transformed_data=train_file ) # Kernel based elif name == "rocket": return ROCKETClassifier(random_state=resample_id) elif name == "arsenal": return Arsenal(random_state=resample_id, save_transformed_data=train_file) # Shapelet based elif name == "stc" or name == "shapelettransformclassifier": return ShapeletTransformClassifier( random_state=resample_id, save_transformed_data=train_file ) elif name == "mrseql" or name == "mrseqlclassifier": return MrSEQLClassifier(seql_mode="fs", symrep=["sax", "sfa"]) else: raise Exception("UNKNOWN CLASSIFIER")
random_state=0, default_fc_parameters="minimal", relevant_feature_extractor=False, estimator=RandomForestClassifier(n_estimators=10), ) ), ) _print_array( "HIVECOTEV1 - UnitTest", _reproduce_classification_unit_test( HIVECOTEV1( random_state=0, stc_params={ "estimator": RandomForestClassifier(n_estimators=3), "n_shapelet_samples": 500, "max_shapelets": 20, }, tsf_params={"n_estimators": 10}, rise_params={"n_estimators": 10}, cboss_params={"n_parameter_samples": 25, "max_ensemble_size": 5}, ) ), ) _print_array( "HIVECOTEV2 - UnitTest", _reproduce_classification_unit_test( HIVECOTEV2( random_state=0, stc_params={ "estimator": RandomForestClassifier(n_estimators=3), "n_shapelet_samples": 500,