def test_boss_on_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 BOSS
boss = BOSSEnsemble(random_state=47)
boss.fit(X_train, y_train)
score = boss.score(X_test.iloc[indices], y_test[indices])
assert (score >= 0.80)
def test_boss_on_gunpoint():
# load gunpoint data
X_train, y_train = load_gunpoint(split='train', return_X_y=True)
X_test, y_test = load_gunpoint(split='test', return_X_y=True)
indices = np.random.RandomState(0).permutation(10)
# train boss
boss = BOSSEnsemble(random_state=0)
boss.fit(X_train.iloc[indices], y_train[indices])
# assert probabilities are the same
probas = boss.predict_proba(X_test.iloc[indices])
testing.assert_array_equal(probas, boss_gunpoint_probas)
def classifierBuilder(clf_name, params):
clf_params_dict = list_to_dict(params)
if (clf_name == 'BOSSE_CLF'):
clf = BOSSEnsemble()
else:
raise ValueError("Specified classifier is not an option")
return clf
def test_boss_train_estimate():
"""Test of BOSS train estimate on unit test data."""
# load unit test data
X_train, y_train = load_unit_test(split="train")
# train BOSS
boss = BOSSEnsemble(max_ensemble_size=2,
random_state=0,
save_train_predictions=True)
boss.fit(X_train, y_train)
# test train estimate
train_probas = boss._get_train_probs(X_train, y_train)
assert train_probas.shape == (20, 2)
train_preds = boss.classes_[np.argmax(train_probas, axis=1)]
assert accuracy_score(y_train, train_preds) >= 0.6
def classifierBuilder(clf_name, params):
clf_params_dict = list_to_dict(params)
if (clf_name == 'BOSSE_CLF'):
BOSSE_params = BOSSE_default_parameters
for e in clf_params_dict:
BOSSE_params[e] = clf_params_dict[e]
clf = BOSSEnsemble(min_window=BOSSE_params['min_window'],
threshold=BOSSE_params['threshold'])
else:
raise ValueError("Specified classifier is not an option")
return clf
def test_boss_on_unit_test_data():
"""Test of BOSS 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 BOSS
boss = BOSSEnsemble(max_ensemble_size=5,
random_state=0,
save_train_predictions=True)
boss.fit(X_train, y_train)
# assert probabilities are the same
probas = boss.predict_proba(X_test.iloc[indices])
testing.assert_array_almost_equal(probas, boss_unit_test_probas, decimal=2)
# test train estimate
train_probas = boss._get_train_probs(X_train, y_train)
train_preds = boss.classes_[np.argmax(train_probas, axis=1)]
assert accuracy_score(y_train, train_preds) >= 0.75
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")
print(test_name)
print("[")
for sub_array in array:
print("[")
for value in sub_array:
print(value.astype(str), end="")
print(", ")
print("],")
print("]")
if __name__ == "__main__":
_print_array(
"BOSSEnsemble - UnitTest",
_reproduce_classification_unit_test(
BOSSEnsemble(max_ensemble_size=5, random_state=0)
),
)
_print_array(
"IndividualBOSS - UnitTest",
_reproduce_classification_unit_test(IndividualBOSS(random_state=0)),
)
_print_array(
"ContractableBOSS - UnitTest",
_reproduce_classification_unit_test(
ContractableBOSS(
n_parameter_samples=25, max_ensemble_size=5, random_state=0
)
),
)
_print_array(
def set_classifier(cls, resampleId):
"""
Basic way of determining the classifier to build. To differentiate settings just and another elif. So, for example, if
you wanted tuned TSF, you just pass TuneTSF and set up the tuning mechanism in the elif.
This may well get superceded, it is just how e have always done it
:param cls: String indicating which classifier you want
:return: A classifier.
"""
if cls.lower() == "pf":
return pf.ProximityForest(random_state=resampleId)
elif cls.lower() == "pt":
return pf.ProximityTree(random_state=resampleId)
elif cls.lower() == "ps":
return pf.ProximityStump(random_state=resampleId)
elif cls.lower() == "rise":
return fb.RandomIntervalSpectralForest(random_state=resampleId)
elif cls.lower() == "tsf":
return ib.TimeSeriesForest(random_state=resampleId)
elif cls.lower() == "cif":
return CanonicalIntervalForest(random_state=resampleId)
elif cls.lower() == "boss":
return BOSSEnsemble(random_state=resampleId)
elif cls.lower() == "cboss":
return ContractableBOSS(random_state=resampleId)
elif cls.lower() == "tde":
return TemporalDictionaryEnsemble(random_state=resampleId)
elif cls.lower() == "st":
return st.ShapeletTransformClassifier(time_contract_in_mins=1500)
elif cls.lower() == "dtwcv":
return nn.KNeighborsTimeSeriesClassifier(metric="dtwcv")
elif cls.lower() == "ee" or cls.lower() == "elasticensemble":
return dist.ElasticEnsemble()
elif cls.lower() == "tsfcomposite":
# It defaults to TSF
return ensemble.TimeSeriesForestClassifier()
elif cls.lower() == "risecomposite":
steps = [
("segment", RandomIntervalSegmenter(n_intervals=1, min_length=5)),
(
"transform",
FeatureUnion([
(
"acf",
make_row_transformer(
FunctionTransformer(func=acf_coefs,
validate=False)),
),
(
"ps",
make_row_transformer(
FunctionTransformer(func=powerspectrum,
validate=False)),
),
]),
),
("tabularise", Tabularizer()),
("clf", DecisionTreeClassifier()),
]
base_estimator = Pipeline(steps)
return ensemble.TimeSeriesForestClassifier(estimator=base_estimator,
n_estimators=100)
elif cls.lower() == "rocket":
rocket_pipeline = make_pipeline(
Rocket(random_state=resampleId),
RidgeClassifierCV(alphas=np.logspace(-3, 3, 10), normalize=True),
)
return rocket_pipeline
else:
raise Exception("UNKNOWN CLASSIFIER")