def test_y_proba_on_gunpoint():
X, y = load_gunpoint(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.1, random_state=42
)
estimator = TimeSeriesForestClassifier(random_state=42, n_estimators=20)
estimator.fit(X_train, y_train)
actual = estimator.predict_proba(X_test)
np.testing.assert_array_equal(actual, expected)
def test_tsf_on_unit_test_data():
"""Test of TimeSeriesForestClassifier on unit test data."""
# load unit test data
X_train, y_train = load_unit_test(split="train")
X_test, y_test = load_unit_test(split="test")
indices = np.random.RandomState(0).choice(len(y_train), 10, replace=False)
# train TSF
tsf = TimeSeriesForestClassifier(n_estimators=10, random_state=0)
tsf.fit(X_train, y_train)
# assert probabilities are the same
probas = tsf.predict_proba(X_test.iloc[indices])
testing.assert_array_equal(probas, tsf_unit_test_probas)
def test_teaser_near_classification_points():
"""Test of TEASER with incremental time stamps outside defined class points."""
X_train, y_train, X_test, y_test, indices = load_unit_data()
# train probability threshold
teaser = TEASER(
random_state=0,
classification_points=[6, 10, 14, 18, 24],
estimator=TimeSeriesForestClassifier(n_estimators=10, random_state=0),
)
teaser.fit(X_train, y_train)
# use test_points that are not within list above
test_points = [7, 11, 19, 20]
X_test = from_nested_to_3d_numpy(X_test)
states = None
for i in test_points:
X = X_test[indices, :, :i]
if i == 20:
with pytest.raises(ValueError):
probas, decisions, states = teaser.predict_proba(
X, state_info=states)
else:
probas, decisions, states = teaser.predict_proba(X,
state_info=states)
def test_teaser_with_different_decision_maker():
"""Test of TEASER with different One-Class-Classifier."""
X_train, y_train, X_test, y_test, indices = load_unit_data()
# train probability threshold
teaser = TEASER(
random_state=0,
classification_points=[6, 10, 16, 24],
estimator=TimeSeriesForestClassifier(n_estimators=10, random_state=0),
one_class_classifier=IsolationForest(n_estimators=5),
one_class_param_grid={"bootstrap": [True, False]},
)
teaser.fit(X_train, y_train)
final_probas = np.zeros((10, 2))
final_decisions = np.zeros(10)
X_test = from_nested_to_3d_numpy(X_test)
states = None
for i in teaser.classification_points:
X = X_test[indices, :, :i]
probas, decisions, states = teaser.predict_proba(X, state_info=states)
for n in range(10):
if decisions[n] and final_decisions[n] == 0:
final_probas[n] = probas[n]
final_decisions[n] = i
testing.assert_array_equal(final_probas, teaser_if_unit_test_probas)
def test_run_classification_experiment(tmp_path):
"""Test running and saving results for classifiers.
Currently it just checks the files have been created, then deletes them.
"""
dataset = "UnitTest"
train_X, train_Y = load_unit_test("TRAIN")
test_X, test_Y = load_unit_test("TEST")
run_classification_experiment(
train_X,
train_Y,
test_X,
test_Y,
TimeSeriesForestClassifier(n_estimators=10),
str(tmp_path),
cls_name="TSF",
dataset="UnitTest",
resample_id=0,
train_file=True,
)
test_path = tmp_path.joinpath(
f"TSF/Predictions/{dataset}/testResample0.csv")
train_path = tmp_path.joinpath(
f"TSF/Predictions/{dataset}/trainResample0.csv")
assert test_path.is_file()
assert train_path.is_file()
# remove files
test_path.unlink()
train_path.unlink()
def test_prob_threshold_on_unit_test_data():
"""Test of ProbabilityThresholdEarlyClassifier 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 probability threshold
pt = ProbabilityThresholdEarlyClassifier(
random_state=0,
classification_points=[6, 16, 24],
probability_threshold=1,
estimator=TimeSeriesForestClassifier(n_estimators=10, random_state=0),
)
pt.fit(X_train, y_train)
final_probas = np.zeros((10, 2))
final_decisions = np.zeros(10)
X_test = from_nested_to_3d_numpy(X_test)
states = None
for i in pt.classification_points:
X = X_test[indices, :, :i]
probas = pt.predict_proba(X)
decisions, states = pt.decide_prediction_safety(X, probas, states)
for n in range(10):
if decisions[n] and final_decisions[n] == 0:
final_probas[n] = probas[n]
final_decisions[n] = i
testing.assert_array_equal(final_probas, pt_unit_test_probas)
def test_run_classification_experiment():
"""Test running and saving results for classifiers.
Currently it just checks the files have been created, then deletes them.
"""
dataset = "UnitTest"
train_X, train_Y = load_unit_test("TRAIN", return_X_y=True)
test_X, test_Y = load_unit_test("TEST", return_X_y=True)
run_classification_experiment(
train_X,
train_Y,
test_X,
test_Y,
TimeSeriesForestClassifier(n_estimators=10),
"../Temp/",
cls_name="TSF",
dataset="UnitTest",
resample_id=0,
train_file=True,
)
test_path = f"../Temp/TSF/Predictions/{dataset}/testResample0.csv"
train_path = f"../Temp/TSF/Predictions/{dataset}/trainResample0.csv"
assert os.path.isfile(test_path)
assert os.path.isfile(train_path)
os.remove(test_path)
os.remove(train_path)
def test_teaser_on_unit_test_data():
"""Test of TEASER on unit test data."""
X_train, y_train, X_test, y_test, indices = load_unit_data()
# train probability threshold
teaser = TEASER(
random_state=0,
classification_points=[6, 10, 16, 24],
estimator=TimeSeriesForestClassifier(n_estimators=10, random_state=0),
)
teaser.fit(X_train, y_train)
final_probas = np.zeros((10, 2))
final_decisions = np.zeros(10)
X_test = from_nested_to_3d_numpy(X_test)
states = None
for i in teaser.classification_points:
X = X_test[indices, :, :i]
probas, decisions, states = teaser.predict_proba(X, state_info=states)
for n in range(10):
if decisions[n] and final_decisions[n] == 0:
final_probas[n] = probas[n]
final_decisions[n] = i
testing.assert_array_equal(final_probas, teaser_unit_test_probas)
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 StartTrain(self):
train_files = glob.glob(self.lineEdit.text() + "\\*.csv")
test_files = glob.glob(self.lineEdit_2.text() + "\\*.csv")
train_li = []
for filename in train_files:
df = pd.read_csv(filename, index_col=None, header=None,usecols=[2])
train_li.append(df)
X_df = pd.concat(train_li, axis=1, ignore_index=True)
X_df = X_df.T
test_li = []
for filename in test_files:
df = pd.read_csv(filename, index_col=None, header=None,usecols=[2])
test_li.append(df)
X_df_ng = pd.concat(test_li, axis=1, ignore_index=True)
X_df_ng = X_df_ng.T
X_df = X_df.append(X_df_ng)
X_df_tab = from_2d_array_to_nested(X_df)
Y_df_ok = np.zeros(len(test_li), dtype="int32")
Y_df_ng = np.ones(len(train_li), dtype="int32")
Y_df = np.concatenate([Y_df_ok, Y_df_ng], 0)
X_train, X_test, y_train, y_test = train_test_split(X_df_tab, Y_df, test_size= (100 - self.horizontalSlider.value()) / 100)
self.tableWidget.setRowCount(0)
selectedModel = self.comboBox.currentText()
if(selectedModel == "RandomForestClassifier"):
classifier = make_pipeline(Tabularizer(), RandomForestClassifier())
classifier.fit(X_train, y_train)
self.lineEdit_5.setText(str(classifier.score(X_train, y_train)))
self.lineEdit_6.setText(str(classifier.score(X_test, y_test)))
for i in range(len(X_test)):
row = self.tableWidget.rowCount()
self.tableWidget.setRowCount(row)
classifier_preds = classifier.predict(X_test.iloc[i].to_frame())
self.addTableRow(self.tableWidget, [str(i),str(y_test[i]), str(classifier_preds)])
elif(selectedModel == "RocketClassifier"):
rocket = RocketClassifier()
rocket.fit(X_train, y_train)
self.lineEdit_5.setText(str(rocket.score(X_train, y_train)))
self.lineEdit_6.setText(str(rocket.score(X_test, y_test)))
for i in range(len(X_test)):
row = self.tableWidget.rowCount()
self.tableWidget.setRowCount(row)
rocket_preds = rocket.predict(X_test.iloc[i].to_frame())
self.addTableRow(self.tableWidget, [str(i),str(y_test[i]), str(rocket_preds)])
elif(selectedModel == "TimeSeriesForestClassifier"):
tsf = TimeSeriesForestClassifier(n_estimators=50, random_state=47)
tsf.fit(X_train, y_train)
self.lineEdit_5.setText(str(tsf.score(X_train, y_train)))
self.lineEdit_6.setText(str(tsf.score(X_test, y_test)))
for i in range(len(X_test)):
row = self.tableWidget.rowCount()
self.tableWidget.setRowCount(row)
tsf_preds = tsf.predict(X_test.iloc[i].to_frame())
self.addTableRow(self.tableWidget, [str(i),str(y_test[i]), str(tsf_preds)])
elif(selectedModel == "RandomIntervalSpectralEnsemble"):
rise = RandomIntervalSpectralEnsemble(n_estimators=50, random_state=47)
rise.fit(X_train, y_train)
self.lineEdit_5.setText(str(rise.score(X_train, y_train)))
self.lineEdit_6.setText(str(rise.score(X_test, y_test)))
for i in range(len(X_test)):
row = self.tableWidget.rowCount()
self.tableWidget.setRowCount(row)
rise_preds = rise.predict(X_test.iloc[i].to_frame())
self.addTableRow(self.tableWidget, [str(i),str(y_test[i]), str(rise_preds)])
elif(selectedModel == "SupervisedTimeSeriesForest"):
stsf = SupervisedTimeSeriesForest(n_estimators=50, random_state=47)
stsf.fit(X_train, y_train)
self.lineEdit_5.setText(str(stsf.score(X_train, y_train)))
self.lineEdit_6.setText(str(stsf.score(X_test, y_test)))
for i in range(len(X_test)):
row = self.tableWidget.rowCount()
self.tableWidget.setRowCount(row)
stsf_preds = rise.predict(X_test.iloc[i].to_frame())
self.addTableRow(self.tableWidget, [str(i),str(y_test[i]), str(stsf_preds)])
else:
print("None")
class HIVECOTEV1(BaseClassifier):
"""Hierarchical Vote Collective of Transformation-based Ensembles (HIVE-COTE) V1.
An ensemble of the STC, TSF, RISE and cBOSS classifiers from different feature
representations using the CAWPE structure as described in [1].
Parameters
----------
verbose : int, level of output printed to
the console (for information only) (default = 0)
n_jobs : int, optional (default=1)
The number of jobs to run in parallel for both `fit` and `predict`.
``-1`` means using all processors.
random_state : int or None, seed for random, integer,
optional (default to no seed)
Attributes
----------
n_classes : extracted from the data
Notes
-----
..[1] Anthony Bagnall, Michael Flynn, James Large, Jason Lines and
Matthew Middlehurst.
"On the usage and performance of the Hierarchical Vote Collective of
Transformation-based Ensembles version 1.0 (hive-cote v1. 0)"
International Workshop on Advanced Analytics and Learning on Temporal
Data 2020
Java version
https://github.com/uea-machine-learning/tsml/blob/master/src/main/java/
tsml/classifiers/hybrids/HIVE_COTE.java
"""
# Capability tags
capabilities = {
"multivariate": False,
"unequal_length": False,
"missing_values": False,
"train_estimate": False,
"contractable": False,
}
def __init__(
self,
stc_params=None,
tsf_params=None,
rise_params=None,
cboss_params=None,
verbose=0,
n_jobs=1,
random_state=None,
):
if stc_params is None:
stc_params = {"n_estimators": 500}
if tsf_params is None:
tsf_params = {"n_estimators": 500}
if rise_params is None:
rise_params = {"n_estimators": 500}
if cboss_params is None:
cboss_params = {}
self.stc_params = stc_params
self.tsf_params = tsf_params
self.rise_params = rise_params
self.cboss_params = cboss_params
self.verbose = verbose
self.n_jobs = n_jobs
self.random_state = random_state
self.stc = None
self.tsf = None
self.rise = None
self.cboss = None
self.stc_weight = 0
self.tsf_weight = 0
self.rise_weight = 0
self.cboss_weight = 0
self.n_classes = 0
self.classes_ = []
super(HIVECOTEV1, self).__init__()
def fit(self, X, y):
"""Fit a HIVE-COTEv1.0 classifier.
Parameters
----------
X : nested pandas DataFrame of shape [n_instances, 1]
Nested dataframe with univariate time-series in cells.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X, y = check_X_y(X, y, enforce_univariate=True)
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
cv_size = 10
_, counts = np.unique(y, return_counts=True)
min_class = np.min(counts)
if min_class < cv_size:
cv_size = min_class
self.stc = ShapeletTransformClassifier(
**self.stc_params,
random_state=self.random_state,
)
self.stc.fit(X, y)
if self.verbose > 0:
print("STC ", datetime.now().strftime("%H:%M:%S %d/%m/%Y")) # noqa
train_preds = cross_val_predict(
ShapeletTransformClassifier(
**self.stc_params,
random_state=self.random_state,
),
X=X,
y=y,
cv=cv_size,
n_jobs=self.n_jobs,
)
self.stc_weight = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"STC train estimate ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("STC weight = " + str(self.stc_weight)) # noqa
self.tsf = TimeSeriesForestClassifier(
**self.tsf_params,
random_state=self.random_state,
n_jobs=self.n_jobs,
)
self.tsf.fit(X, y)
if self.verbose > 0:
print("TSF ", datetime.now().strftime("%H:%M:%S %d/%m/%Y")) # noqa
train_preds = cross_val_predict(
TimeSeriesForestClassifier(**self.tsf_params,
random_state=self.random_state),
X=X,
y=y,
cv=cv_size,
n_jobs=self.n_jobs,
)
self.tsf_weight = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"TSF train estimate ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("TSF weight = " + str(self.tsf_weight)) # noqa
self.rise = RandomIntervalSpectralForest(
**self.rise_params,
random_state=self.random_state,
n_jobs=self.n_jobs,
)
self.rise.fit(X, y)
if self.verbose > 0:
print("RISE ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y")) # noqa
train_preds = cross_val_predict(
RandomIntervalSpectralForest(
**self.rise_params,
random_state=self.random_state,
),
X=X,
y=y,
cv=cv_size,
n_jobs=self.n_jobs,
)
self.rise_weight = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"RISE train estimate ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("RISE weight = " + str(self.rise_weight)) # noqa
self.cboss = ContractableBOSS(**self.cboss_params,
random_state=self.random_state,
n_jobs=self.n_jobs)
self.cboss.fit(X, y)
train_probs = self.cboss._get_train_probs(X)
train_preds = self.cboss.classes_[np.argmax(train_probs, axis=1)]
self.cboss_weight = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"cBOSS (estimate included) ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("cBOSS weight = " + str(self.cboss_weight)) # noqa
self._is_fitted = True
return self
def predict(self, X):
"""Make predictions for all cases in X.
Parameters
----------
X : The testing input samples of shape [n_instances,1].
Returns
-------
output : numpy array of shape = [n_instances]
"""
rng = check_random_state(self.random_state)
return np.array([
self.classes_[int(rng.choice(np.flatnonzero(prob == prob.max())))]
for prob in self.predict_proba(X)
])
def predict_proba(self, X):
"""Make class probability estimates on each case in X.
Parameters
----------
X - pandas dataframe of testing data of shape [n_instances,1].
Returns
-------
output : numpy array of shape =
[n_instances, num_classes] of probabilities
"""
self.check_is_fitted()
X = check_X(X, enforce_univariate=True)
dists = np.zeros((X.shape[0], self.n_classes))
dists = np.add(
dists,
self.stc.predict_proba(X) *
(np.ones(self.n_classes) * self.stc_weight),
)
dists = np.add(
dists,
self.tsf.predict_proba(X) *
(np.ones(self.n_classes) * self.tsf_weight),
)
dists = np.add(
dists,
self.rise.predict_proba(X) *
(np.ones(self.n_classes) * self.rise_weight),
)
dists = np.add(
dists,
self.cboss.predict_proba(X) *
(np.ones(self.n_classes) * self.cboss_weight),
)
return dists / dists.sum(axis=1, keepdims=True)
def fit(self, X, y):
"""Fit a HIVE-COTEv1.0 classifier.
Parameters
----------
X : nested pandas DataFrame of shape [n_instances, 1]
Nested dataframe with univariate time-series in cells.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X, y = check_X_y(X, y, enforce_univariate=True)
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
cv_size = 10
_, counts = np.unique(y, return_counts=True)
min_class = np.min(counts)
if min_class < cv_size:
cv_size = min_class
self.stc = ShapeletTransformClassifier(
**self.stc_params,
random_state=self.random_state,
)
self.stc.fit(X, y)
if self.verbose > 0:
print("STC ", datetime.now().strftime("%H:%M:%S %d/%m/%Y")) # noqa
train_preds = cross_val_predict(
ShapeletTransformClassifier(
**self.stc_params,
random_state=self.random_state,
),
X=X,
y=y,
cv=cv_size,
n_jobs=self.n_jobs,
)
self.stc_weight = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"STC train estimate ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("STC weight = " + str(self.stc_weight)) # noqa
self.tsf = TimeSeriesForestClassifier(
**self.tsf_params,
random_state=self.random_state,
n_jobs=self.n_jobs,
)
self.tsf.fit(X, y)
if self.verbose > 0:
print("TSF ", datetime.now().strftime("%H:%M:%S %d/%m/%Y")) # noqa
train_preds = cross_val_predict(
TimeSeriesForestClassifier(**self.tsf_params,
random_state=self.random_state),
X=X,
y=y,
cv=cv_size,
n_jobs=self.n_jobs,
)
self.tsf_weight = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"TSF train estimate ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("TSF weight = " + str(self.tsf_weight)) # noqa
self.rise = RandomIntervalSpectralForest(
**self.rise_params,
random_state=self.random_state,
n_jobs=self.n_jobs,
)
self.rise.fit(X, y)
if self.verbose > 0:
print("RISE ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y")) # noqa
train_preds = cross_val_predict(
RandomIntervalSpectralForest(
**self.rise_params,
random_state=self.random_state,
),
X=X,
y=y,
cv=cv_size,
n_jobs=self.n_jobs,
)
self.rise_weight = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"RISE train estimate ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("RISE weight = " + str(self.rise_weight)) # noqa
self.cboss = ContractableBOSS(**self.cboss_params,
random_state=self.random_state,
n_jobs=self.n_jobs)
self.cboss.fit(X, y)
train_probs = self.cboss._get_train_probs(X)
train_preds = self.cboss.classes_[np.argmax(train_probs, axis=1)]
self.cboss_weight = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"cBOSS (estimate included) ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("cBOSS weight = " + str(self.cboss_weight)) # noqa
self._is_fitted = True
return self
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")
import numpy as np import sktime sktime.datatypes.check_is_mtype(obj, mtype) #@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ # time series forest classifier from sktime.classification.interval_based import TimeSeriesForestClassifier TimeSeriesForestClassifier(n_estimators=200, min_interval=3, n_jobs=1, random_state=None|0) # cannot handle multivariate series .fit(X, y, **kwargs) .predict(X, **kwargs) .predict_proba(X, **kwargs) # example: time_series = [1,2,3,4,5,6,7,8,9] x_train = [ [1,2,3], [2,3,4], [3,4,5], [4,5,6] ] y_train = [ 1, 1, 0, 0, ] model = TimeSeriesForestClassifier(n_estimators=5, min_interval=2) model.fit(np.array(x_train), np.array(y_train)) y_pred = model.predict(np.array(x_train)) print(y_pred) # [1,1,0,0] # examine input output structure: from sktime.datasets import load_unit_test 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) x = [ [list(j) for j in i] for i in X_train.to_numpy()] y = list(y_train)
_print_array(
"RandomIntervalSpectralEnsemble - UnitTest",
_reproduce_classification_unit_test(
RandomIntervalSpectralEnsemble(n_estimators=10, random_state=0)
),
)
_print_array(
"SupervisedTimeSeriesForest - UnitTest",
_reproduce_classification_unit_test(
SupervisedTimeSeriesForest(n_estimators=10, random_state=0)
),
)
_print_array(
"TimeSeriesForestClassifier - UnitTest",
_reproduce_classification_unit_test(
TimeSeriesForestClassifier(n_estimators=10, random_state=0)
),
)
_print_array(
"Arsenal - UnitTest",
_reproduce_classification_unit_test(
Arsenal(num_kernels=200, n_estimators=5, random_state=0)
),
)
_print_array(
"Arsenal - BasicMotions",
_reproduce_classification_basic_motions(
Arsenal(num_kernels=200, n_estimators=5, random_state=0)
),
)
_print_array(
class HIVECOTEV1(BaseClassifier):
"""Hierarchical Vote Collective of Transformation-based Ensembles (HIVE-COTE) V1.
An ensemble of the STC, TSF, RISE and cBOSS classifiers from different feature
representations using the CAWPE structure as described in [1]_.
Parameters
----------
stc_params : dict or None, default=None
Parameters for the ShapeletTransformClassifier module. If None, uses the
default parameters with a 2 hour transform contract.
tsf_params : dict or None, default=None
Parameters for the TimeSeriesForestClassifier module. If None, uses the default
parameters with n_estimators set to 500.
rise_params : dict or None, default=None
Parameters for the RandomIntervalSpectralForest module. If None, uses the
default parameters with n_estimators set to 500.
cboss_params : dict or None, default=None
Parameters for the ContractableBOSS module. If None, uses the default
parameters.
verbose : int, default=0
Level of output printed to the console (for information only).
n_jobs : int, default=1
The number of jobs to run in parallel for both `fit` and `predict`.
``-1`` means using all processors.
random_state : int or None, default=None
Seed for random number generation.
Attributes
----------
n_classes_ : int
The number of classes.
classes_ : list
The unique class labels.
stc_weight_ : float
The weight for STC probabilities.
tsf_weight_ : float
The weight for TSF probabilities.
rise_weight_ : float
The weight for RISE probabilities.
cboss_weight_ : float
The weight for cBOSS probabilities.
See Also
--------
HIVECOTEV2, ShapeletTransformClassifier, TimeSeriesForestClassifier,
RandomIntervalSpectralForest, ContractableBOSS
Notes
-----
For the Java version, see
`https://github.com/uea-machine-learning/tsml/blob/master/src/main/java/
tsml/classifiers/hybrids/HIVE_COTE.java`_.
References
----------
.. [1] Anthony Bagnall, Michael Flynn, James Large, Jason Lines and
Matthew Middlehurst. "On the usage and performance of the Hierarchical Vote
Collective of Transformation-based Ensembles version 1.0 (hive-cote v1.0)"
International Workshop on Advanced Analytics and Learning on Temporal Data 2020
Examples
--------
>>> from sktime.classification.hybrid import HIVECOTEV1
>>> from sktime.contrib.vector_classifiers._rotation_forest import RotationForest
>>> from sktime.datasets import load_unit_test
>>> 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)
>>> clf = HIVECOTEV1(
... 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},
... )
>>> clf.fit(X_train, y_train)
HIVECOTEV1(...)
>>> y_pred = clf.predict(X_test)
"""
_tags = {
"capability:multithreading": True,
}
def __init__(
self,
stc_params=None,
tsf_params=None,
rise_params=None,
cboss_params=None,
verbose=0,
n_jobs=1,
random_state=None,
):
self.stc_params = stc_params
self.tsf_params = tsf_params
self.rise_params = rise_params
self.cboss_params = cboss_params
self.verbose = verbose
self.n_jobs = n_jobs
self.random_state = random_state
self.stc_weight_ = 0
self.tsf_weight_ = 0
self.rise_weight_ = 0
self.cboss_weight_ = 0
self._stc_params = stc_params
self._tsf_params = tsf_params
self._rise_params = rise_params
self._cboss_params = cboss_params
self._stc = None
self._tsf = None
self._rise = None
self._cboss = None
super(HIVECOTEV1, self).__init__()
def _fit(self, X, y):
"""Fit HIVE-COTE 1.0 to training data.
Parameters
----------
X : 3D np.array of shape = [n_instances, n_dimensions, series_length]
The training data.
y : array-like, shape = [n_instances]
The class labels.
Returns
-------
self :
Reference to self.
Notes
-----
Changes state by creating a fitted model that updates attributes
ending in "_" and sets is_fitted flag to True.
"""
# Default values from HC1 paper
if self.stc_params is None:
self._stc_params = {"transform_limit_in_minutes": 120}
if self.tsf_params is None:
self._tsf_params = {"n_estimators": 500}
if self.rise_params is None:
self._rise_params = {"n_estimators": 500}
if self.cboss_params is None:
self._cboss_params = {}
# Cross-validation size for TSF and RISE
cv_size = 10
_, counts = np.unique(y, return_counts=True)
min_class = np.min(counts)
if min_class < cv_size:
cv_size = min_class
# Build STC
self._stc = ShapeletTransformClassifier(
**self._stc_params,
save_transformed_data=True,
random_state=self.random_state,
n_jobs=self._threads_to_use,
)
self._stc.fit(X, y)
if self.verbose > 0:
print("STC ", datetime.now().strftime("%H:%M:%S %d/%m/%Y")) # noqa
# Find STC weight using train set estimate
train_probs = self._stc._get_train_probs(X, y)
train_preds = self._stc.classes_[np.argmax(train_probs, axis=1)]
self.stc_weight_ = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"STC train estimate ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("STC weight = " + str(self.stc_weight_)) # noqa
# Build TSF
self._tsf = TimeSeriesForestClassifier(
**self._tsf_params,
random_state=self.random_state,
n_jobs=self._threads_to_use,
)
self._tsf.fit(X, y)
if self.verbose > 0:
print("TSF ", datetime.now().strftime("%H:%M:%S %d/%m/%Y")) # noqa
# Find TSF weight using train set estimate found through CV
train_preds = cross_val_predict(
TimeSeriesForestClassifier(**self._tsf_params,
random_state=self.random_state),
X=X,
y=y,
cv=cv_size,
n_jobs=self._threads_to_use,
)
self.tsf_weight_ = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"TSF train estimate ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("TSF weight = " + str(self.tsf_weight_)) # noqa
# Build RISE
self._rise = RandomIntervalSpectralEnsemble(
**self._rise_params,
random_state=self.random_state,
n_jobs=self._threads_to_use,
)
self._rise.fit(X, y)
if self.verbose > 0:
print("RISE ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y")) # noqa
# Find RISE weight using train set estimate found through CV
train_preds = cross_val_predict(
RandomIntervalSpectralEnsemble(
**self._rise_params,
random_state=self.random_state,
),
X=X,
y=y,
cv=cv_size,
n_jobs=self._threads_to_use,
)
self.rise_weight_ = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"RISE train estimate ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("RISE weight = " + str(self.rise_weight_)) # noqa
# Build cBOSS
self._cboss = ContractableBOSS(
**self._cboss_params,
random_state=self.random_state,
n_jobs=self._threads_to_use,
)
self._cboss.fit(X, y)
# Find cBOSS weight using train set estimate
train_probs = self._cboss._get_train_probs(X, y)
train_preds = self._cboss.classes_[np.argmax(train_probs, axis=1)]
self.cboss_weight_ = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"cBOSS (estimate included)",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("cBOSS weight = " + str(self.cboss_weight_)) # noqa
return self
def _predict(self, X):
"""Predicts labels for sequences in X.
Parameters
----------
X : 3D np.array of shape = [n_instances, n_dimensions, series_length]
The data to make predictions for.
Returns
-------
y : array-like, shape = [n_instances]
Predicted class labels.
"""
rng = check_random_state(self.random_state)
return np.array([
self.classes_[int(rng.choice(np.flatnonzero(prob == prob.max())))]
for prob in self.predict_proba(X)
])
def _predict_proba(self, X):
"""Predicts labels probabilities for sequences in X.
Parameters
----------
X : 3D np.array of shape = [n_instances, n_dimensions, series_length]
The data to make predict probabilities for.
Returns
-------
y : array-like, shape = [n_instances, n_classes_]
Predicted probabilities using the ordering in classes_.
"""
dists = np.zeros((X.shape[0], self.n_classes_))
# Call predict proba on each classifier, multiply the probabilities by the
# classifiers weight then add them to the current HC1 probabilities
dists = np.add(
dists,
self._stc.predict_proba(X) *
(np.ones(self.n_classes_) * self.stc_weight_),
)
dists = np.add(
dists,
self._tsf.predict_proba(X) *
(np.ones(self.n_classes_) * self.tsf_weight_),
)
dists = np.add(
dists,
self._rise.predict_proba(X) *
(np.ones(self.n_classes_) * self.rise_weight_),
)
dists = np.add(
dists,
self._cboss.predict_proba(X) *
(np.ones(self.n_classes_) * self.cboss_weight_),
)
# Make each instances probability array sum to 1 and return
return dists / dists.sum(axis=1, keepdims=True)
def _fit(self, X, y):
"""Fit HIVE-COTE 1.0 to training data.
Parameters
----------
X : 3D np.array of shape = [n_instances, n_dimensions, series_length]
The training data.
y : array-like, shape = [n_instances]
The class labels.
Returns
-------
self :
Reference to self.
Notes
-----
Changes state by creating a fitted model that updates attributes
ending in "_" and sets is_fitted flag to True.
"""
# Default values from HC1 paper
if self.stc_params is None:
self._stc_params = {"transform_limit_in_minutes": 120}
if self.tsf_params is None:
self._tsf_params = {"n_estimators": 500}
if self.rise_params is None:
self._rise_params = {"n_estimators": 500}
if self.cboss_params is None:
self._cboss_params = {}
# Cross-validation size for TSF and RISE
cv_size = 10
_, counts = np.unique(y, return_counts=True)
min_class = np.min(counts)
if min_class < cv_size:
cv_size = min_class
# Build STC
self._stc = ShapeletTransformClassifier(
**self._stc_params,
save_transformed_data=True,
random_state=self.random_state,
n_jobs=self._threads_to_use,
)
self._stc.fit(X, y)
if self.verbose > 0:
print("STC ", datetime.now().strftime("%H:%M:%S %d/%m/%Y")) # noqa
# Find STC weight using train set estimate
train_probs = self._stc._get_train_probs(X, y)
train_preds = self._stc.classes_[np.argmax(train_probs, axis=1)]
self.stc_weight_ = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"STC train estimate ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("STC weight = " + str(self.stc_weight_)) # noqa
# Build TSF
self._tsf = TimeSeriesForestClassifier(
**self._tsf_params,
random_state=self.random_state,
n_jobs=self._threads_to_use,
)
self._tsf.fit(X, y)
if self.verbose > 0:
print("TSF ", datetime.now().strftime("%H:%M:%S %d/%m/%Y")) # noqa
# Find TSF weight using train set estimate found through CV
train_preds = cross_val_predict(
TimeSeriesForestClassifier(**self._tsf_params,
random_state=self.random_state),
X=X,
y=y,
cv=cv_size,
n_jobs=self._threads_to_use,
)
self.tsf_weight_ = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"TSF train estimate ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("TSF weight = " + str(self.tsf_weight_)) # noqa
# Build RISE
self._rise = RandomIntervalSpectralEnsemble(
**self._rise_params,
random_state=self.random_state,
n_jobs=self._threads_to_use,
)
self._rise.fit(X, y)
if self.verbose > 0:
print("RISE ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y")) # noqa
# Find RISE weight using train set estimate found through CV
train_preds = cross_val_predict(
RandomIntervalSpectralEnsemble(
**self._rise_params,
random_state=self.random_state,
),
X=X,
y=y,
cv=cv_size,
n_jobs=self._threads_to_use,
)
self.rise_weight_ = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"RISE train estimate ",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("RISE weight = " + str(self.rise_weight_)) # noqa
# Build cBOSS
self._cboss = ContractableBOSS(
**self._cboss_params,
random_state=self.random_state,
n_jobs=self._threads_to_use,
)
self._cboss.fit(X, y)
# Find cBOSS weight using train set estimate
train_probs = self._cboss._get_train_probs(X, y)
train_preds = self._cboss.classes_[np.argmax(train_probs, axis=1)]
self.cboss_weight_ = accuracy_score(y, train_preds)**4
if self.verbose > 0:
print( # noqa
"cBOSS (estimate included)",
datetime.now().strftime("%H:%M:%S %d/%m/%Y"),
)
print("cBOSS weight = " + str(self.cboss_weight_)) # noqa
return self