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
)
stsf = SupervisedTimeSeriesForest(random_state=42, n_estimators=20)
stsf.fit(X_train, y_train)
actual = stsf.predict_proba(X_test)
np.testing.assert_array_equal(actual, expected)
def test_stsf_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 STSF
stsf = SupervisedTimeSeriesForest(random_state=0, n_estimators=20)
stsf.fit(X_train, y_train)
score = stsf.score(X_test.iloc[indices], y_test[indices])
assert score >= 0.92
def test_stsf_on_gunpoint():
"""Test of STSF on gun point."""
# 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)
stsf = SupervisedTimeSeriesForest(n_estimators=20, random_state=0)
stsf.fit(X_train.iloc[indices], y_train[indices])
# assert probabilities are the same
probas = stsf.predict_proba(X_test.iloc[indices])
testing.assert_array_equal(probas, stsf_gunpoint_probas)
def test_stsf_on_unit_test_data():
"""Test of SupervisedTimeSeriesForest 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 STSF
stsf = SupervisedTimeSeriesForest(n_estimators=10, random_state=0)
stsf.fit(X_train, y_train)
# assert probabilities are the same
probas = stsf.predict_proba(X_test.iloc[indices])
testing.assert_array_equal(probas, stsf_unit_test_probas)
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")
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")
_reproduce_classification_unit_test(DrCIF(n_estimators=10, random_state=0)),
)
_print_array(
"DrCIF - BasicMotions",
_reproduce_classification_basic_motions(DrCIF(n_estimators=10, random_state=0)),
)
_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(