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")
# 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) # multivariate workaround (chain 3rd dim into flat 2nd) time_series = [ [1,9], [2,8], [3,7], [4,6], [5,5], [6,4], [7,3], [8,2], [9,1] ] x_train_2d = [ [1,9,2,8,3,7], [2,8,3,7,4,6], [3,7,4,6,5,5], [4,6,5,5,6,4] ] # instead of: x_train_3d = [ [[1,9],[2,8],[3,7]], [[2,8],[3,7],[4,6]], [[3,7],[4,6],[5,5]], ... ] #@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@