print(os.getcwd())
column_list = [
'sample_number', 'positive_number', 'negative_number', 'auc',
'auc 95% CIs', 'accuracy', 'feature_number', 'Yorden Index',
'accuracy', 'sensitivity', 'specificity', 'positive predictive value',
'negative predictive value'
]
df = pd.DataFrame(columns=column_list)
# Set Feature Selector List
feature_selector_list = []
feature_selector_list.append(
FeatureSelectPipeline([
RemoveSameFeatures(),
RemoveCosSimilarityFeatures(),
FeatureSelectByANOVA()
]))
feature_selector_list.append(
FeatureSelectPipeline([
RemoveSameFeatures(),
RemoveCosSimilarityFeatures(),
FeatureSelectByRelief()
]))
feature_selector_list.append(
FeatureSelectPipeline([
RemoveSameFeatures(),
RemoveCosSimilarityFeatures(),
FeatureSelectByRFE()
]))
def CheckAndSave(self):
if self.data_container.IsEmpty():
QMessageBox.warning(self, "Warning", "There is no data",
QMessageBox.Ok)
elif not self.data_container.IsBinaryLabel():
QMessageBox.warning(self, "Warning", "There are not 2 Labels",
QMessageBox.Ok)
non_valid_number_Index = self.data_container.FindNonValidLabelIndex(
)
old_edit_triggers = self.tableFeature.editTriggers()
self.tableFeature.setEditTriggers(QAbstractItemView.CurrentChanged)
self.tableFeature.setCurrentCell(non_valid_number_Index, 0)
self.tableFeature.setEditTriggers(old_edit_triggers)
elif self.data_container.HasNonValidNumber():
QMessageBox.warning(self, "Warning", "There are nan items",
QMessageBox.Ok)
non_valid_number_Index = self.data_container.FindNonValidNumberIndex(
)
old_edit_triggers = self.tableFeature.editTriggers()
self.tableFeature.setEditTriggers(QAbstractItemView.CurrentChanged)
self.tableFeature.setCurrentCell(non_valid_number_Index[0],
non_valid_number_Index[1] + 1)
self.tableFeature.setEditTriggers(old_edit_triggers)
else:
remove_features_with_same_value = RemoveSameFeatures()
self.data_container = remove_features_with_same_value.Run(
self.data_container)
data_balance = DataBalance()
if self.radioDownSampling.isChecked():
data_balance = DownSampling()
elif self.radioUpSampling.isChecked():
data_balance = UpSampling()
elif self.radioSmote.isChecked():
data_balance = SmoteSampling()
if self.checkSeparate.isChecked():
folder_name = QFileDialog.getExistingDirectory(
self, "Save data")
if folder_name != '':
data_separate = DataSeparate.DataSeparate()
try:
if self.__testing_ref_data_container.IsEmpty():
testing_data_percentage = self.spinBoxSeparate.value(
)
training_data_container, _, = data_separate.RunByTestingPercentage(
self.data_container, testing_data_percentage,
folder_name)
else:
training_data_container, _, = data_separate.RunByTestingReference(
self.data_container,
self.__testing_ref_data_container, folder_name)
if training_data_container.IsEmpty():
QMessageBox.information(
self, 'Error',
'The testing data does not mismatch, please check the testing data '
'really exists in current data')
return None
data_balance.Run(training_data_container,
store_path=folder_name)
except Exception as e:
content = 'PrepareConnection, splitting failed: '
self.logger.error('{}{}'.format(content, str(e)))
QMessageBox.about(self, content, e.__str__())
else:
file_name, _ = QFileDialog.getSaveFileName(
self, "Save data", filter="csv files (*.csv)")
if file_name != '':
data_balance.Run(self.data_container, store_path=file_name)
def CheckAndSave(self):
if self.data_container.IsEmpty():
QMessageBox.warning(self, "Warning", "There is no data",
QMessageBox.Ok)
elif not self.data_container.IsBinaryLabel():
QMessageBox.warning(self, "Warning", "There are not 2 Labels",
QMessageBox.Ok)
non_valid_number_index = self.data_container.FindInvalidLabelIndex(
)
old_edit_triggers = self.tableFeature.editTriggers()
self.tableFeature.setEditTriggers(QAbstractItemView.CurrentChanged)
self.tableFeature.setCurrentCell(non_valid_number_index, 0)
self.tableFeature.setEditTriggers(old_edit_triggers)
elif self.data_container.HasInvalidNumber():
QMessageBox.warning(self, "Warning", "There are nan items",
QMessageBox.Ok)
non_valid_number_index = self.data_container.FindInvalidNumberIndex(
)
old_edit_triggers = self.tableFeature.editTriggers()
self.tableFeature.setEditTriggers(QAbstractItemView.CurrentChanged)
self.tableFeature.setCurrentCell(non_valid_number_index[0],
non_valid_number_index[1] + 1)
self.tableFeature.setEditTriggers(old_edit_triggers)
else:
remove_features_with_same_value = RemoveSameFeatures()
self.data_container = remove_features_with_same_value.Run(
self.data_container)
if self.radioSplitRandom.isChecked(
) or self.radioSplitRef.isChecked():
folder_name = QFileDialog.getExistingDirectory(
self, "Save data")
if folder_name != '':
data_separate = DataSeparate.DataSeparate()
try:
if self.__testing_ref_data_container.IsEmpty():
testing_data_percentage = self.spinBoxSeparate.value(
)
if self.__clinical_ref.size == 0:
training_data_container, _, = \
data_separate.RunByTestingPercentage(self.data_container,
testing_data_percentage,
store_folder=folder_name)
else:
training_data_container, _, = \
data_separate.RunByTestingPercentage(self.data_container,
testing_data_percentage,
clinic_df=self.__clinical_ref,
store_folder=folder_name)
else:
training_data_container, _, = \
data_separate.RunByTestingReference(self.data_container,
self.__testing_ref_data_container,
folder_name)
if training_data_container.IsEmpty():
QMessageBox.information(
self, 'Error',
'The testing data does not mismatch, please check the testing data '
'really exists in current data')
return None
os.system("explorer.exe {:s}".format(
os.path.normpath(folder_name)))
except Exception as e:
content = 'PrepareConnection, splitting failed: '
eclog(self._filename).GetLogger().error(
'Split Error: ' + e.__str__())
QMessageBox.about(self, content, e.__str__())
else:
file_name, _ = QFileDialog.getSaveFileName(
self, "Save data", filter="csv files (*.csv)")
if file_name:
self.data_container.Save(file_name)