def Run(self, data_container, store_folder='', store_key=''):
temp_frame = data_container.GetFrame().select_dtypes(include=None, exclude=['object'])
new_data_container = DataContainer()
new_data_container.SetFrame(temp_frame)
if store_folder and os.path.isdir(store_folder):
feature_store_path = os.path.join(store_folder, 'numeric_feature.csv')
featureinfo_store_path = os.path.join(store_folder, 'feature_select_info.csv')
new_data_container.Save(feature_store_path)
SaveSelectInfo(new_data_container.GetFeatureName(), featureinfo_store_path, is_merge=False)
return new_data_container
return output
################################################################
if __name__ == '__main__':
import os
print(os.getcwd())
from FAE.DataContainer.DataContainer import DataContainer
data_container = DataContainer()
print(os.path.abspath(r'..\..\Example\numeric_feature.csv'))
data_container.Load(r'..\..\Example\numeric_feature.csv')
# data_container.UsualNormalize()
print(data_container.GetArray().shape)
print(data_container.GetFeatureName())
fs = FeatureSelectBySubName(['shape', 'ADC'])
output = fs.Run(data_container)
print(output.GetFeatureName())
# fs1 = RemoveNonNumericFeature()
# fs1.SetDataContainer(data_container)
# non_number_data_container = fs1.Run()
#
# fs2 = FeatureSelectByANOVA(10)
# fs2.SetDataContainer(non_number_data_container)
# output = fs2.Run()
# feature_selector_list = [RemoveNonNumericFeature(), RemoveCosSimilarityFeatures(), FeatureSelectByANOVA(5)]
class PrepareConnection(QWidget, Ui_Prepare):
def __init__(self, parent=None):
super(PrepareConnection, self).__init__(parent)
self.setupUi(self)
self.data_container = DataContainer()
self.buttonLoad.clicked.connect(self.LoadData)
self.buttonRemove.clicked.connect(self.RemoveNonValidValue)
self.checkSeparate.clicked.connect(self.SetSeparateStatus)
self.spinBoxSeparate.setEnabled(False)
self.buttonSave.clicked.connect(self.CheckAndSave)
def UpdateTable(self):
if self.data_container.GetArray().size == 0:
return
self.tableFeature.setRowCount(len(self.data_container.GetCaseName()))
header_name = deepcopy(self.data_container.GetFeatureName())
header_name.insert(0, 'Label')
self.tableFeature.setColumnCount(len(header_name))
self.tableFeature.setHorizontalHeaderLabels(header_name)
self.tableFeature.setVerticalHeaderLabels(
list(map(str, self.data_container.GetCaseName())))
for row_index in range(len(self.data_container.GetCaseName())):
for col_index in range(len(header_name)):
if col_index == 0:
self.tableFeature.setItem(
row_index, col_index,
QTableWidgetItem(
str(self.data_container.GetLabel()[row_index])))
else:
self.tableFeature.setItem(
row_index, col_index,
QTableWidgetItem(
str(self.data_container.GetArray()[row_index,
col_index -
1])))
text = "The number of cases: {:d}\n".format(
len(self.data_container.GetCaseName()))
text += "The number of features: {:d}\n".format(
len(self.data_container.GetFeatureName()))
if len(np.unique(self.data_container.GetLabel())) == 2:
positive_number = len(
np.where(self.data_container.GetLabel() == np.max(
self.data_container.GetLabel()))[0])
negative_number = len(
self.data_container.GetLabel()) - positive_number
assert (positive_number + negative_number == len(
self.data_container.GetLabel()))
text += "The number of positive samples: {:d}\n".format(
positive_number)
text += "The number of negative samples: {:d}\n".format(
negative_number)
self.textInformation.setText(text)
def LoadData(self):
dlg = QFileDialog()
file_name, _ = dlg.getOpenFileName(self,
'Open SCV file',
filter="csv files (*.csv)")
try:
self.data_container.Load(file_name)
except:
print('Error')
self.UpdateTable()
def RemoveNonValidValue(self):
if self.radioRemoveNonvalidCases.isChecked():
self.data_container.RemoveUneffectiveCases()
elif self.radioRemoveNonvalidFeatures.isChecked():
self.data_container.RemoveUneffectiveFeatures()
self.UpdateTable()
def SetSeparateStatus(self):
if self.checkSeparate.isChecked():
self.spinBoxSeparate.setEnabled(True)
else:
self.spinBoxSeparate.setEnabled(False)
def CheckAndSave(self):
if self.data_container.IsEmpty():
QMessageBox.warning(self, "Warning", "There is no data",
QMessageBox.Ok)
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)
elif self.checkSeparate.isChecked():
percentage_testing_data = self.spinBoxSeparate.value()
folder_name = QFileDialog.getExistingDirectory(self, "Save data")
if folder_name != '':
data_seperate = DataSeparate.DataSeparate(
percentage_testing_data)
data_seperate.Run(self.data_container, folder_name)
else:
file_name, _ = QFileDialog.getSaveFileName(
self, "Save data", filter="csv files (*.csv)")
if file_name != '':
self.data_container.Save(file_name)
class PrepareConnection(QWidget, Ui_Prepare):
def __init__(self, parent=None):
super(PrepareConnection, self).__init__(parent)
self.setupUi(self)
self.data_container = DataContainer()
self.buttonLoad.clicked.connect(self.LoadData)
self.buttonRemove.clicked.connect(self.RemoveNonValidValue)
self.loadTestingReference.clicked.connect(
self.LoadTestingReferenceDataContainer)
self.clearTestingReference.clicked.connect(
self.ClearTestingReferenceDataContainer)
self.__testing_ref_data_container = DataContainer()
self.checkSeparate.clicked.connect(self.SetSeparateStatus)
self.spinBoxSeparate.setEnabled(False)
self.logger = eclog(os.path.split(__file__)[-1]).GetLogger()
self.loadTestingReference.setEnabled(False)
self.clearTestingReference.setEnabled(False)
self.buttonSave.clicked.connect(self.CheckAndSave)
def UpdateTable(self):
if self.data_container.GetArray().size == 0:
return
self.tableFeature.setRowCount(len(self.data_container.GetCaseName()))
header_name = deepcopy(self.data_container.GetFeatureName())
header_name.insert(0, 'Label')
self.tableFeature.setColumnCount(len(header_name))
self.tableFeature.setHorizontalHeaderLabels(header_name)
self.tableFeature.setVerticalHeaderLabels(
list(map(str, self.data_container.GetCaseName())))
for row_index in range(len(self.data_container.GetCaseName())):
for col_index in range(len(header_name)):
if col_index == 0:
self.tableFeature.setItem(
row_index, col_index,
QTableWidgetItem(
str(self.data_container.GetLabel()[row_index])))
else:
self.tableFeature.setItem(
row_index, col_index,
QTableWidgetItem(
str(self.data_container.GetArray()[row_index,
col_index -
1])))
text = "The number of cases: {:d}\n".format(
len(self.data_container.GetCaseName()))
text += "The number of features: {:d}\n".format(
len(self.data_container.GetFeatureName()))
if len(np.unique(self.data_container.GetLabel())) == 2:
positive_number = len(
np.where(self.data_container.GetLabel() == np.max(
self.data_container.GetLabel()))[0])
negative_number = len(
self.data_container.GetLabel()) - positive_number
assert (positive_number + negative_number == len(
self.data_container.GetLabel()))
text += "The number of positive samples: {:d}\n".format(
positive_number)
text += "The number of negative samples: {:d}\n".format(
negative_number)
self.textInformation.setText(text)
def LoadData(self):
dlg = QFileDialog()
file_name, _ = dlg.getOpenFileName(self,
'Open SCV file',
filter="csv files (*.csv)")
try:
self.data_container.Load(file_name)
self.logger.info('Open the file ' + file_name + ' Succeed.')
except OSError as reason:
self.logger.log('Open SCV file Error, The reason is ' +
str(reason))
QMessageBox.about(self, 'Load data Error', reason.__str__())
print('Error！' + str(reason))
except ValueError:
self.logger.error('Open SCV file ' + file_name +
' Failed. because of value error.')
QMessageBox.information(self, 'Error',
'The selected data file mismatch.')
self.UpdateTable()
self.buttonRemove.setEnabled(True)
self.buttonSave.setEnabled(True)
def LoadTestingReferenceDataContainer(self):
dlg = QFileDialog()
file_name, _ = dlg.getOpenFileName(self,
'Open SCV file',
filter="csv files (*.csv)")
try:
self.__testing_ref_data_container.Load(file_name)
self.loadTestingReference.setEnabled(False)
self.clearTestingReference.setEnabled(True)
self.spinBoxSeparate.setEnabled(False)
except OSError as reason:
self.logger.log('Load Testing Reference Error: ' + str(reason))
print('Error！' + str(reason))
except ValueError:
self.logger.error('Open SCV file ' + file_name +
' Failed. because of value error.')
QMessageBox.information(self, 'Error',
'The selected data file mismatch.')
def ClearTestingReferenceDataContainer(self):
del self.__testing_ref_data_container
self.__testing_ref_data_container = DataContainer()
self.loadTestingReference.setEnabled(True)
self.clearTestingReference.setEnabled(False)
self.spinBoxSeparate.setEnabled(False)
def RemoveNonValidValue(self):
if self.radioRemoveNonvalidCases.isChecked():
self.data_container.RemoveUneffectiveCases()
elif self.radioRemoveNonvalidFeatures.isChecked():
self.data_container.RemoveUneffectiveFeatures()
self.UpdateTable()
def SetSeparateStatus(self):
if self.checkSeparate.isChecked():
self.spinBoxSeparate.setEnabled(True)
self.loadTestingReference.setEnabled(True)
self.clearTestingReference.setEnabled(False)
else:
self.spinBoxSeparate.setEnabled(False)
self.loadTestingReference.setEnabled(False)
self.clearTestingReference.setEnabled(False)
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)
vif_dict[exog] = vif
# calculate tolerance
tolerance = 1 - r_squared
tolerance_dict[exog] = tolerance
# return VIF DataFrame
df_vif = pd.DataFrame({'VIF': vif_dict, 'Tolerance': tolerance_dict})
return df_vif
if __name__ == '__main__':
data_path = r'..\..\Demo\train_numeric_feature.csv'
from FAE.DataContainer.DataContainer import DataContainer
from FAE.FeatureAnalysis.Normalizer import NormalizerZeroCenter
pca = DimensionReductionByPCA()
dc = DataContainer()
dc.Load(data_path)
dc = NormalizerZeroCenter.Run(dc)
# dc = pca.Run(dc)
df = pd.DataFrame(dc.GetArray(),
index=dc.GetCaseName(),
columns=dc.GetFeatureName())
dr = DimensionReductionByVIF()
new_df = dr.CalculateVIF(df)
print(dc.GetArray().shape, new_df.shape)
