def DrawFeatureRelationshipAccordingToCsvFile(file_path,
selected_feature_name_list,
label_name_list,
store_path=''):
'''
Help draw the feature relationship among different features according to the path of the data container.
:param file_path: the file path of the csv file
:param selected_feature_name_list: the features that would be drawn
:param label_name_list: the name of the label. e.g. ['non-cnacer', 'cancer']
:param store_path: The store path, supporting jpg and eps format.
:return:
'''
data_container = DataContainer()
data_container.Load(file_path)
data_container.UsualNormalize()
data, label, feature_name, case_name = data_container.GetData()
if len(selected_feature_name_list) > 3 or len(
selected_feature_name_list) < 1:
print(
"Please check the length of the feature list. It can only show the relationship of the 1, 2, or 3 features"
)
try:
index = [feature_name.index(t) for t in selected_feature_name_list]
except:
print('The selected feature is not in the data container.')
return
result_data = []
for sub_index in index:
result_data.append(data[:, sub_index])
DrawValueRelationship(result_data, selected_feature_name_list, label,
label_name_list, store_path)
def GenerateDescription():
training_data_container = DataContainer()
training_data_container.Load(r'..\..\Example\numeric_feature.csv')
one_pipeline = OnePipeline()
one_pipeline.LoadPipeline(r'C:\MyCode\FAEGitHub\FAE\Example\report_temp\NormUnit_Cos_ANOVA_5_SVM\pipeline_info.csv')
description = Description()
description.Run(training_data_container, one_pipeline, r'..\..\Example\report_temp', r'..\..\Example\report')
def TestNewData(NewDataCsv, model_folder, result_save_path=''):
'''
:param NewDataCsv: New radiomics feature matrix csv file path
:param model_folder:The trained model path
:return:classification result
'''
train_info = LoadTrainInfo(model_folder)
new_data_container = DataContainer()
#Normlization
new_data_container.Load(NewDataCsv)
# feature_selector = FeatureSelector()
# feature_selector.SelectFeatureByName(new_data_container, train_info['selected_features'], is_replace=True)
new_data_container = train_info['normalizer'].Transform(new_data_container)
# data_frame = new_data_container.GetFrame()
# data_frame = data_frame[train_info['selected_features']]
# new_data_container.SetFrame(data_frame)
# new_data_container.UpdateDataByFrame()
##Model
train_info['classifier'].SetDataContainer(new_data_container)
model = train_info['classifier'].GetModel()
predict = model.predict_proba(new_data_container.GetArray())[:, 1]
label = new_data_container.GetLabel()
case_name = new_data_container.GetCaseName()
test_result_info = [['CaseName', 'Pred', 'Label']]
for index in range(len(label)):
test_result_info.append(
[case_name[index], predict[index], label[index]])
metric = EstimateMetirc(predict, label)
info = {}
info.update(metric)
cv = CrossValidation()
print(metric)
print('\t')
if result_save_path:
cv.SaveResult(info, result_save_path)
np.save(os.path.join(result_save_path, 'test_predict.npy'), predict)
np.save(os.path.join(result_save_path, 'test_label.npy'), label)
with open(os.path.join(result_save_path, 'test_info.csv'),
'w',
newline='') as csvfile:
writer = csv.writer(csvfile)
writer.writerows(test_result_info)
return metric
feature_pvalue = self._EstimateDcFeaturePvalue(
train_dc, test_dc, feature_distribution_type)
if np.mean(list(feature_pvalue.values())) > mean_pvalue:
mean_pvalue = np.mean(list(feature_pvalue.values()))
output_train_dc, output_test_dc = train_dc, test_dc
output_pvalue = feature_pvalue
if output_folder is not None and os.path.isdir(output_folder):
output_train_dc.Save(os.path.join(output_folder, 'train.csv'))
output_test_dc.Save(os.path.join(output_folder, 'test.csv'))
pvalue_df = pd.DataFrame(output_pvalue, index=['P Value'])
distibute_df = pd.DataFrame(feature_distribution_type,
index=['Distribution'])
store_df = pd.concat((pvalue_df, distibute_df), axis=0)
store_df.to_csv(os.path.join(output_folder, 'split_info.csv'))
if __name__ == '__main__':
clinics = pd.read_csv(r'..\..\Demo\simulated_clinics.csv', index_col=0)
container = DataContainer()
container.Load(r'..\..\Demo\simulated_feature.csv')
separator = DataSeparate()
train, test = separator.RunByTestingPercentage(container,
0.3,
clinic_df=clinics)
print(train.GetArray().shape, test.GetArray().shape)
print(separator.clinic_split_result)
model_name)
self.total_metric[CV_TRAIN].to_csv(
os.path.join(store_folder, '{}_results.csv'.format(CV_TRAIN)))
self.total_metric[CV_VAL].to_csv(
os.path.join(store_folder, '{}_results.csv'.format(CV_VAL)))
if __name__ == '__main__':
manager = PipelinesManager()
index_dict = Index2Dict()
train = DataContainer()
test = DataContainer()
train.Load(r'C:\Users\yangs\Desktop\train_numeric_feature.csv')
test.Load(r'C:\Users\yangs\Desktop\test_numeric_feature.csv')
faps = PipelinesManager(
balancer=index_dict.GetInstantByIndex('UpSampling'),
normalizer_list=[index_dict.GetInstantByIndex('Mean')],
dimension_reduction_list=[index_dict.GetInstantByIndex('PCC')],
feature_selector_list=[index_dict.GetInstantByIndex('ANOVA')],
feature_selector_num_list=list(np.arange(1, 18)),
classifier_list=[index_dict.GetInstantByIndex('SVM')],
cross_validation=index_dict.GetInstantByIndex('5-Fold'))
# for total, num in faps.RunWithoutCV(train, store_folder=r'..\..\Demo\db2-1'):
# print(total, num)
for total, num, group in faps.RunWithCV(train,
store_folder=r'..\..\Demo\db1'):
input_data_container = output
return output
def SaveInfo(self, store_folder, all_features):
for fs in self.__selector_list:
fs.SaveInfo(store_folder, all_features)
def SaveDataContainer(self, data_container, store_folder, store_key):
for fs in self.__selector_list:
fs.SaveDataContainer(data_container, store_folder, store_key)
################################################################
if __name__ == '__main__':
from BC.DataContainer.DataContainer import DataContainer
from BC.FeatureAnalysis.Normalizer import NormalizerZeroCenter
from BC.FeatureAnalysis.DimensionReduction import DimensionReductionByPCC
dc = DataContainer()
pcc = DimensionReductionByPCC()
fs = FeatureSelectByKruskalWallis(selected_feature_number=5)
dc.Load(r'..\..\Demo\train_numeric_feature.csv')
dc = NormalizerZeroCenter.Run(dc)
dc = pcc.Run(dc)
print(dc.GetArray().shape)
dc = fs.Run(dc)
print(dc.GetArray().shape)
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 BC.DataContainer.DataContainer import DataContainer
from BC.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)
if output_folder is not None and os.path.isdir(output_folder):
output_train_dc.Save(os.path.join(output_folder, 'train.csv'))
output_test_dc.Save(os.path.join(output_folder, 'test.csv'))
p_value_df = pd.DataFrame(output_p_value, index=['P Value'])
distribute_df = pd.DataFrame(feature_distribution_type,
index=['Distribution'])
store_df = pd.concat((p_value_df, distribute_df), axis=0)
store_df.to_csv(os.path.join(output_folder, 'split_info.csv'))
if __name__ == '__main__':
# clinics = pd.read_csv(r'..\..\Demo\simulated_clinics.csv', index_col=0)
# container = DataContainer()
# container.Load(r'..\..\Demo\simulated_feature.csv')
#
# separator = DataSeparate()
# train, test = separator.RunByTestingPercentage(container, 0.3, clinic_df=clinics)
#
# print(train.GetArray().shape, test.GetArray().shape)
# print(separator.clinic_split_result)
cluster_split = DataSplitterByFeatureCluster()
container = DataContainer()
container.Load(r'.\all_feature.csv')
output_path = r'.\output'
clinical_path = r'.\clinical.csv'
cluster_split.VisualizePartsVariance(container, store_folder=output_path)
cluster_split.Run(container, output_path, clinical_feature=clinical_path)
cluster_split.VisualizeCluster(dimension='2d', store_folder=output_path)
cluster_split.VisualizeCluster(dimension='3d', store_folder=output_path)
class PrepareConnection(QWidget, Ui_Prepare):
close_signal = pyqtSignal(bool)
def __init__(self, parent=None):
super(PrepareConnection, self).__init__(parent)
self.setupUi(self)
self.data_container = DataContainer()
self._filename = os.path.split(__file__)[-1]
self.buttonLoad.clicked.connect(self.LoadData)
self.buttonRemoveAndExport.clicked.connect(self.RemoveInvalidValue)
self.__testing_ref_data_container = DataContainer()
self.__clinical_ref = pd.DataFrame()
self.radioSplitRandom.clicked.connect(self.ChangeSeparateMethod)
self.radioSplitRef.clicked.connect(self.ChangeSeparateMethod)
self.checkUseClinicRef.clicked.connect(
self.RandomSeparateButtonUpdates)
self.loadTestingReference.clicked.connect(
self.LoadTestingReferenceDataContainer)
self.clearTestingReference.clicked.connect(
self.ClearTestingReferenceDataContainer)
self.loadClinicRef.clicked.connect(self.LoadClinicalRef)
self.clearClinicRef.clicked.connect(self.ClearClinicalRef)
self.buttonSave.clicked.connect(self.CheckAndSave)
def closeEvent(self, QCloseEvent):
self.close_signal.emit(True)
QCloseEvent.accept()
def UpdateTable(self):
self.tableFeature.setRowCount(self.data_container.GetFrame().shape[0])
header_name = deepcopy(list(self.data_container.GetFrame().columns))
min_col = np.min([len(header_name), 100])
if min_col == 100:
header_name = header_name[:100]
header_name[-1] = '...'
self.tableFeature.setColumnCount(min_col)
self.tableFeature.setHorizontalHeaderLabels(header_name)
self.tableFeature.setVerticalHeaderLabels(
list(map(str,
self.data_container.GetFrame().index)))
for row_index in range(self.data_container.GetFrame().shape[0]):
for col_index in range(min_col):
if col_index < 99:
self.tableFeature.setItem(
row_index, col_index,
QTableWidgetItem(
str(self.data_container.GetFrame().iloc[
row_index, col_index])))
else:
self.tableFeature.setItem(row_index, col_index,
QTableWidgetItem('...'))
text = "The number of cases: {:d}\n".format(
self.data_container.GetFrame().shape[0])
# To process Label temporally
if 'label' in self.data_container.GetFrame().columns:
label_name = 'label'
text += "The number of features: {:d}\n".format(
self.data_container.GetFrame().shape[1] - 1)
elif 'Label' in self.data_container.GetFrame().columns:
label_name = 'Label'
text += "The number of features: {:d}\n".format(
self.data_container.GetFrame().shape[1] - 1)
else:
label_name = ''
text += "The number of features: {:d}\n".format(
self.data_container.GetFrame().shape[1])
if label_name:
labels = np.asarray(
self.data_container.GetFrame()[label_name].values,
dtype=np.int)
if len(np.unique(labels)) == 2:
positive_number = len(np.where(labels == np.max(labels))[0])
negative_number = len(labels) - positive_number
assert (positive_number + negative_number == len(labels))
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 SetButtonsState(self, state):
self.buttonRemoveAndExport.setEnabled(state)
self.buttonSave.setEnabled(state)
self.checkExport.setEnabled(state)
self.radioRemoveNone.setEnabled(state)
self.radioRemoveNonvalidCases.setEnabled(state)
self.radioRemoveNonvalidFeatures.setEnabled(state)
self.radioSplitRandom.setEnabled(state)
self.radioSplitRef.setEnabled(state)
def LoadData(self):
dlg = QFileDialog()
file_name, _ = dlg.getOpenFileName(self,
'Open SCV file',
filter="csv files (*.csv)")
if file_name:
try:
if self.data_container.Load(file_name, is_update=False):
self.UpdateTable()
self.SetButtonsState(True)
except OSError as reason:
eclog(self._filename).GetLogger().error(
'Load CSV Error: {}'.format(reason))
QMessageBox.about(self, 'Load data Error', reason.__str__())
print('Error！' + str(reason))
except ValueError:
eclog(self._filename).GetLogger().error(
'Open CSV Error: {}'.format(file_name))
QMessageBox.information(self, 'Error',
'The selected data file mismatch.')
def LoadTestingReferenceDataContainer(self):
dlg = QFileDialog()
file_name, _ = dlg.getOpenFileName(self,
'Open SCV file',
filter="csv files (*.csv)")
if file_name:
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:
eclog(self._filename).GetLogger().error(
'Load Testing Ref Error: {}'.format(reason))
print('Error！' + str(reason))
except ValueError:
eclog(self._filename).GetLogger().error(
'Open CSV Error: {}'.format(file_name))
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 LoadClinicalRef(self):
dlg = QFileDialog()
file_name, _ = dlg.getOpenFileName(self,
'Open SCV file',
filter="csv files (*.csv)")
if file_name:
try:
self.__clinical_ref = pd.read_csv(file_name, index_col=0)
if list(self.__clinical_ref.index) != list(
self.data_container.GetFrame().index):
QMessageBox.information(
self, 'Error',
'The index of clinical features is not consistent to the data'
)
return None
self.loadClinicRef.setEnabled(False)
self.clearClinicRef.setEnabled(True)
except OSError as reason:
eclog(self._filename).GetLogger().error(
'Load Clinical Ref Error: {}'.format(reason))
QMessageBox.information(self, 'Error',
'Can not Open the Files')
except ValueError:
eclog(self._filename).GetLogger().error(
'OpenCSV Error: {}'.format(file_name))
QMessageBox.information(self, 'Error',
'The selected data file mismatch.')
return None
def ClearClinicalRef(self):
del self.__clinical_ref
self.__clinical_ref = pd.DataFrame()
self.loadClinicRef.setEnabled(True)
self.clearClinicRef.setEnabled(False)
def RemoveInvalidValue(self):
if not self.data_container.IsEmpty():
if self.checkExport.isChecked():
dlg = QFileDialog()
store_path, _ = dlg.getSaveFileName(self,
'Save CSV feature files',
'features.csv',
filter="CSV files (*.csv)")
# folder_name = QFileDialog.getExistingDirectory(self, "Save Invalid data")
# store_path = os.path.join(folder_name, 'invalid_feature.csv')
else:
store_path = ''
if self.radioRemoveNonvalidCases.isChecked():
self.data_container.RemoveInvalid(store_path=store_path,
remove_index=REMOVE_CASE)
elif self.radioRemoveNonvalidFeatures.isChecked():
self.data_container.RemoveInvalid(store_path=store_path,
remove_index=REMOVE_FEATURE)
self.UpdateTable()
def ChangeSeparateMethod(self):
if self.radioSplitRandom.isChecked():
self.spinBoxSeparate.setEnabled(True)
self.checkUseClinicRef.setEnabled(True)
self.loadTestingReference.setEnabled(False)
self.clearTestingReference.setEnabled(False)
elif self.radioSplitRef.isChecked():
self.spinBoxSeparate.setEnabled(False)
self.checkUseClinicRef.setEnabled(False)
if self.__testing_ref_data_container.IsEmpty():
self.loadTestingReference.setEnabled(True)
self.clearTestingReference.setEnabled(False)
else:
self.loadTestingReference.setEnabled(False)
self.clearTestingReference.setEnabled(True)
self.RandomSeparateButtonUpdates()
def RandomSeparateButtonUpdates(self):
if self.checkUseClinicRef.isChecked():
if self.__clinical_ref.size > 0:
self.loadClinicRef.setEnabled(False)
self.clearClinicRef.setEnabled(True)
else:
self.loadClinicRef.setEnabled(True)
self.clearClinicRef.setEnabled(False)
else:
self.loadClinicRef.setEnabled(False)
self.clearClinicRef.setEnabled(False)
def CheckAndSave(self):
if self.data_container.IsEmpty():
QMessageBox.warning(self, "Warning", "There is no data",
QMessageBox.Ok)
return None
if 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])
self.tableFeature.setEditTriggers(old_edit_triggers)
return None
self.data_container.UpdateDataByFrame()
if not self.data_container.IsBinaryLabel():
QMessageBox.warning(self, "Warning", "There are not 2 Labels",
QMessageBox.Ok)
return None
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)
raw_train_data_container, raw_test_data_conainer, store_folder,
is_hyper_parameter)
if store_folder:
self.SavePipeline(len(raw_train_data_container.GetFeatureName()),
os.path.join(store_folder, 'pipeline_info.csv'))
return train_cv_metric, val_cv_metric, test_metric, all_train_metric
if __name__ == '__main__':
index_dict = Index2Dict()
train = DataContainer()
test = DataContainer()
train.Load(r'..\..\Demo\zero_center_normalized_training_feature.csv')
test.Load(r'..\..\Demo\zero_center_normalized_testing_feature.csv')
faps = FeatureAnalysisPipelines(
balancer=index_dict.GetInstantByIndex('NoneBalance'),
normalizer_list=[index_dict.GetInstantByIndex('None')],
dimension_reduction_list=[index_dict.GetInstantByIndex('PCC')],
feature_selector_list=[index_dict.GetInstantByIndex('RFE')],
feature_selector_num_list=[15],
classifier_list=[index_dict.GetInstantByIndex('LR')],
cross_validation=index_dict.GetInstantByIndex('5-Folder'))
for temp in faps.Run(train, test, store_folder=r'..\..\Demo\db2-2'):
print(temp)
print('Done')
return "To Remove the unbalance of the training data set, we applied an Tomek link after the " \
"Synthetic Minority Oversampling TEchnique (SMOTE) to make positive/negative samples balance. "
def Run(self, data_container, store_path=''):
data, label, feature_name, label_name = data_container.GetData()
data_resampled, label_resampled = self._model.fit_sample(data, label)
new_case_name = [
'Generate' + str(index) for index in range(data_resampled.shape[0])
]
new_data_container = DataContainer(data_resampled, label_resampled,
data_container.GetFeatureName(),
new_case_name)
if store_path != '':
if os.path.isdir(store_path):
new_data_container.Save(
os.path.join(store_path,
'{}_features.csv'.format(self._name)))
else:
new_data_container.Save(store_path)
return new_data_container
if __name__ == '__main__':
dc = DataContainer()
dc.Load(r'..\..\Example\numeric_feature.csv')
print(dc.GetArray().shape, np.sum(dc.GetLabel()))
b = SmoteTomekSampling()
new = b.Run(dc)
print(new.GetArray().shape, np.sum(new.GetLabel()))
'''
import pandas as pd
from copy import deepcopy
from BC.DataContainer.DataContainer import DataContainer
class FeatureEncodingOneHot():
def __init__(self):
pass
def OneHotOneColumn(self, data_container, feature_list):
info = data_container.GetFrame()
feature_name = data_container.GetFeatureName()
for feature in feature_list:
assert (feature in feature_name)
new_info = pd.get_dummies(info, columns=feature_list)
new_data = DataContainer()
new_data.SetFrame(new_info)
return new_data
if __name__ == '__main__':
data = DataContainer()
data.Load(r'c:\Users\yangs\Desktop\test.csv')
info = data.GetFrame()
new_info = pd.get_dummies(
info, columns=['bGs', 'PIRADS', 't2score', 'DWIscore', 'MR_stage'])
new_info.to_csv(r'c:\Users\yangs\Desktop\test_onehot.csv')
