def LoadPipelineInfo(self, store_folder):
index_2_dict = Index2Dict()
with open(os.path.join(store_folder, 'pipeline_info.csv'),
'r',
newline='') as csvfile:
reader = csv.reader(csvfile)
for row in reader:
if row[0] == 'Normalizer':
self.__normalizer_list = []
for index in row[1:]:
self.__normalizer_list.append(
index_2_dict.GetInstantByIndex(index))
elif row[0] == 'DimensionReduction':
self._dimension_reduction_list = []
for index in row[1:]:
self._dimension_reduction_list.append(
index_2_dict.GetInstantByIndex(index))
elif row[0] == 'FeatureSelector':
self.__feature_selector_list = []
for index in row[1:]:
self.__feature_selector_list.append(
index_2_dict.GetInstantByIndex(index))
elif row[0] == 'FeatureNumber':
self.__feature_selector_num_list = row[1:]
elif row[0] == 'Classifier':
self.__classifier_list = []
for index in row[1:]:
self.__classifier_list.append(
index_2_dict.GetInstantByIndex(index))
elif row[0] == 'CrossValidation':
self.__cross_validation = index_2_dict.GetInstantByIndex(
row[1])
else:
print('Unknown name.')
def LoadPipelineInfo(self, store_folder):
index_2_dict = Index2Dict()
info_path = os.path.join(store_folder, 'pipeline_info.csv')
if not os.path.exists(info_path):
return False
with open(info_path, 'r', newline='') as csvfile:
reader = csv.reader(csvfile)
for row in reader:
if row[0] == VERSION_NAME:
self.version = row[1]
if self.version not in ACCEPT_VERSION:
return False
elif row[0] == CROSS_VALIDATION:
self.cv = index_2_dict.GetInstantByIndex(row[1])
elif row[0] == BALANCE:
self.balance = index_2_dict.GetInstantByIndex(row[1])
elif row[0] == NORMALIER:
self.normalizer_list = [index_2_dict.GetInstantByIndex(index) for index in row[1:]]
elif row[0] == DIMENSION_REDUCTION:
self.dimension_reduction_list = [index_2_dict.GetInstantByIndex(index) for index in row[1:]]
elif row[0] == FEATURE_SELECTOR:
self.feature_selector_list = [index_2_dict.GetInstantByIndex(index) for index in row[1:]]
elif row[0] == FEATURE_NUMBER:
self.feature_selector_num_list = row[1:]
elif row[0] == CLASSIFIER:
self.classifier_list = [index_2_dict.GetInstantByIndex(index) for index in row[1:]]
else:
print('Unknown name: {}'.format(row[0]))
raise KeyError
return True
def _MethodDescription(self, pipeline_name, result_root):
index_dict = Index2Dict()
norm_folder, dr_folder, fs_folder, cls_folder = self.__manager.SplitFolder(
pipeline_name, result_root)
normalizer = index_dict.GetInstantByIndex(
os.path.split(norm_folder)[1])
dr = index_dict.GetInstantByIndex(os.path.split(dr_folder)[1])
fs = index_dict.GetInstantByIndex(
os.path.split(fs_folder)[1].split('_')[0])
cls = index_dict.GetInstantByIndex(os.path.split(cls_folder)[1])
with open(os.path.join(result_root, 'pipeline_info.csv'), 'r') as file:
rows = csv.reader(file)
for row in rows:
if CROSS_VALIDATION == row[0]:
cv = index_dict.GetInstantByIndex(row[1])
elif BALANCE == row[0]:
balance = index_dict.GetInstantByIndex(row[1])
method_description = " "
method_description += balance.GetDescription()
method_description += normalizer.GetDescription()
method_description += dr.GetDescription()
method_description += fs.GetDescription()
method_description += cls.GetDescription()
method_description += cv.GetDescription()
method_description += "\n"
return method_description
def LoadPipeline(self, store_path):
index_2_dict = Index2Dict()
feature_number = 0
with open(store_path, 'r', newline='') as csvfile:
reader = csv.reader(csvfile)
for row in reader:
if row[0] == 'Normalizer':
self.__normalizer = index_2_dict.GetInstantByIndex(row[1])
if row[0] == 'DimensionReduction':
self.__dimension_reduction = index_2_dict.GetInstantByIndex(row[1])
if row[0] == 'FeatureSelector':
self.__feature_selector = index_2_dict.GetInstantByIndex(row[1])
if row[0] == 'FeatureNumber':
feature_number = int(row[1])
if row[0] == 'Classifier':
self.__classifier = index_2_dict.GetInstantByIndex(row[1])
if row[0] == 'CrossValidation':
self.__cv = index_2_dict.GetInstantByIndex(row[1])
self.__feature_selector.SetSelectedFeatureNumber(feature_number)
key_word=CV_VAL)
self.__auc_dict[CV_VAL][norm_index, dr_index, fs_index, fn_index, cls_index] = \
cv_val_metric['{}_{}'.format(CV_VAL, AUC)]
self.__auc_std_dict[CV_VAL][norm_index, dr_index, fs_index, fn_index, cls_index] = \
cv_val_metric['{}_{}'.format(CV_VAL, AUC_STD)]
self._AddOneMetric(cv_val_metric, os.path.join(cls_store_folder, 'metrics.csv'))
self._MergeOneMetric(cv_val_metric, CV_VAL, 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'):