def MergeCvResult(self, store_folder):
num = 0
for norm_index, normalizer in enumerate(self.normalizer_list):
norm_store_folder = MakeFolder(store_folder, normalizer.GetName())
for dr_index, dr in enumerate(self.dimension_reduction_list):
dr_store_folder = MakeFolder(norm_store_folder, dr.GetName())
for fs_index, fs in enumerate(self.feature_selector_list):
for fn_index, fn in enumerate(self.feature_selector_num_list):
fs_store_folder = MakeFolder(dr_store_folder, '{}_{}'.format(fs.GetName(), fn))
for cls_index, cls in enumerate(self.classifier_list):
cls_store_folder = MakeFolder(fs_store_folder, cls.GetName())
model_name = self.GetStoreName(normalizer.GetName(),
dr.GetName(),
fs.GetName(),
str(fn),
cls.GetName())
num += 1
yield self.total_num, num
# ADD CV Train
cv_train_info = pd.read_csv(os.path.join(cls_store_folder,
'{}_prediction.csv'.format(CV_TRAIN)),
index_col=0)
cv_train_metric = EstimatePrediction(cv_train_info['Pred'], cv_train_info['Label'],
key_word=CV_TRAIN)
self.__auc_dict[CV_TRAIN][norm_index, dr_index, fs_index, fn_index, cls_index] = \
cv_train_metric['{}_{}'.format(CV_TRAIN, AUC)]
self.__auc_std_dict[CV_TRAIN][norm_index, dr_index, fs_index, fn_index, cls_index] = \
cv_train_metric['{}_{}'.format(CV_TRAIN, AUC_STD)]
self._AddOneMetric(cv_train_metric, os.path.join(cls_store_folder, 'metrics.csv'))
self._MergeOneMetric(cv_train_metric, CV_TRAIN, model_name)
# ADD CV Validation
cv_val_info = pd.read_csv(os.path.join(cls_store_folder,
'{}_prediction.csv'.format(CV_VAL)),
index_col=0)
cv_val_metric = EstimatePrediction(cv_val_info['Pred'], cv_val_info['Label'],
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)))
def RunWithCV(self, train_container, store_folder=''):
for group, containers in enumerate(self.cv.Generate(train_container)):
cv_train_container, cv_val_container = containers
balance_cv_train_container = self.balance.Run(cv_train_container)
num = 0
for norm_index, normalizer in enumerate(self.normalizer_list):
norm_store_folder = MakeFolder(store_folder,
normalizer.GetName())
norm_cv_train_container = normalizer.Run(
balance_cv_train_container)
norm_cv_val_container = normalizer.Transform(cv_val_container)
for dr_index, dr in enumerate(self.dimension_reduction_list):
dr_store_folder = MakeFolder(norm_store_folder,
dr.GetName())
if dr:
dr_cv_train_container = dr.Run(norm_cv_train_container)
dr_cv_val_container = dr.Transform(
norm_cv_val_container)
else:
dr_cv_train_container = norm_cv_train_container
dr_cv_val_container = norm_cv_val_container
for fs_index, fs in enumerate(self.feature_selector_list):
for fn_index, fn in enumerate(
self.feature_selector_num_list):
if fs:
fs_store_folder = MakeFolder(
dr_store_folder,
'{}_{}'.format(fs.GetName(), fn))
fs.SetSelectedFeatureNumber(fn)
fs_cv_train_container = fs.Run(
dr_cv_train_container)
fs_cv_val_container = fs.Transform(
dr_cv_val_container)
else:
fs_store_folder = dr_store_folder
fs_cv_train_container = dr_cv_train_container
fs_cv_val_container = dr_cv_val_container
for cls_index, cls in enumerate(
self.classifier_list):
cls_store_folder = MakeFolder(
fs_store_folder, cls.GetName())
model_name = self.GetStoreName(
normalizer.GetName(), dr.GetName(),
fs.GetName(), str(fn), cls.GetName())
num += 1
yield self.total_num, num, group
cls.SetDataContainer(fs_cv_train_container)
cls.Fit()
cv_train_pred = cls.Predict(
fs_cv_train_container.GetArray())
cv_train_label = fs_cv_train_container.GetLabel(
)
cv_train_info = pd.DataFrame(
{
'Pred': cv_train_pred,
'Label': cv_train_label,
'Group':
[group for temp in cv_train_label]
},
index=fs_cv_train_container.GetCaseName())
cv_val_pred = cls.Predict(
fs_cv_val_container.GetArray())
cv_val_label = fs_cv_val_container.GetLabel()
cv_val_info = pd.DataFrame(
{
'Pred': cv_val_pred,
'Label': cv_val_label,
'Group':
[group for temp in cv_val_label]
},
index=fs_cv_val_container.GetCaseName())
if store_folder:
self._AddOneCvPrediction(
os.path.join(
cls_store_folder,
'{}_prediction.csv'.format(
CV_TRAIN)), cv_train_info)
self._AddOneCvPrediction(
os.path.join(
cls_store_folder,
'{}_prediction.csv'.format(
CV_VAL)), cv_val_info)
def RunWithoutCV(self,
train_container,
test_container=DataContainer(),
store_folder=''):
self.SavePipelineInfo(store_folder)
num = 0
# TODO: Balance后面也可以变成循环处理:
balance_train_container = self.balance.Run(train_container,
store_folder)
for norm_index, normalizer in enumerate(self.normalizer_list):
norm_store_folder = MakeFolder(store_folder, normalizer.GetName())
norm_balance_train_container = normalizer.Run(
balance_train_container,
norm_store_folder,
store_key=BALANCE_TRAIN)
norm_train_container = normalizer.Transform(train_container,
norm_store_folder,
store_key=TRAIN)
norm_test_container = normalizer.Transform(test_container,
norm_store_folder,
store_key=TEST)
for dr_index, dr in enumerate(self.dimension_reduction_list):
dr_store_folder = MakeFolder(norm_store_folder, dr.GetName())
if dr:
dr_balance_train_container = dr.Run(
norm_balance_train_container, dr_store_folder,
BALANCE_TRAIN)
dr_train_container = dr.Transform(norm_train_container,
dr_store_folder, TRAIN)
if not test_container.IsEmpty():
dr_test_container = dr.Transform(
norm_test_container, dr_store_folder, TEST)
else:
dr_test_container = norm_test_container
else:
dr_balance_train_container = norm_balance_train_container
dr_train_container = norm_train_container
dr_test_container = norm_test_container
for fs_index, fs in enumerate(self.feature_selector_list):
for fn_index, fn in enumerate(
self.feature_selector_num_list):
if fs:
fs_store_folder = MakeFolder(
dr_store_folder,
'{}_{}'.format(fs.GetName(), fn))
fs.SetSelectedFeatureNumber(fn)
fs_balance_train_container = fs.Run(
dr_balance_train_container, fs_store_folder,
BALANCE_TRAIN)
fs_train_container = fs.Transform(
dr_train_container, fs_store_folder, TRAIN)
fs_test_container = fs.Transform(
dr_test_container, fs_store_folder, TEST)
else:
fs_store_folder = dr_store_folder
fs_balance_train_container = dr_balance_train_container
fs_train_container = dr_train_container
fs_test_container = dr_test_container
for cls_index, cls in enumerate(self.classifier_list):
cls_store_folder = MakeFolder(
fs_store_folder, cls.GetName())
model_name = self.GetStoreName(
normalizer.GetName(), dr.GetName(),
fs.GetName(), str(fn), cls.GetName())
matrics_index = (norm_index, dr_index, fs_index,
fn_index, cls_index)
num += 1
yield self.total_num, num
cls.SetDataContainer(fs_balance_train_container)
cls.Fit()
cls.Save(cls_store_folder)
balance_train_pred = cls.Predict(
fs_balance_train_container.GetArray())
balance_train_label = fs_balance_train_container.GetLabel(
)
self.SaveOneResult(
balance_train_pred, balance_train_label,
BALANCE_TRAIN,
fs_balance_train_container.GetCaseName(),
matrics_index, model_name, store_folder,
cls_store_folder)
train_data = fs_train_container.GetArray()
train_label = fs_train_container.GetLabel()
train_pred = cls.Predict(train_data)
self.SaveOneResult(
train_pred, train_label, TRAIN,
fs_train_container.GetCaseName(),
matrics_index, model_name, store_folder,
cls_store_folder)
if not test_container.IsEmpty():
test_data = fs_test_container.GetArray()
test_label = fs_test_container.GetLabel()
test_pred = cls.Predict(test_data)
self.SaveOneResult(
test_pred, test_label, TEST,
fs_test_container.GetCaseName(),
matrics_index, model_name, store_folder,
cls_store_folder)
self.total_metric[BALANCE_TRAIN].to_csv(
os.path.join(store_folder, '{}_results.csv'.format(BALANCE_TRAIN)))
self.total_metric[TRAIN].to_csv(
os.path.join(store_folder, '{}_results.csv'.format(TRAIN)))
if not test_container.IsEmpty():
self.total_metric[TEST].to_csv(
os.path.join(store_folder, '{}_results.csv'.format(TEST)))