def feature_selection_fit(self,
data_instance,
flow_id='sample_flowid',
without_transform=False):
if self.mode == consts.H**O:
LOGGER.info(
"H**o feature selection is not supporting yet. Coming soon")
return data_instance
if data_instance is None:
return data_instance
if self.workflow_param.need_feature_selection:
LOGGER.info("Start feature selection")
feature_select_param = param_generator.FeatureSelectionParam()
feature_select_param = ParamExtract.parse_param_from_config(
feature_select_param, self.config_path)
param_checker.FeatureSelectionParamChecker.check_param(
feature_select_param)
if self.role == consts.HOST:
feature_selector = HeteroFeatureSelectionHost(
feature_select_param)
elif self.role == consts.GUEST:
feature_selector = HeteroFeatureSelectionGuest(
feature_select_param)
elif self.role == consts.ARBITER:
return data_instance
else:
raise ValueError("Unknown role of workflow")
feature_selector.set_flowid(flow_id)
filter_methods = feature_select_param.filter_method
previous_model = {}
if 'iv_value_thres' in filter_methods or 'iv_percentile' in filter_methods:
binning_model = {
'name': self.workflow_param.model_table,
'namespace': self.workflow_param.model_namespace
}
previous_model['binning_model'] = binning_model
feature_selector.init_previous_model(**previous_model)
if without_transform:
data_instance = feature_selector.fit(data_instance)
else:
data_instance = feature_selector.fit_transform(data_instance)
save_result = feature_selector.save_model(
self.workflow_param.model_table,
self.workflow_param.model_namespace)
# Save model result in pipeline
for meta_buffer_type, param_buffer_type in save_result:
self.pipeline.node_meta.append(meta_buffer_type)
self.pipeline.node_param.append(param_buffer_type)
LOGGER.info("Finish feature selection")
return data_instance
else:
LOGGER.info("No need to do feature selection")
return data_instance
def feature_selection_fit(self, data_instance, flow_id='sample_flowid'):
if self.mode == consts.H**O:
LOGGER.info(
"H**o feature selection is not supporting yet. Coming soon")
return data_instance
if data_instance is None:
return data_instance
if self.workflow_param.need_feature_selection:
LOGGER.info("Start feature selection")
feature_select_param = param_generator.FeatureSelectionParam()
feature_select_param = ParamExtract.parse_param_from_config(
feature_select_param, self.config_path)
param_checker.FeatureSelectionParamChecker.check_param(
feature_select_param)
if self.role == consts.HOST:
feature_selector = HeteroFeatureSelectionHost(
feature_select_param)
elif self.role == consts.GUEST:
feature_selector = HeteroFeatureSelectionGuest(
feature_select_param)
elif self.role == consts.ARBITER:
return data_instance
else:
raise ValueError("Unknown role of workflow")
feature_selector.set_flowid(flow_id)
local_only = feature_select_param.local_only # Decide whether do fit_local or fit
if local_only:
data_instance = feature_selector.fit_local_transform(
data_instance)
save_result = feature_selector.save_model(
self.workflow_param.model_table,
self.workflow_param.model_namespace)
# Save model result in pipeline
for meta_buffer_type, param_buffer_type in save_result:
self.pipeline.node_meta.append(meta_buffer_type)
self.pipeline.node_param.append(param_buffer_type)
else:
data_instance = feature_selector.fit_transform(data_instance)
save_result = feature_selector.save_model(
self.workflow_param.model_table,
self.workflow_param.model_namespace)
# Save model result in pipeline
for meta_buffer_type, param_buffer_type in save_result:
self.pipeline.node_meta.append(meta_buffer_type)
self.pipeline.node_param.append(param_buffer_type)
LOGGER.info("Finish feature selection")
return data_instance
else:
LOGGER.info("No need to do feature selection")
return data_instance
def feature_selection_transform(self,
data_instance,
flow_id='sample_flowid'):
if self.mode == consts.H**O:
LOGGER.info(
"H**o feature selection is not supporting yet. Coming soon")
return data_instance
if data_instance is None:
return data_instance
if self.workflow_param.need_feature_selection:
LOGGER.info("Start feature selection transform")
feature_select_param = param_generator.FeatureSelectionParam()
feature_select_param = ParamExtract.parse_param_from_config(
feature_select_param, self.config_path)
param_checker.FeatureSelectionParamChecker.check_param(
feature_select_param)
if self.role == consts.HOST:
feature_selector = HeteroFeatureSelectionHost(
feature_select_param)
elif self.role == consts.GUEST:
feature_selector = HeteroFeatureSelectionGuest(
feature_select_param)
elif self.role == consts.ARBITER:
return data_instance
else:
raise ValueError("Unknown role of workflow")
feature_selector.set_flowid(flow_id)
feature_selector.load_model(self.workflow_param.model_table,
self.workflow_param.model_namespace)
LOGGER.debug(
"Role: {}, in transform feature selector left_cols: {}".format(
self.role, feature_selector.left_cols))
data_instance = feature_selector.transform(data_instance)
LOGGER.info("Finish feature selection")
return data_instance
else:
LOGGER.info("No need to do feature selection")
return data_instance
