def fit(self, data):
self.__init_intersect_method()
if self.model_param.repeated_id_process:
if self.model_param.intersect_cache_param.use_cache is True and self.model_param.intersect_method == consts.RSA:
raise ValueError(
"Not support cache module while repeated id process.")
if len(
self.host_party_id_list
) > 1 and self.model_param.repeated_id_owner != consts.GUEST:
raise ValueError(
"While multi-host, repeated_id_owner should be guest.")
proc_obj = RepeatedIDIntersect(
repeated_id_owner=self.model_param.repeated_id_owner,
role=self.role)
data = proc_obj.run(data=data)
if self.model_param.allow_info_share:
if self.model_param.intersect_method == consts.RSA and self.model_param.info_owner == consts.GUEST \
or self.model_param.intersect_method == consts.RAW and self.model_param.join_role == self.model_param.info_owner:
self.model_param.sync_intersect_ids = False
self.intersect_ids = self.intersection_obj.run(data)
if self.model_param.allow_info_share:
self.intersect_ids = self.__share_info(data)
LOGGER.info("Finish intersection")
if self.intersect_ids:
self.intersect_num = self.intersect_ids.count()
self.intersect_rate = self.intersect_num * 1.0 / data.count()
self.set_summary(self.get_model_summary())
self.callback_metric(metric_name=self.metric_name,
metric_namespace=self.metric_namespace,
metric_data=[
Metric("intersect_count", self.intersect_num),
Metric("intersect_rate", self.intersect_rate)
])
self.tracker.set_metric_meta(metric_namespace=self.metric_namespace,
metric_name=self.metric_name,
metric_meta=MetricMeta(
name=self.metric_name,
metric_type=self.metric_type))
def fit(self, data):
self.init_intersect_method()
if self.model_param.repeated_id_process:
if self.model_param.intersect_cache_param.use_cache is True and self.model_param.intersect_method == consts.RSA:
raise ValueError(
"Not support cache module while repeated id process.")
if len(
self.host_party_id_list
) > 1 and self.model_param.repeated_id_owner != consts.GUEST:
raise ValueError(
"While multi-host, repeated_id_owner should be guest.")
proc_obj = RepeatedIDIntersect(
repeated_id_owner=self.model_param.repeated_id_owner,
role=self.role)
if self.model_param.with_sample_id:
proc_obj.use_sample_id()
data = proc_obj.recover(data=data)
self.intersect_ids = self.intersection_obj.run_intersect(data)
if self.model_param.repeated_id_process:
if not self.model_param.sync_intersect_ids:
self.intersect_ids = data
self.intersect_ids = proc_obj.expand(self.intersect_ids)
if self.model_param.repeated_id_owner == self.role and self.model_param.only_output_key:
sid_name = self.intersect_ids.schema.get('sid_name')
self.intersect_ids = self.intersect_ids.mapValues(
lambda v: None)
self.intersect_ids.schema['sid_name'] = sid_name
# LOGGER.info("repeated_id process:{}".format(self.intersect_ids.count()))
if self.model_param.allow_info_share:
if self.model_param.intersect_method == consts.RSA and self.model_param.info_owner == consts.GUEST \
or self.model_param.intersect_method == consts.RAW and self.model_param.join_role == self.model_param.info_owner:
self.model_param.sync_intersect_ids = False
self.intersect_ids = self.__share_info(self.intersect_ids)
LOGGER.info("Finish intersection")
if self.intersect_ids:
self.intersect_num = self.intersect_ids.count()
self.intersect_rate = self.intersect_num * 1.0 / data.count()
self.set_summary(self.get_model_summary())
self.callback_metric(metric_name=self.metric_name,
metric_namespace=self.metric_namespace,
metric_data=[
Metric("intersect_count", self.intersect_num),
Metric("intersect_rate", self.intersect_rate)
])
self.tracker.set_metric_meta(metric_namespace=self.metric_namespace,
metric_name=self.metric_name,
metric_meta=MetricMeta(
name=self.metric_name,
metric_type=self.metric_type))