def predict_f_value(self, data_inst):
LOGGER.info("predict tree f value")
tree_dim = self.tree_dim
self.F = data_inst.mapValues(lambda v: np.zeros(tree_dim))
for i in range(len(self.trees_)):
n_tree = self.trees_[i]
for tidx in range(len(n_tree)):
tree_inst = HeteroDecisionTreeGuest(self.tree_param)
tree_inst.set_tree_model(n_tree[tidx])
tree_inst.set_flowid(self.generate_flowid(i, tidx))
predict_data = tree_inst.predict(data_inst)
self.update_f_value(predict_data, tidx)
def predict_f_value(self, data_inst):
LOGGER.info("predict tree f value, there are {} trees".format(len(self.trees_)))
tree_dim = self.tree_dim
init_score = self.init_score
self.F = data_inst.mapValues(lambda v: init_score)
rounds = len(self.trees_) // self.tree_dim
for i in range(rounds):
for tidx in range(self.tree_dim):
tree_inst = HeteroDecisionTreeGuest(self.tree_param)
tree_inst.load_model(self.tree_meta, self.trees_[i * self.tree_dim + tidx])
# tree_inst.set_tree_model(self.trees_[i * self.tree_dim + tidx])
tree_inst.set_flowid(self.generate_flowid(i, tidx))
predict_data = tree_inst.predict(data_inst)
self.update_f_value(new_f=predict_data, tidx=tidx)
def predict_f_value(self, data_inst, cache_dataset_key):
LOGGER.info("predict tree f value, there are {} trees".format(
len(self.trees_)))
init_score = self.init_score
last_round = self.predict_data_cache.predict_data_last_round(
cache_dataset_key)
LOGGER.debug("jyp last_round is {}".format(last_round))
rounds = len(self.trees_) // self.tree_dim
if last_round == -1:
self.predict_F = data_inst.mapValues(lambda v: init_score)
else:
LOGGER.debug("hit cache, cached round is {}".format(last_round))
if last_round >= rounds - 1:
LOGGER.debug(
"predict data cached, rounds is {}, total cached round is {}"
.format(rounds, last_round))
self.predict_F = self.predict_data_cache.predict_data_at(
cache_dataset_key, min(rounds - 1, last_round))
self.sync_predict_start_round(last_round + 1)
# LOGGER.debug("jyp self.predict_F is {}".format(self.predict_F))
# LOGGER.debug("jyp self.predict_F.collect() is {}".format(self.predict_F.collect()))
# LOGGER.debug("jyp self.predict_F.count() is {}".format(self.predict_F.count()))
# LOGGER.debug("jyp self.predict_F.first() is {}".format(self.predict_F.first()))
for i in range(last_round + 1, rounds):
for tidx in range(self.tree_dim):
tree_inst = HeteroDecisionTreeGuest(self.tree_param)
tree_inst.load_model(self.tree_meta,
self.trees_[i * self.tree_dim + tidx])
# tree_inst.set_tree_model(self.trees_[i * self.tree_dim + tidx])
tree_inst.set_flowid(self.generate_flowid(i, tidx))
tree_inst.set_runtime_idx(
self.component_properties.local_partyid)
tree_inst.set_host_party_idlist(
self.component_properties.host_party_idlist)
tree_inst.set_encrypter(self.encrypter)
predict_data = tree_inst.predict(data_inst)
# LOGGER.debug("jyp predict_data type is {}".format(type(predict_data)))
self.update_f_value(new_f=predict_data,
tidx=tidx,
mode="predict")
self.predict_data_cache.add_data(cache_dataset_key, self.predict_F)