def predict(self, data_inst, predict_param=None):
LOGGER.info("start predict")
cache_dataset_key = self.predict_data_cache.get_data_key(data_inst)
if cache_dataset_key in self.data_alignment_map:
data_inst = self.data_alignment_map[cache_dataset_key]
else:
data_inst = self.data_alignment(data_inst)
header = [None] * len(self.feature_name_fid_mapping)
for idx, col in self.feature_name_fid_mapping.items():
header[idx] = col
data_inst = data_overview.header_alignment(data_inst, header)
self.data_alignment_map[cache_dataset_key] = data_inst
rounds = len(self.trees_) // self.tree_dim
predict_start_round = self.sync_predict_start_round()
for i in range(predict_start_round, rounds):
# n_tree = self.trees_[i]
for tidx in range(self.tree_dim):
LOGGER.info(
"start to predict, boost round: {}, tree index: {}".format(
i, tidx))
tree_inst = HeteroDecisionTreeHost(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.predict(data_inst)
LOGGER.info("end predict")
def fit(self, data_inst):
LOGGER.info("begin to train secureboosting guest model")
self.gen_feature_fid_mapping(data_inst.schema)
LOGGER.debug("schema is {}".format(data_inst.schema))
data_inst = self.data_alignment(data_inst)
self.convert_feature_to_bin(data_inst)
self.sync_tree_dim()
for i in range(self.num_trees):
for tidx in range(self.tree_dim):
tree_inst = HeteroDecisionTreeHost(self.tree_param)
tree_inst.set_inputinfo(data_bin=self.data_bin, bin_split_points=self.bin_split_points,
bin_sparse_points=self.bin_sparse_points)
valid_features = self.sample_valid_features()
tree_inst.set_flowid(self.generate_flowid(i, tidx))
tree_inst.set_runtime_idx(self.runtime_idx)
tree_inst.set_valid_features(valid_features)
tree_inst.fit()
tree_meta, tree_param = tree_inst.get_model()
self.trees_.append(tree_param)
if self.tree_meta is None:
self.tree_meta = tree_meta
if self.n_iter_no_change is True:
stop_flag = self.sync_stop_flag(i)
if stop_flag:
break
LOGGER.info("end to train secureboosting guest model")
def fit(self, data_inst, validate_data=None):
LOGGER.info("begin to train secureboosting guest model")
self.gen_feature_fid_mapping(data_inst.schema)
LOGGER.debug("schema is {}".format(data_inst.schema))
data_inst = self.data_alignment(data_inst)
self.convert_feature_to_bin(data_inst)
self.sync_tree_dim()
self.validation_strategy = self.init_validation_strategy(
data_inst, validate_data)
for i in range(self.num_trees):
# n_tree = []
for tidx in range(self.tree_dim):
LOGGER.info(
"start to fit, boost round: {}, tree index: {}".format(
i, tidx))
tree_inst = HeteroDecisionTreeHost(self.tree_param)
tree_inst.set_inputinfo(
data_bin=self.data_bin,
bin_split_points=self.bin_split_points,
bin_sparse_points=self.bin_sparse_points)
valid_features = self.sample_valid_features()
tree_inst.set_flowid(self.generate_flowid(i, tidx))
tree_inst.set_runtime_idx(
self.component_properties.local_partyid)
tree_inst.set_valid_features(valid_features)
tree_inst.fit()
tree_meta, tree_param = tree_inst.get_model()
self.trees_.append(tree_param)
if self.tree_meta is None:
self.tree_meta = tree_meta
# n_tree.append(tree_inst.get_tree_model())
# self.trees_.append(n_tree)
if self.validation_strategy:
LOGGER.debug('host running validation')
self.validation_strategy.validate(self, i)
if self.validation_strategy.need_stop():
LOGGER.debug('early stopping triggered')
break
if self.n_iter_no_change is True:
stop_flag = self.sync_stop_flag(i)
if stop_flag:
break
if self.validation_strategy and self.validation_strategy.has_saved_best_model(
):
self.load_model(self.validation_strategy.cur_best_model)
LOGGER.info("end to train secureboosting guest model")
def predict_f_value(self, data_inst, predict_start_round, rounds):
for i in range(predict_start_round, rounds):
# n_tree = self.trees_[i]
for tidx in range(self.tree_dim):
tree_inst = HeteroDecisionTreeHost(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.predict(data_inst)
def predict(self, data_inst, predict_param=None):
LOGGER.info("start predict")
data_inst = self.data_alignment(data_inst)
rounds = len(self.trees_) // self.tree_dim
for i in range(rounds):
for tidx in range(self.tree_dim):
tree_inst = HeteroDecisionTreeHost(self.tree_param)
tree_inst.load_model(self.tree_meta, self.trees_[i * self.tree_dim + tidx])
tree_inst.set_flowid(self.generate_flowid(i, tidx))
tree_inst.set_runtime_idx(self.runtime_idx)
tree_inst.predict(data_inst)
LOGGER.info("end predict")
def predict(self, data_inst, predict_param=None):
LOGGER.info("start predict")
data_inst = self.data_alignment(data_inst)
rounds = len(self.trees_) // self.tree_dim
predict_start_round = self.sync_predict_start_round()
for i in range(predict_start_round, rounds):
# n_tree = self.trees_[i]
for tidx in range(self.tree_dim):
tree_inst = HeteroDecisionTreeHost(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.predict(data_inst)
LOGGER.info("end predict")