def get_buckets(self, stamp_token):
"""Returns quantile buckets created during previous flush."""
are_buckets_ready, buckets = (
gen_quantile_ops.quantile_accumulator_get_buckets(
quantile_accumulator_handles=[self.resource_handle],
stamp_token=stamp_token))
return are_buckets_ready[0], buckets[0]
def _make_dense_split(quantile_accumulator_handle, stats_accumulator_handle,
stamp_token, next_stamp_token, multiclass_strategy,
class_id, feature_column_id, l1_regularization,
l2_regularization, tree_complexity_regularization,
min_node_weight, is_multi_dimentional,
loss_uses_sum_reduction, weak_learner_type):
"""Function that builds splits for a dense feature column."""
# Get the bucket boundaries
are_splits_ready, buckets = (
gen_quantile_ops.quantile_accumulator_get_buckets(
quantile_accumulator_handles=[quantile_accumulator_handle],
stamp_token=stamp_token))
# quantile_accumulator_get_buckets returns a list of results per handle that
# we pass to it. In this case we're getting results just for one resource.
are_splits_ready = are_splits_ready[0]
buckets = buckets[0]
# After we receive the boundaries from previous iteration we can flush
# the quantile accumulator.
with ops.control_dependencies([buckets]):
flush_quantiles = gen_quantile_ops.quantile_accumulator_flush(
quantile_accumulator_handle=quantile_accumulator_handle,
stamp_token=stamp_token,
next_stamp_token=next_stamp_token)
if is_multi_dimentional:
num_minibatches, partition_ids, bucket_ids, gradients, hessians = (
gen_stats_accumulator_ops.stats_accumulator_tensor_flush(
stats_accumulator_handle, stamp_token, next_stamp_token))
else:
num_minibatches, partition_ids, bucket_ids, gradients, hessians = (
gen_stats_accumulator_ops.stats_accumulator_scalar_flush(
stats_accumulator_handle, stamp_token, next_stamp_token))
# For sum_reduction, we don't need to divide by number of minibatches.
num_minibatches = control_flow_ops.cond(
loss_uses_sum_reduction,
lambda: math_ops.cast(1, dtypes.int64),
lambda: num_minibatches)
# Put quantile and stats accumulator flushing in the dependency path.
with ops.control_dependencies([flush_quantiles, partition_ids]):
are_splits_ready = array_ops.identity(are_splits_ready)
partition_ids, gains, split_infos = (
split_handler_ops.build_dense_inequality_splits(
num_minibatches=num_minibatches,
bucket_boundaries=buckets,
partition_ids=partition_ids,
bucket_ids=bucket_ids,
gradients=gradients,
hessians=hessians,
class_id=class_id,
feature_column_group_id=feature_column_id,
l1_regularization=l1_regularization,
l2_regularization=l2_regularization,
tree_complexity_regularization=tree_complexity_regularization,
min_node_weight=min_node_weight,
multiclass_strategy=multiclass_strategy,
weak_learner_type=weak_learner_type))
return are_splits_ready, partition_ids, gains, split_infos
def _make_dense_split(quantile_accumulator_handle, stats_accumulator_handle,
stamp_token, next_stamp_token, multiclass_strategy,
class_id, feature_column_id, l1_regularization,
l2_regularization, tree_complexity_regularization,
min_node_weight, is_multi_dimentional,
loss_uses_sum_reduction, weak_learner_type):
"""Function that builds splits for a dense feature column."""
# Get the bucket boundaries
are_splits_ready, buckets = (
gen_quantile_ops.quantile_accumulator_get_buckets(
quantile_accumulator_handles=[quantile_accumulator_handle],
stamp_token=stamp_token))
# quantile_accumulator_get_buckets returns a list of results per handle that
# we pass to it. In this case we're getting results just for one resource.
are_splits_ready = are_splits_ready[0]
buckets = buckets[0]
# After we receive the boundaries from previous iteration we can flush
# the quantile accumulator.
with ops.control_dependencies([buckets]):
flush_quantiles = gen_quantile_ops.quantile_accumulator_flush(
quantile_accumulator_handle=quantile_accumulator_handle,
stamp_token=stamp_token,
next_stamp_token=next_stamp_token)
if is_multi_dimentional:
num_minibatches, partition_ids, bucket_ids, gradients, hessians = (
gen_stats_accumulator_ops.stats_accumulator_tensor_flush(
stats_accumulator_handle, stamp_token, next_stamp_token))
else:
num_minibatches, partition_ids, bucket_ids, gradients, hessians = (
gen_stats_accumulator_ops.stats_accumulator_scalar_flush(
stats_accumulator_handle, stamp_token, next_stamp_token))
# For sum_reduction, we don't need to divide by number of minibatches.
num_minibatches = control_flow_ops.cond(loss_uses_sum_reduction,
lambda: math_ops.to_int64(1),
lambda: num_minibatches)
# Put quantile and stats accumulator flushing in the dependency path.
with ops.control_dependencies([flush_quantiles, partition_ids]):
are_splits_ready = array_ops.identity(are_splits_ready)
partition_ids, gains, split_infos = (
split_handler_ops.build_dense_inequality_splits(
num_minibatches=num_minibatches,
bucket_boundaries=buckets,
partition_ids=partition_ids,
bucket_ids=bucket_ids,
gradients=gradients,
hessians=hessians,
class_id=class_id,
feature_column_group_id=feature_column_id,
l1_regularization=l1_regularization,
l2_regularization=l2_regularization,
tree_complexity_regularization=tree_complexity_regularization,
min_node_weight=min_node_weight,
multiclass_strategy=multiclass_strategy,
weak_learner_type=weak_learner_type))
return are_splits_ready, partition_ids, gains, split_infos
