tf.raw_ops.BoostedTreesCalculateBestGainsPerFeature

Calculates gains for each feature and returns the best possible split information for the feature.

tf.raw_ops.BoostedTreesCalculateBestGainsPerFeature(
    node_id_range,
    stats_summary_list,
    l1,
    l2,
    tree_complexity,
    min_node_weight,
    max_splits,
    name=None
)

The split information is the best threshold (bucket id), gains and left/right node contributions per node for each feature.

It is possible that not all nodes can be split on each feature. Hence, the list of possible nodes can differ between the features. Therefore, we return node_ids_list for each feature, containing the list of nodes that this feature can be used to split.

In this manner, the output is the best split per features and per node, so that it needs to be combined later to produce the best split for each node (among all possible features).

The length of output lists are all of the same length, num_features. The output shapes are compatible in a way that the first dimension of all tensors of all lists are the same and equal to the number of possible split nodes for each feature.

node_id_rangeA Tensor of type int32. A Rank 1 tensor (shape=[2]) to specify the range [first, last) of node ids to process within stats_summary_list. The nodes are iterated between the two nodes specified by the tensor, as like for node_id in range(node_id_range[0], node_id_range[1]) (Note that the last index node_id_range[1] is exclusive).
stats_summary_listA list of at least 1 Tensor objects with type float32. A list of Rank 3 tensor (#shape=[max_splits, bucket, 2]) for accumulated stats summary (gradient/hessian) per node per buckets for each feature. The first dimension of the tensor is the maximum number of splits, and thus not all elements of it will be used, but only the indexes specified by node_ids will be used.
l1A Tensor of type float32. l1 regularization factor on leaf weights, per instance based.
l2A Tensor of type float32. l2 regularization factor on leaf weights, per instance based.
tree_complexityA Tensor of type float32. adjustment to the gain, per leaf based.
min_node_weightA Tensor of type float32. minimum avg of hessians in a node before required for the node to be considered for splitting.
max_splitsAn int that is >= 1. the number of nodes that can be split in the whole tree. Used as a dimension of output tensors.
nameA name for the operation (optional).

A tuple of Tensor objects (node_ids_list, gains_list, thresholds_list, left_node_contribs_list, right_node_contribs_list).
node_ids_listA list with the same length as stats_summary_list of Tensor objects with type int32.
gains_listA list with the same length as stats_summary_list of Tensor objects with type float32.
thresholds_listA list with the same length as stats_summary_list of Tensor objects with type int32.
left_node_contribs_listA list with the same length as stats_summary_list of Tensor objects with type float32.
right_node_contribs_listA list with the same length as stats_summary_list of Tensor objects with type float32.