General Tree Inference Library (GTIL)
GTIL is a reference implementation of a prediction runtime for all Treelite models. It has the following goals:
Universal coverage: GTIL shall support all tree ensemble models that can be represented as Treelite objects.
Accessible code: GTIL should be written in an easytoread style that can be understood to a firsttime contributor. We prefer code legibility to performance optimization.
Correct output: As a reference implementation, GTIL should produce correct prediction outputs.
General Tree Inference Library (GTIL)
Functions:

Predict with a Treelite model using the General Tree Inference Library (GTIL). 

Predict with a Treelite model, outputting the leaf node's ID for each row. 

Predict with a Treelite model and output prediction of each tree. 
 treelite.gtil.predict(model, data, *, nthread=1, pred_margin=False)
Predict with a Treelite model using the General Tree Inference Library (GTIL).
 Parameters:
model (
Model
object) – Treelite model objectdata (
numpy.ndarray
/scipy.sparse.csr_matrix
) – Data matrix, with which to run predictionnthread (
int
, optional) – Number of CPU cores to use in prediction. If <= 0, use all CPU cores.pred_margin (bool) – Whether to produce raw margin scores. If pred_margin=True, postprocessing is no longer applied and raw margin scores are produced.
 Returns:
prediction – Prediction output. Expected dimensions: (num_row, num_target, max(num_class))
 Return type:
numpy.ndarray
array
 treelite.gtil.predict_leaf(model, data, *, nthread=1)
Predict with a Treelite model, outputting the leaf node’s ID for each row.
 Parameters:
model (
Model
object) – Treelite model objectdata (
numpy.ndarray
/scipy.sparse.csr_matrix
) – Data matrix, with which to run predictionnthread (
int
, optional) – Number of CPU cores to use in prediction. If <= 0, use all CPU cores.
 Returns:
prediction – Prediction output. Expected output dimensions: (num_row, num_tree)
 Return type:
numpy.ndarray
array
Notes
Treelite assigns a unique integer ID for every node in the tree, including leaf nodes as well as internal nodes. It does so by traversing the tree breadthfirst. So, for example, the root node is assigned ID 0, and the two nodes at depth=1 is assigned ID 1 and 2, respectively. Call
treelite.Model.dump_as_json()
to obtain the ID of every tree node.
 treelite.gtil.predict_per_tree(model, data, *, nthread=1)
Predict with a Treelite model and output prediction of each tree. This function computes one or more margin scores per tree.
 Parameters:
model (
Model
object) – Treelite model objectdata (
numpy.ndarray
/scipy.sparse.csr_matrix
) – Data matrix, with which to run predictionnthread (
int
, optional) – Number of CPU cores to use in prediction. If <= 0, use all CPU cores.
 Returns:
prediction – Prediction output. Expected output dimensions: (num_row, num_tree, leaf_vector_shape[0] * leaf_vector_shape[1])
 Return type:
numpy.ndarray
array