def test_count_nodes(self):
n_trees, n_nodes = ProxyXGBoost._count_nodes(model_file)
# print "Num Trees: %d\nNum Nodes: %d" % (n_trees, n_nodes),
assert_equal(n_trees, 2)
assert_equal(n_nodes, 14)
assert_equal(n_trees, self.model.trees_root.size)
assert_equal(n_nodes, self.model.trees_nodes_value.size)
def save(self, f, format="QuickRank"):
"""
Save the model onto the file identified by file_path, using the given
model format.
Parameters
----------
f : str
The path to the filename where the model has to be saved
format : str
The format to use for saving the model
Returns
-------
status : bool
Returns true if the save is successful, false otherwise
"""
if format == "QuickRank":
from rankeval.model import ProxyQuickRank
return ProxyQuickRank.save(f, self)
elif format == "LightGBM":
from rankeval.model import ProxyLightGBM
return ProxyLightGBM.save(f, self)
elif format == "XGBoost":
from rankeval.model import ProxyXGBoost
return ProxyXGBoost.save(f, self)
elif format == "ScikitLearn":
from rankeval.model import ProxyScikitLearn
return ProxyScikitLearn.save(f, self)
else:
raise TypeError("Model format %s not yet supported!" % format)
def __init__(self,
file_path,
name=None,
format="QuickRank",
base_score=None,
learning_rate=1,
n_trees=None):
"""
Load the model from the file identified by file_path using the given
format.
Parameters
----------
file_path : str
The fpath to the filename where the model has been saved
name : str
The name to be given to the current model
format : ['QuickRank', 'ScikitLearn', 'XGBoost', 'LightGBM']
The format of the model to load.
base_score : None or float
The initial prediction score of all instances, global bias.
If None, it uses default value used by each software
(0.5 XGBoost, 0.0 all the others).
learning_rate : None or float
The learning rate used by the model to shrinks the contribution of
each tree. By default it is set to 1 (no shrinking at all).
n_trees : None or int
The maximum number of trees to load from the model. By default it is
set to None, meaning the method will load all the trees.
Attributes
----------
file : str
The path to the filename where the model has been saved
name : str
The name to be given to the current model
n_trees : integer
The number of regression trees in the ensemble.
n_nodes : integer
The total number of nodes (splitting nodes and leaves) in the ensemble
trees_root: list of integers
Numpy array modelling the indexes of the root nodes of the regression trees composing the ensemble. The indexes
refer to the following data structures:
* trees_left_child
* trees_right_child
* trees_nodes_value
* trees_nodes_feature
trees_weight: list of floats
Numpy array modelling the weights of the regression trees composing the ensemble.
trees_left_child: list of integers
Numpy array modelling the structure (shape) of the regression trees, considering only the left children.
Given a node of a regression tree (a single cell in this array), the value identify the index of the left
children. If the node is a leaf, the children assumes -1 value.
trees_right_child: list of integers
Numpy array modelling the structure (shape) of the regression trees, considering only the right children.
Given a node of a regression tree (a single cell in this array), the value identify the index of the right
children. If the node is a leaf, the children assumes -1 value.
trees_nodes_value: list of integers
Numpy array modelling either the output of a leaf node (whether the node is a leaf, in accordance with the
trees_structure data structure) or the splitting value of the node in the regression trees (with respect to the
feature identified by the trees_nodes_feature data structure).
trees_nodes_feature: list of integers
Numpy array modelling the feature-id used by the selected splitting node (or -1 if the node is a leaf).
Returns
-------
model : RegressionTreeEnsemble
The loaded model as a RTEnsemble object
"""
self.file = file_path
self.name = "RTEnsemble: " + file_path
if name is not None:
self.name = name
self.learning_rate = learning_rate
self.base_score = base_score
if self.base_score is None and format == "XGBoost":
self.base_score = 0.5
self.n_trees = None
self.n_nodes = None
self.trees_root = None
self.trees_weight = None
self.trees_left_child = None
self.trees_right_child = None
self.trees_nodes_value = None
self.trees_nodes_feature = None
self._cache_scorer = dict()
if format == "QuickRank":
from rankeval.model import ProxyQuickRank
ProxyQuickRank.load(file_path, self)
elif format == "LightGBM":
from rankeval.model import ProxyLightGBM
ProxyLightGBM.load(file_path, self)
elif format == "XGBoost":
from rankeval.model import ProxyXGBoost
ProxyXGBoost.load(file_path, self)
elif format == "ScikitLearn":
from rankeval.model import ProxyScikitLearn
ProxyScikitLearn.load(file_path, self)
else:
raise TypeError("Model format %s not yet supported!" % format)
if n_trees is not None and n_trees < self.n_trees:
self._prune_model(n_trees)