def _deactivate_learning_node(self, to_deactivate: ActiveLearningNode,
parent: SplitNode, parent_branch: int):
"""Deactivate a learning node.
Parameters
----------
to_deactivate: ActiveLearningNode
The node to deactivate.
parent: SplitNode
The node's parent.
parent_branch: int
Parent node's branch index.
"""
if self.leaf_prediction == _TARGET_MEAN:
new_leaf = InactiveLearningNodeForRegression(
to_deactivate.get_observed_class_distribution())
else:
new_leaf = InactiveLearningNodePerceptron(
to_deactivate.get_observed_class_distribution(),
to_deactivate.perceptron_weight)
if parent is None:
self._tree_root = new_leaf
else:
parent.set_child(parent_branch, new_leaf)
self._active_leaf_node_cnt -= 1
self._inactive_leaf_node_cnt += 1
def _deactivate_learning_node(self, to_deactivate: ActiveLearningNode,
parent: SplitNode, parent_branch: int):
"""Deactivate a learning node.
Parameters
----------
to_deactivate: ActiveLearningNode
The node to deactivate.
parent: SplitNode
The node's parent.
parent_branch: int
Parent node's branch index.
"""
if self.leaf_prediction == _TARGET_MEAN:
new_leaf = InactiveLearningNodeForRegression(
to_deactivate.get_observed_class_distribution())
elif self.leaf_prediction == _PERCEPTRON:
new_leaf = InactiveLearningNodePerceptronMultiTarget(
to_deactivate.get_observed_class_distribution(),
to_deactivate.perceptron_weight, to_deactivate.random_state)
elif self.leaf_prediction == _ADAPTIVE:
new_leaf = InactiveLearningNodeAdaptiveMultiTarget(
to_deactivate.get_observed_class_distribution(),
to_deactivate.perceptron_weight, to_deactivate.random_state)
new_leaf.fMAE_M = to_deactivate.fMAE_M
new_leaf.fMAE_P = to_deactivate.fMAE_P
if parent is None:
self._tree_root = new_leaf
else:
parent.set_child(parent_branch, new_leaf)
self._active_leaf_node_cnt -= 1
self._inactive_leaf_node_cnt += 1
def _deactivate_learning_node(self, to_deactivate: ActiveLearningNode,
parent: SplitNode, parent_branch: int):
"""Deactivate a learning node.
Parameters
----------
to_deactivate: ActiveLearningNode
The node to deactivate.
parent: SplitNode
The node's parent.
parent_branch: int
Parent node's branch index.
"""
new_leaf = self._new_learning_node(
to_deactivate.get_observed_class_distribution(),
to_deactivate,
is_active_node=False)
if parent is None:
self._tree_root = new_leaf
else:
parent.set_child(parent_branch, new_leaf)
self._active_leaf_node_cnt -= 1
self._inactive_leaf_node_cnt += 1
def _attempt_to_split(self, node: ActiveLearningNode, parent: SplitNode,
parent_idx: int):
""" Attempt to split a node.
If the samples seen so far are not from the same class then:
1. Find split candidates and select the top 2.
2. Compute the Hoeffding bound.
3. If the difference between the top 2 split candidates is larger than the Hoeffding bound:
3.1 Replace the leaf node by a split node.
3.2 Add a new leaf node on each branch of the new split node.
3.3 Update tree's metrics
Optional: Disable poor attribute. Depends on the tree's configuration.
Parameters
----------
node: ActiveLearningNode
The node to evaluate.
parent: SplitNode
The node's parent.
parent_idx: int
Parent node's branch index.
"""
if not node.observed_class_distribution_is_pure():
if self._split_criterion == GINI_SPLIT:
split_criterion = GiniSplitCriterion()
elif self._split_criterion == INFO_GAIN_SPLIT:
split_criterion = InfoGainSplitCriterion()
elif self._split_criterion == HELLINGER:
split_criterion = HellingerDistanceCriterion()
else:
split_criterion = InfoGainSplitCriterion()
best_split_suggestions = node.get_best_split_suggestions(
split_criterion, self)
best_split_suggestions.sort(key=attrgetter('merit'))
should_split = False
if len(best_split_suggestions) < 2:
should_split = len(best_split_suggestions) > 0
else:
hoeffding_bound = self.compute_hoeffding_bound(
split_criterion.get_range_of_merit(
node.get_observed_class_distribution()),
self.split_confidence, node.get_weight_seen())
best_suggestion = best_split_suggestions[-1]
second_best_suggestion = best_split_suggestions[-2]
if (best_suggestion.merit - second_best_suggestion.merit >
hoeffding_bound or hoeffding_bound < self.tie_threshold
): # best_suggestion.merit > 1e-10 and \
should_split = True
if self.remove_poor_atts is not None and self.remove_poor_atts:
poor_atts = set()
# Scan 1 - add any poor attribute to set
for i in range(len(best_split_suggestions)):
if best_split_suggestions[i] is not None:
split_atts = best_split_suggestions[
i].split_test.get_atts_test_depends_on()
if len(split_atts) == 1:
if best_suggestion.merit - best_split_suggestions[
i].merit > hoeffding_bound:
poor_atts.add(int(split_atts[0]))
# Scan 2 - remove good attributes from set
for i in range(len(best_split_suggestions)):
if best_split_suggestions[i] is not None:
split_atts = best_split_suggestions[
i].split_test.get_atts_test_depends_on()
if len(split_atts) == 1:
if best_suggestion.merit - best_split_suggestions[
i].merit < hoeffding_bound:
poor_atts.remove(int(split_atts[0]))
for poor_att in poor_atts:
node.disable_attribute(poor_att)
if should_split:
split_decision = best_split_suggestions[-1]
if split_decision.split_test is None:
# Preprune - null wins
self._deactivate_learning_node(node, parent, parent_idx)
else:
new_split = self.new_split_node(
split_decision.split_test,
node.get_observed_class_distribution())
for i in range(split_decision.num_splits()):
new_child = self._new_learning_node(
split_decision.
resulting_class_distribution_from_split(i))
new_split.set_child(i, new_child)
self._active_leaf_node_cnt -= 1
self._decision_node_cnt += 1
self._active_leaf_node_cnt += split_decision.num_splits()
if parent is None:
self._tree_root = new_split
else:
parent.set_child(parent_idx, new_split)
# Manage memory
self.enforce_tracker_limit()