def __refresh_statistics(self):
'''
Recalculates the statistics for this rule.
'''
self.coverage = self.covered_examples.count()
indices = self.kb.bits_to_indices(self.covered_examples)
ex_scores = [self.kb.get_score(idx) for idx in indices]
if self.target_type == Example.Ranked:
self.mean = avg(ex_scores)
self.sd = std(ex_scores)
self.score = self.kb.score_fun(self)
else:
self.distribution = defaultdict(int)
for score in ex_scores:
self.distribution[score] += 1
self.score = self.kb.score_fun(self)
def __refresh_statistics(self):
'''
Recalculates the statistics for this rule.
'''
self.coverage = self.covered_examples.count()
indices = self.kb.bits_to_indices(self.covered_examples)
ex_scores = [self.kb.get_score(idx) for idx in indices]
if self.target_type == Example.Ranked:
self.mean = avg(ex_scores)
self.sd = std(ex_scores)
self.score = self.kb.score_fun(self)
else:
self.distribution = defaultdict(int)
for score in ex_scores:
self.distribution[score] += 1
self.score = self.kb.score_fun(self)
def __init__(self, triplets, score_fun, instances_as_leaves=True):
'''
Initialize the knowledge base with the given triplet graph.
The target class is given with 'target_class' - this is the
class to be described in the induction step.
'''
self.instances_as_leaves = instances_as_leaves
self.score_fun = score_fun
self.sub_class_of = defaultdict(list)
self.super_class_of = defaultdict(list)
self.predicates = set()
self.binary_predicates = set()
self.class_values = set()
self.annotation_name = defaultdict(list)
self.examples, all_annotations = self._build_examples(triplets)
# Ranked or class-labeled data
self.target_type = self.examples[0].target_type
self._build_subclassof(triplets)
self._calc_predicate_members(triplets)
self._find_roots(all_annotations)
self._calc_members_closure()
self._calc_binary_members()
self._propagate_annotation_names(triplets)
# Statistics
if self.target_type == Example.Ranked:
self.mean = avg([ex.score for ex in self.examples])
self.sd = std([ex.score for ex in self.examples])
else:
self.distribution = defaultdict(int)
for ex in self.examples:
self.distribution[ex.score] += 1
logger.debug('Class distribution: %s' % str(self.distribution))
def __init__(self, triplets, score_fun, instances_as_leaves=True):
"""
Initialize the knowledge base with the given triplet graph.
The target class is given with 'target_class' - this is the
class to be described in the induction step.
"""
self.instances_as_leaves = instances_as_leaves
self.score_fun = score_fun
self.sub_class_of = defaultdict(list)
self.super_class_of = defaultdict(list)
self.predicates = set()
self.binary_predicates = set()
self.class_values = set()
self.annotation_name = defaultdict(list)
self.examples, all_annotations = self._build_examples(triplets)
# Ranked or class-labeled data
self.target_type = self.examples[0].target_type
self._build_subclassof(triplets)
self._calc_predicate_members(triplets)
self._find_roots(all_annotations)
self._calc_members_closure()
self._calc_binary_members()
self._propagate_annotation_names(triplets)
# Statistics
if self.target_type == Example.Ranked:
self.mean = avg([ex.score for ex in self.examples])
self.sd = std([ex.score for ex in self.examples])
else:
self.distribution = defaultdict(int)
for ex in self.examples:
self.distribution[ex.score] += 1
logger.debug("Class distribution: %s" % str(self.distribution))