def __init__(self, tree, fields, objective_field=None):
self.fields = fields
self.objective_id = objective_field
self.output = tree['output']
if tree['predicate'] is True:
self.predicate = True
else:
self.predicate = Predicate(tree['predicate']['operator'],
tree['predicate']['field'],
tree['predicate']['value'],
tree['predicate'].get('term', None))
self.id = tree.get('id')
children = []
if 'children' in tree:
for child in tree['children']:
children.append(self.__class__( \
child,
self.fields,
objective_field=objective_field))
self.children = children
self.count = tree['count']
self.g_sum = tree.get('g_sum')
self.h_sum = tree.get('h_sum')
def __init__(self, predicates_list):
self.predicates = []
for predicate in predicates_list:
if predicate == True:
self.predicates.append(True)
else:
self.predicates.append(
Predicate(predicate.get('op'), predicate.get('field'),
predicate.get('value'), predicate.get('term')))
def __init__(self, tree, offsets):
predicate = get_predicate(tree)
if isinstance(predicate, bool):
self.predicate = predicate
else:
[operator, field, value, term, _] = predicate
self.predicate = Predicate(INVERSE_OP[operator], field, value,
term)
node = get_node(tree)
for attr in offsets:
if attr not in ["children#", "children"]:
setattr(self, attr, node[offsets[attr]])
children = [] if node[offsets["children#"]] == 0 else \
node[offsets["children"]]
setattr(self, "children", children)
def __init__(self, tree, fields, objective_field=None):
self.fields = fields
self.objective_field = objective_field
self.output = tree['output']
if tree['predicate'] is True:
self.predicate = True
else:
self.predicate = Predicate(tree['predicate']['operator'],
tree['predicate']['field'],
tree['predicate']['value'],
tree['predicate'].get('term', None))
children = []
if 'children' in tree:
for child in tree['children']:
children.append(Tree(child, self.fields, objective_field))
self.children = children
self.count = tree['count']
self.confidence = tree.get('confidence', None)
if 'distribution' in tree:
self.distribution = tree['distribution']
elif ('objective_summary' in tree):
summary = tree['objective_summary']
if 'bins' in summary:
self.distribution = summary['bins']
elif 'counts' in summary:
self.distribution = summary['counts']
elif 'categories' in summary:
self.distribution = summary['categories']
else:
summary = self.fields[self.objective_field]['summary']
if 'bins' in summary:
self.distribution = summary['bins']
elif 'counts' in summary:
self.distribution = summary['counts']
elif 'categories' in summary:
self.distribution = summary['categories']
def depth_first_search(tree, path):
"""Search for leafs' values and instances
"""
node = get_node(tree)
predicate = get_predicate(tree)
if isinstance(predicate, list):
[operation, field, value, term, _] = predicate
operator = INVERSE_OP[operation]
path.append(Predicate(operator, field, value, term))
if term:
if field not in model.terms:
model.terms[field] = []
if term not in model.terms[field]:
model.terms[field].append(term)
if node[offsets["children#"]] == 0:
add_to_groups(
groups, node[offsets["output"]], path, node[offsets["count"]],
node[offsets["confidence"]],
gini_impurity(node[offsets["distribution"]],
node[offsets["count"]]))
return node[offsets["count"]]
children = node[offsets["children"]][:]
children.reverse()
children_sum = 0
for child in children:
children_sum += depth_first_search(child, path[:])
if children_sum < node[offsets["count"]]:
add_to_groups(
groups, node[offsets["output"]], path,
node[offsets["count"]] - children_sum,
node[offsets["confidence"]],
gini_impurity(node[offsets["distribution"]],
node[offsets["count"]]))
return node[offsets["count"]]
def __init__(self,
tree,
fields,
objective_field=None,
root_distribution=None,
parent_id=None,
ids_map=None,
subtree=True):
self.fields = fields
self.objective_id = objective_field
self.output = tree['output']
if tree['predicate'] is True:
self.predicate = True
else:
self.predicate = Predicate(tree['predicate']['operator'],
tree['predicate']['field'],
tree['predicate']['value'],
tree['predicate'].get('term', None))
if 'id' in tree:
self.id = tree['id']
self.parent_id = parent_id
if isinstance(ids_map, dict):
ids_map[self.id] = self
else:
self.id = None
children = []
if 'children' in tree:
for child in tree['children']:
children.append(
Tree(child,
self.fields,
objective_field=objective_field,
parent_id=self.id,
ids_map=ids_map,
subtree=subtree))
self.children = children
self.regression = self.is_regression()
self.count = tree['count']
self.confidence = tree.get('confidence', None)
if 'distribution' in tree:
self.distribution = tree['distribution']
elif 'objective_summary' in tree:
summary = tree['objective_summary']
if 'bins' in summary:
self.distribution = summary['bins']
elif 'counts' in summary:
self.distribution = summary['counts']
elif 'categories' in summary:
self.distribution = summary['categories']
else:
summary = root_distribution
if 'bins' in summary:
self.distribution = summary['bins']
elif 'counts' in summary:
self.distribution = summary['counts']
elif 'categories' in summary:
self.distribution = summary['categories']
def __init__(self,
tree,
fields,
objective_field=None,
root_distribution=None,
parent_id=None,
ids_map=None,
subtree=True,
tree_info=None):
self.fields = fields
self.objective_id = objective_field
self.output = tree['output']
if tree['predicate'] is True:
self.predicate = True
else:
self.predicate = Predicate(tree['predicate']['operator'],
tree['predicate']['field'],
tree['predicate']['value'],
tree['predicate'].get('term', None))
if 'id' in tree:
self.id = tree['id']
self.parent_id = parent_id
if isinstance(ids_map, dict):
ids_map[self.id] = self
else:
self.id = None
children = []
if 'children' in tree:
for child in tree['children']:
children.append(self.__class__( \
child,
self.fields,
objective_field=objective_field,
parent_id=self.id,
ids_map=ids_map,
subtree=subtree,
tree_info=tree_info))
self.children = children
self.regression = self.is_regression()
tree_info['regression'] = (self.regression
and tree_info.get('regression', True))
self.count = tree['count']
self.confidence = tree.get('confidence', None)
self.distribution = None
self.max = None
self.min = None
self.weighted = False
summary = None
if 'distribution' in tree:
self.distribution = tree['distribution']
elif 'objective_summary' in tree:
summary = tree['objective_summary']
(self.distribution_unit,
self.distribution) = extract_distribution(summary)
if 'weighted_objective_summary' in tree:
summary = tree['weighted_objective_summary']
(self.weighted_distribution_unit,
self.weighted_distribution) = extract_distribution(summary)
self.weight = tree['weight']
self.weighted = True
else:
summary = root_distribution
(self.distribution_unit,
self.distribution) = extract_distribution(summary)
if self.regression:
tree_info['max_bins'] = max(tree_info.get('max_bins', 0),
len(self.distribution))
self.median = None
if summary:
self.median = summary.get('median')
if not self.median:
self.median = dist_median(self.distribution, self.count)
self.max = summary.get('maximum') or \
max([value for [value, _] in self.distribution])
self.min = summary.get('minimum') or \
min([value for [value, _] in self.distribution])
self.impurity = None
if not self.regression and self.distribution is not None:
self.impurity = self.gini_impurity()
