def build_tree(self, data, active_inst, level=1):
"""Induce a tree from the given data
Returns:
root node (Node)"""
node_insts = data[active_inst]
if len(node_insts) < self.min_samples_leaf:
return None
if len(node_insts) < self.min_samples_split or \
self.max_depth is not None and level > self.max_depth:
node, branches, n_children = Node(None, None, None), None, 0
else:
node, branches, n_children = self._select_attr(node_insts)
mean, var = np.mean(node_insts.Y), np.var(node_insts.Y)
node.value = np.array([mean, 1 if np.isnan(var) else var])
node.subset = active_inst
if branches is not None:
node.children = [
self.build_tree(data, active_inst[branches == br], level + 1)
for br in range(n_children)]
return node
def build_tree(self, data, active_inst, level=1):
"""Induce a tree from the given data
Returns:
root node (Node)"""
node_insts = data[active_inst]
if len(node_insts) < self.min_samples_leaf:
return None
if len(node_insts) < self.min_samples_split or \
self.max_depth is not None and level > self.max_depth:
node, branches, n_children = Node(None, None, None), None, 0
else:
node, branches, n_children = self._select_attr(node_insts)
mean, var = np.mean(node_insts.Y), np.var(node_insts.Y)
node.value = np.array([mean, 1 if np.isnan(var) else var])
node.subset = active_inst
if branches is not None:
node.children = [
self.build_tree(data, active_inst[branches == br], level + 1)
for br in range(n_children)]
return node
def _build_tree(self, data, active_inst, level=1):
"""Induce a tree from the given data
Returns:
root node (Node)"""
node_insts = data[active_inst]
distr = distribution.Discrete(node_insts, data.domain.class_var)
if len(node_insts) < self.min_samples_leaf:
return None
if len(node_insts) < self.min_samples_split or \
max(distr) >= sum(distr) * self.sufficient_majority or \
self.max_depth is not None and level > self.max_depth:
node, branches, n_children = Node(None, None, distr), None, 0
else:
node, branches, n_children = self._select_attr(node_insts)
node.subset = active_inst
if branches is not None:
node.children = [
self._build_tree(data, active_inst[branches == br], level + 1)
for br in range(n_children)]
return node
def build_tree(self, data, active_inst, level=1):
"""Induce a tree from the given data
Returns:
root node (Node)"""
node_insts = data[active_inst]
distr = distribution.Discrete(node_insts, data.domain.class_var)
if len(node_insts) < self.min_samples_leaf:
return None
if len(node_insts) < self.min_samples_split or \
max(distr) >= sum(distr) * self.sufficient_majority or \
self.max_depth is not None and level > self.max_depth:
node, branches, n_children = Node(None, None, distr), None, 0
else:
node, branches, n_children = self._select_attr(node_insts)
node.subset = active_inst
if branches is not None:
node.children = [
self.build_tree(data, active_inst[branches == br], level + 1)
for br in range(n_children)]
return node