def __prun_tree(self, cur_node):
'''剪枝'''
if len(cur_node.childNode) == 0: #叶子节点直接跳过
return
else:
cur_node.cls = get_cls_from_data(cur_node.dataset)
cur_err_sum = get_err_sum(cur_node.cls, cur_node.dataset) + 0.5
leaf_err_set = []
self.leaf_err_sum(cur_node, leaf_err_set)
leaf_e_sum = sum(leaf_err_set) + 0.5 * len(leaf_err_set)
leaf_err_ratio = leaf_e_sum / len(cur_node.dataset)
std_dev = np.sqrt(leaf_err_ratio * (1 - leaf_err_ratio))
if leaf_e_sum + std_dev > cur_err_sum:
print leaf_e_sum + std_dev, cur_err_sum, " prun!!!!"
cur_node.childNode = {}
cur_node.cls = get_cls_from_data(cur_node.dataset)
else:
for _, c in cur_node.childNode.items():
self.__prun_tree(c)
def __prun_tree(self, cur_node):
'''剪枝'''
if len(cur_node.childNode) == 0: #叶子节点直接跳过
return
else:
cur_node.cls = get_cls_from_data(cur_node.dataset)
cur_err_sum = get_err_sum(cur_node.cls, cur_node.dataset) + 0.5
leaf_err_set = []
self.leaf_err_sum(cur_node, leaf_err_set)
leaf_e_sum = sum(leaf_err_set) + 0.5 * len(leaf_err_set)
leaf_err_ratio = leaf_e_sum / len(cur_node.dataset)
std_dev = np.sqrt(leaf_err_ratio * (1 - leaf_err_ratio))
if leaf_e_sum + std_dev > cur_err_sum:
print leaf_e_sum + std_dev, cur_err_sum, " prun!!!!"
cur_node.childNode = {}
cur_node.cls = get_cls_from_data(cur_node.dataset)
else:
for _, c in cur_node.childNode.items():
self.__prun_tree(c)
def __construct_tree(self, cur_node, attr_list):
'''
递归构建决策树
'''
data = cur_node.dataset
data_classified = {}
max_gain_ratio, index = sys.float_info.min, -1
num_border = 0.0
for idx in attr_list:
if idx in self.disc_type: #离散属性
gain_r = self.disc_gain_rt(idx, data)
else: #数值属性
gain_r, num_border = self.num_gain_rt(idx,data)
if gain_r > max_gain_ratio:
max_gain_ratio = gain_r
index = idx
if index == -1: #所有属性都不能满足条件
cur_node.cls = get_cls_from_data(data)
return
cur_node.attr_index = index
if index in self.disc_type: #离散属性
cur_node.attr_type = 1
#对数据进行分类
for val in self.disc_type[index]:
data_classified[val] = []
for d in data:
data_classified[d[index]].append(d)
else: #连续属性
cur_node.attr_type = 0
cur_node.demark = num_border
data_classified[0] = []
data_classified[1] = []
for d in data:
if d[index] < num_border:
data_classified[0].append(d)
else:
data_classified[1].append(d)
if len(attr_list) == 1: #下一次递归属性集为空
for k, v in data_classified.items():
child_node = TreeNode(v)
#属性值对应的数据集为空，则使用当前节点的数据集判断节点对应的分类
if len(v) == 0:
child_node.cls = get_cls_from_data(data)
else:
child_node.cls = get_cls_from_data(v)
cur_node.childNode[k] = child_node
else:
sub_attr = list(attr_list)
sub_attr.remove(index)
for k, v in data_classified.items():
child_node = TreeNode(v)
if len(v) == 0:
child_node.cls = get_cls_from_data(data)
elif check_purity(v) == 1:
child_node.cls = v[0][-1] #随便取一个sample的标签
else:
self.__construct_tree(child_node, sub_attr) #对子节点进行递归
cur_node.childNode[k] = child_node
def __construct_tree(self, cur_node, attr_list):
'''
递归构建决策树
'''
data = cur_node.dataset
data_classified = {}
max_gain_ratio, index = sys.float_info.min, -1
num_border = 0.0
for idx in attr_list:
if idx in self.disc_type: #离散属性
gain_r = self.disc_gain_rt(idx, data)
else: #数值属性
gain_r, num_border = self.num_gain_rt(idx, data)
if gain_r > max_gain_ratio:
max_gain_ratio = gain_r
index = idx
if index == -1: #所有属性都不能满足条件
cur_node.cls = get_cls_from_data(data)
return
cur_node.attr_index = index
if index in self.disc_type: #离散属性
cur_node.attr_type = 1
#对数据进行分类
for val in self.disc_type[index]:
data_classified[val] = []
for d in data:
data_classified[d[index]].append(d)
else: #连续属性
cur_node.attr_type = 0
cur_node.demark = num_border
data_classified[0] = []
data_classified[1] = []
for d in data:
if d[index] < num_border:
data_classified[0].append(d)
else:
data_classified[1].append(d)
if len(attr_list) == 1: #下一次递归属性集为空
for k, v in data_classified.items():
child_node = TreeNode(v)
#属性值对应的数据集为空，则使用当前节点的数据集判断节点对应的分类
if len(v) == 0:
child_node.cls = get_cls_from_data(data)
else:
child_node.cls = get_cls_from_data(v)
cur_node.childNode[k] = child_node
else:
sub_attr = list(attr_list)
sub_attr.remove(index)
for k, v in data_classified.items():
child_node = TreeNode(v)
if len(v) == 0:
child_node.cls = get_cls_from_data(data)
elif check_purity(v) == 1:
child_node.cls = v[0][-1] #随便取一个sample的标签
else:
self.__construct_tree(child_node, sub_attr) #对子节点进行递归
cur_node.childNode[k] = child_node
