def __build_tree(self, X, y, n_features, feature_indices, depth):
node_data_set = np.column_stack((X, y))
sample_size = len(y)
if len(y) <= self.min_samples_split or (depth != None
and depth == self.max_depth):
estimated_value = np.mean(y) #
leaf = Leaf(estimated_value=estimated_value,
sample_size=sample_size,
leaf_data_set=node_data_set)
return leaf
#寻找分裂属性和最优分裂点
best_feature_index, threshold, min_mes = find_split(
X, y, self.criterion, feature_indices)
X_true, y_true, X_false, y_false = split(X, y, best_feature_index,
threshold) # 分成左子树和右子树
node = Node(feature_index=best_feature_index,
threshold=threshold,
min_mes=min_mes,
sample_size=sample_size,
node_data_set=node_data_set)
# # 随机的选特征
feature_indices = random.sample(range(n_features),
int(self.max_features))
## 递归的创建左子树
node.branch_true = self.__build_tree(X_true, y_true, n_features,
feature_indices, depth + 1)
## 随机的选特征
feature_indices = random.sample(range(n_features),
int(self.max_features))
node.branch_false = self.__build_tree(X_false, y_false, n_features,
feature_indices, depth + 1)
return node
def build_tree(self, X, y, feature_indices,fa_feature_index,select_feature_fa, father_node,depth):
"""
建立决策树
X :
y：
feature_indices：随机选择的特征集合
fa_feature_index：父节点选择的哪个特征作为分裂特征，、初始时为-1，
depth ：树的深度
select_feature_fa ：记录当前节点的父节点的最优分割属性
"""
select_feature_fa.append(fa_feature_index)
n_features = X.shape[1]
n_features_list = [i for i in range(n_features)]
#记录选择的特征
self.select_feature.append(feature_indices)
self.sample_num.append(len(y))
node_data_set = np.column_stack((X, y))
# 树终止条件
if self.criterion == 'entropy':
if depth is self.max_depth or len(y) < self.min_samples_split or entropy(y) is 0:
return mode(y)[0][0]# 返回y数组的众数
# 树终止条件
if self.criterion == 'gini':
temp_gini = gini(y)
self.gini_.append(temp_gini)
sample_num = len(y)
if depth is self.max_depth or sample_num < self.min_samples_split or temp_gini < self.min_impurity_split:
# if depth is self.max_depth or temp_gini < self.min_impurity_split:
#所有的特征都已经被选择了，就随机选择一个特征，使得叶子节点构成双特征
if set(n_features_list) == set(select_feature_fa):
index = random.randrange(len(n_features_list))
current_feature_index = n_features_list[index]
current_max_value = np.max(X[:, current_feature_index])
current_min_value = np.min(X[:, current_feature_index])
else:
to_be_select = list(set(n_features_list) - set(select_feature_fa))
index = random.randrange(len(to_be_select))
current_feature_index = to_be_select[index]
current_max_value = np.max(X[:, current_feature_index])
current_min_value = np.min(X[:, current_feature_index])
leaf = Leaf(mode(y)[0][0],fa_feature_index , np.max(X[:,fa_feature_index]),
np.min(X[:,fa_feature_index]),current_feature_index,current_max_value,
current_min_value,select_feature_fa,node_data_set,sample_num,prior_node= father_node)
self.leaf_list.append(leaf)
return leaf
# feature_index最佳分割属性， threshold 最佳分割属性值,gini_ 系数
feature_index, threshold, max_value ,min_value ,gini_ = find_split(X, y, self.criterion, feature_indices)
fa_max_value = np.max(X[:, fa_feature_index]) # 该节点记录父节点分裂特征的最大值
fa_min_value = np.min(X[:, fa_feature_index]) # 该节点记录父节点分裂特征的最小值
X_true, y_true, X_false, y_false = split(X, y, feature_index, threshold)# 分成左子树和右子树
# 没有元素
if y_true.shape[0] is 0 or y_false.shape[0] is 0:
if set(n_features_list) == set(select_feature_fa):
index = random.randrange(len(n_features_list))
current_feature_index = n_features_list[index]
current_max_value = np.max(X[:, current_feature_index])
current_min_value = np.min(X[:, current_feature_index])
else:
to_be_select = list(set(n_features_list) - set(select_feature_fa))
index = random.randrange(len(to_be_select))
current_feature_index = to_be_select[index]
current_max_value = np.max(X[:, current_feature_index])
current_min_value = np.min(X[:, current_feature_index])
leaf = Leaf(mode(y)[0][0], fa_feature_index, np.max(X[:, fa_feature_index]), np.min(X[:, fa_feature_index]),
current_feature_index,current_max_value,current_min_value,select_feature_fa,node_data_set,prior_node= father_node,sample_num= 0)
self.leaf_list.append(leaf)
return leaf
node = Node(feature_index=feature_index,
fa_feature_index = fa_feature_index,
threshold = threshold, max_value = max_value, min_value = min_value,
fa_max_value = fa_max_value, fa_min_value = fa_min_value,
gini_coefficient = gini_,
node_data_set = node_data_set)
# # 随机的选特征
n_features = X.shape[1]
n_sub_features = int(self.max_features)
#
feature_indices = random.sample(range(n_features), n_sub_features)
select_feature = list()
select_feature += select_feature_fa # 记录节点选择的特征
## 递归的创建左子树
node.branch_true = self.build_tree(X_true, y_true, feature_indices,feature_index,
select_feature,node,depth + 1)
## 随机的选特征
feature_indices = random.sample(range(n_features), n_sub_features)
# 递归的创建右子树
select_feature = list()
select_feature += select_feature_fa # 记录节点选择的特征
node.branch_false = self.build_tree(X_false, y_false, feature_indices,feature_index,
select_feature,node,depth + 1)
node.prior_node = father_node #指向前驱节点
return node