Python中处理树状分类数据的常见方法详解

# 示例：简单的生物分类树
tree = {
    "动物界": {
        "脊索动物门": {
            "哺乳纲": ["人类", "狗", "猫"],
            "鸟纲": ["鹰", "鸽子"]
        },
        "节肢动物门": {
            "昆虫纲": ["蚂蚁", "蝴蝶"],
            "蛛形纲": ["蜘蛛"]
        }
    }
}

# 访问数据
print(tree["动物界"]["脊索动物门"]["哺乳纲"])  # 输出: ['人类', '狗', '猫']

class TreeNode:
    def __init__(self, name, children=None):
        self.name = name
        self.children = children if children is not None else []
    
    def add_child(self, child_node):
        self.children.append(child_node)
    
    def traverse(self, level=0):
        print('  ' * level + self.name)
        for child in self.children:
            child.traverse(level + 1)

# 构建树
root = TreeNode("动物界")
chordata = TreeNode("脊索动物门")
mammalia = TreeNode("哺乳纲")
mammalia.add_child(TreeNode("人类"))
mammalia.add_child(TreeNode("狗"))
chordata.add_child(mammalia)
root.add_child(chordata)

# 遍历树
root.traverse()

from anytree import Node, RenderTree

# 创建节点
root = Node("动物界")
chordata = Node("脊索动物门", parent=root)
mammalia = Node("哺乳纲", parent=chordata)
human = Node("人类", parent=mammalia)
dog = Node("狗", parent=mammalia)

# 打印树结构
for pre, fill, node in RenderTree(root):
    print(f"{pre}{node.name}")

# 查找节点
from anytree import find
found = find(root, lambda node: node.name == "狗")
print(found.path)  # 输出: [Node('/动物界'), Node('/动物界/脊索动物门'), Node('/动物界/脊索动物门/哺乳纲'), Node('/动物界/脊索动物门/哺乳纲/狗')]

from treelib import Node, Tree

# 创建树
tree = Tree()
tree.create_node("动物界", "animal")  # 根节点
tree.create_node("脊索动物门", "chordata", parent="animal")
tree.create_node("哺乳纲", "mammalia", parent="chordata")
tree.create_node("人类", "human", parent="mammalia")
tree.create_node("狗", "dog", parent="mammalia")

# 显示树
tree.show()

# 搜索节点
node = tree.get_node("dog")
print(node.tag)  # 输出: 狗

import pandas as pd

# 创建多级索引的DataFrame
index = pd.MultiIndex.from_tuples([
    ('动物界', '脊索动物门', '哺乳纲', '人类'),
    ('动物界', '脊索动物门', '哺乳纲', '狗'),
    ('动物界', '脊索动物门', '鸟纲', '鹰'),
    ('植物界', '被子植物门', '双子叶植物纲', '玫瑰')
], names=['界', '门', '纲', '种'])

df = pd.DataFrame({'特征': ['智能', '忠诚', '飞翔', '美丽']}, index=index)

# 选择数据
print(df.loc['动物界'])  # 选择所有动物
print(df.loc[('动物界', '脊索动物门')])  # 选择脊索动物

from anytree import Node, RenderTree, search

# 构建组织架构树
company = Node("科技公司")
rd = Node("研发部", parent=company)
ai = Node("AI团队", parent=rd)
ml = Node("机器学习组", parent=ai)
dl = Node("深度学习组", parent=ai)

market = Node("市场部", parent=company)
digital = Node("数字营销组", parent=market)

# 添加员工
Node("张三", parent=ml)
Node("李四", parent=ml)
Node("王五", parent=dl)
Node("赵六", parent=digital)

# 查找所有AI团队成员
ai_team = search.findall(company, lambda node: "AI团队" in node.path and node.parent == ai)
print([node.name for node in ai_team])  # 输出: ['张三', '李四', '王五']

# 打印整个组织架构
for pre, fill, node in RenderTree(company):
    print(f"{pre}{node.name}")