如何在pyspark或python中建立父子关系？

from pyspark.sql import SparkSession
from pyspark.sql.functions import col, when

# 初始化SparkSession
spark = SparkSession.builder.appName("ParentChildExample").getOrCreate()

# 创建示例数据
data = [
    (1, None, "Root"),
    (2, 1, "Child1"),
    (3, 1, "Child2"),
    (4, 2, "GrandChild1"),
    (5, 3, "GrandChild2")
]

columns = ["id", "parent_id", "name"]

# 创建DataFrame
df = spark.createDataFrame(data, columns)

# 显示原始数据
df.show()

# 添加一个列来表示层级关系
df = df.withColumn("level", when(col("parent_id").isNull(), 0).otherwise(1 + col("parent_id")))

# 显示带有层级关系的数据
df.show()

class Node:
    def __init__(self, name, parent=None):
        self.name = name
        self.parent = parent
        self.children = []

    def add_child(self, child):
        self.children.append(child)
        child.parent = self

# 创建节点
root = Node("Root")
child1 = Node("Child1")
child2 = Node("Child2")
grandchild1 = Node("GrandChild1")

# 建立父子关系
root.add_child(child1)
root.add_child(child2)
child1.add_child(grandchild1)

# 打印层次结构
def print_hierarchy(node, level=0):
    print("  " * level + node.name)
    for child in node.children:
        print_hierarchy(child, level + 1)

print_hierarchy(root)