在pyspark中根据复杂条件创建列

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

# 创建SparkSession
spark = SparkSession.builder.getOrCreate()

# 创建示例数据
data = [("Alice", 25), ("Bob", 30), ("Charlie", 35)]
df = spark.createDataFrame(data, ["name", "age"])

# 使用when和otherwise创建新列
df = df.withColumn("category", when(df.age < 30, "Young").otherwise("Old"))

# 显示结果
df.show()

+-------+---+--------+
|   name|age|category|
+-------+---+--------+
|  Alice| 25|   Young|
|    Bob| 30|     Old|
|Charlie| 35|     Old|
+-------+---+--------+