多个列上的pyspark条件并返回新列

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

# 创建SparkSession
spark = SparkSession.builder.appName("Multiple Column Conditions").getOrCreate()

# 创建示例数据
data = [("Alice", 25, "F"),
        ("Bob", 30, "M"),
        ("Charlie", 35, "M"),
        ("Diana", 40, "F")]

df = spark.createDataFrame(data, ["name", "age", "gender"])

# 应用条件并返回新列
df = df.withColumn("age_group", when(col("age") < 30, "Young")
                               .when(col("age") >= 30, "Adult")
                               .otherwise("Unknown"))

# 显示结果
df.show()