从spark数据帧中的列生成不同的值

from pyspark.sql import SparkSession
from pyspark.sql.functions import col, lit, 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"])

# 从列生成不同的值
df_new = df.select("name", "age", when(col("age") < 30, lit("Young")).otherwise(lit("Old")).alias("age_group"))

# 查看生成的结果
df_new.show()