根据条件pyspark计算不同的列值

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, "F"), ("Bob", 30, "M"), ("Charlie", 35, "M")]
df = spark.createDataFrame(data, ["name", "age", "gender"])

# 根据条件计算新列值
df = df.withColumn("category", when(df.age < 30, "Young").otherwise("Old"))

# 显示结果
df.show()

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