Pyspark中的多个WHEN条件实现

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

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

# 创建示例数据
data = [("John", 25), ("Alice", 30), ("Mike", 35)]
df = spark.createDataFrame(data, ["Name", "Age"])

# 添加一个新的列根据不同的条件逻辑进行处理
df = df.withColumn("Category", 
                   when(df.Age < 30, "Young")
                   .when(df.Age >= 30, "Adult")
                   .otherwise("Unknown"))

# 显示结果
df.show()