将SQL Case语句转换为Spark

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

# 创建SparkSession
spark = SparkSession.builder.appName("SQL Case转换为Spark").getOrCreate()

# 创建示例数据
data = [("John", 25), ("Alice", 30), ("Bob", 20)]
df = spark.createDataFrame(data, ["name", "age"])

# 使用DataFrame API进行转换
df = df.withColumn("age_group", when(df.age < 25, "Young")
                            .when(df.age < 30, "Adult")
                            .otherwise("Old"))

# 显示结果
df.show()

from pyspark.sql import SparkSession

# 创建SparkSession
spark = SparkSession.builder.appName("SQL Case转换为Spark").getOrCreate()

# 创建示例数据
data = [("John", 25), ("Alice", 30), ("Bob", 20)]
df = spark.createDataFrame(data, ["name", "age"])
df.createOrReplaceTempView("people")

# 使用Spark SQL进行转换
sql_query = """
SELECT name, age,
    CASE
        WHEN age < 25 THEN 'Young'
        WHEN age < 30 THEN 'Adult'
        ELSE 'Old'
    END AS age_group
FROM people
"""
df = spark.sql(sql_query)

# 显示结果
df.show()