将SQL schema分配给Spark DataFrame

import org.apache.spark.sql.{SparkSession, Row}
import org.apache.spark.sql.types.{StructType, StructField, StringType, IntegerType}

// 创建SparkSession
val spark = SparkSession.builder()
  .appName("SQL Schema Assignment")
  .master("local")
  .getOrCreate()

// 定义SQL schema
val schema = StructType(Seq(
  StructField("id", IntegerType, nullable = false),
  StructField("name", StringType, nullable = false),
  StructField("age", IntegerType, nullable = false)
))

// 创建DataFrame
val data = Seq(
  Row(1, "Alice", 25),
  Row(2, "Bob", 30),
  Row(3, "Charlie", 35)
)

val df = spark.createDataFrame(spark.sparkContext.parallelize(data), schema)

// 将DataFrame注册为临时表
df.createOrReplaceTempView("people")

// 执行SQL查询
val result = spark.sql("SELECT * FROM people WHERE age > 30")

// 显示查询结果
result.show()