使用Scala语言编程例程:
方式一:通过 case class 创建 DataFrames(反射)
//定义case class,相当于表结构
case class People(var name:String,var age:Int)
object TestDataFrame1 {
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("RDDToDataFrame").setMaster("local")
val sc = new SparkContext(conf)
val context = new SQLContext(sc)
// 将本地的数据读入 RDD, 并将 RDD 与 case class 关联
val peopleRDD = sc.textFile("E:\\666\\people.txt")
.map(line => People(line.split(",")(0), line.split(",")(1).trim.toInt))
import context.implicits._
// 将RDD 转换成 DataFrames
val df = peopleRDD.toDF
//将DataFrames创建成一个临时的视图
df.createOrReplaceTempView("people")
//使用SQL语句进行查询
context.sql("select * from people").show()
}
}
方式二:通过 structType 创建 DataFrames(编程接口)
object TestDataFrame2 {
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("TestDataFrame2").setMaster("local")
val sc = new SparkContext(conf)
val sqlContext = new SQLContext(sc)
val fileRDD = sc.textFile("E:\\666\\people.txt")
// 将 RDD 数据映射成 Row,需要 import org.apache.spark.sql.Row
val rowRDD: RDD[Row] = fileRDD.map(line => {
val fields = line.split(",")
Row(fields(0), fields(1).trim.toInt)
})
// 创建 StructType 来定义结构
val structType: StructType = StructType(
//字段名,字段类型,是否可以为空
StructField("name", StringType, true) ::
StructField("age", IntegerType, true) :: Nil
)
/**
* rows: java.util.List[Row],
* schema: StructType
* */
val df: DataFrame = sqlContext.createDataFrame(rowRDD,structType)
df.createOrReplaceTempView("people")
sqlContext.sql("select * from people").show()
}
}
方式三:通过 json 文件创建 DataFrames
object TestDataFrame3 {
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("TestDataFrame2").setMaster("local")
val sc = new SparkContext(conf)
val sqlContext = new SQLContext(sc)
val df: DataFrame = sqlContext.read.json("E:\\666\\people.json")
df.createOrReplaceTempView("people")
sqlContext.sql("select * from people").show()
}
}