191、Spark 2.0之Dataset开发详解-typed操

except：获取在当前dataset中有，但是在另外一个dataset中没有的元素
filter：根据我们自己的逻辑，如果返回true，那么就保留该元素，否则就过滤掉该元素
intersect：获取两个数据集的交集

代码

object TypedOperation {

  case class Employee(name: String, age: Long, depId: Long, gender: String, salary: Long)

  def main(args: Array[String]): Unit = {
    val sparkSession = SparkSession
      .builder()
      .appName("BasicOperation")
      .master("local")
      .getOrCreate()

    import sparkSession.implicits._
    import org.apache.spark.sql.functions._

    val employeePath = this.getClass.getClassLoader.getResource("employee.json").getPath
    val employee2Path = this.getClass.getClassLoader.getResource("employee2.json").getPath

    val employeeDF = sparkSession.read.json(employeePath)
    val employee2DF = sparkSession.read.json(employee2Path)

    val employeeDS = employeeDF.as[Employee]
    val employee2DS = employee2DF.as[Employee]

    employeeDS.except(employee2DS).show()

    employeeDS.filter(employee => employee.age > 30).show()

    employeeDS.intersect(employee2DS).show()

  }
}