数据统计
import org.apache.spark.SparkConf
import org.apache.spark.streaming.{Seconds, StreamingContext}
/**
* Spark Streaming 处理Socket数据
* 采用nc测试
*/
object NetworkWordCount {
def main(args: Array[String]): Unit = {
val sparkConf = new SparkConf().setMaster("local[2]").setAppName("NetworkWordCount")
/**
* 创建需要StreamingContext需要两个参数:SparkConf和batch interaal
*/
val ssc = new StreamingContext(sparkConf,Seconds(5))
val lines = ssc.socketTextStream("192.168.25.131",6789)
val result = lines.flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_)
result.print()
ssc.start()
ssc.awaitTermination()
}
}
测试:
实时统计: