object MaxTemp { System.setProperty("hadoop.home.dir","D:\\hadoop\\hadoop-2.9.2") def main(args: Array[String]): Unit = { val conf = new SparkConf().setMaster("local").setAppName("TopN") val sc = new SparkContext(conf) val lines = sc.textFile(args(0)) lines.map(line => { val year = line.split("\t")(0).substring(0,4) (year,line) }).groupByKey() .map(tuple => { val list = tuple._2 var maxTemp = Double.MinValue var day = "" for (valueStr <- list){ if (valueStr.split("\t")(1).toDouble > maxTemp){ maxTemp = valueStr.split("\t")(1).toDouble day = valueStr.split("\t")(0) } } (tuple._1,maxTemp+" "+day) }).foreach(println(_)) sc.stop() } }
spark的最高气温
最新推荐文章于 2020-08-19 14:01:43 发布