野兽

benchmark2("hllc")(10000000)(hcclcodeanddecode2) benchmark("hllc")(10000000)(hcclcodeanddecode) def hcclcodeanddecode() :Unit = { val hllc = new HLLCounter(14) hllc.add("ads...

package hllctestimport java.utilimport org.scalatest.{FlatSpec}import org.spark.sqludf.HLLCounterimport scala.collection.mutableimport scala.collection.mutable.ArrayBufferimport scal...

var udfNotInited = true override def newExecuteStatementOperation( parentSession: HiveSession, statement: String, confOverlay: JMap[String, String], async: Boolean...

window 下通过 source 读文件各种鬼 改用 BufferedReader用于删除文件中中文 object ChineseDrop extends App { // val stArray = Array("胜多负少","abadsf","13123123") // stArray.foreach( word => println(s" $...

--master yarn --deploy-mode client --num-executors 4 --executor-memory 6g --executor-cores 3 --conf spark.default.parallelism=40 --conf spark.sql.shuffle.partitions=20

object FunnelUtil { var gson: Gson = new GsonBuilder().create val maxFunnelLength = 10 var beginTimestamp = 0 var eventLength = 0 var eventMap : mutable.HashMap[Short,Byte] = null ...

object DataProcess extends App { val spark = SparkSession .builder() .appName("UserBehiviorToHHDataPartition") .getOrCreate() val dataCollection = spark.sparkContext.textFile("....

maven-compiler-plugin 1.8 1.8 UTF-8 ...

val THREAD_POOL_SIZE = 10 val THREAD_POOL = Executors.newScheduledThreadPool(THREAD_POOL_SIZE);THREAD_POOL.scheduleWithFixedDelay(new Runnable() { def run() { otsQueueProcess ...

val gson: Gson = new GsonBuilder().create def jsonToMap(jsonstring: String): java.util.Map[String, String] = { val typeOfHashMap: Type = new TypeToken[java.util.Map[String, String]]() { ...

结论： testHllcError(10, tt) 31 开始出现误差 testHllcError(11, tt) 33 开始出现误差 testHllcError(13, tt) 42 开始出现误差 testHllcError(14, tt) 100 开始出现误差package hllctesti...