ITPub博客

首页 > 大数据 > 数据分析 > spark lac 分析停留最长的两个地方

spark lac 分析停留最长的两个地方

原创 数据分析 作者:hgs19921112 时间:2018-10-11 23:27:09 0 删除 编辑
package hgs.spark.othertest
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
object FindTheTop2 {
  def main(args: Array[String]): Unit = {
    
    val conf = new  SparkConf().setAppName("FindTheTop2").setMaster("local[3]")
    val sc = new SparkContext(conf)
    val rdd1 = sc.textFile("D:\\bs_log")  
    //rdd_phone_lac_time:(18688888888 16030401EAFB68F1E3CDF819735E1C66,-20160327082400,1), (18611132889 16030401EAFB68F1E3CDF819735E1C66,-20160327082500,1)
    //先映射为上一行为例的map(K,V)
    val rdd_phone_lac_time = rdd1.map(x=>{
      val list = x.split(",")
      if(Integer.parseInt(list(3))==1)
      (list(0)+" "+list(2),-list(1).toLong)
      else{
       (list(0)+" "+list(2),list(1).toLong)
         }
     }
    )
    //根据rdd_phone_lac_time 的key进行reduce,将所有key相同的数据相加
    val rdd_reduce_phone_lackey = rdd_phone_lac_time.reduceByKey((x,y)=>x+y)
    //(18688888888,CompactBuffer((18688888888 16030401EAFB68F1E3CDF819735E1C66,87600), (18688888888 9F36407EAD0629FC166F14DDE7970F68,51200), (18688888888 CC0710CC94ECC657A8561DE549D940E0,1300)))
    //取top2,mapValues对values操作,返回的是map(K,V),K是原始的K,V是操作后得到的V
    val rdd_reduce_phone_lackey_groupyed = rdd_reduce_phone_lackey.groupBy(x=>x._1.split(" ")(0))
    val rdd_top2 = rdd_reduce_phone_lackey_groupyed.mapValues(x=>{
      x.toList.sortBy(_._2).reverse.take(2)    
    })
    //(16030401EAFB68F1E3CDF819735E1C66,(18688888888,16030401EAFB68F1E3CDF819735E1C66,87600))
    //下面需要与另一个map根据特定的字段例如16030401EAFB68F1E3CDF819735E1C66进行join,所以需要将‘18688888888 16030401EAFB68F1E3CDF819735E1C66’拆开,将第二个作为K,返回新的map
    val rdd_result = rdd_top2.flatMap(x=>{
         x._2.map(y=>{
           val li = y._1.split(" ")
           (li(1),(li(0),li(1),y._2))
         })
         
       })
       //该文件中即是需要与上面的结果进行join
     val lati_longti = sc.textFile("D:\\lac_info", 1)
     //(9F36407EAD0629FC166F14DDE7970F68,(116.304864,40.050645))
     //映射成如上一行的map
     val rdd_coordinate = lati_longti.map(f=>{
       val li = f.split(",")
       (li(0),(li(0),li(1),li(2)))
     })
     //进行join
     //rdd_coordinate 与rdd_result的结构类型已改是一样的,即K,V的类型对应,否则无法join
     val join_resultWithcoordinate = rdd_coordinate.join(rdd_result)
    // rdd_coordinate.to
     //println(rdd_result.collect().length)
     //保存文件
    join_resultWithcoordinate.saveAsTextFile("d:\\dest")
    sc.stop()
    
  }
}


样例数据

D:\\bs_log
18688888888,20160327082400,16030401EAFB68F1E3CDF819735E1C66,1
18611132889,20160327082500,16030401EAFB68F1E3CDF819735E1C66,1
18688888888,20160327170000,16030401EAFB68F1E3CDF819735E1C66,0
18611132889,20160327075000,9F36407EAD0629FC166F14DDE7970F68,1
18688888888,20160327075100,9F36407EAD0629FC166F14DDE7970F68,1
18611132889,20160327081000,9F36407EAD0629FC166F14DDE7970F68,0
18688888888,20160327081300,9F36407EAD0629FC166F14DDE7970F68,0
18688888888,20160327175000,9F36407EAD0629FC166F14DDE7970F68,1
18611132889,20160327182000,9F36407EAD0629FC166F14DDE7970F68,1
18688888888,20160327220000,9F36407EAD0629FC166F14DDE7970F68,0
18611132889,20160327230000,9F36407EAD0629FC166F14DDE7970F68,0
18611132889,20160327180000,16030401EAFB68F1E3CDF819735E1C66,0
18611132889,20160327081100,CC0710CC94ECC657A8561DE549D940E0,1
18688888888,20160327081200,CC0710CC94ECC657A8561DE549D940E0,1
18688888888,20160327081900,CC0710CC94ECC657A8561DE549D940E0,0
18611132889,20160327082000,CC0710CC94ECC657A8561DE549D940E0,0
18688888888,20160327171000,CC0710CC94ECC657A8561DE549D940E0,1
18688888888,20160327171600,CC0710CC94ECC657A8561DE549D940E0,0
18611132889,20160327180500,CC0710CC94ECC657A8561DE549D940E0,1
18611132889,20160327181500,CC0710CC94ECC657A8561DE549D940E0,0
D:\\lac_info  
9F36407EAD0629FC166F14DDE7970F68,116.304864,40.050645,6
CC0710CC94ECC657A8561DE549D940E0,116.303955,40.041935,6
16030401EAFB68F1E3CDF819735E1C66,116.296302,40.032296,6
数据结果:
(16030401EAFB68F1E3CDF819735E1C66,((16030401EAFB68F1E3CDF819735E1C66,116.296302,40.032296),(18688888888,16030401EAFB68F1E3CDF819735E1C66,87600)))
(16030401EAFB68F1E3CDF819735E1C66,((16030401EAFB68F1E3CDF819735E1C66,116.296302,40.032296),(18611132889,16030401EAFB68F1E3CDF819735E1C66,97500)))
(9F36407EAD0629FC166F14DDE7970F68,((9F36407EAD0629FC166F14DDE7970F68,116.304864,40.050645),(18688888888,9F36407EAD0629FC166F14DDE7970F68,51200)))
(9F36407EAD0629FC166F14DDE7970F68,((9F36407EAD0629FC166F14DDE7970F68,116.304864,40.050645),(18611132889,9F36407EAD0629FC166F14DDE7970F68,54000)))


来自 “ ITPUB博客 ” ,链接:http://blog.itpub.net/31506529/viewspace-2216122/,如需转载,请注明出处,否则将追究法律责任。

请登录后发表评论 登录
全部评论

注册时间:2017-11-22

  • 博文量
    76
  • 访问量
    27345