Commit 94d8043e authored by 王志伟's avatar 王志伟

统计推荐日记重复指标

parent 46b4d733
......@@ -229,10 +229,18 @@ object Repeated_content_recommendation {
val get_result =exp_diary.rdd.map((_, 1)).reduceByKey(_ + _)
.sortBy(_._2,false)
val temp=get_result.collect()
for (i <- 0 until 30 ) {
println(temp(i))
}
val more_than2=get_result.filter(_._2 >=2).map(_._2).reduce((x,y)=>x+y)
val all =get_result.map(_._2).reduce((x,y)=>x+y)
val repeated_rate=more_than2/all
println(repeated_rate)
// val temp=get_result.collect()
// for (i <- 0 until 30 ) {
// println(temp(i))
// }
}
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment