import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.stat.Statistics
val rdd = sc.makeRDD(Array(Array(1.0,10.1,2.5),Array(2.0,5.2,3.8)))
val rdd2 = sc.makeRDD(Array(1.2,2.3,3.4))
val data = rdd.map(f=>Vectors.dense(f))
println("data: \n" +data)
val stat = Statistics.colStats(data)
println("stat: \n"+stat)
println("min:" +stat.min)//min,max等等都是向量,2个Array时,min:[1.0,5.2,2.5]
println("max:" +stat.max)//max:[2.0,10.1,3.8]
Vectors.dense()
最新推荐文章于 2025-07-04 07:14:10 发布