如何将 RowMatrix 转换为 RDD[vector]？

Question

矩阵是 PCA 的输出，我使用 PCA 的结果进行聚类。

val lData =  sqlContext.read.parquet("/usr/local/spark/dataset/data/user")
val vecData = lData.rdd.map(s => Vectors.dense(s.getInt(0),s.getAs[Seq[Double]](1):_*)).cache()
val mat = new RowMatrix(vecData)
val pc = mat.computePrincipalComponents(2)
val projected = mat.multiply(pc)
val numClusters =10
val numIteration = 10
val model=KMeans.train(vectors,numClusters,numIteration)

出现这个错误

类型不匹配; 发现：org.apache.spark.mllib.linalg.distributed.RowMatrix 需要：org.apache.spark.rdd.RDD[org.apache.spark.mllib.linalg.Vector]

如何纠正？