Issue in using DenseVector in RowMatrix, error could be due to ml and mllib package changes

[satyajit vegesna]

Hi All,

PFB code.


import org.apache.spark.ml.feature.{HashingTF, IDF}
import org.apache.spark.ml.linalg.SparseVector
import org.apache.spark.mllib.linalg.distributed.RowMatrix
import org.apache.spark.sql.SparkSession
import org.apache.spark.{SparkConf, SparkContext}

/**
  * Created by satyajit on 12/7/16.
  */
object DIMSUMusingtf extends App {

  val conf = new SparkConf()
    .setMaster("local[1]")
    .setAppName("testColsim")
  val sc = new SparkContext(conf)
  val spark = SparkSession
    .builder
    .appName("testColSim").getOrCreate()

  import org.apache.spark.ml.feature.Tokenizer

  val sentenceData = spark.createDataFrame(Seq(
    (0, "Hi I heard about Spark"),
    (0, "I wish Java could use case classes"),
    (1, "Logistic regression models are neat")
  )).toDF("label", "sentence")

  val tokenizer = new Tokenizer().setInputCol("sentence").setOutputCol("words")

  val wordsData = tokenizer.transform(sentenceData)


  val hashingTF = new HashingTF()
    .setInputCol("words").setOutputCol("rawFeatures").setNumFeatures(20)

  val featurizedData = hashingTF.transform(wordsData)


  val idf = new IDF().setInputCol("rawFeatures").setOutputCol("features")
  val idfModel = idf.fit(featurizedData)
  val rescaledData = idfModel.transform(featurizedData)
  rescaledData.show()
  rescaledData.select("features", "label").take(3).foreach(println)
  val check = rescaledData.select("features")

  val row = check.rdd.map(row => row.getAs[SparseVector]("features"))

  val mat = new RowMatrix(row) //i am basically trying to use
Dense.vector as a direct input to

rowMatrix, but i get an error that RowMatrix Cannot resolve constructor

  row.foreach(println)
}

Any help would be appreciated.

Regards,
Satyajit.