Spark 2.0 - Convert DataFrame to DataSet - scala

Question

I want to load my data and do some basic linear regression on it. So first, I need to use VectorAssembler to produce my features column. However, when I use assembler.transform(df), df is a DataFrame, and it expects a DataSet. I tried df.toDS, but it gives value toDS is not a member of org.apache.spark.sql.DataFrame. Indeed, it is a member of org.apache.spark.sql.DatasetHolder.
What am I getting wrong here?
package main.scala
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf
import org.apache.spark.sql.functions._
import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.DatasetHolder
import org.apache.spark.ml.regression.LinearRegression
import org.apache.spark.ml.feature.RFormula
import org.apache.spark.ml.feature.VectorAssembler
import org.apache.spark.ml.linalg.Vectors
object Analyzer {
def main(args: Array[String]) {
val conf = new SparkConf()
val sc = new SparkContext(conf)
val sqlContext = new SQLContext(sc)
import sqlContext.implicits._
val df = sqlContext.read
.format("com.databricks.spark.csv")
.option("header", "false")
.option("delimiter", "\t")
.option("parserLib", "UNIVOCITY")
.option("inferSchema", "true")
.load("data/snap/*")
val assembler = new VectorAssembler()
.setInputCols(Array("own", "want", "wish", "trade", "comment"))
.setOutputCol("features")
val df1 = assembler.transform(df)
val formula = new RFormula().setFormula("rank ~ own + want + wish + trade + comment")
.setFeaturesCol("features")
.setLabelCol("rank")
}
}

Answer 1

Apparently the problem was because I still using Spark 1.6 style of Spark and SQLContext. I changed for the SparkSession, and transform() was able to implicitly accept the DataFrame.
package main.scala
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.Dataset
import org.apache.spark.ml.regression.LinearRegression
import org.apache.spark.ml.feature.RFormula
import org.apache.spark.ml.feature.VectorAssembler
import org.apache.spark.ml.linalg.Vectors
object Analyzer {
def main(args: Array[String]) {
val spark = SparkSession.builder().getOrCreate()
import spark.implicits._
val df = spark.read
.format("com.databricks.spark.csv")
.option("header", "false")
.option("delimiter", "\t")
.option("parserLib", "UNIVOCITY")
.option("inferSchema", "true")
.load("data/snap/*")
df.show()
val assembler = new VectorAssembler()
.setInputCols(Array("own", "want", "wish", "trade", "comment"))
.setOutputCol("features")
val df1 = assembler.transform(df)
}
}