val words = Array("one", "two", "two", "three", "three", "three") val wordsDF = sc.parallelize(words).toDF("word") scala> val words = Array("one", "two", "two", "three", "three", "three") words: Array[String] = Array(one, two, two, three, three, three) scala> val wordsDF = sc.parallelize(words).toDF("word") wordsDF: org.apache.spark.sql.DataFrame = [word: string] scala> wordsDF.printSchema root |-