Spark DataFrame handing empty String in OneHotEncoder

Question

I am importing a CSV file (using spark-csv) into a DataFrame which has empty String values. When applied the OneHotEncoder, the applic

Answer 1

if the column contains null the OneHotEncoder fails with a NullPointerException. therefore i extended the udf to tanslate null values as well

object OneHotEncoderExample {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("OneHotEncoderExample Application").setMaster("local[2]")
    val sc = new SparkContext(conf)
    val sqlContext = new SQLContext(sc)

    // $example on$
    val df1 = sqlContext.createDataFrame(Seq(
      (0.0, "a"),
      (1.0, "b"),
      (2.0, "c"),
      (3.0, ""),
      (4.0, null),
      (5.0, "c")
    )).toDF("id", "category")


    import org.apache.spark.sql.functions.udf
    def emptyValueSubstitution = udf[String, String] {
      case "" => "NA"
      case null => "null"
      case value => value
    }
    val df = df1.withColumn("category", emptyValueSubstitution( df1("category")) )


    val indexer = new StringIndexer()
      .setInputCol("category")
      .setOutputCol("categoryIndex")
      .fit(df)
    val indexed = indexer.transform(df)
    indexed.show()

    val encoder = new OneHotEncoder()
      .setInputCol("categoryIndex")
      .setOutputCol("categoryVec")
      .setDropLast(false)
    val encoded = encoder.transform(indexed)
    encoded.show()
    // $example off$
    sc.stop()
  }
}