public static void main(String[] args) {

    SparkConf conf = new SparkConf().setAppName("JavaStopWordsRemoverExample");

    JavaSparkContext jsc = new JavaSparkContext(conf);

    SQLContext jsql = new SQLContext(jsc);



    StopWordsRemover remover = new StopWordsRemover()

      .setInputCol("raw")

      .setOutputCol("filtered");



    JavaRDD<Row> rdd = jsc.parallelize(Arrays.asList(

      RowFactory.create(Arrays.asList("I", "saw", "the", "red", "baloon")),

      RowFactory.create(Arrays.asList("Mary", "had", "a", "little", "lamb"))

    ));



    StructType schema = new StructType(new StructField[]{

      new StructField(

        "raw", DataTypes.createArrayType(DataTypes.StringType), false, Metadata.empty())

    });



    DataFrame dataset = jsql.createDataFrame(rdd, schema);

    remover.transform(dataset).show();

    jsc.stop();

  }