public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("JavaDCTExample");
JavaSparkContext jsc = new JavaSparkContext(conf);
SQLContext jsql = new SQLContext(jsc);
JavaRDD<Row> data = jsc.parallelize(Arrays.asList(
RowFactory.create(Vectors.dense(0.0, 1.0, -2.0, 3.0)),
RowFactory.create(Vectors.dense(-1.0, 2.0, 4.0, -7.0)),
RowFactory.create(Vectors.dense(14.0, -2.0, -5.0, 1.0))
));
StructType schema = new StructType(new StructField[]{
new StructField("features", new VectorUDT(), false, Metadata.empty()),
});
DataFrame df = jsql.createDataFrame(data, schema);
DCT dct = new DCT()
.setInputCol("features")
.setOutputCol("featuresDCT")
.setInverse(false);
DataFrame dctDf = dct.transform(df);
dctDf.select("featuresDCT").show(3);
jsc.stop();
}
|