org.apache.spark.mllib.linalg.DenseVector Java Examples

@Test
public void testVectorBinarizerDense() {
    // prepare data

    JavaRDD<Row> jrdd = sc.parallelize(Arrays.asList(
            RowFactory.create(0d, 1d, new DenseVector(new double[]{-2d, -3d, -4d, -1d, 6d, -7d, 8d, 0d, 0d, 0d, 0d, 0d})),
            RowFactory.create(1d, 2d, new DenseVector(new double[]{4d, -5d, 6d, 7d, -8d, 9d, -10d, 0d, 0d, 0d, 0d, 0d})),
            RowFactory.create(2d, 3d, new DenseVector(new double[]{-5d, 6d, -8d, 9d, 10d, 11d, 12d, 0d, 0d, 0d, 0d, 0d}))
    ));

    StructType schema = new StructType(new StructField[]{
            new StructField("id", DataTypes.DoubleType, false, Metadata.empty()),
            new StructField("value1", DataTypes.DoubleType, false, Metadata.empty()),
            new StructField("vector1", new VectorUDT(), false, Metadata.empty())
    });

    DataFrame df = sqlContext.createDataFrame(jrdd, schema);
    VectorBinarizer vectorBinarizer = new VectorBinarizer()
            .setInputCol("vector1")
            .setOutputCol("binarized")
            .setThreshold(2d);


    //Export this model
    byte[] exportedModel = ModelExporter.export(vectorBinarizer, df);

    //Import and get Transformer
    Transformer transformer = ModelImporter.importAndGetTransformer(exportedModel);
    //compare predictions
    Row[] sparkOutput = vectorBinarizer.transform(df).orderBy("id").select("id", "value1", "vector1", "binarized").collect();
    for (Row row : sparkOutput) {

        Map<String, Object> data = new HashMap<>();
        data.put(vectorBinarizer.getInputCol(), ((DenseVector) row.get(2)).toArray());
        transformer.transform(data);
        double[] output = (double[]) data.get(vectorBinarizer.getOutputCol());
        assertArrayEquals(output, ((DenseVector) row.get(3)).toArray(), 0d);
    }
}
 

/**
 *
 * ExecRow is one-based as far as the elements
 *
 * @param execRow
 * @return
 */
public static Vector convertExecRowToVector(ExecRow execRow) throws StandardException {
    int length = execRow.nColumns();
    double[] vectorValues = new double[length];
    for (int i=1;i<=length;i++) {
        vectorValues[i] = execRow.getColumn(i).getDouble();
    }
    return new DenseVector(vectorValues);
}
 

@Test
public void testVectorAssembler() {
    // prepare data

    JavaRDD<Row> jrdd = sc.parallelize(Arrays.asList(
            RowFactory.create(0d, 1d, new DenseVector(new double[]{2d, 3d})),
            RowFactory.create(1d, 2d, new DenseVector(new double[]{3d, 4d})),
            RowFactory.create(2d, 3d, new DenseVector(new double[]{4d, 5d})),
            RowFactory.create(3d, 4d, new DenseVector(new double[]{5d, 6d})),
            RowFactory.create(4d, 5d, new DenseVector(new double[]{6d, 7d}))
    ));

    StructType schema = new StructType(new StructField[]{
            new StructField("id", DataTypes.DoubleType, false, Metadata.empty()),
            new StructField("value1", DataTypes.DoubleType, false, Metadata.empty()),
            new StructField("vector1", new VectorUDT(), false, Metadata.empty())
    });

    DataFrame df = sqlContext.createDataFrame(jrdd, schema);
    VectorAssembler vectorAssembler = new VectorAssembler()
            .setInputCols(new String[]{"value1", "vector1"})
            .setOutputCol("feature");


    //Export this model
    byte[] exportedModel = ModelExporter.export(vectorAssembler, null);

    String exportedModelJson = new String(exportedModel);
    //Import and get Transformer
    Transformer transformer = ModelImporter.importAndGetTransformer(exportedModel);
    //compare predictions
    Row[] sparkOutput = vectorAssembler.transform(df).orderBy("id").select("id", "value1", "vector1", "feature").collect();
    for (Row row : sparkOutput) {

        Map<String, Object> data = new HashMap<>();
        data.put(vectorAssembler.getInputCols()[0], row.get(1));
        data.put(vectorAssembler.getInputCols()[1], ((DenseVector) row.get(2)).toArray());
        transformer.transform(data);
        double[] output = (double[]) data.get(vectorAssembler.getOutputCol());
        assertArrayEquals(output, ((DenseVector) row.get(3)).toArray(), 0d);
    }
}
 

@Test
public void testChiSqSelector() {
    // prepare data

    JavaRDD<Row> jrdd = sc.parallelize(Arrays.asList(
            RowFactory.create(0d, 0d, new DenseVector(new double[]{8d, 7d, 0d})),
            RowFactory.create(1d, 1d, new DenseVector(new double[]{0d, 9d, 6d})),
            RowFactory.create(2d, 1d, new DenseVector(new double[]{0.0d, 9.0d, 8.0d})),
            RowFactory.create(3d, 2d, new DenseVector(new double[]{8.0d, 9.0d, 5.0d}))
    ));

    double[] preFilteredData = {0.0d, 6.0d, 8.0d, 5.0d};

    StructType schema = new StructType(new StructField[]{
            new StructField("id", DataTypes.DoubleType, false, Metadata.empty()),
            new StructField("label", DataTypes.DoubleType, false, Metadata.empty()),
            new StructField("features", new VectorUDT(), false, Metadata.empty())
    });

    DataFrame df = sqlContext.createDataFrame(jrdd, schema);
    ChiSqSelector chiSqSelector = new ChiSqSelector();
    chiSqSelector.setNumTopFeatures(1);
    chiSqSelector.setFeaturesCol("features");
    chiSqSelector.setLabelCol("label");
    chiSqSelector.setOutputCol("output");

    ChiSqSelectorModel chiSqSelectorModel = chiSqSelector.fit(df);

    //Export this model
    byte[] exportedModel = ModelExporter.export(chiSqSelectorModel, null);

    String exportedModelJson = new String(exportedModel);

    //Import and get Transformer
    Transformer transformer = ModelImporter.importAndGetTransformer(exportedModel);

    //compare predictions
    Row[] sparkOutput = chiSqSelectorModel.transform(df).orderBy("id").select("id", "label", "features", "output").collect();
    for (Row row : sparkOutput) {
        Map<String, Object> data = new HashMap<>();
        data.put(chiSqSelectorModel.getFeaturesCol(), ((DenseVector) row.get(2)).toArray());
        transformer.transform(data);
        double[] output = (double[]) data.get(chiSqSelectorModel.getOutputCol());
        System.out.println(Arrays.toString(output));
        assertArrayEquals(output, ((DenseVector) row.get(3)).toArray(), 0d);
    }
}
 

@Override
public Vector format(Object value){
	List<String> labels = getLabels();

	HasProbability hasProbability = (HasProbability)value;

	double[] probabilities = new double[labels.size()];

	for(int i = 0; i < labels.size(); i++){
		String label = labels.get(i);

		probabilities[i] = hasProbability.getProbability(label);
	}

	return new DenseVector(probabilities);
}
 

/**
 *
 * ExecRow is one-based as far as the elements
 *
 * @param execRow
 * @param fieldsToConvert
 * @return
 */
public static Vector convertExecRowToVector(ExecRow execRow,int[] fieldsToConvert) throws StandardException {
    double[] vectorValues = new double[fieldsToConvert.length];
    for (int i=0;i<fieldsToConvert.length;i++) {
        vectorValues[i] = execRow.getColumn(fieldsToConvert[i]).getDouble();
    }
    return new DenseVector(vectorValues);
}