• 设为首页
  • 点击收藏
  • 手机版
    手机扫一扫访问
    迪恩网络手机版
  • 关注官方公众号
    微信扫一扫关注
    公众号
登陆 注册

Java VectorUDT类代码示例

原作者: [db:作者] 来自: [db:来源] 收藏 邀请

本文整理汇总了Java中org.apache.spark.ml.linalg.VectorUDT类的典型用法代码示例。如果您正苦于以下问题：Java VectorUDT类的具体用法？Java VectorUDT怎么用？Java VectorUDT使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。



VectorUDT类属于org.apache.spark.ml.linalg包，在下文中一共展示了VectorUDT类的20个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于我们的系统推荐出更棒的Java代码示例。

示例1: convertToStructField

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
/**
 * StructField，
 *
 * @return
 * @throws CantConverException
 */
public static StructField convertToStructField(FieldInfo info) throws CantConverException {
    if (info.getIndex() != -1) {
        return DataTypes.createStructField(info.getName(), sparkDataType(info.getDataType()), info.isNullable());
    } else {
        switch (info.getDataType()) {
            case FieldInfo.STRING_DATATYPE: {
                return new StructField(info.getName(), DataTypes.createArrayType(DataTypes.StringType), info.isNullable(), Metadata.empty());
            }
            case FieldInfo.DOUBLE_DATATYPE:
            case FieldInfo.INTEGER_DATATYPE:
            case FieldInfo.LONG_DATATYPE: {
                return new StructField(info.getName(), new VectorUDT(), info.isNullable(), Metadata.empty());
            }
            default:
                throw new CantConverException("不合法类型");
        }
    }
}
开发者ID:hays2hong，项目名称:stonk，代码行数:25，代码来源:SparkDataFileConverter.java


示例2: binaryBlockToDataFrame

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
public static Dataset<Row> binaryBlockToDataFrame(SparkSession sparkSession,
		JavaPairRDD<MatrixIndexes, MatrixBlock> in, MatrixCharacteristics mc, boolean toVector)  
{
	if( !mc.colsKnown() )
		throw new RuntimeException("Number of columns needed to convert binary block to data frame.");
	
	//slice blocks into rows, align and convert into data frame rows
	JavaRDD<Row> rowsRDD = in
		.flatMapToPair(new SliceBinaryBlockToRowsFunction(mc.getRowsPerBlock()))
		.groupByKey().map(new ConvertRowBlocksToRows((int)mc.getCols(), mc.getColsPerBlock(), toVector));
	
	//create data frame schema
	List<StructField> fields = new ArrayList<>();
	fields.add(DataTypes.createStructField(DF_ID_COLUMN, DataTypes.DoubleType, false));
	if( toVector )
		fields.add(DataTypes.createStructField("C1", new VectorUDT(), false));
	else { // row
		for(int i = 1; i <= mc.getCols(); i++)
			fields.add(DataTypes.createStructField("C"+i, DataTypes.DoubleType, false));
	}
	
	//rdd to data frame conversion
	return sparkSession.createDataFrame(rowsRDD.rdd(), DataTypes.createStructType(fields));
}
开发者ID:apache，项目名称:systemml，代码行数:25，代码来源:RDDConverterUtils.java


示例3: testDataFrameSumDMLVectorWithIDColumn

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testDataFrameSumDMLVectorWithIDColumn() {
	System.out.println("MLContextTest - DataFrame sum DML, vector with ID column");

	List<Tuple2<Double, Vector>> list = new ArrayList<Tuple2<Double, Vector>>();
	list.add(new Tuple2<Double, Vector>(1.0, Vectors.dense(1.0, 2.0, 3.0)));
	list.add(new Tuple2<Double, Vector>(2.0, Vectors.dense(4.0, 5.0, 6.0)));
	list.add(new Tuple2<Double, Vector>(3.0, Vectors.dense(7.0, 8.0, 9.0)));
	JavaRDD<Tuple2<Double, Vector>> javaRddTuple = sc.parallelize(list);

	JavaRDD<Row> javaRddRow = javaRddTuple.map(new DoubleVectorRow());
	List<StructField> fields = new ArrayList<StructField>();
	fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
	fields.add(DataTypes.createStructField("C1", new VectorUDT(), true));
	StructType schema = DataTypes.createStructType(fields);
	Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);

	MatrixMetadata mm = new MatrixMetadata(MatrixFormat.DF_VECTOR_WITH_INDEX);

	Script script = dml("print('sum: ' + sum(M));").in("M", dataFrame, mm);
	setExpectedStdOut("sum: 45.0");
	ml.execute(script);
}
开发者ID:apache，项目名称:systemml，代码行数:24，代码来源:MLContextTest.java


示例4: testDataFrameSumPYDMLVectorWithIDColumn

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testDataFrameSumPYDMLVectorWithIDColumn() {
	System.out.println("MLContextTest - DataFrame sum PYDML, vector with ID column");

	List<Tuple2<Double, Vector>> list = new ArrayList<Tuple2<Double, Vector>>();
	list.add(new Tuple2<Double, Vector>(1.0, Vectors.dense(1.0, 2.0, 3.0)));
	list.add(new Tuple2<Double, Vector>(2.0, Vectors.dense(4.0, 5.0, 6.0)));
	list.add(new Tuple2<Double, Vector>(3.0, Vectors.dense(7.0, 8.0, 9.0)));
	JavaRDD<Tuple2<Double, Vector>> javaRddTuple = sc.parallelize(list);

	JavaRDD<Row> javaRddRow = javaRddTuple.map(new DoubleVectorRow());
	List<StructField> fields = new ArrayList<StructField>();
	fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
	fields.add(DataTypes.createStructField("C1", new VectorUDT(), true));
	StructType schema = DataTypes.createStructType(fields);
	Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);

	MatrixMetadata mm = new MatrixMetadata(MatrixFormat.DF_VECTOR_WITH_INDEX);

	Script script = pydml("print('sum: ' + sum(M))").in("M", dataFrame, mm);
	setExpectedStdOut("sum: 45.0");
	ml.execute(script);
}
开发者ID:apache，项目名称:systemml，代码行数:24，代码来源:MLContextTest.java


示例5: testDataFrameSumDMLMllibVectorWithIDColumn

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testDataFrameSumDMLMllibVectorWithIDColumn() {
	System.out.println("MLContextTest - DataFrame sum DML, mllib vector with ID column");

	List<Tuple2<Double, org.apache.spark.mllib.linalg.Vector>> list = new ArrayList<Tuple2<Double, org.apache.spark.mllib.linalg.Vector>>();
	list.add(new Tuple2<Double, org.apache.spark.mllib.linalg.Vector>(1.0,
			org.apache.spark.mllib.linalg.Vectors.dense(1.0, 2.0, 3.0)));
	list.add(new Tuple2<Double, org.apache.spark.mllib.linalg.Vector>(2.0,
			org.apache.spark.mllib.linalg.Vectors.dense(4.0, 5.0, 6.0)));
	list.add(new Tuple2<Double, org.apache.spark.mllib.linalg.Vector>(3.0,
			org.apache.spark.mllib.linalg.Vectors.dense(7.0, 8.0, 9.0)));
	JavaRDD<Tuple2<Double, org.apache.spark.mllib.linalg.Vector>> javaRddTuple = sc.parallelize(list);

	JavaRDD<Row> javaRddRow = javaRddTuple.map(new DoubleMllibVectorRow());
	List<StructField> fields = new ArrayList<StructField>();
	fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
	fields.add(DataTypes.createStructField("C1", new org.apache.spark.mllib.linalg.VectorUDT(), true));
	StructType schema = DataTypes.createStructType(fields);
	Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);

	MatrixMetadata mm = new MatrixMetadata(MatrixFormat.DF_VECTOR_WITH_INDEX);

	Script script = dml("print('sum: ' + sum(M));").in("M", dataFrame, mm);
	setExpectedStdOut("sum: 45.0");
	ml.execute(script);
}
开发者ID:apache，项目名称:systemml，代码行数:27，代码来源:MLContextTest.java


示例6: testDataFrameSumPYDMLMllibVectorWithIDColumn

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testDataFrameSumPYDMLMllibVectorWithIDColumn() {
	System.out.println("MLContextTest - DataFrame sum PYDML, mllib vector with ID column");

	List<Tuple2<Double, org.apache.spark.mllib.linalg.Vector>> list = new ArrayList<Tuple2<Double, org.apache.spark.mllib.linalg.Vector>>();
	list.add(new Tuple2<Double, org.apache.spark.mllib.linalg.Vector>(1.0,
			org.apache.spark.mllib.linalg.Vectors.dense(1.0, 2.0, 3.0)));
	list.add(new Tuple2<Double, org.apache.spark.mllib.linalg.Vector>(2.0,
			org.apache.spark.mllib.linalg.Vectors.dense(4.0, 5.0, 6.0)));
	list.add(new Tuple2<Double, org.apache.spark.mllib.linalg.Vector>(3.0,
			org.apache.spark.mllib.linalg.Vectors.dense(7.0, 8.0, 9.0)));
	JavaRDD<Tuple2<Double, org.apache.spark.mllib.linalg.Vector>> javaRddTuple = sc.parallelize(list);

	JavaRDD<Row> javaRddRow = javaRddTuple.map(new DoubleMllibVectorRow());
	List<StructField> fields = new ArrayList<StructField>();
	fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
	fields.add(DataTypes.createStructField("C1", new org.apache.spark.mllib.linalg.VectorUDT(), true));
	StructType schema = DataTypes.createStructType(fields);
	Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);

	MatrixMetadata mm = new MatrixMetadata(MatrixFormat.DF_VECTOR_WITH_INDEX);

	Script script = pydml("print('sum: ' + sum(M))").in("M", dataFrame, mm);
	setExpectedStdOut("sum: 45.0");
	ml.execute(script);
}
开发者ID:apache，项目名称:systemml，代码行数:27，代码来源:MLContextTest.java


示例7: testDataFrameSumDMLVectorWithNoIDColumn

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testDataFrameSumDMLVectorWithNoIDColumn() {
	System.out.println("MLContextTest - DataFrame sum DML, vector with no ID column");

	List<Vector> list = new ArrayList<Vector>();
	list.add(Vectors.dense(1.0, 2.0, 3.0));
	list.add(Vectors.dense(4.0, 5.0, 6.0));
	list.add(Vectors.dense(7.0, 8.0, 9.0));
	JavaRDD<Vector> javaRddVector = sc.parallelize(list);

	JavaRDD<Row> javaRddRow = javaRddVector.map(new VectorRow());
	List<StructField> fields = new ArrayList<StructField>();
	fields.add(DataTypes.createStructField("C1", new VectorUDT(), true));
	StructType schema = DataTypes.createStructType(fields);
	Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);

	MatrixMetadata mm = new MatrixMetadata(MatrixFormat.DF_VECTOR);

	Script script = dml("print('sum: ' + sum(M));").in("M", dataFrame, mm);
	setExpectedStdOut("sum: 45.0");
	ml.execute(script);
}
开发者ID:apache，项目名称:systemml，代码行数:23，代码来源:MLContextTest.java


示例8: testDataFrameSumPYDMLVectorWithNoIDColumn

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testDataFrameSumPYDMLVectorWithNoIDColumn() {
	System.out.println("MLContextTest - DataFrame sum PYDML, vector with no ID column");

	List<Vector> list = new ArrayList<Vector>();
	list.add(Vectors.dense(1.0, 2.0, 3.0));
	list.add(Vectors.dense(4.0, 5.0, 6.0));
	list.add(Vectors.dense(7.0, 8.0, 9.0));
	JavaRDD<Vector> javaRddVector = sc.parallelize(list);

	JavaRDD<Row> javaRddRow = javaRddVector.map(new VectorRow());
	List<StructField> fields = new ArrayList<StructField>();
	fields.add(DataTypes.createStructField("C1", new VectorUDT(), true));
	StructType schema = DataTypes.createStructType(fields);
	Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);

	MatrixMetadata mm = new MatrixMetadata(MatrixFormat.DF_VECTOR);

	Script script = pydml("print('sum: ' + sum(M))").in("M", dataFrame, mm);
	setExpectedStdOut("sum: 45.0");
	ml.execute(script);
}
开发者ID:apache，项目名称:systemml，代码行数:23，代码来源:MLContextTest.java


示例9: testDataFrameSumDMLMllibVectorWithNoIDColumn

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testDataFrameSumDMLMllibVectorWithNoIDColumn() {
	System.out.println("MLContextTest - DataFrame sum DML, mllib vector with no ID column");

	List<org.apache.spark.mllib.linalg.Vector> list = new ArrayList<org.apache.spark.mllib.linalg.Vector>();
	list.add(org.apache.spark.mllib.linalg.Vectors.dense(1.0, 2.0, 3.0));
	list.add(org.apache.spark.mllib.linalg.Vectors.dense(4.0, 5.0, 6.0));
	list.add(org.apache.spark.mllib.linalg.Vectors.dense(7.0, 8.0, 9.0));
	JavaRDD<org.apache.spark.mllib.linalg.Vector> javaRddVector = sc.parallelize(list);

	JavaRDD<Row> javaRddRow = javaRddVector.map(new MllibVectorRow());
	List<StructField> fields = new ArrayList<StructField>();
	fields.add(DataTypes.createStructField("C1", new org.apache.spark.mllib.linalg.VectorUDT(), true));
	StructType schema = DataTypes.createStructType(fields);
	Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);

	MatrixMetadata mm = new MatrixMetadata(MatrixFormat.DF_VECTOR);

	Script script = dml("print('sum: ' + sum(M));").in("M", dataFrame, mm);
	setExpectedStdOut("sum: 45.0");
	ml.execute(script);
}
开发者ID:apache，项目名称:systemml，代码行数:23，代码来源:MLContextTest.java


示例10: testDataFrameSumPYDMLMllibVectorWithNoIDColumn

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testDataFrameSumPYDMLMllibVectorWithNoIDColumn() {
	System.out.println("MLContextTest - DataFrame sum PYDML, mllib vector with no ID column");

	List<org.apache.spark.mllib.linalg.Vector> list = new ArrayList<org.apache.spark.mllib.linalg.Vector>();
	list.add(org.apache.spark.mllib.linalg.Vectors.dense(1.0, 2.0, 3.0));
	list.add(org.apache.spark.mllib.linalg.Vectors.dense(4.0, 5.0, 6.0));
	list.add(org.apache.spark.mllib.linalg.Vectors.dense(7.0, 8.0, 9.0));
	JavaRDD<org.apache.spark.mllib.linalg.Vector> javaRddVector = sc.parallelize(list);

	JavaRDD<Row> javaRddRow = javaRddVector.map(new MllibVectorRow());
	List<StructField> fields = new ArrayList<StructField>();
	fields.add(DataTypes.createStructField("C1", new org.apache.spark.mllib.linalg.VectorUDT(), true));
	StructType schema = DataTypes.createStructType(fields);
	Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);

	MatrixMetadata mm = new MatrixMetadata(MatrixFormat.DF_VECTOR);

	Script script = pydml("print('sum: ' + sum(M))").in("M", dataFrame, mm);
	setExpectedStdOut("sum: 45.0");
	ml.execute(script);
}
开发者ID:apache，项目名称:systemml，代码行数:23，代码来源:MLContextTest.java


示例11: testDataFrameSumDMLVectorWithIDColumnNoFormatSpecified

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testDataFrameSumDMLVectorWithIDColumnNoFormatSpecified() {
	System.out.println("MLContextTest - DataFrame sum DML, vector with ID column, no format specified");

	List<Tuple2<Double, Vector>> list = new ArrayList<Tuple2<Double, Vector>>();
	list.add(new Tuple2<Double, Vector>(1.0, Vectors.dense(1.0, 2.0, 3.0)));
	list.add(new Tuple2<Double, Vector>(2.0, Vectors.dense(4.0, 5.0, 6.0)));
	list.add(new Tuple2<Double, Vector>(3.0, Vectors.dense(7.0, 8.0, 9.0)));
	JavaRDD<Tuple2<Double, Vector>> javaRddTuple = sc.parallelize(list);

	JavaRDD<Row> javaRddRow = javaRddTuple.map(new DoubleVectorRow());
	List<StructField> fields = new ArrayList<StructField>();
	fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
	fields.add(DataTypes.createStructField("C1", new VectorUDT(), true));
	StructType schema = DataTypes.createStructType(fields);
	Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);

	Script script = dml("print('sum: ' + sum(M));").in("M", dataFrame);
	setExpectedStdOut("sum: 45.0");
	ml.execute(script);
}
开发者ID:apache，项目名称:systemml，代码行数:22，代码来源:MLContextTest.java


示例12: testDataFrameSumPYDMLVectorWithIDColumnNoFormatSpecified

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testDataFrameSumPYDMLVectorWithIDColumnNoFormatSpecified() {
	System.out.println("MLContextTest - DataFrame sum PYDML, vector with ID column, no format specified");

	List<Tuple2<Double, Vector>> list = new ArrayList<Tuple2<Double, Vector>>();
	list.add(new Tuple2<Double, Vector>(1.0, Vectors.dense(1.0, 2.0, 3.0)));
	list.add(new Tuple2<Double, Vector>(2.0, Vectors.dense(4.0, 5.0, 6.0)));
	list.add(new Tuple2<Double, Vector>(3.0, Vectors.dense(7.0, 8.0, 9.0)));
	JavaRDD<Tuple2<Double, Vector>> javaRddTuple = sc.parallelize(list);

	JavaRDD<Row> javaRddRow = javaRddTuple.map(new DoubleVectorRow());
	List<StructField> fields = new ArrayList<StructField>();
	fields.add(DataTypes.createStructField(RDDConverterUtils.DF_ID_COLUMN, DataTypes.DoubleType, true));
	fields.add(DataTypes.createStructField("C1", new VectorUDT(), true));
	StructType schema = DataTypes.createStructType(fields);
	Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);

	Script script = dml("print('sum: ' + sum(M))").in("M", dataFrame);
	setExpectedStdOut("sum: 45.0");
	ml.execute(script);
}
开发者ID:apache，项目名称:systemml，代码行数:22，代码来源:MLContextTest.java


示例13: testDataFrameSumDMLVectorWithNoIDColumnNoFormatSpecified

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testDataFrameSumDMLVectorWithNoIDColumnNoFormatSpecified() {
	System.out.println("MLContextTest - DataFrame sum DML, vector with no ID column, no format specified");

	List<Vector> list = new ArrayList<Vector>();
	list.add(Vectors.dense(1.0, 2.0, 3.0));
	list.add(Vectors.dense(4.0, 5.0, 6.0));
	list.add(Vectors.dense(7.0, 8.0, 9.0));
	JavaRDD<Vector> javaRddVector = sc.parallelize(list);

	JavaRDD<Row> javaRddRow = javaRddVector.map(new VectorRow());
	List<StructField> fields = new ArrayList<StructField>();
	fields.add(DataTypes.createStructField("C1", new VectorUDT(), true));
	StructType schema = DataTypes.createStructType(fields);
	Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);

	Script script = dml("print('sum: ' + sum(M));").in("M", dataFrame);
	setExpectedStdOut("sum: 45.0");
	ml.execute(script);
}
开发者ID:apache，项目名称:systemml，代码行数:21，代码来源:MLContextTest.java


示例14: testDataFrameSumPYDMLVectorWithNoIDColumnNoFormatSpecified

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testDataFrameSumPYDMLVectorWithNoIDColumnNoFormatSpecified() {
	System.out.println("MLContextTest - DataFrame sum PYDML, vector with no ID column, no format specified");

	List<Vector> list = new ArrayList<Vector>();
	list.add(Vectors.dense(1.0, 2.0, 3.0));
	list.add(Vectors.dense(4.0, 5.0, 6.0));
	list.add(Vectors.dense(7.0, 8.0, 9.0));
	JavaRDD<Vector> javaRddVector = sc.parallelize(list);

	JavaRDD<Row> javaRddRow = javaRddVector.map(new VectorRow());
	List<StructField> fields = new ArrayList<StructField>();
	fields.add(DataTypes.createStructField("C1", new VectorUDT(), true));
	StructType schema = DataTypes.createStructType(fields);
	Dataset<Row> dataFrame = spark.createDataFrame(javaRddRow, schema);

	Script script = dml("print('sum: ' + sum(M))").in("M", dataFrame);
	setExpectedStdOut("sum: 45.0");
	ml.execute(script);
}
开发者ID:apache，项目名称:systemml，代码行数:21，代码来源:MLContextTest.java


示例15: testMinMaxScaler

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testMinMaxScaler() {
    //prepare data
    JavaRDD<Row> jrdd = jsc.parallelize(Arrays.asList(
            RowFactory.create(1.0, Vectors.dense(data[0])),
            RowFactory.create(2.0, Vectors.dense(data[1])),
            RowFactory.create(3.0, Vectors.dense(data[2])),
            RowFactory.create(4.0, Vectors.dense(data[3]))
    ));

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

    Dataset<Row> df = spark.createDataFrame(jrdd, schema);

    //train model in spark
    MinMaxScalerModel sparkModel = new MinMaxScaler()
            .setInputCol("features")
            .setOutputCol("scaled")
            .setMin(-5)
            .setMax(5)
            .fit(df);


    //Export model, import it back and get transformer
    byte[] exportedModel = ModelExporter.export(sparkModel);
    final Transformer transformer = ModelImporter.importAndGetTransformer(exportedModel);

    //compare predictions
    List<Row> sparkOutput = sparkModel.transform(df).orderBy("label").select("features", "scaled").collectAsList();
    assertCorrectness(sparkOutput, expected, transformer);
}
开发者ID:flipkart-incubator，项目名称:spark-transformers，代码行数:35，代码来源:MinMaxScalerBridgeTest.java


示例16: testStandardScaler

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testStandardScaler() {


    JavaRDD<Row> jrdd = jsc.parallelize(Arrays.asList(
            RowFactory.create(1.0, Vectors.dense(data[0])),
            RowFactory.create(2.0, Vectors.dense(data[1])),
            RowFactory.create(3.0, Vectors.dense(data[2]))
    ));

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

    Dataset<Row> df = spark.createDataFrame(jrdd, schema);

    //train model in spark
    StandardScalerModel sparkModelNone = new StandardScaler()
            .setInputCol("features")
            .setOutputCol("scaledOutput")
            .setWithMean(false)
            .setWithStd(false)
            .fit(df);

    StandardScalerModel sparkModelWithMean = new StandardScaler()
            .setInputCol("features")
            .setOutputCol("scaledOutput")
            .setWithMean(true)
            .setWithStd(false)
            .fit(df);

    StandardScalerModel sparkModelWithStd = new StandardScaler()
            .setInputCol("features")
            .setOutputCol("scaledOutput")
            .setWithMean(false)
            .setWithStd(true)
            .fit(df);

    StandardScalerModel sparkModelWithBoth = new StandardScaler()
            .setInputCol("features")
            .setOutputCol("scaledOutput")
            .setWithMean(true)
            .setWithStd(true)
            .fit(df);


    //Export model, import it back and get transformer
    byte[] exportedModel = ModelExporter.export(sparkModelNone);
    final Transformer transformerNone = ModelImporter.importAndGetTransformer(exportedModel);

    exportedModel = ModelExporter.export(sparkModelWithMean);
    final Transformer transformerWithMean = ModelImporter.importAndGetTransformer(exportedModel);

    exportedModel = ModelExporter.export(sparkModelWithStd);
    final Transformer transformerWithStd = ModelImporter.importAndGetTransformer(exportedModel);

    exportedModel = ModelExporter.export(sparkModelWithBoth);
    final Transformer transformerWithBoth = ModelImporter.importAndGetTransformer(exportedModel);


    //compare predictions
    List<Row> sparkNoneOutput = sparkModelNone.transform(df).orderBy("label").select("features", "scaledOutput").collectAsList();
    assertCorrectness(sparkNoneOutput, data, transformerNone);

    List<Row> sparkWithMeanOutput = sparkModelWithMean.transform(df).orderBy("label").select("features", "scaledOutput").collectAsList();
    assertCorrectness(sparkWithMeanOutput, resWithMean, transformerWithMean);

    List<Row> sparkWithStdOutput = sparkModelWithStd.transform(df).orderBy("label").select("features", "scaledOutput").collectAsList();
    assertCorrectness(sparkWithStdOutput, resWithStd, transformerWithStd);

    List<Row> sparkWithBothOutput = sparkModelWithBoth.transform(df).orderBy("label").select("features", "scaledOutput").collectAsList();
    assertCorrectness(sparkWithBothOutput, resWithBoth, transformerWithBoth);

}
开发者ID:flipkart-incubator，项目名称:spark-transformers，代码行数:76，代码来源:StandardScalerBridgeTest.java


示例17: determineMatrixFormatIfNeeded

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
/**
 * If the MatrixFormat of the DataFrame has not been explicitly specified,
 * attempt to determine the proper MatrixFormat.
 *
 * @param dataFrame
 *            the Spark {@code DataFrame}
 * @param matrixMetadata
 *            the matrix metadata, if available
 */
public static void determineMatrixFormatIfNeeded(Dataset<Row> dataFrame, MatrixMetadata matrixMetadata) {
	if (matrixMetadata == null) {
		return;
	}
	MatrixFormat matrixFormat = matrixMetadata.getMatrixFormat();
	if (matrixFormat != null) {
		return;
	}
	StructType schema = dataFrame.schema();
	boolean hasID = false;
	try {
		schema.fieldIndex(RDDConverterUtils.DF_ID_COLUMN);
		hasID = true;
	} catch (IllegalArgumentException iae) {
	}

	StructField[] fields = schema.fields();
	MatrixFormat mf = null;
	if (hasID) {
		if (fields[1].dataType() instanceof VectorUDT) {
			mf = MatrixFormat.DF_VECTOR_WITH_INDEX;
		} else {
			mf = MatrixFormat.DF_DOUBLES_WITH_INDEX;
		}
	} else {
		if (fields[0].dataType() instanceof VectorUDT) {
			mf = MatrixFormat.DF_VECTOR;
		} else {
			mf = MatrixFormat.DF_DOUBLES;
		}
	}

	if (mf == null) {
		throw new MLContextException("DataFrame format not recognized as an accepted SystemML MatrixFormat");
	}
	matrixMetadata.setMatrixFormat(mf);
}
开发者ID:apache，项目名称:systemml，代码行数:47，代码来源:MLContextConversionUtil.java


示例18: getColVectFromDFSchema

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
/**
 * Obtain column vector from DataFrame schema
 * 
 * @param dfschema schema as StructType
 * @param containsID if true, contains ID column
 * @return 0-based column index of vector column, -1 if no vector.
 */
private static int getColVectFromDFSchema(StructType dfschema, boolean containsID) {
	int off = containsID ? 1 : 0;
	for( int i=off; i<dfschema.fields().length; i++ ) {
		StructField structType = dfschema.apply(i);
		if(structType.dataType() instanceof VectorUDT)
			return i-off;
	}
	
	return -1;
}
开发者ID:apache，项目名称:systemml，代码行数:18，代码来源:FrameRDDConverterUtils.java


示例19: testOutputDataFrameOfVectorsDML

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
@Test
public void testOutputDataFrameOfVectorsDML() {
	System.out.println("MLContextTest - output DataFrame of vectors DML");

	String s = "m=matrix('1 2 3 4',rows=2,cols=2);";
	Script script = dml(s).out("m");
	MLResults results = ml.execute(script);
	Dataset<Row> df = results.getDataFrame("m", true);
	Dataset<Row> sortedDF = df.sort(RDDConverterUtils.DF_ID_COLUMN);

	// verify column types
	StructType schema = sortedDF.schema();
	StructField[] fields = schema.fields();
	StructField idColumn = fields[0];
	StructField vectorColumn = fields[1];
	Assert.assertTrue(idColumn.dataType() instanceof DoubleType);
	Assert.assertTrue(vectorColumn.dataType() instanceof VectorUDT);

	List<Row> list = sortedDF.collectAsList();

	Row row1 = list.get(0);
	Assert.assertEquals(1.0, row1.getDouble(0), 0.0);
	Vector v1 = (DenseVector) row1.get(1);
	double[] arr1 = v1.toArray();
	Assert.assertArrayEquals(new double[] { 1.0, 2.0 }, arr1, 0.0);

	Row row2 = list.get(1);
	Assert.assertEquals(2.0, row2.getDouble(0), 0.0);
	Vector v2 = (DenseVector) row2.get(1);
	double[] arr2 = v2.toArray();
	Assert.assertArrayEquals(new double[] { 3.0, 4.0 }, arr2, 0.0);
}
开发者ID:apache，项目名称:systemml，代码行数:33，代码来源:MLContextTest.java


示例20: main

import org.apache.spark.ml.linalg.VectorUDT; //导入依赖的package包/类
public static void main(String[] args) {
   SparkSession spark = SparkSession
     .builder().master("local").config("spark.sql.warehouse.dir", "file:///C:/Users/sumit.kumar/Downloads/bin/warehouse")
     .appName("JavaEstimatorTransformerParamExample")
     .getOrCreate();
   Logger rootLogger = LogManager.getRootLogger();
rootLogger.setLevel(Level.WARN);
   // $example on$
   // Prepare training data.
   List<Row> dataTraining = Arrays.asList(
       RowFactory.create(1.0, Vectors.dense(0.0, 1.1, 0.1)),
       RowFactory.create(0.0, Vectors.dense(2.0, 1.0, -1.0)),
       RowFactory.create(0.0, Vectors.dense(2.0, 1.3, 1.0)),
       RowFactory.create(1.0, Vectors.dense(0.0, 1.2, -0.5))
   );
   StructType schema = new StructType(new StructField[]{
       new StructField("label", DataTypes.DoubleType, false, Metadata.empty()),
       new StructField("features", new VectorUDT(), false, Metadata.empty())
   });
   Dataset<Row> training = spark.createDataFrame(dataTraining, schema);

   // Create a LogisticRegression instance. This instance is an Estimator.
   LogisticRegression lr = new LogisticRegression();
   // Print out the parameters, documentation, and any default values.
   System.out.println("LogisticRegression parameters:\n" + lr.explainParams() + "\n");

   // We may set parameters using setter methods.
   lr.setMaxIter(10).setRegParam(0.01);

   // Learn a LogisticRegression model. This uses the parameters stored in lr.
   LogisticRegressionModel model1 = lr.fit(training);
   // Since model1 is a Model (i.e., a Transformer produced by an Estimator),
   // we can view the parameters it used during fit().
   // This prints the parameter (name: value) pairs, where names are unique IDs for this
   // LogisticRegression instance.
   System.out.println("Model 1 was fit using parameters: " + model1.parent().extractParamMap());

   // We may alternatively specify parameters using a ParamMap.
   ParamMap paramMap = new ParamMap()
     .put(lr.maxIter().w(20))  // Specify 1 Param.
     .put(lr.maxIter(), 30)  // This overwrites the original maxIter.
     .put(lr.regParam().w(0.1), lr.threshold().w(0.55));  // Specify multiple Params.

   // One can also combine ParamMaps.
   ParamMap paramMap2 = new ParamMap()
     .put(lr.probabilityCol().w("myProbability"));  // Change output column name
   ParamMap paramMapCombined = paramMap.$plus$plus(paramMap2);

   // Now learn a new model using the paramMapCombined parameters.
   // paramMapCombined overrides all parameters set earlier via lr.set* methods.
   LogisticRegressionModel model2 = lr.fit(training, paramMapCombined);
   System.out.println("Model 2 was fit using parameters: " + model2.parent().extractParamMap());

   // Prepare test documents.
   List<Row> dataTest = Arrays.asList(
       RowFactory.create(1.0, Vectors.dense(-1.0, 1.5, 1.3)),
       RowFactory.create(0.0, Vectors.dense(3.0, 2.0, -0.1)),
       RowFactory.create(1.0, Vectors.dense(0.0, 2.2, -1.5))
   );
   Dataset<Row> test = spark.createDataFrame(dataTest, schema);

   // Make predictions on test documents using the Transformer.transform() method.
   // LogisticRegression.transform will only use the 'features' column.
   // Note that model2.transform() outputs a 'myProbability' column instead of the usual
   // 'probability' column since we renamed the lr.probabilityCol parameter previously.
   Dataset<Row> results = model2.transform(test);
   Dataset<Row> rows = results.select("features", "label", "myProbability", "prediction");
   for (Row r: rows.collectAsList()) {
     System.out.println("(" + r.get(0) + ", " + r.get(1) + ") -> prob=" + r.get(2)
       + ", prediction=" + r.get(3));
   }
   // $example off$

   spark.stop();
 }
开发者ID:PacktPublishing，项目名称:Apache-Spark-2x-for-Java-Developers，代码行数:76，代码来源:JavaEstimatorTransformerParamExample.java



注：本文中的org.apache.spark.ml.linalg.VectorUDT类示例整理自Github/MSDocs等源码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。

鲜花
握手
雷人
路过
鸡蛋
该文章已有0人参与评论

请发表评论

全部评论

专题导读
More+
上一篇：
Java EntityEnderSignal类代码示例发布时间：2022-05-23
下一篇：
Java DefaultHttp2FrameWriter类代码示例发布时间：2022-05-23
热门推荐
More+
热门话题
More+
阅读排行榜

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服（服务时间 9:00～18:00）

在线QQ客服
地址：深圳市南山区西丽大学城创智工业园
电邮：jeky_zhao#qq.com
移动电话：139-2527-9053

Powered by 互联科技 X3.4© 2001-2213 极客世界.|Sitemap