spark MLlib DataType ML中的数据类型

package ML.DataType;


import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.mllib.linalg.*;
import org.apache.spark.mllib.linalg.distributed.*;
import org.apache.spark.mllib.regression.LabeledPoint;
import org.apache.spark.mllib.util.MLUtils;

import java.util.Arrays;

/**
 * TODO
 *
 * @ClassName: DataType
 * @author: DingH
 * @since: 2019/4/3 10:06
 */
public class DataType {
    public static void main(String[] args) {

        SparkConf conf = new SparkConf().setMaster("local").setAppName("Datatype");
        JavaSparkContext javaSparkContext = new JavaSparkContext(conf);

        /**
         * @Title: vectors.dense方法生成向量，sparse生成稀疏向量。第一个3是向量的大小，第二个列表是不为0的下表，第三个是对应的value.
         */
        Vector dense = Vectors.dense(1.0, 0.0, 3.0);
        Vector sparse = Vectors.sparse(3, new int[]{0, 2}, new double[]{1.0, 3.0});

        /**
         * @Title: 对向量进行标记，1.0为正，0.0为负
         */
        LabeledPoint labeledPoint = new LabeledPoint(1.0, dense);
        LabeledPoint labeledPoint1 = new LabeledPoint(0.0, sparse);

        /**
         * @Title: libSVM文件： lable1  index1:value1  index2:value2
         */
        JavaRDD<LabeledPoint> labeledPointJavaRDD = MLUtils.loadLibSVMFile(javaSparkContext.sc(), "/data...").toJavaRDD();

        /**
         * @Title: matricex.dense生成矩阵。3*2的矩阵  列式优先
         * [1.0 2.0
         * 3.0 4.0
         * 5.0 6.0]
         */
        Matrix dense1 = Matrices.dense(3, 2, new double[]{1.0, 3.0, 5.0, 2.0, 4.0, 6.0});

        /**
         * @Title: matricex.sparse生成稀疏矩阵。3*2的矩阵。第三个参数和第四个参数对应为不为0的元素。
         * [9 0
         * 0 6
         * 0 8]     第三个参数： 1-0=1，3-1=2，每列不为0的元素分别是1个和2个。   第四个参数，从头开始遍历行，不为0的行。
         */
        Matrix sparse1 = Matrices.sparse(3, 2, new int[]{0, 1, 3}, new int[]{0, 2, 1}, new double[]{9, 6, 8});

        /**
         * @Title: Rowmatrix
         */
        JavaRDD<Vector> parallelize = javaSparkContext.parallelize(Arrays.asList(
                Vectors.dense(1, 2, 3),
                Vectors.dense(2, 3, 4),
                Vectors.dense(3, 4, 5)
        ));
        RowMatrix rowMatrix = new RowMatrix(parallelize.rdd());
        long l = rowMatrix.numRows();
        long l1 = rowMatrix.numCols();
        QRDecomposition<RowMatrix, Matrix> rowMatrixMatrixQRDecomposition = rowMatrix.tallSkinnyQR(true);

        /**
         * @Title: IndexedRowMatrix
         */
        JavaRDD<IndexedRow> parallelize1 = javaSparkContext.parallelize(Arrays.asList(
                new IndexedRow(1, dense),
                new IndexedRow(2, dense),
                new IndexedRow(3, dense)
        ));
        IndexedRowMatrix indexedRowMatrix = new IndexedRowMatrix(parallelize1.rdd());
        long l2 = indexedRowMatrix.numCols();
        long l3 = indexedRowMatrix.numRows();
        RowMatrix rowMatrix1 = indexedRowMatrix.toRowMatrix();

        /**
         * @Title: CoordinateMatrix
         */
        JavaRDD<MatrixEntry> parallelize2 = javaSparkContext.parallelize(Arrays.asList(
                new MatrixEntry(0, 1, 3),
                new MatrixEntry(1, 3, 1),
                new MatrixEntry(2, 1, 1)
        ));
        CoordinateMatrix coordinateMatrix = new CoordinateMatrix(parallelize2.rdd());
        long l4 = coordinateMatrix.numCols();
        long l5 = coordinateMatrix.numRows();
        IndexedRowMatrix indexedRowMatrix1 = coordinateMatrix.toIndexedRowMatrix();

        /**
         * @Title: BlocakMatrix 。   toBlockMatrix可以设置参数，规定row,col的大小，默认1024*1024
         */
        BlockMatrix cache = indexedRowMatrix.toBlockMatrix().cache();
        BlockMatrix cache1 = coordinateMatrix.toBlockMatrix().cache();
        cache.validate();
        BlockMatrix multiply = cache.transpose().multiply(cache);
    }
}