0001
0002
0003
0004
0005
0006
0007
0008
0009
0010
0011
0012
0013
0014
0015
0016
0017
0018 package org.apache.spark.examples.ml;
0019
0020 import org.apache.spark.sql.SparkSession;
0021
0022
0023 import java.util.Arrays;
0024 import java.util.List;
0025
0026 import org.apache.spark.ml.attribute.Attribute;
0027 import org.apache.spark.ml.attribute.AttributeGroup;
0028 import org.apache.spark.ml.attribute.NumericAttribute;
0029 import org.apache.spark.ml.feature.VectorSlicer;
0030 import org.apache.spark.ml.linalg.Vectors;
0031 import org.apache.spark.sql.Dataset;
0032 import org.apache.spark.sql.Row;
0033 import org.apache.spark.sql.RowFactory;
0034 import org.apache.spark.sql.types.*;
0035
0036
0037 public class JavaVectorSlicerExample {
0038 public static void main(String[] args) {
0039 SparkSession spark = SparkSession
0040 .builder()
0041 .appName("JavaVectorSlicerExample")
0042 .getOrCreate();
0043
0044
0045 Attribute[] attrs = {
0046 NumericAttribute.defaultAttr().withName("f1"),
0047 NumericAttribute.defaultAttr().withName("f2"),
0048 NumericAttribute.defaultAttr().withName("f3")
0049 };
0050 AttributeGroup group = new AttributeGroup("userFeatures", attrs);
0051
0052 List<Row> data = Arrays.asList(
0053 RowFactory.create(Vectors.sparse(3, new int[]{0, 1}, new double[]{-2.0, 2.3})),
0054 RowFactory.create(Vectors.dense(-2.0, 2.3, 0.0))
0055 );
0056
0057 Dataset<Row> dataset =
0058 spark.createDataFrame(data, (new StructType()).add(group.toStructField()));
0059
0060 VectorSlicer vectorSlicer = new VectorSlicer()
0061 .setInputCol("userFeatures").setOutputCol("features");
0062
0063 vectorSlicer.setIndices(new int[]{1}).setNames(new String[]{"f3"});
0064
0065
0066 Dataset<Row> output = vectorSlicer.transform(dataset);
0067 output.show(false);
0068
0069
0070 spark.stop();
0071 }
0072 }
0073