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.feature.Normalizer;
0027 import org.apache.spark.ml.linalg.Vectors;
0028 import org.apache.spark.ml.linalg.VectorUDT;
0029 import org.apache.spark.sql.Dataset;
0030 import org.apache.spark.sql.Row;
0031 import org.apache.spark.sql.RowFactory;
0032 import org.apache.spark.sql.types.DataTypes;
0033 import org.apache.spark.sql.types.Metadata;
0034 import org.apache.spark.sql.types.StructField;
0035 import org.apache.spark.sql.types.StructType;
0036
0037
0038 public class JavaNormalizerExample {
0039 public static void main(String[] args) {
0040 SparkSession spark = SparkSession
0041 .builder()
0042 .appName("JavaNormalizerExample")
0043 .getOrCreate();
0044
0045
0046 List<Row> data = Arrays.asList(
0047 RowFactory.create(0, Vectors.dense(1.0, 0.1, -8.0)),
0048 RowFactory.create(1, Vectors.dense(2.0, 1.0, -4.0)),
0049 RowFactory.create(2, Vectors.dense(4.0, 10.0, 8.0))
0050 );
0051 StructType schema = new StructType(new StructField[]{
0052 new StructField("id", DataTypes.IntegerType, false, Metadata.empty()),
0053 new StructField("features", new VectorUDT(), false, Metadata.empty())
0054 });
0055 Dataset<Row> dataFrame = spark.createDataFrame(data, schema);
0056
0057
0058 Normalizer normalizer = new Normalizer()
0059 .setInputCol("features")
0060 .setOutputCol("normFeatures")
0061 .setP(1.0);
0062
0063 Dataset<Row> l1NormData = normalizer.transform(dataFrame);
0064 l1NormData.show();
0065
0066
0067 Dataset<Row> lInfNormData =
0068 normalizer.transform(dataFrame, normalizer.p().w(Double.POSITIVE_INFINITY));
0069 lInfNormData.show();
0070
0071
0072 spark.stop();
0073 }
0074 }