examples/ml/JavaPCAExample.java

0001 /*
0002  * Licensed to the Apache Software Foundation (ASF) under one or more
0003  * contributor license agreements.  See the NOTICE file distributed with
0004  * this work for additional information regarding copyright ownership.
0005  * The ASF licenses this file to You under the Apache License, Version 2.0
0006  * (the "License"); you may not use this file except in compliance with
0007  * the License.  You may obtain a copy of the License at
0008  *
0009  *    http://www.apache.org/licenses/LICENSE-2.0
0010  *
0011  * Unless required by applicable law or agreed to in writing, software
0012  * distributed under the License is distributed on an "AS IS" BASIS,
0013  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014  * See the License for the specific language governing permissions and
0015  * limitations under the License.
0016  */
0017
0018 package org.apache.spark.examples.ml;
0019
0020 import org.apache.spark.sql.SparkSession;
0021
0022 // $example on$
0023 import java.util.Arrays;
0024 import java.util.List;
0025
0026 import org.apache.spark.ml.feature.PCA;
0027 import org.apache.spark.ml.feature.PCAModel;
0028 import org.apache.spark.ml.linalg.VectorUDT;
0029 import org.apache.spark.ml.linalg.Vectors;
0030 import org.apache.spark.sql.Dataset;
0031 import org.apache.spark.sql.Row;
0032 import org.apache.spark.sql.RowFactory;
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 // $example off$
0037
0038 public class JavaPCAExample {
0039   public static void main(String[] args) {
0040     SparkSession spark = SparkSession
0041       .builder()
0042       .appName("JavaPCAExample")
0043       .getOrCreate();
0044
0045     // $example on$
0046     List<Row> data = Arrays.asList(
0047       RowFactory.create(Vectors.sparse(5, new int[]{1, 3}, new double[]{1.0, 7.0})),
0048       RowFactory.create(Vectors.dense(2.0, 0.0, 3.0, 4.0, 5.0)),
0049       RowFactory.create(Vectors.dense(4.0, 0.0, 0.0, 6.0, 7.0))
0050     );
0051
0052     StructType schema = new StructType(new StructField[]{
0053       new StructField("features", new VectorUDT(), false, Metadata.empty()),
0054     });
0055
0056     Dataset<Row> df = spark.createDataFrame(data, schema);
0057
0058     PCAModel pca = new PCA()
0059       .setInputCol("features")
0060       .setOutputCol("pcaFeatures")
0061       .setK(3)
0062       .fit(df);
0063
0064     Dataset<Row> result = pca.transform(df).select("pcaFeatures");
0065     result.show(false);
0066     // $example off$
0067     spark.stop();
0068   }
0069 }
0070