com.andado.spark.examples.ml.JavaPCAExample.java Source code

Introduction

Here is the source code for com.andado.spark.examples.ml.JavaPCAExample.java

Source

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package com.andado.spark.examples.ml;

import org.apache.spark.ml.feature.PCA;
import org.apache.spark.ml.feature.PCAModel;
import org.apache.spark.ml.linalg.VectorUDT;
import org.apache.spark.ml.linalg.Vectors;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.types.Metadata;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;

import java.util.Arrays;
import java.util.List;

// $example on$
// $example off$

public class JavaPCAExample {
    public static void main(String[] args) {
        SparkSession spark = SparkSession.builder().appName("JavaPCAExample").getOrCreate();

        // $example on$
        List<Row> data = Arrays.asList(
                RowFactory.create(Vectors.sparse(5, new int[] { 1, 3 }, new double[] { 1.0, 7.0 })),
                RowFactory.create(Vectors.dense(2.0, 0.0, 3.0, 4.0, 5.0)),
                RowFactory.create(Vectors.dense(4.0, 0.0, 0.0, 6.0, 7.0)));

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

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

        PCAModel pca = new PCA().setInputCol("features").setOutputCol("pcaFeatures").setK(3).fit(df);

        Dataset<Row> result = pca.transform(df).select("pcaFeatures");
        result.show(false);
        // $example off$
        spark.stop();
    }
}