examples/ml/JavaPowerIterationClusteringExample.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 // $example on$
0021 import java.util.Arrays;
0022 import java.util.List;
0023
0024 import org.apache.spark.ml.clustering.PowerIterationClustering;
0025 import org.apache.spark.sql.Dataset;
0026 import org.apache.spark.sql.Row;
0027 import org.apache.spark.sql.RowFactory;
0028 import org.apache.spark.sql.SparkSession;
0029 import org.apache.spark.sql.types.DataTypes;
0030 import org.apache.spark.sql.types.Metadata;
0031 import org.apache.spark.sql.types.StructField;
0032 import org.apache.spark.sql.types.StructType;
0033 // $example off$
0034
0035 public class JavaPowerIterationClusteringExample {
0036   public static void main(String[] args) {
0037     // Create a SparkSession.
0038     SparkSession spark = SparkSession
0039       .builder()
0040       .appName("JavaPowerIterationClustering")
0041       .getOrCreate();
0042
0043     // $example on$
0044     List<Row> data = Arrays.asList(
0045       RowFactory.create(0L, 1L, 1.0),
0046       RowFactory.create(0L, 2L, 1.0),
0047       RowFactory.create(1L, 2L, 1.0),
0048       RowFactory.create(3L, 4L, 1.0),
0049       RowFactory.create(4L, 0L, 0.1)
0050     );
0051
0052     StructType schema = new StructType(new StructField[]{
0053       new StructField("src", DataTypes.LongType, false, Metadata.empty()),
0054       new StructField("dst", DataTypes.LongType, false, Metadata.empty()),
0055       new StructField("weight", DataTypes.DoubleType, false, Metadata.empty())
0056     });
0057
0058     Dataset<Row> df = spark.createDataFrame(data, schema);
0059
0060     PowerIterationClustering model = new PowerIterationClustering()
0061       .setK(2)
0062       .setMaxIter(10)
0063       .setInitMode("degree")
0064       .setWeightCol("weight");
0065
0066     Dataset<Row> result = model.assignClusters(df);
0067     result.show(false);
0068     // $example off$
0069     spark.stop();
0070   }
0071 }