examples/ml/JavaSummarizerExample.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.*;
0021
0022 // $example on$
0023 import java.util.Arrays;
0024 import java.util.List;
0025
0026 import org.apache.spark.ml.linalg.Vector;
0027 import org.apache.spark.ml.linalg.Vectors;
0028 import org.apache.spark.ml.linalg.VectorUDT;
0029 import org.apache.spark.ml.stat.Summarizer;
0030 import org.apache.spark.sql.types.DataTypes;
0031 import org.apache.spark.sql.types.Metadata;
0032 import org.apache.spark.sql.types.StructField;
0033 import org.apache.spark.sql.types.StructType;
0034 // $example off$
0035
0036 public class JavaSummarizerExample {
0037   public static void main(String[] args) {
0038     SparkSession spark = SparkSession
0039       .builder()
0040       .appName("JavaSummarizerExample")
0041       .getOrCreate();
0042
0043     // $example on$
0044     List<Row> data = Arrays.asList(
0045       RowFactory.create(Vectors.dense(2.0, 3.0, 5.0), 1.0),
0046       RowFactory.create(Vectors.dense(4.0, 6.0, 7.0), 2.0)
0047     );
0048
0049     StructType schema = new StructType(new StructField[]{
0050       new StructField("features", new VectorUDT(), false, Metadata.empty()),
0051       new StructField("weight", DataTypes.DoubleType, false, Metadata.empty())
0052     });
0053
0054     Dataset<Row> df = spark.createDataFrame(data, schema);
0055
0056     Row result1 = df.select(Summarizer.metrics("mean", "variance")
0057       .summary(new Column("features"), new Column("weight")).as("summary"))
0058       .select("summary.mean", "summary.variance").first();
0059     System.out.println("with weight: mean = " + result1.<Vector>getAs(0).toString() +
0060       ", variance = " + result1.<Vector>getAs(1).toString());
0061
0062     Row result2 = df.select(
0063       Summarizer.mean(new Column("features")),
0064       Summarizer.variance(new Column("features"))
0065     ).first();
0066     System.out.println("without weight: mean = " + result2.<Vector>getAs(0).toString() +
0067       ", variance = " + result2.<Vector>getAs(1).toString());
0068     // $example off$
0069     spark.stop();
0070   }
0071 }