examples/ml/JavaElementwiseProductExample.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.Dataset;
0021 import org.apache.spark.sql.SparkSession;
0022
0023 // $example on$
0024 import java.util.ArrayList;
0025 import java.util.Arrays;
0026 import java.util.List;
0027
0028 import org.apache.spark.ml.feature.ElementwiseProduct;
0029 import org.apache.spark.ml.linalg.Vector;
0030 import org.apache.spark.ml.linalg.VectorUDT;
0031 import org.apache.spark.ml.linalg.Vectors;
0032 import org.apache.spark.sql.Row;
0033 import org.apache.spark.sql.RowFactory;
0034 import org.apache.spark.sql.types.DataTypes;
0035 import org.apache.spark.sql.types.StructField;
0036 import org.apache.spark.sql.types.StructType;
0037 // $example off$
0038
0039 public class JavaElementwiseProductExample {
0040   public static void main(String[] args) {
0041     SparkSession spark = SparkSession
0042       .builder()
0043       .appName("JavaElementwiseProductExample")
0044       .getOrCreate();
0045
0046     // $example on$
0047     // Create some vector data; also works for sparse vectors
0048     List<Row> data = Arrays.asList(
0049       RowFactory.create("a", Vectors.dense(1.0, 2.0, 3.0)),
0050       RowFactory.create("b", Vectors.dense(4.0, 5.0, 6.0))
0051     );
0052
0053     List<StructField> fields = new ArrayList<>(2);
0054     fields.add(DataTypes.createStructField("id", DataTypes.StringType, false));
0055     fields.add(DataTypes.createStructField("vector", new VectorUDT(), false));
0056
0057     StructType schema = DataTypes.createStructType(fields);
0058
0059     Dataset<Row> dataFrame = spark.createDataFrame(data, schema);
0060
0061     Vector transformingVector = Vectors.dense(0.0, 1.0, 2.0);
0062
0063     ElementwiseProduct transformer = new ElementwiseProduct()
0064       .setScalingVec(transformingVector)
0065       .setInputCol("vector")
0066       .setOutputCol("transformedVector");
0067
0068     // Batch transform the vectors to create new column:
0069     transformer.transform(dataFrame).show();
0070     // $example off$
0071     spark.stop();
0072   }
0073 }