examples/ml/JavaSQLTransformerExample.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.feature.SQLTransformer;
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.*;
0030 // $example off$
0031
0032 public class JavaSQLTransformerExample {
0033   public static void main(String[] args) {
0034     SparkSession spark = SparkSession
0035       .builder()
0036       .appName("JavaSQLTransformerExample")
0037       .getOrCreate();
0038
0039     // $example on$
0040     List<Row> data = Arrays.asList(
0041       RowFactory.create(0, 1.0, 3.0),
0042       RowFactory.create(2, 2.0, 5.0)
0043     );
0044     StructType schema = new StructType(new StructField [] {
0045       new StructField("id", DataTypes.IntegerType, false, Metadata.empty()),
0046       new StructField("v1", DataTypes.DoubleType, false, Metadata.empty()),
0047       new StructField("v2", DataTypes.DoubleType, false, Metadata.empty())
0048     });
0049     Dataset<Row> df = spark.createDataFrame(data, schema);
0050
0051     SQLTransformer sqlTrans = new SQLTransformer().setStatement(
0052       "SELECT *, (v1 + v2) AS v3, (v1 * v2) AS v4 FROM __THIS__");
0053
0054     sqlTrans.transform(df).show();
0055     // $example off$
0056
0057     spark.stop();
0058   }
0059 }