examples/ml/JavaImputerExample.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.Imputer;
0025 import org.apache.spark.ml.feature.ImputerModel;
0026 import org.apache.spark.sql.Dataset;
0027 import org.apache.spark.sql.Row;
0028 import org.apache.spark.sql.RowFactory;
0029 import org.apache.spark.sql.SparkSession;
0030 import org.apache.spark.sql.types.*;
0031 // $example off$
0032
0033 import static org.apache.spark.sql.types.DataTypes.*;
0034
0035 /**
0036  * An example demonstrating Imputer.
0037  * Run with:
0038  *   bin/run-example ml.JavaImputerExample
0039  */
0040 public class JavaImputerExample {
0041   public static void main(String[] args) {
0042     SparkSession spark = SparkSession
0043       .builder()
0044       .appName("JavaImputerExample")
0045       .getOrCreate();
0046
0047     // $example on$
0048     List<Row> data = Arrays.asList(
0049       RowFactory.create(1.0, Double.NaN),
0050       RowFactory.create(2.0, Double.NaN),
0051       RowFactory.create(Double.NaN, 3.0),
0052       RowFactory.create(4.0, 4.0),
0053       RowFactory.create(5.0, 5.0)
0054     );
0055     StructType schema = new StructType(new StructField[]{
0056       createStructField("a", DoubleType, false),
0057       createStructField("b", DoubleType, false)
0058     });
0059     Dataset<Row> df = spark.createDataFrame(data, schema);
0060
0061     Imputer imputer = new Imputer()
0062       .setInputCols(new String[]{"a", "b"})
0063       .setOutputCols(new String[]{"out_a", "out_b"});
0064
0065     ImputerModel model = imputer.fit(df);
0066     model.transform(df).show();
0067     // $example off$
0068
0069     spark.stop();
0070   }
0071 }