examples/ml/JavaRFormulaExample.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.SparkSession;
0021
0022 // $example on$
0023 import java.util.Arrays;
0024 import java.util.List;
0025
0026 import org.apache.spark.ml.feature.RFormula;
0027 import org.apache.spark.sql.Dataset;
0028 import org.apache.spark.sql.Row;
0029 import org.apache.spark.sql.RowFactory;
0030 import org.apache.spark.sql.types.StructField;
0031 import org.apache.spark.sql.types.StructType;
0032
0033 import static org.apache.spark.sql.types.DataTypes.*;
0034 // $example off$
0035
0036 public class JavaRFormulaExample {
0037   public static void main(String[] args) {
0038     SparkSession spark = SparkSession
0039       .builder()
0040       .appName("JavaRFormulaExample")
0041       .getOrCreate();
0042
0043     // $example on$
0044     StructType schema = createStructType(new StructField[]{
0045       createStructField("id", IntegerType, false),
0046       createStructField("country", StringType, false),
0047       createStructField("hour", IntegerType, false),
0048       createStructField("clicked", DoubleType, false)
0049     });
0050
0051     List<Row> data = Arrays.asList(
0052       RowFactory.create(7, "US", 18, 1.0),
0053       RowFactory.create(8, "CA", 12, 0.0),
0054       RowFactory.create(9, "NZ", 15, 0.0)
0055     );
0056
0057     Dataset<Row> dataset = spark.createDataFrame(data, schema);
0058     RFormula formula = new RFormula()
0059       .setFormula("clicked ~ country + hour")
0060       .setFeaturesCol("features")
0061       .setLabelCol("label");
0062     Dataset<Row> output = formula.fit(dataset).transform(dataset);
0063     output.select("features", "label").show();
0064     // $example off$
0065     spark.stop();
0066   }
0067 }
0068