Back to home page

OSCL-LXR

 
 

    


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.MinMaxScaler;
0027 import org.apache.spark.ml.feature.MinMaxScalerModel;
0028 import org.apache.spark.ml.linalg.Vectors;
0029 import org.apache.spark.ml.linalg.VectorUDT;
0030 import org.apache.spark.sql.Dataset;
0031 import org.apache.spark.sql.Row;
0032 import org.apache.spark.sql.RowFactory;
0033 import org.apache.spark.sql.types.DataTypes;
0034 import org.apache.spark.sql.types.Metadata;
0035 import org.apache.spark.sql.types.StructField;
0036 import org.apache.spark.sql.types.StructType;
0037 // $example off$
0038 
0039 public class JavaMinMaxScalerExample {
0040   public static void main(String[] args) {
0041     SparkSession spark = SparkSession
0042       .builder()
0043       .appName("JavaMinMaxScalerExample")
0044       .getOrCreate();
0045 
0046     // $example on$
0047     List<Row> data = Arrays.asList(
0048         RowFactory.create(0, Vectors.dense(1.0, 0.1, -1.0)),
0049         RowFactory.create(1, Vectors.dense(2.0, 1.1, 1.0)),
0050         RowFactory.create(2, Vectors.dense(3.0, 10.1, 3.0))
0051     );
0052     StructType schema = new StructType(new StructField[]{
0053         new StructField("id", DataTypes.IntegerType, false, Metadata.empty()),
0054         new StructField("features", new VectorUDT(), false, Metadata.empty())
0055     });
0056     Dataset<Row> dataFrame = spark.createDataFrame(data, schema);
0057 
0058     MinMaxScaler scaler = new MinMaxScaler()
0059       .setInputCol("features")
0060       .setOutputCol("scaledFeatures");
0061 
0062     // Compute summary statistics and generate MinMaxScalerModel
0063     MinMaxScalerModel scalerModel = scaler.fit(dataFrame);
0064 
0065     // rescale each feature to range [min, max].
0066     Dataset<Row> scaledData = scalerModel.transform(dataFrame);
0067     System.out.println("Features scaled to range: [" + scaler.getMin() + ", "
0068         + scaler.getMax() + "]");
0069     scaledData.select("features", "scaledFeatures").show();
0070     // $example off$
0071 
0072     spark.stop();
0073   }
0074 }