spark JavaBinarizerExample 源码
spark JavaBinarizerExample 代码
文件路径：/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.spark.examples.ml;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.SparkSession;
// $example on$
import java.util.Arrays;
import java.util.List;
import org.apache.spark.ml.feature.Binarizer;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.Metadata;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;
// $example off$
public class JavaBinarizerExample {
public static void main(String[] args) {
SparkSession spark = SparkSession
.builder()
.appName("JavaBinarizerExample")
.getOrCreate();
// $example on$
List<Row> data = Arrays.asList(
RowFactory.create(0, 0.1),
RowFactory.create(1, 0.8),
RowFactory.create(2, 0.2)
);
StructType schema = new StructType(new StructField[]{
new StructField("id", DataTypes.IntegerType, false, Metadata.empty()),
new StructField("feature", DataTypes.DoubleType, false, Metadata.empty())
});
Dataset<Row> continuousDataFrame = spark.createDataFrame(data, schema);
Binarizer binarizer = new Binarizer()
.setInputCol("feature")
.setOutputCol("binarized_feature")
.setThreshold(0.5);
Dataset<Row> binarizedDataFrame = binarizer.transform(continuousDataFrame);
System.out.println("Binarizer output with Threshold = " + binarizer.getThreshold());
binarizedDataFrame.show();
// $example off$
spark.stop();
}
}
相关信息
相关文章
spark JavaAFTSurvivalRegressionExample 源码
spark JavaBisectingKMeansExample 源码
spark JavaBucketedRandomProjectionLSHExample 源码
spark JavaBucketizerExample 源码
spark JavaChiSqSelectorExample 源码
spark JavaChiSquareTestExample 源码
spark JavaCorrelationExample 源码
0
赞
热门推荐
-
2、 - 优质文章
-
3、 gate.io
-
6、 golang
-
7、 openharmony