blob: a4f62e78710d44b12cb6292c1f632c494d233912 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
|
/*
* 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.
*/
// scalastyle:off println
package org.apache.spark.examples.ml
// $example on$
import org.apache.spark.ml.feature.Binarizer
// $example off$
import org.apache.spark.sql.{SparkSession}
object BinarizerExample {
def main(args: Array[String]): Unit = {
val spark = SparkSession
.builder
.appName("BinarizerExample")
.getOrCreate()
// $example on$
val data = Array((0, 0.1), (1, 0.8), (2, 0.2))
val dataFrame = spark.createDataFrame(data).toDF("id", "feature")
val binarizer: Binarizer = new Binarizer()
.setInputCol("feature")
.setOutputCol("binarized_feature")
.setThreshold(0.5)
val binarizedDataFrame = binarizer.transform(dataFrame)
println(s"Binarizer output with Threshold = ${binarizer.getThreshold}")
binarizedDataFrame.show()
// $example off$
spark.stop()
}
}
// scalastyle:on println
|