Spark2 feature Bucketizer之将连续数据离散化到指定的范围区间

import org.apache.spark.ml.feature.Bucketizer

// Double.NegativeInfinity：负无穷；Double.PositiveInfinity：正无穷
// 分为6个组：[负无穷,-100),[-100,-10),[-10,0),[0,10),[10,90),[90,正无穷)
val splits = Array(Double.NegativeInfinity, -100, -10, 0.0, 10, 90, Double.PositiveInfinity)

val data: Array[Double] = Array(-180,-160,-100,-50,-70,-20,-8,-5,-3, 0.0, 1,3,7,10,30,60,90,100,120,150)

val dataFrame = spark.createDataFrame(data.map(Tuple1.apply)).toDF("features")
dataFrame: org.apache.spark.sql.DataFrame = [features: double]

val bucketizer = new Bucketizer()
.setInputCol("features")
.setOutputCol("bucketedFeatures")
.setSplits(splits)

// 将原始数据转换为桶索引
val bucketedData = bucketizer.transform(dataFrame)
bucketedData: org.apache.spark.sql.DataFrame = [features: double, bucketedFeatures: double]

bucketedData.show(50,truncate=false)
+--------+----------------+
|features|bucketedFeatures|
+--------+----------------+
|-180.0  |0.0             |
|-160.0  |0.0             |
|-100.0  |1.0             |
|-50.0   |1.0             |
|-70.0   |1.0             |
|-20.0   |1.0             |
|-8.0    |2.0             |
|-5.0    |2.0             |
|-3.0    |2.0             |
|0.0     |3.0             |
|1.0     |3.0             |
|3.0     |3.0             |
|7.0     |3.0             |
|10.0    |4.0             |
|30.0    |4.0             |
|60.0    |4.0             |
|90.0    |5.0             |
|100.0   |5.0             |
|120.0   |5.0             |
|150.0   |5.0             |
+--------+----------------+