Spark特征(提取，转换，选择)extracting, transforming and selecting features

VectorAssembler字段转换成特征向量 

import org.apache.spark.ml.feature.VectorAssembler

val colArray = Array("age", "yearsmarried", "religiousness", "education", "occupation", "rating")

// 字段转换成特征向量
val assembler = new VectorAssembler().setInputCols(colArray).setOutputCol("features")

val vecDF: DataFrame = assembler.transform(data)
vecDF: org.apache.spark.sql.DataFrame = [affairs: double, gender: string ... 8 more fields]

vecDF.select("features", colArray: _*).show(10, truncate = false)
+----------------------------+----+------------+-------------+---------+----------+------+
|features                    |age |yearsmarried|religiousness|education|occupation|rating|
+----------------------------+----+------------+-------------+---------+----------+------+
|[37.0,10.0,3.0,18.0,7.0,4.0]|37.0|10.0        |3.0          |18.0     |7.0       |4.0   |
|[27.0,4.0,4.0,14.0,6.0,4.0] |27.0|4.0         |4.0          |14.0     |6.0       |4.0   |
|[32.0,15.0,1.0,12.0,1.0,4.0]|32.0|15.0        |1.0          |12.0     |1.0       |4.0   |
|[57.0,15.0,5.0,18.0,6.0,5.0]|57.0|15.0        |5.0          |18.0     |6.0       |5.0   |
|[22.0,0.75,2.0,17.0,6.0,3.0]|22.0|0.75        |2.0          |17.0     |6.0       |3.0   |
|[32.0,1.5,2.0,17.0,5.0,5.0] |32.0|1.5         |2.0          |17.0     |5.0       |5.0   |
|[22.0,0.75,2.0,12.0,1.0,3.0]|22.0|0.75        |2.0          |12.0     |1.0       |3.0   |
|[57.0,15.0,2.0,14.0,4.0,4.0]|57.0|15.0        |2.0          |14.0     |4.0       |4.0   |
|[32.0,15.0,4.0,16.0,1.0,2.0]|32.0|15.0        |4.0          |16.0     |1.0       |2.0   |
|[22.0,1.5,4.0,14.0,4.0,5.0] |22.0|1.5         |4.0          |14.0     |4.0       |5.0   |
+----------------------------+----+------------+-------------+---------+----------+------+
only showing top 10 rows

VectorIndexer自动识别分类的特征，并对它们进行索引

import org.apache.spark.ml.feature.VectorIndexer

val colArray = Array("age", "yearsmarried", "religiousness", "education", "occupation", "rating") 

// 自动识别分类的特征，并对它们进行索引
// 具有大于7个不同的值的特征被视为连续。
val featureIndexer = new VectorIndexer()
.setInputCol("features")
.setOutputCol("indexedFeatures")
.setMaxCategories(7)
.fit(vecDF)


val categoricalFeatures: Set[Int] = featureIndexer.categoryMaps.keys.toSet
categoricalFeatures: Set[Int] = Set(2, 3, 4, 5)

println(s"Chose ${categoricalFeatures.size} categorical features: " +
         categoricalFeatures.mkString(", "))
Chose 4 categorical features: 2, 3, 4, 5

// 由此看出，当MaxCategories=7，从6个字段中识别出了4个“类别特征字段”，
// 他们的下标索引为(2, 3, 4, 5),分别对应colArray中的(2, 3, 4, 5)元素，即"religiousness", "education", "occupation", "rating"
// 为什么识别出了4个“类别特征字段”呢，请看本人博客http://www.cnblogs.com/wwxbi/p/6125363.html“统计字段中元素的个数”
// 从“统计字段中元素的个数”看出，("religiousness", "education", "occupation", "rating")这4个字段的元素个数<=7

// Create new column "indexedFeatures" with categorical values transformed to indices
val indexedData = featureIndexer.transform(vecDF)
indexedData: org.apache.spark.sql.DataFrame = [affairs: double, gender: string ... 9 more fields]

val resColArray = Array("indexedFeatures", "features", "age", "yearsmarried", "religiousness", "education", "occupation", "rating")
resColArray: Array[String] = Array(indexedFeatures, features, age, yearsmarried, religiousness, education, occupation, rating)

indexedData.selectExpr(resColArray: _*).show(10, truncate = false)
+---------------------------+----------------------------+----+------------+-------------+---------+----------+------+
|indexedFeatures            |features                    |age |yearsmarried|religiousness|education|occupation|rating|
+---------------------------+----------------------------+----+------------+-------------+---------+----------+------+
|[37.0,10.0,2.0,5.0,6.0,3.0]|[37.0,10.0,3.0,18.0,7.0,4.0]|37.0|10.0        |3.0          |18.0     |7.0       |4.0   |
|[27.0,4.0,3.0,2.0,5.0,3.0] |[27.0,4.0,4.0,14.0,6.0,4.0] |27.0|4.0         |4.0          |14.0     |6.0       |4.0   |
|[32.0,15.0,0.0,1.0,0.0,3.0]|[32.0,15.0,1.0,12.0,1.0,4.0]|32.0|15.0        |1.0          |12.0     |1.0       |4.0   |
|[57.0,15.0,4.0,5.0,5.0,4.0]|[57.0,15.0,5.0,18.0,6.0,5.0]|57.0|15.0        |5.0          |18.0     |6.0       |5.0   |
|[22.0,0.75,1.0,4.0,5.0,2.0]|[22.0,0.75,2.0,17.0,6.0,3.0]|22.0|0.75        |2.0          |17.0     |6.0       |3.0   |
|[32.0,1.5,1.0,4.0,4.0,4.0] |[32.0,1.5,2.0,17.0,5.0,5.0] |32.0|1.5         |2.0          |17.0     |5.0       |5.0   |
|[22.0,0.75,1.0,1.0,0.0,2.0]|[22.0,0.75,2.0,12.0,1.0,3.0]|22.0|0.75        |2.0          |12.0     |1.0       |3.0   |
|[57.0,15.0,1.0,2.0,3.0,3.0]|[57.0,15.0,2.0,14.0,4.0,4.0]|57.0|15.0        |2.0          |14.0     |4.0       |4.0   |
|[32.0,15.0,3.0,3.0,0.0,1.0]|[32.0,15.0,4.0,16.0,1.0,2.0]|32.0|15.0        |4.0          |16.0     |1.0       |2.0   |
|[22.0,1.5,3.0,2.0,3.0,4.0] |[22.0,1.5,4.0,14.0,4.0,5.0] |22.0|1.5         |4.0          |14.0     |4.0       |5.0   |
+---------------------------+----------------------------+----+------------+-------------+---------+----------+------+
only showing top 10 rows

import org.apache.spark.ml.feature.VectorSlicer

val slicer = new VectorSlicer().setInputCol("indexedFeatures").setOutputCol("slicerFeatures")
slicer.setIndices(Array(3))  // 此处的3对应“索引化”之前的字段“education”

val output = slicer.transform(indexedData)
output.select("indexedFeatures", 
        "slicerFeatures",
        "education").limit(10).orderBy($"education").show(10, truncate = false)
+---------------------------+--------------+---------+
|indexedFeatures            |slicerFeatures|education|
+---------------------------+--------------+---------+
|[32.0,15.0,0.0,1.0,0.0,3.0]|[1.0]         |12.0     |
|[22.0,0.75,1.0,1.0,0.0,2.0]|[1.0]         |12.0     |
|[27.0,4.0,3.0,2.0,5.0,3.0] |[2.0]         |14.0     |
|[57.0,15.0,1.0,2.0,3.0,3.0]|[2.0]         |14.0     |
|[22.0,1.5,3.0,2.0,3.0,4.0] |[2.0]         |14.0     |
|[32.0,15.0,3.0,3.0,0.0,1.0]|[3.0]         |16.0     |
|[32.0,1.5,1.0,4.0,4.0,4.0] |[4.0]         |17.0     |
|[22.0,0.75,1.0,4.0,5.0,2.0]|[4.0]         |17.0     |
|[37.0,10.0,2.0,5.0,6.0,3.0]|[5.0]         |18.0     |
|[57.0,15.0,4.0,5.0,5.0,4.0]|[5.0]         |18.0     |
+---------------------------+--------------+---------+
// 由此看出，“类别特征字段”被索引化后，索引的编号是跟“原字段值的大小顺序”对照的，索引从0开始
// 索引编号(0,1,2,3,4,5,6)对应[9.0, 12.0, 14.0, 16.0, 17.0, 18.0, 20.0]

VectorSlicer向量切割

import org.apache.spark.ml.feature.VectorSlicer

val colArray = Array("age", "yearsmarried", "religiousness", "education", "occupation", "rating") 

// 字段转换成特征向量
val assembler = new VectorAssembler().setInputCols(colArray).setOutputCol("features")
val vecDF = assembler.transform(data)

val slicer = new VectorSlicer().setInputCol("features").setOutputCol("slicerFeatures")
// 指定“向量字段features”中的下标索引
// (2, 3, 4)分别对应字段("religiousness", "education", "occupation")
slicer.setIndices(Array(2, 3, 4)) 

val output = slicer.transform(vecDF)
output.select("features", "slicerFeatures","religiousness", "education", "occupation").show(10, truncate = false)
+----------------------------+--------------+-------------+---------+----------+
|features                    |slicerFeatures|religiousness|education|occupation|
+----------------------------+--------------+-------------+---------+----------+
|[37.0,10.0,3.0,18.0,7.0,4.0]|[3.0,18.0,7.0]|3.0          |18.0     |7.0       |
|[27.0,4.0,4.0,14.0,6.0,4.0] |[4.0,14.0,6.0]|4.0          |14.0     |6.0       |
|[32.0,15.0,1.0,12.0,1.0,4.0]|[1.0,12.0,1.0]|1.0          |12.0     |1.0       |
|[57.0,15.0,5.0,18.0,6.0,5.0]|[5.0,18.0,6.0]|5.0          |18.0     |6.0       |
|[22.0,0.75,2.0,17.0,6.0,3.0]|[2.0,17.0,6.0]|2.0          |17.0     |6.0       |
|[32.0,1.5,2.0,17.0,5.0,5.0] |[2.0,17.0,5.0]|2.0          |17.0     |5.0       |
|[22.0,0.75,2.0,12.0,1.0,3.0]|[2.0,12.0,1.0]|2.0          |12.0     |1.0       |
|[57.0,15.0,2.0,14.0,4.0,4.0]|[2.0,14.0,4.0]|2.0          |14.0     |4.0       |
|[32.0,15.0,4.0,16.0,1.0,2.0]|[4.0,16.0,1.0]|4.0          |16.0     |1.0       |
|[22.0,1.5,4.0,14.0,4.0,5.0] |[4.0,14.0,4.0]|4.0          |14.0     |4.0       |
+----------------------------+--------------+-------------+---------+----------+
only showing top 10 rows


output.printSchema()
root
 |-- affairs: double (nullable = false)
 |-- gender: string (nullable = true)
 |-- age: double (nullable = false)
 |-- yearsmarried: double (nullable = false)
 |-- children: string (nullable = true)
 |-- religiousness: double (nullable = false)
 |-- education: double (nullable = false)
 |-- occupation: double (nullable = false)
 |-- rating: double (nullable = false)
 |-- features: vector (nullable = true)
 |-- slicerFeatures: vector (nullable = true)

Bucketizer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             |
+--------+----------------+