upstream/piflow-bundle/src/main/scala/cn/piflow/bundle/ml_clustering/GaussianMixtureTraining.scala
1package cn.piflow.bundle.ml_clustering
2
3import cn.piflow.{JobContext, JobInputStream, JobOutputStream, ProcessContext}
4import cn.piflow.conf.{ConfigurableStop, Port, StopGroup}
5import cn.piflow.conf.bean.PropertyDescriptor
6import cn.piflow.conf.util.{ImageUtil, MapUtil}
7import org.apache.spark.ml.clustering.GaussianMixture
8import org.apache.spark.sql.SparkSession
9
10class GaussianMixtureTraining extends ConfigurableStop{
11 val authorEmail: String = "06whuxx@163.com"
12 val description: String = "GaussianMixture clustering"
13 val inportList: List[String] = List(Port.DefaultPort)
14 val outportList: List[String] = List(Port.DefaultPort)
15 var training_data_path:String =_
16 var model_save_path:String=_
17 var k:String=_
18 var maxIter:String=_
19 var tol:String=_
20
21 def perform(in: JobInputStream, out: JobOutputStream, pec: JobContext): Unit = {
22 val spark = pec.get[SparkSession]()
23
24 //load data stored in libsvm format as a dataframe
25 val data=spark.read.format("libsvm").load(training_data_path)
26
27 var kValue:Int=2
28 if(k!=""){
29 kValue=k.toInt
30 }
31
32 //Param for maximum number of iterations (>= 0)
33 var maxIterValue:Int=50
34 if(maxIter!=""){
35 maxIterValue=maxIter.toInt
36 }
37
38
39 var tolValue:Double=0.0001
40 if(tol=="online"){
41 tolValue=tol.toDouble
42 }
43
44
45 //clustering with GaussianMixture algorithm
46 val model=new GaussianMixture()
47 .setMaxIter(maxIterValue)
48 .setTol(tolValue)
49 .setK(kValue)
50 .fit(data)
51
52 //model persistence
53 model.save(model_save_path)
54
55 import spark.implicits._
56 val dfOut=Seq(model_save_path).toDF
57 dfOut.show()
58 out.write(dfOut)
59
60 }
61
62 def initialize(ctx: ProcessContext): Unit = {
63
64 }
65
66
67 def setProperties(map: Map[String, Any]): Unit = {
68 training_data_path=MapUtil.get(map,key="training_data_path").asInstanceOf[String]
69 model_save_path=MapUtil.get(map,key="model_save_path").asInstanceOf[String]
70 maxIter=MapUtil.get(map,key="maxIter").asInstanceOf[String]
71 k=MapUtil.get(map,key="k").asInstanceOf[String]
72 tol=MapUtil.get(map,key="tol").asInstanceOf[String]
73
74 }
75
76 override def getPropertyDescriptor(): List[PropertyDescriptor] = {
77 var descriptor : List[PropertyDescriptor] = List()
78 val training_data_path = new PropertyDescriptor().name("training_data_path").displayName("TRAINING_DATA_PATH").defaultValue("").required(true)
79 val model_save_path = new PropertyDescriptor().name("model_save_path").displayName("MODEL_SAVE_PATH").description("").defaultValue("").required(true)
80 val maxIter=new PropertyDescriptor().name("maxIter").displayName("MAX_ITER").description("Param for maximum number of iterations (>= 0).").defaultValue("").required(false)
81 val k=new PropertyDescriptor().name("k").displayName("K").description("Number of independent Gaussians in the mixture model. Must be greater than 1. Default: 2. ").defaultValue("").required(false)
82 val tol=new PropertyDescriptor().name("tol").displayName("TOL").description("Param for the convergence tolerance for iterative algorithms (>= 0).").defaultValue("").required(false)
83 descriptor = training_data_path :: descriptor
84 descriptor = model_save_path :: descriptor
85 descriptor = maxIter :: descriptor
86 descriptor = tol :: descriptor
87 descriptor = k :: descriptor
88 descriptor
89 }
90
91 override def getIcon(): Array[Byte] = {
92 ImageUtil.getImage("icon/ml_clustering/GaussianMixtureTraining.png")
93 }
94
95 override def getGroup(): List[String] = {
96 List(StopGroup.MLGroup.toString)
97 }
98
99}