upstream/piflow-bundle/src/main/scala/cn/piflow/bundle/ml_classification/DecisionTreeTraining.scala
1package cn.piflow.bundle.ml_classification
2
3import cn.piflow.conf.bean.PropertyDescriptor
4import cn.piflow.conf.util.{ImageUtil, MapUtil}
5import cn.piflow.conf.{ConfigurableStop, Port, StopGroup}
6import cn.piflow.{JobContext, JobInputStream, JobOutputStream, ProcessContext}
7import org.apache.spark.ml.classification.DecisionTreeClassifier
8import org.apache.spark.sql.SparkSession
9
10class DecisionTreeTraining extends ConfigurableStop{
11 val authorEmail: String = "06whuxx@163.com"
12 val description: String = "Train a decision tree model"
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 maxBins:String=_
18 var maxDepth:String=_
19 var minInfoGain:String=_
20 var minInstancesPerNode:String=_
21 var impurity:String=_
22
23 def perform(in: JobInputStream, out: JobOutputStream, pec: JobContext): Unit = {
24 val spark = pec.get[SparkSession]()
25
26 //load data stored in libsvm format as a dataframe
27 val data=spark.read.format("libsvm").load(training_data_path)
28
29 //Maximum number of bins used for discretizing continuous features and for choosing how to split on features at each node. More bins give higher granularity.Must be >= 2 and >= number of categories in any categorical feature.
30 var maxBinsValue:Int=40
31 if(maxBins!=""){
32 maxBinsValue=maxBins.toInt
33 }
34
35 //Maximum depth of the tree (>= 0).The maximum is 30.
36 var maxDepthValue:Int=30
37 if(maxDepth!=""){
38 maxDepthValue=maxDepth.toInt
39 }
40
41 //Minimum information gain for a split to be considered at a tree node.
42 var minInfoGainValue:Double=0.2
43 if(minInfoGain!=""){
44 minInfoGainValue=minInfoGain.toDouble
45 }
46
47 //Minimum number of instances each child must have after split.
48 var minInstancesPerNodeValue:Int=3
49 if(minInstancesPerNode!=""){
50 minInstancesPerNodeValue=minInstancesPerNode.toInt
51 }
52
53 //Param for the name of family which is a description of the label distribution to be used in the model
54 var impurityValue="gini"
55 if(impurity!=""){
56 impurityValue=impurity
57 }
58
59 //training a Decision Tree model
60 val model=new DecisionTreeClassifier()
61 .setMaxBins(maxBinsValue)
62 .setMaxDepth(maxDepthValue)
63 .setMinInfoGain(minInfoGainValue)
64 .setMinInstancesPerNode(minInstancesPerNodeValue)
65 .setImpurity(impurityValue)
66 .fit(data)
67
68 //model persistence
69 model.save(model_save_path)
70
71 import spark.implicits._
72 val dfOut=Seq(model_save_path).toDF
73 dfOut.show()
74 out.write(dfOut)
75
76 }
77
78 def initialize(ctx: ProcessContext): Unit = {
79
80 }
81
82
83 def setProperties(map: Map[String, Any]): Unit = {
84 training_data_path=MapUtil.get(map,key="training_data_path").asInstanceOf[String]
85 model_save_path=MapUtil.get(map,key="model_save_path").asInstanceOf[String]
86 maxBins=MapUtil.get(map,key="maxBins").asInstanceOf[String]
87 maxDepth=MapUtil.get(map,key="maxDepth").asInstanceOf[String]
88 minInfoGain=MapUtil.get(map,key="minInfoGain").asInstanceOf[String]
89 minInstancesPerNode=MapUtil.get(map,key="minInstancesPerNode").asInstanceOf[String]
90 impurity=MapUtil.get(map,key="impurity").asInstanceOf[String]
91
92 }
93
94 override def getPropertyDescriptor(): List[PropertyDescriptor] = {
95 var descriptor : List[PropertyDescriptor] = List()
96 val training_data_path = new PropertyDescriptor().name("training_data_path").displayName("TRAINING_DATA_PATH").defaultValue("").required(true)
97 val model_save_path = new PropertyDescriptor().name("model_save_path").displayName("MODEL_SAVE_PATH").description("ddd").defaultValue("").required(true)
98 val maxBins=new PropertyDescriptor().name("maxBins").displayName("MAX_BINS").description("Maximum number of bins used for discretizing continuous features and for choosing how to split on features at each node.").defaultValue("").required(true)
99 val maxDepth=new PropertyDescriptor().name("maxDepth").displayName("MAX_DEPTH").description("Maximum depth of the tree").defaultValue("").required(true)
100 val minInfoGain=new PropertyDescriptor().name("minInfoGain").displayName("MIN_INFO_GAIN").description("Minimum information gain for a split to be considered at a tree node").defaultValue("").required(true)
101 val minInstancesPerNode=new PropertyDescriptor().name("minInstancesPerNode").displayName("MIN_INSTANCES_PER_NODE").description("Minimum number of instances each child must have after split.").defaultValue("").required(true)
102 val impurity=new PropertyDescriptor().name("impurity").displayName("IMPURITY").description("Criterion used for information gain calculation (case-insensitive). Supported: \"entropy\" and \"gini\". (default = gini)").defaultValue("").required(true)
103 descriptor = training_data_path :: descriptor
104 descriptor = model_save_path :: descriptor
105 descriptor = maxBins :: descriptor
106 descriptor = maxDepth :: descriptor
107 descriptor = minInfoGain :: descriptor
108 descriptor = minInstancesPerNode :: descriptor
109 descriptor = impurity :: descriptor
110 descriptor
111 }
112
113 override def getIcon(): Array[Byte] = {
114 ImageUtil.getImage("icon/ml_classification/DecisionTreeTraining.png")
115 }
116
117 override def getGroup(): List[String] = {
118 List(StopGroup.MLGroup.toString)
119 }
120
121}