本文整理汇总了Scala中org.apache.spark.ml.classification.DecisionTreeClassificationModel类的典型用法代码示例。如果您正苦于以下问题：Scala DecisionTreeClassificationModel类的具体用法？Scala DecisionTreeClassificationModel怎么用？Scala DecisionTreeClassificationModel使用的例子？那么, 这里精选的类代码示例或许可以为您提供帮助。
在下文中一共展示了DecisionTreeClassificationModel类的5个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Scala代码示例。
示例1: LocalDecisionTreeClassificationModel
//设置package包名称以及导入依赖的类
package io.hydrosphere.spark_ml_serving.classification
import io.hydrosphere.spark_ml_serving._
import org.apache.spark.ml.classification.DecisionTreeClassificationModel
import org.apache.spark.ml.linalg.{Vector, Vectors}
import org.apache.spark.ml.tree.Node
class LocalDecisionTreeClassificationModel(override val sparkTransformer: DecisionTreeClassificationModel) extends LocalTransformer[DecisionTreeClassificationModel] {
override def transform(localData: LocalData): LocalData = {
localData.column(sparkTransformer.getFeaturesCol) match {
case Some(column) =>
val method = classOf[DecisionTreeClassificationModel].getMethod("predict", classOf[Vector])
method.setAccessible(true)
val newColumn = LocalDataColumn(sparkTransformer.getPredictionCol, column.data.map(f => Vectors.dense(f.asInstanceOf[Array[Double]])).map { vector =>
method.invoke(sparkTransformer, vector).asInstanceOf[Double]
})
localData.withColumn(newColumn)
case None => localData
}
}
}
object LocalDecisionTreeClassificationModel extends LocalModel[DecisionTreeClassificationModel] {
override def load(metadata: Metadata, data: Map[String, Any]): DecisionTreeClassificationModel = {
createTree(metadata, data)
}
def createTree(metadata: Metadata, data: Map[String, Any]): DecisionTreeClassificationModel = {
val ctor = classOf[DecisionTreeClassificationModel].getDeclaredConstructor(classOf[String], classOf[Node], classOf[Int], classOf[Int])
ctor.setAccessible(true)
val inst = ctor.newInstance(
metadata.uid,
DataUtils.createNode(0, metadata, data),
metadata.numFeatures.get.asInstanceOf[java.lang.Integer],
metadata.numClasses.get.asInstanceOf[java.lang.Integer]
)
inst
.setFeaturesCol(metadata.paramMap("featuresCol").asInstanceOf[String])
.setPredictionCol(metadata.paramMap("predictionCol").asInstanceOf[String])
.setProbabilityCol(metadata.paramMap("probabilityCol").asInstanceOf[String])
.setRawPredictionCol(metadata.paramMap("rawPredictionCol").asInstanceOf[String])
inst
.set(inst.seed, metadata.paramMap("seed").toString.toLong)
.set(inst.cacheNodeIds, metadata.paramMap("cacheNodeIds").toString.toBoolean)
.set(inst.maxDepth, metadata.paramMap("maxDepth").toString.toInt)
.set(inst.labelCol, metadata.paramMap("labelCol").toString)
.set(inst.minInfoGain, metadata.paramMap("minInfoGain").toString.toDouble)
.set(inst.checkpointInterval, metadata.paramMap("checkpointInterval").toString.toInt)
.set(inst.minInstancesPerNode, metadata.paramMap("minInstancesPerNode").toString.toInt)
.set(inst.maxMemoryInMB, metadata.paramMap("maxMemoryInMB").toString.toInt)
.set(inst.maxBins, metadata.paramMap("maxBins").toString.toInt)
.set(inst.impurity, metadata.paramMap("impurity").toString)
}
override implicit def getTransformer(transformer: DecisionTreeClassificationModel): LocalTransformer[DecisionTreeClassificationModel] = new LocalDecisionTreeClassificationModel(transformer)
} 示例2: Forest
//设置package包名称以及导入依赖的类
package com.redislabs.provider.redis.ml
import org.apache.spark.ml.tree
import org.apache.spark.ml.classification.DecisionTreeClassificationModel
import redis.clients.jedis.Protocol.Command
import redis.clients.jedis.{Jedis, _}
import com.redislabs.client.redisml.MLClient
import org.apache.spark.ml.tree.{CategoricalSplit, ContinuousSplit, InternalNode}
class Forest(trees: Array[DecisionTreeClassificationModel]) {
private def subtreeToRedisString(n: org.apache.spark.ml.tree.Node, path: String = "."): String = {
val prefix: String = s",${path},"
n.getClass.getSimpleName match {
case "InternalNode" => {
val in = n.asInstanceOf[InternalNode]
val splitStr = in.split match {
case contSplit: ContinuousSplit => s"numeric,${in.split.featureIndex},${contSplit.threshold}"
case catSplit: CategoricalSplit => s"categoric,${in.split.featureIndex}," +
catSplit.leftCategories.mkString(":")
}
prefix + splitStr + subtreeToRedisString(in.leftChild, path + "l") +
subtreeToRedisString(in.rightChild, path + "r")
}
case "LeafNode" => {
prefix + s"leaf,${n.prediction}" +
s",stats,${n.getImpurityStats.mkString(":")}"
}
}
}
private def toRedisString: String = {
trees.zipWithIndex.map { case (tree, treeIndex) =>
s"${treeIndex}" + subtreeToRedisString(tree.rootNode, ".")
}.fold("") { (a, b) => a + "\n" + b }
}
def toDebugArray: Array[String] = {
toRedisString.split("\n").drop(1)
}
def loadToRedis(forestId: String = "test_forest", host: String = "localhost") {
val jedis = new Jedis(host)
val commands = toRedisString.split("\n").drop(1)
jedis.getClient.sendCommand(Command.MULTI)
jedis.getClient().getStatusCodeReply
for (cmd <- commands) {
val cmdArray = forestId +: cmd.split(",")
jedis.getClient.sendCommand(MLClient.ModuleCommand.FOREST_ADD, cmdArray: _*)
jedis.getClient().getStatusCodeReply
}
jedis.getClient.sendCommand(Command.EXEC)
jedis.getClient.getMultiBulkReply
}
} 示例3: LocalRandomForestClassificationModel
//设置package包名称以及导入依赖的类
package io.hydrosphere.mist.api.ml.classification
import io.hydrosphere.mist.api.ml._
import org.apache.spark.ml.classification.{DecisionTreeClassificationModel, RandomForestClassificationModel}
import org.apache.spark.ml.linalg.{DenseVector, Vector, Vectors}
class LocalRandomForestClassificationModel(override val sparkTransformer: RandomForestClassificationModel) extends LocalTransformer[RandomForestClassificationModel] {
override def transform(localData: LocalData): LocalData = {
localData.column(sparkTransformer.getFeaturesCol) match {
case Some(column) =>
val cls = classOf[RandomForestClassificationModel]
val rawPredictionCol = LocalDataColumn(sparkTransformer.getRawPredictionCol, column.data.map(f => Vectors.dense(f.asInstanceOf[Array[Double]])).map { vector =>
val predictRaw = cls.getDeclaredMethod("predictRaw", classOf[Vector])
predictRaw.invoke(sparkTransformer, vector)
})
val probabilityCol = LocalDataColumn(sparkTransformer.getProbabilityCol, rawPredictionCol.data.map(_.asInstanceOf[DenseVector]).map { vector =>
val raw2probabilityInPlace = cls.getDeclaredMethod("raw2probabilityInPlace", classOf[Vector])
raw2probabilityInPlace.invoke(sparkTransformer, vector.copy)
})
val predictionCol = LocalDataColumn(sparkTransformer.getPredictionCol, rawPredictionCol.data.map(_.asInstanceOf[DenseVector]).map { vector =>
val raw2prediction = cls.getMethod("raw2prediction", classOf[Vector])
raw2prediction.invoke(sparkTransformer, vector.copy)
})
localData.withColumn(rawPredictionCol)
.withColumn(probabilityCol)
.withColumn(predictionCol)
case None => localData
}
}
}
object LocalRandomForestClassificationModel extends LocalModel[RandomForestClassificationModel] {
override def load(metadata: Metadata, data: Map[String, Any]): RandomForestClassificationModel = {
val treesMetadata = metadata.paramMap("treesMetadata").asInstanceOf[Map[String, Any]]
val trees = treesMetadata map { treeKv =>
val treeMeta = treeKv._2.asInstanceOf[Map[String, Any]]
val meta = treeMeta("metadata").asInstanceOf[Metadata]
LocalDecisionTreeClassificationModel.createTree(
meta,
data(treeKv._1).asInstanceOf[Map[String, Any]]
)
}
val ctor = classOf[RandomForestClassificationModel].getDeclaredConstructor(classOf[String], classOf[Array[DecisionTreeClassificationModel]], classOf[Int], classOf[Int])
ctor.setAccessible(true)
ctor
.newInstance(
metadata.uid,
trees.to[Array],
metadata.numFeatures.get.asInstanceOf[java.lang.Integer],
metadata.numClasses.get.asInstanceOf[java.lang.Integer]
)
.setFeaturesCol(metadata.paramMap("featuresCol").asInstanceOf[String])
.setPredictionCol(metadata.paramMap("predictionCol").asInstanceOf[String])
.setProbabilityCol(metadata.paramMap("probabilityCol").asInstanceOf[String])
}
override implicit def getTransformer(transformer: RandomForestClassificationModel): LocalTransformer[RandomForestClassificationModel] = new LocalRandomForestClassificationModel(transformer)
} 示例4: LocalDecisionTreeClassificationModel
//设置package包名称以及导入依赖的类
package io.hydrosphere.mist.api.ml.classification
import io.hydrosphere.mist.api.ml._
import org.apache.spark.ml.classification.DecisionTreeClassificationModel
import org.apache.spark.ml.linalg.{Vector, Vectors}
import org.apache.spark.ml.tree.Node
class LocalDecisionTreeClassificationModel(override val sparkTransformer: DecisionTreeClassificationModel) extends LocalTransformer[DecisionTreeClassificationModel] {
override def transform(localData: LocalData): LocalData = {
localData.column(sparkTransformer.getFeaturesCol) match {
case Some(column) =>
val method = classOf[DecisionTreeClassificationModel].getMethod("predict", classOf[Vector])
method.setAccessible(true)
val newColumn = LocalDataColumn(sparkTransformer.getPredictionCol, column.data.map(f => Vectors.dense(f.asInstanceOf[Array[Double]])).map { vector =>
method.invoke(sparkTransformer, vector).asInstanceOf[Double]
})
localData.withColumn(newColumn)
case None => localData
}
}
}
object LocalDecisionTreeClassificationModel extends LocalModel[DecisionTreeClassificationModel] {
override def load(metadata: Metadata, data: Map[String, Any]): DecisionTreeClassificationModel = {
createTree(metadata, data)
}
def createTree(metadata: Metadata, data: Map[String, Any]): DecisionTreeClassificationModel = {
val ctor = classOf[DecisionTreeClassificationModel].getDeclaredConstructor(classOf[String], classOf[Node], classOf[Int], classOf[Int])
ctor.setAccessible(true)
val inst = ctor.newInstance(
metadata.uid,
DataUtils.createNode(0, metadata, data),
metadata.numFeatures.get.asInstanceOf[java.lang.Integer],
metadata.numClasses.get.asInstanceOf[java.lang.Integer]
)
inst
.setFeaturesCol(metadata.paramMap("featuresCol").asInstanceOf[String])
.setPredictionCol(metadata.paramMap("predictionCol").asInstanceOf[String])
.setProbabilityCol(metadata.paramMap("probabilityCol").asInstanceOf[String])
.setRawPredictionCol(metadata.paramMap("rawPredictionCol").asInstanceOf[String])
inst
.set(inst.seed, metadata.paramMap("seed").toString.toLong)
.set(inst.cacheNodeIds, metadata.paramMap("cacheNodeIds").toString.toBoolean)
.set(inst.maxDepth, metadata.paramMap("maxDepth").toString.toInt)
.set(inst.labelCol, metadata.paramMap("labelCol").toString)
.set(inst.minInfoGain, metadata.paramMap("minInfoGain").toString.toDouble)
.set(inst.checkpointInterval, metadata.paramMap("checkpointInterval").toString.toInt)
.set(inst.minInstancesPerNode, metadata.paramMap("minInstancesPerNode").toString.toInt)
.set(inst.maxMemoryInMB, metadata.paramMap("maxMemoryInMB").toString.toInt)
.set(inst.maxBins, metadata.paramMap("maxBins").toString.toInt)
.set(inst.impurity, metadata.paramMap("impurity").toString)
}
override implicit def getTransformer(transformer: DecisionTreeClassificationModel): LocalTransformer[DecisionTreeClassificationModel] = new LocalDecisionTreeClassificationModel(transformer)
} 示例5: RandomForestClassificationModelToMleap
//设置package包名称以及导入依赖的类
package org.apache.spark.ml.mleap.converter.runtime.classification
import com.truecar.mleap.core.classification.RandomForestClassification
import com.truecar.mleap.runtime.transformer
import org.apache.spark.ml.classification.{DecisionTreeClassificationModel, RandomForestClassificationModel}
import org.apache.spark.ml.mleap.converter.runtime.TransformerToMleap
object RandomForestClassificationModelToMleap extends TransformerToMleap[RandomForestClassificationModel, transformer.RandomForestClassificationModel] {
override def toMleap(t: RandomForestClassificationModel): transformer.RandomForestClassificationModel = {
val trees = t.trees.asInstanceOf[Array[DecisionTreeClassificationModel]]
.map(tree => DecisionTreeClassificationModelToMleap(tree).toMleap)
val model = RandomForestClassification(trees,
t.numFeatures,
t.numClasses)
transformer.RandomForestClassificationModel(t.getFeaturesCol,
t.getPredictionCol,
model)
}
}