本文整理汇总了Scala中org.apache.spark.ml.classification.GBTClassifier类的典型用法代码示例。如果您正苦于以下问题:Scala GBTClassifier类的具体用法?Scala GBTClassifier怎么用?Scala GBTClassifier使用的例子?那么恭喜您, 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GBTClassifier类的2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: GBTClassification
//设置package包名称以及导入依赖的类
package com.databricks.spark.sql.perf.mllib.classification
import org.apache.spark.ml.{Estimator, ModelBuilder, Transformer, TreeUtils}
import org.apache.spark.ml.classification.GBTClassifier
import org.apache.spark.ml.evaluation.{Evaluator, MulticlassClassificationEvaluator}
import org.apache.spark.sql._
import com.databricks.spark.sql.perf.mllib._
import com.databricks.spark.sql.perf.mllib.OptionImplicits._
import com.databricks.spark.sql.perf.mllib.data.DataGenerator
object GBTClassification extends BenchmarkAlgorithm
with TestFromTraining with TrainingSetFromTransformer with ScoringWithEvaluator {
import TreeOrForestClassification.getFeatureArity
override protected def initialData(ctx: MLBenchContext) = {
import ctx.params._
val featureArity: Array[Int] = getFeatureArity(ctx)
val data: DataFrame = DataGenerator.generateMixedFeatures(ctx.sqlContext, numExamples,
ctx.seed(), numPartitions, featureArity)
TreeUtils.setMetadata(data, "features", featureArity)
}
override protected def trueModel(ctx: MLBenchContext): Transformer = {
import ctx.params._
// We add +1 to the depth to make it more likely that many iterations of boosting are needed
// to model the true tree.
ModelBuilder.newDecisionTreeClassificationModel(depth + 1, numClasses, getFeatureArity(ctx),
ctx.seed())
}
override def getEstimator(ctx: MLBenchContext): Estimator[_] = {
import ctx.params._
// TODO: subsamplingRate, featureSubsetStrategy
// TODO: cacheNodeIds, checkpoint?
new GBTClassifier()
.setMaxDepth(depth)
.setMaxIter(maxIter)
.setSeed(ctx.seed())
}
override protected def evaluator(ctx: MLBenchContext): Evaluator =
new MulticlassClassificationEvaluator()
}
示例2: GBTClassification
//设置package包名称以及导入依赖的类
package com.databricks.spark.sql.perf.mllib.classification
import org.apache.spark.ml.{Estimator, ModelBuilder, Transformer, TreeUtils}
import org.apache.spark.ml.classification.GBTClassifier
import org.apache.spark.ml.evaluation.{Evaluator, MulticlassClassificationEvaluator}
import org.apache.spark.sql._
import com.databricks.spark.sql.perf.mllib._
import com.databricks.spark.sql.perf.mllib.OptionImplicits._
import com.databricks.spark.sql.perf.mllib.data.DataGenerator
object GBTClassification extends BenchmarkAlgorithm
with TestFromTraining with TrainingSetFromTransformer with ScoringWithEvaluator {
import TreeOrForestClassification.getFeatureArity
override protected def initialData(ctx: MLBenchContext) = {
import ctx.params._
val featureArity: Array[Int] = getFeatureArity(ctx)
val data: DataFrame = DataGenerator.generateMixedFeatures(ctx.sqlContext, numExamples,
ctx.seed(), numPartitions, featureArity)
TreeUtils.setMetadata(data, "label", numClasses, "features", featureArity)
}
override protected def trueModel(ctx: MLBenchContext): Transformer = {
import ctx.params._
// We add +1 to the depth to make it more likely that many iterations of boosting are needed
// to model the true tree.
ModelBuilder.newDecisionTreeClassificationModel(depth + 1, numClasses, getFeatureArity(ctx),
ctx.seed())
}
override def getEstimator(ctx: MLBenchContext): Estimator[_] = {
import ctx.params._
// TODO: subsamplingRate, featureSubsetStrategy
// TODO: cacheNodeIds, checkpoint?
new GBTClassifier()
.setMaxDepth(depth)
.setMaxIter(maxIter)
.setSeed(ctx.seed())
}
override protected def evaluator(ctx: MLBenchContext): Evaluator =
new MulticlassClassificationEvaluator()
}