• 设为首页
  • 点击收藏
  • 手机版
    手机扫一扫访问
    迪恩网络手机版
  • 关注官方公众号
    微信扫一扫关注
    公众号

Scala RegressionEvaluator类代码示例

原作者: [db:作者] 来自: [db:来源] 收藏 邀请

本文整理汇总了Scala中org.apache.spark.ml.evaluation.RegressionEvaluator的典型用法代码示例。如果您正苦于以下问题:Scala RegressionEvaluator类的具体用法?Scala RegressionEvaluator怎么用?Scala RegressionEvaluator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RegressionEvaluator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,您的评价将有助于我们的系统推荐出更棒的Scala代码示例。

示例1: ALSModeling

//设置package包名称以及导入依赖的类
package com.spark.recommendation

import java.util

import com.spark.recommendation.FeatureExtraction.{Rating, parseRating}
import org.apache.spark.ml.evaluation.RegressionEvaluator
import org.apache.spark.ml.recommendation.ALS
import org.apache.spark.sql.{Row, DataFrame, DataFrameWriter}


object ALSModeling {

  def createALSModel() {
    val ratings = FeatureExtraction.getFeatures();

    val Array(training, test) = ratings.randomSplit(Array(0.8, 0.2))
    println(training.first())

    // Build the recommendation model using ALS on the training data
    val als = new ALS()
      .setMaxIter(5)
      .setRegParam(0.01)
      .setUserCol("userId")
      .setItemCol("movieId")
      .setRatingCol("rating")

    val model = als.fit(training)
    println(model.userFactors.count())
    println(model.itemFactors.count())

    val predictions = model.transform(test)
    println(predictions.printSchema())

    val evaluator = new RegressionEvaluator()
      .setMetricName("rmse")
      .setLabelCol("rating")
      .setPredictionCol("prediction")
    val rmse = evaluator.evaluate(predictions)

    println(s"Root-mean-square error = $rmse")
  }

  def main(args: Array[String]) {
    createALSModel()
  }

} 
开发者ID:PacktPublishing,项目名称:Machine-Learning-with-Spark-Second-Edition,代码行数:48,代码来源:ALSModeling.scala


示例2: GLMRegression

//设置package包名称以及导入依赖的类
package com.databricks.spark.sql.perf.mllib.regression

import org.apache.spark.ml.evaluation.{Evaluator, RegressionEvaluator}
import org.apache.spark.ml.linalg.Vectors
import org.apache.spark.ml.regression.GeneralizedLinearRegression
import org.apache.spark.ml.{Estimator, ModelBuilder, Transformer}

import com.databricks.spark.sql.perf.mllib.OptionImplicits._
import com.databricks.spark.sql.perf.mllib._
import com.databricks.spark.sql.perf.mllib.data.DataGenerator


object GLMRegression extends BenchmarkAlgorithm with TestFromTraining with
  TrainingSetFromTransformer with ScoringWithEvaluator {

  override protected def initialData(ctx: MLBenchContext) = {
    import ctx.params._
    DataGenerator.generateContinuousFeatures(
      ctx.sqlContext,
      numExamples,
      ctx.seed(),
      numPartitions,
      numFeatures)
  }

  override protected def trueModel(ctx: MLBenchContext): Transformer = {
    import ctx.params._
    val rng = ctx.newGenerator()
    val coefficients =
      Vectors.dense(Array.fill[Double](ctx.params.numFeatures)(2 * rng.nextDouble() - 1))
    // Small intercept to prevent some skew in the data.
    val intercept = 0.01 * (2 * rng.nextDouble - 1)
    val m = ModelBuilder.newGLR(coefficients, intercept)
    m.set(m.link, link.get)
    m.set(m.family, family.get)
    m
  }

  override def getEstimator(ctx: MLBenchContext): Estimator[_] = {
    import ctx.params._
    new GeneralizedLinearRegression()
      .setLink(link)
      .setFamily(family)
      .setRegParam(regParam)
      .setMaxIter(maxIter)
      .setTol(tol)
  }

  override protected def evaluator(ctx: MLBenchContext): Evaluator =
    new RegressionEvaluator()
} 
开发者ID:summerDG,项目名称:spark-sql-perf,代码行数:52,代码来源:GLMRegression.scala


示例3: LinearRegression

//设置package包名称以及导入依赖的类
package com.databricks.spark.sql.perf.mllib.regression

import org.apache.spark.ml
import org.apache.spark.ml.evaluation.{Evaluator, RegressionEvaluator}
import org.apache.spark.ml.linalg.Vectors
import org.apache.spark.ml.{Estimator, ModelBuilder, Transformer}

import com.databricks.spark.sql.perf.mllib.OptionImplicits._
import com.databricks.spark.sql.perf.mllib._
import com.databricks.spark.sql.perf.mllib.data.DataGenerator


object LinearRegression extends BenchmarkAlgorithm with TestFromTraining with
  TrainingSetFromTransformer with ScoringWithEvaluator {

  override protected def initialData(ctx: MLBenchContext) = {
    import ctx.params._
    DataGenerator.generateContinuousFeatures(
      ctx.sqlContext,
      numExamples,
      ctx.seed(),
      numPartitions,
      numFeatures)
  }

  override protected def trueModel(ctx: MLBenchContext): Transformer = {
    val rng = ctx.newGenerator()
    val coefficients =
      Vectors.dense(Array.fill[Double](ctx.params.numFeatures)(2 * rng.nextDouble() - 1))
    // Small intercept to prevent some skew in the data.
    val intercept = 0.01 * (2 * rng.nextDouble - 1)
    ModelBuilder.newLinearRegressionModel(coefficients, intercept)
  }

  override def getEstimator(ctx: MLBenchContext): Estimator[_] = {
    import ctx.params._
    new ml.regression.LinearRegression()
      .setSolver("l-bfgs")
      .setRegParam(regParam)
      .setMaxIter(maxIter)
      .setTol(tol)
  }

  override protected def evaluator(ctx: MLBenchContext): Evaluator =
    new RegressionEvaluator()
} 
开发者ID:summerDG,项目名称:spark-sql-perf,代码行数:47,代码来源:LinearRegression.scala


示例4: ALS

//设置package包名称以及导入依赖的类
package com.databricks.spark.sql.perf.mllib.recommendation

import org.apache.spark.ml
import org.apache.spark.ml.evaluation.{RegressionEvaluator, Evaluator}
import org.apache.spark.ml.{Transformer, Estimator}
import org.apache.spark.sql._

import com.databricks.spark.sql.perf.mllib.OptionImplicits._
import com.databricks.spark.sql.perf.mllib.data.DataGenerator
import com.databricks.spark.sql.perf.mllib.{ScoringWithEvaluator, BenchmarkAlgorithm, MLBenchContext}

object ALS extends BenchmarkAlgorithm with ScoringWithEvaluator {

  override def trainingDataSet(ctx: MLBenchContext): DataFrame = {
    import ctx.params._
    DataGenerator.generateRatings(
      ctx.sqlContext,
      numUsers,
      numItems,
      numExamples,
      numTestExamples,
      implicitPrefs = false,
      numPartitions,
      ctx.seed())._1
  }

  override def testDataSet(ctx: MLBenchContext): DataFrame = {
    import ctx.params._
    DataGenerator.generateRatings(
      ctx.sqlContext,
      numUsers,
      numItems,
      numExamples,
      numTestExamples,
      implicitPrefs = false,
      numPartitions,
      ctx.seed())._2
  }

  override def getEstimator(ctx: MLBenchContext): Estimator[_] = {
    import ctx.params._
    new ml.recommendation.ALS()
      .setSeed(ctx.seed())
      .setRegParam(regParam)
      .setNumBlocks(numPartitions)
      .setRank(rank)
      .setMaxIter(maxIter)
  }

  override protected def evaluator(ctx: MLBenchContext): Evaluator = {
    new RegressionEvaluator().setLabelCol("rating")
  }
} 
开发者ID:summerDG,项目名称:spark-sql-perf,代码行数:54,代码来源:ALS.scala


示例5: SitelinkEntry

//设置package包名称以及导入依赖的类
package org.wikimedia.research.recommendation.job.translation

import org.apache.spark.ml.evaluation.RegressionEvaluator
import org.apache.spark.ml.linalg.DenseVector
import org.apache.spark.ml.regression.RandomForestRegressor
import org.apache.spark.sql.{DataFrame, SparkSession}

case class SitelinkEntry(id: String, site: String, title: String)

case class PagecountEntry(site: String, title: String, pageviews: Double)

case class SitelinkPageviewsEntry(id: String, site: String, title: String, pageviews: Double)

case class RankedEntry(id: String, site: String, title: String, pageviews: Double, rank: Double)

object Utils {
  val FEATURES = "features"
  val LABEL = "label"
  val PREDICTION = "prediction"
  val EXISTS = 1.0
  val NOT_EXISTS = 0.0
  val REGRESSOR: RandomForestRegressor = new RandomForestRegressor()
    .setLabelCol(LABEL)
    .setFeaturesCol(FEATURES)
  val EVALUATOR: RegressionEvaluator = new RegressionEvaluator()
    .setLabelCol(LABEL)
    .setPredictionCol(PREDICTION)
    .setMetricName("rmse")

  def getWorkData(spark: SparkSession, data: DataFrame, target: String, exists: Boolean = true): DataFrame = {
    val workData: DataFrame = data.filter(row =>
      row(row.fieldIndex("exists_" + target)) == (if (exists) EXISTS else NOT_EXISTS))

    import spark.implicits._
    val labeledData = workData.map(row =>
      (
        row.getString(row.fieldIndex("id")),
        row.getDouble(row.fieldIndex("rank_" + target)),
        
        new DenseVector((
          (1 until row.fieldIndex("pageviews_" + target)).map(row.getDouble) ++
            (row.fieldIndex("exists_" + target) + 1 until row.length).map(row.getDouble)
          ).toArray)
      )
    ).rdd

    spark.createDataFrame(labeledData).toDF("id", LABEL, FEATURES)
  }
} 
开发者ID:schana,项目名称:recommendation-translation,代码行数:50,代码来源:Utils.scala



注:本文中的org.apache.spark.ml.evaluation.RegressionEvaluator类示例整理自Github/MSDocs等源码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。


鲜花

握手

雷人

路过

鸡蛋
该文章已有0人参与评论

请发表评论

全部评论

专题导读
上一篇:
Scala DecisionTreeClassifier类代码示例发布时间:2022-05-23
下一篇:
Scala StaticLoggerBinder类代码示例发布时间:2022-05-23
热门推荐
热门话题
阅读排行榜

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服(服务时间 9:00~18:00)

在线QQ客服
地址:深圳市南山区西丽大学城创智工业园
电邮:jeky_zhao#qq.com
移动电话:139-2527-9053

Powered by 互联科技 X3.4© 2001-2213 极客世界.|Sitemap