[ 
https://issues.apache.org/jira/browse/SPARK-29811?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Dong Wang updated SPARK-29811:
------------------------------
    Description: 
The rdd oldDataset in ml.regression.RandomForestRegressor.train() needs to be 
persisted, because it used in two actions in RandomForest.run() and 
oldDataset.first().
{code:scala}
override protected def train(
      dataset: Dataset[_]): RandomForestRegressionModel = instrumented { instr 
=>
    val categoricalFeatures: Map[Int, Int] =
      MetadataUtils.getCategoricalFeatures(dataset.schema($(featuresCol)))
    val oldDataset: RDD[LabeledPoint] = extractLabeledPoints(dataset) // Needs 
to persist
    val strategy =
      super.getOldStrategy(categoricalFeatures, numClasses = 0, 
OldAlgo.Regression, getOldImpurity)

    instr.logPipelineStage(this)
    instr.logDataset(dataset)
    instr.logParams(this, labelCol, featuresCol, predictionCol, impurity, 
numTrees,
      featureSubsetStrategy, maxDepth, maxBins, maxMemoryInMB, minInfoGain,
      minInstancesPerNode, seed, subsamplingRate, cacheNodeIds, 
checkpointInterval)
   // First use oldDataset
    val trees = RandomForest
      .run(oldDataset, strategy, getNumTrees, getFeatureSubsetStrategy, 
getSeed, Some(instr))
      .map(_.asInstanceOf[DecisionTreeRegressionModel])
   // Second use oldDataset
    val numFeatures = oldDataset.first().features.size
    instr.logNamedValue(Instrumentation.loggerTags.numFeatures, numFeatures)
    new RandomForestRegressionModel(uid, trees, numFeatures)
  }
{code}

The same situation exits in ml.classification.RandomForestClassifier.train.

This issue is reported by our tool CacheCheck, which is used to dynamically 
detecting persist()/unpersist() api misuses.

  was:
The rdd oldDataset in ml.regression.RandomForestRegressor.train() needs to be 
persisted, because it used in two actions in RandomForest.run() and 
oldDataset.first().
{code:scala}
override protected def train(
      dataset: Dataset[_]): RandomForestRegressionModel = instrumented { instr 
=>
    val categoricalFeatures: Map[Int, Int] =
      MetadataUtils.getCategoricalFeatures(dataset.schema($(featuresCol)))
    val oldDataset: RDD[LabeledPoint] = extractLabeledPoints(dataset) // Needs 
to persist
    val strategy =
      super.getOldStrategy(categoricalFeatures, numClasses = 0, 
OldAlgo.Regression, getOldImpurity)

    instr.logPipelineStage(this)
    instr.logDataset(dataset)
    instr.logParams(this, labelCol, featuresCol, predictionCol, impurity, 
numTrees,
      featureSubsetStrategy, maxDepth, maxBins, maxMemoryInMB, minInfoGain,
      minInstancesPerNode, seed, subsamplingRate, cacheNodeIds, 
checkpointInterval)
   // First use oldDataset
    val trees = RandomForest
      .run(oldDataset, strategy, getNumTrees, getFeatureSubsetStrategy, 
getSeed, Some(instr))
      .map(_.asInstanceOf[DecisionTreeRegressionModel])
   // Second use oldDataset
    val numFeatures = oldDataset.first().features.size
    instr.logNamedValue(Instrumentation.loggerTags.numFeatures, numFeatures)
    new RandomForestRegressionModel(uid, trees, numFeatures)
  }
{code}

The same situation exits in ml.classification.RandomForestClassifier.train.
{code:scala}

{code}
This issue is reported by our tool CacheCheck, which is used to dynamically 
detecting persist()/unpersist() api misuses.


> Missing persist on oldDataset in ml.RandomForestRegressor.train()
> -----------------------------------------------------------------
>
>                 Key: SPARK-29811
>                 URL: https://issues.apache.org/jira/browse/SPARK-29811
>             Project: Spark
>          Issue Type: Improvement
>          Components: ML
>    Affects Versions: 2.4.3
>            Reporter: Dong Wang
>            Priority: Major
>
> The rdd oldDataset in ml.regression.RandomForestRegressor.train() needs to be 
> persisted, because it used in two actions in RandomForest.run() and 
> oldDataset.first().
> {code:scala}
> override protected def train(
>       dataset: Dataset[_]): RandomForestRegressionModel = instrumented { 
> instr =>
>     val categoricalFeatures: Map[Int, Int] =
>       MetadataUtils.getCategoricalFeatures(dataset.schema($(featuresCol)))
>     val oldDataset: RDD[LabeledPoint] = extractLabeledPoints(dataset) // 
> Needs to persist
>     val strategy =
>       super.getOldStrategy(categoricalFeatures, numClasses = 0, 
> OldAlgo.Regression, getOldImpurity)
>     instr.logPipelineStage(this)
>     instr.logDataset(dataset)
>     instr.logParams(this, labelCol, featuresCol, predictionCol, impurity, 
> numTrees,
>       featureSubsetStrategy, maxDepth, maxBins, maxMemoryInMB, minInfoGain,
>       minInstancesPerNode, seed, subsamplingRate, cacheNodeIds, 
> checkpointInterval)
>    // First use oldDataset
>     val trees = RandomForest
>       .run(oldDataset, strategy, getNumTrees, getFeatureSubsetStrategy, 
> getSeed, Some(instr))
>       .map(_.asInstanceOf[DecisionTreeRegressionModel])
>    // Second use oldDataset
>     val numFeatures = oldDataset.first().features.size
>     instr.logNamedValue(Instrumentation.loggerTags.numFeatures, numFeatures)
>     new RandomForestRegressionModel(uid, trees, numFeatures)
>   }
> {code}
> The same situation exits in ml.classification.RandomForestClassifier.train.
> This issue is reported by our tool CacheCheck, which is used to dynamically 
> detecting persist()/unpersist() api misuses.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org

Reply via email to