Skip to content

[SPARK-34591][MLLIB][WIP] Add decision tree pruning as a parameter #32813

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
CBribiescas wants to merge 13 commits into from
Closed

[SPARK-34591][MLLIB][WIP] Add decision tree pruning as a parameter #32813

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
1db47ef
[SPARK-34591][MLLIB] Disable decision tree pruning
Jun 8, 2021
36a3527
Merge branch 'master' into SPARK-34591
Jun 8, 2021
6e52df6
[SPARK-34591][MLLIB] Disable decision tree pruning
Jun 8, 2021
b53c0e4
Merge branch 'master' into SPARK-34591
Jun 8, 2021
6898a0e
This PR disables a feature created in SPARK-3159 where LearningNodes …
Jun 8, 2021
2fc33ec
Merge branch 'master' into SPARK-34591
Jun 8, 2021
fb835db
Exposed pruning parameter accessible in Scala WIP
CBribiescas Jun 14, 2021
a471d5e
Merge branch 'master' into SPARK-34591
CBribiescas Jun 14, 2021
43ee852
Added to decision tree classifier and to python
CBribiescas Jun 20, 2021
dcec830
Merge branch 'master' into SPARK-34591
CBribiescas Jun 20, 2021
4bb58f6
Finished a TODO for comments in Strategy.scala
CBribiescas Jun 20, 2021
ea028d4
Merge branch 'master' into SPARK-34591
CBribiescas Jul 8, 2021
f51bbae
Merge branch 'master' into SPARK-34591
CBribiescas Sep 1, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,6 +72,10 @@ class DecisionTreeClassifier @Since("1.4.0") (
@Since("1.4.0")
def setMinInfoGain(value: Double): this.type = set(minInfoGain, value)

/** @group setParam */
@Since("3.1.2")
def setPruneTree(value: Boolean): this.type = set(pruneTree, value)

/** @group expertSetParam */
@Since("1.4.0")
def setMaxMemoryInMB(value: Int): this.type = set(maxMemoryInMB, value)
Expand Down Expand Up @@ -126,9 +130,11 @@ class DecisionTreeClassifier @Since("1.4.0") (
val instances = extractInstances(dataset, numClasses)
val strategy = getOldStrategy(categoricalFeatures, numClasses)
require(!strategy.bootstrap, "DecisionTreeClassifier does not need bootstrap sampling")
strategy.pruneTree = $(pruneTree)

instr.logNumClasses(numClasses)
instr.logParams(this, labelCol, featuresCol, predictionCol, rawPredictionCol,
probabilityCol, leafCol, maxDepth, maxBins, minInstancesPerNode, minInfoGain,
probabilityCol, leafCol, maxDepth, maxBins, minInstancesPerNode, minInfoGain, pruneTree,
maxMemoryInMB, cacheNodeIds, checkpointInterval, impurity, seed, thresholds)

val trees = RandomForest.run(instances, strategy, numTrees = 1, featureSubsetStrategy = "all",
Expand Down
7 changes: 6 additions & 1 deletion mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,6 +75,10 @@ class RandomForestClassifier @Since("1.4.0") (
@Since("1.4.0")
def setMinInfoGain(value: Double): this.type = set(minInfoGain, value)

/** @group setParam */
@Since("3.1.2")
def setPruneTree(value: Boolean): this.type = set(pruneTree, value)

/** @group expertSetParam */
@Since("1.4.0")
def setMaxMemoryInMB(value: Int): this.type = set(maxMemoryInMB, value)
Expand Down Expand Up @@ -152,10 +156,11 @@ class RandomForestClassifier @Since("1.4.0") (
val strategy =
super.getOldStrategy(categoricalFeatures, numClasses, OldAlgo.Classification, getOldImpurity)
strategy.bootstrap = $(bootstrap)
strategy.pruneTree = $(pruneTree)

instr.logParams(this, labelCol, featuresCol, weightCol, predictionCol, probabilityCol,
rawPredictionCol, leafCol, impurity, numTrees, featureSubsetStrategy, maxDepth, maxBins,
maxMemoryInMB, minInfoGain, minInstancesPerNode, minWeightFractionPerNode, seed,
maxMemoryInMB, minInfoGain, pruneTree, minInstancesPerNode, minWeightFractionPerNode, seed,
subsamplingRate, thresholds, cacheNodeIds, checkpointInterval, bootstrap)

val trees = RandomForest
Expand Down
Loading