[SPARK-18619][ML] Make QuantileDiscretizer/Bucketizer/StringIndexer/RFormula inherit from HasHandleInvalid #18582
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -64,7 +64,7 @@ private[regression] trait LinearRegressionParams extends PredictorParams | |
| * | ||
| * @group param | ||
| */ | ||
| @Since("1.6.0") | ||
| final override val solver: Param[String] = new Param[String](this, "solver", | ||
| "The solver algorithm for optimization. Supported options: " + | ||
| s"${supportedSolvers.mkString(", ")}. (Default auto)", | ||
|
|
@@ -194,7 +194,7 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String | |
| */ | ||
| @Since("1.6.0") | ||
| def setSolver(value: String): this.type = set(solver, value) | ||
| setDefault(solver -> Auto) | ||
|
|
||
| /** | ||
| * Suggested depth for treeAggregate (greater than or equal to 2). | ||
|
|
@@ -224,8 +224,8 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String | |
| elasticNetParam, fitIntercept, maxIter, regParam, standardization, aggregationDepth) | ||
| instr.logNumFeatures(numFeatures) | ||
|
|
||
| if (($(solver) == Auto && | ||
| numFeatures <= WeightedLeastSquares.MAX_NUM_FEATURES) || $(solver) == Normal) { | ||
| // For low dimensional data, WeightedLeastSquares is more efficient since the | ||
| // training algorithm only requires one pass through the data. (SPARK-10668) | ||
|
|
||
|
|
@@ -460,16 +460,16 @@ object LinearRegression extends DefaultParamsReadable[LinearRegression] { | |
| val MAX_FEATURES_FOR_NORMAL_SOLVER: Int = WeightedLeastSquares.MAX_NUM_FEATURES | ||
|
|
||
| /** String name for "auto". */ | ||
| private[regression] val Auto = "auto" | ||
|
There was a problem hiding this comment. Is There was a problem hiding this comment. @facaiy It's not related to this PR, just addressed other small issues by the way. There was a problem hiding this comment. @facaiy We had some offline discussion, and decided to fix some small issues in this PR. |
||
|
|
||
| /** String name for "normal". */ | ||
| private[regression] val Normal = "normal" | ||
|
|
||
| /** String name for "l-bfgs". */ | ||
| private[regression] val LBFGS = "l-bfgs" | ||
|
|
||
| /** Set of solvers that LinearRegression supports. */ | ||
| private[regression] val supportedSolvers = Array(Auto, Normal, LBFGS) | ||
| } | ||
|
|
||
| /** | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -314,7 +314,8 @@ class BucketedRandomProjectionLSHModel(LSHModel, JavaMLReadable, JavaMLWritable) | |
|
|
||
|
|
||
| @inherit_doc | ||
| class Bucketizer(JavaTransformer, HasInputCol, HasOutputCol, HasHandleInvalid, | ||
| JavaMLReadable, JavaMLWritable): | ||
| """ | ||
| Maps a column of continuous features to a column of feature buckets. | ||
|
|
||
|
|
@@ -398,20 +399,6 @@ def getSplits(self): | |
| """ | ||
| return self.getOrDefault(self.splits) | ||
|
|
||
|
|
||
| @inherit_doc | ||
| class CountVectorizer(JavaEstimator, HasInputCol, HasOutputCol, JavaMLReadable, JavaMLWritable): | ||
|
|
@@ -1623,7 +1610,8 @@ def getDegree(self): | |
|
|
||
|
|
||
| @inherit_doc | ||
| class QuantileDiscretizer(JavaEstimator, HasInputCol, HasOutputCol, HasHandleInvalid, | ||
| JavaMLReadable, JavaMLWritable): | ||
| """ | ||
| .. note:: Experimental | ||
|
|
||
|
|
@@ -1743,20 +1731,6 @@ def getRelativeError(self): | |
| """ | ||
| return self.getOrDefault(self.relativeError) | ||
|
|
||
| def _create_model(self, java_model): | ||
| """ | ||
| Private method to convert the java_model to a Python model. | ||
|
|
@@ -2977,7 +2951,8 @@ def explainedVariance(self): | |
|
|
||
|
|
||
| @inherit_doc | ||
| class RFormula(JavaEstimator, HasFeaturesCol, HasLabelCol, HasHandleInvalid, | ||
| JavaMLReadable, JavaMLWritable): | ||
| """ | ||
| .. note:: Experimental | ||
|
|
||
|
|
@@ -3020,6 +2995,8 @@ class RFormula(JavaEstimator, HasFeaturesCol, HasLabelCol, JavaMLReadable, JavaM | |
| True | ||
| >>> loadedRF.getLabelCol() == rf.getLabelCol() | ||
| True | ||
| >>> loadedRF.getHandleInvalid() == rf.getHandleInvalid() | ||
| True | ||
| >>> str(loadedRF) | ||
| 'RFormula(y ~ x + s) (uid=...)' | ||
| >>> modelPath = temp_path + "/rFormulaModel" | ||
|
|
@@ -3058,26 +3035,37 @@ class RFormula(JavaEstimator, HasFeaturesCol, HasLabelCol, JavaMLReadable, JavaM | |
| "RFormula drops the same category as R when encoding strings.", | ||
| typeConverter=TypeConverters.toString) | ||
|
|
||
| handleInvalid = Param(Params._dummy(), "handleInvalid", "how to handle invalid entries. " + | ||
|
There was a problem hiding this comment. If I understand correctly, There was a problem hiding this comment. @facaiy We have to override it to keep the pydoc in line with scala side. |
||
| "Options are 'skip' (filter out rows with invalid values), " + | ||
| "'error' (throw an error), or 'keep' (put invalid data in a special " + | ||
| "additional bucket, at index numLabels).", | ||
| typeConverter=TypeConverters.toString) | ||
|
|
||
| @keyword_only | ||
| def __init__(self, formula=None, featuresCol="features", labelCol="label", | ||
| forceIndexLabel=False, stringIndexerOrderType="frequencyDesc", | ||
| handleInvalid="error"): | ||
| """ | ||
| __init__(self, formula=None, featuresCol="features", labelCol="label", \ | ||
| forceIndexLabel=False, stringIndexerOrderType="frequencyDesc", \ | ||
| handleInvalid="error") | ||
| """ | ||
| super(RFormula, self).__init__() | ||
| self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.RFormula", self.uid) | ||
| self._setDefault(forceIndexLabel=False, stringIndexerOrderType="frequencyDesc", | ||
| handleInvalid="error") | ||
| kwargs = self._input_kwargs | ||
| self.setParams(**kwargs) | ||
|
|
||
| @keyword_only | ||
| @since("1.5.0") | ||
| def setParams(self, formula=None, featuresCol="features", labelCol="label", | ||
| forceIndexLabel=False, stringIndexerOrderType="frequencyDesc", | ||
| handleInvalid="error"): | ||
| """ | ||
| setParams(self, formula=None, featuresCol="features", labelCol="label", \ | ||
| forceIndexLabel=False, stringIndexerOrderType="frequencyDesc", \ | ||
| handleInvalid="error") | ||
| Sets params for RFormula. | ||
| """ | ||
| kwargs = self._input_kwargs | ||
|
|
||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
How about aligning
withwithextends?There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I guess it was suggested by IDEA.