diff options
author | Yanbo Liang <ybliang8@gmail.com> | 2016-10-10 22:50:59 -0700 |
---|---|---|
committer | Yanbo Liang <ybliang8@gmail.com> | 2016-10-10 22:50:59 -0700 |
commit | 19401a203b441e3355f0d3fc3fd062b6d5bdee1f (patch) | |
tree | 8a5d1158afcdaa9468eb978f301586333f2e3d47 /mllib/src/main | |
parent | b515768f2668749ad37a3bdf9d265ce45ec447b1 (diff) | |
download | spark-19401a203b441e3355f0d3fc3fd062b6d5bdee1f.tar.gz spark-19401a203b441e3355f0d3fc3fd062b6d5bdee1f.tar.bz2 spark-19401a203b441e3355f0d3fc3fd062b6d5bdee1f.zip |
[SPARK-15957][ML] RFormula supports forcing to index label
## What changes were proposed in this pull request?
```RFormula``` will index label only when it is string type currently. If the label is numeric type and we use ```RFormula``` to present a classification model, there is no label attributes in label column metadata. The label attributes are useful when making prediction for classification, so we can force to index label by ```StringIndexer``` whether it is numeric or string type for classification. Then SparkR wrappers can extract label attributes from label column metadata successfully. This feature can help us to fix bug similar with [SPARK-15153](https://issues.apache.org/jira/browse/SPARK-15153).
For regression, we will still to keep label as numeric type.
In this PR, we add a param ```indexLabel``` to control whether to force to index label for ```RFormula```.
## How was this patch tested?
Unit tests.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes #13675 from yanboliang/spark-15957.
Diffstat (limited to 'mllib/src/main')
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala | 29 |
1 files changed, 26 insertions, 3 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala index 2ee899bcca..389898666e 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala @@ -26,7 +26,7 @@ import org.apache.spark.annotation.{Experimental, Since} import org.apache.spark.ml.{Estimator, Model, Pipeline, PipelineModel, PipelineStage, Transformer} import org.apache.spark.ml.attribute.AttributeGroup import org.apache.spark.ml.linalg.VectorUDT -import org.apache.spark.ml.param.{Param, ParamMap} +import org.apache.spark.ml.param.{BooleanParam, Param, ParamMap} import org.apache.spark.ml.param.shared.{HasFeaturesCol, HasLabelCol} import org.apache.spark.ml.util._ import org.apache.spark.sql.{DataFrame, Dataset} @@ -104,6 +104,27 @@ class RFormula @Since("1.5.0") (@Since("1.5.0") override val uid: String) @Since("1.5.0") def setLabelCol(value: String): this.type = set(labelCol, value) + /** + * Force to index label whether it is numeric or string type. + * Usually we index label only when it is string type. + * If the formula was used by classification algorithms, + * we can force to index label even it is numeric type by setting this param with true. + * Default: false. + * @group param + */ + @Since("2.1.0") + val forceIndexLabel: BooleanParam = new BooleanParam(this, "forceIndexLabel", + "Force to index label whether it is numeric or string") + setDefault(forceIndexLabel -> false) + + /** @group getParam */ + @Since("2.1.0") + def getForceIndexLabel: Boolean = $(forceIndexLabel) + + /** @group setParam */ + @Since("2.1.0") + def setForceIndexLabel(value: Boolean): this.type = set(forceIndexLabel, value) + /** Whether the formula specifies fitting an intercept. */ private[ml] def hasIntercept: Boolean = { require(isDefined(formula), "Formula must be defined first.") @@ -167,8 +188,8 @@ class RFormula @Since("1.5.0") (@Since("1.5.0") override val uid: String) encoderStages += new VectorAttributeRewriter($(featuresCol), prefixesToRewrite.toMap) encoderStages += new ColumnPruner(tempColumns.toSet) - if (dataset.schema.fieldNames.contains(resolvedFormula.label) && - dataset.schema(resolvedFormula.label).dataType == StringType) { + if ((dataset.schema.fieldNames.contains(resolvedFormula.label) && + dataset.schema(resolvedFormula.label).dataType == StringType) || $(forceIndexLabel)) { encoderStages += new StringIndexer() .setInputCol(resolvedFormula.label) .setOutputCol($(labelCol)) @@ -181,6 +202,8 @@ class RFormula @Since("1.5.0") (@Since("1.5.0") override val uid: String) @Since("1.5.0") // optimistic schema; does not contain any ML attributes override def transformSchema(schema: StructType): StructType = { + require(!hasLabelCol(schema) || !$(forceIndexLabel), + "If label column already exists, forceIndexLabel can not be set with true.") if (hasLabelCol(schema)) { StructType(schema.fields :+ StructField($(featuresCol), new VectorUDT, true)) } else { |