diff options
author | Holden Karau <holden@pigscanfly.ca> | 2015-06-26 01:19:05 -0700 |
---|---|---|
committer | DB Tsai <dbt@netflix.com> | 2015-06-26 01:19:05 -0700 |
commit | c9e05a315a96fbf3026a2b3c6934dd2dec420099 (patch) | |
tree | 4c63dd605e13e2992b00e6f1651becbbbb5f56e5 | |
parent | 9fed6abfdcb7afcf92be56e5ccbed6599fe66bc4 (diff) | |
download | spark-c9e05a315a96fbf3026a2b3c6934dd2dec420099.tar.gz spark-c9e05a315a96fbf3026a2b3c6934dd2dec420099.tar.bz2 spark-c9e05a315a96fbf3026a2b3c6934dd2dec420099.zip |
[SPARK-8613] [ML] [TRIVIAL] add param to disable linear feature scaling
Add a param to disable linear feature scaling (to be implemented later in linear & logistic regression). Done as a seperate PR so we can use same param & not conflict while working on the sub-tasks.
Author: Holden Karau <holden@pigscanfly.ca>
Closes #7024 from holdenk/SPARK-8522-Disable-Linear_featureScaling-Spark-8613-Add-param and squashes the following commits:
ce8931a [Holden Karau] Regenerate the sharedParams code
fa6427e [Holden Karau] update text for standardization param.
7b24a2b [Holden Karau] generate the new standardization param
3c190af [Holden Karau] Add the standardization param to sharedparamscodegen
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala | 3 | ||||
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala | 17 |
2 files changed, 20 insertions, 0 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala b/mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala index 8ffbcf0d8b..b0a6af171c 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala @@ -53,6 +53,9 @@ private[shared] object SharedParamsCodeGen { ParamDesc[Int]("checkpointInterval", "checkpoint interval (>= 1)", isValid = "ParamValidators.gtEq(1)"), ParamDesc[Boolean]("fitIntercept", "whether to fit an intercept term", Some("true")), + ParamDesc[Boolean]("standardization", "whether to standardize the training features" + + " prior to fitting the model sequence. Note that the coefficients of models are" + + " always returned on the original scale.", Some("true")), ParamDesc[Long]("seed", "random seed", Some("this.getClass.getName.hashCode.toLong")), ParamDesc[Double]("elasticNetParam", "the ElasticNet mixing parameter, in range [0, 1]." + " For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an L1 penalty.", diff --git a/mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala b/mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala index a0c8ccdac9..bbe08939b6 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala @@ -234,6 +234,23 @@ private[ml] trait HasFitIntercept extends Params { } /** + * (private[ml]) Trait for shared param standardization (default: true). + */ +private[ml] trait HasStandardization extends Params { + + /** + * Param for whether to standardize the training features prior to fitting the model sequence. Note that the coefficients of models are always returned on the original scale.. + * @group param + */ + final val standardization: BooleanParam = new BooleanParam(this, "standardization", "whether to standardize the training features prior to fitting the model sequence. Note that the coefficients of models are always returned on the original scale.") + + setDefault(standardization, true) + + /** @group getParam */ + final def getStandardization: Boolean = $(standardization) +} + +/** * (private[ml]) Trait for shared param seed (default: this.getClass.getName.hashCode.toLong). */ private[ml] trait HasSeed extends Params { |