diff options
author | Bryan Cutler <cutlerb@gmail.com> | 2016-06-10 11:27:30 -0700 |
---|---|---|
committer | Yanbo Liang <ybliang8@gmail.com> | 2016-06-10 11:27:30 -0700 |
commit | 7d7a0a5e0749909e97d90188707cc9220a1bb73a (patch) | |
tree | f6919d175658e1b901e9bbc0a469efa0906ad153 /mllib/src | |
parent | 254bc8c34e70241508bdfc8ff42a65491f5280cd (diff) | |
download | spark-7d7a0a5e0749909e97d90188707cc9220a1bb73a.tar.gz spark-7d7a0a5e0749909e97d90188707cc9220a1bb73a.tar.bz2 spark-7d7a0a5e0749909e97d90188707cc9220a1bb73a.zip |
[SPARK-15738][PYSPARK][ML] Adding Pyspark ml RFormula __str__ method similar to Scala API
## What changes were proposed in this pull request?
Adding __str__ to RFormula and model that will show the set formula param and resolved formula. This is currently present in the Scala API, found missing in PySpark during Spark 2.0 coverage review.
## How was this patch tested?
run pyspark-ml tests locally
Author: Bryan Cutler <cutlerb@gmail.com>
Closes #13481 from BryanCutler/pyspark-ml-rformula_str-SPARK-15738.
Diffstat (limited to 'mllib/src')
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala | 2 | ||||
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/feature/RFormulaParser.scala | 14 |
2 files changed, 14 insertions, 2 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 2916b6d9df..a7ca0fe252 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 @@ -182,7 +182,7 @@ class RFormula(override val uid: String) override def copy(extra: ParamMap): RFormula = defaultCopy(extra) - override def toString: String = s"RFormula(${get(formula)}) (uid=$uid)" + override def toString: String = s"RFormula(${get(formula).getOrElse("")}) (uid=$uid)" } @Since("2.0.0") diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormulaParser.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormulaParser.scala index 19aecff038..2dd565a782 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormulaParser.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormulaParser.scala @@ -126,7 +126,19 @@ private[ml] case class ParsedRFormula(label: ColumnRef, terms: Seq[Term]) { * @param hasIntercept whether the formula specifies fitting with an intercept. */ private[ml] case class ResolvedRFormula( - label: String, terms: Seq[Seq[String]], hasIntercept: Boolean) + label: String, terms: Seq[Seq[String]], hasIntercept: Boolean) { + + override def toString: String = { + val ts = terms.map { + case t if t.length > 1 => + s"${t.mkString("{", ",", "}")}" + case t => + t.mkString + } + val termStr = ts.mkString("[", ",", "]") + s"ResolvedRFormula(label=$label, terms=$termStr, hasIntercept=$hasIntercept)" + } +} /** * R formula terms. See the R formula docs here for more information: |