more doc for Transformer

apache · Nov 11, 2014 · ad678e9 · ad678e9
1 parent 4306ed4
commit ad678e9
Show file tree

Hide file tree

Showing 3 changed files with 18 additions and 4 deletions.
diff --git a/mllib/src/main/scala/org/apache/spark/ml/Model.scala b/mllib/src/main/scala/org/apache/spark/ml/Model.scala
@@ -20,7 +20,9 @@ package org.apache.spark.ml
 import org.apache.spark.ml.param.ParamMap
 
 /**
- * A fitted model.
+ * A fitted model, i.e., a [[Transformer]] produced by an [[Estimator]].
+ *
+ * @tparam M model type
  */
 abstract class Model[M <: Model[M]] extends Transformer {
   /**

diff --git a/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala b/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala
@@ -34,7 +34,7 @@ abstract class PipelineStage extends Serializable with Logging {
   def transform(schema: StructType, paramMap: ParamMap): StructType
 
   /**
-   * Drives the output schema from the input schema and parameters, optionally with logging.
+   * Derives the output schema from the input schema and parameters, optionally with logging.
    */
   protected def transform(schema: StructType, paramMap: ParamMap, logging: Boolean): StructType = {
     if (logging) {

diff --git a/mllib/src/main/scala/org/apache/spark/ml/Transformer.scala b/mllib/src/main/scala/org/apache/spark/ml/Transformer.scala
@@ -48,20 +48,32 @@ abstract class Transformer extends PipelineStage with Params {
   }
 
   /**
-   * Transforms the dataset with provided parameter map.
+   * Transforms the dataset with provided parameter map as additional parameters.
    * @param dataset input dataset
-   * @param paramMap parameters
+   * @param paramMap additional parameters, overwrite embedded params
    * @return transformed dataset
    */
   def transform(dataset: SchemaRDD, paramMap: ParamMap): SchemaRDD
 
   // Java-friendly versions of transform.
 
+  /**
+   * Transforms the dataset with optional parameters.
+   * @param dataset input datset
+   * @param paramPairs optional list of param pairs, overwrite embedded params
+   * @return transformed dataset
+   */
   @varargs
   def transform(dataset: JavaSchemaRDD, paramPairs: ParamPair[_]*): JavaSchemaRDD = {
     transform(dataset.schemaRDD, paramPairs: _*).toJavaSchemaRDD
   }
 
+  /**
+   * Transforms the dataset with provided parameter map as additional parameters.
+   * @param dataset input dataset
+   * @param paramMap additional parameters, overwrite embedded params
+   * @return transformed dataset
+   */
   def transform(dataset: JavaSchemaRDD, paramMap: ParamMap): JavaSchemaRDD = {
     transform(dataset.schemaRDD, paramMap).toJavaSchemaRDD
   }