[SPARK-7985] [ML] [MLlib] [Docs] Remove "fittingParamMap" references. Updating ML Doc "Estimator, Transformer, and Param" examples.

Updating ML Doc's *"Estimator, Transformer, and Param"* example to use `model.extractParamMap` instead of `model.fittingParamMap`, which no longer exists.

mengxr, I believe this addresses (part of) the *update documentation* TODO list item from [PR 5820](#5820).

Author: Mike Dusenberry <[email protected]>

Closes #6514 from dusenberrymw/Fix_ML_Doc_Estimator_Transformer_Param_Example and squashes the following commits:

6366e1f [Mike Dusenberry] Updating instances of model.extractParamMap to model.parent.extractParamMap, since the Params of the parent Estimator could possibly differ from thos of the Model.
d850e0e [Mike Dusenberry] Removing all references to "fittingParamMap" throughout Spark, since it has been removed.
0480304 [Mike Dusenberry] Updating the ML Doc "Estimator, Transformer, and Param" Java example to use model.extractParamMap() instead of model.fittingParamMap(), which no longer exists.
7d34939 [Mike Dusenberry] Updating ML Doc "Estimator, Transformer, and Param" example to use model.extractParamMap instead of model.fittingParamMap, which no longer exists.

(cherry picked from commit ad06727)
Signed-off-by: Joseph K. Bradley <[email protected]>

Author: dusenberrymw

docs/ml-guide.md

@@ -207,7 +207,7 @@ val model1 = lr.fit(training.toDF)
 // we can view the parameters it used during fit().
 // This prints the parameter (name: value) pairs, where names are unique IDs for this
 // LogisticRegression instance.
-println("Model 1 was fit using parameters: " + model1.fittingParamMap)
+println("Model 1 was fit using parameters: " + model1.parent.extractParamMap)
 
 // We may alternatively specify parameters using a ParamMap,
 // which supports several methods for specifying parameters.
@@ -222,7 +222,7 @@ val paramMapCombined = paramMap ++ paramMap2
 // Now learn a new model using the paramMapCombined parameters.
 // paramMapCombined overrides all parameters set earlier via lr.set* methods.
 val model2 = lr.fit(training.toDF, paramMapCombined)
-println("Model 2 was fit using parameters: " + model2.fittingParamMap)
+println("Model 2 was fit using parameters: " + model2.parent.extractParamMap)
 
 // Prepare test data.
 val test = sc.parallelize(Seq(
@@ -289,7 +289,7 @@ LogisticRegressionModel model1 = lr.fit(training);
 // we can view the parameters it used during fit().
 // This prints the parameter (name: value) pairs, where names are unique IDs for this
 // LogisticRegression instance.
-System.out.println("Model 1 was fit using parameters: " + model1.fittingParamMap());
+System.out.println("Model 1 was fit using parameters: " + model1.parent().extractParamMap());
 
 // We may alternatively specify parameters using a ParamMap.
 ParamMap paramMap = new ParamMap();
@@ -305,7 +305,7 @@ ParamMap paramMapCombined = paramMap.$plus$plus(paramMap2);
 // Now learn a new model using the paramMapCombined parameters.
 // paramMapCombined overrides all parameters set earlier via lr.set* methods.
 LogisticRegressionModel model2 = lr.fit(training, paramMapCombined);
-System.out.println("Model 2 was fit using parameters: " + model2.fittingParamMap());
+System.out.println("Model 2 was fit using parameters: " + model2.parent().extractParamMap());
 
 // Prepare test documents.
 List<LabeledPoint> localTest = Lists.newArrayList(

mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala

@@ -208,7 +208,7 @@ private[ml] object GBTClassificationModel {
     require(oldModel.algo == OldAlgo.Classification, "Cannot convert GradientBoostedTreesModel" +
       s" with algo=${oldModel.algo} (old API) to GBTClassificationModel (new API).")
     val newTrees = oldModel.trees.map { tree =>
-      // parent, fittingParamMap for each tree is null since there are no good ways to set these.
+      // parent for each tree is null since there is no good way to set this.
       DecisionTreeRegressionModel.fromOld(tree, null, categoricalFeatures)
     }
     val uid = if (parent != null) parent.uid else Identifiable.randomUID("gbtc")

mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala

@@ -170,7 +170,7 @@ private[ml] object RandomForestClassificationModel {
     require(oldModel.algo == OldAlgo.Classification, "Cannot convert RandomForestModel" +
       s" with algo=${oldModel.algo} (old API) to RandomForestClassificationModel (new API).")
     val newTrees = oldModel.trees.map { tree =>
-      // parent, fittingParamMap for each tree is null since there are no good ways to set these.
+      // parent for each tree is null since there is no good way to set this.
       DecisionTreeClassificationModel.fromOld(tree, null, categoricalFeatures)
     }
     val uid = if (parent != null) parent.uid else Identifiable.randomUID("rfc")

mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala

@@ -198,7 +198,7 @@ private[ml] object GBTRegressionModel {
     require(oldModel.algo == OldAlgo.Regression, "Cannot convert GradientBoostedTreesModel" +
       s" with algo=${oldModel.algo} (old API) to GBTRegressionModel (new API).")
     val newTrees = oldModel.trees.map { tree =>
-      // parent, fittingParamMap for each tree is null since there are no good ways to set these.
+      // parent for each tree is null since there is no good way to set this.
       DecisionTreeRegressionModel.fromOld(tree, null, categoricalFeatures)
     }
     val uid = if (parent != null) parent.uid else Identifiable.randomUID("gbtr")

mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala

@@ -152,7 +152,7 @@ private[ml] object RandomForestRegressionModel {
     require(oldModel.algo == OldAlgo.Regression, "Cannot convert RandomForestModel" +
       s" with algo=${oldModel.algo} (old API) to RandomForestRegressionModel (new API).")
     val newTrees = oldModel.trees.map { tree =>
-      // parent, fittingParamMap for each tree is null since there are no good ways to set these.
+      // parent for each tree is null since there is no good way to set this.
       DecisionTreeRegressionModel.fromOld(tree, null, categoricalFeatures)
     }
     new RandomForestRegressionModel(parent.uid, newTrees)

mllib/src/test/scala/org/apache/spark/ml/classification/DecisionTreeClassifierSuite.scala

@@ -266,7 +266,7 @@ private[ml] object DecisionTreeClassifierSuite extends FunSuite {
     val oldTree = OldDecisionTree.train(data, oldStrategy)
     val newData: DataFrame = TreeTests.setMetadata(data, categoricalFeatures, numClasses)
     val newTree = dt.fit(newData)
-    // Use parent, fittingParamMap from newTree since these are not checked anyways.
+    // Use parent from newTree since this is not checked anyways.
     val oldTreeAsNew = DecisionTreeClassificationModel.fromOld(
       oldTree, newTree.parent.asInstanceOf[DecisionTreeClassifier], categoricalFeatures)
     TreeTests.checkEqual(oldTreeAsNew, newTree)

mllib/src/test/scala/org/apache/spark/ml/classification/GBTClassifierSuite.scala

@@ -128,7 +128,7 @@ private object GBTClassifierSuite {
     val oldModel = oldGBT.run(data)
     val newData: DataFrame = TreeTests.setMetadata(data, categoricalFeatures, numClasses = 2)
     val newModel = gbt.fit(newData)
-    // Use parent, fittingParamMap from newTree since these are not checked anyways.
+    // Use parent from newTree since this is not checked anyways.
     val oldModelAsNew = GBTClassificationModel.fromOld(
       oldModel, newModel.parent.asInstanceOf[GBTClassifier], categoricalFeatures)
     TreeTests.checkEqual(oldModelAsNew, newModel)

mllib/src/test/scala/org/apache/spark/ml/classification/RandomForestClassifierSuite.scala

@@ -158,7 +158,7 @@ private object RandomForestClassifierSuite {
       data, oldStrategy, rf.getNumTrees, rf.getFeatureSubsetStrategy, rf.getSeed.toInt)
     val newData: DataFrame = TreeTests.setMetadata(data, categoricalFeatures, numClasses)
     val newModel = rf.fit(newData)
-    // Use parent, fittingParamMap from newTree since these are not checked anyways.
+    // Use parent from newTree since this is not checked anyways.
     val oldModelAsNew = RandomForestClassificationModel.fromOld(
       oldModel, newModel.parent.asInstanceOf[RandomForestClassifier], categoricalFeatures)
     TreeTests.checkEqual(oldModelAsNew, newModel)

mllib/src/test/scala/org/apache/spark/ml/regression/DecisionTreeRegressorSuite.scala

@@ -83,7 +83,7 @@ private[ml] object DecisionTreeRegressorSuite extends FunSuite {
     val oldTree = OldDecisionTree.train(data, oldStrategy)
     val newData: DataFrame = TreeTests.setMetadata(data, categoricalFeatures, numClasses = 0)
     val newTree = dt.fit(newData)
-    // Use parent, fittingParamMap from newTree since these are not checked anyways.
+    // Use parent from newTree since this is not checked anyways.
     val oldTreeAsNew = DecisionTreeRegressionModel.fromOld(
       oldTree, newTree.parent.asInstanceOf[DecisionTreeRegressor], categoricalFeatures)
     TreeTests.checkEqual(oldTreeAsNew, newTree)

mllib/src/test/scala/org/apache/spark/ml/regression/GBTRegressorSuite.scala

@@ -129,7 +129,7 @@ private object GBTRegressorSuite {
     val oldModel = oldGBT.run(data)
     val newData: DataFrame = TreeTests.setMetadata(data, categoricalFeatures, numClasses = 0)
     val newModel = gbt.fit(newData)
-    // Use parent, fittingParamMap from newTree since these are not checked anyways.
+    // Use parent from newTree since this is not checked anyways.
     val oldModelAsNew = GBTRegressionModel.fromOld(
       oldModel, newModel.parent.asInstanceOf[GBTRegressor], categoricalFeatures)
     TreeTests.checkEqual(oldModelAsNew, newModel)