address feedback

apache · Jun 2, 2015 · 136e0dd · 136e0dd
1 parent 1ec29d4
commit 136e0dd
Show file tree

Hide file tree

Showing 6 changed files with 16 additions and 19 deletions.
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionExample.scala
@@ -68,7 +68,7 @@ object LinearRegressionExample {
         s"L1 and L2, default: ${defaultParams.elasticNetParam}")
         .action((x, c) => c.copy(elasticNetParam = x))
       opt[Int]("maxIter")
-        .text(s"maximal number of iterations, default: ${defaultParams.maxIter}")
+        .text(s"maximum number of iterations, default: ${defaultParams.maxIter}")
         .action((x, c) => c.copy(maxIter = x))
       opt[Double]("tol")
         .text(s"the convergence tolerance of iterations, Smaller value will lead " +
@@ -115,9 +115,6 @@ object LinearRegressionExample {
     val (training: DataFrame, test: DataFrame) = DecisionTreeExample.loadDatasets(sc, params.input,
       params.dataFormat, params.testInput, "regression", params.fracTest)
 
-    // Set up Pipeline
-    val stages = new mutable.ArrayBuffer[PipelineStage]()
-
     val lir = new LinearRegression()
       .setFeaturesCol("features")
       .setLabelCol("label")
@@ -126,23 +123,19 @@ object LinearRegressionExample {
       .setMaxIter(params.maxIter)
       .setTol(params.tol)
 
-    stages += lir
-    val pipeline = new Pipeline().setStages(stages.toArray)
-
-    // Fit the Pipeline
+    // Train the model
     val startTime = System.nanoTime()
-    val pipelineModel = pipeline.fit(training)
+    val lirModel = lir.fit(training)
     val elapsedTime = (System.nanoTime() - startTime) / 1e9
     println(s"Training time: $elapsedTime seconds")
 
-    val lirModel = pipelineModel.stages.last.asInstanceOf[LinearRegressionModel]
     // Print the weights and intercept for linear regression.
     println(s"Weights: ${lirModel.weights} Intercept: ${lirModel.intercept}")
 
     println("Training data results:")
-    DecisionTreeExample.evaluateRegressionModel(pipelineModel, training, "label")
+    DecisionTreeExample.evaluateRegressionModel(lirModel, training, "label")
     println("Test data results:")
-    DecisionTreeExample.evaluateRegressionModel(pipelineModel, test, "label")
+    DecisionTreeExample.evaluateRegressionModel(lirModel, test, "label")
 
     sc.stop()
   }

diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/LogisticRegressionExample.scala
@@ -70,7 +70,7 @@ object LogisticRegressionExample {
         s"L1 and L2, default: ${defaultParams.elasticNetParam}")
         .action((x, c) => c.copy(elasticNetParam = x))
       opt[Int]("maxIter")
-        .text(s"maximal number of iterations, default: ${defaultParams.maxIter}")
+        .text(s"maximum number of iterations, default: ${defaultParams.maxIter}")
         .action((x, c) => c.copy(maxIter = x))
       opt[Boolean]("fitIntercept")
         .text(s"whether to fit an intercept term, default: ${defaultParams.fitIntercept}")

diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
@@ -74,7 +74,7 @@ class LogisticRegression(override val uid: String)
   setDefault(elasticNetParam -> 0.0)
 
   /**
-   * Set the maximal number of iterations.
+   * Set the maximum number of iterations.
    * Default is 100.
    * @group setParam
    */
@@ -90,7 +90,11 @@ class LogisticRegression(override val uid: String)
   def setTol(value: Double): this.type = set(tol, value)
   setDefault(tol -> 1E-6)
 
-  /** @group setParam */
+  /**
+   * Whether to fit an intercept term.
+   * Default is true.
+   * @group setParam
+   * */
   def setFitIntercept(value: Boolean): this.type = set(fitIntercept, value)
   setDefault(fitIntercept -> true)
 

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
@@ -33,7 +33,7 @@ private[shared] object SharedParamsCodeGen {
     val params = Seq(
       ParamDesc[Double]("regParam", "regularization parameter (>= 0)",
         isValid = "ParamValidators.gtEq(0)"),
-      ParamDesc[Int]("maxIter", "max number of iterations (>= 0)",
+      ParamDesc[Int]("maxIter", "maximum number of iterations (>= 0)",
         isValid = "ParamValidators.gtEq(0)"),
       ParamDesc[String]("featuresCol", "features column name", Some("\"features\"")),
       ParamDesc[String]("labelCol", "label column name", Some("\"label\"")),

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
@@ -45,10 +45,10 @@ private[ml] trait HasRegParam extends Params {
 private[ml] trait HasMaxIter extends Params {
 
   /**
-   * Param for max number of iterations (>= 0).
+   * Param for maximum number of iterations (>= 0).
    * @group param
    */
-  final val maxIter: IntParam = new IntParam(this, "maxIter", "max number of iterations (>= 0)", ParamValidators.gtEq(0))
+  final val maxIter: IntParam = new IntParam(this, "maxIter", "maximum number of iterations (>= 0)", ParamValidators.gtEq(0))
 
   /** @group getParam */
   final def getMaxIter: Int = $(maxIter)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala
@@ -83,7 +83,7 @@ class LinearRegression(override val uid: String)
   setDefault(elasticNetParam -> 0.0)
 
   /**
-   * Set the maximal number of iterations.
+   * Set the maximum number of iterations.
    * Default is 100.
    * @group setParam
    */