code style: max line lenght <= 100

Signed-off-by: Manish Amde <manish9ue@gmail.com>
apache · Feb 28, 2014 · 9372779 · 9372779
1 parent dd0c0d7
commit 9372779
Show file tree

Hide file tree

Showing 7 changed files with 184 additions and 100 deletions.
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/RegressionTree.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/RegressionTree.scala
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTreeRunner.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTreeRunner.scala
@@ -29,7 +29,7 @@ import org.apache.spark.mllib.tree.configuration.Algo._
 object DecisionTreeRunner extends Logging {
 
   val usage = """
-    Usage: DecisionTreeRunner <master>[slices] --algo <Classification,Regression> --trainDataDir path --testDataDir path --maxDepth num [--impurity <Gini,Entropy,Variance>] [--maxBins num]
+    Usage: DecisionTreeRunner<master>[slices] --algo <Classification,Regression> --trainDataDir path --testDataDir path --maxDepth num [--impurity <Gini,Entropy,Variance>] [--maxBins num]
               """
 
 
@@ -132,7 +132,8 @@ object DecisionTreeRunner extends Logging {
 
   //TODO: Make these generic MLTable metrics
   def meanSquaredError(tree : DecisionTreeModel, data : RDD[LabeledPoint]) : Double = {
-    val meanSumOfSquares = data.map(y => (tree.predict(y.features) - y.label)*(tree.predict(y.features) - y.label)).mean()
+    val meanSumOfSquares =
+      data.map(y => (tree.predict(y.features) - y.label)*(tree.predict(y.features) - y.label)).mean()
     meanSumOfSquares
   }
 

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala
@@ -31,5 +31,7 @@ object Gini extends Impurity {
     }
   }
 
-  def calculate(count: Double, sum: Double, sumSquares: Double): Double = throw new OperationNotSupportedException("Gini.calculate")
+  def calculate(count: Double, sum: Double, sumSquares: Double): Double =
+    throw new OperationNotSupportedException("Gini.calculate")
+
 }
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala
@@ -16,13 +16,12 @@
  */
 package org.apache.spark.mllib.tree.model
 
-class InformationGainStats(val gain : Double,
-                           val impurity: Double,
-                           val leftImpurity : Double,
-                           //val leftSamples : Long,
-                           val rightImpurity : Double,
-                           //val rightSamples : Long
-                           val predict : Double) extends Serializable {
+class InformationGainStats(
+    val gain : Double,
+    val impurity: Double,
+    val leftImpurity : Double,
+    val rightImpurity : Double,
+    val predict : Double) extends Serializable {
 
   override def toString = {
     "gain = %f, impurity = %f, left impurity = %f, right impurity = %f, predict = %f"

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala
@@ -29,11 +29,13 @@ class Node ( val id : Int,
              val stats : Option[InformationGainStats]
              ) extends Serializable with Logging{
 
-  override def toString = "id = " + id + ", isLeaf = " + isLeaf + ", predict = " + predict + ", split = " + split + ", stats = " + stats
+  override def toString = "id = " + id + ", isLeaf = " + isLeaf + ", predict = " + predict + ", " +
+    "split = " + split + ", stats = " + stats
 
   def build(nodes : Array[Node]) : Unit = {
 
-    logDebug("building node " + id + " at level " + (scala.math.log(id + 1)/scala.math.log(2)).toInt )
+    logDebug("building node " + id + " at level " +
+      (scala.math.log(id + 1)/scala.math.log(2)).toInt )
     logDebug("id = " + id + ", split = " + split)
     logDebug("stats = " + stats)
     logDebug("predict = " + predict)

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala
@@ -18,14 +18,23 @@ package org.apache.spark.mllib.tree.model
 
 import org.apache.spark.mllib.tree.configuration.FeatureType.FeatureType
 
-case class Split(feature: Int, threshold : Double, featureType : FeatureType, categories : List[Double]){
+case class Split(
+    feature: Int,
+    threshold : Double,
+    featureType : FeatureType,
+    categories : List[Double]){
+
   override def toString =
-    "Feature = " + feature + ", threshold = " + threshold + ", featureType =  " + featureType + ", categories = " + categories
+    "Feature = " + feature + ", threshold = " + threshold + ", featureType =  " + featureType +
+      ", categories = " + categories
 }
 
-class DummyLowSplit(feature: Int, kind : FeatureType) extends Split(feature, Double.MinValue, kind, List())
+class DummyLowSplit(feature: Int, kind : FeatureType)
+  extends Split(feature, Double.MinValue, kind, List())
 
-class DummyHighSplit(feature: Int, kind : FeatureType) extends Split(feature, Double.MaxValue, kind, List())
+class DummyHighSplit(feature: Int, kind : FeatureType)
+  extends Split(feature, Double.MaxValue, kind, List())
 
-class DummyCategoricalSplit(feature: Int, kind : FeatureType) extends Split(feature, Double.MaxValue, kind, List())
+class DummyCategoricalSplit(feature: Int, kind : FeatureType)
+  extends Split(feature, Double.MaxValue, kind, List())