fixing code style based on feedback

mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala

@@ -14,6 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+
 package org.apache.spark.mllib.tree.configuration
 
 /**
@@ -22,4 +23,4 @@ package org.apache.spark.mllib.tree.configuration
 object Algo extends Enumeration {
   type Algo = Value
   val Classification, Regression = Value
-}
+}

mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala

@@ -14,6 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+
 package org.apache.spark.mllib.tree.configuration
 
 /**

mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala

@@ -14,6 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+
 package org.apache.spark.mllib.tree.configuration
 
 /**

mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala

@@ -14,6 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+
 package org.apache.spark.mllib.tree.configuration
 
 import org.apache.spark.mllib.tree.impurity.Impurity
@@ -34,13 +35,13 @@ import org.apache.spark.mllib.tree.configuration.QuantileStrategy._
  *                                zero-indexed.
  */
 class Strategy  (
-                val algo : Algo,
-                val impurity : Impurity,
-                val maxDepth : Int,
-                val maxBins : Int = 100,
-                val quantileCalculationStrategy : QuantileStrategy = Sort,
-                val categoricalFeaturesInfo : Map[Int,Int] = Map[Int,Int]()) extends Serializable {
+                val algo: Algo,
+                val impurity: Impurity,
+                val maxDepth: Int,
+                val maxBins: Int = 100,
+                val quantileCalculationStrategy: QuantileStrategy = Sort,
+                val categoricalFeaturesInfo: Map[Int,Int] = Map[Int,Int]()) extends Serializable {
 
-  var numBins : Int  = Int.MinValue
+  var numBins: Int  = Int.MinValue
 
 }

mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala

@@ -14,6 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+
 package org.apache.spark.mllib.tree.impurity
 
 import javax.naming.OperationNotSupportedException

mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala

@@ -14,6 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+
 package org.apache.spark.mllib.tree.impurity
 
 import javax.naming.OperationNotSupportedException

mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala

@@ -14,12 +14,29 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+
 package org.apache.spark.mllib.tree.impurity
 
+/**
+ * Trail for calculating information gain
+ */
 trait Impurity extends Serializable {
 
+  /**
+   * information calculation for binary classification
+   * @param c0 count of instances with label 0
+   * @param c1 count of instances with label 1
+   * @return information value
+   */
   def calculate(c0 : Double, c1 : Double): Double
 
-  def calculate(count : Double, sum : Double, sumSquares : Double) : Double
+  /**
+   * information calculation for regression
+   * @param count number of instances
+   * @param sum sum of labels
+   * @param sumSquares summation of squares of the labels
+   * @return information value
+   */
+  def calculate(count: Double, sum: Double, sumSquares: Double): Double
 
 }

mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Variance.scala

@@ -14,6 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+
 package org.apache.spark.mllib.tree.impurity
 
 import javax.naming.OperationNotSupportedException
@@ -23,7 +24,8 @@ import org.apache.spark.Logging
  * Class for calculating variance during regression
  */
 object Variance extends Impurity with Logging {
-   def calculate(c0: Double, c1: Double): Double = throw new OperationNotSupportedException("Variance.calculate")
+   def calculate(c0: Double, c1: Double): Double
+   = throw new OperationNotSupportedException("Variance.calculate")
 
   /**
    * variance calculation

mllib/src/main/scala/org/apache/spark/mllib/tree/model/Bin.scala

@@ -14,6 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+
 package org.apache.spark.mllib.tree.model
 
 import org.apache.spark.mllib.tree.configuration.FeatureType._
@@ -29,6 +30,6 @@ import org.apache.spark.mllib.tree.configuration.FeatureType._
  * @param featureType type of feature -- categorical or continuous
  * @param category categorical label value accepted in the bin
  */
-case class Bin(lowSplit : Split, highSplit : Split, featureType : FeatureType, category : Double) {
+case class Bin(lowSplit: Split, highSplit: Split, featureType: FeatureType, category: Double) {
 
 }

mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala

@@ -14,6 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+
 package org.apache.spark.mllib.tree.model
 
 import org.apache.spark.mllib.tree.configuration.Algo._
@@ -24,15 +25,15 @@ import org.apache.spark.rdd.RDD
  * @param topNode root node
  * @param algo algorithm type -- classification or regression
  */
-class DecisionTreeModel(val topNode : Node, val algo : Algo) extends Serializable {
+class DecisionTreeModel(val topNode: Node, val algo: Algo) extends Serializable {
 
   /**
    * Predict values for a single data point using the model trained.
    *
    * @param features array representing a single data point
    * @return Double prediction from the trained model
    */
-  def predict(features : Array[Double]) : Double = {
+  def predict(features: Array[Double]): Double = {
     algo match {
       case Classification => {
         if (topNode.predictIfLeaf(features) < 0.5) 0.0 else 1.0

mllib/src/main/scala/org/apache/spark/mllib/tree/model/Filter.scala

@@ -14,14 +14,15 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+
 package org.apache.spark.mllib.tree.model
 
 /**
  * Filter specifying a split and type of comparison to be applied on features
  * @param split split specifying the feature index, type and threshold
  * @param comparison integer specifying <,=,>
  */
-case class Filter(split : Split, comparison : Int) {
+case class Filter(split: Split, comparison: Int) {
   // Comparison -1,0,1 signifies <.=,>
   override def toString = " split = " + split + "comparison = " + comparison
 }

mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala

@@ -14,6 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+
 package org.apache.spark.mllib.tree.model
 
 /**
@@ -25,11 +26,11 @@ package org.apache.spark.mllib.tree.model
  * @param predict predicted value
  */
 class InformationGainStats(
-    val gain : Double,
+    val gain: Double,
     val impurity: Double,
-    val leftImpurity : Double,
-    val rightImpurity : Double,
-    val predict : Double) extends Serializable {
+    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"