style update

pdeyhim · Mar 27, 2014 · b11659c · b11659c
1 parent 78c4671
commit b11659c
Show file tree

Hide file tree

Showing 9 changed files with 57 additions and 35 deletions.
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/MLContext.scala b/mllib/src/main/scala/org/apache/spark/mllib/MLContext.scala
@@ -26,11 +26,11 @@ import org.apache.spark.rdd.RDD
 class MLContext(self: SparkContext) {
   /**
    * Reads labeled data in the LIBSVM format into an RDD[LabeledPoint].
-   * The LIBSVM format is a text-based format used by LIBSVM (http://www.csie.ntu.edu.tw/~cjlin/libsvm/).
+   * The LIBSVM format is a text-based format used by LIBSVM and LIBLINEAR.
    * Each line represents a labeled sparse feature vector using the following format:
    * {{{label index1:value1 index2:value2 ...}}}
    * where the indices are one-based and in ascending order.
-   * This method parses each line into a [[org.apache.spark.mllib.regression.LabeledPoint]] instance,
+   * This method parses each line into a [[org.apache.spark.mllib.regression.LabeledPoint]],
    * where the feature indices are converted to zero-based.
    *
    * @param path file or directory path in any Hadoop-supported file system URI

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala
@@ -37,17 +37,17 @@ abstract class Gradient extends Serializable {
   def compute(data: Vector, label: Double, weights: Vector): (Vector, Double)
 
   /**
-   * Compute the gradient and loss given the features of a single data point, add the gradient to a provided vector to
-   * avoid creating new objects, and return loss.
+   * Compute the gradient and loss given the features of a single data point,
+   * add the gradient to a provided vector to avoid creating new objects, and return loss.
    *
    * @param data features for one data point
    * @param label label for this data point
    * @param weights weights/coefficients corresponding to features
-   * @param gradientAddTo gradient will be added to this vector
+   * @param cumGradient the computed gradient will be added to this vector
    *
-   * @return (gradient: Vector, loss: Double)
+   * @return loss
    */
-  def compute(data: Vector, label: Double, weights: Vector, gradientAddTo: Vector): Double
+  def compute(data: Vector, label: Double, weights: Vector, cumGradient: Vector): Double
 }
 
 /**
@@ -71,13 +71,17 @@ class LogisticGradient extends Gradient {
     (Vectors.fromBreeze(gradient), loss)
   }
 
-  override def compute(data: Vector, label: Double, weights: Vector, gradientAddTo: Vector): Double = {
+  override def compute(
+      data: Vector,
+      label: Double,
+      weights: Vector,
+      cumGradient: Vector): Double = {
     val brzData = data.toBreeze
     val brzWeights = weights.toBreeze
     val margin: Double = -1.0 * brzWeights.dot(brzData)
     val gradientMultiplier = (1.0 / (1.0 + math.exp(margin))) - label
 
-    brzAxpy(gradientMultiplier, brzData, gradientAddTo.toBreeze)
+    brzAxpy(gradientMultiplier, brzData, cumGradient.toBreeze)
 
     if (label > 0) {
       math.log(1 + math.exp(margin))
@@ -104,12 +108,16 @@ class LeastSquaresGradient extends Gradient {
     (Vectors.fromBreeze(gradient), loss)
   }
 
-  override def compute(data: Vector, label: Double, weights: Vector, gradientAddTo: Vector): Double = {
+  override def compute(
+      data: Vector,
+      label: Double,
+      weights: Vector,
+      cumGradient: Vector): Double = {
     val brzData = data.toBreeze
     val brzWeights = weights.toBreeze
     val diff = brzWeights.dot(brzData) - label
 
-    brzAxpy(2.0 * diff, brzData, gradientAddTo.toBreeze)
+    brzAxpy(2.0 * diff, brzData, cumGradient.toBreeze)
 
     diff * diff
   }
@@ -137,7 +145,11 @@ class HingeGradient extends Gradient {
     }
   }
 
-  override def compute(data: Vector, label: Double, weights: Vector, gradientAddTo: Vector): Double = {
+  override def compute(
+      data: Vector,
+      label: Double,
+      weights: Vector,
+      cumGradient: Vector): Double = {
     val brzData = data.toBreeze
     val brzWeights = weights.toBreeze
     val dotProduct = brzWeights.dot(brzData)
@@ -147,7 +159,7 @@ class HingeGradient extends Gradient {
     val labelScaled = 2 * label - 1.0
 
     if (1.0 > labelScaled * dotProduct) {
-      brzAxpy(-labelScaled, brzData, gradientAddTo.toBreeze)
+      brzAxpy(-labelScaled, brzData, cumGradient.toBreeze)
       1.0 - labelScaled * dotProduct
     } else {
       0.0

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/Lasso.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/Lasso.scala
@@ -17,13 +17,13 @@
 
 package org.apache.spark.mllib.regression
 
+import breeze.linalg.{Vector => BV}
+
 import org.apache.spark.SparkContext
 import org.apache.spark.rdd.RDD
+import org.apache.spark.mllib.linalg.{Vector, Vectors}
 import org.apache.spark.mllib.optimization._
 import org.apache.spark.mllib.util.MLUtils
-import org.apache.spark.mllib.linalg.{Vector, Vectors}
-
-import breeze.linalg.{Vector => BV, DenseVector => BDV}
 
 /**
  * Regression model trained using Lasso.
@@ -142,7 +142,8 @@ object LassoWithSGD {
       regParam: Double,
       miniBatchFraction: Double,
       initialWeights: Vector): LassoModel = {
-    new LassoWithSGD(stepSize, numIterations, regParam, miniBatchFraction).run(input, initialWeights)
+    new LassoWithSGD(stepSize, numIterations, regParam, miniBatchFraction)
+      .run(input, initialWeights)
   }
 
   /**

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/LinearRegression.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/LinearRegression.scala
@@ -19,9 +19,9 @@ package org.apache.spark.mllib.regression
 
 import org.apache.spark.SparkContext
 import org.apache.spark.rdd.RDD
+import org.apache.spark.mllib.linalg.Vector
 import org.apache.spark.mllib.optimization._
 import org.apache.spark.mllib.util.MLUtils
-import org.apache.spark.mllib.linalg.{Vector, Vectors}
 
 /**
  * Regression model trained using LinearRegression.

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/RidgeRegression.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/RidgeRegression.scala
@@ -17,14 +17,14 @@
 
 package org.apache.spark.mllib.regression
 
+import breeze.linalg.{Vector => BV}
+
 import org.apache.spark.SparkContext
 import org.apache.spark.rdd.RDD
 import org.apache.spark.mllib.optimization._
 import org.apache.spark.mllib.util.MLUtils
 import org.apache.spark.mllib.linalg.{Vectors, Vector}
 
-import breeze.linalg.{Vector => BV, DenseVector => BDV}
-
 /**
  * Regression model trained using RidgeRegression.
  *
@@ -72,9 +72,9 @@ class RidgeRegressionWithSGD private (
   // We don't want to penalize the intercept in RidgeRegression, so set this to false.
   super.setIntercept(false)
 
-  var yMean = 0.0
-  var xColMean: BV[Double] = _
-  var xColSd: BV[Double] = _
+  private var yMean = 0.0
+  private var xColMean: BV[Double] = _
+  private var xColSd: BV[Double] = _
 
   /**
    * Construct a RidgeRegression object with default parameters
@@ -214,8 +214,8 @@ object RidgeRegressionWithSGD {
 
   def main(args: Array[String]) {
     if (args.length != 5) {
-      println("Usage: RidgeRegression <master> <input_dir> <step_size> <regularization_parameter>" +
-        " <niters>")
+      println("Usage: RidgeRegression <master> <input_dir> <step_size> " +
+        "<regularization_parameter> <niters>")
       System.exit(1)
     }
     val sc = new SparkContext(args(0), "RidgeRegression")

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala
@@ -82,7 +82,10 @@ object MLUtils {
    *     xColMean - Row vector with mean for every column (or feature) of the input data
    *     xColSd - Row vector standard deviation for every column (or feature) of the input data.
    */
-  def computeStats(data: RDD[LabeledPoint], numFeatures: Int, numExamples: Long): (Double, Vector, Vector) = {
+  def computeStats(
+      data: RDD[LabeledPoint],
+      numFeatures: Int,
+      numExamples: Long): (Double, Vector, Vector) = {
     val brzData = data.map { case LabeledPoint(label, features) =>
       (label, features.toBreeze)
     }

diff --git a/mllib/src/test/scala/org/apache/spark/mllib/MLContextSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/MLContextSuite.scala
@@ -17,13 +17,16 @@
 
 package org.apache.spark.mllib
 
-import org.apache.spark.mllib.MLContext._
-import org.apache.spark.mllib.util.LocalSparkContext
-import org.scalatest.FunSuite
-import com.google.common.io.Files
 import java.io.File
+
+import org.scalatest.FunSuite
+
 import com.google.common.base.Charsets
+import com.google.common.io.Files
+
+import org.apache.spark.mllib.MLContext._
 import org.apache.spark.mllib.linalg.Vectors
+import org.apache.spark.mllib.util.LocalSparkContext
 
 class MLContextSuite extends FunSuite with LocalSparkContext {
   test("libSVMFile") {

diff --git a/mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala
@@ -21,9 +21,9 @@ import scala.util.Random
 
 import org.scalatest.FunSuite
 
+import org.apache.spark.mllib.linalg.Vectors
 import org.apache.spark.mllib.regression.LabeledPoint
 import org.apache.spark.mllib.util.LocalSparkContext
-import org.apache.spark.mllib.linalg.Vectors
 
 object NaiveBayesSuite {
 

diff --git a/mllib/src/test/scala/org/apache/spark/mllib/regression/LinearRegressionSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/regression/LinearRegressionSuite.scala
@@ -19,8 +19,8 @@ package org.apache.spark.mllib.regression
 
 import org.scalatest.FunSuite
 
-import org.apache.spark.mllib.util.{LinearDataGenerator, LocalSparkContext}
 import org.apache.spark.mllib.linalg.Vectors
+import org.apache.spark.mllib.util.{LinearDataGenerator, LocalSparkContext}
 
 class LinearRegressionSuite extends FunSuite with LocalSparkContext {
 
@@ -88,7 +88,8 @@ class LinearRegressionSuite extends FunSuite with LocalSparkContext {
 
   // Test if we can correctly learn Y = 10*X1 + 10*X10000
   test("sparse linear regression without intercept") {
-    val denseRDD = sc.parallelize(LinearDataGenerator.generateLinearInput(0.0, Array(10.0, 10.0), 100, 42), 2)
+    val denseRDD = sc.parallelize(
+      LinearDataGenerator.generateLinearInput(0.0, Array(10.0, 10.0), 100, 42), 2)
     val sparseRDD = denseRDD.map { case LabeledPoint(label, v) =>
       val sv = Vectors.sparse(10000, Seq((0, v(0)), (9999, v(1))))
       LabeledPoint(label, sv)
@@ -113,9 +114,11 @@ class LinearRegressionSuite extends FunSuite with LocalSparkContext {
     val sparseValidationRDD = sc.parallelize(sparseValidationData, 2)
 
       // Test prediction on RDD.
-    validatePrediction(model.predict(sparseValidationRDD.map(_.features)).collect(), sparseValidationData)
+    validatePrediction(
+      model.predict(sparseValidationRDD.map(_.features)).collect(), sparseValidationData)
 
     // Test prediction on Array.
-    validatePrediction(sparseValidationData.map(row => model.predict(row.features)), sparseValidationData)
+    validatePrediction(
+      sparseValidationData.map(row => model.predict(row.features)), sparseValidationData)
   }
 }