diff options
author | Shivaram Venkataraman <shivaram@eecs.berkeley.edu> | 2013-07-17 14:20:24 -0700 |
---|---|---|
committer | Shivaram Venkataraman <shivaram@eecs.berkeley.edu> | 2013-07-17 14:20:24 -0700 |
commit | 3bf989713654129ad35a80309d1b354ca5ddd06c (patch) | |
tree | ed78bfe242c04f688380263b0e9c79bd01dfd367 /mllib | |
parent | 84fa20c2a135f54745ddde9abb4f5e60af8856d1 (diff) | |
download | spark-3bf989713654129ad35a80309d1b354ca5ddd06c.tar.gz spark-3bf989713654129ad35a80309d1b354ca5ddd06c.tar.bz2 spark-3bf989713654129ad35a80309d1b354ca5ddd06c.zip |
Rename loss -> stochasticLoss and add a note to explain why we have
multiple train methods.
Diffstat (limited to 'mllib')
3 files changed, 13 insertions, 8 deletions
diff --git a/mllib/src/main/scala/spark/mllib/optimization/GradientDescent.scala b/mllib/src/main/scala/spark/mllib/optimization/GradientDescent.scala index 2ac0808357..77f5a7ae24 100644 --- a/mllib/src/main/scala/spark/mllib/optimization/GradientDescent.scala +++ b/mllib/src/main/scala/spark/mllib/optimization/GradientDescent.scala @@ -40,7 +40,8 @@ object GradientDescent { * one iteration of SGD. Default value 1.0. * * @return weights - Column matrix containing weights for every feature. - * @return lossHistory - Array containing the loss computed for every iteration. + * @return stochasticLossHistory - Array containing the stochastic loss computed for + * every iteration. */ def runMiniBatchSGD( data: RDD[(Double, Array[Double])], @@ -51,7 +52,7 @@ object GradientDescent { initialWeights: Array[Double], miniBatchFraction: Double=1.0) : (DoubleMatrix, Array[Double]) = { - val lossHistory = new ArrayBuffer[Double](numIters) + val stochasticLossHistory = new ArrayBuffer[Double](numIters) val nexamples: Long = data.count() val miniBatchSize = nexamples * miniBatchFraction @@ -69,12 +70,12 @@ object GradientDescent { (grad, loss) }.reduce((a, b) => (a._1.addi(b._1), a._2 + b._2)) - lossHistory.append(lossSum / miniBatchSize + reg_val) + stochasticLossHistory.append(lossSum / miniBatchSize + reg_val) val update = updater.compute(weights, gradientSum.div(miniBatchSize), stepSize, i) weights = update._1 reg_val = update._2 } - (weights, lossHistory.toArray) + (weights, stochasticLossHistory.toArray) } } diff --git a/mllib/src/main/scala/spark/mllib/regression/LogisticRegression.scala b/mllib/src/main/scala/spark/mllib/regression/LogisticRegression.scala index dab15aa386..664baf33a3 100644 --- a/mllib/src/main/scala/spark/mllib/regression/LogisticRegression.scala +++ b/mllib/src/main/scala/spark/mllib/regression/LogisticRegression.scala @@ -30,7 +30,7 @@ import org.jblas.DoubleMatrix class LogisticRegressionModel( val weights: DoubleMatrix, val intercept: Double, - val losses: Array[Double]) extends RegressionModel { + val stochasticLosses: Array[Double]) extends RegressionModel { override def predict(testData: spark.RDD[Array[Double]]) = { testData.map { x => @@ -114,7 +114,7 @@ class LogisticRegression private (var stepSize: Double, var miniBatchFraction: D val initalWeightsWithIntercept = Array(1.0, initialWeights:_*) - val (weights, losses) = GradientDescent.runMiniBatchSGD( + val (weights, stochasticLosses) = GradientDescent.runMiniBatchSGD( data, new LogisticGradient(), new SimpleUpdater(), @@ -126,17 +126,19 @@ class LogisticRegression private (var stepSize: Double, var miniBatchFraction: D val weightsScaled = weights.getRange(1, weights.length) val intercept = weights.get(0) - val model = new LogisticRegressionModel(weightsScaled, intercept, losses) + val model = new LogisticRegressionModel(weightsScaled, intercept, stochasticLosses) logInfo("Final model weights " + model.weights) logInfo("Final model intercept " + model.intercept) - logInfo("Last 10 losses " + model.losses.takeRight(10).mkString(", ")) + logInfo("Last 10 stochastic losses " + model.stochasticLosses.takeRight(10).mkString(", ")) model } } /** * Top-level methods for calling Logistic Regression. + * NOTE(shivaram): We use multiple train methods instead of default arguments to support + * Java programs. */ object LogisticRegression { diff --git a/mllib/src/main/scala/spark/mllib/regression/RidgeRegression.scala b/mllib/src/main/scala/spark/mllib/regression/RidgeRegression.scala index 7c7f912b43..f724edd732 100644 --- a/mllib/src/main/scala/spark/mllib/regression/RidgeRegression.scala +++ b/mllib/src/main/scala/spark/mllib/regression/RidgeRegression.scala @@ -164,6 +164,8 @@ class RidgeRegression private (var lambdaLow: Double, var lambdaHigh: Double) /** * Top-level methods for calling Ridge Regression. + * NOTE(shivaram): We use multiple train methods instead of default arguments to support + * Java programs. */ object RidgeRegression { |