diff options
author | Xiangrui Meng <meng@databricks.com> | 2014-08-15 21:04:29 -0700 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2014-08-15 21:04:29 -0700 |
commit | 5d25c0b74f6397d78164b96afb8b8cbb1b15cfbd (patch) | |
tree | d2fb3a33cee986c5d7d7c54c88fdbe4d53d98c92 /mllib/src/main | |
parent | cc3648774e9a744850107bb187f2828d447e0a48 (diff) | |
download | spark-5d25c0b74f6397d78164b96afb8b8cbb1b15cfbd.tar.gz spark-5d25c0b74f6397d78164b96afb8b8cbb1b15cfbd.tar.bz2 spark-5d25c0b74f6397d78164b96afb8b8cbb1b15cfbd.zip |
[SPARK-3078][MLLIB] Make LRWithLBFGS API consistent with others
Should ask users to set parameters through the optimizer. dbtsai
Author: Xiangrui Meng <meng@databricks.com>
Closes #1973 from mengxr/lr-lbfgs and squashes the following commits:
e3efbb1 [Xiangrui Meng] fix tests
21b3579 [Xiangrui Meng] fix method name
641eea4 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into lr-lbfgs
456ab7c [Xiangrui Meng] update LRWithLBFGS
Diffstat (limited to 'mllib/src/main')
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala | 40 | ||||
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/mllib/optimization/LBFGS.scala | 9 |
2 files changed, 14 insertions, 35 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala index 6790c86f65..486bdbfa9c 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala @@ -73,6 +73,8 @@ class LogisticRegressionModel ( /** * Train a classification model for Logistic Regression using Stochastic Gradient Descent. * NOTE: Labels used in Logistic Regression should be {0, 1} + * + * Using [[LogisticRegressionWithLBFGS]] is recommended over this. */ class LogisticRegressionWithSGD private ( private var stepSize: Double, @@ -191,51 +193,19 @@ object LogisticRegressionWithSGD { /** * Train a classification model for Logistic Regression using Limited-memory BFGS. + * Standard feature scaling and L2 regularization are used by default. * NOTE: Labels used in Logistic Regression should be {0, 1} */ -class LogisticRegressionWithLBFGS private ( - private var convergenceTol: Double, - private var maxNumIterations: Int, - private var regParam: Double) +class LogisticRegressionWithLBFGS extends GeneralizedLinearAlgorithm[LogisticRegressionModel] with Serializable { - /** - * Construct a LogisticRegression object with default parameters - */ - def this() = this(1E-4, 100, 0.0) - this.setFeatureScaling(true) - private val gradient = new LogisticGradient() - private val updater = new SimpleUpdater() - // Have to return new LBFGS object every time since users can reset the parameters anytime. - override def optimizer = new LBFGS(gradient, updater) - .setNumCorrections(10) - .setConvergenceTol(convergenceTol) - .setMaxNumIterations(maxNumIterations) - .setRegParam(regParam) + override val optimizer = new LBFGS(new LogisticGradient, new SquaredL2Updater) override protected val validators = List(DataValidators.binaryLabelValidator) - /** - * Set the convergence tolerance of iterations for L-BFGS. Default 1E-4. - * Smaller value will lead to higher accuracy with the cost of more iterations. - */ - def setConvergenceTol(convergenceTol: Double): this.type = { - this.convergenceTol = convergenceTol - this - } - - /** - * Set the maximal number of iterations for L-BFGS. Default 100. - */ - def setNumIterations(numIterations: Int): this.type = { - this.maxNumIterations = numIterations - this - } - override protected def createModel(weights: Vector, intercept: Double) = { new LogisticRegressionModel(weights, intercept) } - } diff --git a/mllib/src/main/scala/org/apache/spark/mllib/optimization/LBFGS.scala b/mllib/src/main/scala/org/apache/spark/mllib/optimization/LBFGS.scala index 033fe44f34..d16d0daf08 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/optimization/LBFGS.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/optimization/LBFGS.scala @@ -69,8 +69,17 @@ class LBFGS(private var gradient: Gradient, private var updater: Updater) /** * Set the maximal number of iterations for L-BFGS. Default 100. + * @deprecated use [[LBFGS#setNumIterations]] instead */ + @deprecated("use setNumIterations instead", "1.1.0") def setMaxNumIterations(iters: Int): this.type = { + this.setNumIterations(iters) + } + + /** + * Set the maximal number of iterations for L-BFGS. Default 100. + */ + def setNumIterations(iters: Int): this.type = { this.maxNumIterations = iters this } |