diff --git a/mllib/src/main/scala/spark/mllib/regression/LogisticRegression.scala b/mllib/src/main/scala/spark/mllib/regression/LogisticRegression.scala index 448ab9dce9017c298c78f014e2c3475563407e5d..e4db7bb9b736fad3287436cecce1403299659e3e 100644 --- a/mllib/src/main/scala/spark/mllib/regression/LogisticRegression.scala +++ b/mllib/src/main/scala/spark/mllib/regression/LogisticRegression.scala @@ -150,7 +150,7 @@ object LogisticRegression { System.exit(1) } val sc = new SparkContext(args(0), "LogisticRegression") - val data = MLUtils.loadData(sc, args(1)) + val data = MLUtils.loadLabeledData(sc, args(1)) val model = LogisticRegression.train(data, args(3).toInt, args(2).toDouble) sc.stop() diff --git a/mllib/src/main/scala/spark/mllib/regression/LogisticRegressionGenerator.scala b/mllib/src/main/scala/spark/mllib/regression/LogisticRegressionGenerator.scala index 9f6abab70b99e8cea51c865f282bed5adf48109c..6e7c023bac79bcaeddef7b7c06afe72901605065 100644 --- a/mllib/src/main/scala/spark/mllib/regression/LogisticRegressionGenerator.scala +++ b/mllib/src/main/scala/spark/mllib/regression/LogisticRegressionGenerator.scala @@ -35,7 +35,7 @@ object LogisticRegressionGenerator { (y, x) } - MLUtils.saveData(data, outputPath) + MLUtils.saveLabeledData(data, outputPath) sc.stop() } } diff --git a/mllib/src/main/scala/spark/mllib/regression/RidgeRegression.scala b/mllib/src/main/scala/spark/mllib/regression/RidgeRegression.scala index f66025bc0bb97f521a79009df4fba9f0734b9ab1..5f813df402afa4f4a8fe9ec265d52382c0136f7c 100644 --- a/mllib/src/main/scala/spark/mllib/regression/RidgeRegression.scala +++ b/mllib/src/main/scala/spark/mllib/regression/RidgeRegression.scala @@ -187,7 +187,7 @@ object RidgeRegression { System.exit(1) } val sc = new SparkContext(args(0), "RidgeRegression") - val data = MLUtils.loadData(sc, args(1)) + val data = MLUtils.loadLabeledData(sc, args(1)) val model = RidgeRegression.train(data, 0, 1000) sc.stop() } diff --git a/mllib/src/main/scala/spark/mllib/regression/RidgeRegressionGenerator.scala b/mllib/src/main/scala/spark/mllib/regression/RidgeRegressionGenerator.scala index c9ac4a8b07c733881aefc1a2a0d2b023d05e0fcb..b83f505d8e41a5896b64566f1a7f50c2f448f574 100644 --- a/mllib/src/main/scala/spark/mllib/regression/RidgeRegressionGenerator.scala +++ b/mllib/src/main/scala/spark/mllib/regression/RidgeRegressionGenerator.scala @@ -49,7 +49,7 @@ object RidgeRegressionGenerator { } } - MLUtils.saveData(data, outputPath) + MLUtils.saveLabeledData(data, outputPath) sc.stop() } } diff --git a/mllib/src/main/scala/spark/mllib/util/MLUtils.scala b/mllib/src/main/scala/spark/mllib/util/MLUtils.scala index 0a4a037c7139aa6bc03e398e4b2e562a687d5d42..08a031dded1783ff260f0c78aeafc7da96df8072 100644 --- a/mllib/src/main/scala/spark/mllib/util/MLUtils.scala +++ b/mllib/src/main/scala/spark/mllib/util/MLUtils.scala @@ -19,7 +19,7 @@ object MLUtils { * @return An RDD of tuples. For each tuple, the first element is the label, and the second * element represents the feature values (an array of Double). */ - def loadData(sc: SparkContext, dir: String): RDD[(Double, Array[Double])] = { + def loadLabeledData(sc: SparkContext, dir: String): RDD[(Double, Array[Double])] = { sc.textFile(dir).map { line => val parts = line.split(",") val label = parts(0).toDouble @@ -28,7 +28,7 @@ object MLUtils { } } - def saveData(data: RDD[(Double, Array[Double])], dir: String) { + def saveLabeledData(data: RDD[(Double, Array[Double])], dir: String) { val dataStr = data.map(x => x._1 + "," + x._2.mkString(" ")) dataStr.saveAsTextFile(dir) }