diff options
Diffstat (limited to 'docs')
-rw-r--r-- | docs/mllib-clustering.md | 3 | ||||
-rw-r--r-- | docs/mllib-linear-methods.md | 9 | ||||
-rw-r--r-- | docs/mllib-optimization.md | 1 |
3 files changed, 8 insertions, 5 deletions
diff --git a/docs/mllib-clustering.md b/docs/mllib-clustering.md index dfd9cd5728..d10bd63746 100644 --- a/docs/mllib-clustering.md +++ b/docs/mllib-clustering.md @@ -52,7 +52,7 @@ import org.apache.spark.mllib.linalg.Vectors // Load and parse the data val data = sc.textFile("data/mllib/kmeans_data.txt") -val parsedData = data.map(s => Vectors.dense(s.split(' ').map(_.toDouble))) +val parsedData = data.map(s => Vectors.dense(s.split(' ').map(_.toDouble))).cache() // Cluster the data into two classes using KMeans val numClusters = 2 @@ -100,6 +100,7 @@ public class KMeansExample { } } ); + parsedData.cache(); // Cluster the data into two classes using KMeans int numClusters = 2; diff --git a/docs/mllib-linear-methods.md b/docs/mllib-linear-methods.md index 9137f9dc1b..d31bec3e1b 100644 --- a/docs/mllib-linear-methods.md +++ b/docs/mllib-linear-methods.md @@ -396,7 +396,7 @@ val data = sc.textFile("data/mllib/ridge-data/lpsa.data") val parsedData = data.map { line => val parts = line.split(',') LabeledPoint(parts(0).toDouble, Vectors.dense(parts(1).split(' ').map(_.toDouble))) -} +}.cache() // Building the model val numIterations = 100 @@ -455,6 +455,7 @@ public class LinearRegression { } } ); + parsedData.cache(); // Building the model int numIterations = 100; @@ -470,7 +471,7 @@ public class LinearRegression { } } ); - JavaRDD<Object> MSE = new JavaDoubleRDD(valuesAndPreds.map( + double MSE = new JavaDoubleRDD(valuesAndPreds.map( new Function<Tuple2<Double, Double>, Object>() { public Object call(Tuple2<Double, Double> pair) { return Math.pow(pair._1() - pair._2(), 2.0); @@ -553,8 +554,8 @@ but in practice you will likely want to use unlabeled vectors for test data. {% highlight scala %} -val trainingData = ssc.textFileStream('/training/data/dir').map(LabeledPoint.parse) -val testData = ssc.textFileStream('/testing/data/dir').map(LabeledPoint.parse) +val trainingData = ssc.textFileStream("/training/data/dir").map(LabeledPoint.parse).cache() +val testData = ssc.textFileStream("/testing/data/dir").map(LabeledPoint.parse) {% endhighlight %} diff --git a/docs/mllib-optimization.md b/docs/mllib-optimization.md index 26ce5f3c50..45141c235b 100644 --- a/docs/mllib-optimization.md +++ b/docs/mllib-optimization.md @@ -217,6 +217,7 @@ import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics import org.apache.spark.mllib.linalg.Vectors import org.apache.spark.mllib.util.MLUtils import org.apache.spark.mllib.classification.LogisticRegressionModel +import org.apache.spark.mllib.optimization.{LBFGS, LogisticGradient, SquaredL2Updater} val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") val numFeatures = data.take(1)(0).features.size |