diff options
Diffstat (limited to 'docs/mllib-linear-methods.md')
-rw-r--r-- | docs/mllib-linear-methods.md | 9 |
1 files changed, 5 insertions, 4 deletions
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 %} |