From 7a5c4b647bdd12d2a6d6285d0349680f1a848b01 Mon Sep 17 00:00:00 2001 From: Matei Zaharia Date: Sun, 8 Sep 2013 21:47:24 -0700 Subject: Small tweaks to MLlib docs --- docs/mllib-guide.md | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) (limited to 'docs') diff --git a/docs/mllib-guide.md b/docs/mllib-guide.md index 1a629994cc..1583ce4a58 100644 --- a/docs/mllib-guide.md +++ b/docs/mllib-guide.md @@ -4,7 +4,7 @@ title: Machine Learning Library (MLlib) --- MLlib is a Spark implementation of some common machine learning (ML) -functionality, as well associated unit tests and data generators. MLlib +functionality, as well associated tests and data generators. MLlib currently supports four common types of machine learning problem settings, namely, binary classification, regression, clustering and collaborative filtering, as well as an underlying gradient descent optimization primitive. @@ -44,22 +44,20 @@ import org.apache.spark.mllib.regression.LabeledPoint // Load and parse the data file val data = sc.textFile("mllib/data/sample_svm_data.txt") -val parsedData = data.map(line => { +val parsedData = data.map { line => val parts = line.split(' ') LabeledPoint(parts(0).toDouble, parts.tail.map(x => x.toDouble).toArray) -}) +} // Run training algorithm val numIterations = 20 -val model = SVMWithSGD.train( - parsedData, - numIterations) +val model = SVMWithSGD.train(parsedData, numIterations) // Evaluate model on training examples and compute training error -val labelAndPreds = parsedData.map(r => { - val prediction = model.predict(r.features) - (r.label, prediction) -}) +val labelAndPreds = parsedData.map { point => + val prediction = model.predict(point.features) + (point.label, prediction) +} val trainErr = labelAndPreds.filter(r => r._1 != r._2).count.toDouble / parsedData.count println("trainError = " + trainErr) {% endhighlight %} -- cgit v1.2.3