diff options
author | wm624@hotmail.com <wm624@hotmail.com> | 2016-05-27 20:59:24 -0500 |
---|---|---|
committer | Sean Owen <sowen@cloudera.com> | 2016-05-27 20:59:24 -0500 |
commit | 5d4dafe8fdea49dcbd6b0e4c23e3791fa30c8911 (patch) | |
tree | 57f130594c229600e6f392c8f1b76012a5bd5ddd /examples/src/main/scala | |
parent | 4a2fb8b87ca4517e0f4a1d7a1a1b3c08c1c1294d (diff) | |
download | spark-5d4dafe8fdea49dcbd6b0e4c23e3791fa30c8911.tar.gz spark-5d4dafe8fdea49dcbd6b0e4c23e3791fa30c8911.tar.bz2 spark-5d4dafe8fdea49dcbd6b0e4c23e3791fa30c8911.zip |
[SPARK-15449][MLLIB][EXAMPLE] Wrong Data Format - Documentation Issue
## What changes were proposed in this pull request?
(Please fill in changes proposed in this fix)
In the MLLib naivebayes example, scala and python example doesn't use libsvm data, but Java does.
I make changes in scala and python example to use the libsvm data as the same as Java example.
## How was this patch tested?
Manual tests
Author: wm624@hotmail.com <wm624@hotmail.com>
Closes #13301 from wangmiao1981/example.
Diffstat (limited to 'examples/src/main/scala')
-rw-r--r-- | examples/src/main/scala/org/apache/spark/examples/mllib/NaiveBayesExample.scala | 14 |
1 files changed, 4 insertions, 10 deletions
diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/NaiveBayesExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/NaiveBayesExample.scala index 0187ad603a..b321d8e127 100644 --- a/examples/src/main/scala/org/apache/spark/examples/mllib/NaiveBayesExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/NaiveBayesExample.scala @@ -21,8 +21,7 @@ package org.apache.spark.examples.mllib import org.apache.spark.{SparkConf, SparkContext} // $example on$ import org.apache.spark.mllib.classification.{NaiveBayes, NaiveBayesModel} -import org.apache.spark.mllib.linalg.Vectors -import org.apache.spark.mllib.regression.LabeledPoint +import org.apache.spark.mllib.util.MLUtils // $example off$ object NaiveBayesExample { @@ -31,16 +30,11 @@ object NaiveBayesExample { val conf = new SparkConf().setAppName("NaiveBayesExample") val sc = new SparkContext(conf) // $example on$ - val data = sc.textFile("data/mllib/sample_naive_bayes_data.txt") - val parsedData = data.map { line => - val parts = line.split(',') - LabeledPoint(parts(0).toDouble, Vectors.dense(parts(1).split(' ').map(_.toDouble))) - } + // Load and parse the data file. + val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") // Split data into training (60%) and test (40%). - val splits = parsedData.randomSplit(Array(0.6, 0.4), seed = 11L) - val training = splits(0) - val test = splits(1) + val Array(training, test) = data.randomSplit(Array(0.6, 0.4)) val model = NaiveBayes.train(training, lambda = 1.0, modelType = "multinomial") |