Repository: spark Updated Branches: refs/heads/branch-2.0 80a40e8e2 -> 8467e2102
[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: [email protected] <[email protected]> Closes #13301 from wangmiao1981/example. (cherry picked from commit 5d4dafe8fdea49dcbd6b0e4c23e3791fa30c8911) Signed-off-by: Sean Owen <[email protected]> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/8467e210 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/8467e210 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/8467e210 Branch: refs/heads/branch-2.0 Commit: 8467e2102886da1cefb43f2aaa69864375fe91bc Parents: 80a40e8 Author: [email protected] <[email protected]> Authored: Fri May 27 20:59:24 2016 -0500 Committer: Sean Owen <[email protected]> Committed: Fri May 27 20:59:34 2016 -0500 ---------------------------------------------------------------------- data/mllib/sample_naive_bayes_data.txt | 12 ------------ .../spark/examples/mllib/JavaNaiveBayesExample.java | 4 ++-- examples/src/main/python/mllib/naive_bayes_example.py | 13 ++++--------- .../spark/examples/mllib/NaiveBayesExample.scala | 14 ++++---------- 4 files changed, 10 insertions(+), 33 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/8467e210/data/mllib/sample_naive_bayes_data.txt ---------------------------------------------------------------------- diff --git a/data/mllib/sample_naive_bayes_data.txt b/data/mllib/sample_naive_bayes_data.txt deleted file mode 100644 index bd22bea..0000000 --- a/data/mllib/sample_naive_bayes_data.txt +++ /dev/null @@ -1,12 +0,0 @@ -0,1 0 0 -0,2 0 0 -0,3 0 0 -0,4 0 0 -1,0 1 0 -1,0 2 0 -1,0 3 0 -1,0 4 0 -2,0 0 1 -2,0 0 2 -2,0 0 3 -2,0 0 4 \ No newline at end of file http://git-wip-us.apache.org/repos/asf/spark/blob/8467e210/examples/src/main/java/org/apache/spark/examples/mllib/JavaNaiveBayesExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaNaiveBayesExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaNaiveBayesExample.java index 2b17dbb..f4ec04b 100644 --- a/examples/src/main/java/org/apache/spark/examples/mllib/JavaNaiveBayesExample.java +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaNaiveBayesExample.java @@ -36,9 +36,9 @@ public class JavaNaiveBayesExample { SparkConf sparkConf = new SparkConf().setAppName("JavaNaiveBayesExample"); JavaSparkContext jsc = new JavaSparkContext(sparkConf); // $example on$ - String path = "data/mllib/sample_naive_bayes_data.txt"; + String path = "data/mllib/sample_libsvm_data.txt"; JavaRDD<LabeledPoint> inputData = MLUtils.loadLibSVMFile(jsc.sc(), path).toJavaRDD(); - JavaRDD<LabeledPoint>[] tmp = inputData.randomSplit(new double[]{0.6, 0.4}, 12345); + JavaRDD<LabeledPoint>[] tmp = inputData.randomSplit(new double[]{0.6, 0.4}); JavaRDD<LabeledPoint> training = tmp[0]; // training set JavaRDD<LabeledPoint> test = tmp[1]; // test set final NaiveBayesModel model = NaiveBayes.train(training.rdd(), 1.0); http://git-wip-us.apache.org/repos/asf/spark/blob/8467e210/examples/src/main/python/mllib/naive_bayes_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/mllib/naive_bayes_example.py b/examples/src/main/python/mllib/naive_bayes_example.py index 35724f7..749353b 100644 --- a/examples/src/main/python/mllib/naive_bayes_example.py +++ b/examples/src/main/python/mllib/naive_bayes_example.py @@ -29,15 +29,9 @@ import shutil from pyspark import SparkContext # $example on$ from pyspark.mllib.classification import NaiveBayes, NaiveBayesModel -from pyspark.mllib.linalg import Vectors -from pyspark.mllib.regression import LabeledPoint +from pyspark.mllib.util import MLUtils -def parseLine(line): - parts = line.split(',') - label = float(parts[0]) - features = Vectors.dense([float(x) for x in parts[1].split(' ')]) - return LabeledPoint(label, features) # $example off$ if __name__ == "__main__": @@ -45,10 +39,11 @@ if __name__ == "__main__": sc = SparkContext(appName="PythonNaiveBayesExample") # $example on$ - data = sc.textFile('data/mllib/sample_naive_bayes_data.txt').map(parseLine) + # Load and parse the data file. + data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt") # Split data approximately into training (60%) and test (40%) - training, test = data.randomSplit([0.6, 0.4], seed=0) + training, test = data.randomSplit([0.6, 0.4]) # Train a naive Bayes model. model = NaiveBayes.train(training, 1.0) http://git-wip-us.apache.org/repos/asf/spark/blob/8467e210/examples/src/main/scala/org/apache/spark/examples/mllib/NaiveBayesExample.scala ---------------------------------------------------------------------- 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 0187ad6..b321d8e 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") --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
