diff options
| author | Sean Owen <srowen@gmail.com> | 2014-07-30 17:34:32 -0700 |
|---|---|---|
| committer | Xiangrui Meng <meng@databricks.com> | 2014-07-30 17:34:32 -0700 |
| commit | e9b275b7697e7ad3b52b157d3274acc17ca8d828 (patch) | |
| tree | c72a43b2a387bf15f6960b99d4c3a42c2dedaead /examples | |
| parent | 88a519db90d66ee5a1455ef4fcc1ad2a687e3d0b (diff) | |
| download | spark-e9b275b7697e7ad3b52b157d3274acc17ca8d828.tar.gz spark-e9b275b7697e7ad3b52b157d3274acc17ca8d828.tar.bz2 spark-e9b275b7697e7ad3b52b157d3274acc17ca8d828.zip | |
SPARK-2341 [MLLIB] loadLibSVMFile doesn't handle regression datasets
Per discussion at https://issues.apache.org/jira/browse/SPARK-2341 , this is a look at deprecating the multiclass parameter. Thoughts welcome of course.
Author: Sean Owen <srowen@gmail.com>
Closes #1663 from srowen/SPARK-2341 and squashes the following commits:
8a3abd7 [Sean Owen] Suppress MIMA error for removed package private classes
18a8c8e [Sean Owen] Updates from review
83d0092 [Sean Owen] Deprecated methods with multiclass, and instead always parse target as a double (ie. multiclass = true)
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/src/main/scala/org/apache/spark/examples/mllib/LinearRegression.scala | 2 | ||||
| -rw-r--r-- | examples/src/main/scala/org/apache/spark/examples/mllib/SparseNaiveBayes.scala | 4 |
2 files changed, 3 insertions, 3 deletions
diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/LinearRegression.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/LinearRegression.scala index 4811bb70e4..05b7d66f8d 100644 --- a/examples/src/main/scala/org/apache/spark/examples/mllib/LinearRegression.scala +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/LinearRegression.scala @@ -91,7 +91,7 @@ object LinearRegression extends App { Logger.getRootLogger.setLevel(Level.WARN) - val examples = MLUtils.loadLibSVMFile(sc, params.input, multiclass = true).cache() + val examples = MLUtils.loadLibSVMFile(sc, params.input).cache() val splits = examples.randomSplit(Array(0.8, 0.2)) val training = splits(0).cache() diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/SparseNaiveBayes.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/SparseNaiveBayes.scala index 537e68a099..88acd9dbb0 100644 --- a/examples/src/main/scala/org/apache/spark/examples/mllib/SparseNaiveBayes.scala +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/SparseNaiveBayes.scala @@ -22,7 +22,7 @@ import scopt.OptionParser import org.apache.spark.{SparkConf, SparkContext} import org.apache.spark.mllib.classification.NaiveBayes -import org.apache.spark.mllib.util.{MLUtils, MulticlassLabelParser} +import org.apache.spark.mllib.util.MLUtils /** * An example naive Bayes app. Run with @@ -76,7 +76,7 @@ object SparseNaiveBayes { if (params.minPartitions > 0) params.minPartitions else sc.defaultMinPartitions val examples = - MLUtils.loadLibSVMFile(sc, params.input, multiclass = true, params.numFeatures, minPartitions) + MLUtils.loadLibSVMFile(sc, params.input, params.numFeatures, minPartitions) // Cache examples because it will be used in both training and evaluation. examples.cache() |