diff options
author | Yanbo Liang <ybliang8@gmail.com> | 2015-11-23 11:51:29 -0800 |
---|---|---|
committer | Joseph K. Bradley <joseph@databricks.com> | 2015-11-23 11:51:29 -0800 |
commit | 98d7ec7df4bb115dbd84cb9acd744b6c8abfebd5 (patch) | |
tree | 1c9f2845324f06519e5f42a0559873d2041fae0e /examples | |
parent | 5231cd5acaae69d735ba3209531705cc222f3cfb (diff) | |
download | spark-98d7ec7df4bb115dbd84cb9acd744b6c8abfebd5.tar.gz spark-98d7ec7df4bb115dbd84cb9acd744b6c8abfebd5.tar.bz2 spark-98d7ec7df4bb115dbd84cb9acd744b6c8abfebd5.zip |
[SPARK-11920][ML][DOC] ML LinearRegression should use correct dataset in examples and user guide doc
ML ```LinearRegression``` use ```data/mllib/sample_libsvm_data.txt``` as dataset in examples and user guide doc, but it's actually classification dataset rather than regression dataset. We should use ```data/mllib/sample_linear_regression_data.txt``` instead.
The deeper causes is that ```LinearRegression``` with "normal" solver can not solve this dataset correctly, may be due to the ill condition and unreasonable label. This issue has been reported at [SPARK-11918](https://issues.apache.org/jira/browse/SPARK-11918).
It will confuse users if they run the example code but get exception, so we should make this change which can clearly illustrate the usage of ```LinearRegression``` algorithm.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes #9905 from yanboliang/spark-11920.
Diffstat (limited to 'examples')
3 files changed, 5 insertions, 3 deletions
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaLinearRegressionWithElasticNetExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaLinearRegressionWithElasticNetExample.java index 593f8fb3e9..4ad7676c8d 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaLinearRegressionWithElasticNetExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaLinearRegressionWithElasticNetExample.java @@ -37,7 +37,7 @@ public class JavaLinearRegressionWithElasticNetExample { // $example on$ // Load training data DataFrame training = sqlContext.read().format("libsvm") - .load("data/mllib/sample_libsvm_data.txt"); + .load("data/mllib/sample_linear_regression_data.txt"); LinearRegression lr = new LinearRegression() .setMaxIter(10) diff --git a/examples/src/main/python/ml/linear_regression_with_elastic_net.py b/examples/src/main/python/ml/linear_regression_with_elastic_net.py index b027827633..a4cd40cf26 100644 --- a/examples/src/main/python/ml/linear_regression_with_elastic_net.py +++ b/examples/src/main/python/ml/linear_regression_with_elastic_net.py @@ -29,7 +29,8 @@ if __name__ == "__main__": # $example on$ # Load training data - training = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") + training = sqlContext.read.format("libsvm")\ + .load("data/mllib/sample_linear_regression_data.txt") lr = LinearRegression(maxIter=10, regParam=0.3, elasticNetParam=0.8) diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionWithElasticNetExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionWithElasticNetExample.scala index 5a51ece6f9..22c824cea8 100644 --- a/examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionWithElasticNetExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/ml/LinearRegressionWithElasticNetExample.scala @@ -33,7 +33,8 @@ object LinearRegressionWithElasticNetExample { // $example on$ // Load training data - val training = sqlCtx.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") + val training = sqlCtx.read.format("libsvm") + .load("data/mllib/sample_linear_regression_data.txt") val lr = new LinearRegression() .setMaxIter(10) |