Repository: spark Updated Branches: refs/heads/branch-1.4 e45cd9f73 -> 58534b0ab
[SPARK-7568] [ML] ml.LogisticRegression doesn't output the right prediction The difference is because we previously don't fit the intercept in Spark 1.3. Here, we change the input `String` so that the probability of instance 6 can be classified as `1.0` without any ambiguity. with lambda = 0.001 in current LOR implementation, the prediction is ``` (4, spark i j k) --> prob=[0.1596407738787411,0.8403592261212589], prediction=1.0 (5, l m n) --> prob=[0.8378325685476612,0.16216743145233883], prediction=0.0 (6, spark hadoop spark) --> prob=[0.0692663313297627,0.9307336686702373], prediction=1.0 (7, apache hadoop) --> prob=[0.9821575333444208,0.01784246665557917], prediction=0.0 ``` and the training accuracy is ``` (0, a b c d e spark) --> prob=[0.0021342419881406746,0.9978657580118594], prediction=1.0 (1, b d) --> prob=[0.9959176174854043,0.004082382514595685], prediction=0.0 (2, spark f g h) --> prob=[0.0014541569986711233,0.9985458430013289], prediction=1.0 (3, hadoop mapreduce) --> prob=[0.9982978367343561,0.0017021632656438518], prediction=0.0 ``` Author: DB Tsai <d...@netflix.com> Closes #6109 from dbtsai/lor-example and squashes the following commits: ac63ce4 [DB Tsai] first commit (cherry picked from commit c1080b6fddb22d84694da2453e46a03fbc041576) Signed-off-by: Xiangrui Meng <m...@databricks.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/58534b0a Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/58534b0a Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/58534b0a Branch: refs/heads/branch-1.4 Commit: 58534b0ab3f3e5af2d2ac302e2f60b92548918ec Parents: e45cd9f Author: DB Tsai <d...@netflix.com> Authored: Thu May 14 01:26:08 2015 -0700 Committer: Xiangrui Meng <m...@databricks.com> Committed: Thu May 14 01:26:17 2015 -0700 ---------------------------------------------------------------------- .../spark/examples/ml/JavaSimpleTextClassificationPipeline.java | 4 ++-- .../src/main/python/ml/simple_text_classification_pipeline.py | 4 ++-- .../spark/examples/ml/SimpleTextClassificationPipeline.scala | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/58534b0a/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleTextClassificationPipeline.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleTextClassificationPipeline.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleTextClassificationPipeline.java index ef1ec10..5473881 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleTextClassificationPipeline.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleTextClassificationPipeline.java @@ -66,7 +66,7 @@ public class JavaSimpleTextClassificationPipeline { .setOutputCol("features"); LogisticRegression lr = new LogisticRegression() .setMaxIter(10) - .setRegParam(0.01); + .setRegParam(0.001); Pipeline pipeline = new Pipeline() .setStages(new PipelineStage[] {tokenizer, hashingTF, lr}); @@ -77,7 +77,7 @@ public class JavaSimpleTextClassificationPipeline { List<Document> localTest = Lists.newArrayList( new Document(4L, "spark i j k"), new Document(5L, "l m n"), - new Document(6L, "mapreduce spark"), + new Document(6L, "spark hadoop spark"), new Document(7L, "apache hadoop")); DataFrame test = jsql.createDataFrame(jsc.parallelize(localTest), Document.class); http://git-wip-us.apache.org/repos/asf/spark/blob/58534b0a/examples/src/main/python/ml/simple_text_classification_pipeline.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/simple_text_classification_pipeline.py b/examples/src/main/python/ml/simple_text_classification_pipeline.py index fab21f0..b4f06bf 100644 --- a/examples/src/main/python/ml/simple_text_classification_pipeline.py +++ b/examples/src/main/python/ml/simple_text_classification_pipeline.py @@ -48,7 +48,7 @@ if __name__ == "__main__": # Configure an ML pipeline, which consists of tree stages: tokenizer, hashingTF, and lr. tokenizer = Tokenizer(inputCol="text", outputCol="words") hashingTF = HashingTF(inputCol=tokenizer.getOutputCol(), outputCol="features") - lr = LogisticRegression(maxIter=10, regParam=0.01) + lr = LogisticRegression(maxIter=10, regParam=0.001) pipeline = Pipeline(stages=[tokenizer, hashingTF, lr]) # Fit the pipeline to training documents. @@ -58,7 +58,7 @@ if __name__ == "__main__": Document = Row("id", "text") test = sc.parallelize([(4, "spark i j k"), (5, "l m n"), - (6, "mapreduce spark"), + (6, "spark hadoop spark"), (7, "apache hadoop")]) \ .map(lambda x: Document(*x)).toDF() http://git-wip-us.apache.org/repos/asf/spark/blob/58534b0a/examples/src/main/scala/org/apache/spark/examples/ml/SimpleTextClassificationPipeline.scala ---------------------------------------------------------------------- diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/SimpleTextClassificationPipeline.scala b/examples/src/main/scala/org/apache/spark/examples/ml/SimpleTextClassificationPipeline.scala index 6772efd..1324b06 100644 --- a/examples/src/main/scala/org/apache/spark/examples/ml/SimpleTextClassificationPipeline.scala +++ b/examples/src/main/scala/org/apache/spark/examples/ml/SimpleTextClassificationPipeline.scala @@ -64,7 +64,7 @@ object SimpleTextClassificationPipeline { .setOutputCol("features") val lr = new LogisticRegression() .setMaxIter(10) - .setRegParam(0.01) + .setRegParam(0.001) val pipeline = new Pipeline() .setStages(Array(tokenizer, hashingTF, lr)) @@ -75,7 +75,7 @@ object SimpleTextClassificationPipeline { val test = sc.parallelize(Seq( Document(4L, "spark i j k"), Document(5L, "l m n"), - Document(6L, "mapreduce spark"), + Document(6L, "spark hadoop spark"), Document(7L, "apache hadoop"))) // Make predictions on test documents. --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
