diff options
3 files changed, 6 insertions, 6 deletions
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 ef1ec103a8..54738813d0 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); 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 fab21f003b..b4f06bf888 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() 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 6772efd2c5..1324b066c3 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. |