[
https://issues.apache.org/jira/browse/SPARK-16832?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15438789#comment-15438789
]
Apache Spark commented on SPARK-16832:
--------------------------------------
User 'srowen' has created a pull request for this issue:
https://github.com/apache/spark/pull/14826
> CrossValidator and TrainValidationSplit are not random without seed
> -------------------------------------------------------------------
>
> Key: SPARK-16832
> URL: https://issues.apache.org/jira/browse/SPARK-16832
> Project: Spark
> Issue Type: Bug
> Components: ML, PySpark
> Affects Versions: 2.0.0
> Reporter: Max Moroz
> Priority: Minor
>
> Repeatedly running CrossValidator or TrainValidationSplit without an explicit
> seed parameter does not change results. It is supposed to be seeded with a
> random seed, but it seems to be instead seeded with some constant. (If seed
> is explicitly provided, the two classes behave as expected.)
> {code}
> dataset = spark.createDataFrame(
> [(Vectors.dense([0.0]), 0.0),
> (Vectors.dense([0.4]), 1.0),
> (Vectors.dense([0.5]), 0.0),
> (Vectors.dense([0.6]), 1.0),
> (Vectors.dense([1.0]), 1.0)] * 1000,
> ["features", "label"]).cache()
> paramGrid = pyspark.ml.tuning.ParamGridBuilder().build()
> tvs =
> pyspark.ml.tuning.TrainValidationSplit(estimator=pyspark.ml.regression.LinearRegression(),
>
> estimatorParamMaps=paramGrid,
>
> evaluator=pyspark.ml.evaluation.RegressionEvaluator(),
> trainRatio=0.8)
> model = tvs.fit(train)
> print(model.validationMetrics)
> for folds in (3, 5, 10):
> cv =
> pyspark.ml.tuning.CrossValidator(estimator=pyspark.ml.regression.LinearRegression(),
>
> estimatorParamMaps=paramGrid,
>
> evaluator=pyspark.ml.evaluation.RegressionEvaluator(),
> numFolds=folds
> )
> cvModel = cv.fit(dataset)
> print(folds, cvModel.avgMetrics)
> {code}
> This code produces identical results upon repeated calls.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
