Repository: spark Updated Branches: refs/heads/master 57746295e -> b76e35537
[SPARK-15741][PYSPARK][ML] Pyspark cleanup of set default seed to None ## What changes were proposed in this pull request? Several places set the seed Param default value to None which will translate to a zero value on the Scala side. This is unnecessary because a default fixed value already exists and if a test depends on a zero valued seed, then it should explicitly set it to zero instead of relying on this translation. These cases can be safely removed except for the ALS doc test, which has been changed to set the seed value to zero. ## How was this patch tested? Ran PySpark tests locally Author: Bryan Cutler <cutl...@gmail.com> Closes #13672 from BryanCutler/pyspark-cleanup-setDefault-seed-SPARK-15741. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/b76e3553 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/b76e3553 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/b76e3553 Branch: refs/heads/master Commit: b76e3553760b3c68bebc2c71b0851598718e6f87 Parents: 5774629 Author: Bryan Cutler <cutl...@gmail.com> Authored: Tue Jun 21 11:43:25 2016 -0700 Committer: Xiangrui Meng <m...@databricks.com> Committed: Tue Jun 21 11:43:25 2016 -0700 ---------------------------------------------------------------------- python/pyspark/ml/classification.py | 4 ++-- python/pyspark/ml/feature.py | 2 +- python/pyspark/ml/recommendation.py | 4 ++-- python/pyspark/ml/regression.py | 4 ++-- 4 files changed, 7 insertions(+), 7 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/b76e3553/python/pyspark/ml/classification.py ---------------------------------------------------------------------- diff --git a/python/pyspark/ml/classification.py b/python/pyspark/ml/classification.py index a3cd917..e86c27e 100644 --- a/python/pyspark/ml/classification.py +++ b/python/pyspark/ml/classification.py @@ -685,7 +685,7 @@ class RandomForestClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred self._java_obj = self._new_java_obj( "org.apache.spark.ml.classification.RandomForestClassifier", self.uid) self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, - maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=None, + maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini", numTrees=20, featureSubsetStrategy="auto") kwargs = self.__init__._input_kwargs self.setParams(**kwargs) @@ -825,7 +825,7 @@ class GBTClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol "org.apache.spark.ml.classification.GBTClassifier", self.uid) self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, - lossType="logistic", maxIter=20, stepSize=0.1, seed=None) + lossType="logistic", maxIter=20, stepSize=0.1) kwargs = self.__init__._input_kwargs self.setParams(**kwargs) http://git-wip-us.apache.org/repos/asf/spark/blob/b76e3553/python/pyspark/ml/feature.py ---------------------------------------------------------------------- diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py index 1e9ec0f..bbbb94f 100755 --- a/python/pyspark/ml/feature.py +++ b/python/pyspark/ml/feature.py @@ -2260,7 +2260,7 @@ class Word2Vec(JavaEstimator, HasStepSize, HasMaxIter, HasSeed, HasInputCol, Has super(Word2Vec, self).__init__() self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.Word2Vec", self.uid) self._setDefault(vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1, - seed=None, windowSize=5, maxSentenceLength=1000) + windowSize=5, maxSentenceLength=1000) kwargs = self.__init__._input_kwargs self.setParams(**kwargs) http://git-wip-us.apache.org/repos/asf/spark/blob/b76e3553/python/pyspark/ml/recommendation.py ---------------------------------------------------------------------- diff --git a/python/pyspark/ml/recommendation.py b/python/pyspark/ml/recommendation.py index 0a70967..e28d38b 100644 --- a/python/pyspark/ml/recommendation.py +++ b/python/pyspark/ml/recommendation.py @@ -68,7 +68,7 @@ class ALS(JavaEstimator, HasCheckpointInterval, HasMaxIter, HasPredictionCol, Ha >>> df = spark.createDataFrame( ... [(0, 0, 4.0), (0, 1, 2.0), (1, 1, 3.0), (1, 2, 4.0), (2, 1, 1.0), (2, 2, 5.0)], ... ["user", "item", "rating"]) - >>> als = ALS(rank=10, maxIter=5) + >>> als = ALS(rank=10, maxIter=5, seed=0) >>> model = als.fit(df) >>> model.rank 10 @@ -142,7 +142,7 @@ class ALS(JavaEstimator, HasCheckpointInterval, HasMaxIter, HasPredictionCol, Ha super(ALS, self).__init__() self._java_obj = self._new_java_obj("org.apache.spark.ml.recommendation.ALS", self.uid) self._setDefault(rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10, - implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=None, + implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", ratingCol="rating", nonnegative=False, checkpointInterval=10, intermediateStorageLevel="MEMORY_AND_DISK", finalStorageLevel="MEMORY_AND_DISK") http://git-wip-us.apache.org/repos/asf/spark/blob/b76e3553/python/pyspark/ml/regression.py ---------------------------------------------------------------------- diff --git a/python/pyspark/ml/regression.py b/python/pyspark/ml/regression.py index 8d2378d..29efd6a 100644 --- a/python/pyspark/ml/regression.py +++ b/python/pyspark/ml/regression.py @@ -894,7 +894,7 @@ class RandomForestRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi "org.apache.spark.ml.regression.RandomForestRegressor", self.uid) self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, - impurity="variance", subsamplingRate=1.0, seed=None, numTrees=20, + impurity="variance", subsamplingRate=1.0, numTrees=20, featureSubsetStrategy="auto") kwargs = self.__init__._input_kwargs self.setParams(**kwargs) @@ -1023,7 +1023,7 @@ class GBTRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol, self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, maxMemoryInMB=256, cacheNodeIds=False, subsamplingRate=1.0, checkpointInterval=10, lossType="squared", maxIter=20, stepSize=0.1, - seed=None, impurity="variance") + impurity="variance") kwargs = self.__init__._input_kwargs self.setParams(**kwargs) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
