Fix a bunch of seeds with default values to have None as the default which will then result in using the hash of the class name

Author: holdenk

python/pyspark/ml/classification.py

@@ -319,12 +319,12 @@ class RandomForestClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred
     def __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction",
                  maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
                  maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini",
-                 numTrees=20, featureSubsetStrategy="auto", seed=42):
+                 numTrees=20, featureSubsetStrategy="auto", seed=None):
         """
         __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
                  maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
                  maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini", \
-                 numTrees=20, featureSubsetStrategy="auto", seed=42)
+                 numTrees=20, featureSubsetStrategy="auto", seed=None)
         """
         super(RandomForestClassifier, self).__init__()
         self._java_obj = self._new_java_obj(
@@ -347,20 +347,20 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
                   "The number of features to consider for splits at each tree node. Supported " +
                   "options: " + ", ".join(RandomForestParams.supportedFeatureSubsetStrategies))
         self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
-                         maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=42,
+                         maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=None,
                          impurity="gini", numTrees=20, featureSubsetStrategy="auto")
         kwargs = self.__init__._input_kwargs
         self.setParams(**kwargs)
 
     @keyword_only
     def setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction",
                   maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
-                  maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=42,
+                  maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=None,
                   impurity="gini", numTrees=20, featureSubsetStrategy="auto"):
         """
         setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
                   maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
-                  maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=42, \
+                  maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=None, \
                   impurity="gini", numTrees=20, featureSubsetStrategy="auto")
         Sets params for linear classification.
         """

python/pyspark/ml/recommendation.py

@@ -89,11 +89,11 @@ class ALS(JavaEstimator, HasCheckpointInterval, HasMaxIter, HasPredictionCol, Ha
 
     @keyword_only
     def __init__(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10,
-                 implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=0,
+                 implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=None,
                  ratingCol="rating", nonnegative=False, checkpointInterval=10):
         """
         __init__(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10, \
-                 implicitPrefs=false, alpha=1.0, userCol="user", itemCol="item", seed=0, \
+                 implicitPrefs=false, alpha=1.0, userCol="user", itemCol="item", seed=None, \
                  ratingCol="rating", nonnegative=false, checkpointInterval=10)
         """
         super(ALS, self).__init__()
@@ -109,18 +109,18 @@ def __init__(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemB
         self.nonnegative = Param(self, "nonnegative",
                                  "whether to use nonnegative constraint for least squares")
         self._setDefault(rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10,
-                         implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=0,
+                         implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=None,
                          ratingCol="rating", nonnegative=False, checkpointInterval=10)
         kwargs = self.__init__._input_kwargs
         self.setParams(**kwargs)
 
     @keyword_only
     def setParams(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10,
-                  implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=0,
+                  implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=None,
                   ratingCol="rating", nonnegative=False, checkpointInterval=10):
         """
         setParams(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10, \
-                 implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=0, \
+                 implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=None, \
                  ratingCol="rating", nonnegative=False, checkpointInterval=10)
         Sets params for ALS.
         """