update docstring seeds to none and some other default seeds from 42

Author: holdenk

python/pyspark/ml/feature.py

@@ -793,7 +793,7 @@ def __init__(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025,
                  seed=None, inputCol=None, outputCol=None):
         """
         __init__(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1,
-                 seed=42, inputCol=None, outputCol=None)
+                 seed=None, inputCol=None, outputCol=None)
         """
         super(Word2Vec, self).__init__()
         self.vectorSize = Param(self, "vectorSize",
@@ -804,7 +804,7 @@ def __init__(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025,
                               "the minimum number of times a token must appear to be included " +
                               "in the word2vec model's vocabulary")
         self._setDefault(vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1,
-                         seed=42)
+                         seed=None)
         kwargs = self.__init__._input_kwargs
         self.setParams(**kwargs)
 

python/pyspark/ml/regression.py

@@ -271,7 +271,7 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
         __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction",
                  maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
                  maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="variance",
-                 numTrees=20, featureSubsetStrategy="auto", seed=42)
+                 numTrees=20, featureSubsetStrategy="auto", seed=None)
         """
         super(RandomForestRegressor, self).__init__()
         #: param for Criterion used for information gain calculation (case-insensitive).
@@ -292,7 +292,7 @@ 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="variance", numTrees=20, featureSubsetStrategy="auto")
         kwargs = self.__init__._input_kwargs
         self.setParams(**kwargs)
@@ -305,7 +305,7 @@ def setParams(self, featuresCol="features", labelCol="label", predictionCol="pre
         """
         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="variance", numTrees=20, featureSubsetStrategy="auto")
         Sets params for linear regression.
         """