diff options
Diffstat (limited to 'python/pyspark/ml/regression.py')
| -rw-r--r-- | python/pyspark/ml/regression.py | 13 |
1 files changed, 7 insertions, 6 deletions
diff --git a/python/pyspark/ml/regression.py b/python/pyspark/ml/regression.py index ff809cdafd..b139e27372 100644 --- a/python/pyspark/ml/regression.py +++ b/python/pyspark/ml/regression.py @@ -257,7 +257,7 @@ class RandomForestRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi >>> df = sqlContext.createDataFrame([ ... (1.0, Vectors.dense(1.0)), ... (0.0, Vectors.sparse(1, [], []))], ["label", "features"]) - >>> rf = RandomForestRegressor(numTrees=2, maxDepth=2) + >>> rf = RandomForestRegressor(numTrees=2, maxDepth=2, seed=42) >>> model = rf.fit(df) >>> test0 = sqlContext.createDataFrame([(Vectors.dense(-1.0),)], ["features"]) >>> model.transform(test0).head().prediction @@ -284,12 +284,13 @@ class RandomForestRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi 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="variance", - 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="variance", numTrees=20, featureSubsetStrategy="auto", seed=42) + impurity="variance", numTrees=20, \ + featureSubsetStrategy="auto", seed=None) """ super(RandomForestRegressor, self).__init__() self._java_obj = self._new_java_obj( @@ -312,7 +313,7 @@ class RandomForestRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi "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) @@ -320,12 +321,12 @@ class RandomForestRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi @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="variance", 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="variance", numTrees=20, featureSubsetStrategy="auto") Sets params for linear regression. """ |