diff options
Diffstat (limited to 'python/pyspark/ml/param')
-rw-r--r-- | python/pyspark/ml/param/_shared_params_code_gen.py | 3 | ||||
-rw-r--r-- | python/pyspark/ml/param/shared.py | 2 |
2 files changed, 3 insertions, 2 deletions
diff --git a/python/pyspark/ml/param/_shared_params_code_gen.py b/python/pyspark/ml/param/_shared_params_code_gen.py index 7dd2937db7..715fa9e9f8 100644 --- a/python/pyspark/ml/param/_shared_params_code_gen.py +++ b/python/pyspark/ml/param/_shared_params_code_gen.py @@ -164,7 +164,8 @@ if __name__ == "__main__": "split will be discarded as invalid. Should be >= 1.", "TypeConverters.toInt"), ("minInfoGain", "Minimum information gain for a split to be considered at a tree node.", "TypeConverters.toFloat"), - ("maxMemoryInMB", "Maximum memory in MB allocated to histogram aggregation.", + ("maxMemoryInMB", "Maximum memory in MB allocated to histogram aggregation. If too small," + + " then 1 node will be split per iteration, and its aggregates may exceed this size.", "TypeConverters.toInt"), ("cacheNodeIds", "If false, the algorithm will pass trees to executors to match " + "instances with nodes. If true, the algorithm will cache node IDs for each instance. " + diff --git a/python/pyspark/ml/param/shared.py b/python/pyspark/ml/param/shared.py index 83fbd59039..d79d55e463 100644 --- a/python/pyspark/ml/param/shared.py +++ b/python/pyspark/ml/param/shared.py @@ -568,7 +568,7 @@ class DecisionTreeParams(Params): maxBins = Param(Params._dummy(), "maxBins", "Max number of bins for discretizing continuous features. Must be >=2 and >= number of categories for any categorical feature.", typeConverter=TypeConverters.toInt) minInstancesPerNode = Param(Params._dummy(), "minInstancesPerNode", "Minimum number of instances each child must have after split. If a split causes the left or right child to have fewer than minInstancesPerNode, the split will be discarded as invalid. Should be >= 1.", typeConverter=TypeConverters.toInt) minInfoGain = Param(Params._dummy(), "minInfoGain", "Minimum information gain for a split to be considered at a tree node.", typeConverter=TypeConverters.toFloat) - maxMemoryInMB = Param(Params._dummy(), "maxMemoryInMB", "Maximum memory in MB allocated to histogram aggregation.", typeConverter=TypeConverters.toInt) + maxMemoryInMB = Param(Params._dummy(), "maxMemoryInMB", "Maximum memory in MB allocated to histogram aggregation. If too small, then 1 node will be split per iteration, and its aggregates may exceed this size.", typeConverter=TypeConverters.toInt) cacheNodeIds = Param(Params._dummy(), "cacheNodeIds", "If false, the algorithm will pass trees to executors to match instances with nodes. If true, the algorithm will cache node IDs for each instance. Caching can speed up training of deeper trees. Users can set how often should the cache be checkpointed or disable it by setting checkpointInterval.", typeConverter=TypeConverters.toBoolean) |