diff options
Diffstat (limited to 'python/pyspark/ml/param/_shared_params_code_gen.py')
| -rw-r--r-- | python/pyspark/ml/param/_shared_params_code_gen.py | 6 |
1 files changed, 4 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 070c5db01a..0528dc1e3a 100644 --- a/python/pyspark/ml/param/_shared_params_code_gen.py +++ b/python/pyspark/ml/param/_shared_params_code_gen.py @@ -118,7 +118,8 @@ if __name__ == "__main__": ("inputCols", "input column names.", None), ("outputCol", "output column name.", "self.uid + '__output'"), ("numFeatures", "number of features.", None), - ("checkpointInterval", "checkpoint interval (>= 1).", None), + ("checkpointInterval", "set checkpoint interval (>= 1) or disable checkpoint (-1). " + + "E.g. 10 means that the cache will get checkpointed every 10 iterations.", None), ("seed", "random seed.", "hash(type(self).__name__)"), ("tol", "the convergence tolerance for iterative algorithms.", None), ("stepSize", "Step size to be used for each iteration of optimization.", None), @@ -157,7 +158,8 @@ if __name__ == "__main__": ("maxMemoryInMB", "Maximum memory in MB allocated to histogram aggregation."), ("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.")] + "Caching can speed up training of deeper trees. Users can set how often should the " + + "cache be checkpointed or disable it by setting checkpointInterval.")] decisionTreeCode = '''class DecisionTreeParams(Params): """ |