diff options
| author | Xiangrui Meng <meng@databricks.com> | 2015-05-20 17:26:26 -0700 |
|---|---|---|
| committer | Joseph K. Bradley <joseph@databricks.com> | 2015-05-20 17:26:26 -0700 |
| commit | c330e52dae6a3ec7e67ca82e2c2f4ea873976458 (patch) | |
| tree | a6e98424c41b264292f6b8f7b777c7dc8e0547f3 /python | |
| parent | f2faa7af30662e3bdf15780f8719c71108f8e30b (diff) | |
| download | spark-c330e52dae6a3ec7e67ca82e2c2f4ea873976458.tar.gz spark-c330e52dae6a3ec7e67ca82e2c2f4ea873976458.tar.bz2 spark-c330e52dae6a3ec7e67ca82e2c2f4ea873976458.zip | |
[SPARK-7762] [MLLIB] set default value for outputCol
Set a default value for `outputCol` instead of forcing users to name it. This is useful for intermediate transformers in the pipeline. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes #6289 from mengxr/SPARK-7762 and squashes the following commits:
54edebc [Xiangrui Meng] merge master
bff8667 [Xiangrui Meng] update unit test
171246b [Xiangrui Meng] add unit test for outputCol
a4321bd [Xiangrui Meng] set default value for outputCol
Diffstat (limited to 'python')
| -rw-r--r-- | python/pyspark/ml/param/_shared_params_code_gen.py | 2 | ||||
| -rw-r--r-- | python/pyspark/ml/param/shared.py | 3 |
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 ccb929af18..69efc424ec 100644 --- a/python/pyspark/ml/param/_shared_params_code_gen.py +++ b/python/pyspark/ml/param/_shared_params_code_gen.py @@ -116,7 +116,7 @@ if __name__ == "__main__": ("rawPredictionCol", "raw prediction (a.k.a. confidence) column name", "'rawPrediction'"), ("inputCol", "input column name", None), ("inputCols", "input column names", None), - ("outputCol", "output column name", None), + ("outputCol", "output column name", "self.uid + '__output'"), ("numFeatures", "number of features", None), ("checkpointInterval", "checkpoint interval (>= 1)", None), ("seed", "random seed", "hash(type(self).__name__)"), diff --git a/python/pyspark/ml/param/shared.py b/python/pyspark/ml/param/shared.py index 0b93788899..bc088e4c29 100644 --- a/python/pyspark/ml/param/shared.py +++ b/python/pyspark/ml/param/shared.py @@ -280,6 +280,7 @@ class HasOutputCol(Params): super(HasOutputCol, self).__init__() #: param for output column name self.outputCol = Param(self, "outputCol", "output column name") + self._setDefault(outputCol=self.uid + '__output') def setOutputCol(self, value): """ @@ -459,7 +460,7 @@ class DecisionTreeParams(Params): self.maxMemoryInMB = Param(self, "maxMemoryInMB", "Maximum memory in MB allocated to histogram aggregation.") #: param for 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. self.cacheNodeIds = Param(self, "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.") - + def setMaxDepth(self, value): """ Sets the value of :py:attr:`maxDepth`. |