diff options
| author | Holden Karau <holden@us.ibm.com> | 2016-01-26 15:53:48 -0800 |
|---|---|---|
| committer | Joseph K. Bradley <joseph@databricks.com> | 2016-01-26 15:53:48 -0800 |
| commit | eb917291ca1a2d68ca0639cb4b1464a546603eba (patch) | |
| tree | 380dcaa33273baa68beaf089387bd498d5ee88e8 /python/pyspark/ml/clustering.py | |
| parent | 19fdb21afbf0eae4483cf6d4ef32daffd1994b89 (diff) | |
| download | spark-eb917291ca1a2d68ca0639cb4b1464a546603eba.tar.gz spark-eb917291ca1a2d68ca0639cb4b1464a546603eba.tar.bz2 spark-eb917291ca1a2d68ca0639cb4b1464a546603eba.zip | |
[SPARK-10509][PYSPARK] Reduce excessive param boiler plate code
The current python ml params require cut-and-pasting the param setup and description between the class & ```__init__``` methods. Remove this possible case of errors & simplify use of custom params by adding a ```_copy_new_parent``` method to param so as to avoid cut and pasting (and cut and pasting at different indentation levels urgh).
Author: Holden Karau <holden@us.ibm.com>
Closes #10216 from holdenk/SPARK-10509-excessive-param-boiler-plate-code.
Diffstat (limited to 'python/pyspark/ml/clustering.py')
| -rw-r--r-- | python/pyspark/ml/clustering.py | 7 |
1 files changed, 0 insertions, 7 deletions
diff --git a/python/pyspark/ml/clustering.py b/python/pyspark/ml/clustering.py index 9189c02220..60d1c9aaec 100644 --- a/python/pyspark/ml/clustering.py +++ b/python/pyspark/ml/clustering.py @@ -73,7 +73,6 @@ class KMeans(JavaEstimator, HasFeaturesCol, HasPredictionCol, HasMaxIter, HasTol .. versionadded:: 1.5.0 """ - # a placeholder to make it appear in the generated doc k = Param(Params._dummy(), "k", "number of clusters to create") initMode = Param(Params._dummy(), "initMode", "the initialization algorithm. This can be either \"random\" to " + @@ -90,12 +89,6 @@ class KMeans(JavaEstimator, HasFeaturesCol, HasPredictionCol, HasMaxIter, HasTol """ super(KMeans, self).__init__() self._java_obj = self._new_java_obj("org.apache.spark.ml.clustering.KMeans", self.uid) - self.k = Param(self, "k", "number of clusters to create") - self.initMode = Param(self, "initMode", - "the initialization algorithm. This can be either \"random\" to " + - "choose random points as initial cluster centers, or \"k-means||\" " + - "to use a parallel variant of k-means++") - self.initSteps = Param(self, "initSteps", "steps for k-means initialization mode") self._setDefault(k=2, initMode="k-means||", initSteps=5, tol=1e-4, maxIter=20) kwargs = self.__init__._input_kwargs self.setParams(**kwargs) |