[SPARK-6893][ML] default pipeline parameter handling in python

Same as #5431 but for Python. jkbradley

Author: Xiangrui Meng <meng@databricks.com>

Closes #5534 from mengxr/SPARK-6893 and squashes the following commits:

d3b519b [Xiangrui Meng] address comments
ebaccc6 [Xiangrui Meng] style update
fce244e [Xiangrui Meng] update explainParams with test
4d6b07a [Xiangrui Meng] add tests
5294500 [Xiangrui Meng] update default param handling in python

1 files changed, 10 insertions, 9 deletions

diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py
index 1cfcd019df..263fe2a5bc 100644
--- a/python/pyspark/ml/feature.py
+++ b/python/pyspark/ml/feature.py
@@ -52,22 +52,22 @@ class Tokenizer(JavaTransformer, HasInputCol, HasOutputCol):
     _java_class = "org.apache.spark.ml.feature.Tokenizer"
 
     @keyword_only
-    def __init__(self, inputCol="input", outputCol="output"):
+    def __init__(self, inputCol=None, outputCol=None):
         """
-        __init__(self, inputCol="input", outputCol="output")
+        __init__(self, inputCol=None, outputCol=None)
         """
         super(Tokenizer, self).__init__()
         kwargs = self.__init__._input_kwargs
         self.setParams(**kwargs)
 
     @keyword_only
-    def setParams(self, inputCol="input", outputCol="output"):
+    def setParams(self, inputCol=None, outputCol=None):
         """
         setParams(self, inputCol="input", outputCol="output")
         Sets params for this Tokenizer.
         """
         kwargs = self.setParams._input_kwargs
-        return self._set_params(**kwargs)
+        return self._set(**kwargs)
 
 
 @inherit_doc
@@ -91,22 +91,23 @@ class HashingTF(JavaTransformer, HasInputCol, HasOutputCol, HasNumFeatures):
     _java_class = "org.apache.spark.ml.feature.HashingTF"
 
     @keyword_only
-    def __init__(self, numFeatures=1 << 18, inputCol="input", outputCol="output"):
+    def __init__(self, numFeatures=1 << 18, inputCol=None, outputCol=None):
         """
-        __init__(self, numFeatures=1 << 18, inputCol="input", outputCol="output")
+        __init__(self, numFeatures=1 << 18, inputCol=None, outputCol=None)
         """
         super(HashingTF, self).__init__()
+        self._setDefault(numFeatures=1 << 18)
         kwargs = self.__init__._input_kwargs
         self.setParams(**kwargs)
 
     @keyword_only
-    def setParams(self, numFeatures=1 << 18, inputCol="input", outputCol="output"):
+    def setParams(self, numFeatures=1 << 18, inputCol=None, outputCol=None):
         """
-        setParams(self, numFeatures=1 << 18, inputCol="input", outputCol="output")
+        setParams(self, numFeatures=1 << 18, inputCol=None, outputCol=None)
         Sets params for this HashingTF.
         """
         kwargs = self.setParams._input_kwargs
-        return self._set_params(**kwargs)
+        return self._set(**kwargs)
 
 
 if __name__ == "__main__":