[SPARK-7427] [PYSPARK] Make sharedParams match in Scala, Python

Modified 2 files:
python/pyspark/ml/param/_shared_params_code_gen.py
python/pyspark/ml/param/shared.py

Generated shared.py on Linux using Python 2.6.6 on Redhat Enterprise Linux Server 6.6.
python _shared_params_code_gen.py > shared.py

Only changed maxIter, regParam, rawPredictionCol based on strings from SharedParamsCodeGen.scala.  Note warning was displayed when committing shared.py:
warning: LF will be replaced by CRLF in python/pyspark/ml/param/shared.py.

Author: Glenn Weidner <gweidner@us.ibm.com>

Closes #6023 from gweidner/br-7427 and squashes the following commits:

db72e32 [Glenn Weidner] [SPARK-7427] [PySpark] Make sharedParams match in Scala, Python
825e4a9 [Glenn Weidner] [SPARK-7427] [PySpark] Make sharedParams match in Scala, Python
e6a865e [Glenn Weidner] [SPARK-7427] [PySpark] Make sharedParams match in Scala, Python
1eee702 [Glenn Weidner] Merge remote-tracking branch 'upstream/master'
1ac10e5 [Glenn Weidner] Merge remote-tracking branch 'upstream/master'
cafd104 [Glenn Weidner] Merge remote-tracking branch 'upstream/master'
9bea1eb [Glenn Weidner] Merge remote-tracking branch 'upstream/master'
4a35c20 [Glenn Weidner] Merge remote-tracking branch 'upstream/master'
9790cbe [Glenn Weidner] Merge remote-tracking branch 'upstream/master'
d9c30f4 [Glenn Weidner] [SPARK-7275] [SQL] [WIP] Make LogicalRelation public

python/pyspark/ml/param/_shared_params_code_gen.py

@@ -88,12 +88,12 @@ if __name__ == "__main__":
     print("\n# DO NOT MODIFY THIS FILE! It was generated by _shared_params_code_gen.py.\n")
     print("from pyspark.ml.param import Param, Params\n\n")
     shared = [
-        ("maxIter", "max number of iterations", None),
-        ("regParam", "regularization constant", None),
+        ("maxIter", "max number of iterations (>= 0)", None),
+        ("regParam", "regularization parameter (>= 0)", None),
         ("featuresCol", "features column name", "'features'"),
         ("labelCol", "label column name", "'label'"),
         ("predictionCol", "prediction column name", "'prediction'"),
-        ("rawPredictionCol", "raw prediction column name", "'rawPrediction'"),
+        ("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),

python/pyspark/ml/param/shared.py

@@ -22,16 +22,16 @@ from pyspark.ml.param import Param, Params
 
 class HasMaxIter(Params):
     """
-    Mixin for param maxIter: max number of iterations.
+    Mixin for param maxIter: max number of iterations (>= 0).
     """
 
     # a placeholder to make it appear in the generated doc
-    maxIter = Param(Params._dummy(), "maxIter", "max number of iterations")
+    maxIter = Param(Params._dummy(), "maxIter", "max number of iterations (>= 0)")
 
     def __init__(self):
         super(HasMaxIter, self).__init__()
-        #: param for max number of iterations
-        self.maxIter = Param(self, "maxIter", "max number of iterations")
+        #: param for max number of iterations (>= 0)
+        self.maxIter = Param(self, "maxIter", "max number of iterations (>= 0)")
         if None is not None:
             self._setDefault(maxIter=None)
 
@@ -51,16 +51,16 @@ class HasMaxIter(Params):
 
 class HasRegParam(Params):
     """
-    Mixin for param regParam: regularization constant.
+    Mixin for param regParam: regularization parameter (>= 0).
     """
 
     # a placeholder to make it appear in the generated doc
-    regParam = Param(Params._dummy(), "regParam", "regularization constant")
+    regParam = Param(Params._dummy(), "regParam", "regularization parameter (>= 0)")
 
     def __init__(self):
         super(HasRegParam, self).__init__()
-        #: param for regularization constant
-        self.regParam = Param(self, "regParam", "regularization constant")
+        #: param for regularization parameter (>= 0)
+        self.regParam = Param(self, "regParam", "regularization parameter (>= 0)")
         if None is not None:
             self._setDefault(regParam=None)
 
@@ -167,16 +167,16 @@ class HasPredictionCol(Params):
 
 class HasRawPredictionCol(Params):
     """
-    Mixin for param rawPredictionCol: raw prediction column name.
+    Mixin for param rawPredictionCol: raw prediction (a.k.a. confidence) column name.
     """
 
     # a placeholder to make it appear in the generated doc
-    rawPredictionCol = Param(Params._dummy(), "rawPredictionCol", "raw prediction column name")
+    rawPredictionCol = Param(Params._dummy(), "rawPredictionCol", "raw prediction (a.k.a. confidence) column name")
 
     def __init__(self):
         super(HasRawPredictionCol, self).__init__()
-        #: param for raw prediction column name
-        self.rawPredictionCol = Param(self, "rawPredictionCol", "raw prediction column name")
+        #: param for raw prediction (a.k.a. confidence) column name
+        self.rawPredictionCol = Param(self, "rawPredictionCol", "raw prediction (a.k.a. confidence) column name")
         if 'rawPrediction' is not None:
             self._setDefault(rawPredictionCol='rawPrediction')
 
@@ -403,14 +403,12 @@ class HasStepSize(Params):
     """
 
     # a placeholder to make it appear in the generated doc
-    stepSize = Param(Params._dummy(), "stepSize",
-                     "Step size to be used for each iteration of optimization.")
+    stepSize = Param(Params._dummy(), "stepSize", "Step size to be used for each iteration of optimization.")
 
     def __init__(self):
         super(HasStepSize, self).__init__()
         #: param for Step size to be used for each iteration of optimization.
-        self.stepSize = Param(self, "stepSize",
-                              "Step size to be used for each iteration of optimization.")
+        self.stepSize = Param(self, "stepSize", "Step size to be used for each iteration of optimization.")
         if None is not None:
             self._setDefault(stepSize=None)
 

python/pyspark/ml/tests.py

@@ -128,7 +128,7 @@ class ParamTests(PySparkTestCase):
         testParams = TestParams()
         maxIter = testParams.maxIter
         self.assertEqual(maxIter.name, "maxIter")
-        self.assertEqual(maxIter.doc, "max number of iterations")
+        self.assertEqual(maxIter.doc, "max number of iterations (>= 0)")
         self.assertTrue(maxIter.parent is testParams)
 
     def test_params(self):
@@ -156,7 +156,7 @@ class ParamTests(PySparkTestCase):
         self.assertEquals(
             testParams.explainParams(),
             "\n".join(["inputCol: input column name (undefined)",
-                       "maxIter: max number of iterations (default: 10, current: 100)"]))
+                       "maxIter: max number of iterations (>= 0) (default: 10, current: 100)"]))
 
 
 if __name__ == "__main__":

tox.ini

@@ -15,4 +15,4 @@
 
 [pep8]
 max-line-length=100
-exclude=cloudpickle.py,heapq3.py
+exclude=cloudpickle.py,heapq3.py,shared.py