[SPARK-7388] [SPARK-7383] wrapper for VectorAssembler in Python

The wrapper required the implementation of the `ArrayParam`, because `Array[T]` is hard to obtain from Python. `ArrayParam` has an extra function called `wCast` which is an internal function to obtain `Array[T]` from `Seq[T]`

Author: Burak Yavuz <brkyvz@gmail.com>
Author: Xiangrui Meng <meng@databricks.com>

Closes #5930 from brkyvz/ml-feat and squashes the following commits:

73e745f [Burak Yavuz] Merge pull request #3 from mengxr/SPARK-7388
c221db9 [Xiangrui Meng] overload StringArrayParam.w
c81072d [Burak Yavuz] addressed comments
99c2ebf [Burak Yavuz] add to python_shared_params
39ecb07 [Burak Yavuz] fix scalastyle
7f7ea2a [Burak Yavuz] [SPARK-7388][SPARK-7383] wrapper for VectorAssembler in Python

2 files changed, 30 insertions, 0 deletions

diff --git a/python/pyspark/ml/param/_shared_params_code_gen.py b/python/pyspark/ml/param/_shared_params_code_gen.py
index c71c823db2..c1c8e921dd 100644
--- a/python/pyspark/ml/param/_shared_params_code_gen.py
+++ b/python/pyspark/ml/param/_shared_params_code_gen.py
@@ -95,6 +95,7 @@ if __name__ == "__main__":
         ("predictionCol", "prediction column name", "'prediction'"),
         ("rawPredictionCol", "raw prediction column name", "'rawPrediction'"),
         ("inputCol", "input column name", None),
+        ("inputCols", "input column names", None),
         ("outputCol", "output column name", None),
         ("numFeatures", "number of features", None)]
     code = []
diff --git a/python/pyspark/ml/param/shared.py b/python/pyspark/ml/param/shared.py
index 4f243844f8..aaf80f0008 100644
--- a/python/pyspark/ml/param/shared.py
+++ b/python/pyspark/ml/param/shared.py
@@ -223,6 +223,35 @@ class HasInputCol(Params):
         return self.getOrDefault(self.inputCol)
 
 
+class HasInputCols(Params):
+    """
+    Mixin for param inputCols: input column names.
+    """
+
+    # a placeholder to make it appear in the generated doc
+    inputCols = Param(Params._dummy(), "inputCols", "input column names")
+
+    def __init__(self):
+        super(HasInputCols, self).__init__()
+        #: param for input column names
+        self.inputCols = Param(self, "inputCols", "input column names")
+        if None is not None:
+            self._setDefault(inputCols=None)
+
+    def setInputCols(self, value):
+        """
+        Sets the value of :py:attr:`inputCols`.
+        """
+        self.paramMap[self.inputCols] = value
+        return self
+
+    def getInputCols(self):
+        """
+        Gets the value of inputCols or its default value.
+        """
+        return self.getOrDefault(self.inputCols)
+
+
 class HasOutputCol(Params):
     """
     Mixin for param outputCol: output column name.