[SPARK-2461] [PySpark] Add a toString method to GeneralizedLinearModel

Add a toString method to GeneralizedLinearModel, also change `__str__` to `__repr__` for some classes, to provide better message in repr.

This PR is based on #1388, thanks to sryza!

closes #1388

Author: Sandy Ryza <sandy@cloudera.com>
Author: Davies Liu <davies.liu@gmail.com>

Closes #2625 from davies/string and squashes the following commits:

3544aad [Davies Liu] fix LinearModel
0bcd642 [Davies Liu] Merge branch 'sandy-spark-2461' of github.com:sryza/spark
1ce5c2d [Sandy Ryza] __repr__ back to __str__ in a couple places
aa9e962 [Sandy Ryza] Switch __str__ to __repr__
a0c5041 [Sandy Ryza] Add labels back in
1aa17f5 [Sandy Ryza] Match existing conventions
fac1bc4 [Sandy Ryza] Fix PEP8 error
f7b58ed [Sandy Ryza] SPARK-2461. Add a toString method to GeneralizedLinearModel

3 files changed, 7 insertions, 4 deletions

diff --git a/python/pyspark/mllib/regression.py b/python/pyspark/mllib/regression.py
index cbdbc09858..8fe8c6db2a 100644
--- a/python/pyspark/mllib/regression.py
+++ b/python/pyspark/mllib/regression.py
@@ -66,6 +66,9 @@ class LinearModel(object):
     def intercept(self):
         return self._intercept
 
+    def __repr__(self):
+        return "(weights=%s, intercept=%s)" % (self._coeff, self._intercept)
+
 
 class LinearRegressionModelBase(LinearModel):
 
diff --git a/python/pyspark/serializers.py b/python/pyspark/serializers.py
index 2672da36c1..099fa54cf2 100644
--- a/python/pyspark/serializers.py
+++ b/python/pyspark/serializers.py
@@ -211,7 +211,7 @@ class BatchedSerializer(Serializer):
         return (isinstance(other, BatchedSerializer) and
                 other.serializer == self.serializer)
 
-    def __str__(self):
+    def __repr__(self):
         return "BatchedSerializer<%s>" % str(self.serializer)
 
 
@@ -279,7 +279,7 @@ class CartesianDeserializer(FramedSerializer):
         return (isinstance(other, CartesianDeserializer) and
                 self.key_ser == other.key_ser and self.val_ser == other.val_ser)
 
-    def __str__(self):
+    def __repr__(self):
         return "CartesianDeserializer<%s, %s>" % \
                (str(self.key_ser), str(self.val_ser))
 
@@ -306,7 +306,7 @@ class PairDeserializer(CartesianDeserializer):
         return (isinstance(other, PairDeserializer) and
                 self.key_ser == other.key_ser and self.val_ser == other.val_ser)
 
-    def __str__(self):
+    def __repr__(self):
         return "PairDeserializer<%s, %s>" % (str(self.key_ser), str(self.val_ser))
 
 
diff --git a/python/pyspark/sql.py b/python/pyspark/sql.py
index 974b5e287b..114644ab8b 100644
--- a/python/pyspark/sql.py
+++ b/python/pyspark/sql.py
@@ -201,7 +201,7 @@ class ArrayType(DataType):
         self.elementType = elementType
         self.containsNull = containsNull
 
-    def __str__(self):
+    def __repr__(self):
         return "ArrayType(%s,%s)" % (self.elementType,
                                      str(self.containsNull).lower())