Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/11663#discussion_r57024837
--- Diff: python/pyspark/ml/param/__init__.py ---
@@ -65,6 +75,146 @@ def __eq__(self, other):
return False
+class TypeConverters(object):
+ """
+ .. note:: DeveloperApi
+
+ Factory methods for common type conversion functions for
`Param.typeConverter`.
+
+ .. versionadded:: 2.0.0
+ """
+
+ @staticmethod
+ def _is_numeric(value):
+ vtype = type(value)
+ return vtype in [int, float, np.float64, np.int64] or
vtype.__name__ == 'long'
+
+ @staticmethod
+ def _is_integer(value):
+ if TypeConverters._is_numeric(value):
+ value = float(value)
+ return value.is_integer()
+ else:
+ return False
+
+ @staticmethod
+ def _can_convert_to_list(value):
+ vtype = type(value)
+ return vtype == list or vtype == np.ndarray or isinstance(value,
Vector)
+
+ @staticmethod
+ def _is_string(value):
--- End diff --
I'd follow existing conventions. Look at, e.g., the beginning of file
feature.py:
```
import sys
if sys.version > '3':
basestring = str
```
Then you can use ```isinstance(blah, basestring)```
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
