yeandy commented on a change in pull request #16677:
URL: https://github.com/apache/beam/pull/16677#discussion_r819148400
##########
File path: sdks/python/apache_beam/dataframe/frames.py
##########
@@ -4721,13 +4721,82 @@ def repeat(self, repeats):
pd.core.strings.StringMethods, 'get_dummies',
reason='non-deferred-columns')
- split = frame_base.wont_implement_method(
- pd.core.strings.StringMethods, 'split',
- reason='non-deferred-columns')
+ def _split_helper(
+ self, rsplit=False, pat=None, expand=False, regex=None, **kwargs):
+ if not expand:
+ # Not creating separate columns
+ proxy = self._expr.proxy()
+ func = lambda s: pd.concat([proxy,
+ (s.str.split(pat=pat, expand=expand, regex=regex, **kwargs)
+ if not rsplit else s.str.rsplit(pat=pat, expand=expand, **kwargs))]
+ )
+ else:
+ # Creating separate columns, so must be more strict on dtype
+ dtype = self._expr.proxy().dtype
+ if not isinstance(dtype, pd.CategoricalDtype):
+ method_name = 'rsplit' if rsplit else 'split'
+ raise frame_base.WontImplementError(
+ method_name + "() of non-categorical type is not supported because
"
+ "the type of the output column depends on the data. Please use "
+ "pd.CategoricalDtype with explicit categories.",
+ reason="non-deferred-columns")
- rsplit = frame_base.wont_implement_method(
- pd.core.strings.StringMethods, 'rsplit',
- reason='non-deferred-columns')
+ if regex is False or (
+ regex is None and isinstance(pat, str) and len(pat) == 1):
+ # Treat pat as literal string
+ split_cats = [
+ cat.split(
+ sep=kwargs.get('pat'),
+ maxsplit=kwargs.get('n', -1)
+ ) for cat in dtype.categories
+ ]
+ else:
+ # Treat pat as regex
+ split_cats = [
+ re.split(
+ pattern=pat,
+ string=cat,
+ maxsplit=kwargs.get('n', 0)
+ ) for cat in dtype.categories
+ ]
+
+ max_splits = len(max(split_cats, key=len))
+ proxy = pd.DataFrame(columns=range(max_splits))
+
+ func = lambda s: pd.concat([proxy,
+ (s.str.split(pat=pat, expand=expand, regex=regex, **kwargs)
+ if not rsplit else s.str.rsplit(pat=pat, expand=expand, **kwargs))]
+ ).replace(np.nan, value=None)
+
+ return frame_base.DeferredFrame.wrap(
+ expressions.ComputedExpression(
+ 'split',
+ func,
+ [self._expr],
+ proxy=proxy,
+ requires_partition_by=partitionings.Arbitrary(),
+ preserves_partition_by=partitionings.Arbitrary()))
+
+ @frame_base.with_docs_from(pd.core.strings.StringMethods)
+ @frame_base.args_to_kwargs(pd.core.strings.StringMethods)
+ def split(self, pat=None, expand=False, regex=None, **kwargs):
+ """
+ Like other non-deferred methods, dtype must be CategoricalDtype.
+ One exception is when ``expand`` is ``False``. Because we are not
+ creating new columns at construction time dtype can be `str`.
+ """
+ return self._split_helper(
+ rsplit=False, pat=pat, expand=expand, regex=regex, **kwargs)
+
+ @frame_base.with_docs_from(pd.core.strings.StringMethods)
+ @frame_base.args_to_kwargs(pd.core.strings.StringMethods)
+ def rsplit(self, pat=None, expand=False, **kwargs):
Review comment:
Looks like it was
[filed](https://github.com/pandas-dev/pandas/issues/29633) a while time ago,
but no one has picked it up. I'll assign it to myself to do. In the meantime, I
can add a subtask (under the non-deferred
[ticket](https://issues.apache.org/jira/browse/BEAM-12169)?) to remind us to
update the function api once the `rsplit` fix in pandas is released.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
