yeandy commented on a change in pull request #16677:
URL: https://github.com/apache/beam/pull/16677#discussion_r805836633
##########
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)
Review comment:
If an entry in a series is `np.nan`, and then is converted to dtype
CategoricalDtype, then pandas
[behavior](https://pandas.pydata.org/docs/reference/api/pandas.Series.str.split.html)
is to propogate the NaN. Example:
```
>>>s = pd.Series(
[
"this is a regular sentence",
"https://docs.python.org/3/tutorial/index.html";,
np.nan
]
)
>>>s.str.split(expand=True)
0 1 2 3
4
0 this is a regular
sentence
1 https://docs.python.org/3/tutorial/index.html None None None
None
2 NaN NaN NaN NaN
NaN
```
In row 1, where which the string does not get split, in order to propagate
`None` into other columns, I do `.replace(np.nan, value=None)`. However this
makes row 2 be all `None` instead of `NaN`.
Is there a way to only choose specific rows to be `NaN` and not `None`?
i.e. use `s.isna()` to find those indices?
--
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]
