Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Change pd.core.strings.StringMethods for Pandas 2 compatability. #28455

Merged
merged 3 commits into from
Sep 20, 2023
Merged

Change pd.core.strings.StringMethods for Pandas 2 compatability. #28455

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
69df894
strings
caneff Sep 13, 2023
4f5e2c5
Revert "strings"
caneff Sep 13, 2023
9358eb5
Replace deprecated call to StringMethods
caneff Sep 13, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 17 additions & 17 deletions sdks/python/apache_beam/dataframe/frames.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4907,9 +4907,9 @@ def __setitem__(self, index, value):


class _DeferredStringMethods(frame_base.DeferredBase):
@frame_base.with_docs_from(pd.core.strings.StringMethods)
@frame_base.args_to_kwargs(pd.core.strings.StringMethods)
@frame_base.populate_defaults(pd.core.strings.StringMethods)
@frame_base.with_docs_from(pd.Series.str)
caneff marked this conversation as resolved.
Show resolved Hide resolved
@frame_base.args_to_kwargs(pd.Series.str)
@frame_base.populate_defaults(pd.Series.str)
def cat(self, others, join, **kwargs):
"""If defined, ``others`` must be a :class:`DeferredSeries` or a ``list`` of
``DeferredSeries``."""
Expand Down Expand Up @@ -4949,8 +4949,8 @@ def func(*args):
requires_partition_by=requires,
preserves_partition_by=partitionings.Arbitrary()))

@frame_base.with_docs_from(pd.core.strings.StringMethods)
@frame_base.args_to_kwargs(pd.core.strings.StringMethods)
@frame_base.with_docs_from(pd.Series.str)
@frame_base.args_to_kwargs(pd.Series.str)
def repeat(self, repeats):
"""``repeats`` must be an ``int`` or a :class:`DeferredSeries`. Lists are
not supported because they make this operation order-sensitive."""
Expand Down Expand Up @@ -4987,8 +4987,8 @@ def repeat(self, repeats):
raise TypeError("str.repeat(repeats=) value must be an int or a "
f"DeferredSeries (encountered {type(repeats)}).")

@frame_base.with_docs_from(pd.core.strings.StringMethods)
@frame_base.args_to_kwargs(pd.core.strings.StringMethods)
@frame_base.with_docs_from(pd.Series.str)
@frame_base.args_to_kwargs(pd.Series.str)
def get_dummies(self, **kwargs):
"""
Series must be categorical dtype. Please cast to ``CategoricalDtype``
Expand Down Expand Up @@ -5070,9 +5070,9 @@ def func(s):
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)
@frame_base.populate_defaults(pd.core.strings.StringMethods)
@frame_base.with_docs_from(pd.Series.str)
@frame_base.args_to_kwargs(pd.Series.str)
@frame_base.populate_defaults(pd.Series.str)
def split(self, **kwargs):
"""
Like other non-deferred methods, dtype must be CategoricalDtype.
Expand All @@ -5081,9 +5081,9 @@ def split(self, **kwargs):
"""
return self._split_helper(rsplit=False, **kwargs)

@frame_base.with_docs_from(pd.core.strings.StringMethods)
@frame_base.args_to_kwargs(pd.core.strings.StringMethods)
@frame_base.populate_defaults(pd.core.strings.StringMethods)
@frame_base.with_docs_from(pd.Series.str)
@frame_base.args_to_kwargs(pd.Series.str)
@frame_base.populate_defaults(pd.Series.str)
def rsplit(self, **kwargs):
"""
Like other non-deferred methods, dtype must be CategoricalDtype.
Expand Down Expand Up @@ -5161,25 +5161,25 @@ def func(df, *args, **kwargs):
return func

for method in ELEMENTWISE_STRING_METHODS:
if not hasattr(pd.core.strings.StringMethods, method):
if not hasattr(pd.Series.str, method):
# older versions (1.0.x) don't support some of these methods
continue
setattr(_DeferredStringMethods,
method,
frame_base._elementwise_method(make_str_func(method),
name=method,
base=pd.core.strings.StringMethods))
base=pd.Series.str))

for method in NON_ELEMENTWISE_STRING_METHODS:
if not hasattr(pd.core.strings.StringMethods, method):
if not hasattr(pd.Series.str, method):
# older versions (1.0.x) don't support some of these methods
continue
setattr(_DeferredStringMethods,
method,
frame_base._proxy_method(
make_str_func(method),
name=method,
base=pd.core.strings.StringMethods,
base=pd.Series.str,
requires_partition_by=partitionings.Arbitrary(),
preserves_partition_by=partitionings.Singleton()))

Expand Down
2 changes: 1 addition & 1 deletion sdks/python/apache_beam/dataframe/frames_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2936,7 +2936,7 @@ class DocstringTest(unittest.TestCase):
(frames.DeferredDataFrame, pd.DataFrame),
(frames.DeferredSeries, pd.Series),
#(frames._DeferredIndex, pd.Index),
(frames._DeferredStringMethods, pd.core.strings.StringMethods),
(frames._DeferredStringMethods, pd.Series.str),
(
frames._DeferredCategoricalMethods,
pd.core.arrays.categorical.CategoricalAccessor),
Expand Down
Loading