Skip to content

[ArrowStringArray] CLN: remove hasattr checks #41327

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

Merged
merged 5 commits into from
May 5, 2021
Merged

[ArrowStringArray] CLN: remove hasattr checks #41327

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
625ceae
[ArrowStringArray] CLN: remove hasattr checks
simonjayhawkins May 5, 2021
f578330
move to pandas/compat/pyarrow.py
simonjayhawkins May 5, 2021
57811fb
Merge remote-tracking branch 'upstream/master' into misc2
simonjayhawkins May 5, 2021
bdfdaf9
Merge remote-tracking branch 'upstream/master' into misc2
simonjayhawkins May 5, 2021
df7b613
update isin to use pa_version_under
simonjayhawkins May 5, 2021
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
21 changes: 21 additions & 0 deletions pandas/compat/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@
Other items:
* platform checker
"""
from distutils.version import LooseVersion
import platform
import sys
import warnings
Expand Down Expand Up @@ -129,11 +130,31 @@ def get_lzma_file(lzma):
return lzma.LZMAFile


# pyarrow versioning
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you put in pandas.compat.pyarrow (and import), similar to how we do numpy

try:
import pyarrow as pa

_pa_version = pa.__version__
_palv = LooseVersion(_pa_version)
pa_version_under1p0 = _palv < LooseVersion("1.0.0")
pa_version_under2p0 = _palv < LooseVersion("2.0.0")
pa_version_under3p0 = _palv < LooseVersion("3.0.0")
pa_version_under4p0 = _palv < LooseVersion("4.0.0")
except ImportError:
pa_version_under1p0 = True
pa_version_under2p0 = True
pa_version_under3p0 = True
pa_version_under4p0 = True

__all__ = [
"is_numpy_dev",
"np_array_datetime64_compat",
"np_datetime64_compat",
"np_version_under1p18",
"np_version_under1p19",
"np_version_under1p20",
"pa_version_under1p0",
"pa_version_under2p0",
"pa_version_under3p0",
"pa_version_under4p0",
]
98 changes: 47 additions & 51 deletions pandas/core/arrays/string_arrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,10 @@
PositionalIndexer,
type_t,
)
from pandas.compat import (
pa_version_under2p0,
pa_version_under4p0,
)
from pandas.util._decorators import doc
from pandas.util._validators import validate_fillna_kwargs

Expand Down Expand Up @@ -773,11 +777,10 @@ def _str_contains(self, pat, case=True, flags=0, na=np.nan, regex: bool = True):
return super()._str_contains(pat, case, flags, na, regex)

if regex:
# match_substring_regex added in pyarrow 4.0.0
if hasattr(pc, "match_substring_regex") and case:
result = pc.match_substring_regex(self._data, pat)
else:
if pa_version_under4p0 or case is False:
return super()._str_contains(pat, case, flags, na, regex)
else:
result = pc.match_substring_regex(self._data, pat)
else:
if case:
result = pc.match_substring(self._data, pat)
Expand All @@ -789,27 +792,25 @@ def _str_contains(self, pat, case=True, flags=0, na=np.nan, regex: bool = True):
return result

def _str_startswith(self, pat, na=None):
# match_substring_regex added in pyarrow 4.0.0
if hasattr(pc, "match_substring_regex"):
result = pc.match_substring_regex(self._data, "^" + re.escape(pat))
result = BooleanDtype().__from_arrow__(result)
if not isna(na):
result[isna(result)] = bool(na)
return result
else:
if pa_version_under4p0:
return super()._str_startswith(pat, na)

result = pc.match_substring_regex(self._data, "^" + re.escape(pat))
result = BooleanDtype().__from_arrow__(result)
if not isna(na):
result[isna(result)] = bool(na)
return result

def _str_endswith(self, pat, na=None):
# match_substring_regex added in pyarrow 4.0.0
if hasattr(pc, "match_substring_regex"):
result = pc.match_substring_regex(self._data, re.escape(pat) + "$")
result = BooleanDtype().__from_arrow__(result)
if not isna(na):
result[isna(result)] = bool(na)
return result
else:
if pa_version_under4p0:
return super()._str_endswith(pat, na)

result = pc.match_substring_regex(self._data, re.escape(pat) + "$")
result = BooleanDtype().__from_arrow__(result)
if not isna(na):
result[isna(result)] = bool(na)
return result

def _str_isalnum(self):
result = pc.utf8_is_alnum(self._data)
return BooleanDtype().__from_arrow__(result)
Expand All @@ -835,13 +836,12 @@ def _str_isnumeric(self):
return BooleanDtype().__from_arrow__(result)

def _str_isspace(self):
# utf8_is_space added in pyarrow 2.0.0
if hasattr(pc, "utf8_is_space"):
result = pc.utf8_is_space(self._data)
return BooleanDtype().__from_arrow__(result)
else:
if pa_version_under2p0:
return super()._str_isspace()

result = pc.utf8_is_space(self._data)
return BooleanDtype().__from_arrow__(result)

def _str_istitle(self):
result = pc.utf8_is_title(self._data)
return BooleanDtype().__from_arrow__(result)
Expand All @@ -851,48 +851,44 @@ def _str_isupper(self):
return BooleanDtype().__from_arrow__(result)

def _str_len(self):
# utf8_length added in pyarrow 4.0.0
if hasattr(pc, "utf8_length"):
result = pc.utf8_length(self._data)
return Int64Dtype().__from_arrow__(result)
else:
if pa_version_under4p0:
return super()._str_len()

result = pc.utf8_length(self._data)
return Int64Dtype().__from_arrow__(result)

def _str_lower(self):
return type(self)(pc.utf8_lower(self._data))

def _str_upper(self):
return type(self)(pc.utf8_upper(self._data))

def _str_strip(self, to_strip=None):
if pa_version_under4p0:
return super()._str_strip(to_strip)

if to_strip is None:
# utf8_trim_whitespace added in pyarrow 4.0.0
if hasattr(pc, "utf8_trim_whitespace"):
return type(self)(pc.utf8_trim_whitespace(self._data))
result = pc.utf8_trim_whitespace(self._data)
else:
# utf8_trim added in pyarrow 4.0.0
if hasattr(pc, "utf8_trim"):
return type(self)(pc.utf8_trim(self._data, characters=to_strip))
return super()._str_strip(to_strip)
result = pc.utf8_trim(self._data, characters=to_strip)
return type(self)(result)

def _str_lstrip(self, to_strip=None):
if pa_version_under4p0:
return super()._str_lstrip(to_strip)

if to_strip is None:
# utf8_ltrim_whitespace added in pyarrow 4.0.0
if hasattr(pc, "utf8_ltrim_whitespace"):
return type(self)(pc.utf8_ltrim_whitespace(self._data))
result = pc.utf8_ltrim_whitespace(self._data)
else:
# utf8_ltrim added in pyarrow 4.0.0
if hasattr(pc, "utf8_ltrim"):
return type(self)(pc.utf8_ltrim(self._data, characters=to_strip))
return super()._str_lstrip(to_strip)
result = pc.utf8_ltrim(self._data, characters=to_strip)
return type(self)(result)

def _str_rstrip(self, to_strip=None):
if pa_version_under4p0:
return super()._str_rstrip(to_strip)

if to_strip is None:
# utf8_rtrim_whitespace added in pyarrow 4.0.0
if hasattr(pc, "utf8_rtrim_whitespace"):
return type(self)(pc.utf8_rtrim_whitespace(self._data))
result = pc.utf8_rtrim_whitespace(self._data)
else:
# utf8_rtrim added in pyarrow 4.0.0
if hasattr(pc, "utf8_rtrim"):
return type(self)(pc.utf8_rtrim(self._data, characters=to_strip))
return super()._str_rstrip(to_strip)
result = pc.utf8_rtrim(self._data, characters=to_strip)
return type(self)(result)