Skip to content

ENH: Use more arrow compute functions for string[pyarrow] dtype #54957

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 1 commit into from
Sep 5, 2023
Merged

ENH: Use more arrow compute functions for string[pyarrow] dtype #54957

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
50 changes: 25 additions & 25 deletions pandas/core/arrays/string_arrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -417,7 +417,7 @@ def _str_isupper(self):

def _str_len(self):
result = pc.utf8_length(self._pa_array)
return Int64Dtype().__from_arrow__(result)
return self._convert_int_dtype(result)

def _str_lower(self):
return type(self)(pc.utf8_lower(self._pa_array))
Expand Down Expand Up @@ -446,6 +446,29 @@ def _str_rstrip(self, to_strip=None):
result = pc.utf8_rtrim(self._pa_array, characters=to_strip)
return type(self)(result)

def _str_count(self, pat: str, flags: int = 0):
if flags:
return super()._str_count(pat, flags)
result = pc.count_substring_regex(self._pa_array, pat)
return self._convert_int_dtype(result)

def _str_find(self, sub: str, start: int = 0, end: int | None = None):
if start != 0 and end is not None:
slices = pc.utf8_slice_codeunits(self._pa_array, start, stop=end)
result = pc.find_substring(slices, sub)
not_found = pc.equal(result, -1)
offset_result = pc.add(result, end - start)
result = pc.if_else(not_found, result, offset_result)
elif start == 0 and end is None:
slices = self._pa_array
result = pc.find_substring(slices, sub)
else:
return super()._str_find(sub, start, end)
return self._convert_int_dtype(result)

def _convert_int_dtype(self, result):
return Int64Dtype().__from_arrow__(result)


class ArrowStringArrayNumpySemantics(ArrowStringArray):
_storage = "pyarrow_numpy"
Expand Down Expand Up @@ -517,34 +540,11 @@ def _str_map(
return lib.map_infer_mask(arr, f, mask.view("uint8"))

def _convert_int_dtype(self, result):
result = result.to_numpy()
if result.dtype == np.int32:
result = result.astype(np.int64)
return result

def _str_count(self, pat: str, flags: int = 0):
if flags:
return super()._str_count(pat, flags)
result = pc.count_substring_regex(self._pa_array, pat).to_numpy()
return self._convert_int_dtype(result)

def _str_len(self):
result = pc.utf8_length(self._pa_array).to_numpy()
return self._convert_int_dtype(result)

def _str_find(self, sub: str, start: int = 0, end: int | None = None):
if start != 0 and end is not None:
slices = pc.utf8_slice_codeunits(self._pa_array, start, stop=end)
result = pc.find_substring(slices, sub)
not_found = pc.equal(result, -1)
offset_result = pc.add(result, end - start)
result = pc.if_else(not_found, result, offset_result)
elif start == 0 and end is None:
slices = self._pa_array
result = pc.find_substring(slices, sub)
else:
return super()._str_find(sub, start, end)
return self._convert_int_dtype(result.to_numpy())

def _cmp_method(self, other, op):
result = super()._cmp_method(other, op)
return result.to_numpy(np.bool_, na_value=False)
Expand Down