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

BUG: Use large_string in string array consistently #58590

Merged
merged 1 commit into from
May 6, 2024
Merged

BUG: Use large_string in string array consistently #58590

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
16 changes: 10 additions & 6 deletions pandas/core/arrays/string_arrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -196,13 +196,13 @@ def _from_sequence(
na_values = scalars._mask
result = scalars._data
result = lib.ensure_string_array(result, copy=copy, convert_na_value=False)
return cls(pa.array(result, mask=na_values, type=pa.string()))
return cls(pa.array(result, mask=na_values, type=pa.large_string()))
elif isinstance(scalars, (pa.Array, pa.ChunkedArray)):
return cls(pc.cast(scalars, pa.string()))
return cls(pc.cast(scalars, pa.large_string()))

# convert non-na-likes to str
result = lib.ensure_string_array(scalars, copy=copy)
return cls(pa.array(result, type=pa.string(), from_pandas=True))
return cls(pa.array(result, type=pa.large_string(), from_pandas=True))

@classmethod
def _from_sequence_of_strings(
Expand Down Expand Up @@ -245,7 +245,7 @@ def isin(self, values: ArrayLike) -> npt.NDArray[np.bool_]:
value_set = [
pa_scalar.as_py()
for pa_scalar in [pa.scalar(value, from_pandas=True) for value in values]
if pa_scalar.type in (pa.string(), pa.null())
if pa_scalar.type in (pa.string(), pa.null(), pa.large_string())
]

# short-circuit to return all False array.
Expand Down Expand Up @@ -332,7 +332,9 @@ def _str_map(
result = lib.map_infer_mask(
arr, f, mask.view("uint8"), convert=False, na_value=na_value
)
result = pa.array(result, mask=mask, type=pa.string(), from_pandas=True)
result = pa.array(
result, mask=mask, type=pa.large_string(), from_pandas=True
)
return type(self)(result)
else:
# This is when the result type is object. We reach this when
Expand Down Expand Up @@ -655,7 +657,9 @@ def _str_map(
result = lib.map_infer_mask(
arr, f, mask.view("uint8"), convert=False, na_value=na_value
)
result = pa.array(result, mask=mask, type=pa.string(), from_pandas=True)
result = pa.array(
result, mask=mask, type=pa.large_string(), from_pandas=True
)
return type(self)(result)
else:
# This is when the result type is object. We reach this when
Expand Down