Skip to content

GH1033 Add overloads of engine for pd.read_json #1035

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 6 commits into from
Nov 21, 2024
Merged

GH1033 Add overloads of engine for pd.read_json #1035

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
7603dde
GHXXX Add overloads of engine for pd.read_json
loicdiridollou Nov 16, 2024
e64c085
GH1033 PR Feedback
loicdiridollou Nov 20, 2024
a7a35bd
Merge branch 'main' of github.com:loicdiridollou/pandas-stubs into gh…
loicdiridollou Nov 20, 2024
b7eb663
GH1033 PR Feedback
loicdiridollou Nov 20, 2024
53af846
GH1033 Fix ignore type
loicdiridollou Nov 20, 2024
62ce800
GH1033 PR feedback
loicdiridollou Nov 21, 2024
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
106 changes: 105 additions & 1 deletion pandas-stubs/io/json/_json.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,10 +48,61 @@ def read_json(
nrows: int | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | NoDefault = ...,
engine: Literal["ujson"] = ...,
) -> JsonReader[Series]: ...
@overload
def read_json(
path_or_buf: FilePath | ReadBuffer[str] | ReadBuffer[bytes],
path_or_buf: FilePath | ReadBuffer[bytes],
*,
orient: JsonSeriesOrient | None = ...,
typ: Literal["series"],
dtype: bool | Mapping[HashableT, DtypeArg] | None = ...,
convert_axes: bool | None = ...,
convert_dates: bool | list[str] = ...,
keep_default_dates: bool = ...,
precise_float: bool = ...,
date_unit: TimeUnit | None = ...,
encoding: str | None = ...,
encoding_errors: (
Literal["strict", "ignore", "replace", "backslashreplace", "surrogateescape"]
| None
) = ...,
lines: Literal[True],
chunksize: int,
compression: CompressionOptions = ...,
nrows: int | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | NoDefault = ...,
engine: Literal["pyarrow"],
) -> JsonReader[Series]: ...
@overload
def read_json(
path_or_buf: FilePath | ReadBuffer[bytes],
*,
orient: JsonFrameOrient | None = ...,
typ: Literal["frame"] = ...,
dtype: bool | Mapping[HashableT, DtypeArg] | None = ...,
convert_axes: bool | None = ...,
convert_dates: bool | list[str] = ...,
keep_default_dates: bool = ...,
precise_float: bool = ...,
date_unit: TimeUnit | None = ...,
encoding: str | None = ...,
encoding_errors: (
Literal["strict", "ignore", "replace", "backslashreplace", "surrogateescape"]
| None
) = ...,
lines: Literal[True],
chunksize: int,
compression: CompressionOptions = ...,
nrows: int | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | NoDefault = ...,
engine: Literal["ujson"] = ...,
) -> JsonReader[DataFrame]: ...
@overload
def read_json(
path_or_buf: FilePath | ReadBuffer[bytes],
*,
orient: JsonFrameOrient | None = ...,
typ: Literal["frame"] = ...,
Expand All @@ -72,6 +123,7 @@ def read_json(
nrows: int | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | NoDefault = ...,
engine: Literal["pyarrow"],
) -> JsonReader[DataFrame]: ...
@overload
def read_json(
Expand All @@ -96,6 +148,32 @@ def read_json(
nrows: int | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | NoDefault = ...,
engine: Literal["ujson"] = ...,
) -> Series: ...
@overload
def read_json(
path_or_buf: FilePath | ReadBuffer[bytes],
*,
orient: JsonSeriesOrient | None = ...,
typ: Literal["series"],
dtype: bool | Mapping[HashableT, DtypeArg] | None = ...,
convert_axes: bool | None = ...,
convert_dates: bool | list[str] = ...,
keep_default_dates: bool = ...,
precise_float: bool = ...,
date_unit: TimeUnit | None = ...,
encoding: str | None = ...,
encoding_errors: (
Literal["strict", "ignore", "replace", "backslashreplace", "surrogateescape"]
| None
) = ...,
lines: Literal[True],
chunksize: None = ...,
compression: CompressionOptions = ...,
nrows: int | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | NoDefault = ...,
engine: Literal["pyarrow"],
) -> Series: ...
@overload
def read_json(
Expand All @@ -120,6 +198,32 @@ def read_json(
nrows: int | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | NoDefault = ...,
engine: Literal["ujson"] = ...,
) -> DataFrame: ...
@overload
def read_json(
path_or_buf: FilePath | ReadBuffer[bytes],
*,
orient: JsonFrameOrient | None = ...,
typ: Literal["frame"] = ...,
dtype: bool | Mapping[HashableT, DtypeArg] | None = ...,
convert_axes: bool | None = ...,
convert_dates: bool | list[str] = ...,
keep_default_dates: bool = ...,
precise_float: bool = ...,
date_unit: TimeUnit | None = ...,
encoding: str | None = ...,
encoding_errors: (
Literal["strict", "ignore", "replace", "backslashreplace", "surrogateescape"]
| None
) = ...,
lines: Literal[True],
chunksize: None = ...,
compression: CompressionOptions = ...,
nrows: int | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | NoDefault = ...,
engine: Literal["pyarrow"],
) -> DataFrame: ...

class JsonReader(abc.Iterator, Generic[NDFrameT]):
Expand Down
30 changes: 30 additions & 0 deletions tests/test_io.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1714,3 +1714,33 @@ def test_read_excel_index_col() -> None:
),
pd.DataFrame,
)


def test_read_json_engine() -> None:
"""Test the engine argument for `pd.read_json` introduced with pandas 2.0."""
data = """{"index": {"0": 0, "1": 1},
"a": {"0": 1, "1": null},
"b": {"0": 2.5, "1": 4.5},
"c": {"0": true, "1": false},
"d": {"0": "a", "1": "b"},
"e": {"0": 1577.2, "1": 1577.1}}"""
check(
assert_type(pd.read_json(io.StringIO(data), engine="ujson"), pd.DataFrame),
pd.DataFrame,
)

data_lines = b"""{"col 1":"a","col 2":"b"}
{"col 1":"c","col 2":"d"}"""
dd = io.BytesIO(data_lines)
check(
assert_type(
pd.read_json(dd, lines=True, engine="pyarrow"),
pd.DataFrame,
),
pd.DataFrame,
)

if TYPE_CHECKING_INVALID_USAGE:
pd.read_json(dd, lines=False, engine="pyarrow") # type: ignore[call-overload] # pyright: ignore[reportArgumentType, reportCallIssue]
pd.read_json(io.StringIO(data), engine="pyarrow") # type: ignore[call-overload] # pyright: ignore[reportArgumentType]
pd.read_json(io.StringIO(data), lines=True, engine="pyarrow") # type: ignore[call-overload] # pyright: ignore[reportArgumentType, reportCallIssue]
Loading