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.

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

GH1033 Add overloads of engine for pd.read_json #1035

Merged
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
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
81 changes: 80 additions & 1 deletion pandas-stubs/io/json/_json.pyi
Original file line number Diff line number Diff line change
Expand Up @@ -42,16 +42,42 @@ def read_json(
Literal["strict", "ignore", "replace", "backslashreplace", "surrogateescape"]
| None
) = ...,
lines: bool,
loicdiridollou marked this conversation as resolved.
Show resolved Hide resolved
chunksize: int,
compression: CompressionOptions = ...,
nrows: int | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | NoDefault = ...,
engine: Literal["ujson"] = ...,
) -> JsonReader[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: int,
compression: CompressionOptions = ...,
nrows: int | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | NoDefault = ...,
engine: Literal["pyarrow"] = ...,
loicdiridollou marked this conversation as resolved.
Show resolved Hide resolved
) -> JsonReader[Series]: ...
@overload
def read_json(
path_or_buf: FilePath | ReadBuffer[str] | ReadBuffer[bytes],
path_or_buf: FilePath | ReadBuffer[bytes],
*,
orient: JsonFrameOrient | None = ...,
typ: Literal["frame"] = ...,
Expand All @@ -72,6 +98,7 @@ def read_json(
nrows: int | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | NoDefault = ...,
engine: Literal["pyarrow"] = ...,
loicdiridollou marked this conversation as resolved.
Show resolved Hide resolved
) -> JsonReader[DataFrame]: ...
@overload
def read_json(
Expand All @@ -96,6 +123,32 @@ 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"] = ...,
loicdiridollou marked this conversation as resolved.
Show resolved Hide resolved
) -> Series: ...
@overload
def read_json(
Expand All @@ -120,6 +173,32 @@ 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"] = ...,
loicdiridollou marked this conversation as resolved.
Show resolved Hide resolved
) -> DataFrame: ...

class JsonReader(abc.Iterator, Generic[NDFrameT]):
Expand Down
25 changes: 25 additions & 0 deletions tests/test_io.py
Original file line number Diff line number Diff line change
Expand Up @@ -1625,3 +1625,28 @@ 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,
)
Dr-Irv marked this conversation as resolved.
Show resolved Hide resolved
Loading