Skip to content

896 dataframe from dict columns dtype args #897

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 7 commits into from
Apr 1, 2024
Merged

896 dataframe from dict columns dtype args #897

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
da80815
tentative solution for #896
Mar 29, 2024
b4c85be
remove Unnecessary "# pyright: ignore" rule error
Mar 29, 2024
050c6f9
improving dataframe.from_dict test
Mar 29, 2024
729bdb5
check(assert_type every test
Apr 1, 2024
bc05ade
remove unwanted ellipsis
Apr 1, 2024
f760452
Adding overload and test to cover when litteral is not used
Apr 1, 2024
3b6f9b6
Revert "Adding overload and test to cover when litteral is not used"
Apr 1, 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
2 changes: 1 addition & 1 deletion pandas-stubs/_libs/tslibs/timestamps.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -219,7 +219,7 @@ class Timestamp(datetime):
@overload
def __sub__(self, other: TimedeltaSeries) -> TimestampSeries: ...
@overload
def __sub__( # pyright: ignore[reportIncompatibleMethodOverride]
def __sub__(
self, other: npt.NDArray[np.timedelta64]
) -> npt.NDArray[np.datetime64]: ...
@overload
Expand Down
15 changes: 12 additions & 3 deletions pandas-stubs/core/frame.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -272,13 +272,22 @@ class DataFrame(NDFrame, OpsMixin):
def dot(self, other: Series) -> Series: ...
def __matmul__(self, other): ...
def __rmatmul__(self, other): ...
@overload
@classmethod
def from_dict(
cls,
data: dict[Any, Any],
orient: Literal["index"],
dtype: AstypeArg | None = ...,
columns: Axes | None = ...,
) -> DataFrame: ...
@overload
@classmethod
def from_dict(
cls,
data: dict[Any, Any],
orient: Literal["columns", "index", "tight"] = ...,
dtype: _str = ...,
columns: list[_str] = ...,
orient: Literal["columns", "tight"] = ...,
dtype: AstypeArg | None = ...,
) -> DataFrame: ...
def to_numpy(
self,
Expand Down
121 changes: 105 additions & 16 deletions tests/test_frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1438,25 +1438,114 @@ def test_types_to_dict() -> None:


def test_types_from_dict() -> None:
pd.DataFrame.from_dict({"col_1": [3, 2, 1, 0], "col_2": ["a", "b", "c", "d"]})
pd.DataFrame.from_dict({1: [3, 2, 1, 0], 2: ["a", "b", "c", "d"]})
pd.DataFrame.from_dict({"a": {1: 2}, "b": {3: 4, 1: 4}}, orient="index")
pd.DataFrame.from_dict({"a": {"row1": 2}, "b": {"row2": 4, "row1": 4}})
pd.DataFrame.from_dict({"a": (1, 2, 3), "b": (2, 4, 5)})
pd.DataFrame.from_dict(
data={"col_1": {"a": 1}, "col_2": {"a": 1, "b": 2}}, orient="columns"
check(
assert_type(
pd.DataFrame.from_dict(
{"col_1": [3, 2, 1, 0], "col_2": ["a", "b", "c", "d"]}
),
pd.DataFrame,
),
pd.DataFrame,
)
check(
assert_type(
pd.DataFrame.from_dict({1: [3, 2, 1, 0], 2: ["a", "b", "c", "d"]}),
pd.DataFrame,
),
pd.DataFrame,
)
check(
assert_type(
pd.DataFrame.from_dict({"a": {1: 2}, "b": {3: 4, 1: 4}}, orient="index"),
pd.DataFrame,
),
pd.DataFrame,
)
check(
assert_type(
pd.DataFrame.from_dict({"a": {"row1": 2}, "b": {"row2": 4, "row1": 4}}),
pd.DataFrame,
),
pd.DataFrame,
)
check(
assert_type(
pd.DataFrame.from_dict({"a": (1, 2, 3), "b": (2, 4, 5)}), pd.DataFrame
),
pd.DataFrame,
)
check(
assert_type(
pd.DataFrame.from_dict(
data={"col_1": {"a": 1}, "col_2": {"a": 1, "b": 2}}, orient="columns"
),
pd.DataFrame,
),
pd.DataFrame,
)
# orient param accepting "tight" added in 1.4.0 https://pandas.pydata.org/docs/whatsnew/v1.4.0.html
pd.DataFrame.from_dict(
data={
"index": [("a", "b"), ("a", "c")],
"columns": [("x", 1), ("y", 2)],
"data": [[1, 3], [2, 4]],
"index_names": ["n1", "n2"],
"column_names": ["z1", "z2"],
},
orient="tight",
check(
assert_type(
pd.DataFrame.from_dict(
data={
"index": [("a", "b"), ("a", "c")],
"columns": [("x", 1), ("y", 2)],
"data": [[1, 3], [2, 4]],
"index_names": ["n1", "n2"],
"column_names": ["z1", "z2"],
},
orient="tight",
),
pd.DataFrame,
),
pd.DataFrame,
)
# added following #896
data = {"l1": [1, 2, 3], "l2": [4, 5, 6]}
# testing `dtype`
check(
assert_type(
pd.DataFrame.from_dict(data, orient="index", dtype="float"), pd.DataFrame
),
pd.DataFrame,
)
check(
assert_type(
pd.DataFrame.from_dict(data, orient="index", dtype=float), pd.DataFrame
),
pd.DataFrame,
)
check(
assert_type(
pd.DataFrame.from_dict(data, orient="index", dtype=None), pd.DataFrame
),
pd.DataFrame,
)
# testing `columns`
check(
assert_type(
pd.DataFrame.from_dict(data, orient="index", columns=["a", "b", "c"]),
pd.DataFrame,
),
pd.DataFrame,
)
check(
assert_type(
pd.DataFrame.from_dict(
data, orient="index", columns=[1.0, 2, datetime.datetime.now()]
),
pd.DataFrame,
),
pd.DataFrame,
)
if TYPE_CHECKING_INVALID_USAGE:
check(
assert_type( # type: ignore[assert-type]
pd.DataFrame.from_dict(data, orient="columns", columns=["a", "b", "c"]), # type: ignore[call-overload] # pyright: ignore[reportArgumentType]
pd.DataFrame,
),
pd.DataFrame,
)


def test_pipe() -> None:
Expand Down
Loading