Skip to content

Commit

Permalink
GH1089 Fix pandas nightly and migrate tests to new framework (#1088)
Browse files Browse the repository at this point in the history 
* GH1089 Fix pandas nightly and migrate tests to new framework

* GH1089 Migrate timefuncs tests to new framework
  • Loading branch information
@loicdiridollou
loicdiridollou authored Jan 9, 2025
1 parent d410f2e commit dc636d8
Show file tree
Hide file tree
Showing 7 changed files with 269 additions and 80 deletions.
5 changes: 5 additions & 0 deletions tests/test_frame.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2958,6 +2958,7 @@ def sum_mean(x: pd.DataFrame) -> float:
with pytest_warns_bounded(
DeprecationWarning,
"DataFrameGroupBy.apply operated on the grouping columns.",
upper="2.99",
):
check(
assert_type(df.groupby("col1").apply(sum_mean), pd.Series),
Expand All @@ -2968,6 +2969,7 @@ def sum_mean(x: pd.DataFrame) -> float:
with pytest_warns_bounded(
DeprecationWarning,
"DataFrameGroupBy.apply operated on the grouping columns.",
upper="2.99",
):
check(assert_type(df.groupby("col1").apply(lfunc), pd.Series), pd.Series)

Expand All @@ -2977,6 +2979,7 @@ def sum_to_list(x: pd.DataFrame) -> list:
with pytest_warns_bounded(
DeprecationWarning,
"DataFrameGroupBy.apply operated on the grouping columns.",
upper="2.99",
):
check(assert_type(df.groupby("col1").apply(sum_to_list), pd.Series), pd.Series)

Expand All @@ -2986,6 +2989,7 @@ def sum_to_series(x: pd.DataFrame) -> pd.Series:
with pytest_warns_bounded(
DeprecationWarning,
"DataFrameGroupBy.apply operated on the grouping columns.",
upper="2.99",
):
check(
assert_type(df.groupby("col1").apply(sum_to_series), pd.DataFrame),
Expand All @@ -2998,6 +3002,7 @@ def sample_to_df(x: pd.DataFrame) -> pd.DataFrame:
with pytest_warns_bounded(
DeprecationWarning,
"DataFrameGroupBy.apply operated on the grouping columns.",
upper="2.99",
):
check(
assert_type(
Expand Down
4 changes: 4 additions & 0 deletions tests/test_groupby.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -80,6 +80,7 @@ def test_frame_groupby_resample() -> None:
with pytest_warns_bounded(
DeprecationWarning,
"DataFrameGroupBy.(apply|resample) operated on the grouping columns",
upper="2.99",
):
check(assert_type(GB_DF.resample("ME").sum(), DataFrame), DataFrame)
check(assert_type(GB_DF.resample("ME").prod(), DataFrame), DataFrame)
Expand Down Expand Up @@ -126,6 +127,7 @@ def test_frame_groupby_resample() -> None:
with pytest_warns_bounded(
DeprecationWarning,
"DataFrameGroupBy.(apply|resample) operated on the grouping columns",
upper="2.99",
):
with pytest_warns_bounded(
FutureWarning,
Expand Down Expand Up @@ -173,6 +175,7 @@ def f(val: DataFrame) -> Series:
with pytest_warns_bounded(
DeprecationWarning,
"DataFrameGroupBy.(apply|resample) operated on the grouping columns",
upper="2.99",
):
check(assert_type(GB_DF.resample("ME").aggregate(f), DataFrame), DataFrame)

Expand All @@ -189,6 +192,7 @@ def df2scalar(val: DataFrame) -> float:
with pytest_warns_bounded(
DeprecationWarning,
"DataFrameGroupBy.(apply|resample) operated on the grouping columns",
upper="2.99",
):
with pytest_warns_bounded(
FutureWarning,
Expand Down
3 changes: 3 additions & 0 deletions tests/test_indexes.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -84,10 +84,13 @@ def test_column_contains() -> None:
df = pd.DataFrame({"A": [1, 2], "B": ["c", "d"], "E": [3, 4]})

collist = [column for column in df.columns]
check(assert_type(collist, list[str]), list, str)

collist2 = [column for column in df.columns[df.columns.str.contains("A|B")]]
check(assert_type(collist2, list[str]), list, str)

length = len(df.columns[df.columns.str.contains("A|B")])
check(assert_type(length, int), int)


def test_column_sequence() -> None:
Expand Down
61 changes: 47 additions & 14 deletions tests/test_interval.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -12,28 +12,61 @@


def test_interval_init() -> None:
i1: pd.Interval = pd.Interval(1, 2, closed="both")
i2: pd.Interval = pd.Interval(1, right=2, closed="right")
i3: pd.Interval = pd.Interval(left=1, right=2, closed="left")
check(
assert_type(pd.Interval(1, 2, closed="both"), "pd.Interval[int]"),
pd.Interval,
int,
)
check(
assert_type(pd.Interval(1, right=2, closed="right"), "pd.Interval[int]"),
pd.Interval,
int,
)
check(
assert_type(pd.Interval(left=1, right=2, closed="left"), "pd.Interval[int]"),
pd.Interval,
int,
)


def test_interval_arithmetic() -> None:
i1: pd.Interval = pd.Interval(1, 2, closed="both")
i2: pd.Interval = pd.Interval(1, right=2, closed="right")
i1 = pd.Interval(1, 2, closed="both")
check(assert_type(i1, "pd.Interval[int]"), pd.Interval, int)
check(
assert_type(pd.Interval(1, right=2, closed="right"), "pd.Interval[int]"),
pd.Interval,
int,
)

i3: pd.Interval = i1 + 1
i4: pd.Interval = i1 - 1
i5: pd.Interval = i1 * 2
i6: pd.Interval = i1 / 2
i7: pd.Interval = i1 // 2
check(assert_type(i1 + 1, "pd.Interval[int]"), pd.Interval, int)
check(assert_type(i1 - 1, "pd.Interval[int]"), pd.Interval, int)
check(assert_type(i1 * 2, "pd.Interval[int]"), pd.Interval, int)
check(assert_type(i1 / 2, "pd.Interval[float]"), pd.Interval, float)
check(assert_type(i1 // 2, "pd.Interval[int]"), pd.Interval, int)


def test_max_intervals() -> None:
i1 = pd.Interval(
pd.Timestamp("2000-01-01"), pd.Timestamp("2000-01-02"), closed="both"
check(
assert_type(
pd.Interval(
pd.Timestamp("2000-01-01"), pd.Timestamp("2000-01-02"), closed="both"
),
"pd.Interval[pd.Timestamp]",
),
pd.Interval,
pd.Timestamp,
)
i2 = pd.Interval(
pd.Timestamp("2000-01-01T12:00:00"), pd.Timestamp("2000-01-02"), closed="both"
check(
assert_type(
pd.Interval(
pd.Timestamp("2000-01-01T12:00:00"),
pd.Timestamp("2000-01-02"),
closed="both",
),
"pd.Interval[pd.Timestamp]",
),
pd.Interval,
pd.Timestamp,
)


Expand Down
58 changes: 47 additions & 11 deletions tests/test_interval_index.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -9,27 +9,63 @@


def test_from_breaks() -> None:
ind1: pd.IntervalIndex = pd.IntervalIndex.from_breaks([0, 1, 2, 3], name="test")
ind2: pd.IntervalIndex = pd.IntervalIndex.from_breaks(
[0, 1, 2, 3], closed="right", name=123
check(
assert_type(
pd.IntervalIndex.from_breaks([0, 1, 2, 3], name="test"),
"pd.IntervalIndex[pd.Interval[int]]",
),
pd.IntervalIndex,
pd.Interval,
)
check(
assert_type(
pd.IntervalIndex.from_breaks([0, 1, 2, 3], closed="right", name=123),
"pd.IntervalIndex[pd.Interval[int]]",
),
pd.IntervalIndex,
pd.Interval,
)


def test_from_arrays() -> None:
ind1: pd.IntervalIndex = pd.IntervalIndex.from_arrays(
[0, 1, 2], [1, 2, 3], name="test"
check(
assert_type(
pd.IntervalIndex.from_arrays([0, 1, 2], [1, 2, 3], name="test"),
"pd.IntervalIndex[pd.Interval[int]]",
),
pd.IntervalIndex,
pd.Interval,
)
ind2: pd.IntervalIndex = pd.IntervalIndex.from_arrays(
[0, 1, 2], [1, 2, 3], closed="right", name=123
check(
assert_type(
pd.IntervalIndex.from_arrays(
[0, 1, 2], [1, 2, 3], closed="right", name=123
),
"pd.IntervalIndex[pd.Interval[int]]",
),
pd.IntervalIndex,
pd.Interval,
)


def test_from_tuples() -> None:
ind1: pd.IntervalIndex = pd.IntervalIndex.from_tuples(
[(0, 1), (1, 2), (2, 3)], name="test"
check(
assert_type(
pd.IntervalIndex.from_tuples([(0, 1), (1, 2), (2, 3)], name="test"),
"pd.IntervalIndex[pd.Interval[int]]",
),
pd.IntervalIndex,
pd.Interval,
)
ind2: pd.IntervalIndex = pd.IntervalIndex.from_tuples(
[(0, 1), (1, 2), (2, 3)], closed="right", name=123
check(
assert_type(
pd.IntervalIndex.from_tuples(
[(0, 1), (1, 2), (2, 3)], closed="right", name=123
),
"pd.IntervalIndex[pd.Interval[int]]",
),
pd.IntervalIndex,
pd.Interval,
)


Expand Down
98 changes: 80 additions & 18 deletions tests/test_pandas.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@
import pytest
from typing_extensions import (
Never,
TypeAlias,
assert_type,
)

Expand All @@ -33,23 +34,66 @@
pytest_warns_bounded,
)

if TYPE_CHECKING:
from pandas.core.series import TimestampSeries
else:
TimestampSeries: TypeAlias = pd.Series


def test_types_to_datetime() -> None:
df = pd.DataFrame({"year": [2015, 2016], "month": [2, 3], "day": [4, 5]})
r1: pd.Series = pd.to_datetime(df)
check(assert_type(pd.to_datetime(df), TimestampSeries), pd.Series, pd.Timestamp)

r2: pd.Series = pd.to_datetime(df, unit="s", origin="unix")
r3: pd.Series = pd.to_datetime(
df, unit="ns", dayfirst=True, utc=False, format="%M:%D", exact=False
check(
assert_type(pd.to_datetime(df, unit="s", origin="unix"), TimestampSeries),
pd.Series,
pd.Timestamp,
)
check(
assert_type(
pd.to_datetime(
df, unit="ns", dayfirst=True, utc=False, format="%M:%D", exact=False
),
TimestampSeries,
),
pd.Series,
pd.Timestamp,
)
check(
assert_type(
pd.to_datetime([1, 2], unit="D", origin=pd.Timestamp("01/01/2000")),
pd.DatetimeIndex,
),
pd.DatetimeIndex,
)
check(
assert_type(
pd.to_datetime([1, 2], unit="D", origin=3),
pd.DatetimeIndex,
),
pd.DatetimeIndex,
)
check(
assert_type(
pd.to_datetime(["2022-01-03", "2022-02-22"]),
pd.DatetimeIndex,
),
pd.DatetimeIndex,
)
r4: pd.DatetimeIndex = pd.to_datetime(
[1, 2], unit="D", origin=pd.Timestamp("01/01/2000")
check(
assert_type(
pd.to_datetime(pd.Index(["2022-01-03", "2022-02-22"])),
pd.DatetimeIndex,
),
pd.DatetimeIndex,
)
r5: pd.DatetimeIndex = pd.to_datetime([1, 2], unit="D", origin=3)
r6: pd.DatetimeIndex = pd.to_datetime(["2022-01-03", "2022-02-22"])
r7: pd.DatetimeIndex = pd.to_datetime(pd.Index(["2022-01-03", "2022-02-22"]))
r8: pd.Series = pd.to_datetime(
{"year": [2015, 2016], "month": [2, 3], "day": [4, 5]}
check(
assert_type(
pd.to_datetime({"year": [2015, 2016], "month": [2, 3], "day": [4, 5]}),
TimestampSeries,
),
pd.Series,
pd.Timestamp,
)


Expand Down Expand Up @@ -179,7 +223,7 @@ def test_types_concat() -> None:

check(
assert_type(
pd.concat(map(lambda x: s2, ["some_value", 3]), axis=1), pd.DataFrame
pd.concat(map(lambda _: s2, ["some_value", 3]), axis=1), pd.DataFrame
),
pd.DataFrame,
)
Expand Down Expand Up @@ -306,14 +350,32 @@ def test_types_json_normalize() -> None:
{"name": {"given": "Mose", "family": "Regner"}},
{"id": 2, "name": "Faye Raker"},
]
df1: pd.DataFrame = pd.json_normalize(data=data1)
df2: pd.DataFrame = pd.json_normalize(data=data1, max_level=0, sep=";")
df3: pd.DataFrame = pd.json_normalize(
data=data1, meta_prefix="id", record_prefix="name", errors="raise"
check(assert_type(pd.json_normalize(data=data1), pd.DataFrame), pd.DataFrame)
check(
assert_type(pd.json_normalize(data=data1, max_level=0, sep=";"), pd.DataFrame),
pd.DataFrame,
)
check(
assert_type(
pd.json_normalize(
data=data1, meta_prefix="id", record_prefix="name", errors="raise"
),
pd.DataFrame,
),
pd.DataFrame,
)
check(
assert_type(
pd.json_normalize(data=data1, record_path=None, meta="id"), pd.DataFrame
),
pd.DataFrame,
)
df4: pd.DataFrame = pd.json_normalize(data=data1, record_path=None, meta="id")
data2: dict[str, Any] = {"name": {"given": "Mose", "family": "Regner"}}
df5: pd.DataFrame = pd.json_normalize(data=data2)
check(
assert_type(data2, dict[str, Any]),
dict,
)
check(assert_type(pd.json_normalize(data=data2), pd.DataFrame), pd.DataFrame)


def test_isna() -> None:
Expand Down
Loading

0 comments on commit dc636d8

Please sign in to comment.