Skip to content

datetime: propagate NaN for week and days_in_month with missing_values=ignore #1017

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

Open
AlejandroCoronadoN wants to merge 1 commit into
base: main
Choose a base branch
from
Open

datetime: propagate NaN for week and days_in_month with missing_values=ignore #1017

Show file tree
Hide file tree
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
4 changes: 2 additions & 2 deletions feature_engine/datetime/_datetime_constants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,7 +61,7 @@
"quarter": lambda x: x.dt.quarter,
"semester": lambda x: np.where(x.dt.month <= 6, 1, 2).astype(np.int64),
"year": lambda x: x.dt.year,
"week": lambda x: x.dt.isocalendar().week.astype(np.int64),
"week": lambda x: x.dt.isocalendar().week.astype("float64"),
"day_of_week": lambda x: x.dt.dayofweek,
"day_of_month": lambda x: x.dt.day,
"day_of_year": lambda x: x.dt.dayofyear,
Expand All @@ -73,7 +73,7 @@
"year_start": lambda x: x.dt.is_year_start.astype(np.int64),
"year_end": lambda x: x.dt.is_year_end.astype(np.int64),
"leap_year": lambda x: x.dt.is_leap_year.astype(np.int64),
"days_in_month": lambda x: x.dt.days_in_month.astype(np.int64),
"days_in_month": lambda x: x.dt.days_in_month.astype("float64"),
"hour": lambda x: x.dt.hour,
"minute": lambda x: x.dt.minute,
"second": lambda x: x.dt.second,
Expand Down
17 changes: 17 additions & 0 deletions tests/test_datetime/test_datetime_features.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -472,6 +472,23 @@ def test_extract_features_from_variables_containing_nans():
)


def test_ignore_nan_for_week_and_days_in_month():
# week and days_in_month must propagate NaN like the other features when
# missing_values="ignore", instead of raising on the int cast of a NaT.
X = DatetimeFeatures(
features_to_extract=["week", "days_in_month"], missing_values="ignore"
).fit_transform(dates_nan)
pd.testing.assert_frame_equal(
X,
pd.DataFrame(
{
"dates_na_week": [5.0, np.nan, 22.0, np.nan],
"dates_na_days_in_month": [28.0, np.nan, 30.0, np.nan],
}
),
)


def test_extract_features_with_different_datetime_parsing_options(df_datetime):
X = DatetimeFeatures(
features_to_extract=["day_of_month"], dayfirst=True
Expand Down