Skip to content

CLN: Use more pytest idioms in test_momemts_ewm.py #36801

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 2 commits into from
Oct 2, 2020
Merged

CLN: Use more pytest idioms in test_momemts_ewm.py #36801

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
24ac32f
CLN: Use more pytest idioms in test_momemts_ewm.py
Oct 2, 2020
1bab68e
Address comments
Oct 2, 2020
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
195 changes: 144 additions & 51 deletions pandas/tests/window/moments/test_moments_ewm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,21 +7,15 @@
import pandas._testing as tm


def check_ew(name=None, preserve_nan=False, series=None, frame=None, nan_locs=None):
series_result = getattr(series.ewm(com=10), name)()
def test_ewma(series, frame):
series_result = series.ewm(com=10).mean()
assert isinstance(series_result, Series)

frame_result = getattr(frame.ewm(com=10), name)()
frame_result = frame.ewm(com=10).mean()
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

rather than a test use two fixtures independently, could have a test_ewma_series and test_ewma_frame

assert type(frame_result) == DataFrame

result = getattr(series.ewm(com=10), name)()
if preserve_nan:
assert result[nan_locs].isna().all()


def test_ewma(series, frame, nan_locs):
check_ew(name="mean", frame=frame, series=series, nan_locs=nan_locs)

def test_ewma_adjust():
vals = pd.Series(np.zeros(1000))
vals[5] = 1
result = vals.ewm(span=100, adjust=False).mean().sum()
Expand Down Expand Up @@ -53,63 +47,162 @@ def test_ewma_nan_handling():
result = s.ewm(com=5).mean()
tm.assert_series_equal(result, Series([np.nan] * 2 + [1.0] * 4))

# GH 7603
s0 = Series([np.nan, 1.0, 101.0])
s1 = Series([1.0, np.nan, 101.0])
s2 = Series([np.nan, 1.0, np.nan, np.nan, 101.0, np.nan])
s3 = Series([1.0, np.nan, 101.0, 50.0])
com = 2.0
alpha = 1.0 / (1.0 + com)

def simple_wma(s, w):
return (s.multiply(w).cumsum() / w.cumsum()).fillna(method="ffill")

for (s, adjust, ignore_na, w) in [
(s0, True, False, [np.nan, (1.0 - alpha), 1.0]),
(s0, True, True, [np.nan, (1.0 - alpha), 1.0]),
(s0, False, False, [np.nan, (1.0 - alpha), alpha]),
(s0, False, True, [np.nan, (1.0 - alpha), alpha]),
(s1, True, False, [(1.0 - alpha) ** 2, np.nan, 1.0]),
(s1, True, True, [(1.0 - alpha), np.nan, 1.0]),
(s1, False, False, [(1.0 - alpha) ** 2, np.nan, alpha]),
(s1, False, True, [(1.0 - alpha), np.nan, alpha]),
(s2, True, False, [np.nan, (1.0 - alpha) ** 3, np.nan, np.nan, 1.0, np.nan]),
(s2, True, True, [np.nan, (1.0 - alpha), np.nan, np.nan, 1.0, np.nan]),
Copy link
Member

@simonjayhawkins simonjayhawkins Oct 2, 2020 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

i'm not sure that the parameterisation is clearer.

maybe parameterise s, adjust and ignore_na independently (maybe with fixtures) and create a w fixture with a dictionary lookup. i.e. pass s, adjust and ignore_na to w fixture

maybe use a class just for namespacing and use class level fixtures.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'll consider doing this change in a follow up PR. The main motivation with this pass is to ensure that parameterized test failures are more easily visible within pytest


@pytest.mark.parametrize(
"s, adjust, ignore_na, w",
[
(
Series([np.nan, 1.0, 101.0]),
True,
False,
[np.nan, (1.0 - (1.0 / (1.0 + 2.0))), 1.0],
),
(
Series([np.nan, 1.0, 101.0]),
True,
True,
[np.nan, (1.0 - (1.0 / (1.0 + 2.0))), 1.0],
),
(
Series([np.nan, 1.0, 101.0]),
False,
False,
[np.nan, (1.0 - (1.0 / (1.0 + 2.0))), (1.0 / (1.0 + 2.0))],
),
(
Series([np.nan, 1.0, 101.0]),
False,
True,
[np.nan, (1.0 - (1.0 / (1.0 + 2.0))), (1.0 / (1.0 + 2.0))],
),
(
Series([1.0, np.nan, 101.0]),
True,
False,
[(1.0 - (1.0 / (1.0 + 2.0))) ** 2, np.nan, 1.0],
),
(
s2,
Series([1.0, np.nan, 101.0]),
True,
True,
[(1.0 - (1.0 / (1.0 + 2.0))), np.nan, 1.0],
),
(
Series([1.0, np.nan, 101.0]),
False,
False,
[np.nan, (1.0 - alpha) ** 3, np.nan, np.nan, alpha, np.nan],
[(1.0 - (1.0 / (1.0 + 2.0))) ** 2, np.nan, (1.0 / (1.0 + 2.0))],
),
(s2, False, True, [np.nan, (1.0 - alpha), np.nan, np.nan, alpha, np.nan]),
(s3, True, False, [(1.0 - alpha) ** 3, np.nan, (1.0 - alpha), 1.0]),
(s3, True, True, [(1.0 - alpha) ** 2, np.nan, (1.0 - alpha), 1.0]),
(
s3,
Series([1.0, np.nan, 101.0]),
False,
True,
[(1.0 - (1.0 / (1.0 + 2.0))), np.nan, (1.0 / (1.0 + 2.0))],
),
(
Series([np.nan, 1.0, np.nan, np.nan, 101.0, np.nan]),
True,
False,
[np.nan, (1.0 - (1.0 / (1.0 + 2.0))) ** 3, np.nan, np.nan, 1.0, np.nan],
),
(
Series([np.nan, 1.0, np.nan, np.nan, 101.0, np.nan]),
True,
True,
[np.nan, (1.0 - (1.0 / (1.0 + 2.0))), np.nan, np.nan, 1.0, np.nan],
),
(
Series([np.nan, 1.0, np.nan, np.nan, 101.0, np.nan]),
False,
False,
[
(1.0 - alpha) ** 3,
np.nan,
(1.0 - alpha) * alpha,
alpha * ((1.0 - alpha) ** 2 + alpha),
(1.0 - (1.0 / (1.0 + 2.0))) ** 3,
np.nan,
np.nan,
(1.0 / (1.0 + 2.0)),
np.nan,
],
),
(s3, False, True, [(1.0 - alpha) ** 2, np.nan, (1.0 - alpha) * alpha, alpha]),
]:
expected = simple_wma(s, Series(w))
result = s.ewm(com=com, adjust=adjust, ignore_na=ignore_na).mean()
(
Series([np.nan, 1.0, np.nan, np.nan, 101.0, np.nan]),
False,
True,
[
np.nan,
(1.0 - (1.0 / (1.0 + 2.0))),
np.nan,
np.nan,
(1.0 / (1.0 + 2.0)),
np.nan,
],
),
(
Series([1.0, np.nan, 101.0, 50.0]),
True,
False,
[
(1.0 - (1.0 / (1.0 + 2.0))) ** 3,
np.nan,
(1.0 - (1.0 / (1.0 + 2.0))),
1.0,
],
),
(
Series([1.0, np.nan, 101.0, 50.0]),
True,
True,
[
(1.0 - (1.0 / (1.0 + 2.0))) ** 2,
np.nan,
(1.0 - (1.0 / (1.0 + 2.0))),
1.0,
],
),
(
Series([1.0, np.nan, 101.0, 50.0]),
False,
False,
[
(1.0 - (1.0 / (1.0 + 2.0))) ** 3,
np.nan,
(1.0 - (1.0 / (1.0 + 2.0))) * (1.0 / (1.0 + 2.0)),
(1.0 / (1.0 + 2.0))
* ((1.0 - (1.0 / (1.0 + 2.0))) ** 2 + (1.0 / (1.0 + 2.0))),
],
),
(
Series([1.0, np.nan, 101.0, 50.0]),
False,
True,
[
(1.0 - (1.0 / (1.0 + 2.0))) ** 2,
np.nan,
(1.0 - (1.0 / (1.0 + 2.0))) * (1.0 / (1.0 + 2.0)),
(1.0 / (1.0 + 2.0)),
],
),
],
)
def test_ewma_nan_handling_cases(s, adjust, ignore_na, w):
# GH 7603
expected = (s.multiply(w).cumsum() / Series(w).cumsum()).fillna(method="ffill")
result = s.ewm(com=2.0, adjust=adjust, ignore_na=ignore_na).mean()

tm.assert_series_equal(result, expected)
if ignore_na is False:
# check that ignore_na defaults to False
result = s.ewm(com=2.0, adjust=adjust).mean()
tm.assert_series_equal(result, expected)
if ignore_na is False:
# check that ignore_na defaults to False
result = s.ewm(com=com, adjust=adjust).mean()
tm.assert_series_equal(result, expected)


@pytest.mark.parametrize("name", ["var", "vol"])
def test_ewmvar_ewmvol(series, frame, nan_locs, name):
check_ew(name=name, frame=frame, series=series, nan_locs=nan_locs)
def test_ewmvar_ewmvol(series, frame, name):
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can this be combined with test_ewma

series_result = getattr(series.ewm(com=10), name)()
assert isinstance(series_result, Series)

frame_result = getattr(frame.ewm(com=10), name)()
assert type(frame_result) == DataFrame
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why not isinstance?



def test_ewma_span_com_args(series):
Expand Down