Skip to content

BUG: rolling_* functions should not shrink window #7766

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

Closed
wants to merge 1 commit into from
Closed

BUG: rolling_* functions should not shrink window #7766

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
24 changes: 24 additions & 0 deletions doc/source/v0.15.0.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,30 @@ API changes

- Raise a ``ValueError`` in ``df.to_hdf`` with 'fixed' format, if ``df`` has non-unique columns as the resulting file will be broken (:issue:`7761`)

- :func:`rolling_min`, :func:`rolling_max`, :func:`rolling_cov`, and :func:`rolling_corr`
now return objects with all ``NaN``s when ``len(arg) < min_periods <= window``
(like all other rolling functions do) rather than producing an error message. (:issue:`7766`)
For example, this is the old behavior:
.. ipython:: python
In [14]: s = Series([10, 11, 12, 13])

In [15]: rolling_min(s, window=10, min_periods=5)
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-15-f622819d7987> in <module>()
----> 1 rolling_min(s, window=10, min_periods=5)
...
ValueError: min_periods (5) must be <= window (4)
whereas this is the new behavior:
.. ipython:: python
In [16]: rolling_min(s, window=10, min_periods=5)
Out[16]:
0 NaN
1 NaN
2 NaN
3 NaN
dtype: float64

.. _whatsnew_0150.cat:

Categoricals in Series/DataFrame
Expand Down
4 changes: 0 additions & 4 deletions pandas/algos.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1551,8 +1551,6 @@ def roll_max2(ndarray[float64_t] a, int window, int minp):

minp = _check_minp(window, minp, n0)

window = min(window, n0)

ring = <pairs*>stdlib.malloc(window * sizeof(pairs))
end = ring + window
last = ring
Expand Down Expand Up @@ -1650,8 +1648,6 @@ def roll_min2(np.ndarray[np.float64_t, ndim=1] a, int window, int minp):
raise ValueError('Invalid min_periods size %d greater than window %d'
% (minp, window))

window = min(window, n0)

minp = _check_minp(window, minp, n0)

ring = <pairs*>stdlib.malloc(window * sizeof(pairs))
Expand Down
12 changes: 5 additions & 7 deletions pandas/stats/moments.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -211,9 +211,8 @@ def rolling_cov(arg1, arg2=None, window=None, min_periods=None, freq=None,
arg2 = _conv_timerule(arg2, freq, how)

def _get_cov(X, Y):
adj_window = min(window, len(X), len(Y))
mean = lambda x: rolling_mean(x, adj_window, min_periods, center=center)
count = rolling_count(X + Y, adj_window, center=center)
mean = lambda x: rolling_mean(x, window, min_periods, center=center)
count = rolling_count(X + Y, window, center=center)
bias_adj = count / (count - 1)
return (mean(X * Y) - mean(X) * mean(Y)) * bias_adj
rs = _flex_binary_moment(arg1, arg2, _get_cov, pairwise=bool(pairwise))
Expand All @@ -236,12 +235,11 @@ def rolling_corr(arg1, arg2=None, window=None, min_periods=None, freq=None,
arg2 = _conv_timerule(arg2, freq, how)

def _get_corr(a, b):
adj_window = min(window, len(a), len(b))
num = rolling_cov(a, b, adj_window, min_periods, freq=freq,
num = rolling_cov(a, b, window, min_periods, freq=freq,
center=center)
den = (rolling_std(a, adj_window, min_periods, freq=freq,
den = (rolling_std(a, window, min_periods, freq=freq,
center=center) *
rolling_std(b, adj_window, min_periods, freq=freq,
rolling_std(b, window, min_periods, freq=freq,
center=center))
return num / den

Expand Down
44 changes: 42 additions & 2 deletions pandas/stats/tests/test_moments.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,9 +6,9 @@
from numpy.random import randn
import numpy as np

from pandas import Series, DataFrame, bdate_range, isnull, notnull
from pandas import Series, DataFrame, Panel, bdate_range, isnull, notnull
from pandas.util.testing import (
assert_almost_equal, assert_series_equal, assert_frame_equal
assert_almost_equal, assert_series_equal, assert_frame_equal, assert_panel_equal
)
import pandas.core.datetools as datetools
import pandas.stats.moments as mom
Expand Down Expand Up @@ -841,6 +841,46 @@ def test_rolling_corr_diff_length(self):
result = mom.rolling_corr(s1, s2a, window=3, min_periods=2)
assert_series_equal(result, expected)

def test_rolling_functions_window_non_shrinkage(self):
# GH 7764
s = Series(range(4))
s_expected = Series(np.nan, index=s.index)
df = DataFrame([[1,5], [3, 2], [3,9], [-1,0]], columns=['A','B'])
df_expected = DataFrame(np.nan, index=df.index, columns=df.columns)
df_expected_panel = Panel(items=df.index, major_axis=df.columns, minor_axis=df.columns)

functions = [lambda x: mom.rolling_cov(x, x, pairwise=False, window=10, min_periods=5),
lambda x: mom.rolling_corr(x, x, pairwise=False, window=10, min_periods=5),
lambda x: mom.rolling_max(x, window=10, min_periods=5),
lambda x: mom.rolling_min(x, window=10, min_periods=5),
lambda x: mom.rolling_sum(x, window=10, min_periods=5),
lambda x: mom.rolling_mean(x, window=10, min_periods=5),
lambda x: mom.rolling_std(x, window=10, min_periods=5),
lambda x: mom.rolling_var(x, window=10, min_periods=5),
lambda x: mom.rolling_skew(x, window=10, min_periods=5),
lambda x: mom.rolling_kurt(x, window=10, min_periods=5),
lambda x: mom.rolling_quantile(x, quantile=0.5, window=10, min_periods=5),
lambda x: mom.rolling_median(x, window=10, min_periods=5),
lambda x: mom.rolling_apply(x, func=sum, window=10, min_periods=5),
lambda x: mom.rolling_window(x, win_type='boxcar', window=10, min_periods=5),
]
for f in functions:
s_result = f(s)
assert_series_equal(s_result, s_expected)

df_result = f(df)
assert_frame_equal(df_result, df_expected)

functions = [lambda x: mom.rolling_cov(x, x, pairwise=True, window=10, min_periods=5),
lambda x: mom.rolling_corr(x, x, pairwise=True, window=10, min_periods=5),
# rolling_corr_pairwise is depracated, so the following line should be deleted
# when rolling_corr_pairwise is removed.
lambda x: mom.rolling_corr_pairwise(x, x, window=10, min_periods=5),
]
for f in functions:
df_result_panel = f(df)
assert_panel_equal(df_result_panel, df_expected_panel)

def test_expanding_cov_pairwise_diff_length(self):
# GH 7512
df1 = DataFrame([[1,5], [3, 2], [3,9]], columns=['A','B'])
Expand Down