def test_stale_values_diff_handles_negatives(data_with_negatives):
"""stale_values_diff works with negative values.
Notes
-----
Copyright (c) 2019 SolarArbiter. See the file
LICENSES/SOLARFORECASTARBITER_LICENSE at the top level directory
of this distribution and at `<https://github.com/pvlib/
pvanalytics/blob/master/LICENSES/SOLARFORECASTARBITER_LICENSE>`_
for more information.
"""
res = gaps.stale_values_diff(data_with_negatives, window=3, mark='end')
assert_series_equal(
res, pd.Series([False, False, True, True, False, False, False]))
res = gaps.stale_values_diff(data_with_negatives,
window=3,
atol=1e-3,
mark='end')
assert_series_equal(
res, pd.Series([False, False, True, True, True, True, True]))
res = gaps.stale_values_diff(data_with_negatives,
window=3,
atol=1e-5,
mark='end')
assert_series_equal(
res, pd.Series([False, False, True, True, True, False, False]))
res = gaps.stale_values_diff(data_with_negatives,
window=3,
atol=2e-5,
mark='end')
assert_series_equal(
res, pd.Series([False, False, True, True, True, True, True]))
def test_stale_values_diff_raises_error(stale_data):
"""stale_values_diff raises a ValueError for 'window' < 2.
Notes
-----
Copyright (c) 2019 SolarArbiter. See the file
LICENSES/SOLARFORECASTARBITER_LICENSE at the top level directory
of this distribution and at `<https://github.com/pvlib/
pvanalytics/blob/master/LICENSES/SOLARFORECASTARBITER_LICENSE>`_
for more information.
"""
with pytest.raises(ValueError):
gaps.stale_values_diff(stale_data, window=1)
def test_stale_values_diff_mark_tail(stale_data):
"""When mark='tail' (the default), every point in the window except
the first is marked stale."""
assert_series_equal(
pd.Series(
[False, False, True, True, True, True, True, True, False, False]),
gaps.stale_values_diff(stale_data, window=4))
def test_stale_values_diff(stale_data):
"""stale_values_diff properly identifies stuck values.
Notes
-----
Copyright (c) 2019 SolarArbiter. See the file
LICENSES/SOLARFORECASTARBITER_LICENSE at the top level directory
of this distribution and at `<https://github.com/pvlib/
pvanalytics/blob/master/LICENSES/SOLARFORECASTARBITER_LICENSE>`_
for more information.
"""
res0 = gaps.stale_values_diff(stale_data, mark='end')
res1 = gaps.stale_values_diff(stale_data, window=3, mark='end')
res2 = gaps.stale_values_diff(stale_data, rtol=1e-8, window=2, mark='end')
res3 = gaps.stale_values_diff(stale_data, window=7, mark='end')
res4 = gaps.stale_values_diff(stale_data, window=8, mark='end')
res5 = gaps.stale_values_diff(stale_data, rtol=1e-8, window=4, mark='end')
res6 = gaps.stale_values_diff(stale_data[1:], window=3, mark='end')
res7 = gaps.stale_values_diff(stale_data[1:8], window=3, mark='end')
assert_series_equal(
res0,
pd.Series([
False, False, False, False, False, False, True, True, False, False
]))
assert_series_equal(
res1,
pd.Series(
[False, False, False, True, True, True, True, True, False, False]))
assert_series_equal(
res2,
pd.Series(
[False, False, True, True, True, False, False, True, False,
False]))
assert_series_equal(
res3,
pd.Series([
False, False, False, False, False, False, False, True, False, False
]))
assert not all(res4)
assert_series_equal(
res5,
pd.Series([
False, False, False, False, True, False, False, False, False, False
]))
assert_series_equal(
res6,
pd.Series(
index=stale_data[1:].index,
data=[False, False, True, True, True, True, True, False, False]))
assert_series_equal(
res7,
pd.Series(index=stale_data[1:8].index,
data=[False, False, True, True, True, True, True]))
data['value_normalized'].plot()
data.loc[data["stale_data_mask"], "value_normalized"].plot(ls='', marker='.')
plt.legend(labels=["AC Power", "Inserted Stale Data"])
plt.xlabel("Date")
plt.ylabel("Normalized AC Power")
plt.tight_layout()
plt.show()
# %%
# Now, we use :py:func:`pvanalytics.quality.gaps.stale_values_diff` to
# identify stale values in data. We visualize the detected stale periods
# graphically. Please note that nighttime periods generally contain consecutive
# repeating 0 values, which are flagged by
# :py:func:`pvanalytics.quality.gaps.stale_values_diff`.
stale_data_mask = gaps.stale_values_diff(data['value_normalized'])
data['value_normalized'].plot()
data.loc[stale_data_mask, "value_normalized"].plot(ls='', marker='.')
plt.legend(labels=["AC Power", "Detected Stale Data"])
plt.xlabel("Date")
plt.ylabel("Normalized AC Power")
plt.tight_layout()
plt.show()
# %%
# Now, we use :py:func:`pvanalytics.quality.gaps.stale_values_round` to
# identify stale values in data, using rounded data. This function yields
# similar results as :py:func:`pvanalytics.quality.gaps.stale_values_diff`,
# except it looks for consecutive repeating data that has been rounded to
# a settable decimals place.
# Please note that nighttime periods generally
def test_stale_values_diff_mark_all(stale_data):
"""When mark='all' the full window is marked stale"""
assert_series_equal(
pd.Series(
[False, True, True, True, True, True, True, True, False, False]),
gaps.stale_values_diff(stale_data, window=4, mark='all'))
def test_stale_values_diff_raises_error_for_bad_mark(stale_data):
"""Passing mark not in ['all', 'end', 'tail'] raises a ValueError."""
with pytest.raises(ValueError):
gaps.stale_values_diff(stale_data, mark='head')