def calculate_test_positivity(positive_tests: pd.Series,
negative_tests: pd.Series,
smooth: int = 7,
lag_lookback: int = 7) -> pd.Series:
"""Calculates positive test rate.
Args:
positive_tests: Number of cumulative positive tests.
negative_tests: Number of cumulative negative tests.
Returns:
Positive test rate.
"""
daily_negative_tests = negative_tests.diff()
daily_positive_tests = positive_tests.diff()
positive_smoothed = series_utils.smooth_with_rolling_average(
daily_positive_tests)
negative_smoothed = series_utils.smooth_with_rolling_average(
daily_negative_tests, include_trailing_zeros=False)
last_n_positive = positive_smoothed[-lag_lookback:]
last_n_negative = negative_smoothed[-lag_lookback:]
if any(last_n_positive) and last_n_negative.isna().all():
return pd.Series([], dtype="float64")
return positive_smoothed / (negative_smoothed + positive_smoothed)
def calculate_test_positivity(
region_dataset: OneRegionTimeseriesDataset, lag_lookback: int = 7
) -> pd.Series:
"""Calculates positive test rate from combined data."""
data = region_dataset.date_indexed
positive_tests = series_utils.interpolate_stalled_and_missing_values(
data[CommonFields.POSITIVE_TESTS]
)
negative_tests = series_utils.interpolate_stalled_and_missing_values(
data[CommonFields.NEGATIVE_TESTS]
)
daily_negative_tests = negative_tests.diff()
daily_positive_tests = positive_tests.diff()
positive_smoothed = series_utils.smooth_with_rolling_average(daily_positive_tests)
negative_smoothed = series_utils.smooth_with_rolling_average(
daily_negative_tests, include_trailing_zeros=False
)
last_n_positive = positive_smoothed[-lag_lookback:]
last_n_negative = negative_smoothed[-lag_lookback:]
if any(last_n_positive) and last_n_negative.isna().all():
return pd.Series([], dtype="float64")
return positive_smoothed / (negative_smoothed + positive_smoothed)
def test_window_exceeds_series():
"""
It should not average the first value.
"""
series = _series_with_date_index([1, 2])
smoothed = series_utils.smooth_with_rolling_average(series=series,
window=5)
pd.testing.assert_series_equal(smoothed, _series_with_date_index([1, 1.5]))
def test_exclude_trailing_zeroes():
"""
It should not average the first value.
"""
series = _series_with_date_index([1, 2, 4, 5, 0])
smoothed = series_utils.smooth_with_rolling_average(
series=series, window=2, include_trailing_zeros=False)
pd.testing.assert_series_equal(
smoothed, _series_with_date_index([1, 1.5, 3, 4.5, np.nan]))
def test_sliding_window():
"""
It should average within sliding window.
"""
series = _series_with_date_index([1, 2, 4, 5, 0])
smoothed = series_utils.smooth_with_rolling_average(series=series,
window=2)
pd.testing.assert_series_equal(
smoothed, _series_with_date_index([1, 1.5, 3, 4.5, 2.5]))
def _calculate_smoothed_daily_cases(new_cases: pd.Series, smooth: int = 7):
if new_cases.first_valid_index() is None:
return new_cases
new_cases = new_cases.copy()
# Front filling all cases with 0s. We're assuming all regions are accurately
# reporting the first day a new case occurs. This will affect the first few cases
# in a timeseries, because it's smoothing over a full period, rather than just the first
# couple days of reported data.
new_cases[:new_cases.first_valid_index() - timedelta(days=1)] = 0
smoothed = series_utils.smooth_with_rolling_average(new_cases,
window=smooth)
return smoothed