CLN: Clean _test_moments_consistency in common.py (#30577)

Author: charlesdong1991

pandas/tests/window/common.py

@@ -212,40 +212,23 @@ def _create_data(self):
  super()._create_data()
  self.data = _consistency_data
 
- def _test_moments_consistency(
- self,
- min_periods,
- count,
- mean,
- mock_mean,
- corr,
- var_unbiased=None,
- std_unbiased=None,
- cov_unbiased=None,
- var_biased=None,
- std_biased=None,
- cov_biased=None,
- var_debiasing_factors=None,
- ):
- def _non_null_values(x):
- values = x.values.ravel()
- return set(values[notna(values)].tolist())
-
+ def _test_moments_consistency_mock_mean(self, mean, mock_mean):
  for (x, is_constant, no_nans) in self.data:
- count_x = count(x)
  mean_x = mean(x)
+ # check that correlation of a series with itself is either 1 or NaN
 
  if mock_mean:
  # check that mean equals mock_mean
  expected = mock_mean(x)
  tm.assert_equal(mean_x, expected.astype("float64"))
 
+ def _test_moments_consistency_is_constant(self, min_periods, count, mean, corr):
+ for (x, is_constant, no_nans) in self.data:
+ count_x = count(x)
+ mean_x = mean(x)
  # check that correlation of a series with itself is either 1 or NaN
  corr_x_x = corr(x, x)
 
- # assert _non_null_values(corr_x_x).issubset(set([1.]))
- # restore once rolling_cov(x, x) is identically equal to var(x)
-
  if is_constant:
  exp = x.max() if isinstance(x, Series) else x.max().max()
 
@@ -258,13 +241,35 @@ def _non_null_values(x):
  expected[:] = np.nan
  tm.assert_equal(corr_x_x, expected)
 
+ def _test_moments_consistency_var_debiasing_factors(
+ self, var_biased=None, var_unbiased=None, var_debiasing_factors=None
+ ):
+ for (x, is_constant, no_nans) in self.data:
  if var_unbiased and var_biased and var_debiasing_factors:
  # check variance debiasing factors
  var_unbiased_x = var_unbiased(x)
  var_biased_x = var_biased(x)
  var_debiasing_factors_x = var_debiasing_factors(x)
  tm.assert_equal(var_unbiased_x, var_biased_x * var_debiasing_factors_x)
 
+ def _test_moments_consistency(
+ self,
+ min_periods,
+ count,
+ mean,
+ corr,
+ var_unbiased=None,
+ std_unbiased=None,
+ cov_unbiased=None,
+ var_biased=None,
+ std_biased=None,
+ cov_biased=None,
+ ):
+
+ for (x, is_constant, no_nans) in self.data:
+ count_x = count(x)
+ mean_x = mean(x)
+
  for (std, var, cov) in [
  (std_biased, var_biased, cov_biased),
  (std_unbiased, var_unbiased, cov_unbiased),

pandas/tests/window/moments/test_moments_ewm.py

@@ -379,16 +379,50 @@ def _ewma(s, com, min_periods, adjust, ignore_na):
  return result
 
  com = 3.0
+ self._test_moments_consistency_mock_mean(
+ mean=lambda x: x.ewm(
+ com=com, min_periods=min_periods, adjust=adjust, ignore_na=ignore_na
+ ).mean(),
+ mock_mean=lambda x: _ewma(
+ x, com=com, min_periods=min_periods, adjust=adjust, ignore_na=ignore_na
+ ),
+ )
+
+ self._test_moments_consistency_is_constant(
+ min_periods=min_periods,
+ count=lambda x: x.expanding().count(),
+ mean=lambda x: x.ewm(
+ com=com, min_periods=min_periods, adjust=adjust, ignore_na=ignore_na
+ ).mean(),
+ corr=lambda x, y: x.ewm(
+ com=com, min_periods=min_periods, adjust=adjust, ignore_na=ignore_na
+ ).corr(y),
+ )
+
+ self._test_moments_consistency_var_debiasing_factors(
+ var_unbiased=lambda x: (
+ x.ewm(
+ com=com, min_periods=min_periods, adjust=adjust, ignore_na=ignore_na
+ ).var(bias=False)
+ ),
+ var_biased=lambda x: (
+ x.ewm(
+ com=com, min_periods=min_periods, adjust=adjust, ignore_na=ignore_na
+ ).var(bias=True)
+ ),
+ var_debiasing_factors=lambda x: (
+ _variance_debiasing_factors(
+ x, com=com, adjust=adjust, ignore_na=ignore_na
+ )
+ ),
+ )
  # test consistency between different ewm* moments
  self._test_moments_consistency(
  min_periods=min_periods,
  count=lambda x: x.expanding().count(),
  mean=lambda x: x.ewm(
  com=com, min_periods=min_periods, adjust=adjust, ignore_na=ignore_na
  ).mean(),
- mock_mean=lambda x: _ewma(
- x, com=com, min_periods=min_periods, adjust=adjust, ignore_na=ignore_na
- ),
  corr=lambda x, y: x.ewm(
  com=com, min_periods=min_periods, adjust=adjust, ignore_na=ignore_na
  ).corr(y),
@@ -420,9 +454,4 @@ def _ewma(s, com, min_periods, adjust, ignore_na):
  com=com, min_periods=min_periods, adjust=adjust, ignore_na=ignore_na
  ).cov(y, bias=True)
  ),
- var_debiasing_factors=lambda x: (
- _variance_debiasing_factors(
- x, com=com, adjust=adjust, ignore_na=ignore_na
- )
- ),
  )

pandas/tests/window/moments/test_moments_expanding.py

@@ -328,12 +328,31 @@ def test_expanding_consistency(self, min_periods):
  )
 
  # test consistency between different expanding_* moments
+ self._test_moments_consistency_mock_mean(
+ mean=lambda x: x.expanding(min_periods=min_periods).mean(),
+ mock_mean=lambda x: x.expanding(min_periods=min_periods).sum()
+ / x.expanding().count(),
+ )
+
+ self._test_moments_consistency_is_constant(
+ min_periods=min_periods,
+ count=lambda x: x.expanding().count(),
+ mean=lambda x: x.expanding(min_periods=min_periods).mean(),
+ corr=lambda x, y: x.expanding(min_periods=min_periods).corr(y),
+ )
+
+ self._test_moments_consistency_var_debiasing_factors(
+ var_unbiased=lambda x: x.expanding(min_periods=min_periods).var(),
+ var_biased=lambda x: x.expanding(min_periods=min_periods).var(ddof=0),
+ var_debiasing_factors=lambda x: (
+ x.expanding().count()
+ / (x.expanding().count() - 1.0).replace(0.0, np.nan)
+ ),
+ )
  self._test_moments_consistency(
  min_periods=min_periods,
  count=lambda x: x.expanding().count(),
  mean=lambda x: x.expanding(min_periods=min_periods).mean(),
- mock_mean=lambda x: x.expanding(min_periods=min_periods).sum()
- / x.expanding().count(),
  corr=lambda x, y: x.expanding(min_periods=min_periods).corr(y),
  var_unbiased=lambda x: x.expanding(min_periods=min_periods).var(),
  std_unbiased=lambda x: x.expanding(min_periods=min_periods).std(),
@@ -343,10 +362,6 @@ def test_expanding_consistency(self, min_periods):
  cov_biased=lambda x, y: x.expanding(min_periods=min_periods).cov(
  y, ddof=0
  ),
- var_debiasing_factors=lambda x: (
- x.expanding().count()
- / (x.expanding().count() - 1.0).replace(0.0, np.nan)
- ),
  )
 
  # test consistency between expanding_xyz() and either (a)

pandas/tests/window/moments/test_moments_rolling.py

@@ -945,9 +945,7 @@ def test_rolling_consistency(self, window, min_periods, center):
  )
 
  # test consistency between different rolling_* moments
- self._test_moments_consistency(
- min_periods=min_periods,
- count=lambda x: (x.rolling(window=window, center=center).count()),
+ self._test_moments_consistency_mock_mean(
  mean=lambda x: (
  x.rolling(
  window=window, min_periods=min_periods, center=center
@@ -962,6 +960,53 @@ def test_rolling_consistency(self, window, min_periods, center):
  ).count()
  )
  ),
+ )
+
+ self._test_moments_consistency_is_constant(
+ min_periods=min_periods,
+ count=lambda x: (x.rolling(window=window, center=center).count()),
+ mean=lambda x: (
+ x.rolling(
+ window=window, min_periods=min_periods, center=center
+ ).mean()
+ ),
+ corr=lambda x, y: (
+ x.rolling(
+ window=window, min_periods=min_periods, center=center
+ ).corr(y)
+ ),
+ )
+
+ self._test_moments_consistency_var_debiasing_factors(
+ var_unbiased=lambda x: (
+ x.rolling(
+ window=window, min_periods=min_periods, center=center
+ ).var()
+ ),
+ var_biased=lambda x: (
+ x.rolling(
+ window=window, min_periods=min_periods, center=center
+ ).var(ddof=0)
+ ),
+ var_debiasing_factors=lambda x: (
+ x.rolling(window=window, center=center)
+ .count()
+ .divide(
+ (x.rolling(window=window, center=center).count() - 1.0).replace(
+ 0.0, np.nan
+ )
+ )
+ ),
+ )
+
+ self._test_moments_consistency(
+ min_periods=min_periods,
+ count=lambda x: (x.rolling(window=window, center=center).count()),
+ mean=lambda x: (
+ x.rolling(
+ window=window, min_periods=min_periods, center=center
+ ).mean()
+ ),
  corr=lambda x, y: (
  x.rolling(
  window=window, min_periods=min_periods, center=center
@@ -997,15 +1042,6 @@ def test_rolling_consistency(self, window, min_periods, center):
  window=window, min_periods=min_periods, center=center
  ).cov(y, ddof=0)
  ),
- var_debiasing_factors=lambda x: (
- x.rolling(window=window, center=center)
- .count()
- .divide(
- (x.rolling(window=window, center=center).count() - 1.0).replace(
- 0.0, np.nan
- )
- )
- ),
  )
 
  # test consistency between rolling_xyz() and either (a)