def test_corr(self):
"""Test function corr"""
np.random.seed(123)
mean, cov = [4, 6], [(1, .6), (.6, 1)]
x, y = np.random.multivariate_normal(mean, cov, 30).T
x[3], y[5] = 12, -8
corr(x, y, method='pearson', tail='one-sided')
corr(x, y, method='spearman', tail='two-sided')
corr(x, y, method='kendall')
corr(x, y, method='shepherd', tail='two-sided')
# Compare with robust corr toolbox
stats = corr(x, y, method='skipped')
assert np.round(stats['r'].to_numpy(), 3) == 0.512
assert stats['outliers'].to_numpy() == 2
# Changing the method using kwargs
sk_sp = corr(x, y, method='skipped', corr_type='spearman')
sk_pe = corr(x, y, method='skipped', corr_type='pearson')
assert not sk_sp.equals(sk_pe)
stats = corr(x, y, method='shepherd')
assert stats['outliers'].to_numpy() == 2
_, _, outliers = skipped(x, y, corr_type='pearson')
assert outliers.size == x.size
assert stats['n'].to_numpy() == 30
stats = corr(x, y, method='percbend')
assert np.round(stats['r'].to_numpy(), 3) == 0.484
# Compare biweight correlation to astropy
stats = corr(x, y, method='bicor')
assert np.isclose(stats['r'].to_numpy(), 0.4951417784979)
# Changing the value of C using kwargs
stats = corr(x, y, method='bicor', c=5)
assert np.isclose(stats['r'].to_numpy(), 0.4940706950017)
# Not normally distributed
z = np.random.uniform(size=30)
corr(x, z, method='pearson')
# With NaN values
x[3] = np.nan
corr(x, y)
# With the same array
# Disabled because of AppVeyor failure
# assert corr(x, x).loc['pearson', 'BF10'] == str(np.inf)
# Wrong argument
with pytest.raises(ValueError):
corr(x, y, method='error')
# Compare BF10 with JASP
df = read_dataset('pairwise_corr')
stats = corr(df['Neuroticism'], df['Extraversion'])
assert np.isclose(1 / float(stats['BF10'].to_numpy()), 1.478e-13)
# When one column is a constant, the correlation is not defined
# and Pingouin return a DataFrame full of NaN, except for ``n``
x, y = [1, 1, 1], [1, 2, 3]
stats = corr(x, y)
assert stats.at['pearson', 'n']
assert np.isnan(stats.at['pearson', 'r'])
# Biweight midcorrelation returns NaN when MAD is not defined
assert np.isnan(bicor(np.array([1, 1, 1, 1, 0, 1]), np.arange(6))[0])
def test_corr(self):
"""Test function corr
Compare to R `correlation` package. See test_correlation.R file.
"""
np.random.seed(123)
mean, cov = [4, 6], [(1, .6), (.6, 1)]
x, y = np.random.multivariate_normal(mean, cov, 30).T
x2, y2 = x.copy(), y.copy()
x[3], y[5] = 12, -8
x2[3], y2[5] = 7, 2.6
# Pearson correlation
stats = corr(x, y, method='pearson')
assert np.isclose(stats.loc['pearson', 'r'], 0.1761221)
assert np.isclose(stats.loc['pearson', 'p-val'], 0.3518659)
assert stats.loc['pearson', 'CI95%'][0] == round(-0.1966232, 2)
assert stats.loc['pearson', 'CI95%'][1] == round(0.5043872, 2)
# - One-sided: greater
stats = corr(x, y, method='pearson', alternative='greater')
assert np.isclose(stats.loc['pearson', 'r'], 0.1761221)
assert np.isclose(stats.loc['pearson', 'p-val'], 0.175933)
assert stats.loc['pearson', 'CI95%'][0] == round(-0.1376942, 2)
assert stats.loc['pearson', 'CI95%'][1] == 1
# - One-sided: less
stats = corr(x, y, method='pearson', alternative='less')
assert np.isclose(stats.loc['pearson', 'r'], 0.1761221)
assert np.isclose(stats.loc['pearson', 'p-val'], 0.824067)
assert stats.loc['pearson', 'CI95%'][0] == -1
assert stats.loc['pearson', 'CI95%'][1] == round(0.4578044, 2)
# Spearman correlation
stats = corr(x, y, method='spearman')
assert np.isclose(stats.loc['spearman', 'r'], 0.4740823)
assert np.isclose(stats.loc['spearman', 'p-val'], 0.008129768)
# CI are calculated using a different formula for Spearman in R
# assert stats.loc['spearman', 'CI95%'][0] == round(0.1262988, 2)
# assert stats.loc['spearman', 'CI95%'][1] == round(0.7180799, 2)
# Kendall correlation
# R uses a different estimation method than scipy for the p-value
stats = corr(x, y, method='kendall')
assert np.isclose(stats.loc['kendall', 'r'], 0.3517241)
# Skipped correlation -- compare with robust corr toolbox
# https://sourceforge.net/projects/robustcorrtool/
stats = corr(x, y, method='skipped')
assert round(stats.loc['skipped', 'r'], 4) == 0.5123
assert stats.loc['skipped', 'outliers'] == 2
sk_sp = corr(x2, y2, method='skipped')
assert round(sk_sp.loc['skipped', 'r'], 4) == 0.5123
assert sk_sp.loc['skipped', 'outliers'] == 2
# Pearson skipped correlation
sk_pe = corr(x2, y2, method='skipped', corr_type='pearson')
assert np.round(sk_pe.loc['skipped', 'r'], 4) == 0.5254
assert sk_pe.loc['skipped', 'outliers'] == 2
assert not sk_sp.equals(sk_pe)
# Shepherd
stats = corr(x, y, method='shepherd')
assert np.isclose(stats.loc['shepherd', 'r'], 0.5123153)
assert np.isclose(stats.loc['shepherd', 'p-val'], 0.005316)
assert stats.loc['shepherd', 'outliers'] == 2
_, _, outliers = skipped(x, y, corr_type='pearson')
assert outliers.size == x.size
assert stats.loc['shepherd', 'n'] == 30
# Percbend -- compare with robust corr toolbox
stats = corr(x, y, method='percbend')
assert round(stats.loc['percbend', 'r'], 4) == 0.4843
assert np.isclose(stats.loc['percbend', 'r'], 0.4842686)
assert np.isclose(stats.loc['percbend', 'p-val'], 0.006693313)
stats = corr(x2, y2, method='percbend')
assert round(stats.loc['percbend', 'r'], 4) == 0.4843
stats = corr(x, y, method='percbend', beta=.5)
assert round(stats.loc['percbend', 'r'], 4) == 0.4848
# Compare biweight correlation to astropy
stats = corr(x, y, method='bicor')
assert np.isclose(stats.loc['bicor', 'r'], 0.4951418)
assert np.isclose(stats.loc['bicor', 'p-val'], 0.005403701)
assert stats.loc['bicor', 'CI95%'][0] == round(0.1641553, 2)
assert stats.loc['bicor', 'CI95%'][1] == round(0.7259185, 2)
stats = corr(x, y, method='bicor', c=5)
assert np.isclose(stats.loc['bicor', 'r'], 0.4940706950017)
# Not normally distributed
z = np.random.uniform(size=30)
corr(x, z, method='pearson')
# With NaN values
x[3] = np.nan
corr(x, y)
# With the same array
# Disabled because of AppVeyor failure
# assert corr(x, x).loc['pearson', 'BF10'] == str(np.inf)
# Wrong argument
with pytest.raises(ValueError):
corr(x, y, method='error')
with pytest.raises(ValueError):
corr(x, y, tail='error')
# Compare BF10 with JASP
df = read_dataset('pairwise_corr')
stats = corr(df['Neuroticism'], df['Extraversion'])
assert np.isclose(1 / float(stats['BF10'].to_numpy()), 1.478e-13)
# Perfect correlation, CI and power should be 1, BF should be Inf
# https://github.com/raphaelvallat/pingouin/issues/195
stats = corr(x, x)
assert np.isclose(stats.at['pearson', 'r'], 1)
assert np.isclose(stats.at['pearson', 'power'], 1)
# When one column is a constant, the correlation is not defined
# and Pingouin return a DataFrame full of NaN, except for ``n``
x, y = [1, 1, 1], [1, 2, 3]
stats = corr(x, y)
assert stats.at['pearson', 'n']
assert np.isnan(stats.at['pearson', 'r'])
# Biweight midcorrelation returns NaN when MAD is not defined
assert np.isnan(bicor(np.array([1, 1, 1, 1, 0, 1]), np.arange(6))[0])