def test_logistic_regression(self):
"""Test function logistic_regression."""
# Simple regression
lom = logistic_regression(df['X'], df['Ybin'], as_dataframe=False)
# Compare to JASP
assert_equal(np.round(lom['coef'], 1), [1.3, -0.2])
assert_equal(np.round(lom['se'], 2), [0.76, 0.12])
assert_equal(np.round(lom['z'], 1), [1.7, -1.6])
assert_equal(np.round(lom['pval'], 1), [0.1, 0.1])
assert_equal(np.round(lom['CI[2.5%]'], 1), [-.2, -.4])
assert_equal(np.round(lom['CI[97.5%]'], 1), [2.8, 0.0])
# Multiple predictors
X = df[['X', 'M']].values
y = df['Ybin'].values
lom = logistic_regression(X, y) # Pingouin
# Compare against JASP
assert_equal(np.round(lom['coef'].values, 1), [1.3, -0.2, -0.0])
assert_equal(np.round(lom['se'].values, 2), [0.78, 0.14, 0.13])
assert_equal(np.round(lom['z'].values, 1), [1.7, -1.4, -0.1])
assert_equal(np.round(lom['pval'].values, 1), [0.1, 0.2, 1.])
assert_equal(np.round(lom['CI[2.5%]'].values, 1), [-.2, -.5, -.3])
assert_equal(np.round(lom['CI[97.5%]'].values, 1), [2.8, 0.1, 0.2])
# Test other arguments
c = logistic_regression(df[['X', 'M']], df['Ybin'], coef_only=True)
assert_equal(np.round(c, 1), [1.3, -0.2, -0.0])
# Test **kwargs
logistic_regression(X, y, solver='sag', C=10, max_iter=10000)
with pytest.raises(ValueError):
y[3] = 2
logistic_regression(X, y)
def test_logistic_regression(self):
"""Test function logistic_regression."""
# Simple regression
lom = logistic_regression(df['X'], df['Ybin'], as_dataframe=False)
# Compare to R
# Reproduce in jupyter notebook with rpy2 using
# %load_ext rpy2.ipython (in a separate cell)
# Together in one cell below
# %%R -i df
# summary(glm(Ybin ~ X, data=df, family=binomial))
assert_equal(np.round(lom['coef'], 4), [1.3191, -0.1995])
assert_equal(np.round(lom['se'], 4), [0.7582, 0.1211])
assert_equal(np.round(lom['z'], 4), [1.7399, -1.6476])
assert_equal(np.round(lom['pval'], 4), [0.0819, 0.0994])
assert_equal(np.round(lom['CI[2.5%]'], 4), [-.1669, -.4367])
assert_equal(np.round(lom['CI[97.5%]'], 4), [2.8050, 0.0378])
# Multiple predictors
X = df[['X', 'M']].values
y = df['Ybin'].values
lom = logistic_regression(X, y).round(4) # Pingouin
# Compare against R
# summary(glm(Ybin ~ X+M, data=df, family=binomial))
assert_equal(lom['coef'].values, [1.3276, -0.1960, -0.0060])
assert_equal(lom['se'].values, [0.7784, 0.1408, 0.1253])
assert_equal(lom['z'].values, [1.7056, -1.3926, -0.0476])
assert_equal(lom['pval'].values, [0.0881, 0.1637, 0.9620])
assert_equal(lom['CI[2.5%]'].values, [-.1980, -.4719, -.2516])
assert_equal(lom['CI[97.5%]'].values, [2.8531, 0.0799, 0.2397])
# Test other arguments
c = logistic_regression(df[['X', 'M']], df['Ybin'], coef_only=True)
assert_equal(np.round(c, 4), [1.3276, -0.1960, -0.0060])
# With missing values
logistic_regression(df_nan[['X', 'M']], df_nan['Ybin'], remove_na=True)
# Test **kwargs
logistic_regression(X,
y,
solver='sag',
C=10,
max_iter=10000,
penalty="l2")
logistic_regression(X, y, solver='sag', multi_class='auto')
# Test regularization coefficients are strictly closer to 0 than
# unregularized
c = logistic_regression(df['X'], df['Ybin'], coef_only=True)
c_reg = logistic_regression(df['X'],
df['Ybin'],
coef_only=True,
penalty='l2')
assert all(np.abs(c - 0) > np.abs(c_reg - 0))
# With one column that has only one unique value
c = logistic_regression(df[['One', 'X']], df['Ybin'])
assert np.array_equal(c.loc[:, 'names'], ['Intercept', 'X'])
c = logistic_regression(df[['X', 'One', 'M', 'Zero']], df['Ybin'])
assert np.array_equal(c.loc[:, 'names'], ['Intercept', 'X', 'M'])
# With duplicate columns
c = logistic_regression(df[['X', 'M', 'X']], df['Ybin'])
assert np.array_equal(c.loc[:, 'names'], ['Intercept', 'X', 'M'])
c = logistic_regression(df[['X', 'X', 'X']], df['Ybin'])
assert np.array_equal(c.loc[:, 'names'], ['Intercept', 'X'])
# Error: dependent variable is not binary
with pytest.raises(ValueError):
y[3] = 2
logistic_regression(X, y)
def test_logistic_regression(self):
"""Test function logistic_regression."""
# Simple regression
lom = logistic_regression(df['X'], df['Ybin'], as_dataframe=False)
# Compare to R
# Reproduce in jupyter notebook with rpy2 using
# %load_ext rpy2.ipython (in a separate cell)
# Together in one cell below
# %%R -i df
# summary(glm(Ybin ~ X, data=df, family=binomial))
assert_equal(np.round(lom['coef'], 4), [1.3191, -0.1995])
assert_equal(np.round(lom['se'], 4), [0.7582, 0.1211])
assert_equal(np.round(lom['z'], 4), [1.7399, -1.6476])
assert_equal(np.round(lom['pval'], 4), [0.0819, 0.0994])
assert_equal(np.round(lom['CI[2.5%]'], 4), [-.1669, -.4367])
assert_equal(np.round(lom['CI[97.5%]'], 4), [2.8050, 0.0378])
# Multiple predictors
X = df[['X', 'M']].to_numpy()
y = df['Ybin'].to_numpy()
lom = logistic_regression(X, y).round(4) # Pingouin
# Compare against R
# summary(glm(Ybin ~ X+M, data=df, family=binomial))
assert_equal(lom['coef'].to_numpy(), [1.3275, -0.1960, -0.0060])
assert_equal(lom['se'].to_numpy(), [0.7784, 0.1408, 0.1253])
assert_equal(lom['z'].to_numpy(), [1.7055, -1.3926, -0.0475])
assert_equal(lom['pval'].to_numpy(), [0.0881, 0.1637, 0.9621])
assert_equal(lom['CI[2.5%]'].to_numpy(), [-.1981, -.4719, -.2516])
assert_equal(lom['CI[97.5%]'].to_numpy(), [2.8531, 0.0799, 0.2397])
# Test other arguments
c = logistic_regression(df[['X', 'M']], df['Ybin'], coef_only=True)
assert_equal(np.round(c, 4), [1.3275, -0.1960, -0.0060])
# With missing values
logistic_regression(df_nan[['X', 'M']], df_nan['Ybin'], remove_na=True)
# Test **kwargs
logistic_regression(X, y, solver='sag', C=10, max_iter=10000,
penalty="l2")
logistic_regression(X, y, solver='sag', multi_class='auto')
# Test regularization coefficients are strictly closer to 0 than
# unregularized
c = logistic_regression(df['X'], df['Ybin'], coef_only=True)
c_reg = logistic_regression(df['X'], df['Ybin'], coef_only=True,
penalty='l2')
assert all(np.abs(c - 0) > np.abs(c_reg - 0))
# With one column that has only one unique value
c = logistic_regression(df[['One', 'X']], df['Ybin'])
assert_equal(c.loc[:, 'names'].to_numpy(), ['Intercept', 'X'])
c = logistic_regression(df[['X', 'One', 'M', 'Zero']], df['Ybin'])
assert_equal(c.loc[:, 'names'].to_numpy(), ['Intercept', 'X', 'M'])
# With duplicate columns
c = logistic_regression(df[['X', 'M', 'X']], df['Ybin'])
assert_equal(c.loc[:, 'names'].to_numpy(), ['Intercept', 'X', 'M'])
c = logistic_regression(df[['X', 'X', 'X']], df['Ybin'])
assert_equal(c.loc[:, 'names'].to_numpy(), ['Intercept', 'X'])
# Error: dependent variable is not binary
with pytest.raises(ValueError):
y[3] = 2
logistic_regression(X, y)
# --------------------------------------------------------------------
# 2ND dataset (Penguin)-- compare to R
lom = logistic_regression(data['body_mass_g'], data['male'],
as_dataframe=False)
assert np.allclose(lom['coef'], [-5.162541644, 0.001239819])
assert_equal(np.round(lom['se'], 5), [0.72439, 0.00017])
assert_equal(np.round(lom['z'], 3), [-7.127, 7.177])
assert np.allclose(lom['pval'], [1.03e-12, 7.10e-13])
assert_equal(np.round(lom['CI[2.5%]'], 3), [-6.582, 0.001])
assert_equal(np.round(lom['CI[97.5%]'], 3), [-3.743, 0.002])
# With a different scaling: z / p-values should be similar
lom = logistic_regression(data['body_mass_kg'], data['male'],
as_dataframe=False)
assert np.allclose(lom['coef'], [-5.162542, 1.239819])
assert_equal(np.round(lom['se'], 4), [0.7244, 0.1727])
assert_equal(np.round(lom['z'], 3), [-7.127, 7.177])
assert np.allclose(lom['pval'], [1.03e-12, 7.10e-13])
assert_equal(np.round(lom['CI[2.5%]'], 3), [-6.582, 0.901])
assert_equal(np.round(lom['CI[97.5%]'], 3), [-3.743, 1.578])
# With no intercept
lom = logistic_regression(data['body_mass_kg'], data['male'],
as_dataframe=False, fit_intercept=False)
assert np.isclose(lom['coef'], 0.04150582)
assert np.round(lom['se'], 5) == 0.02570
assert np.round(lom['z'], 3) == 1.615
assert np.round(lom['pval'], 3) == 0.106
assert np.round(lom['CI[2.5%]'], 3) == -0.009
assert np.round(lom['CI[97.5%]'], 3) == 0.092
# With categorical predictors
# R: >>> glm("male ~ body_mass_kg + species", family=binomial, ...)
# >>> confint.default(model) # Wald CI
# See https://stats.stackexchange.com/a/275421/253579
data_dum = pd.get_dummies(data, columns=['species'], drop_first=True)
X = data_dum[['body_mass_kg', 'species_Chinstrap', 'species_Gentoo']]
y = data_dum['male']
lom = logistic_regression(X, y, as_dataframe=False)
assert_equal(np.round(lom['coef'], 7),
[-27.1318593, 7.3728436, -0.2559251, -10.1778083])
assert_equal(np.round(lom['se'], 4),
[2.9984, 0.8141, 0.4293, 1.1946])
assert_equal(np.round(lom['z'], 3),
[-9.049, 9.056, -0.596, -8.520])
assert_equal(np.round(lom['CI[2.5%]'], 3),
[-33.009, 5.777, -1.097, -12.519])
assert_equal(np.round(lom['CI[97.5%]'], 3),
[-21.255, 8.969, 0.586, -7.836])
def test_logistic_regression(self):
"""Test function logistic_regression."""
# Simple regression
lom = logistic_regression(df['X'], df['Ybin'], as_dataframe=False)
# Compare to JASP
assert_equal(np.round(lom['coef'], 1), [1.3, -0.2])
assert_equal(np.round(lom['se'], 2), [0.76, 0.12])
assert_equal(np.round(lom['z'], 1), [1.7, -1.6])
assert_equal(np.round(lom['pval'], 1), [0.1, 0.1])
assert_equal(np.round(lom['CI[2.5%]'], 1), [-.2, -.4])
assert_equal(np.round(lom['CI[97.5%]'], 1), [2.8, 0.0])
# Multiple predictors
X = df[['X', 'M']].values
y = df['Ybin'].values
lom = logistic_regression(X, y) # Pingouin
# Compare against JASP
assert_equal(np.round(lom['coef'].values, 1), [1.3, -0.2, -0.0])
assert_equal(np.round(lom['se'].values, 2), [0.78, 0.14, 0.13])
assert_equal(np.round(lom['z'].values, 1), [1.7, -1.4, -0.1])
assert_equal(np.round(lom['pval'].values, 1), [0.1, 0.2, 1.])
assert_equal(np.round(lom['CI[2.5%]'].values, 1), [-.2, -.5, -.3])
assert_equal(np.round(lom['CI[97.5%]'].values, 1), [2.8, 0.1, 0.2])
# Test other arguments
c = logistic_regression(df[['X', 'M']], df['Ybin'], coef_only=True)
assert_equal(np.round(c, 1), [1.3, -0.2, -0.0])
# With missing values
logistic_regression(df_nan[['X', 'M']], df_nan['Ybin'], remove_na=True)
# Test **kwargs
logistic_regression(X, y, solver='sag', C=10, max_iter=10000)
logistic_regression(X, y, solver='sag', multi_class='auto')
# With one column that has only one unique value
c = logistic_regression(df[['One', 'X']], df['Ybin'])
assert np.array_equal(c.loc[:, 'names'], ['Intercept', 'X'])
c = logistic_regression(df[['X', 'One', 'M', 'Zero']], df['Ybin'])
assert np.array_equal(c.loc[:, 'names'], ['Intercept', 'X', 'M'])
# With duplicate columns
c = logistic_regression(df[['X', 'M', 'X']], df['Ybin'])
assert np.array_equal(c.loc[:, 'names'], ['Intercept', 'X', 'M'])
c = logistic_regression(df[['X', 'X', 'X']], df['Ybin'])
assert np.array_equal(c.loc[:, 'names'], ['Intercept', 'X'])
# Error: dependent variable is not binary
with pytest.raises(ValueError):
y[3] = 2
logistic_regression(X, y)