def __init__(self, X, dist='OLS', alphas=[0.05, 0.01], log=True):
self.X, self.xLen, self.dist, self.permute, self.zero_prob, self.alphas, self.dfd, self.dfn = X, len(
X.names), dist, self.permute_REG, 0.0, alphas, len(
X.names) - 1, len(X.array) - len(X.names)
#F_KEY = {'TW': sfams.Tweedie(link=slinks.log), 'PO': sfams.Poisson(link=slinks.log), 'NB': sfams.NegativeBinomial(link=slinks.log), 'GA': sfams.Gamma(link=slinks.log), 'NO': sfams.Gaussian(link=slinks.log)}
F_KEY = {
'TW': sfams.Tweedie(),
'PO': sfams.Poisson(),
'NB': sfams.NegativeBinomial(),
'GA': sfams.Gamma(),
'NO': sfams.Gaussian()
}
if self.dist.upper() == 'OLS':
self.reg, self.execute = sm.OLS, self.execute_REG
elif self.dist.upper()[0] == 'G':
self.reg, self.execute, self.family = scm.ZeroInflatedNegativeBinomialP, self.execute_GIN, F_KEY[
'NB']
elif self.dist.upper()[0] != 'Z':
self.execute, self.permute, self.family = self.execute_GLM, self.permute_GLM, F_KEY[
self.dist.upper()[0:2]]
else:
if self.dist.upper()[0:3] in ['ZIP', 'ZPO']:
self.reg, self.execute, self.family = CUSTOM_ZPO, self.execute_ZIN, F_KEY[
'PO']
elif self.dist.upper()[0:3] in ['ZIN', 'ZNB']:
self.reg, self.execute, self.family = CUSTOM_ZNB, self.execute_ZIN, F_KEY[
'NB']
elif self.dist.upper()[0:3] in ['ZGP', 'ZGP']:
self.reg, self.execute, self.family = CUSTOM_ZGP, self.execute_ZIN, F_KEY[
'GP']
def setup_class(cls):
# adjusted for Gamma, not in test_gee.py
vs = Independence()
family = families.Gamma(link=links.log)
np.random.seed(987126)
#Y = np.random.normal(size=100)**2
Y = np.exp(0.1 + np.random.normal(size=100)) # log-normal
X1 = np.random.normal(size=100)
X2 = np.random.normal(size=100)
X3 = np.random.normal(size=100)
groups = np.random.randint(0, 4, size=100)
D = pd.DataFrame({"Y": Y, "X1": X1, "X2": X2, "X3": X3})
mod1 = GEE.from_formula("Y ~ X1 + X2 + X3",
groups,
D,
family=family,
cov_struct=vs)
cls.result1 = mod1.fit()
mod2 = GLM.from_formula("Y ~ X1 + X2 + X3", data=D, family=family)
cls.result2 = mod2.fit(disp=False)