def setup_class(cls):
cls.res2 = results.results_noexposure_constraint2
cls.idx = [7, 3, 4, 5, 6, 0, 1] # 2 is dropped baseline for categorical
# example without offset
formula = 'deaths ~ logpyears + smokes + C(agecat)'
mod = Poisson.from_formula(formula, data=data)
# get start_params, example fails to converge on one py TravisCI
k_vars = len(mod.exog_names)
start_params = np.zeros(k_vars)
start_params[0] = np.log(mod.endog.mean())
# if we need it, this is desired params
p = np.array([-9.43762015, 1.52762442, 2.74155711, 3.58730007,
4.08730007, 1.15987869, 0.12111539])
constr = 'C(agecat)[T.5] - C(agecat)[T.4] = 0.5'
lc = patsy.DesignInfo(mod.exog_names).linear_constraint(constr)
cls.res1 = fit_constrained(mod, lc.coefs, lc.constants,
start_params=start_params,
fit_kwds={'method': 'bfgs', 'disp': 0})
# TODO: Newton fails
# test method of Poisson, not monkey patched
cls.res1m = mod.fit_constrained(constr, start_params=start_params,
method='bfgs', disp=0)
def fit_constrained(self, constraints, start_params=None, **fit_kwds):
"""fit the model subject to linear equality constraints
The constraints are of the form `R params = q`
where R is the constraint_matrix and q is the vector of
constraint_values.
The estimation creates a new model with transformed design matrix,
exog, and converts the results back to the original parameterization.
Parameters
----------
constraints : formula expression or tuple
If it is a tuple, then the constraint needs to be given by two
arrays (constraint_matrix, constraint_value), i.e. (R, q).
Otherwise, the constraints can be given as strings or list of
strings.
see t_test for details
start_params : None or array_like
starting values for the optimization. `start_params` needs to be
given in the original parameter space and are internally
transformed.
**fit_kwds : keyword arguments
fit_kwds are used in the optimization of the transformed model.
Returns
-------
results : Results instance
"""
from patsy import DesignInfo
from statsmodels.base._constraints import fit_constrained
# same pattern as in base.LikelihoodModel.t_test
lc = DesignInfo(self.exog_names).linear_constraint(constraints)
R, q = lc.coefs, lc.constants
# TODO: add start_params option, need access to tranformation
# fit_constrained needs to do the transformation
params, cov, res_constr = fit_constrained(self,
R,
q,
start_params=start_params,
fit_kwds=fit_kwds)
#create dummy results Instance, TODO: wire up properly
res = self.fit(start_params=params, maxiter=0) # we get a wrapper back
res._results.params = params
res._results.normalized_cov_params = cov
k_constr = len(q)
res._results.df_resid += k_constr
res._results.df_model -= k_constr
res._results.constraints = lc
res._results.k_constr = k_constr
res._results.results_constrained = res_constr
# TODO: the next is not the best. history should bin in results
res._results.model.history = res_constr.model.history
res._results.mu = res_constr.mu
return res
def setup_class(cls):
cls.res2 = results.results_noexposure_constraint
cls.idx = [7, 3, 4, 5, 6, 0, 1] # 2 is dropped baseline for categorical
# example without offset
formula = 'deaths ~ logpyears + smokes + C(agecat)'
mod = Poisson.from_formula(formula, data=data)
#res1a = mod1a.fit()
# get start_params, example fails to converge on one py TravisCI
k_vars = len(mod.exog_names)
start_params = np.zeros(k_vars)
start_params[0] = np.log(mod.endog.mean())
# if we need it, this is desired params
p = np.array([-3.93478643, 1.37276214, 2.33077032, 2.71338891,
2.71338891, 0.57966535, 0.97254074])
constr = 'C(agecat)[T.4] = C(agecat)[T.5]'
lc = patsy.DesignInfo(mod.exog_names).linear_constraint(constr)
cls.res1 = fit_constrained(mod, lc.coefs, lc.constants,
start_params=start_params,
fit_kwds={'method': 'bfgs',
'disp': 0})
# TODO: Newton fails
# test method of Poisson, not monkey patched
cls.res1m = mod.fit_constrained(constr, start_params=start_params,
method='bfgs', disp=0)
def setup_class(cls):
cls.res2 = results.results_noexposure_constraint2
cls.idx = [7, 3, 4, 5, 6, 0, 1] # 2 is dropped baseline for categorical
# example without offset
formula = 'deaths ~ logpyears + smokes + C(agecat)'
mod = Poisson.from_formula(formula, data=data)
# get start_params, example fails to converge on one py TravisCI
k_vars = len(mod.exog_names)
start_params = np.zeros(k_vars)
start_params[0] = np.log(mod.endog.mean())
# if we need it, this is desired params
p = np.array([-9.43762015, 1.52762442, 2.74155711, 3.58730007,
4.08730007, 1.15987869, 0.12111539])
constr = 'C(agecat)[T.5] - C(agecat)[T.4] = 0.5'
lc = patsy.DesignInfo(mod.exog_names).linear_constraint(constr)
cls.res1 = fit_constrained(mod, lc.coefs, lc.constants,
start_params=start_params,
fit_kwds={'method': 'bfgs', 'disp': 0})
# TODO: Newton fails
# test method of Poisson, not monkey patched
cls.res1m = mod.fit_constrained(constr, start_params=start_params,
method='bfgs', disp=0)
def setup_class(cls):
cls.res2 = results.results_exposure_constraint2
#cls.idx = [3, 4, 5, 6, 0, 1] # 2 is dropped baseline for categorical
cls.idx = [6, 2, 3, 4, 5, 0] # 2 is dropped baseline for categorical
# example without offset
formula = 'deaths ~ smokes + C(agecat)'
mod = Poisson.from_formula(formula,
data=data,
offset=np.log(data['pyears'].values))
constr = 'C(agecat)[T.5] - C(agecat)[T.4] = 0.5'
lc = patsy.DesignInfo(mod.exog_names).linear_constraint(constr)
cls.res1 = fit_constrained(mod,
lc.coefs,
lc.constants,
fit_kwds={
'method': 'newton',
'disp': 0
})
cls.constraints = lc
# TODO: bfgs fails
# test method of Poisson, not monkey patched
cls.res1m = mod.fit_constrained(constr,
method='bfgs',
disp=0,
start_params=cls.res1[0])
def setup_class(cls):
cls.res2 = results.results_noexposure_constraint
cls.idx = [7, 3, 4, 5, 6, 0, 1] # 2 is dropped baseline for categorical
# example without offset
formula = 'deaths ~ logpyears + smokes + C(agecat)'
mod = Poisson.from_formula(formula, data=data)
#res1a = mod1a.fit()
# get start_params, example fails to converge on one py TravisCI
k_vars = len(mod.exog_names)
start_params = np.zeros(k_vars)
start_params[0] = np.log(mod.endog.mean())
# if we need it, this is desired params
p = np.array([-3.93478643, 1.37276214, 2.33077032, 2.71338891,
2.71338891, 0.57966535, 0.97254074])
constr = 'C(agecat)[T.4] = C(agecat)[T.5]'
lc = patsy.DesignInfo(mod.exog_names).linear_constraint(constr)
cls.res1 = fit_constrained(mod, lc.coefs, lc.constants,
start_params=start_params,
fit_kwds={'method': 'bfgs',
'disp': 0})
# TODO: Newton fails
# test method of Poisson, not monkey patched
cls.res1m = mod.fit_constrained(constr, start_params=start_params,
method='bfgs', disp=0)
def setup_class(cls):
cls.idx = slice(None) # params sequence same as Stata
#res1ul = Logit(data.endog, data.exog).fit(method="newton", disp=0)
cls.res2 = reslogit.results_constraint2_robust
mod1 = GLM(spector_data.endog,
spector_data.exog,
family=families.Binomial())
# not used to match Stata for HC
# nobs, k_params = mod1.exog.shape
# k_params -= 1 # one constraint
cov_type = 'HC0'
cov_kwds = {'scaling_factor': 32 / 31}
# looks like nobs / (nobs - 1) and not (nobs - 1.) / (nobs - k_params)}
constr = 'x1 - x3 = 0'
cls.res1m = mod1.fit_constrained(constr,
cov_type=cov_type,
cov_kwds=cov_kwds,
atol=1e-10)
R, q = cls.res1m.constraints.coefs, cls.res1m.constraints.constants
cls.res1 = fit_constrained(mod1,
R,
q,
fit_kwds={
'atol': 1e-10,
'cov_type': cov_type,
'cov_kwds': cov_kwds
})
cls.constraints_rq = (R, q)
def fit_constrained(self, constraints, start_params=None, **fit_kwds):
"""fit the model subject to linear equality constraints
The constraints are of the form `R params = q`
where R is the constraint_matrix and q is the vector of
constraint_values.
The estimation creates a new model with transformed design matrix,
exog, and converts the results back to the original parameterization.
Parameters
----------
constraints : formula expression or tuple
If it is a tuple, then the constraint needs to be given by two
arrays (constraint_matrix, constraint_value), i.e. (R, q).
Otherwise, the constraints can be given as strings or list of
strings.
see t_test for details
start_params : None or array_like
starting values for the optimization. `start_params` needs to be
given in the original parameter space and are internally
transformed.
**fit_kwds : keyword arguments
fit_kwds are used in the optimization of the transformed model.
Returns
-------
results : Results instance
"""
from patsy import DesignInfo
from statsmodels.base._constraints import fit_constrained
# same pattern as in base.LikelihoodModel.t_test
lc = DesignInfo(self.exog_names).linear_constraint(constraints)
R, q = lc.coefs, lc.constants
# TODO: add start_params option, need access to tranformation
# fit_constrained needs to do the transformation
params, cov, res_constr = fit_constrained(self, R, q,
start_params=start_params,
fit_kwds=fit_kwds)
#create dummy results Instance, TODO: wire up properly
res = self.fit(start_params=params, maxiter=0) # we get a wrapper back
res._results.params = params
res._results.normalized_cov_params = cov
k_constr = len(q)
res._results.df_resid += k_constr
res._results.df_model -= k_constr
res._results.constraints = lc
res._results.k_constr = k_constr
res._results.results_constrained = res_constr
# TODO: the next is not the best. history should bin in results
res._results.model.history = res_constr.model.history
res._results.mu = res_constr.mu
return res
def setup_class(cls):
cls.idx = slice(None) # params sequence same as Stata
cls.res2 = reslogit.results_constraint2
mod1 = GLM(spector_data.endog, spector_data.exog,
family=families.Binomial())
constr = 'x1 - x3 = 0'
cls.res1m = mod1.fit_constrained(constr, atol=1e-10)
# patsy compatible constraints
R, q = cls.res1m.constraints.coefs, cls.res1m.constraints.constants
cls.res1 = fit_constrained(mod1, R, q, fit_kwds={'atol': 1e-10})
cls.constraints_rq = (R, q)
def setup_class(cls):
cls.idx = slice(None) # params sequence same as Stata
#res1ul = Logit(data.endog, data.exog).fit(method="newton", disp=0)
cls.res2 = reslogit.results_constraint2
mod1 = GLM(spector_data.endog, spector_data.exog,
family=families.Binomial())
constr = 'x1 - x3 = 0'
cls.res1m = mod1.fit_constrained(constr, atol=1e-10)
R, q = cls.res1m.constraints.coefs, cls.res1m.constraints.constants
cls.res1 = fit_constrained(mod1, R, q, fit_kwds={'atol': 1e-10})
cls.constraints_rq = (R, q)
def setup_class(cls):
cls.idx = slice(None) # params sequence same as Stata
#res1ul = Logit(data.endog, data.exog).fit(method="newton", disp=0)
cls.res2 = reslogit.results_constraint2
mod1 = GLM(spector_data.endog, spector_data.exog,
family=families.Binomial())
constr = 'x1 - x3 = 0'
cls.res1m = mod1.fit_constrained(constr, atol=1e-10)
R, q = cls.res1m.constraints.coefs, cls.res1m.constraints.constants
cls.res1 = fit_constrained(mod1, R, q, fit_kwds={'atol': 1e-10})
cls.constraints_rq = (R, q)
def setup_class(cls):
cls.idx = slice(None)
# params sequence same as Stata, but Stata reports param = nan
# and we have param = value = 0
cls.res2 = reslogit.results_constraint1
mod1 = GLM(spector_data.endog, spector_data.exog,
family=families.Binomial())
constr = 'x1 = 2.8'
cls.res1m = mod1.fit_constrained(constr)
R, q = cls.res1m.constraints
cls.res1 = fit_constrained(mod1, R, q)
def setup_class(cls):
from statsmodels.base._constraints import fit_constrained
cls.res2 = results.results_noexposure_constraint
cls.idx = [7, 3, 4, 5, 6, 0,
1] # 2 is dropped baseline for categorical
# example without offset
formula = 'deaths ~ logpyears + smokes + C(agecat)'
mod = GLM.from_formula(formula, data=data, family=families.Poisson())
constr = 'C(agecat)[T.4] = C(agecat)[T.5]'
lc = patsy.DesignInfo(mod.exog_names).linear_constraint(constr)
cls.res1 = fit_constrained(mod, lc.coefs, lc.constants)
cls.constraints = lc
cls.res1m = mod.fit_constrained(constr)
def setup_class(cls):
cls.idx = slice(None)
# params sequence same as Stata, but Stata reports param = nan
# and we have param = value = 0
# res1ul = Logit(data.endog, data.exog).fit(method="newton", disp=0)
cls.res2 = reslogit.results_constraint1
mod1 = Logit(spector_data.endog, spector_data.exog)
constr = 'x1 = 2.8'
# newton doesn't work, raises hessian singular
cls.res1m = mod1.fit_constrained(constr, method='bfgs')
R, q = cls.res1m.constraints.coefs, cls.res1m.constraints.constants
cls.res1 = fit_constrained(mod1, R, q, fit_kwds={'method': 'bfgs'})
def setup_class(cls):
cls.idx = slice(None)
# params sequence same as Stata, but Stata reports param = nan
# and we have param = value = 0
#res1ul = Logit(data.endog, data.exog).fit(method="newton", disp=0)
cls.res2 = reslogit.results_constraint1
mod1 = GLM(spector_data.endog, spector_data.exog,
family=families.Binomial())
constr = 'x1 = 2.8'
cls.res1m = mod1.fit_constrained(constr)
R, q = cls.res1m.constraints.coefs, cls.res1m.constraints.constants
cls.res1 = fit_constrained(mod1, R, q)
def setup_class(cls):
from statsmodels.base._constraints import fit_constrained
cls.res2 = results.results_noexposure_constraint
cls.idx = [7, 3, 4, 5, 6, 0, 1] # 2 is dropped baseline for categorical
# example without offset
formula = 'deaths ~ logpyears + smokes + C(agecat)'
mod = GLM.from_formula(formula, data=data,
family=families.Poisson())
constr = 'C(agecat)[T.4] = C(agecat)[T.5]'
lc = patsy.DesignInfo(mod.exog_names).linear_constraint(constr)
cls.res1 = fit_constrained(mod, lc.coefs, lc.constants)
cls.constraints = lc
cls.res1m = mod.fit_constrained(constr)
def setup_class(cls):
from statsmodels.genmod.generalized_linear_model import GLM
from statsmodels.genmod import families
from statsmodels.base._constraints import fit_constrained
cls.res2 = results.results_exposure_constraint
cls.idx = [6, 2, 3, 4, 5, 0] # 2 is dropped baseline for categorical
# example with offset
formula = 'deaths ~ smokes + C(agecat)'
mod = GLM.from_formula(formula, data=data,
family=families.Poisson(),
offset=np.log(data['pyears'].values))
constr = 'C(agecat)[T.4] = C(agecat)[T.5]'
lc = patsy.DesignInfo(mod.exog_names).linear_constraint(constr)
cls.res1 = fit_constrained(mod, lc.coefs, lc.constants)
cls.constraints = lc
cls.res1m = mod.fit_constrained(constr)._results
def setup_class(cls):
cls.res2 = results.results_exposure_constraint
#cls.idx = [3, 4, 5, 6, 0, 1] # 2 is dropped baseline for categorical
cls.idx = [6, 2, 3, 4, 5, 0] # 2 is dropped baseline for categorical
# example without offset
formula = 'deaths ~ smokes + C(agecat)'
mod = Poisson.from_formula(formula, data=data,
offset=np.log(data['pyears'].values))
#res1a = mod1a.fit()
constr = 'C(agecat)[T.4] = C(agecat)[T.5]'
lc = patsy.DesignInfo(mod.exog_names).linear_constraint(constr)
cls.res1 = fit_constrained(mod, lc.coefs, lc.constants,
fit_kwds={'method':'newton'})
cls.constraints = lc
# TODO: bfgs fails
# test method of Poisson, not monkey patched
cls.res1m = mod.fit_constrained(constr, method='newton')
def setup_class(cls):
from statsmodels.genmod.generalized_linear_model import GLM
from statsmodels.genmod import families
from statsmodels.base._constraints import fit_constrained
cls.res2 = results.results_exposure_constraint
cls.idx = [6, 2, 3, 4, 5, 0] # 2 is dropped baseline for categorical
# example with offset
formula = 'deaths ~ smokes + C(agecat)'
mod = GLM.from_formula(formula,
data=data,
family=families.Poisson(),
offset=np.log(data['pyears'].values))
constr = 'C(agecat)[T.4] = C(agecat)[T.5]'
lc = patsy.DesignInfo(mod.exog_names).linear_constraint(constr)
cls.res1 = fit_constrained(mod, lc.coefs, lc.constants)
cls.constraints = lc
cls.res1m = mod.fit_constrained(constr)._results
def setup_class(cls):
cls.idx = slice(None) # params sequence same as Stata
#res1ul = Logit(data.endog, data.exog).fit(method="newton", disp=0)
cls.res2 = reslogit.results_constraint2_robust
mod1 = GLM(spector_data.endog, spector_data.exog,
family=families.Binomial())
# not used to match Stata for HC
# nobs, k_params = mod1.exog.shape
# k_params -= 1 # one constraint
cov_type = 'HC0'
cov_kwds = {'scaling_factor': 32/31}
# looks like nobs / (nobs - 1) and not (nobs - 1.) / (nobs - k_params)}
constr = 'x1 - x3 = 0'
cls.res1m = mod1.fit_constrained(constr, cov_type=cov_type,
cov_kwds=cov_kwds, atol=1e-10)
R, q = cls.res1m.constraints.coefs, cls.res1m.constraints.constants
cls.res1 = fit_constrained(mod1, R, q, fit_kwds={'atol': 1e-10,
'cov_type': cov_type,
'cov_kwds': cov_kwds})
cls.constraints_rq = (R, q)
def setup_class(cls):
cls.res2 = results.results_exposure_constraint2
#cls.idx = [3, 4, 5, 6, 0, 1] # 2 is dropped baseline for categorical
cls.idx = [6, 2, 3, 4, 5, 0] # 2 is dropped baseline for categorical
# example without offset
formula = 'deaths ~ smokes + C(agecat)'
mod = Poisson.from_formula(formula, data=data,
#offset=np.log(data['pyears'].values))
exposure=data['pyears'].values)
#res1a = mod1a.fit()
constr = 'C(agecat)[T.5] - C(agecat)[T.4] = 0.5'
lc = patsy.DesignInfo(mod.exog_names).linear_constraint(constr)
cls.res1 = fit_constrained(mod, lc.coefs, lc.constants,
fit_kwds={'method': 'newton',
'disp': 0})
cls.constraints = lc
# TODO: bfgs fails to converge. overflow somewhere?
# test method of Poisson, not monkey patched
cls.res1m = mod.fit_constrained(constr, method='bfgs', disp=0,
start_params=cls.res1[0])
# cov_params3 = transf3.transf_mat.dot(res3.cov_params()).dot(transf3.transf_mat.T)
# bse3 = np.sqrt(np.diag(cov_params3))
poisson_mod0 = sm.Poisson(rand_data.endog, rand_exog)
poisson_res0 = poisson_mod0.fit(method="newton")
tp = transform_params_constraint(poisson_res0.params, poisson_res0.cov_params(), transfp.R, transfp.q)
cov_params3 = transf3.transf_mat.dot(res3.cov_params()).dot(transf3.transf_mat.T)
bse3 = np.sqrt(np.diag(cov_params3))
# try again same example as it was intended
poisson_mod = sm.Poisson(rand_data.endog, rand_exog[:, :-2], offset=rand_exog[:, -1])
poisson_res = poisson_mod.fit(method="newton")
exogp_st = transfp.reduce(rand_exog)
poisson_modr = sm.Poisson(rand_data.endog, exogp_st, offset=rand_exog.dot(transfp.constant.squeeze()))
poisson_resr = poisson_modr.fit(method="newton")
paramsp = transfp.expand(poisson_resr.params).squeeze()
print('\nPoisson')
print(paramsp)
print(poisson_resr.params)
tp = transform_params_constraint(poisson_res0.params, poisson_res0.cov_params(), transfp.R, transfp.q)
cov_paramsp = transfp.transf_mat.dot(poisson_resr.cov_params()).dot(transfp.transf_mat.T)
bsep = np.sqrt(np.diag(cov_paramsp))
print(bsep)
p, cov, res_r = fit_constrained(poisson_mod0, transfp.R, transfp.q)
se = np.sqrt(np.diag(cov))
print(p)
print(se)
# cov_params3 = transf3.transf_mat.dot(res3.cov_params()).dot(transf3.transf_mat.T)
# bse3 = np.sqrt(np.diag(cov_params3))
poisson_mod0 = sm.Poisson(rand_data.endog, rand_exog)
poisson_res0 = poisson_mod0.fit(method="newton")
tp = transform_params_constraint(poisson_res0.params, poisson_res0.cov_params(), transfp.R, transfp.q)
cov_params3 = transf3.transf_mat.dot(res3.cov_params()).dot(transf3.transf_mat.T)
bse3 = np.sqrt(np.diag(cov_params3))
# try again same example as it was intended
poisson_mod = sm.Poisson(rand_data.endog, rand_exog[:, :-2], offset=rand_exog[:, -1])
poisson_res = poisson_mod.fit(method="newton")
exogp_st = transfp.reduce(rand_exog)
poisson_modr = sm.Poisson(rand_data.endog, exogp_st, offset=rand_exog.dot(transfp.constant.squeeze()))
poisson_resr = poisson_modr.fit(method="newton")
paramsp = transfp.expand(poisson_resr.params).squeeze()
print('\nPoisson')
print(paramsp)
print(poisson_resr.params)
tp = transform_params_constraint(poisson_res0.params, poisson_res0.cov_params(), transfp.R, transfp.q)
cov_paramsp = transfp.transf_mat.dot(poisson_resr.cov_params()).dot(transfp.transf_mat.T)
bsep = np.sqrt(np.diag(cov_paramsp))
print(bsep)
p, cov, res_r = fit_constrained(poisson_mod0, transfp.R, transfp.q)
se = np.sqrt(np.diag(cov))
print(p)
print(se)
