def junk():
# Singular Matrix in mod1a.fit()
formula1 = 'deaths ~ smokes + C(agecat)'
formula2 = 'deaths ~ C(agecat) + C(smokes) : C(agecat)' # same as Stata default
mod = Poisson.from_formula(formula2,
data=data,
exposure=data['pyears'].values)
res0 = mod.fit()
constraints = 'C(smokes)[T.1]:C(agecat)[3] = C(smokes)[T.1]:C(agecat)[4]'
import patsy
lc = patsy.DesignInfo(mod.exog_names).linear_constraint(constraints)
R, q = lc.coefs, lc.constants
resc = mod.fit_constrained(R, q, fit_kwds={'method': 'bfgs'})
# example without offset
formula1a = 'deaths ~ logpyears + smokes + C(agecat)'
mod1a = Poisson.from_formula(formula1a, data=data)
print(mod1a.exog.shape)
res1a = mod1a.fit()
lc_1a = patsy.DesignInfo(
mod1a.exog_names).linear_constraint('C(agecat)[T.4] = C(agecat)[T.5]')
resc1a = mod1a.fit_constrained(lc_1a.coefs,
lc_1a.constants,
fit_kwds={'method': 'newton'})
print(resc1a[0])
print(resc1a[1])
def junk(): # FIXME: make this into a test, or move/remove
# Singular Matrix in mod1a.fit()
# same as Stata default
formula2 = 'deaths ~ C(agecat) + C(smokes) : C(agecat)'
mod = Poisson.from_formula(formula2, data=data,
exposure=data['pyears'].values)
mod.fit()
constraints = 'C(smokes)[T.1]:C(agecat)[3] = C(smokes)[T.1]:C(agec`at)[4]'
import patsy
lc = patsy.DesignInfo(mod.exog_names).linear_constraint(constraints)
R, q = lc.coefs, lc.constants
mod.fit_constrained(R, q, fit_kwds={'method': 'bfgs'})
# example without offset
formula1a = 'deaths ~ logpyears + smokes + C(agecat)'
mod1a = Poisson.from_formula(formula1a, data=data)
mod1a.fit()
lc_1a = patsy.DesignInfo(mod1a.exog_names).linear_constraint(
'C(agecat)[T.4] = C(agecat)[T.5]')
mod1a.fit_constrained(lc_1a.coefs, lc_1a.constants,
fit_kwds={'method': 'newton'})
def junk():
# Singular Matrix in mod1a.fit()
formula1 = 'deaths ~ smokes + C(agecat)'
formula2 = 'deaths ~ C(agecat) + C(smokes) : C(agecat)' # same as Stata default
mod = Poisson.from_formula(formula2, data=data, exposure=data['pyears'].values)
res0 = mod.fit()
constraints = 'C(smokes)[T.1]:C(agecat)[3] = C(smokes)[T.1]:C(agecat)[4]'
import patsy
lc = patsy.DesignInfo(mod.exog_names).linear_constraint(constraints)
R, q = lc.coefs, lc.constants
resc = mod.fit_constrained(R,q, fit_kwds={'method':'bfgs'})
# example without offset
formula1a = 'deaths ~ logpyears + smokes + C(agecat)'
mod1a = Poisson.from_formula(formula1a, data=data)
print(mod1a.exog.shape)
res1a = mod1a.fit()
lc_1a = patsy.DesignInfo(mod1a.exog_names).linear_constraint('C(agecat)[T.4] = C(agecat)[T.5]')
resc1a = mod1a.fit_constrained(lc_1a.coefs, lc_1a.constants, fit_kwds={'method':'newton'})
print(resc1a[0])
print(resc1a[1])
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_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 test_compare_glm_poisson(self):
res1 = self.res1m
res2 = self.res2
formula = 'deaths ~ smokes + C(agecat)'
mod = Poisson.from_formula(
formula,
data=data,
#offset=np.log(data['pyears'].values))
exposure=data['pyears'].values)
constr = 'C(agecat)[T.4] = C(agecat)[T.5]'
res2 = mod.fit_constrained(constr,
start_params=self.res1m.params,
method='newton',
warn_convergence=False,
disp=0)
# we get high precision because we use the params as start_params
# basic, just as check that we have the same model
assert_allclose(res1.params, res2.params, rtol=1e-12)
assert_allclose(res1.bse, res2.bse, rtol=1e-11)
# check predict, fitted, ...
predicted = res1.predict()
assert_allclose(predicted, res2.predict(), rtol=1e-10)
assert_allclose(res1.mu, predicted, rtol=1e-10)
assert_allclose(res1.fittedvalues, predicted, rtol=1e-10)
assert_allclose(res2.predict(linear=True),
res2.predict(linear=True),
rtol=1e-10)
def test_compare_glm_poisson(self):
res1 = self.res1m
res2 = self.res2
formula = 'deaths ~ smokes + C(agecat)'
mod = Poisson.from_formula(formula, data=data,
exposure=data['pyears'].values)
#offset=np.log(data['pyears'].values))
constr = 'C(agecat)[T.4] = C(agecat)[T.5]'
res2 = mod.fit_constrained(constr, start_params=self.res1m.params,
method='newton', warn_convergence=False,
disp=0)
# we get high precision because we use the params as start_params
# basic, just as check that we have the same model
assert_allclose(res1.params, res2.params, rtol=1e-12)
assert_allclose(res1.bse, res2.bse, rtol=1e-12)
# check predict, fitted, ...
predicted = res1.predict()
assert_allclose(predicted, res2.predict(), rtol=1e-10)
assert_allclose(res1.mu, predicted, rtol=1e-10)
assert_allclose(res1.fittedvalues, predicted, rtol=1e-10)
assert_allclose(res2.predict(linear=True), res2.predict(linear=True),
rtol=1e-10)
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_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_noconstraint
cls.idx = [6, 2, 3, 4, 5, 0] # 1 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))
res1 = mod.fit(disp=0)._results
# res1 is duplicate check, so we can follow the same pattern
cls.res1 = (res1.params, res1.cov_params())
cls.res1m = res1
def setup_class(cls):
from statsmodels.discrete.discrete_model import Poisson
import statsmodels.stats.tests.test_anova as ttmod
test = ttmod.TestAnova3()
test.setup_class()
cls.data = test.data.drop([0,1,2])
mod = Poisson.from_formula("Days ~ C(Duration) + C(Weight)", cls.data)
cls.res = mod.fit(cov_type='HC0')
cls.term_name = "C(Weight)"
cls.constraints = ['C(Weight)[T.2]',
'C(Weight)[T.3]',
'C(Weight)[T.3] - C(Weight)[T.2]']
def setup_class(cls):
from statsmodels.discrete.discrete_model import Poisson
import statsmodels.stats.tests.test_anova as ttmod
test = ttmod.TestAnova3()
test.setup_class()
cls.data = test.data.drop([0,1,2])
mod = Poisson.from_formula("Days ~ C(Duration) + C(Weight)", cls.data)
cls.res = mod.fit(cov_type='HC0')
cls.term_name = "C(Weight)"
cls.constraints = ['C(Weight)[T.2]',
'C(Weight)[T.3]',
'C(Weight)[T.3] - C(Weight)[T.2]']
def setup_class(cls):
cls.res2 = results.results_exposure_noconstraint
cls.idx = [6, 2, 3, 4, 5, 0] # 1 is dropped baseline for categorical
# example without offset
formula = 'deaths ~ smokes + C(agecat)'
mod = Poisson.from_formula(formula, data=data,
#exposure=data['pyears'].values)
offset=np.log(data['pyears'].values))
res1 = mod.fit(disp=0)._results
# res1 is duplicate check, so we can follow the same pattern
cls.res1 = (res1.params, res1.cov_params())
cls.res1m = res1
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):
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])
def initialize(cls):
from statsmodels.discrete.discrete_model import Poisson
mod = Poisson.from_formula("Days ~ C(Duration, Sum)*C(Weight, Sum)",
cls.data)
cls.res = mod.fit(cov_type='HC0')
from statsmodels.formula.api import ols, glm, poisson
from statsmodels.discrete.discrete_model import Poisson
import statsmodels.stats.tests.test_anova as ttmod
test = ttmod.TestAnova3()
test.setup_class()
data = test.data.drop([0, 1, 2])
res_ols = ols("np.log(Days+1) ~ C(Duration, Sum)*C(Weight, Sum)",
data).fit(use_t=False)
res_glm = glm("np.log(Days+1) ~ C(Duration, Sum)*C(Weight, Sum)", data).fit()
res_poi = Poisson.from_formula("Days ~ C(Weight) * C(Duration)",
data).fit(cov_type='HC0')
res_poi_2 = poisson("Days ~ C(Weight) + C(Duration)", data).fit(cov_type='HC0')
print('\nOLS')
print(res_ols.wald_test_terms())
print('\nGLM')
print(
res_glm.wald_test_terms(skip_single=False,
combine_terms=['Duration', 'Weight']))
print('\nPoisson 1')
print(
res_poi.wald_test_terms(skip_single=False,
combine_terms=['Duration', 'Weight']))
print('\nPoisson 2')
print(res_poi_2.wald_test_terms(skip_single=False))
from statsmodels.formula.api import ols, glm, poisson
from statsmodels.discrete.discrete_model import Poisson
import statsmodels.stats.tests.test_anova as ttmod
test = ttmod.TestAnova3()
test.setupClass()
data = test.data.drop([0,1,2])
res_ols = ols("np.log(Days+1) ~ C(Duration, Sum)*C(Weight, Sum)", data).fit(use_t=False)
res_glm = glm("np.log(Days+1) ~ C(Duration, Sum)*C(Weight, Sum)",
data).fit()
res_poi = Poisson.from_formula("Days ~ C(Weight) * C(Duration)", data).fit(cov_type='HC0')
res_poi_2 = poisson("Days ~ C(Weight) + C(Duration)", data).fit(cov_type='HC0')
print('\nOLS')
print(res_ols.wald_test_terms())
print('\nGLM')
print(res_glm.wald_test_terms(skip_single=False, combine_terms=['Duration', 'Weight']))
print('\nPoisson 1')
print(res_poi.wald_test_terms(skip_single=False, combine_terms=['Duration', 'Weight']))
print('\nPoisson 2')
print(res_poi_2.wald_test_terms(skip_single=False))
from statsmodels.discrete.discrete_model import NegativeBinomial
res_nb2 = NegativeBinomial.from_formula("Days ~ C(Weight) * C(Duration)", data).fit()
print('\nNegative Binomial nb2')
print(res_nb2.wald_test_terms(skip_single=False))
def initialize(cls):
from statsmodels.discrete.discrete_model import Poisson
mod = Poisson.from_formula("Days ~ C(Duration, Sum)*C(Weight, Sum)", cls.data)
cls.res = mod.fit(cov_type='HC0')
