def setup_class(cls):
# generate artificial data
np.random.seed(98765678)
nobs = 200
rvs = np.random.randn(nobs,6)
data_exog = rvs
data_exog = sm.add_constant(data_exog, prepend=False)
xbeta = 1 + 0.1*rvs.sum(1)
data_endog = np.random.poisson(np.exp(xbeta))
mod_glm = sm.GLM(data_endog, data_exog, family=sm.families.Poisson())
cls.res_glm = mod_glm.fit()
#estimate generic MLE
#cls.mod = PoissonGMLE(data_endog, data_exog)
#res = cls.mod.fit()
#create offset variable based on first exog
cls.res_discrete = Poisson(data_endog, data_exog).fit(disp=0)
offset = cls.res_discrete.params[0] * data_exog[:,0] #1d ???
#estimate discretemod.Poisson as benchmark, now has offset
cls.res_discrete = Poisson(data_endog, data_exog[:,1:],
offset=offset).fit(disp=0)
mod_glm = sm.GLM(data_endog, data_exog, family=sm.families.Poisson())
cls.res_glm = mod_glm.fit()
#cls.res = PoissonOffsetGMLE(data_endog, data_exog[:,1:], offset=offset).fit(start_params = np.ones(6)/2., method='nm')
modo = PoissonOffsetGMLE(data_endog, data_exog[:,1:], offset=offset)
cls.res = modo.fit(start_params = 0.9*cls.res_discrete.params,
method='bfgs', disp=0)
def __init__(self):
# generate artificial data
np.random.seed(98765678)
nobs = 200
rvs = np.random.randn(nobs, 6)
data_exog = rvs
data_exog = sm.add_constant(data_exog, prepend=False)
xbeta = 1 + 0.1 * rvs.sum(1)
data_endog = np.random.poisson(np.exp(xbeta))
mod_glm = sm.GLM(data_endog, data_exog, family=sm.families.Poisson())
self.res_glm = mod_glm.fit()
#estimate generic MLE
#self.mod = PoissonGMLE(data_endog, data_exog)
#res = self.mod.fit()
#create offset variable based on first exog
self.res_discrete = Poisson(data_endog, data_exog).fit(disp=0)
offset = self.res_discrete.params[0] * data_exog[:, 0] #1d ???
#estimate discretemod.Poisson as benchmark, now has offset
self.res_discrete = Poisson(data_endog,
data_exog[:, 1:],
offset=offset).fit(disp=0)
# Note : ZI has one extra parameter
self.res = PoissonZiGMLE(
data_endog, data_exog[:, 1:], offset=offset).fit(
start_params=np.r_[0.9 * self.res_discrete.params, 10],
method='bfgs',
disp=0)
self.decimal = 4
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 __init__(self,
endog,
exog,
exog_infl=None,
offset=None,
exposure=None,
inflation='logit',
missing='none',
**kwargs):
super(ZeroInflatedPoisson, self).__init__(endog,
exog,
offset=offset,
inflation=inflation,
exog_infl=exog_infl,
exposure=exposure,
missing=missing,
**kwargs)
self.model_main = Poisson(self.endog,
self.exog,
offset=offset,
exposure=exposure)
self.distribution = zipoisson
self.result_class = ZeroInflatedPoissonResults
self.result_class_wrapper = ZeroInflatedPoissonResultsWrapper
self.result_class_reg = L1ZeroInflatedPoissonResults
self.result_class_reg_wrapper = L1ZeroInflatedPoissonResultsWrapper
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):
expected_params = [1, 1, 0.5]
np.random.seed(987123)
nobs = 500
exog = np.ones((nobs, 2))
exog[:nobs // 2, 1] = 0
# offset is used to create misspecification of the model
# for predicted probabilities conditional moment test
#offset = 0.5 * np.random.randn(nobs)
#range_mix = 0.5
#offset = -range_mix / 2 + range_mix * np.random.rand(nobs)
offset = 0
mu_true = np.exp(exog.dot(expected_params[:-1]) + offset)
endog_poi = np.random.poisson(mu_true / 5)
# endog3 = distr.zigenpoisson.rvs(mu_true, 0,
# 2, 0.01, size=mu_true.shape)
model_poi = Poisson(endog_poi, exog)
res_poi = model_poi.fit(method='bfgs', maxiter=5000, maxfun=5000)
cls.exog = exog
cls.endog = endog_poi
cls.res = res_poi
cls.nobs = nobs
def poisson_regression(self, endog, exog, clean_data="greedy"):
s = self.map_column_to_sheet(endog)
arg_endog = endog
arg_exog = exog
# prepare data
v = np.copy(exog)
v = np.append(v, endog)
dfClean = s.cleanData(v, clean_data)
exog = sm.add_constant(dfClean[exog])
endog = dfClean[endog]
poisson = Poisson(endog, exog)
fit = poisson.fit()
utterance = (
"Here are the results of a Poisson regression with endogenous variables "
)
utterance = (
utterance
+ str(arg_endog)
+ " and exogenous variables "
+ str(arg_exog)
+ ".\n"
)
utterance = utterance + str(fit.summary())
return QueryResult(fit.summary(), utterance)
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 test_netchop_improvement(key):
res = Poisson(
ddf[key].values,
add_constant(ddf.method_simultaneous)
).fit()
print(res.summary())
return res
def setup_class(cls):
expected_params = [1, 1, 0.5]
np.random.seed(987123)
nobs = 500
exog = np.ones((nobs, 2))
exog[:nobs//2, 1] = 0
# offset is used to create misspecification of the model
# for predicted probabilities conditional moment test
#offset = 0.5 * np.random.randn(nobs)
#range_mix = 0.5
#offset = -range_mix / 2 + range_mix * np.random.rand(nobs)
offset = 0
mu_true = np.exp(exog.dot(expected_params[:-1]) + offset)
endog_poi = np.random.poisson(mu_true / 5)
# endog3 = distr.zigenpoisson.rvs(mu_true, 0,
# 2, 0.01, size=mu_true.shape)
model_poi = Poisson(endog_poi, exog)
res_poi = model_poi.fit(method='bfgs', maxiter=5000, maxfun=5000)
cls.exog = exog
cls.endog = endog_poi
cls.res = res_poi
cls.nobs = nobs
def _initialize(cls):
y, x = cls.y, cls.x
modp = Poisson(y, x)
cls.res2 = modp.fit(disp=0)
mod = PoissonPenalized(y, x)
mod.pen_weight = 0
cls.res1 = mod.fit(method='bfgs', maxiter=100, disp=0)
cls.atol = 5e-6
def _initialize(cls):
y, x = cls.y, cls.x
modp = Poisson(y, x)
cls.res2 = modp.fit(disp=0)
mod = PoissonPenalized(y, x)
mod.pen_weight = 0
cls.res1 = mod.fit(method='bfgs', maxiter=100, disp=0)
cls.atol = 5e-6
def setup_class(cls):
# here we don't need to check convergence from default start_params
start_params = [14.1709, 0.7085, -3.4548, -0.539, 3.2368, -7.9299,
-5.0529]
mod_poi = Poisson(endog, exog)
res_poi = mod_poi.fit(start_params=start_params)
marge_poi = res_poi.get_margeff(dummy=True)
cls.res = res_poi
cls.margeff = marge_poi
cls.res1_slice = [0, 1, 2, 3, 5, 6]
cls.res1 = res_stata.results_poisson_margins_dummy
def setup_class(cls):
df = data_bin
mod = GLM(df['constrict'], df[['const', 'log_rate', 'log_volumne']],
family=families.Poisson())
res = mod.fit(attach_wls=True, atol=1e-10)
from statsmodels.discrete.discrete_model import Poisson
mod2 = Poisson(df['constrict'],
df[['const', 'log_rate', 'log_volumne']])
res2 = mod2.fit(tol=1e-10)
cls.infl0 = res.get_influence()
cls.infl1 = res2.get_influence()
def _initialize(cls):
y, x = cls.y, cls.x
modp = Poisson(y, x[:, :cls.k_nonzero])
cls.res2 = modp.fit(disp=0)
mod = PoissonPenalized(y, x, penal=cls.penalty)
mod.pen_weight *= 1.5
mod.penal.tau = 0.05
cls.res1 = mod.fit(method='bfgs', maxiter=100, disp=0)
cls.exog_index = slice(None, cls.k_nonzero, None)
cls.atol = 5e-3
def _initialize(cls):
y, x = cls.y, cls.x
modp = Poisson(y, x[:, :cls.k_nonzero])
cls.res2 = modp.fit(disp=0)
mod = PoissonPenalized(y, x, penal=cls.penalty)
mod.pen_weight *= 1.5
mod.penal.tau = 0.05
cls.res1 = mod.fit(method='bfgs', maxiter=100, disp=0)
cls.exog_index = slice(None, cls.k_nonzero, None)
cls.atol = 5e-3
def setup_class(cls):
# here we don't need to check convergence from default start_params
start_params = [
14.1709, 0.7085, -3.4548, -0.539, 3.2368, -7.9299, -5.0529
]
mod_poi = Poisson(endog, exog)
res_poi = mod_poi.fit(start_params=start_params)
marge_poi = res_poi.get_margeff(dummy=True)
cls.res = res_poi
cls.margeff = marge_poi
cls.res1_slice = [0, 1, 2, 3, 5, 6]
cls.res1 = res_stata.results_poisson_margins_dummy
def setup_class(cls):
# here we don't need to check convergence from default start_params
start_params = [14.1709, 0.7085, -3.4548, -0.539, 3.2368, -7.9299,
-5.0529]
mod_poi = Poisson(endog, exog)
res_poi = mod_poi.fit(start_params=start_params)
#res_poi = mod_poi.fit(maxiter=100)
marge_poi = res_poi.get_margeff()
cls.res = res_poi
cls.margeff = marge_poi
cls.rtol_fac = 1
cls.res1_slice = slice(None, None, None)
cls.res1 = res_stata.results_poisson_margins_cont
def setup_class(cls):
# here we don't need to check convergence from default start_params
start_params = [
14.1709, 0.7085, -3.4548, -0.539, 3.2368, -7.9299, -5.0529
]
mod_poi = Poisson(endog, exog)
res_poi = mod_poi.fit(start_params=start_params)
#res_poi = mod_poi.fit(maxiter=100)
marge_poi = res_poi.get_margeff()
cls.res = res_poi
cls.margeff = marge_poi
cls.rtol_fac = 1
cls.res1_slice = slice(None, None, None)
cls.res1 = res_stata.results_poisson_margins_cont
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_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 setupClass(cls):
data = sm.datasets.randhie.load()
exog = sm.add_constant(data.exog, prepend=False)
cls.res1 = Poisson(data.endog, exog).fit(method='newton', disp=0)
res2 = RandHIE()
res2.poisson()
cls.res2 = res2
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 __init__(self):
# generate artificial data
np.random.seed(98765678)
nobs = 200
rvs = np.random.randn(nobs,6)
data_exog = rvs
data_exog = sm.add_constant(data_exog, prepend=False)
xbeta = 1 + 0.1*rvs.sum(1)
data_endog = np.random.poisson(np.exp(xbeta))
#estimate discretemod.Poisson as benchmark
self.res_discrete = Poisson(data_endog, data_exog).fit(disp=0)
mod_glm = sm.GLM(data_endog, data_exog, family=sm.families.Poisson())
self.res_glm = mod_glm.fit()
#estimate generic MLE
#self.mod = PoissonGMLE(data_endog, data_exog)
#res = self.mod.fit()
offset = self.res_discrete.params[0] * data_exog[:,0] #1d ???
#self.res = PoissonOffsetGMLE(data_endog, data_exog[:,1:], offset=offset).fit(start_params = np.ones(6)/2., method='nm')
modo = PoissonOffsetGMLE(data_endog, data_exog[:,1:], offset=offset)
self.res = modo.fit(start_params = 0.9*self.res_discrete.params[1:],
method='nm', disp=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,
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 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 setupClass(cls):
from results.results_discrete import RandHIE
data = sm.datasets.randhie.load()
exog = sm.add_constant(data.exog)
cls.res1 = Poisson(data.endog, exog).fit(method='newton', disp=0)
res2 = RandHIE()
res2.poisson()
cls.res2 = res2
def testSimulate(self):
np.random.seed(123)
beta0 = np.r_[1.1, 2.2, 3.3, 4.4]
y, X = poisson.simulate(100, beta0)
self.assertEqual(X.shape, (100, 4))
self.assertEqual(y.shape, (100, ))
# try to recover params using frequentist regression
ml_fit = Poisson(y, X).fit()
self.assertLess(np.linalg.norm(beta0 - ml_fit.params, 2), 2.0)
def setup_class(cls):
# copy-paste except for model
nobs, k_vars = 500, 5
np.random.seed(786452)
x = np.random.randn(nobs, k_vars)
x[:, 0] = 1
x2 = np.random.randn(nobs, 2)
xx = np.column_stack((x, x2))
if cls.dispersed:
het = np.random.randn(nobs)
y = np.random.poisson(np.exp(x.sum(1) * 0.5 + het))
#y_mc = np.random.negative_binomial(np.exp(x.sum(1) * 0.5), 2)
else:
y = np.random.poisson(np.exp(x.sum(1) * 0.5))
cls.exog_extra = x2
cls.model_full = Poisson(y, xx)
cls.model_drop = Poisson(y, x)
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):
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 fit(self, rs: RecordSet) -> None:
"""
fit a Probit regression mdl
:param rs: The record set to fit with.
"""
# set params
self.data = cp.deepcopy(rs)
patterns = self.data.entries[:, :-1]
out = self.data.entries[:, -1:]
if self.add_intercept:
intercept = np.ones((patterns.shape[0], 1))
patterns = np.hstack((intercept, patterns))
# avoid error
if self.alpha == 0:
raise Exception("Alpha Probit too low to obtain reliable results")
self.model = Poisson(endog=out.ravel(), exog=patterns)
self.model = self.model.fit_regularized(alpha=self.alpha,
maxiter=10e8,
disp=False)
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 __init__(self, endog, exog, exog_infl=None, offset=None, exposure=None,
inflation='logit', missing='none', **kwargs):
super(ZeroInflatedPoisson, self).__init__(endog, exog, offset=offset,
inflation=inflation,
exog_infl=exog_infl,
exposure=exposure,
missing=missing, **kwargs)
self.model_main = Poisson(self.endog, self.exog, offset=offset,
exposure=exposure)
self.distribution = zipoisson
self.result_class = ZeroInflatedPoissonResults
self.result_class_wrapper = ZeroInflatedPoissonResultsWrapper
self.result_class_reg = L1ZeroInflatedPoissonResults
self.result_class_reg_wrapper = L1ZeroInflatedPoissonResultsWrapper
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_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 __init__(self):
# generate artificial data
np.random.seed(98765678)
nobs = 200
rvs = np.random.randn(nobs,6)
data_exog = rvs
data_exog = sm.add_constant(data_exog, prepend=False)
xbeta = 0.1 + 0.1*rvs.sum(1)
data_endog = np.random.poisson(np.exp(xbeta))
#estimate discretemod.Poisson as benchmark
self.res_discrete = Poisson(data_endog, data_exog).fit(disp=0)
mod_glm = sm.GLM(data_endog, data_exog, family=sm.families.Poisson())
self.res_glm = mod_glm.fit()
#estimate generic MLE
self.mod = PoissonGMLE(data_endog, data_exog)
self.res = self.mod.fit(start_params=0.9 * self.res_discrete.params,
method='nm', 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))
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 test_spec_tests(self):
# regression test, numbers similar to Monte Carlo simulation
res_dispersion = np.array([[0.1396096387543, 0.8889684245877],
[0.1396096387543, 0.8889684245877],
[0.2977840351238, 0.7658680002106],
[0.1307899995877, 0.8959414342111],
[0.1307899995877, 0.8959414342111],
[0.1357101381056, 0.8920504328246],
[0.2776587511235, 0.7812743277372]])
res_zi = np.array([
[00.1389582826821, 0.7093188241734],
[-0.3727710861669, 0.7093188241734],
[-0.2496729648642, 0.8028402670888],
[00.0601651553909, 0.8062350958880],
])
respoi = Poisson(self.endog, self.exog).fit(disp=0)
dia = PoissonDiagnostic(respoi)
t_disp = dia.test_dispersion()[0]
assert_allclose(t_disp, res_dispersion, rtol=1e-8)
nobs = self.endog.shape[0]
t_zi_jh = dia.test_poisson_zeroinflation(method="broek",
exog_infl=np.ones(nobs))
t_zib = dia.test_poisson_zeroinflation(method="broek")
t_zim = dia.test_poisson_zeroinflation(method="prob")
t_zichi2 = dia.test_chisquare_prob(bin_edges=np.arange(3))
t_zi = np.vstack([t_zi_jh[:2], t_zib[:2], t_zim[:2], t_zichi2[:2]])
assert_allclose(t_zi, res_zi, rtol=1e-8)
# test jansakul and hinde with exog_infl
t_zi_ex = dia.test_poisson_zeroinflation(method="broek",
exog_infl=self.exog)
res_zi_ex = np.array([3.7813218150779, 0.1509719973257])
assert_allclose(t_zi_ex[:2], res_zi_ex, rtol=1e-8)
def test_poisson_screening():
np.random.seed(987865)
y, x, idx_nonzero_true, beta = _get_poisson_data()
nobs = len(y)
xnames_true = ['var%4d' % ii for ii in idx_nonzero_true]
xnames_true[0] = 'const'
parameters = pd.DataFrame(beta[idx_nonzero_true],
index=xnames_true,
columns=['true'])
xframe_true = pd.DataFrame(x[:, idx_nonzero_true], columns=xnames_true)
res_oracle = Poisson(y, xframe_true).fit()
parameters['oracle'] = res_oracle.params
mod_initial = PoissonPenalized(y, np.ones(nobs), pen_weight=nobs * 5)
screener = VariableScreening(mod_initial)
exog_candidates = x[:, 1:]
res_screen = screener.screen_exog(exog_candidates, maxiter=10)
assert_equal(np.sort(res_screen.idx_nonzero), idx_nonzero_true)
xnames = ['var%4d' % ii for ii in res_screen.idx_nonzero]
xnames[0] = 'const'
# smoke test
res_screen.results_final.summary(xname=xnames)
res_screen.results_pen.summary()
assert_equal(res_screen.results_final.mle_retvals['converged'], True)
ps = pd.Series(res_screen.results_final.params, index=xnames, name='final')
parameters = parameters.join(ps, how='outer')
assert_allclose(parameters['oracle'], parameters['final'], atol=5e-6)
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')
class PredictPlayerStats(ConvertMixin):
def __init__(self, engine, player_name, stat_to_predict, opposing_team_name,
predictor_stats=('csum_min_kills', 'csum_min_minions_killed'),
defense_predictor_stats=('csum_prev_min_allowed_kills', 'csum_prev_min_allowed_assists'),
game_range=None):
self.engine = engine
self.player_name = player_name
self.stat_to_predict = stat_to_predict
if predictor_stats:
self.predictor_stats = ('csum_prev_min_kills', 'csum_prev_min_minions_killed')
else:
self.predictor_stats = ('csum_prev_min_kills', 'csum_prev_min_minions_killed')
role_stats = ('Jungler', 'Mid', 'Coach', 'Support', 'AD', 'Sub', 'Top')
self.predictor_stats = self.predictor_stats + defense_predictor_stats + role_stats
self.opposing_team_name = opposing_team_name
self.player_stats_table_name = 'player_stats_df'
self.processed_player_stars_table_name = 'processed_player_stats_df'
self.key_stats = ('kills', 'deaths', 'assists', 'minions_killed', 'gold',
'k_a', 'a_over_k')
self.game_range = game_range
self._process_player_stats_and_train()
def _process_player_stats_and_train(self):
processed_player_stats_df = self._get_processed_player_stats_in_df()
self.latest_predictor_numpy_array = self._get_latest_player_stats_numpy_array(processed_player_stats_df)
print('latest predictors numpy array {}'.format(self.latest_predictor_numpy_array))
predictors, y_array = self._get_predictors_in_numpy_arrays(processed_player_stats_df)
self._train_model(predictors, y_array)
def _get_latest_player_stats_numpy_array(self, processed_player_stats_df):
player_id = self._get_player_id_by_player_name(self.player_name)
player_stats_df = processed_player_stats_df[processed_player_stats_df['player_id'] == player_id]
latest_player_stats_df = player_stats_df.sort(['game_id'], ascending=False).head(1)
dict_player = latest_player_stats_df.to_dict('records')[0]
player_predictor_stats = []
for predictor_stat in self.predictor_stats:
# print('processing predictor stat {}'.format(predictor_stat))
player_predictor_stats.append(dict_player[predictor_stat])
latest_predictor_numpy_array = numpy.array([player_predictor_stats])
return latest_predictor_numpy_array
def _get_predictors_in_numpy_arrays(self, processed_player_stats_df):
player_game_records = self._get_predictors(processed_player_stats_df)
game_list = []
y_array_list = []
for player_game_record in player_game_records:
game_predictor_stats = []
if not (numpy.isnan(player_game_record['csum_prev_min_kills'])
or numpy.isnan(player_game_record['csum_prev_min_allowed_kills'])):
if player_game_record['csum_prev_min_assists'] != 0:
prev_predictor_stats = self._convert_predictors_to_prev_csum(self.predictor_stats)
for prev_predictor_stat in prev_predictor_stats:
game_predictor_stats.append(player_game_record[prev_predictor_stat])
game_list.append(game_predictor_stats)
y_array_list.append(player_game_record['y_element'])
predictors = numpy.array(game_list)
y_array = numpy.array([y_array_list])
return predictors, y_array
def _get_predictors(self, processed_player_stats_df):
player_game_records = processed_player_stats_df.to_dict('records')
player_game_records.sort(key=itemgetter('game_id'))
for player_game_record in player_game_records:
player_game_record['y_element'] = player_game_record[self.stat_to_predict]
return player_game_records
def _train_model(self, predictors, y_array):
y_1darray = numpy.squeeze(y_array)
self.poisson = Poisson(y_1darray, predictors)
self.pos_result = self.poisson.fit(method='bfgs')
def _get_game_ids_from_database(self):
game_ids_row = Game.objects.values_list('id', flat=True)
game_ids = [game for game in game_ids_row]
return game_ids
def _get_lastest_processed_team_stats_by_name(self):
return ProcessedTeamStatsDf.objects.filter(name=self.opposing_team_name).order_by('-id').first()
def _get_game_by_ids(self, game_ids):
return Game.objects.filter(id__in=game_ids)
def _get_player_id_by_player_name(self, player_name):
player = Player.objects.filter(name=player_name)
return player[0].id
def _get_processed_player_stats_in_df(self):
game_ids = self._get_game_ids_from_database()
last_game_number = game_ids[-1]
has_processed_team_stats_table = self.engine.has_table(self.processed_player_stars_table_name)
if has_processed_team_stats_table:
df_game_stats = pandas.read_sql(self.player_stats_table_name, self.engine)
df_game_stats_all = df_game_stats[df_game_stats.game_id.isin(game_ids)]
# Using game_numbers here since we need the last few games to check.
max_game_id_cached = df_game_stats_all['game_id'].max()
max_index_cached = df_game_stats_all['index'].max()
if pandas.isnull(max_game_id_cached):
max_game_id_cached = game_ids[0]
# Check if all the game numbers have been cached,
# if not return what game to start form and what game to end from.
if max_game_id_cached != last_game_number:
# Get the index of the max_game_id
max_game_id_index = game_ids.index(max_game_id_cached)
# Trim down the list to only the games that need to be retrieved,
# start from the max_id + 1 because we don't
# want to count max_id we already have it
game_ids_to_find = game_ids[max_game_id_index:]
games = self._get_game_by_ids(game_ids_to_find)
player_stats_df = self._get_player_stats_in_df(games, max_index_cached)
self._insert_into_player_stats_df_tables(player_stats_df)
else:
# If everything was cached return cached as true and just return the last numbers
# I could do this part better.
print("everything cached no need to retrieve from api")
else:
_get_player_stats_in_df = 0
# Table did not exist, have to get all
games = self._get_game_by_ids(game_ids)
player_stats_df = self._get_player_stats_in_df(games, _get_player_stats_in_df)
print('table does not exist inserting full table')
self._insert_into_player_stats_df_tables(player_stats_df)
print('table inserted')
if self.game_range == '5':
processed_player_stats_df = pandas.read_sql('select * from processed_player_stats_df_limit_5',
con=self.engine)
elif self.game_range == '10':
processed_player_stats_df = pandas.read_sql('select * from processed_player_stats_df_limit_10',
con=self.engine)
else:
processed_player_stats_df = pandas.read_sql_table(self.processed_player_stars_table_name, self.engine)
return processed_player_stats_df
def _process_player_stats_df(self, player_stats_df):
player_stats_df = player_stats_df.sort(['game_id', 'player_id'])
key_stats = ['game_length_minutes'] + (list(self.key_stats))
player_stats_df['clean_kills'] = player_stats_df['kills']
player_stats_df.ix[player_stats_df.clean_kills == 0, 'clean_kills'] = 1
player_stats_df['k_a'] = \
player_stats_df['kills'] + player_stats_df['assists']
player_stats_df['a_over_k'] = \
player_stats_df['assists'] / player_stats_df['clean_kills']
player_stats_for_pivot = player_stats_df[['player_name', 'role']]
player_stats_for_pivot['value'] = 1
player_pivot_df = player_stats_for_pivot.pivot_table(index='player_name', columns='role', values='value')
player_pivot_df.fillna(0, inplace=True)
player_pivot_df.reset_index(inplace=True)
player_stats_df = pandas.merge(player_stats_df, player_pivot_df, on='player_name')
for key_stat in key_stats:
print('doing key stats {}'.format(key_stat))
player_stats_df['csum_{}'.format(key_stat)] = player_stats_df.groupby(by='player_id')[key_stat].cumsum()
player_stats_df['csum_prev_{}'.format(key_stat)] = \
player_stats_df['csum_{}'.format(key_stat)] - player_stats_df[key_stat]
# player_stats_df['csum_prev_avg_{}'.format(key_stat)] = \
# player_stats_df['csum_prev_{}'.format(key_stat)] / player_stats_df['csum_prev_game_number']
player_stats_df['per_min_{}'.format(key_stat)] = player_stats_df[key_stat] / \
player_stats_df['game_length_minutes']
if key_stat not in ['game_number', 'game_length_minutes']:
print('doing stats not game_number {}'.format(key_stat))
player_stats_df['csum_min_{}'.format(key_stat)] = \
player_stats_df['csum_{}'.format(key_stat)] / player_stats_df['csum_game_length_minutes']
player_stats_df['csum_prev_min_{}'.format(key_stat)] = \
player_stats_df['csum_prev_{}'.format(key_stat)] / player_stats_df['csum_prev_game_length_minutes']
player_stats_df['csum_prev_min_{}'.format(key_stat)].fillna(0, inplace=True)
player_stats_df = player_stats_df.sort(['game_id'])
return player_stats_df
def _get_player_stats_in_df(self, games, max_index_cached):
player_stats_df = None
for game in games:
players_stats = self._convert_game_to_player_stats_df(game)
if player_stats_df is None:
player_stats_df = pandas.DataFrame(players_stats, index=list(range(max_index_cached, (max_index_cached + 10))))
else:
single_game_player_stats_df = pandas.DataFrame(players_stats, index=list(range(max_index_cached, (max_index_cached + 10))))
player_stats_df = player_stats_df.append(single_game_player_stats_df)
max_index_cached += 10
return player_stats_df
def _convert_game_to_player_stats_df(self, game):
players_stats = game.playerstats_set.all()
players_stats_dict = game.playerstats_set.all().values()
player_stats_list = []
for player_stats, player_stats_dict in zip(players_stats, players_stats_dict):
player_stats_dict['game_length_minutes'] = float(game.game_length_minutes)
player_stats_dict['gold'] = float(player_stats_dict['gold'])
player_stats_dict['player_name'] = player_stats.player.name
self._populate_player_stats_with_defense_stats(player_stats_dict, player_stats, game)
player_stats_list.append(player_stats_dict)
return player_stats_list
def _populate_player_stats_with_defense_stats(self, player_stats_dict, player_stats, game):
current_team = player_stats.team
processed_team_stats_dict = game.processedteamstatsdf_set.exclude(team_name=current_team).values()[0]
for key_stat in self.key_stats:
player_stats_dict['csum_prev_min_allowed_{}'.format(key_stat)] = \
processed_team_stats_dict['csum_prev_min_allowed_{}'.format(key_stat)]
player_stats_dict['csum_min_allowed_{}'.format(key_stat)] = \
processed_team_stats_dict['csum_min_allowed_{}'.format(key_stat)]
def _insert_into_player_stats_df_tables(self, player_stats_df):
player_stats_df.to_sql(self.player_stats_table_name, self.engine, if_exists='append')
# Could be optimized kinda a hack
player_stats_df = pandas.read_sql("select ps.*, p.role, p.image from player_stats_df ps, player p "
"where ps.player_id = p.id", self.engine)
processed_team_stats_df = self._process_player_stats_df(player_stats_df)
processed_team_stats_df.to_sql(self.processed_player_stars_table_name, self.engine, if_exists='append')
def predict_player_stat(self):
#reshaped_numpy_array = numpy.reshape(self.latest_predictor_numpy_array, 3,1)
probability_in_numpy_array = self.poisson.predict(self.pos_result.params, self.latest_predictor_numpy_array)
return {self.player_name: probability_in_numpy_array}
def _train_model(self, predictors, y_array):
y_1darray = numpy.squeeze(y_array)
self.poisson = Poisson(y_1darray, predictors)
self.pos_result = self.poisson.fit(method='bfgs')
class ZeroInflatedPoisson(GenericZeroInflated):
__doc__ = """
Poisson Zero Inflated model for count data
%(params)s
%(extra_params)s
Attributes
-----------
endog : array
A reference to the endogenous response variable
exog : array
A reference to the exogenous design.
exog_infl: array
A reference to the zero-inflated exogenous design.
""" % {'params' : base._model_params_doc,
'extra_params' : _doc_zi_params + base._missing_param_doc}
def __init__(self, endog, exog, exog_infl=None, offset=None, exposure=None,
inflation='logit', missing='none', **kwargs):
super(ZeroInflatedPoisson, self).__init__(endog, exog, offset=offset,
inflation=inflation,
exog_infl=exog_infl,
exposure=exposure,
missing=missing, **kwargs)
self.model_main = Poisson(self.endog, self.exog, offset=offset,
exposure=exposure)
self.distribution = zipoisson
self.result_class = ZeroInflatedPoissonResults
self.result_class_wrapper = ZeroInflatedPoissonResultsWrapper
self.result_class_reg = L1ZeroInflatedPoissonResults
self.result_class_reg_wrapper = L1ZeroInflatedPoissonResultsWrapper
def _hessian_main(self, params):
params_infl = params[:self.k_inflate]
params_main = params[self.k_inflate:]
y = self.endog
w = self.model_infl.predict(params_infl)
w = np.clip(w, np.finfo(float).eps, 1 - np.finfo(float).eps)
score = self.score(params)
zero_idx = np.nonzero(y == 0)[0]
nonzero_idx = np.nonzero(y)[0]
mu = self.model_main.predict(params_main)
hess_arr = np.zeros((self.k_exog, self.k_exog))
coeff = (1 + w[zero_idx] * (np.exp(mu[zero_idx]) - 1))
#d2l/dp2
for i in range(self.k_exog):
for j in range(i, -1, -1):
hess_arr[i, j] = ((
self.exog[zero_idx, i] * self.exog[zero_idx, j] *
mu[zero_idx] * (w[zero_idx] - 1) * (1 / coeff -
w[zero_idx] * mu[zero_idx] * np.exp(mu[zero_idx]) /
coeff**2)).sum() - (mu[nonzero_idx] * self.exog[nonzero_idx, i] *
self.exog[nonzero_idx, j]).sum())
return hess_arr
def _predict_prob(self, params, exog, exog_infl, exposure, offset):
params_infl = params[:self.k_inflate]
params_main = params[self.k_inflate:]
counts = np.atleast_2d(np.arange(0, np.max(self.endog)+1))
if len(exog_infl.shape) < 2:
transform = True
w = np.atleast_2d(
self.model_infl.predict(params_infl, exog_infl))[:, None]
else:
transform = False
w = self.model_infl.predict(params_infl, exog_infl)[:, None]
w = np.clip(w, np.finfo(float).eps, 1 - np.finfo(float).eps)
mu = self.model_main.predict(params_main, exog,
offset=offset)[:, None]
result = self.distribution.pmf(counts, mu, w)
return result[0] if transform else result
def _get_start_params(self):
start_params = self.model_main.fit(disp=0, method="nm").params
start_params = np.append(np.ones(self.k_inflate) * 0.1, start_params)
return start_params
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')
nobs = 1000
rvs = np.random.randn(nobs,6)
data_exog = rvs
data_exog = sm.add_constant(data_exog)
xbeta = 1 + 0.1*rvs.sum(1)
data_endog = np.random.poisson(np.exp(xbeta))
#print data_endog
modp = PoissonGMLE(data_endog, data_exog)
resp = modp.fit()
print resp.params
print resp.bse
from statsmodels.discrete.discrete_model import Poisson
resdp = Poisson(data_endog, data_exog).fit()
print '\ncompare with discretemod'
print 'compare params'
print resdp.params - resp.params
print 'compare bse'
print resdp.bse - resp.bse
gmlp = sm.GLM(data_endog, data_exog, family=sm.families.Poisson())
resgp = gmlp.fit()
''' this creates a warning, bug bse is double defined ???
c:\josef\eclipsegworkspace\statsmodels-josef-experimental-gsoc\scikits\statsmodels\decorators.py:105: CacheWriteWarning: The attribute 'bse' cannot be overwritten
warnings.warn(errmsg, CacheWriteWarning)
'''
print '\ncompare with GLM'
print 'compare params'
print resgp.params - resp.params