class ZeroInflatedNegativeBinomialP(GenericZeroInflated):
__doc__ = """
Zero Inflated Generalized Negative Binomial 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.
p: scalar
P denotes parametrizations for ZINB regression. p=1 for ZINB-1 and
p=2 for ZINB-2. Default is p=2
""" % {'params' : base._model_params_doc,
'extra_params' : _doc_zi_params +
"""p : float
dispersion power parameter for the NegativeBinomialP model. p=1 for
ZINB-1 and p=2 for ZINM-2. Default is p=2
""" + base._missing_param_doc}
def __init__(self, endog, exog, exog_infl=None, offset=None, exposure=None,
inflation='logit', p=2, missing='none', **kwargs):
super(ZeroInflatedNegativeBinomialP, self).__init__(endog, exog,
offset=offset,
inflation=inflation,
exog_infl=exog_infl,
exposure=exposure,
missing=missing, **kwargs)
self.model_main = NegativeBinomialP(self.endog, self.exog,
offset=offset, exposure=exposure, p=p)
self.distribution = zinegbin
self.k_exog += 1
self.k_extra += 1
self.exog_names.append("alpha")
self.result_class = ZeroInflatedNegativeBinomialResults
self.result_class_wrapper = ZeroInflatedNegativeBinomialResultsWrapper
self.result_class_reg = L1ZeroInflatedNegativeBinomialResults
self.result_class_reg_wrapper = L1ZeroInflatedNegativeBinomialResultsWrapper
def _get_init_kwds(self):
kwds = super(ZeroInflatedNegativeBinomialP, self)._get_init_kwds()
kwds['p'] = self.model_main.parameterization
return kwds
def _predict_prob(self, params, exog, exog_infl, exposure, offset):
params_infl = params[:self.k_inflate]
params_main = params[self.k_inflate:]
p = self.model_main.parameterization
counts = 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,
exposure=exposure, offset=offset)[:, None]
result = self.distribution.pmf(counts, mu, params_main[-1], p, w)
return result[0] if transform else result
def _get_start_params(self):
with warnings.catch_warnings():
warnings.simplefilter("ignore", category=ConvergenceWarning)
start_params = self.model_main.fit(disp=0, method='nm').params
start_params = np.append(np.zeros(self.k_inflate), start_params)
return start_params
class ZeroInflatedNegativeBinomialP(GenericZeroInflated):
__doc__ = """
Zero Inflated Generalized Negative Binomial Model
%(params)s
%(extra_params)s
Attributes
----------
endog : ndarray
A reference to the endogenous response variable
exog : ndarray
A reference to the exogenous design.
exog_infl : ndarray
A reference to the zero-inflated exogenous design.
p : scalar
P denotes parametrizations for ZINB regression. p=1 for ZINB-1 and
p=2 for ZINB-2. Default is p=2
""" % {'params' : base._model_params_doc,
'extra_params' : _doc_zi_params +
"""p : float
dispersion power parameter for the NegativeBinomialP model. p=1 for
ZINB-1 and p=2 for ZINM-2. Default is p=2
""" + base._missing_param_doc}
def __init__(self, endog, exog, exog_infl=None, offset=None, exposure=None,
inflation='logit', p=2, missing='none', **kwargs):
super(ZeroInflatedNegativeBinomialP, self).__init__(endog, exog,
offset=offset,
inflation=inflation,
exog_infl=exog_infl,
exposure=exposure,
missing=missing, **kwargs)
self.model_main = NegativeBinomialP(self.endog, self.exog,
offset=offset, exposure=exposure, p=p)
self.distribution = zinegbin
self.k_exog += 1
self.k_extra += 1
self.exog_names.append("alpha")
self.result_class = ZeroInflatedNegativeBinomialResults
self.result_class_wrapper = ZeroInflatedNegativeBinomialResultsWrapper
self.result_class_reg = L1ZeroInflatedNegativeBinomialResults
self.result_class_reg_wrapper = L1ZeroInflatedNegativeBinomialResultsWrapper
def _get_init_kwds(self):
kwds = super(ZeroInflatedNegativeBinomialP, self)._get_init_kwds()
kwds['p'] = self.model_main.parameterization
return kwds
def _predict_prob(self, params, exog, exog_infl, exposure, offset,
y_values=None):
params_infl = params[:self.k_inflate]
params_main = params[self.k_inflate:]
p = self.model_main.parameterization
if y_values is None:
y_values = 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,
exposure=exposure, offset=offset)[:, None]
result = self.distribution.pmf(y_values, mu, params_main[-1], p, w)
return result[0] if transform else result
def _predict_var(self, params, mu, prob_infl):
"""predict values for conditional variance V(endog | exog)
Parameters
----------
params : array_like
The model parameters. This is only used to extract extra params
like dispersion parameter.
mu : array_like
Array of mean predictions for main model.
prob_inlf : array_like
Array of predicted probabilities of zero-inflation `w`.
Returns
-------
Predicted conditional variance.
"""
alpha = params[-1]
w = prob_infl
p = self.model_main.parameterization
var_ = (1 - w) * mu * (1 + alpha * mu**(p - 1) + w * mu)
return var_
def _get_start_params(self):
with warnings.catch_warnings():
warnings.simplefilter("ignore", category=ConvergenceWarning)
start_params = self.model_main.fit(disp=0, method='nm').params
start_params = np.append(np.zeros(self.k_inflate), start_params)
return start_params
@Appender(ZeroInflatedPoisson.get_distribution.__doc__)
def get_distribution(self, params, exog=None, exog_infl=None,
exposure=None, offset=None):
p = self.model_main.parameterization
mu = self.predict(params, exog=exog, exog_infl=exog_infl,
exposure=exposure, offset=offset, which="mean-main")
w = self.predict(params, exog=exog, exog_infl=exog_infl,
exposure=exposure, offset=offset, which="prob-main")
distr = self.distribution(mu[:, None], params[-1], p, 1 - w[:, None])
return distr