def _fit_pirls(self, alpha, start_params=None, maxiter=100, tol=1e-8, scale=None, cov_type='nonrobust', cov_kwds=None, use_t=None, weights=None): """fit model with penalized reweighted least squares """ # TODO: this currently modifies several attributes # self.scale, self.scaletype, self.mu, self.weights # self.data_weights, # and possibly self._offset_exposure # several of those might not be necessary, e.g. mu and weights # alpha = alpha * len(y) * self.scale / 100 # TODO: we need to rescale alpha endog = self.endog wlsexog = self.exog # smoother.basis spl_s = self.penal.penalty_matrix(alpha=alpha) nobs, n_columns = wlsexog.shape # TODO what are these values? if weights is None: self.data_weights = np.array([1.] * nobs) else: self.data_weights = weights if not hasattr(self, '_offset_exposure'): self._offset_exposure = 0 self.scaletype = scale # TODO: check default scale types # self.scaletype = 'dev' # during iteration self.scale = 1 if start_params is None: mu = self.family.starting_mu(endog) lin_pred = self.family.predict(mu) else: lin_pred = np.dot(wlsexog, start_params) + self._offset_exposure mu = self.family.fitted(lin_pred) dev = self.family.deviance(endog, mu) history = dict(params=[None, start_params], deviance=[np.inf, dev]) converged = False criterion = history['deviance'] # This special case is used to get the likelihood for a specific # params vector. if maxiter == 0: mu = self.family.fitted(lin_pred) self.scale = self.estimate_scale(mu) wls_results = lm.RegressionResults(self, start_params, None) iteration = 0 for iteration in range(maxiter): # TODO: is this equivalent to point 1 of page 136: # w = 1 / (V(mu) * g'(mu)) ? self.weights = self.data_weights * self.family.weights(mu) # TODO: is this equivalent to point 1 of page 136: # z = g(mu)(y - mu) + X beta ? wlsendog = (lin_pred + self.family.link.deriv(mu) * (endog - mu) - self._offset_exposure) # this defines the augmented matrix point 2a on page 136 wls_results = penalized_wls(wlsendog, wlsexog, spl_s, self.weights) lin_pred = np.dot(wlsexog, wls_results.params).ravel() lin_pred += self._offset_exposure mu = self.family.fitted(lin_pred) # We don't need to update scale in GLM/LEF models # We might need it in dispersion models. # self.scale = self.estimate_scale(mu) history = self._update_history(wls_results, mu, history) if endog.squeeze().ndim == 1 and np.allclose(mu - endog, 0): msg = "Perfect separation detected, results not available" raise PerfectSeparationError(msg) # TODO need atol, rtol # args of _check_convergence: (criterion, iteration, atol, rtol) converged = _check_convergence(criterion, iteration, tol, 0) if converged: break self.mu = mu self.scale = self.estimate_scale(mu) glm_results = GLMGamResults(self, wls_results.params, wls_results.normalized_cov_params, self.scale, cov_type=cov_type, cov_kwds=cov_kwds, use_t=use_t) glm_results.method = "PIRLS" history['iteration'] = iteration + 1 glm_results.fit_history = history glm_results.converged = converged return GLMGamResultsWrapper(glm_results)
def _fit_pirls(self, alpha, start_params=None, maxiter=100, tol=1e-8, scale=None, cov_type='nonrobust', cov_kwds=None, use_t=None, weights=None): """fit model with penalized reweighted least squares """ # TODO: this currently modifies several attributes # self.scale, self.scaletype, self.mu, self.weights # self.data_weights, # and possibly self._offset_exposure # several of those might not be necessary, e.g. mu and weights # alpha = alpha * len(y) * self.scale / 100 # TODO: we need to rescale alpha endog = self.endog wlsexog = self.exog # smoother.basis spl_s = self.penal.penalty_matrix(alpha=alpha) nobs, n_columns = wlsexog.shape # TODO what are these values? if weights is None: self.data_weights = np.array([1.] * nobs) else: self.data_weights = weights if not hasattr(self, '_offset_exposure'): self._offset_exposure = 0 self.scaletype = scale # TODO: check default scale types # self.scaletype = 'dev' # during iteration self.scale = 1 if start_params is None: mu = self.family.starting_mu(endog) lin_pred = self.family.predict(mu) else: lin_pred = np.dot(wlsexog, start_params) + self._offset_exposure mu = self.family.fitted(lin_pred) dev = self.family.deviance(endog, mu) history = dict(params=[None, start_params], deviance=[np.inf, dev]) converged = False criterion = history['deviance'] # This special case is used to get the likelihood for a specific # params vector. if maxiter == 0: mu = self.family.fitted(lin_pred) self.scale = self.estimate_scale(mu) wls_results = lm.RegressionResults(self, start_params, None) iteration = 0 for iteration in range(maxiter): # TODO: is this equivalent to point 1 of page 136: # w = 1 / (V(mu) * g'(mu)) ? self.weights = self.data_weights * self.family.weights(mu) # TODO: is this equivalent to point 1 of page 136: # z = g(mu)(y - mu) + X beta ? wlsendog = (lin_pred + self.family.link.deriv(mu) * (endog - mu) - self._offset_exposure) # this defines the augmented matrix point 2a on page 136 wls_results = penalized_wls(wlsendog, wlsexog, spl_s, self.weights) lin_pred = np.dot(wlsexog, wls_results.params).ravel() lin_pred += self._offset_exposure mu = self.family.fitted(lin_pred) # We don't need to update scale in GLM/LEF models # We might need it in dispersion models. # self.scale = self.estimate_scale(mu) history = self._update_history(wls_results, mu, history) if endog.squeeze().ndim == 1 and np.allclose(mu - endog, 0): msg = "Perfect separation detected, results not available" raise PerfectSeparationError(msg) # TODO need atol, rtol # args of _check_convergence: (criterion, iteration, atol, rtol) converged = _check_convergence(criterion, iteration, tol, 0) if converged: break self.mu = mu self.scale = self.estimate_scale(mu) glm_results = GLMGamResults(self, wls_results.params, wls_results.normalized_cov_params, self.scale, cov_type=cov_type, cov_kwds=cov_kwds, use_t=use_t) glm_results.method = "PIRLS" history['iteration'] = iteration + 1 glm_results.fit_history = history glm_results.converged = converged return GLMGamResultsWrapper(glm_results)