metacountregressor 0.1.238__py3-none-any.whl → 0.1.241__py3-none-any.whl

metacountregressor/helperprocess.py

@@ -45,6 +45,43 @@ def delete_all_folders(directory_path):
     except Exception as e:
         print(f"An error occurred: {e}")
 
+def delete_all_contents(directory_path):
+    try:
+        # Check if the directory exists
+        if not os.path.exists(directory_path):
+            print(f"The directory '{directory_path}' does not exist.")
+            return
+
+        # Iterate through items in the directory
+        for item in os.listdir(directory_path):
+            item_path = os.path.join(directory_path, item)
+            
+            # If the item is a directory, delete it
+            if os.path.isdir(item_path):
+                shutil.rmtree(item_path)  # Recursively delete the folder
+                print(f"Deleted folder: {item_path}")
+            else:
+                # If the item is a file, delete it
+                os.remove(item_path)
+                print(f"Deleted file: {item_path}")
+                
+        print("All contents deleted successfully.")
+    except Exception as e:
+        print(f"An error occurred: {e}")
+
+def delete_folder_and_contents(directory_path):
+    try:
+        # Check if the directory exists
+        if not os.path.exists(directory_path):
+            print(f"The directory '{directory_path}' does not exist.")
+            return
+
+        # Delete the entire folder and its contents
+        shutil.rmtree(directory_path)
+        print(f"Deleted folder and all its contents: {directory_path}")
+    except Exception as e:
+        print(f"An error occurred: {e}")
+
 
 
 ##Select the best Features Based on RF

metacountregressor/metaheuristics.py

@@ -236,15 +236,15 @@ def differential_evolution(objective_function, initial_slns=None, **kwargs):
     else:
         de = DifferentialEvolution(objective_function, **kwargs)
 
-        iterations, solutions, best_solutions, best_fitness, best_struct, average_best = de.differential_evolution_run(
+        iterations, solutions, best_solutions, best_fitness, best_struct = de.differential_evolution_run(
             initial_slns=initial_slns, mod_init=man)
-
+        AVERAGE_BEST = st.mean(best_solutions)
         end = datetime.now()
         elapsed_time = end - start
         return DifferentialEvolutionResults(elapsed_time=elapsed_time, iteration=iterations,
                                             iter_solution=solutions, best_solutions=best_solutions,
                                             best_fitness=best_fitness,
-                                            best_struct=best_struct, average_best=average_best)
+                                            best_struct=best_struct, average_best=AVERAGE_BEST)
 
 
 def simulated_annealing(objective_function, initial_slns=None, **kwargs):

metacountregressor/solution.py

@@ -33,6 +33,7 @@ from statsmodels.tools.numdiff import approx_fprime, approx_hess
 from sklearn.preprocessing import StandardScaler, MinMaxScaler
 from texttable import Texttable
 import time
+
 try:
     from ._device_cust import device as dev
     from .pareto_file import Pareto, Solution
@@ -121,14 +122,16 @@ class ObjectiveFunction(object):
     """
 
     def __init__(self, x_data, y_data, **kwargs):
+        self.gbl_best = 1000000.0
+        self.run_bootstrap =  kwargs.get('run_bootstrap', False)
         self.linear_regression = kwargs.get('linear_model', False)
-        self.reg_penalty = 0
+        self.reg_penalty = 1
         self.power_up_ll = False
         self.nb_parma = 1
         self.bic = None
         self.other_bic = False
         self.test_flag = 1
-        self.no_extra_param =1 #if true, fix dispersion. w
+        self.no_extra_param =0  #if true, fix dispersion. w
         if self.other_bic:
             print('change this to false latter ')
 
@@ -150,7 +153,7 @@ class ObjectiveFunction(object):
         self.rdm_fit = None
         self.rdm_cor_fit = None
         self.dist_fit = None
-        self.rounding_point = kwargs.get('decimals_in_coeff', 2)
+        self.rounding_point = kwargs.get('decimals_in_coeff', 4)
         self.MAE = None
         self.best_obj_1 = 1000000.0
         self._obj_1 = kwargs.get('_obj_1', 'bic') 
@@ -425,7 +428,7 @@ class ObjectiveFunction(object):
 
 
 
-        self.Ndraws = kwargs.get('Ndraws', 200)
+        self.Ndraws = kwargs.get('Ndraws', 100)
         self.draws1 = None
         self.initial_sig = 1  # pass the test of a single model
         self.pvalue_sig_value = .1
@@ -446,10 +449,9 @@ class ObjectiveFunction(object):
             print('Setup Complete...')
             self._characteristics_names = list(self._x_data.columns)
         # define the variables
-        # self._transformations = ["no", "sqrt", "log", "exp", "fact", "arcsinh", 2, 3]
-        self._transformations = ["no", "sqrt", "log", "arcsinh"]
-        self._transformations = kwargs.get('_transformation', ["no", "sqrt", "log", 'arcsinh'])
-        self._transformations = kwargs.get('_transformation', ["no", "log", "sqrt", "arcsinh"])
+       
+       
+        self._transformations = kwargs.get('_transformations', ["no", "log", "sqrt", "arcsinh"])
         # self._distribution = ['triangular', 'uniform', 'normal', 'ln_normal', 'tn_normal', 'lindley']
 
         self._distribution = kwargs.get('_distributions', ['triangular', 'uniform', 'normal', 'ln_normal', 'tn_normal'])
@@ -485,8 +487,8 @@ class ObjectiveFunction(object):
             model_types = [[0, 1]]  # add 2 for Generalized Poisson
             #model_types = [[0]]
         
-        if self:
-            model_types = [[0]]
+        if self.linear_regression:
+            model_types = [[1]]
             self.grad_yes = False
             
             print(f'Linear Model Selected: turning off gradient calculation')
@@ -494,6 +496,11 @@ class ObjectiveFunction(object):
 
         model_t_dict = {'Poisson':0,
                         "NB":1}
+        if self.linear_regression:
+        # Rename key "NB" to "sigma" if it exists in the dictionary
+            if "NB" in model_t_dict:
+                model_t_dict["sigma"] = model_t_dict.pop("NB")
+
         # Retrieve the keys (model names) corresponding to the values in model_types
         model_keys = [key for key, value in model_t_dict.items() if value in model_types[0]]
         # Print the formatted result
@@ -503,6 +510,7 @@ class ObjectiveFunction(object):
 
         self._model_type_codes = ['p', 'nb',
                                   'gp', "pl", ["nb-theta", 'nb-dis']]
+        self.update_model_type_codes()
         self._variable = [True] * len(self._discrete_values)
         self._lower_bounds = [None] * \
                              len(self._discrete_values)  # TODO have continus
@@ -522,7 +530,18 @@ class ObjectiveFunction(object):
 
         self.solution_analyst = None
 
+    def update_model_type_codes(self):
+        if self.linear_regression:
+            # Recursively update all occurrences of 'nb' to 'sigma'
+            def replace_nb_with_sigma(item):
+                if isinstance(item, list):
+                    return [replace_nb_with_sigma(sub_item) for sub_item in item]
+                elif item == 'nb':
+                    return 'sigma'
+                return item
 
+            # Update the _model_type_codes list
+            self._model_type_codes = replace_nb_with_sigma(self._model_type_codes)
 
 
     def over_ride_self(self, **kwargs):
@@ -584,6 +603,7 @@ class ObjectiveFunction(object):
         self.set_defined_seed(42)  # Set a specific seed
 
         modified_fit = self.modify_initial_fit(manual_fit)  # Modify the initial fit based on manual_fit
+        self.significant = 1
         self.makeRegression(modified_fit)  # Perform regression with the modified fit
 
 
@@ -820,6 +840,10 @@ class ObjectiveFunction(object):
 
         if dispersion == 0:
             return None
+        if dispersion == 1:
+            return np.clip(np.exp(betas[-1]),None, 2)
+            
+
         elif dispersion == 2 or dispersion == 1:
             if self.no_extra_param:
                 return self.nb_parma
@@ -1085,15 +1109,7 @@ class ObjectiveFunction(object):
                                    [''] * (len(names) - len(self.transform_id_names))
             self.coeff_names = names
 
-        '''
-        if betas is not None:
-            try:
-                if len(betas) != len(names):
-                    print('standard_model', no_draws)
-
-            except Exception as e:
-                print(e)
-        '''
+       
 
 
 
@@ -1134,7 +1150,8 @@ class ObjectiveFunction(object):
                     print("-" * 80)
 
                 if solution is not None:
-                    print(f"{self._obj_2}: {self.round_with_padding(solution[self._obj_2], 2)}")
+                    if self.is_multi:
+                        print(f"{self._obj_2}: {self.round_with_padding(solution[self._obj_2], 2)}")
             
             self.pvalues = [self.round_with_padding(
                 x, 2) for x in self.pvalues]
@@ -1148,13 +1165,15 @@ class ObjectiveFunction(object):
                     self.zvalues = np.append(self.zvalues, 50)
 
                 elif self.coeff_[-1] < 0.25:
-                    print(self.coeff_[-1], 'Warning Check Dispersion')
-                    print(np.exp(self.coeff_[-1]))
+                    #print(self.coeff_[-1], 'Warning Check Dispersion')
+                    print(f'dispession is para,aters {np.exp(self.coeff_[-1])}')
                     #self.coeff_[-1] = np.exp(self.coeff_[-1])  # min possible value for negbinom
+            
 
 
+    
+            self.coeff_ = self.convert_coefficients(self.coeff_, model)
             self.coeff_ = [self.round_with_padding(x, self.rounding_point) for x in self.coeff_]
-
             self.stderr = [self.round_with_padding(x, 2) for x in self.stderr]
             self.zvalues = [self.round_with_padding(
                 x, 2) for x in self.zvalues]
@@ -1969,7 +1988,7 @@ class ObjectiveFunction(object):
                 subpvalues = pvalues.copy()
             else:
                 slice_this_amount = self.num_dispersion_params(dispersion)
-                slice_this_amount = 0  # TODO handle this
+                
                 if pvalues[-1] > sig_value:
                     vio_counts += 1
                 subpvalues = pvalues[:-slice_this_amount].copy()
@@ -2379,6 +2398,12 @@ class ObjectiveFunction(object):
         else:
             sorted(my_dict, key=lambda x: x[0]['pval_percentage'])
 
+    def update_gbl_best(self, obj_1):
+        '''Method to update the global best solution. Also sets the significant attribute to 1 if the global best is updated'''
+        if self.gbl_best > obj_1[self._obj_1]:
+            self.gbl_best = obj_1[self._obj_1]
+            self.significant = 1
+
     def get_fitness(self, vector, multi=False, verbose=False, max_routine=3):
         obj_1 = 10.0 ** 4
         obj_best = None
@@ -2405,7 +2430,7 @@ class ObjectiveFunction(object):
 
         a = {}
         obj_1, model_mod = self.makeRegression(model_nature, layout=layout, **a)
-
+        self.update_gbl_best(obj_1)
         if self.pvalues is None:
             self.reset_sln()
             return obj_1
@@ -3255,6 +3280,35 @@ class ObjectiveFunction(object):
         print('output', out)
         return out
 
+    def custom_betas_to_penalise(self, params, dispersion):
+        num_params = self.get_num_params()
+        skip_count = sum(num_params[:2])
+        betas_start = params[:skip_count]
+        if dispersion:
+            betas_end = params[-dispersion:]
+            betas_ = np.concatenate((betas_start,betas_end))
+            return betas_
+        else: return betas_start
+
+
+    def convert_coefficients(self, params, dispersion):
+        num_params = self.get_num_params()
+        skip_count = sum(num_params[:2])
+        remain_params = num_params[2:]
+        params[skip_count:skip_count+remain_params[1]] = np.abs(params[skip_count:skip_count+remain_params[1]])
+        return params
+            
+        
+
+    def custom_penalty(self, params, penalty):
+        num_params = self.get_num_params()
+        skip_count = sum(num_params[:2])
+        
+        for i in params[skip_count:-1]:
+            if i < 0.25:
+                penalty += self.reg_penalty*np.maximum(0, 2.25 -i)**2
+        return penalty
+
     # p is the paramaterisation GP1 is at 0
     def general_poisson(self, mu, y, nu, p=0):  # TODO laxywhere??
 
@@ -3917,8 +3971,10 @@ class ObjectiveFunction(object):
 
         
         if dispersion:
+            sigma = dispersion
             eta=  np.dot(Xd, params_main)[:, :, None] + np.array(offset[:, :, :])
 
+            epsilon = np.random.normal(loc=0, scale=sigma, size=eta.shape)
             #eta=  np.dot(Xd, params_main)[:, :, None] + np.array(offset[:, :, :])+dispersion
             #print('check if this holds size')
         else:
@@ -3927,7 +3983,7 @@ class ObjectiveFunction(object):
 
 
         if linear:
-            eta = eta.astype('float')
+            eta = eta.astype('float') +epsilon.astype('float')
             return eta
 
 
@@ -4585,7 +4641,48 @@ class ObjectiveFunction(object):
 
         brstd = br_std
 
+    def _loglik_prefit(self, betas, Xd, y, draws=None, Xf=None, Xr=None, batch_size=None, return_gradient=False,
+                         return_gradient_n=False, dispersion=0, test_set=0, return_EV=False, verbose=0, corr_list=None,
+                         zi_list=None, exog_infl=None, draws_grouped=None, Xgroup=None, model_nature=None, kwarg=None,
+                         **kwargs):
+        """Fixed and random parameters are handled separately to speed up the estimation and the results are concatenated.
+        pass
+        """
+        pass
+    def _linear_logliklihood(self, y, eta, sigma):
+        """
+        Calculate the log-likelihood for a linear regression model with random parameters.
+
+        Parameters:
+        y (np.ndarray): Observed responses (n_samples,).
+        eta (np.ndarray): Predicted values (linear predictor) (n_samples, 1, n_draws).
+        sigma (float): Standard deviation of the error term.
+
+        Returns:
+        float: The log-likelihood value aggregated across all draws.
+        """
+        n_samples, _, n_draws = eta.shape  # Number of observations and draws
+
+        # Repeat y to match the shape of eta
+        y_repeated = np.repeat(y, n_draws, axis=2)  # Shape (n_samples, 1, n_draws)
 
+        # Calculate residuals for each draw
+        residuals = y_repeated - eta  # Shape (n_samples, 1, n_draws)
+
+        # Calculate the residual sum of squares (RSS) for each draw
+        rss = np.sum(residuals ** 2, axis=(0, 1))  # Shape (n_draws,)
+
+        # Log-likelihood for each draw
+        log_likelihood_per_draw = (
+            -0.5 * n_samples * np.log(2 * np.pi)  # Constant term
+            - 0.5 * n_samples * np.log(sigma**2)  # Variance term
+            - 0.5 * rss / sigma**2                # Residual term
+        )  # Shape (n_draws,)
+
+        # Aggregate across draws (e.g., take the mean log-likelihood)
+        log_likelihood_value = np.mean(log_likelihood_per_draw)
+
+        return log_likelihood_value
 
     def _loglik_gradient(self, betas, Xd, y, draws=None, Xf=None, Xr=None, batch_size=None, return_gradient=False,
                          return_gradient_n=False, dispersion=0, test_set=0, return_EV=False, verbose=0, corr_list=None,
@@ -4650,8 +4747,9 @@ class ObjectiveFunction(object):
 
                 if self.linear_regression:
                     # LINEAR MODEL PROCESS
-                    mse = np.mean((y - eVd) ** 2)
-                    return mse
+                    mse = self._linear_logliklihood(y, eVd, main_disper)
+                    #mse = np.mean((y - eVd) ** 2)
+                    return (-mse + penalty)*self.minimize_scaler
 
                 ### GLM PROCESS ########
                 llf_main = self.loglik_obs(
@@ -4667,7 +4765,10 @@ class ObjectiveFunction(object):
 
                     loglik += 2*loglik
                     print('am i powering up')
-                penalty =  self.regularise_l2(betas)
+                
+                b_pen = self.custom_betas_to_penalise(betas, dispersion)
+                penalty =  self.regularise_l2(betas) + self.regularise_l1(betas)
+                penalty = self.custom_penalty(betas, penalty)
 
                 if not np.isreal(loglik):
                     loglik = - 10000000.0
@@ -4884,12 +4985,24 @@ class ObjectiveFunction(object):
                 betas_hetro_sd = None
 
             Vdr = dev.cust_einsum("njk,nkr -> njr", Xdr, Br)  # (N,P,R)
-            if self:
+            if self.linear_regression:
                 ### LINEAR MODEL WAY #######
                 eVd = np.clip(
                 Vdf[:, :, None] + Vdr + Vdh + dev.np.array(offset), None, None)
-                mse = np.mean((y - eVd) ** 2)
-                return mse
+                main_disper = self.get_dispersion_paramaters(betas, dispersion)
+                penalty, main_disper = self._penalty_dispersion(
+                    dispersion, main_disper, eVd, y, penalty, model_nature)
+                error_term = np.random.normal(loc=0, scale=main_disper, size=eVd.shape)
+                b_pen = self.custom_betas_to_penalise(betas, dispersion)
+                penalty += self.regularise_l2(b_pen) + self.regularise_l1(b_pen)
+                #penalty = 0
+                penalty = self.custom_penalty(betas, penalty)
+                    # LINEAR MODEL PROCESS
+                mse = self._linear_logliklihood(y, eVd, main_disper)
+                    #mse = np.mean((y - eVd) ** 2)
+                    
+                return -mse + penalty
+                
 
             ##### GLM WAY #####
             eVd = dev.np.exp(np.clip(
@@ -4955,7 +5068,7 @@ class ObjectiveFunction(object):
             if self.power_up_ll:
                 penalty += self.regularise_l2(betas)
 
-            penalty += self.regularise_l2(betas)
+            penalty += self.regularise_l2(betas) + self.regularise_l1(betas)
             if not return_gradient:
 
                 output = ((-loglik + penalty)*self.minimize_scaler,)
@@ -5018,6 +5131,11 @@ class ObjectiveFunction(object):
         else:
             return -self.reg_penalty*sum(np.square(betas.copy()))
 
+    def regularise_l1(self, betas, backwards = False):
+        if backwards == False:
+            return self.reg_penalty*sum(np.square(betas.copy()))
+        else:
+            return -self.reg_penalty*sum(np.abs(betas.copy()))
 
     def _concat_gradients(self, gr_f):
         gr = np.concatenate((gr_f), axis=1)
@@ -5453,20 +5571,36 @@ class ObjectiveFunction(object):
         # self.grad_n = optim_res['grad_n']
         # self.total_fun_eval = optim_res['nfev']2
 
+    def handle_covariance(self, covariance):
+        """
+        Safely handle covariance matrix, converting it to a dense NumPy array if needed.
+
+        Parameters:
+            covariance: The covariance matrix, which may be a `LbfgsInvHessProduct`.
+
+        Returns:
+            A dense NumPy array of the covariance matrix.
+        """
+        # Check if the covariance is an `LbfgsInvHessProduct`
+        if hasattr(covariance, "todense"):
+            # Convert to a dense NumPy array
+            covariance = covariance.todense()
+        return covariance
+
+
     def _post_fit_ll_aic_bic(self, optim_res, verbose=1, robust=False, simple_fit=True, is_dispersion=0):
         # sample_size = len(self._x_data) - len(optim_res['x']) -1
         sample_size = len(self._x_data)
         convergence = optim_res['success']
         coeff_ = optim_res['x']
         penalty = 0
-        for i in coeff_:  # pvalue penalty should handle this
-            if abs(i) > 120:
-                penalty += abs(i)
+        
         if 'hess_inv' in optim_res:
             covariance = self._robust_covariance(optim_res['hess_inv'], optim_res['grad_n']) \
                 if robust else optim_res['hess_inv']
         else:
             covariance = np.diag(np.ones(len(optim_res.x)))
+        covariance = self.handle_covariance(covariance)
         covariance = np.clip(covariance, 0, None)
         stderr = np.sqrt(np.diag(covariance))
         # stderr =  [if np.abs(optim_res['x'][i]) >.1 else min(np.abs(optim_res['x'][i]/1.5), stderr[i]) for i in range(len(optim_res['x']))]
@@ -5474,16 +5608,7 @@ class ObjectiveFunction(object):
         # stderr = [np.min(np.abs(optim_res['x'][i]/random.uniform(1.8, 3)), stderr[i]) if i > len(self.none_handler(self.fixed_fit)) and np.abs(optim_res['x'][i] > 0.2) else stderr[i] for i in range(len(optim_res['x']))]
         if is_dispersion:
             stderr[-1] = random.uniform(0.001, 0.005)
-        if simple_fit == False:
-            # gets the number of parmas before the correlations
-            pre_cor_pams = sum(self.get_num_params()[:3])
-            # gets the number of correlated rpm
-            post_cor_pams = sum(self.get_num_params()[:5])
-
-
-            # this calculation takes into account the correlated rpms distinct values
-            for i in range(pre_cor_pams, post_cor_pams):
-                stderr[i] = stderr[i] / np.sqrt(sample_size)
+        
 
         if np.isnan(stderr).any():
             raise ValueError("Error: Matrix contains NaN values")
@@ -5496,6 +5621,9 @@ class ObjectiveFunction(object):
             optim_res['fun'] = 10.0 ** 10
         if self.power_up_ll:
             loglikelihood =-optim_res['fun']/2 - penalty
+        elif self.linear_regression:
+            loglikelihood= -optim_res['fun']
+    
         else:
             loglikelihood = -optim_res['fun']/self.minimize_scaler - penalty
 
@@ -5542,10 +5670,9 @@ class ObjectiveFunction(object):
             self.none_handler(self.rdm_cor_fit) + \
             self.get_dispersion_name(dispersion)
         return a
-
-    def fitRegression(self, mod,
+    
+    def fitRegression_prefit(self, mod,
                       dispersion=0, maxiter=2000, batch_size=None, num_hess=False, **kwargs):
-
         """
         Fits a poisson regression given data and outcomes if dispersion is not declared
         if declared, fits a NB (dispersion = 1) regression or GP (disperions = 2)
@@ -5581,7 +5708,714 @@ class ObjectiveFunction(object):
             zvalues = None
             if mod.get('Xr') is not None or mod.get('XG') is not None or mod.get('XH') is not None:
                 calc_gradient = True
+                calc_gradient = False if self.linear_regression else True
+                n, p, k = mod.get('X').shape
+                _r, pr, kr = mod.get('Xr').shape
+                kh = mod.get('XH').shape[2]
+
+                if 'XG' in mod:
+                    _g, pg, kg = mod.get('XG').shape
+                else:
+                    _g, pg, kg = 0, 0, 0
+
+                dispersion_param_num = self.is_dispersion(dispersion)
+                if self.no_extra_param:
+                    dispersion_param_num =0
+
+                #paramNum = self.get_param_num(dispersion)
+                self.no_random_paramaters = 0
+                if 'XG' in mod:
+                    XX = np.concatenate((mod.get('X'), mod.get('XG'), mod.get('Xr'), mod.get('XH')), axis=2)
+                elif 'XH' in mod:
+                    XX = np.concatenate((mod.get('X'), mod.get('Xr'), mod.get('XH')), axis=2)
+                else:
+                    XX = np.concatenate((mod.get('X'), mod.get('Xr')), axis=2)
+
+                if self.is_multi:
+                    if mod.get('X_test') is not None and mod.get('Xr_test') is not None:
+                        if 'XH' in mod:
+                            XX_test = np.concatenate((mod.get('X_test'), mod.get('Xr_test'), mod.get('XH_test')),
+                                                     axis=2)
+                        else:
+                            XX_test = np.concatenate((mod.get('X_test'), mod.get('Xr_test')), axis=2)
+
+
+
+                    else:
+
+                        XX = mod.get('Xr')
+                        if mod.get('Xr_test') is not None:
+                            XX_test = mod.get('Xr_test')
+
+                bb = np.random.uniform(
+                    -0.05, 0.05, size=k + kr + kg + kh + dispersion_param_num)
+
+                if method == 'L-BFGS-B':
+                    if dispersion == 0:
+                        bounds = []
+                        for i in bb:
+                            bounds = bounds + [(i - 30, i + 30)]
+
+                        # bound = [(-100,100) ]*len(b)
+
+                    elif dispersion == 1:  # TODO test bounds was NOne
+                        bounds = []
+                        for i in bb[:-1]:
+                            bounds = bounds + [(i - 30, i + 30)]
+                        bounds = bounds + [(-1, 5)]
+
+                    elif dispersion == 2:
+                        bounds = []
+                        for i in bb[:-1]:
+                            bounds = bounds + [(i - 5, i + 5)]
+                        bounds = bounds + [(0.1, .99)]
+
+                    else:
+                        bounds = None
+                else:
+                    bb[0] = self.constant_value
+                    if dispersion == 1:
+                        if not self.no_extra_param:
+                            bb[-1] = self.negative_binomial_value
+                    bounds = None
+
+
+
+                # intial_beta = minimize(self._loglik_gradient, bb, args =(XX, y, None, None, None, None, calc_gradient, hess_est, dispersion, 0, False, 0, None, sub_zi, exog_infl, None, None, mod), method = 'nelder-mead', options={'gtol': 1e-7*len(XX)})
+                hess_est = False if method2 in ['L-BFGS-B', 'BFGS_2', 'Nelder-Mead-BFGS'] else True
+                
+                if self.no_extra_param:
+                    dispersion_poisson = 0
+                    initial_beta = self._minimize(self._loglik_gradient, bb,
+                                              args=(XX, y, None, None, None, None, calc_gradient, hess_est,
+                                                    dispersion_poisson, 0, False, 0, None, None, None, None, None,
+                                                    mod),
+                                              method=method2, tol=1e-5, options={'gtol': tol['gtol']},
+                                              bounds=bounds)
+                    if dispersion:
+                        try:
+                            nb_parma = self.poisson_mean_get_dispersion(initial_beta.x, XX, y)
+                        except: 
+                            nb_parma = 0.5
+                    
+                if method2 == 'L-BFGS-B':
+                    if hasattr(initial_beta.hess_inv, 'todense'):
+                        initial_beta['hess_inv'] = initial_beta.hess_inv.todense() if hasattr(initial_beta.hess_inv,
+                                                                                              'todense') else np.array(
+                            [initial_beta.hess_inv(np.eye(len(bb))[i]) for i in range(len(bb))])
+
+                bb = initial_beta['x'].copy()
+
+                if initial_beta is not None and np.isnan(initial_beta['fun']):
+                    initial_beta = self._minimize(self._loglik_gradient, bb,
+                                                  args=(XX, y, None, None, None, None, True, True, dispersion,
+                                                        0, False, 0, None, None, None, None, None, mod),
+                                                  method=method2, tol=tol['ftol'], options={'gtol': tol['gtol']})
+
+                if initial_beta is not None and not np.isnan(initial_beta['fun']):
+                    self._no_random_paramaters = 1
+                    if initial_beta['success'] != 0:
+                        self.convergance = 0
+                    else:
+                        self.convergance = 1
+                print('TODO NEED TO RETURN THE THINGS I CARE ABOUT')
+            else:
+                
+                is_halton = 0
+
+                print('Solution was not finite, error. Continue')
+                sol.add_objective()
+                return sol, None, None, None, None, None, None, 0
+        except Exception as e:
+            exc_type, exc_obj, exc_tb = sys.exc_info()
+            fname = os.path.split(exc_tb.tb_frame.f_code.co_filename)[1]
+            print(exc_type, fname, exc_tb.tb_lineno)
+
+    def fitRegression_in_chunks(self, mod,dispersion=0, maxiter=2000, batch_size=None, num_hess=False, **kwargs):
+        """
+        Fits a poisson regression given data and outcomes if dispersion is not declared
+        if declared, fits a NB (dispersion = 1) regression or GP (disperions = 2)
+        
+        #TODO lineraregression
+        Inputs:
+        X - array.  Design matrix
+        y - array.  Observed outcomes
+        Outputs:
+        betas_est - array.  Coefficients which maximize the negative log-liklihood.
+        """
+        # Set defualt method
+        #TODO, the inital fit worked but it throws
+        tol = {'ftol': 1e-8, 'gtol': 1e-6}
+        
+        sol = Solution()
+        
+        initial_betas = self.fitRegression_prefit(mod, dispersion, maxiter, batch_size, num_hess, **kwargs)
+        
+
+      
+        
+    def _build_design_matrix(self, mod):
+        """
+        Build the design matrix `XX` by combining `X`, `Xr`, `XG`, and `XH`.
+
+        Parameters:
+            mod: Dictionary containing data and parameters.
+
+        Returns:
+            Combined design matrix `XX`.
+        """
+        X, Xr, XG, XH = mod.get('X'), mod.get('Xr'), mod.get('XG'), mod.get('XH')
+        if XG is not None:
+            return np.concatenate((X, XG, Xr, XH), axis=2)
+        elif XH is not None:
+            return np.concatenate((X, Xr, XH), axis=2)
+        else:
+            return np.concatenate((X, Xr), axis=2)
+        
+   
+    def _update_attributes(self, optimization_result, mod):
+        """
+        Update instance attributes like `self.significant` and `self.draws`.
+
+        Parameters:
+            optimization_result: The result of the optimization process.
+            mod: The model dictionary containing data and parameters.
+        """
+        # Update `self.significant` based on p-values or other criteria
+        if optimization_result is not None:
+            significant_threshold = 0.05  # Example threshold for significance
+            self.significant = all(
+                p < significant_threshold for p in mod.get("pvalues", [])
+            )
+        else:
+            self.significant = False  # Mark as not significant if optimization failed
+
+        # Update `self.draws` based on `mod` or other factors
+        if "Xr" in mod:
+            Xr = mod.get("Xr")
+            draws = Xr.shape[0] if Xr is not None else 0  # Example: Number of rows in Xr
+            self.draws = draws
+        else:
+            self.draws = 0
+    
+    def _run_optimization(self, XX, y, dispersion, initial_params, bounds, tol, mod):
+        """
+        Run the optimization process with draws logic and update the Solution object.
+
+        Parameters:
+            XX: Design matrix.
+            y: Observed outcomes.
+            dispersion: Dispersion parameter (0=Poisson, 1=NB, 2=GP).
+            initial_params: Initial parameter array.
+            bounds: List of bounds for each parameter.
+            tol: Tolerance for the optimization process (dictionary with ftol and gtol).
+            mod: Dictionary containing additional data.
+
+        Returns:
+            Solution object with updated objectives.
+        """
+        # Extract relevant data
+        X, Xr, XG = mod.get('X'), mod.get('Xr'), mod.get('XG')
+        distribution = mod.get('dist_fit')
+
+        # Prepare draws
+        draws = self._prepare_draws(Xr, distribution)
+        draws_grouped = self._prepare_grouped_draws(XG, mod) if XG is not None else None
+
+        # Optimization method and options
+        method = self.method_ll if bounds is None else 'L-BFGS-B'
+        print('updataing methods')
+
+        #method = 'Nelder-Mead-BFGS'
+        options = {'gtol': tol['gtol'], 'ftol': tol['ftol'], 'maxiter': 4000}
+        args=(
+                X, y, draws, X, Xr, self.batch_size, self.grad_yes, self.hess_yes, dispersion, 0, False, 0,
+                self.rdm_cor_fit, None, None, draws_grouped, XG, mod
+            )
+        # Run optimization
+        optimization_result = self._minimize(
+            self._loglik_gradient,
+            initial_params,
+            args=(
+                X, y, draws, X, Xr, self.batch_size, self.grad_yes, self.hess_yes, dispersion, 0, False, 0,
+                self.rdm_cor_fit, None, None, draws_grouped, XG, mod
+            ),
+            method=method,
+            bounds=bounds,
+            tol=tol.get('ftol', 1e-8),  # Use 'ftol' as the default tolerance
+            options=options
+        )
+
+       
+
+        # Run the bootstrap to calculate standard errors
+        if self.run_bootstrap:
+
+            std_errors = self.bootstrap_std_dev(
+                initial_params=optimization_result.x,
+                XX=XX,
+                y=y,
+                dispersion=dispersion,
+                bounds=bounds,
+                tol=tol,
+                mod=mod,
+                n_bootstraps=100
+            )
+            self.stderr = std_errors
+
+        
+
+    
+        return optimization_result
+
+
+   
+
+    def bootstrap_std_dev(self, initial_params, XX, y, dispersion, bounds, tol, mod, n_bootstraps=100):
+        """
+        Perform bootstrap resampling to estimate the standard deviations of the parameters.
+
+        Parameters:
+            self: Reference to the class instance.
+            initial_params: Initial parameter estimates from the optimization.
+            XX: Design matrix.
+            y: Observed outcomes.
+            dispersion: Dispersion parameter (0=Poisson, 1=NB, 2=GP).
+            bounds: List of bounds for each parameter.
+            tol: Tolerance for the optimization process (dictionary with ftol and gtol).
+            mod: Dictionary containing additional data.
+            n_bootstraps: Number of bootstrap resamples (default=100).
+
+        Returns:
+            std_devs: Standard deviations of the parameter estimates (from bootstrap resampling).
+        """
+        # List to store parameter estimates from each bootstrap iteration
+        bootstrap_estimates = []
+
+        # Extract design matrices and additional components from `mod`
+        X, Xr, XG = mod.get('X'), mod.get('Xr'), mod.get('XG')
+        distribution = mod.get('dist_fit')
+
+        # Prepare draws
+        draws = self._prepare_draws(Xr, distribution)
+        draws_grouped = self._prepare_grouped_draws(XG, mod) if XG is not None else None
+
+        # Perform bootstrap iterations
+        for _ in range(n_bootstraps):
+            # Resample data with replacement
+            indices = np.random.choice(len(y), size=len(y), replace=True)
+            X_resampled = X[indices]
+            y_resampled = y[indices]
+
+            # Refit the model with resampled data
+            bootstrap_result = self._minimize(
+                self._loglik_gradient,
+                initial_params,
+                args=(
+                    X_resampled, y_resampled, draws, X_resampled, Xr, self.batch_size, self.grad_yes,
+                    self.hess_yes, dispersion, 0, False, 0, self.rdm_cor_fit, None, None,
+                    draws_grouped, XG, mod
+                ),
+                method=self.method_ll,
+                bounds=bounds,
+                tol=tol.get('ftol', 1e-8),  # Use 'ftol' as the default tolerance
+                options={'gtol': tol['gtol'], 'ftol': tol['ftol'], 'maxiter': 2000}
+            )
+
+            # Store the parameter estimates from this bootstrap iteration
+            bootstrap_estimates.append(bootstrap_result.x)
+
+        # Convert bootstrap parameter estimates to a NumPy array
+        bootstrap_estimates = np.array(bootstrap_estimates)
+
+        # Compute the standard deviations of the parameter estimates
+        std_devs = np.std(bootstrap_estimates, axis=0)
+
+        return std_devs
+    
+    def _initialize_params_and_bounds(self, XX, dispersion):
+        """Initialize parameters and set bounds for optimization."""
+        num_params = XX.shape[2]  # Number of features
+        initial_params = np.random.uniform(-0.05, 0.05, size=num_params)
+
+        # Define bounds for optimization
+        if dispersion == 0:
+            bounds = [(-30, 30) for _ in initial_params]
+        elif dispersion == 1:
+            bounds = [(-30, 30) for _ in initial_params[:-1]] + [(-1, 5)]
+        elif dispersion == 2:
+            bounds = [(-5, 5) for _ in initial_params[:-1]] + [(0.1, 0.99)]
+        else:
+            bounds = None
+
+        return initial_params, bounds
+    
+
+    def _prepare_data(self, mod):
+        """Prepare data matrices (XX, XX_test) and outcomes (y, y_test)."""
+        y = mod.get('y')
+        y_test = mod.get('y_test')
+
+        # Combine main data matrices
+        XX = self._combine_data_matrices(mod)
+        
+        # Combine test data matrices
+        if mod.get('X_test') is not None and mod.get('Xr_test') is not None:
+            if 'XH' in mod:
+                XX_test = np.concatenate(
+                    (mod.get('X_test'), mod.get('Xr_test'), mod.get('XH_test')), axis=2
+                )
+            else:
+                XX_test = np.concatenate((mod.get('X_test'), mod.get('Xr_test')), axis=2)
+        else:
+            XX_test = None
+
+        return XX, XX_test, y, y_test
+
+    def _handle_error(self, e):
+        """Handle exceptions and log errors."""
+        import sys, os
+        exc_type, exc_obj, exc_tb = sys.exc_info()
+        fname = os.path.split(exc_tb.tb_frame.f_code.co_filename)[1]
+        print(f"Error: {e}, File: {fname}, Line: {exc_tb.tb_lineno}")
+
+
+    
+    
+    
+    def _postprocess_results(self, optimization_result, XX, XX_test, y, y_test, dispersion, mod):
+        """
+        Process optimization results and calculate metrics.
+
+        Parameters:
+            optimization_result: The result of the optimization process.
+            XX: Design matrix for training data.
+            XX_test: Design matrix for test data (if applicable).
+            y: Observed outcomes for training data.
+            y_test: Observed outcomes for test data (if applicable).
+            dispersion: Dispersion parameter (0=Poisson, 1=NB, 2=GP).
+            mod: Dictionary containing additional model data.
+
+        Returns:
+            log_ll, aic, bic, stderr, zvalues, pvalue_alt, in_sample_mae, out_sample_mae
+        """
+        if optimization_result is not None and np.isfinite(optimization_result['fun']):
+            # Calculate post-fit metrics (log-likelihood, AIC, BIC, etc.)
+            log_ll, aic, bic, stderr, zvalues, pvalue_alt, other_measures = self._post_fit_ll_aic_bic(
+                optimization_result, simple_fit=False, is_dispersion=dispersion
+            )
+
+            # Validation metrics if test data is available (in-sample and out-of-sample MAE)
+            in_sample_mae = None
+            out_sample_mae = None
+            if self.is_multi and XX_test is not None:
+                in_sample_mae = self.validation(
+                    optimization_result['x'], y, XX, dispersion=dispersion, model_nature=mod, testing=0
+                )
+                out_sample_mae = self.validation(
+                    optimization_result['x'], y_test, XX_test, dispersion=dispersion, model_nature=mod
+                )
+
+            return log_ll, aic, bic, stderr, zvalues, pvalue_alt, in_sample_mae, out_sample_mae
+
+        else:
+            # Optimization failed, return None for all metrics
+            print("Optimization failed.")
+            return None, None, None, None, None, None, None, None
+    def _prepare_data_and_bounds(self, mod, dispersion):
+        """Prepare the data matrices, bounds, and initial parameters."""
+        # Prepare data matrices
+        XX = self._combine_data_matrices(mod)  # Combine mod['X'], mod['Xr'], mod['XH'], etc.
+
+        # Set initial parameters
+        initial_params = self._initialize_parameters(XX, dispersion)
+
+        # Define bounds for optimization
+        bounds = self._set_bounds(initial_params, dispersion)
+
+        return XX, bounds, initial_params
+
+
+    def _combine_data_matrices(self, mod):
+        """Combine data matrices (X, Xr, XH, etc.) into a single matrix."""
+        if 'XG' in mod:
+            return np.concatenate((mod.get('X'), mod.get('XG'), mod.get('Xr'), mod.get('XH')), axis=2)
+        elif 'XH' in mod:
+            return np.concatenate((mod.get('X'), mod.get('Xr'), mod.get('XH')), axis=2)
+        else:
+            return np.concatenate((mod.get('X'), mod.get('Xr')), axis=2)
+
+
+    def _initialize_parameters(self, XX, dispersion):
+        """Initialize random parameters for optimization."""
+        num_params = XX.shape[2]  # Number of features
+        return np.random.uniform(-0.05, 0.05, size=num_params)
+
+
+    def _set_bounds(self, initial_params, dispersion):
+        """Set bounds for optimization based on the dispersion type."""
+        return None
+        if dispersion == 0:
+            return [(-30, 30) for _ in initial_params]
+        elif dispersion == 1:
+            num_params = self.get_num_params()
+            skip_count = sum(num_params[:2])
+        
+        
+            bounds = [(-3, 3) for _ in initial_params[:-1]] + [(-1, 1)]
+            bounds[skip_count: -1] = [(0.02, None) for _ in bounds[skip_count: -1]]
+            return bounds
+        elif dispersion == 2:
+            return [(-5, 5) for _ in initial_params[:-1]] + [(0.1, 0.99)]
+        else:
+            return None
+    def _build_test_matrix(self, mod):
+        """
+        Build the test matrix `XX_test` by combining `X_test`, `Xr_test`, and `XH_test`.
+
+        Parameters:
+            mod: Dictionary containing test data.
+
+        Returns:
+            Combined test matrix `XX_test`.
+        """
+        X_test, Xr_test, XG_test, XH_test = (
+            mod.get('X_test'), mod.get('Xr_test'), mod.get('XG_test'), mod.get('XH_test')
+        )
+        if X_test is None or Xr_test is None:
+            return None
+
+        if XH_test is not None:
+            return np.concatenate((X_test, Xr_test, XH_test), axis=2)
+        elif XG_test is not None:
+            return np.concatenate((X_test, XG_test, Xr_test), axis=2)
+        else:
+            return np.concatenate((X_test, Xr_test), axis=2)
+        
+    def _calculate_num_coefficients(self, mod, dispersion):
+        """
+        Calculate the total number of coefficients for the regression model.
+
+        Parameters:
+            mod: Dictionary containing data and parameters.
+            dispersion: Dispersion parameter (0=Poisson, 1=NB, 2=GP).
+
+        Returns:
+            Total number of coefficients.
+        """
+        X, Xr, XG, XH = mod.get('X'), mod.get('Xr'), mod.get('XG'), mod.get('XH')
+        n, p, k = X.shape
+        kr = Xr.shape[2] if Xr is not None else 0
+        kg = XG.shape[2] if XG is not None else 0
+        kh = XH.shape[2] if XH is not None else 0
+
+        # Dispersion adds one additional parameter if enabled
+        dispersion_param = 1 if dispersion > 0 else 0
+        return sum(self.get_num_params()) + dispersion_param
+        #return k + kr + kg + kh + dispersion_param
+    def _build_initial_params(self, num_coefficients, dispersion):
+        """
+        Build the initial parameter array for optimization.
+
+        Parameters:
+            num_coefficients: Total number of coefficients.
+            dispersion: Dispersion parameter (0=Poisson, 1=NB, 2=GP).
+
+        Returns:
+            Initial parameter array.
+        """
+        # Generate random initial coefficients
+        initial_params = np.random.uniform(-.1, 0.1, size=num_coefficients)
+        parma_sum = sum(self.get_num_params()[:2])
+       
+                       
+        initial_params[parma_sum:-dispersion] =0.5
+
+        # Add dispersion parameter if applicable
+        if dispersion > 0:
+            initial_params[-1] =  0.0
+            #initial_params[0] =3
+
+        return initial_params
+    
+    def fitRegression(self, mod, dispersion=0, maxiter=4000, batch_size=None, num_hess=False, **kwargs):
+        """
+        Fits a Poisson regression, NB regression (dispersion=1), or GP regression (dispersion=2).
+
+        Parameters:
+            mod: Dictionary containing data and parameters.
+            dispersion: 0 for Poisson, 1 for NB, 2 for GP.
+            maxiter: Maximum number of optimization iterations.
+            batch_size: Batch size for certain methods (if applicable).
+            num_hess: Whether to compute the numerical Hessian.
+
+        Returns:
+            obj_1, log_lik, betas, stderr, pvalues, zvalues, is_halton, is_delete
+        """
+        try:
+            dispersion = mod.get('dispersion', dispersion)
+            # Preprocessing
+            tol = {'ftol': 1e-6, 'gtol': 1e-6, 'xtol': 1e-6}
+            y, X, Xr, XG, XH = mod.get('y'), mod.get('X'), mod.get('Xr'), mod.get('XG'), mod.get('XH')
+
+            # Validate input data
+            if y is None or X is None:
+                raise ValueError("Both `y` and `X` must be provided in the `mod` dictionary.")
+
+            # Build the design matrix `XX` and test matrix `XX_test` if applicable
+            XX = self._build_design_matrix(mod)
+            XX_test = self._build_test_matrix(mod) if self.is_multi else None
+
+            # Determine the number of coefficients
+            num_coefficients = self._calculate_num_coefficients(mod, dispersion)
+
+            # Build initial parameters and bounds
+            initial_params = self._build_initial_params(num_coefficients, dispersion)
+            bounds = self._set_bounds(initial_params, dispersion)
+
+       
+            # Run optimization
+            optimization_result = self._run_optimization(
+                XX, y, dispersion, initial_params, bounds, tol, mod
+            )
+            
+            # Post-process results
+            log_lik, aic, bic, stderr, zvalues, pvalues, in_sample_mae, out_sample_mae = self._postprocess_results(
+                optimization_result, XX, XX_test, y, mod.get('y_test'), dispersion, mod
+            )
+           
+            # Extract other outputs
+            betas = optimization_result['x'] if optimization_result is not None else None
+            is_halton = Xr is not None and Xr.size > 0  # Halton draws used if `Xr` is not empty
+
+            # Determine `is_delete`
+            is_delete = not (
+                optimization_result is not None
+                and 'fun' in optimization_result
+                and not math.isnan(optimization_result['fun'])
+                and not math.isinf(optimization_result['fun'])
+            )
+
+            betas_est = optimization_result
+
+            # Post-fit metrics
+            log_ll, aic, bic, stderr, zvalues, pvalue_alt, other_measures = self._post_fit_ll_aic_bic(
+                betas_est, simple_fit=False, is_dispersion=dispersion
+            )
+
+            # Number of parameters
+            paramNum = len(betas_est['x'])
+
+            # Naming for printing (optional, for formatting or debugging purposes)
+            self.convergance = not is_delete
+            self.naming_for_printing(betas_est['x'], 0, dispersion, model_nature=mod)
+
+            # Add metrics to solution object
+            sol = Solution()  # Assuming Solution is the appropriate class to store results
+            sol.add_objective(
+                bic=bic,
+                aic=aic,
+                loglik=log_ll,
+                num_parm=paramNum,
+                GOF=other_measures
+            )
+
+
+            return (
+                sol,  # obj_1
+                log_lik,
+                betas,
+                stderr,
+                pvalues,
+                zvalues,
+                is_halton,
+                is_delete
+            )
+
+        except Exception as e:
+            self._handle_error(e)
+            return None, None, None, None, None, None, None, 0
+   
+   
+    def _prepare_draws(self, Xr, distribution):
+        """
+        Prepare the draws for the random effects.
+
+        Parameters:
+            Xr: Random effect design matrix.
+            distribution: Distribution type for the random effects.
+
+        Returns:
+            Draws matrix or None if `Xr` is not provided.
+        """
+        if Xr is None or Xr.size == 0:
+            return None
+
+        n_samples, n_features, n_random_effects = Xr.shape
+        return self.prepare_halton(
+            n_random_effects, n_samples, self.Ndraws, distribution, long=False, slice_this_way=self.group_halton
+        )
+
+    def _prepare_grouped_draws(self, XG, mod):
+        """
+        Prepare the grouped draws for the regression model.
+
+        Parameters:
+            XG: Grouped design matrix.
+            mod: Dictionary containing additional data.
+
+        Returns:
+            Grouped draws matrix.
+        """
+        n_samples, n_features, n_groups = XG.shape
+        if n_features == 0:
+            return None
+        group_distribution = mod.get('dist_fit_grouped', np.zeros(n_groups))
 
+        return self.prepare_halton(
+            n_groups, n_samples, self.Ndraws, group_distribution, slice_this_way=self.group_halton
+        )
+
+    def fitRegression_o(self, mod,
+                      dispersion=0, maxiter=2000, batch_size=None, num_hess=False, **kwargs):
+
+        """
+        Fits a poisson regression given data and outcomes if dispersion is not declared
+        if declared, fits a NB (dispersion = 1) regression or GP (disperions = 2)
+        
+        #TODO lineraregression
+        Inputs:
+        X - array.  Design matrix
+        y - array.  Observed outcomes
+        Outputs:
+        betas_est - array.  Coefficients which maximize the negative log-liklihood.
+        """
+        # Set defualt method
+        #TODO, the inital fit worked but it throws
+        tol = {'ftol': 1e-8, 'gtol': 1e-6}
+        
+
+        
+        sol = Solution()
+
+        tol = {'ftol': 1e-8, 'gtol': 1e-6}
+        is_delete = 0
+        dispersion = mod.get('dispersion')
+        y = mod.get('y')
+        try:
+            method = self.method_ll
+            method2 = self.method_ll
+            # method2 = 'BFGS_2'
+            if self.hess_yes == False:
+                method2 = 'BFGS_2'
+                method2 = self.method_ll
+
+            bic = None
+            pvalue_alt = None
+            zvalues = None
+            if mod.get('Xr') is not None or mod.get('XG') is not None or mod.get('XH') is not None:
+                calc_gradient = True
+                calc_gradient = False if self.linear_regression else True
                 n, p, k = mod.get('X').shape
                 _r, pr, kr = mod.get('Xr').shape
                 kh = mod.get('XH').shape[2]
@@ -5679,7 +6513,7 @@ class ObjectiveFunction(object):
                         initial_beta['hess_inv'] = initial_beta.hess_inv.todense() if hasattr(initial_beta.hess_inv,
                                                                                               'todense') else np.array(
                             [initial_beta.hess_inv(np.eye(len(bb))[i]) for i in range(len(bb))])
-
+                
                 bb = initial_beta['x'].copy()
 
                 if initial_beta is not None and np.isnan(initial_beta['fun']):
@@ -6070,7 +6904,8 @@ class ObjectiveFunction(object):
     def transformer(self, transform, idc, x_data):
         if transform == 0 or transform == 1 or transform == 'no':
             tr = x_data.astype(float)
-
+        elif transform == 'nil':
+            tr = x_data.astype(float)
         elif transform == 'log':
             tr = np.log1p(x_data.astype(float))
         elif transform == 'exp':
@@ -6087,7 +6922,8 @@ class ObjectiveFunction(object):
             tr = pd.Series(tr)
 
         else:  # will be a number
-            tr = np.power(x_data.astype(float), transform)
+            tr = x_data.astype(float)
+            transform = 'nil'
         # if tr.isin([np.inf, -np.inf, np.nan, None]).any() == True:
 
         if np.any(np.logical_or(pd.isna(tr), np.logical_or(pd.isna(tr), tr is None))):
@@ -6740,7 +7576,7 @@ class ObjectiveFunction(object):
             sequence.append(n_th_number)
         return sequence
 
-    def _generate_halton_draws(self, sample_size, n_draws, n_vars, shuffled=False, drop=100, primes=None,
+    def _generate_halton_draws(self, sample_size, n_draws, n_vars, shuffled=False, drop=10, primes=None,
                                long=False) -> np.ndarray:
         """Generate Halton draws for multiple random variables using different primes as base"""
         if primes is None:
@@ -6769,6 +7605,7 @@ class ObjectiveFunction(object):
                     i += 1
                 t += 1
             seq = seq[drop:length + drop]
+            seq = np.clip(seq, 1e-4, 1-1e-4)
             if shuffled:
                 np.random.shuffle(seq)
             return seq
@@ -6822,6 +7659,12 @@ class ObjectiveFunction(object):
             (1 - x) * np.random.gamma(2, scale=theta, size=n)
         return b
 
+ 
+
+
+ 
+
+
     def _compute_derivatives(self, betas, draws, betas_std=None, distribution=None):
         # N, N_draws, K = len(draws)/self.Ndraws, self.Ndraws, len(self._distribution)
         # N, D = draws.shape[0], draws.shape[1]

{metacountregressor-0.1.238.dist-info → metacountregressor-0.1.241.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: metacountregressor
-Version: 0.1.238
+Version: 0.1.241
 Summary: Extensive Testing for Estimation of Data Count Models
 Home-page: https://github.com/zahern/CountDataEstimation
 Author: Zeke Ahern

{metacountregressor-0.1.238.dist-info → metacountregressor-0.1.241.dist-info}/RECORD

@@ -3,18 +3,18 @@ metacountregressor/_device_cust.py,sha256=759fnKmTYccJm4Lpi9_1reurh6OB9d6q9soPR0
 metacountregressor/app_main.py,sha256=vY3GczTbGbBRalbzMkl_9jVW7RMgEOc6z2Dr1IZJv9c,10014
 metacountregressor/data_split_helper.py,sha256=M2fIMdIO8znUaYhx5wlacRyNWdQjNYu1z1wkE-kFUYU,3373
 metacountregressor/halton.py,sha256=jhovA45UBoZYU9g-hl6Lb2sBIx_ZBTNdPrpgkzR9fng,9463
-metacountregressor/helperprocess.py,sha256=k2OvLZE131lxsx7Nupz1lAZ41wipRvimSy1ggz69wfM,23048
+metacountregressor/helperprocess.py,sha256=zBpMI2AI7aZ19IZlEnZrvy2VAtJICIcwpq60JL_OIjQ,24428
 metacountregressor/main.py,sha256=xfpKN2w0kePHp_Q2HOPjtG15PLEN1L3sEnDw1PHBquw,23668
 metacountregressor/main_old.py,sha256=eTS4ygq27MnU-dZ_j983Ucb-D5XfbVF8OJQK2hVVLZc,24123
-metacountregressor/metaheuristics.py,sha256=d9jIwCTf2XRoW4UqrJHXBSS1W4XU-TwSeWWVMGo2Jdw,106731
+metacountregressor/metaheuristics.py,sha256=PyxFBlNqqwq787cDHl36xLaricMA3HTCtDweOe_UM-M,106763
 metacountregressor/pareto_file.py,sha256=whySaoPAUWYjyI8zo0hwAOa3rFk6SIUlHSpqZiLur0k,23096
 metacountregressor/pareto_logger__plot.py,sha256=mEU2QN4wmsM7t39GJ_XhJ_jjsdl09JOmG0U2jICrAkI,30037
 metacountregressor/setup.py,sha256=5UcQCCLR8Fm5odA3MX78WwahavxFq4mVD6oq0IuQvAY,936
 metacountregressor/single_objective_finder.py,sha256=jVG7GJBqzSP4_riYr-kMMKy_LE3SlGmKMunNhHYxgRg,8011
-metacountregressor/solution.py,sha256=LGyzCwdjNkjm8gpqRDXUzOWwyBeUSkEqp0k6K_y5564,283103
+metacountregressor/solution.py,sha256=78CNqLdVfLQCSVFEWVY1NkV3wlNykwbek3aNTcC5-WI,316939
 metacountregressor/test_generated_paper2.py,sha256=pwOoRzl1jJIIOUAAvbkT6HmmTQ81mwpsshn9SLdKOg8,3927
-metacountregressor-0.1.238.dist-info/LICENSE.txt,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-metacountregressor-0.1.238.dist-info/METADATA,sha256=x8rGIKadAXOEkAB1uYIojrde24LX78D1URa2F1qDwD0,23529
-metacountregressor-0.1.238.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
-metacountregressor-0.1.238.dist-info/top_level.txt,sha256=zGG7UC5WIpr76gsFUpwJ4En2aCcoNTONBaS3OewwjR0,19
-metacountregressor-0.1.238.dist-info/RECORD,,
+metacountregressor-0.1.241.dist-info/LICENSE.txt,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+metacountregressor-0.1.241.dist-info/METADATA,sha256=c9KqN-cADG_SSnayPLrL2npCMCW_nway7Upg_Lr-Row,23529
+metacountregressor-0.1.241.dist-info/WHEEL,sha256=beeZ86-EfXScwlR_HKu4SllMC9wUEj_8Z_4FJ3egI2w,91
+metacountregressor-0.1.241.dist-info/top_level.txt,sha256=zGG7UC5WIpr76gsFUpwJ4En2aCcoNTONBaS3OewwjR0,19
+metacountregressor-0.1.241.dist-info/RECORD,,

{metacountregressor-0.1.238.dist-info → metacountregressor-0.1.241.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (76.0.0)
+Generator: setuptools (76.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any