metacountregressor 0.1.207__py3-none-any.whl → 0.1.209__py3-none-any.whl

metacountregressor/solution.py

@@ -501,7 +501,7 @@ class ObjectiveFunction(object):
         # model specs
         self.endog = None
         # solution parameters
-        self._min_characteristics = 1
+        self._min_characteristics = kwargs.get('_min_vars', 3)
         self._max_hurdle = 4
 
         #Manually fit from analyst specification
@@ -1408,16 +1408,47 @@ class ObjectiveFunction(object):
 
         return transform_set
 
+ 
     def poisson_mean_get_dispersion(self, betas, X, y):
+        '''
         eVy = self._loglik_gradient(betas, X, y, None, X, None, None, False, False, dispersion=0,
                                     return_EV=True,
                                     zi_list=None, draws_grouped=None, Xgroup=None)
         
-        ab = ((y - eVy)**2 - eVy)/eVy
-        bb = eVy -1
-        disp = sm.OLS(ab.ravel(), bb.ravel()).fit()
-        gamma = disp.params[0]
+        print('trying thi instead')
+        
+        '''
+        
+        '''       
+        nb_model = sm.GLM(y_long, x_long, family=sm.families.NegativeBinomial()).fit()
+        gamma = nb_model.scale
+
+        '''
+        #poisson way
+        try:
+            num_panels, num_obs, num_features = X.shape  # Dimensions of x
+            x_long = X.reshape(-1, num_features)         # Reshape to (num_panels * num_obs, num_features)
+            y_long = y.reshape(-1) 
+            poisson_model = sm.GLM(y_long, x_long, family=sm.families.Poisson()).fit()
+
+            # Get residual deviance and degrees of freedom
+            residual_deviance = poisson_model.deviance
+            degrees_of_freedom = poisson_model.df_resid
+
+        # Calculate dispersion
+            dispersion = residual_deviance / degrees_of_freedom
+        except:
+            dispersion =1 
+
+        #ab = np.abs(((y - eVy)**2 - eVy)/eVy)
+        
+        #bb = eVy -1
+        #disp = sm.OLS(ab.ravel(), bb.ravel()).fit()
+        #gamma = disp.params[0]
         #print(f'dispersion is {gamma}')
+        gamma = np.min(dispersion,1)
+        if gamma < 0.05:
+            gamma = 0.05
         return gamma
 
     def validation(self, betas, y, X, Xr=None, dispersion=0, rdm_cor_fit=None, zi_list=None, exog_infl=None,
@@ -1946,11 +1977,11 @@ class ObjectiveFunction(object):
 
         else:
             slice_this_amount = self.num_dispersion_params(dispersion)
-            slice_this_amount = 1 #TODO handle this
+            slice_this_amount = 0 #TODO handle this
             if pvalues[-1] > sig_value:
                 vio_counts += 1
             subpvalues = pvalues[:-slice_this_amount].copy()
-
+            
         if Kh > 1:
             if subpvalues[-1] < sig_value:
                 subpvalues[-Kh] = 0
@@ -6437,10 +6468,13 @@ class ObjectiveFunction(object):
                 if not is_delete and is_halton:
                     if obj_1[self._obj_1] <= self.best_obj_1:
                         self.pvalue_sig_value = .1
-
-                    st, self.pvalue_exceed = self.get_pvalue_info_alt(
-                        pvalues, self.coeff_names, self.pvalue_sig_value, dispersion, is_halton, 0, 1)
-
+                    try:
+                        st, self.pvalue_exceed = self.get_pvalue_info_alt(
+                            pvalues, self.coeff_names, self.pvalue_sig_value, dispersion, is_halton, 0, 1)
+                    except Exception as pval_exe:
+                        print(pval_exe)
+                        self.pvalue_exceed = sum(
+                        a > self.pvalue_sig_value for a in pvalues)
                 else:
                     self.pvalue_exceed = sum(
                         a > self.pvalue_sig_value for a in pvalues)

{metacountregressor-0.1.207.dist-info → metacountregressor-0.1.209.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: metacountregressor
-Version: 0.1.207
+Version: 0.1.209
 Summary: Extensive Testing for Estimation of Data Count Models
 Home-page: https://github.com/zahern/CountDataEstimation
 Author: Zeke Ahern

{metacountregressor-0.1.207.dist-info → metacountregressor-0.1.209.dist-info}/RECORD

@@ -11,10 +11,10 @@ metacountregressor/pareto_file.py,sha256=whySaoPAUWYjyI8zo0hwAOa3rFk6SIUlHSpqZiL
 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=51_7HM-wKMsHPrp-TyMFqvA5MQJfN63gE58R1QNbVUk,283381
+metacountregressor/solution.py,sha256=9bPdfwyxUx-4Z2EsOheCsTXbksdPd5oC-o4fx_rDhNE,284645
 metacountregressor/test_generated_paper2.py,sha256=pwOoRzl1jJIIOUAAvbkT6HmmTQ81mwpsshn9SLdKOg8,3927
-metacountregressor-0.1.207.dist-info/LICENSE.txt,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-metacountregressor-0.1.207.dist-info/METADATA,sha256=7PVaRp9kVHTlyax6tuLps9hwpBbgQKWbVCSmyv817u4,23536
-metacountregressor-0.1.207.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
-metacountregressor-0.1.207.dist-info/top_level.txt,sha256=zGG7UC5WIpr76gsFUpwJ4En2aCcoNTONBaS3OewwjR0,19
-metacountregressor-0.1.207.dist-info/RECORD,,
+metacountregressor-0.1.209.dist-info/LICENSE.txt,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+metacountregressor-0.1.209.dist-info/METADATA,sha256=VTXXMO16oHNwdRfj4gslq4CBPvRHnD3Ro2HGHIG7xH0,23536
+metacountregressor-0.1.209.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
+metacountregressor-0.1.209.dist-info/top_level.txt,sha256=zGG7UC5WIpr76gsFUpwJ4En2aCcoNTONBaS3OewwjR0,19
+metacountregressor-0.1.209.dist-info/RECORD,,

{metacountregressor-0.1.207.dist-info → metacountregressor-0.1.209.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.2)
+Generator: setuptools (76.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any