metacountregressor 0.1.36__py3-none-any.whl → 0.1.38__py3-none-any.whl

metacountregressor/solution.py

@@ -145,7 +145,7 @@ class ObjectiveFunction(object):
         self.best_obj_1 = 100000000
         self._obj_1 = 'bic'
         self._obj_2 = 'MSE'
-        self.numerical_hessian_calc = 1 # calculates hessian by statsmodels otherwise scipy
+        self.numerical_hessian_calc = 0 # calculates hessian by statsmodels otherwise scipy
         self.full_model = None
         self.GP_pararameter = 0
         self.is_multi = 0
@@ -156,6 +156,7 @@ class ObjectiveFunction(object):
         #defualt paraamaters for hs
         self.agorithm ='hs'
         self._hms = 20
+        self._max_time = 60*60*24
         self._hmcr = .5
         self._max_imp = 100000
         self._panels = .3
@@ -5577,10 +5578,11 @@ class ObjectiveFunction(object):
                             XX_test = mod.get('Xr_test')
                 
              
-                
-                 
+                bb = np.random.normal(
+                        0.1, 0.05, size=k + kr+kg+kh+dispersion_param_num)
+                '''
                 try:
-                   
+                    
                     res = sm.GLM(mod.get('y')[:, 0], XX[:,  0, :], family=sm.families.Poisson(
                         ), offset=self._offsets[:, 0, :].ravel()).fit()
                     bb = res.params.copy()
@@ -5638,6 +5640,8 @@ class ObjectiveFunction(object):
                     #bb = np.append(bb,1)
                     #initial_beta2 = minimize(self._loglik_gradient, bb, bounds = bounds, jac = calc_gradient, args=(XX, y, None, None, None, None, calc_gradient, calc_gradient, 4, 0, False, 0, None, sub_zi, exog_infl), method=method, tol = tol['ftol'], options={'gtol': tol['gtol']})
                     #print('did this work')
+                '''
+                
                 try:
                     if method == 'L-BFGS-B' or method2 == 'L-BFGS-B':
                         if dispersion == 0:
@@ -5750,10 +5754,13 @@ class ObjectiveFunction(object):
                     # return sol, log_ll, initial_beta['x'], self.stderr, self.pvalues, self.zvalues, is_halton, is_delete_init
                         return sol, log_ll_fixed, initial_beta['x'], stderr_fixed, pvalue_alt_fixed, zvalues_fixed, is_halton, is_delete_init
                         # return obj_1, log_ll_fixed, initial_beta.x, stderr_fixed, pvalue_alt_fixed, zvalues_fixed, is_halton, is_delete_init
-                else:
+                elif initial_beta is None:
+                    
                     self.convergance = None
                     print('why does it do this, this should not happen')
                     return sol, None, initial_beta['x'], None, None, None, 0, 1
+                else:
+                    print('trying fit anyway')
 
                 if dispersion == 0 or dispersion is None or dispersion == 1 or dispersion == 2 or dispersion == 3:
                     if initial_beta is not None:

{metacountregressor-0.1.36.dist-info → metacountregressor-0.1.38.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: metacountregressor
-Version: 0.1.36
+Version: 0.1.38
 Summary: A python package for count regression of rare events assisted by metaheuristics
 Author: zahern
 Author-email: zeke.ahern@hdr.qut.edu.au

{metacountregressor-0.1.36.dist-info → metacountregressor-0.1.38.dist-info}/RECORD

@@ -38,7 +38,7 @@ metacountregressor/set_data.csv,sha256=68iJkW4O4HVM8GyNlO0drwp8ZMXkccXCUc7jnA8xn
 metacountregressor/set_data_s.csv,sha256=hELwnv6RjpmXcMheFafwrYbLbyYE21hFKyqJhA8L05o,11111
 metacountregressor/setup.py,sha256=CpbdBScFhvStc6WByFiAlP7T5wGdWetsLI8X5JRRpP4,268
 metacountregressor/single_objective_finder.py,sha256=QYXUpxJp7-ul5ZiIKGgYGaH_yFFGUbI7X3yKu5asogE,1960
-metacountregressor/solution.py,sha256=eq83FPyydYc_VPmBjdQs1AqUjeEWbcIEn5OnXNshVh0,290278
+metacountregressor/solution.py,sha256=qQNpWCadMamou28o14FvgHQWmiv_H3dqMalr7iAp-7A,290567
 metacountregressor/Stage5A_1848_All_Initial_Columns.csv,sha256=uwsadEyupgIH1w5f8vnlwlo13ryww3VCGYlOnN0dEL0,188769
 metacountregressor/Stage5A_1848_All_Initial_Columns.xlsx,sha256=5U5Ab1jjGi5qoKp06Bw2tpdPjGaDGoyt5976AAFdEbs,699231
 metacountregressor/synth_dataset_generator.ipynb,sha256=caBMQJOaeINPZJw5aTsSOXhmenSqrpS7GycINAzUUxs,27153
@@ -48,6 +48,6 @@ metacountregressor/testML.R,sha256=UbTsLFUhoJG9bJnU2rbUKlfcprAkROnhREK41qKzbvQ,2
 metacountregressor/TestSetFake.csv,sha256=JPYAWYLAw7rgQHdGTz0rltMfapX8QYt3BVSyK_D-Lzg,1640
 metacountregressor/ThaiAccident.csv,sha256=NIi_uPyo5u-B6Hj0Ln9xuJ8fnvGbWK9GLdTWdpG5uug,418202
 metacountregressor/tk_app.py,sha256=0UM76hpQ-ha96ma_Z5ryxYQUSdF4PJBCsLuI1EGu6_E,59490
-metacountregressor-0.1.36.dist-info/METADATA,sha256=KGQAnPy7LHswiyCPkhEI0w8OhmFDgjz2YgRw8BxKqe8,28479
-metacountregressor-0.1.36.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
-metacountregressor-0.1.36.dist-info/RECORD,,
+metacountregressor-0.1.38.dist-info/METADATA,sha256=QofiZ2BrvMOZAA8T0mAd4bdEcltulMF_YpFEXezrlGY,28479
+metacountregressor-0.1.38.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
+metacountregressor-0.1.38.dist-info/RECORD,,