metacountregressor 1.0.4__tar.gz → 1.0.6__tar.gz

{metacountregressor-1.0.4/metacountregressor.egg-info → metacountregressor-1.0.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: metacountregressor
-Version: 1.0.4
+Version: 1.0.6
 Summary: Extensive Testing for Estimation of Data Count Models
 Home-page: https://github.com/zahern/CountDataEstimation
 Author: Zeke Ahern
@@ -95,7 +95,7 @@ X['Offset'] = np.log(df['AADT']) # Explicitley define how to offset the data, no
 X = df.drop(columns=['FREQ', 'ID', 'AADT'])  
 
 #some example argument, these are defualt so the following line is just for claritity. See the later agruments section for detials.
-arguments = {'algorithm': 'hs', 'test_percentage': 0.15, 'test_complexity': 6, 'instance_number':1,
+arguments = {'algorithm': 'hs', 'test_percentage': 0.15, 'test_complexity': 6, 'instance_name':1,
              'val_percentage':0.15, 'obj_1': 'bic', '_obj_2': 'RMSE_TEST', "_max_time": 6}
 # Fit the model with metacountregressor
 obj_fun = ObjectiveFunction(X, y, **arguments)
@@ -135,9 +135,9 @@ arguments = {
         'test_percentage': 0.2, # used in multi-objective optimisation only. Saves 20% of data for testing.
         'val_percenetage:': 0.2, # Saves 20% of data for testing.
         'test_complexity': 6, # Complexity level for testing (6 tests all) or a list to consider potential differences in complexity
-        'instance_number': 'name', # used for creeating a named folder where your models are saved into from the directory
+        'instance_name': 'name', # used for creeting a named folder where your models are saved into from the directory
         'distribution': ['Normal', 'LnNormal', 'Triangular', 'Uniform'],
-        'Model': [0,1],  # or equivalently ['POS', 'NB']
+        'model_types': [[0,1]],  # or equivalently ['POS', 'NB']
         'transformations': ['no', 'sqrt', 'archsinh'],
         'method_ll': 'BFGS_2',
         '_max_time': 10
@@ -156,7 +156,7 @@ manual_fit_spec = {
     'fixed_terms': ['SINGLE', 'LENGTH'],
     'rdm_terms': ['AADT:normal'],
     'rdm_cor_terms': ['GRADEBR:normal', 'CURVES:normal'],
-    'grouped_terms': [],
+    'grouped_rdm': [],
     'hetro_in_means': ['ACCESS:normal', 'MINRAD:normal'],
     'transformations': ['no', 'no', 'log', 'no', 'no', 'no', 'no'],
     'dispersion': 0
@@ -168,7 +168,7 @@ arguments = {
     'algorithm': 'hs',
     'test_percentage': 0.2,
     'test_complexity': 6,
-    'instance_number': 'name',
+    'instance_name': 'name',
     'Manual_Fit': manual_fit_spec
 }
 obj_fun = ObjectiveFunction(X, y, **arguments)
@@ -268,25 +268,22 @@ The following list describes the arguments available in this function. By defaul
 
 2. **`distributions`**: This argument accepts a list of strings where each string corresponds to a distribution. Valid options include:
     - "Normal"
-    - "Lindley"
     - "Uniform"
     - "LogNormal"
     - "Triangular"
-    - "Gamma"
     - "TruncatedNormal"
     - Any of the above, concatenated with ":" (e.g., "Normal:grouped"; requires a grouping term defined in the model)
 
 3. **`Model`**: This argument specifies the model form. It can be a list of integers representing different models to test:
     - 0: Poisson
     - 1: Negative-Binomial
-    - 2: Generalized-Poisson
 
 4. **`transformations`**: This argument accepts a list of strings representing available transformations within the framework. Valid options include:
     - "no"
     - "square-root"
     - "logarithmic"
     - "archsinh"
-    - "as_factor"
+    - "nil"
 
 5. **`is_multi`**: This argument accepts an integer indicating whether single or multiple objectives are to be tested (0 for single, 1 for multiple).
 
@@ -320,9 +317,9 @@ arguments = {
         'val_percentage:': 0.2, # Saves 20% of data for testing.
         'test_complexity': 3, # For Very simple Models
         'obj_1': 'BIC', '_obj_2': 'RMSE_TEST',
-        'instance_number': 'hs_run', # used for creeating a named folder where your models are saved into from the directory
+        'instance_name': 'hs_run', # used for creeating a named folder where your models are saved into from the directory
         'distribution': ['Normal'],
-        'Model': [0, 1],  # or equivalently ['POS', 'NB']
+        'model_types': [0, 1],  # or equivalently ['POS', 'NB']
         'transformations': ['no', 'sqrt', 'archsinh'],
         '_max_time': 10000
 } '''Arguments for the solution algorithm'''
@@ -398,7 +395,7 @@ manual_fit_spec = {
     'fixed_terms': ['const','YEAR'],
     'rdm_terms': [],
     'rdm_cor_terms': [],
-    'grouped_terms': [],
+    'grouped_rdm': [],
     'hetro_in_means': [],
     'transformations': ['no', 'no'],
     'dispersion': 1 #Negative Binomial 
@@ -410,7 +407,7 @@ arguments = {
     'algorithm': 'hs',
     'test_percentage': 0,
     'test_complexity': 6,
-    'instance_number': 'name',
+    'instance': 'name',
     'Manual_Fit': manual_fit_spec
 }
 obj_fun = ObjectiveFunction(data_exog, data_endog, **arguments)

{metacountregressor-1.0.4 → metacountregressor-1.0.6}/README.md

@@ -64,7 +64,7 @@ X['Offset'] = np.log(df['AADT']) # Explicitley define how to offset the data, no
 X = df.drop(columns=['FREQ', 'ID', 'AADT'])  
 
 #some example argument, these are defualt so the following line is just for claritity. See the later agruments section for detials.
-arguments = {'algorithm': 'hs', 'test_percentage': 0.15, 'test_complexity': 6, 'instance_number':1,
+arguments = {'algorithm': 'hs', 'test_percentage': 0.15, 'test_complexity': 6, 'instance_name':1,
              'val_percentage':0.15, 'obj_1': 'bic', '_obj_2': 'RMSE_TEST', "_max_time": 6}
 # Fit the model with metacountregressor
 obj_fun = ObjectiveFunction(X, y, **arguments)
@@ -104,9 +104,9 @@ arguments = {
         'test_percentage': 0.2, # used in multi-objective optimisation only. Saves 20% of data for testing.
         'val_percenetage:': 0.2, # Saves 20% of data for testing.
         'test_complexity': 6, # Complexity level for testing (6 tests all) or a list to consider potential differences in complexity
-        'instance_number': 'name', # used for creeating a named folder where your models are saved into from the directory
+        'instance_name': 'name', # used for creeting a named folder where your models are saved into from the directory
         'distribution': ['Normal', 'LnNormal', 'Triangular', 'Uniform'],
-        'Model': [0,1],  # or equivalently ['POS', 'NB']
+        'model_types': [[0,1]],  # or equivalently ['POS', 'NB']
         'transformations': ['no', 'sqrt', 'archsinh'],
         'method_ll': 'BFGS_2',
         '_max_time': 10
@@ -125,7 +125,7 @@ manual_fit_spec = {
     'fixed_terms': ['SINGLE', 'LENGTH'],
     'rdm_terms': ['AADT:normal'],
     'rdm_cor_terms': ['GRADEBR:normal', 'CURVES:normal'],
-    'grouped_terms': [],
+    'grouped_rdm': [],
     'hetro_in_means': ['ACCESS:normal', 'MINRAD:normal'],
     'transformations': ['no', 'no', 'log', 'no', 'no', 'no', 'no'],
     'dispersion': 0
@@ -137,7 +137,7 @@ arguments = {
     'algorithm': 'hs',
     'test_percentage': 0.2,
     'test_complexity': 6,
-    'instance_number': 'name',
+    'instance_name': 'name',
     'Manual_Fit': manual_fit_spec
 }
 obj_fun = ObjectiveFunction(X, y, **arguments)
@@ -237,25 +237,22 @@ The following list describes the arguments available in this function. By defaul
 
 2. **`distributions`**: This argument accepts a list of strings where each string corresponds to a distribution. Valid options include:
     - "Normal"
-    - "Lindley"
     - "Uniform"
     - "LogNormal"
     - "Triangular"
-    - "Gamma"
     - "TruncatedNormal"
     - Any of the above, concatenated with ":" (e.g., "Normal:grouped"; requires a grouping term defined in the model)
 
 3. **`Model`**: This argument specifies the model form. It can be a list of integers representing different models to test:
     - 0: Poisson
     - 1: Negative-Binomial
-    - 2: Generalized-Poisson
 
 4. **`transformations`**: This argument accepts a list of strings representing available transformations within the framework. Valid options include:
     - "no"
     - "square-root"
     - "logarithmic"
     - "archsinh"
-    - "as_factor"
+    - "nil"
 
 5. **`is_multi`**: This argument accepts an integer indicating whether single or multiple objectives are to be tested (0 for single, 1 for multiple).
 
@@ -289,9 +286,9 @@ arguments = {
         'val_percentage:': 0.2, # Saves 20% of data for testing.
         'test_complexity': 3, # For Very simple Models
         'obj_1': 'BIC', '_obj_2': 'RMSE_TEST',
-        'instance_number': 'hs_run', # used for creeating a named folder where your models are saved into from the directory
+        'instance_name': 'hs_run', # used for creeating a named folder where your models are saved into from the directory
         'distribution': ['Normal'],
-        'Model': [0, 1],  # or equivalently ['POS', 'NB']
+        'model_types': [0, 1],  # or equivalently ['POS', 'NB']
         'transformations': ['no', 'sqrt', 'archsinh'],
         '_max_time': 10000
 } '''Arguments for the solution algorithm'''
@@ -367,7 +364,7 @@ manual_fit_spec = {
     'fixed_terms': ['const','YEAR'],
     'rdm_terms': [],
     'rdm_cor_terms': [],
-    'grouped_terms': [],
+    'grouped_rdm': [],
     'hetro_in_means': [],
     'transformations': ['no', 'no'],
     'dispersion': 1 #Negative Binomial 
@@ -379,7 +376,7 @@ arguments = {
     'algorithm': 'hs',
     'test_percentage': 0,
     'test_complexity': 6,
-    'instance_number': 'name',
+    'instance': 'name',
     'Manual_Fit': manual_fit_spec
 }
 obj_fun = ObjectiveFunction(data_exog, data_endog, **arguments)

{metacountregressor-1.0.4 → metacountregressor-1.0.6}/README.rst

@@ -91,7 +91,7 @@ the Pareto frontier.
     X = df.drop(columns=['FREQ', 'ID', 'AADT'])  
     
     #some example argument, these are defualt so the following line is just for claritity. See the later agruments section for detials.
-    arguments = {'algorithm': 'hs', 'test_percentage': 0.15, 'test_complexity': 6, 'instance_number':1,
+    arguments = {'algorithm': 'hs', 'test_percentage': 0.15, 'test_complexity': 6, 'instance_name':1,
                  'val_percentage':0.15, 'obj_1': 'bic', '_obj_2': 'RMSE_TEST', "_max_time": 6}
     # Fit the model with metacountregressor
     obj_fun = ObjectiveFunction(X, y, **arguments)
@@ -158,9 +158,9 @@ code as a guide.
             'test_percentage': 0.2, # used in multi-objective optimisation only. Saves 20% of data for testing.
             'val_percenetage:': 0.2, # Saves 20% of data for testing.
             'test_complexity': 6, # Complexity level for testing (6 tests all) or a list to consider potential differences in complexity
-            'instance_number': 'name', # used for creeating a named folder where your models are saved into from the directory
+            'instance_name': 'name', # used for creeting a named folder where your models are saved into from the directory
             'distribution': ['Normal', 'LnNormal', 'Triangular', 'Uniform'],
-            'Model': [0,1],  # or equivalently ['POS', 'NB']
+            'model_types': [[0,1]],  # or equivalently ['POS', 'NB']
             'transformations': ['no', 'sqrt', 'archsinh'],
             'method_ll': 'BFGS_2',
             '_max_time': 10
@@ -184,7 +184,7 @@ modeling components may completely replace the initial solution.
         'fixed_terms': ['SINGLE', 'LENGTH'],
         'rdm_terms': ['AADT:normal'],
         'rdm_cor_terms': ['GRADEBR:normal', 'CURVES:normal'],
-        'grouped_terms': [],
+        'grouped_rdm': [],
         'hetro_in_means': ['ACCESS:normal', 'MINRAD:normal'],
         'transformations': ['no', 'no', 'log', 'no', 'no', 'no', 'no'],
         'dispersion': 0
@@ -196,7 +196,7 @@ modeling components may completely replace the initial solution.
         'algorithm': 'hs',
         'test_percentage': 0.2,
         'test_complexity': 6,
-        'instance_number': 'name',
+        'instance_name': 'name',
         'Manual_Fit': manual_fit_spec
     }
     obj_fun = ObjectiveFunction(X, y, **arguments)
@@ -341,11 +341,9 @@ considered. Example code will be provided later in this guide.
    each string corresponds to a distribution. Valid options include:
 
    -  �Normal�
-   -  �Lindley�
    -  �Uniform�
    -  �LogNormal�
    -  �Triangular�
-   -  �Gamma�
    -  �TruncatedNormal�
    -  Any of the above, concatenated with �:� (e.g., �Normal:grouped�;
       requires a grouping term defined in the model)
@@ -355,7 +353,6 @@ considered. Example code will be provided later in this guide.
 
    -  0: Poisson
    -  1: Negative-Binomial
-   -  2: Generalized-Poisson
 
 4. **``transformations``**: This argument accepts a list of strings
    representing available transformations within the framework. Valid
@@ -365,7 +362,7 @@ considered. Example code will be provided later in this guide.
    -  �square-root�
    -  �logarithmic�
    -  �archsinh�
-   -  �as_factor�
+   -  �nil�
 
 5. **``is_multi``**: This argument accepts an integer indicating whether
    single or multiple objectives are to be tested (0 for single, 1 for
@@ -413,9 +410,9 @@ factors for our search.
             'val_percentage:': 0.2, # Saves 20% of data for testing.
             'test_complexity': 3, # For Very simple Models
             'obj_1': 'BIC', '_obj_2': 'RMSE_TEST',
-            'instance_number': 'hs_run', # used for creeating a named folder where your models are saved into from the directory
+            'instance_name': 'hs_run', # used for creeating a named folder where your models are saved into from the directory
             'distribution': ['Normal'],
-            'Model': [0, 1],  # or equivalently ['POS', 'NB']
+            'model_types': [0, 1],  # or equivalently ['POS', 'NB']
             'transformations': ['no', 'sqrt', 'archsinh'],
             '_max_time': 10000
     } '''Arguments for the solution algorithm'''
@@ -495,7 +492,7 @@ packages, including Statsmodels.
         'fixed_terms': ['const','YEAR'],
         'rdm_terms': [],
         'rdm_cor_terms': [],
-        'grouped_terms': [],
+        'grouped_rdm': [],
         'hetro_in_means': [],
         'transformations': ['no', 'no'],
         'dispersion': 1 #Negative Binomial 
@@ -507,7 +504,7 @@ packages, including Statsmodels.
         'algorithm': 'hs',
         'test_percentage': 0,
         'test_complexity': 6,
-        'instance_number': 'name',
+        'instance': 'name',
         'Manual_Fit': manual_fit_spec
     }
     obj_fun = ObjectiveFunction(data_exog, data_endog, **arguments)

{metacountregressor-1.0.4 → metacountregressor-1.0.6}/metacountregressor/metaheuristics.py

@@ -265,6 +265,10 @@ def simulated_annealing(objective_function, initial_slns=None, **kwargs):
     # else:
     #   TEMP_ALPHA, MAX_STEPS, INTL_ACCEPT, STEPS, SWAP_PERC, NUM_INTL_SLNS, IS_MULTI= hyperparameters
     man = None
+    try:
+        objective_function.instance_name = str(0)
+    except:
+        pass
     if 'Manual_Fit' in kwargs:
         if kwargs['Manual_Fit'] is not None:
             man = kwargs['Manual_Fit']
@@ -292,7 +296,10 @@ def harmony_search(objective_function, initial_harmonies=None, hyperparameters=N
         objective_function._hms = kwargs.get('_hms')
     if kwargs.get('_hmcr') is not None:
         objective_function._hmcr = kwargs.get('_hmcr')
-
+    try:
+        objective_function.instance_name = f"run_hs_{str(0)}"
+    except:
+        pass
 
     man = None
     if 'Manual_Fit' in kwargs:
@@ -328,7 +335,7 @@ class Metaheuristic(object):
         self.F = kwargs['_AI']  # mustation scale
         self.iter = kwargs.get('_max_iter', 10000)
         self.cr = kwargs.get('_crossover_perc') or kwargs.get('_cr', 0.2)
-        self.instance_number = str(kwargs.get('instance_number', 1))
+        self.instance_name = str(kwargs.get('instance_name', 1))
         if objective_function.is_multi:
 
             self.obj_1 = objective_function._obj_1
@@ -416,6 +423,10 @@ class DifferentialEvolution(object):
 
     def __init__(self, objective_function, **kwargs):
         objective_function.algorithm = 'de'
+        try:
+            objective_function.instance_name = str(0)
+        except:
+            pass
         self._obj_fun = objective_function
         if self._obj_fun._obj_1 is None:
             print('no objective found, automatically selecting BIC')
@@ -431,8 +442,8 @@ class DifferentialEvolution(object):
         self.F = kwargs.get('_AI', 2)  # mutation scale
         self.iter = kwargs.get('_max_iter', 10000)
         self.cr = kwargs.get('_crossover_perc') or kwargs.get('_cr', 0.2)
-        self.instance_number = str(kwargs.get('instance_number', 1))
-        self.instance_number = objective_function.instance_number
+        self.instance_name = str(kwargs.get('instance_name', 1))
+        self.instance_name = objective_function.instance_name
         self.get_directory()
 
         self._population = list()
@@ -450,13 +461,13 @@ class DifferentialEvolution(object):
     def get_directory(self):
         # checking if the directory demo_folder2 
         # exist or not.
-        if not os.path.isdir(self.instance_number):
+        if not os.path.isdir(self.instance_name):
             # if the demo_folder2 directory is
             # not present then create it.
-            os.makedirs(self.instance_number)
+            os.makedirs(self.instance_name)
 
     def get_instance_name(self):
-        name = str(self.instance_number) + '/log.csv'
+        name = str(self.instance_name) + '/log.csv'
         return name
 
     def _random_selection(self, sln, i):
@@ -655,18 +666,18 @@ class DifferentialEvolution(object):
                         self._population[j] = obj_trial
                         
                         logger(self.it_process, obj_trial, self._population, True,
-                               self.instance_number + '/population_logger_strict_non_pareto.csv', 1)
+                               self.instance_name + '/population_logger_strict_non_pareto.csv', 1)
                         logger(self.it_process, obj_trial, self._pareto_population, True,
-                               self.instance_number + '/population_logger_pareto.csv', 1)
+                               self.instance_name + '/population_logger_pareto.csv', 1)
                     else:
                         if self.pf.calculate_difference(obj_trial, self._population[j]):
                             iterations_without_improvement = 0
                             self._population[j] = obj_trial
                             self._pareto_population = self.pf.Pareto_F
                             logger(self.it_process, obj_trial, self._population, True,
-                                   self.instance_number + '/population_logger_strict_non_pareto.csv', 1)
+                                   self.instance_name + '/population_logger_strict_non_pareto.csv', 1)
                             logger(self.it_process, obj_trial, self._pareto_population, True,
-                                   self.instance_number + '/population_logger_pareto.csv', 1)
+                                   self.instance_name + '/population_logger_pareto.csv', 1)
 
                     if it_best is None:
                         it_best = obj_trial
@@ -811,7 +822,7 @@ class SimulatedAnnealing(object):
         self.temp_min = 0.05
         self._MAX_ITERATIONS = int(kwargs.get('MAX_ITERATIONS', 10000)) or int(kwargs.get('_max_iter', 10000))
 
-        self.instance_number = str(objective_function.instance_number)
+        self.instance_name = str(objective_function.instance_name)
         self.accept = 0
         self.profiler = []
         self.update_t = self.cooling_linear_m
@@ -832,12 +843,12 @@ class SimulatedAnnealing(object):
     def get_directory(self):
         # checking if the directory demo_folder2 
         # exist or not.
-        if not os.path.isdir(self.instance_number):
+        if not os.path.isdir(self.instance_name):
             # not present then create it.
-            os.makedirs(self.instance_number)
+            os.makedirs(self.instance_name)
 
     def get_instance_name(self):
-        name = str(self.instance_number) + '/log.csv'
+        name = str(self.instance_name) + '/log.csv'
         return name
 
     def run(self, initial_slns=None, mod_init=None):
@@ -928,7 +939,7 @@ class SimulatedAnnealing(object):
                     didchange = self.pf.did_it_change()
                     if didchange:
                         pareto_logger(self.pf.Pareto_F, iteration, self._obj_fun.complexity_level,
-                                      self._obj_fun.instance_number)
+                                      self._obj_fun.instance_name)
                     self._current_energy = nbr_energy
                     self.current_struct = nbr_struct
                     self.accept += 1
@@ -1273,7 +1284,7 @@ class HarmonySearch(object):
         self.F = kwargs.get('_AI', 2)  # mutation scale
         self.iter = kwargs.get('_max_iter', 10000)
         self.cr = kwargs.get('_crossover_perc') or kwargs.get('_cr', 0.2)
-        self.instance_number = str(kwargs.get('instance_number', 1))
+        self.instance_name = str(kwargs.get('instance_name', 1))
 
 
 
@@ -1284,7 +1295,7 @@ class HarmonySearch(object):
         # harmony_history stores all hms harmonies every nth improvisations (i.e., one 'generation')
         self._harmony_history = list()
         # saves the best fitness
-        self.instance_number = str(objective_function.instance_number)
+        self.instance_name = str(objective_function.instance_name)
         self.get_directory()
         self._harmony_trace_best = list()
         self._harmony_trace_incumbent = list()
@@ -1304,13 +1315,13 @@ class HarmonySearch(object):
     def get_directory(self):
         # checking if the directory demo_folder2 
         # exist or not.
-        if not os.path.isdir(self.instance_number):
+        if not os.path.isdir(self.instance_name):
             # if the demo_folder2 directory is
             # not present then create it.
-            os.makedirs(self.instance_number)
+            os.makedirs(self.instance_name)
 
     def get_instance_name(self):
-        name = str(self.instance_number) + '/log.csv'
+        name = str(self.instance_name) + '/log.csv'
         return name
 
     def hard_mutate_index_and_value(self):
@@ -1421,7 +1432,7 @@ class HarmonySearch(object):
                                1)  # for consistency
                     except Exception as e:
                         print(e, 'logger run hs')
-                    # logger(num_imp, fitness, self._pareto_harmony_memory, True, self.instance_number +'/log_for_pareto_harmony_memory.csv', 1)
+                    # logger(num_imp, fitness, self._pareto_harmony_memory, True, self.instance_name +'/log_for_pareto_harmony_memory.csv', 1)
 
 
                 else:
@@ -1466,7 +1477,7 @@ class HarmonySearch(object):
 
                 else:
                     pareto_logger(self._pareto_harmony_memory, num_imp / self._obj_fun.get_hms(),
-                                  self._obj_fun.complexity_level, self._obj_fun.instance_number)
+                                  self._obj_fun.complexity_level, self._obj_fun.instance_name)
                 generation += 1
                 iterations_without_improvement += 1
 
@@ -1904,7 +1915,7 @@ class Mutlithreaded_Meta(DifferentialEvolution, SimulatedAnnealing, HarmonySearc
                         logger(num_imp, fitness, self._harmony_memory, True, self.get_instance_name(),
                                1)  # for consistency
                         logger(num_imp, fitness, self._pareto_harmony_memory, True,
-                               self.instance_number + '/log_for_pareto_harmony_memory.csv', 1)
+                               self.instance_name + '/log_for_pareto_harmony_memory.csv', 1)
 
 
                     else:
@@ -1949,7 +1960,7 @@ class Mutlithreaded_Meta(DifferentialEvolution, SimulatedAnnealing, HarmonySearc
 
                 else:
                     pareto_logger(self._pareto_harmony_memory, num_imp / self._obj_fun.get_hms(),
-                                  self._obj_fun.complexity_level, self._obj_fun.instance_number)
+                                  self._obj_fun.complexity_level, self._obj_fun.instance_name)
                 generation += 1
                 iterations_without_improvement += 1
 
@@ -2070,7 +2081,7 @@ class Mutlithreaded_Meta(DifferentialEvolution, SimulatedAnnealing, HarmonySearc
                         didchange = self.pf.did_it_change()
                         if didchange:
                             pareto_logger(self.pf.Pareto_F, iteration, self._obj_fun.complexity_level,
-                                          self._obj_fun.instance_number)
+                                          self._obj_fun.instance_name)
                         current_energy[j] = nbr_energy
 
                         self.accept += 1
@@ -2267,18 +2278,18 @@ class Mutlithreaded_Meta(DifferentialEvolution, SimulatedAnnealing, HarmonySearc
                         self._population[j] = obj_trial
 
                         logger(self.it_process, obj_trial, self._population, True,
-                               self.instance_number + '/population_logger_strict_non_pareto.csv', 1)
+                               self.instance_name + '/population_logger_strict_non_pareto.csv', 1)
                         logger(self.it_process, obj_trial, self._pareto_population, True,
-                               self.instance_number + '/population_logger_pareto.csv', 1)
+                               self.instance_name + '/population_logger_pareto.csv', 1)
                     else:
                         if self.pf.calculate_difference(obj_trial, self._population[j]):
                             iterations_without_improvement = 0
                             self._population[j] = obj_trial
                             self._pareto_population = self.pf.Pareto_F
                             logger(self.it_process, obj_trial, self._population, True,
-                                   self.instance_number + '/population_logger_strict_non_pareto.csv', 1)
+                                   self.instance_name + '/population_logger_strict_non_pareto.csv', 1)
                             logger(self.it_process, obj_trial, self._pareto_population, True,
-                                   self.instance_number + '/population_logger_pareto.csv', 1)
+                                   self.instance_name + '/population_logger_pareto.csv', 1)
 
                     if it_best is None:
                         it_best = obj_trial

{metacountregressor-1.0.4 → metacountregressor-1.0.6}/metacountregressor/solution.py

@@ -212,19 +212,19 @@ class ObjectiveFunction(object):
         if 'complexity_level' in kwargs:
             self.complexity_level = kwargs['complexity_level']
 
-        if 'instance_number' in kwargs:
-            self.instance_number = str(kwargs['instance_number'])
+        if 'instance_name' in kwargs:
+            self.instance_name = str(kwargs['instance_name'])
         else:
             
             print('no name set, setting name as 0')
-            self.instance_number = str(0)  # set an arbitrary instance number
+            self.instance_name = f"run_{str(0)}"  # set an arbitrary instance number
 
         if kwargs.get('save_directory', True):
             self.save_state = True
-            if not os.path.exists(self.instance_number):
+            if not os.path.exists(self.instance_name):
                 if kwargs.get('make_directory', True):
                     print('Making a Directory, if you want to stop from storing the files to this directory set argumet: make_directory:False')
-                    os.makedirs(self.instance_number)
+                    os.makedirs(self.instance_name)
         else:
             self.save_state = False
         if not hasattr(self, '_obj_1'):
@@ -257,7 +257,7 @@ class ObjectiveFunction(object):
             self.test_percentage = float(kwargs.get('test_percentage', 0))
             self.val_percentage = float(kwargs.get('val_percentage', 0))
             if self.test_percentage == 0:
-                print('test percentage is 0, please enter arg test_percentage as decimal, eg 0.8')
+                print('test percentage is 0, please enter arg test_percentage as decimal if intended for multi objective optimisation, eg 0.8')
                 print('continuing single objective')
                 time.sleep(2)
                 self.is_multi = False
@@ -296,6 +296,7 @@ class ObjectiveFunction(object):
                 ids = np.random.choice(N, training_size, replace=False)
                 id_unique = np.array([i for i in range(N)])
                 ids = id_unique[ids]
+                #todo make sure its split so counts are split
                 train_idx = [ii for ii in range(len(id_unique)) if id_unique[ii] in ids]
                 test_idx = [ii for ii in range(len(id_unique)) if id_unique[ii] not in ids]
                 df_train = x_data.loc[train_idx, :]
@@ -429,7 +430,7 @@ class ObjectiveFunction(object):
 
 
 
-        self.Ndraws = kwargs.get('Ndraws', 100)
+        self.Ndraws = kwargs.get('Ndraws', 200)
         self.draws1 = None
         self.initial_sig = 1  # pass the test of a single model
         self.pvalue_sig_value = .1
@@ -455,7 +456,7 @@ class ObjectiveFunction(object):
         self._transformations = kwargs.get('_transformations', ["no", "log", "sqrt", "arcsinh", "nil"])
         # self._distribution = ['triangular', 'uniform', 'normal', 'ln_normal', 'tn_normal', 'lindley']
 
-        self._distribution = kwargs.get('_distributions', ['triangular', 'uniform', 'normal', 'tn_normal'])
+        self._distribution = kwargs.get('_distributions', ['triangular', 'uniform', 'normal', 'tn_normal', 'ln_normal'])
 
         if self.G is not None:
             #TODO need to handle this for groups
@@ -484,12 +485,24 @@ class ObjectiveFunction(object):
         self._discrete_values = self._discrete_values + \
                                 self.define_distributions_analyst(extra=kwargs.get('decisions', None))
 
-        if 'model_types' in kwargs:
-            model_types = kwargs['model_types']
+        if 'model_types' in kwargs or 'Model' in kwargs:
+            model_type_mapping = {
+                    'POS': 0,
+                    'NB': 1
+                }
+            model_types = kwargs.get('model_types', kwargs.get('Model', [[0,1]]))
+            converted_model_types = [
+                                        [model_type_mapping.get(item, item) for item in sublist]
+                                        for sublist in model_types
+                                    ]
+            model_types = converted_model_types
+            #this should be a list of list like [[0, 1]]
+            # also if it is [['POS', 'NB']] then it will be converted to [0, 1]
         else:
 
 
             model_types = [[0, 1]]  # add 2 for Generalized Poisson
+            
             #model_types = [[0]]
         
         if self.linear_regression:
@@ -1250,10 +1263,10 @@ class ObjectiveFunction(object):
                 caption = " ".join(caption_parts)
                 # print(latextable.draw_latex(table, caption=caption, caption_above = True))
                 if solution is None:
-                    file_name = self.instance_number + "/sln" + \
+                    file_name = self.instance_name + "/sln" + \
                                 "_with_BIC_" + str(self.bic) + ".tex"
                 else:
-                    file_name = self.instance_number + "/sln" + \
+                    file_name = self.instance_name + "/sln" + \
                                 str(solution['sol_num']) + \
                                 "_with_BIC_" + str(self.bic) + ".tex"
 

{metacountregressor-1.0.4 → metacountregressor-1.0.6/metacountregressor.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: metacountregressor
-Version: 1.0.4
+Version: 1.0.6
 Summary: Extensive Testing for Estimation of Data Count Models
 Home-page: https://github.com/zahern/CountDataEstimation
 Author: Zeke Ahern
@@ -95,7 +95,7 @@ X['Offset'] = np.log(df['AADT']) # Explicitley define how to offset the data, no
 X = df.drop(columns=['FREQ', 'ID', 'AADT'])  
 
 #some example argument, these are defualt so the following line is just for claritity. See the later agruments section for detials.
-arguments = {'algorithm': 'hs', 'test_percentage': 0.15, 'test_complexity': 6, 'instance_number':1,
+arguments = {'algorithm': 'hs', 'test_percentage': 0.15, 'test_complexity': 6, 'instance_name':1,
              'val_percentage':0.15, 'obj_1': 'bic', '_obj_2': 'RMSE_TEST', "_max_time": 6}
 # Fit the model with metacountregressor
 obj_fun = ObjectiveFunction(X, y, **arguments)
@@ -135,9 +135,9 @@ arguments = {
         'test_percentage': 0.2, # used in multi-objective optimisation only. Saves 20% of data for testing.
         'val_percenetage:': 0.2, # Saves 20% of data for testing.
         'test_complexity': 6, # Complexity level for testing (6 tests all) or a list to consider potential differences in complexity
-        'instance_number': 'name', # used for creeating a named folder where your models are saved into from the directory
+        'instance_name': 'name', # used for creeting a named folder where your models are saved into from the directory
         'distribution': ['Normal', 'LnNormal', 'Triangular', 'Uniform'],
-        'Model': [0,1],  # or equivalently ['POS', 'NB']
+        'model_types': [[0,1]],  # or equivalently ['POS', 'NB']
         'transformations': ['no', 'sqrt', 'archsinh'],
         'method_ll': 'BFGS_2',
         '_max_time': 10
@@ -156,7 +156,7 @@ manual_fit_spec = {
     'fixed_terms': ['SINGLE', 'LENGTH'],
     'rdm_terms': ['AADT:normal'],
     'rdm_cor_terms': ['GRADEBR:normal', 'CURVES:normal'],
-    'grouped_terms': [],
+    'grouped_rdm': [],
     'hetro_in_means': ['ACCESS:normal', 'MINRAD:normal'],
     'transformations': ['no', 'no', 'log', 'no', 'no', 'no', 'no'],
     'dispersion': 0
@@ -168,7 +168,7 @@ arguments = {
     'algorithm': 'hs',
     'test_percentage': 0.2,
     'test_complexity': 6,
-    'instance_number': 'name',
+    'instance_name': 'name',
     'Manual_Fit': manual_fit_spec
 }
 obj_fun = ObjectiveFunction(X, y, **arguments)
@@ -268,25 +268,22 @@ The following list describes the arguments available in this function. By defaul
 
 2. **`distributions`**: This argument accepts a list of strings where each string corresponds to a distribution. Valid options include:
     - "Normal"
-    - "Lindley"
     - "Uniform"
     - "LogNormal"
     - "Triangular"
-    - "Gamma"
     - "TruncatedNormal"
     - Any of the above, concatenated with ":" (e.g., "Normal:grouped"; requires a grouping term defined in the model)
 
 3. **`Model`**: This argument specifies the model form. It can be a list of integers representing different models to test:
     - 0: Poisson
     - 1: Negative-Binomial
-    - 2: Generalized-Poisson
 
 4. **`transformations`**: This argument accepts a list of strings representing available transformations within the framework. Valid options include:
     - "no"
     - "square-root"
     - "logarithmic"
     - "archsinh"
-    - "as_factor"
+    - "nil"
 
 5. **`is_multi`**: This argument accepts an integer indicating whether single or multiple objectives are to be tested (0 for single, 1 for multiple).
 
@@ -320,9 +317,9 @@ arguments = {
         'val_percentage:': 0.2, # Saves 20% of data for testing.
         'test_complexity': 3, # For Very simple Models
         'obj_1': 'BIC', '_obj_2': 'RMSE_TEST',
-        'instance_number': 'hs_run', # used for creeating a named folder where your models are saved into from the directory
+        'instance_name': 'hs_run', # used for creeating a named folder where your models are saved into from the directory
         'distribution': ['Normal'],
-        'Model': [0, 1],  # or equivalently ['POS', 'NB']
+        'model_types': [0, 1],  # or equivalently ['POS', 'NB']
         'transformations': ['no', 'sqrt', 'archsinh'],
         '_max_time': 10000
 } '''Arguments for the solution algorithm'''
@@ -398,7 +395,7 @@ manual_fit_spec = {
     'fixed_terms': ['const','YEAR'],
     'rdm_terms': [],
     'rdm_cor_terms': [],
-    'grouped_terms': [],
+    'grouped_rdm': [],
     'hetro_in_means': [],
     'transformations': ['no', 'no'],
     'dispersion': 1 #Negative Binomial 
@@ -410,7 +407,7 @@ arguments = {
     'algorithm': 'hs',
     'test_percentage': 0,
     'test_complexity': 6,
-    'instance_number': 'name',
+    'instance': 'name',
     'Manual_Fit': manual_fit_spec
 }
 obj_fun = ObjectiveFunction(data_exog, data_endog, **arguments)

metacountregressor-1.0.6/version.txt

@@ -0,0 +1 @@
+1.0.6

metacountregressor-1.0.4/version.txt

@@ -1 +0,0 @@
-1.0.4