metacountregressor 0.1.91__tar.gz → 0.1.96__tar.gz

{metacountregressor-0.1.91 → metacountregressor-0.1.96}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: metacountregressor
-Version: 0.1.91
+Version: 0.1.96
 Summary: Extensions for a Python package for estimation of count models.
 Home-page: https://github.com/zahern/CountDataEstimation
 Author: Zeke Ahern
@@ -274,6 +274,8 @@ Let's begin by fitting very simple models and use the structure of these models
 
 
 ```python
+
+'''Setup Data'''
 df = pd.read_csv(
 "https://raw.githubusercontent.com/zahern/data/main/Ex-16-3.csv")
 X = df
@@ -281,25 +283,158 @@ y = df['FREQ']  # Frequency of crashes
 X['Offset'] = np.log(df['AADT']) # Explicitley define how to offset the data, no offset otherwise
 # Drop Y, selected offset term and  ID as there are no panels
 X = df.drop(columns=['FREQ', 'ID', 'AADT'])  
-
+'''Aguments for Solution'''
 arguments = {
-        'algorithm': 'hs', #alternatively input 'de', or 'sa'
-        'is_multi': 1,
+        'is_multi': 1, #is two objectives considered
         'test_percentage': 0.2, # used in multi-objective optimisation only. Saves 20% of data for testing.
         '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': 'name', # used for creeating a named folder where your models are saved into from the directory
+        'instance_number': 'hs_run', # used for creeating a named folder where your models are saved into from the directory
         'distribution': ['Normal'],
-        'Model': [0],  # or equivalently ['POS', 'NB']
+        'Model': [0, 1],  # or equivalently ['POS', 'NB']
         'transformations': ['no', 'sqrt', 'archsinh'],
         '_max_time': 10000
-    }
+} '''Arguments for the solution algorithm'''
+argument_hs = {
+    '_hms': 20, #harmony memory size,
+    '_mpai': 1, #adjustement inded
+    '_par': 0.3,
+    '_hmcr': .5
+}
 obj_fun = ObjectiveFunction(X, y, **arguments)
-results = harmony_search(obj_fun)
+results = harmony_search(obj_fun, None, argument_hs)
 print(results)
 ```
 
+## Example: Assistance by Differential Evololution and Simulated Annealing
+Similiar to the above example we only need to change the hyperparamaters, the obj_fun can remane the same
+
+
+```python
+argument_de = {'_AI': 2,
+            '_crossover_perc': .2,
+            '_max_iter': 1000,
+            '_pop_size': 25
+}
+de_results = differential_evolution(obj_fun, None, **argument_de)
+print(de_results)
+
+
+args_sa = {'alpha': .99,
+        'STEPS_PER_TEMP': 10,
+        'INTL_ACPT': 0.5,
+        '_crossover_perc': .3,
+        'MAX_ITERATIONS': 1000,
+        '_num_intl_slns': 25,
+}
+
+sa_results = simulated_annealing(obj_fun, None, **args_sa)
+print(sa_results)
+```
+
+## Comparing to statsmodels
+The following example illustrates how the output compares to well-known packages, including Statsmodels."
+
+
+```python
+# Load modules and data
+import statsmodels.api as sm
+
+data = sm.datasets.sunspots.load_pandas().data
+#print(data.exog)
+data_exog = data['YEAR']
+data_exog = sm.add_constant(data_exog)
+data_endog = data['SUNACTIVITY']
+
+# Instantiate a gamma family model with the default link function.
+import numpy as np
+
+gamma_model = sm.NegativeBinomial(data_endog, data_exog)
+gamma_results = gamma_model.fit()
+
+print(gamma_results.summary())
+
+
+
+
+#NOW LET's COMPARE THIS TO METACOUNTREGRESSOR
+
+
+
+
+ #Model Decisions, 
+manual_fit_spec = {
+    'fixed_terms': ['const','YEAR'],
+    'rdm_terms': [],
+    'rdm_cor_terms': [],
+    'grouped_terms': [],
+    'hetro_in_means': [],
+    'transformations': ['no', 'no'],
+    'dispersion': 1 #Negative Binomial 
+}
+
+
+#Arguments
+arguments = {
+    'algorithm': 'hs',
+    'test_percentage': 0,
+    'test_complexity': 6,
+    'instance_number': 'name',
+    'Manual_Fit': manual_fit_spec
+}
+obj_fun = ObjectiveFunction(data_exog, data_endog, **arguments)
+
+
+
+
+
+
+
+```
+
+    Optimization terminated successfully.
+             Current function value: 4.877748
+             Iterations: 22
+             Function evaluations: 71
+             Gradient evaluations: 70
+                         NegativeBinomial Regression Results                      
+    ==============================================================================
+    Dep. Variable:            SUNACTIVITY   No. Observations:                  309
+    Model:               NegativeBinomial   Df Residuals:                      307
+    Method:                           MLE   Df Model:                            1
+    Date:                Tue, 13 Aug 2024   Pseudo R-squ.:                0.004087
+    Time:                        14:13:22   Log-Likelihood:                -1507.2
+    converged:                       True   LL-Null:                       -1513.4
+    Covariance Type:            nonrobust   LLR p-value:                 0.0004363
+    ==============================================================================
+                     coef    std err          z      P>|z|      [0.025      0.975]
+    ------------------------------------------------------------------------------
+    const          0.2913      1.017      0.287      0.774      -1.701       2.284
+    YEAR           0.0019      0.001      3.546      0.000       0.001       0.003
+    alpha          0.7339      0.057     12.910      0.000       0.622       0.845
+    ==============================================================================
+    0.1.88
+    Setup Complete...
+    Benchmaking test with Seed 42
+    1
+    --------------------------------------------------------------------------------
+    Log-Likelihood:  -1509.0683662284273
+    --------------------------------------------------------------------------------
+    bic: 3035.84
+    --------------------------------------------------------------------------------
+    MSE: 10000000.00
+    +--------+--------+-------+----------+----------+------------+
+    | Effect | $\tau$ | Coeff | Std. Err | z-values | Prob |z|>Z |
+    +========+========+=======+==========+==========+============+
+    | const  | no     | 0.10  |   0.25   |   0.39   | 0.70       |
+    +--------+--------+-------+----------+----------+------------+
+    | YEAR   | no     | 0.00  |   0.00   |  20.39   | 0.00***    |
+    +--------+--------+-------+----------+----------+------------+
+    | nb     |        | 1.33  |   0.00   |  50.00   | 0.00***    |
+    +--------+--------+-------+----------+----------+------------+
+    
+
 ## Paper
 
 The following tutorial is in conjunction with our latest paper. A link the current paper can be found here [MetaCountRegressor](https://www.overleaf.com/read/mszwpwzcxsng#c5eb0c)

{metacountregressor-0.1.91 → metacountregressor-0.1.96}/README.rst

@@ -9,7 +9,7 @@ Tutorial also available as a jupyter notebook
 =============================================
 
 `Download Example
-Notebook <https://github.com/zahern/CountDataEstimation/blob/main/README.ipynb>`__
+Notebook <https://github.com/zahern/CountDataEstimation/blob/main/Tutorial.ipynb>`__
 
 The tutorial provides more extensive examples on how to run the code and
 perform experiments. Further documentation is currently in development.
@@ -376,6 +376,8 @@ factors for our search.
 
 .. code:: ipython3
 
+    
+    '''Setup Data'''
     df = pd.read_csv(
     "https://raw.githubusercontent.com/zahern/data/main/Ex-16-3.csv")
     X = df
@@ -383,24 +385,164 @@ factors for our search.
     X['Offset'] = np.log(df['AADT']) # Explicitley define how to offset the data, no offset otherwise
     # Drop Y, selected offset term and  ID as there are no panels
     X = df.drop(columns=['FREQ', 'ID', 'AADT'])  
-    
+    '''Aguments for Solution'''
     arguments = {
-            'algorithm': 'hs', #alternatively input 'de', or 'sa'
-            'is_multi': 1,
+            'is_multi': 1, #is two objectives considered
             'test_percentage': 0.2, # used in multi-objective optimisation only. Saves 20% of data for testing.
             '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': 'name', # used for creeating a named folder where your models are saved into from the directory
+            'instance_number': 'hs_run', # used for creeating a named folder where your models are saved into from the directory
             'distribution': ['Normal'],
-            'Model': [0],  # or equivalently ['POS', 'NB']
+            'Model': [0, 1],  # or equivalently ['POS', 'NB']
             'transformations': ['no', 'sqrt', 'archsinh'],
             '_max_time': 10000
-        }
+    } '''Arguments for the solution algorithm'''
+    argument_hs = {
+        '_hms': 20, #harmony memory size,
+        '_mpai': 1, #adjustement inded
+        '_par': 0.3,
+        '_hmcr': .5
+    }
     obj_fun = ObjectiveFunction(X, y, **arguments)
-    results = harmony_search(obj_fun)
+    results = harmony_search(obj_fun, None, argument_hs)
     print(results)
 
+Example: Assistance by Differential Evololution and Simulated Annealing
+-----------------------------------------------------------------------
+
+Similiar to the above example we only need to change the
+hyperparamaters, the obj_fun can remane the same
+
+.. code:: ipython3
+
+    argument_de = {'_AI': 2,
+                '_crossover_perc': .2,
+                '_max_iter': 1000,
+                '_pop_size': 25
+    }
+    de_results = differential_evolution(obj_fun, None, **argument_de)
+    print(de_results)
+    
+    
+    args_sa = {'alpha': .99,
+            'STEPS_PER_TEMP': 10,
+            'INTL_ACPT': 0.5,
+            '_crossover_perc': .3,
+            'MAX_ITERATIONS': 1000,
+            '_num_intl_slns': 25,
+    }
+    
+    sa_results = simulated_annealing(obj_fun, None, **args_sa)
+    print(sa_results)
+
+Comparing to statsmodels
+------------------------
+
+The following example illustrates how the output compares to well-known
+packages, including Statsmodels.�
+
+.. code:: ipython3
+
+    # Load modules and data
+    import statsmodels.api as sm
+    
+    data = sm.datasets.sunspots.load_pandas().data
+    #print(data.exog)
+    data_exog = data['YEAR']
+    data_exog = sm.add_constant(data_exog)
+    data_endog = data['SUNACTIVITY']
+    
+    # Instantiate a gamma family model with the default link function.
+    import numpy as np
+    
+    gamma_model = sm.NegativeBinomial(data_endog, data_exog)
+    gamma_results = gamma_model.fit()
+    
+    print(gamma_results.summary())
+    
+    
+    
+    
+    #NOW LET's COMPARE THIS TO METACOUNTREGRESSOR
+    
+    
+    
+    
+     #Model Decisions, 
+    manual_fit_spec = {
+        'fixed_terms': ['const','YEAR'],
+        'rdm_terms': [],
+        'rdm_cor_terms': [],
+        'grouped_terms': [],
+        'hetro_in_means': [],
+        'transformations': ['no', 'no'],
+        'dispersion': 1 #Negative Binomial 
+    }
+    
+    
+    #Arguments
+    arguments = {
+        'algorithm': 'hs',
+        'test_percentage': 0,
+        'test_complexity': 6,
+        'instance_number': 'name',
+        'Manual_Fit': manual_fit_spec
+    }
+    obj_fun = ObjectiveFunction(data_exog, data_endog, **arguments)
+    
+    
+    
+    
+    
+    
+    
+
+
+.. parsed-literal::
+
+    Optimization terminated successfully.
+             Current function value: 4.877748
+             Iterations: 22
+             Function evaluations: 71
+             Gradient evaluations: 70
+                         NegativeBinomial Regression Results                      
+    ==============================================================================
+    Dep. Variable:            SUNACTIVITY   No. Observations:                  309
+    Model:               NegativeBinomial   Df Residuals:                      307
+    Method:                           MLE   Df Model:                            1
+    Date:                Tue, 13 Aug 2024   Pseudo R-squ.:                0.004087
+    Time:                        14:13:22   Log-Likelihood:                -1507.2
+    converged:                       True   LL-Null:                       -1513.4
+    Covariance Type:            nonrobust   LLR p-value:                 0.0004363
+    ==============================================================================
+                     coef    std err          z      P>|z|      [0.025      0.975]
+    ------------------------------------------------------------------------------
+    const          0.2913      1.017      0.287      0.774      -1.701       2.284
+    YEAR           0.0019      0.001      3.546      0.000       0.001       0.003
+    alpha          0.7339      0.057     12.910      0.000       0.622       0.845
+    ==============================================================================
+    0.1.88
+    Setup Complete...
+    Benchmaking test with Seed 42
+    1
+    --------------------------------------------------------------------------------
+    Log-Likelihood:  -1509.0683662284273
+    --------------------------------------------------------------------------------
+    bic: 3035.84
+    --------------------------------------------------------------------------------
+    MSE: 10000000.00
+    +--------+--------+-------+----------+----------+------------+
+    | Effect | $\tau$ | Coeff | Std. Err | z-values | Prob |z|>Z |
+    +========+========+=======+==========+==========+============+
+    | const  | no     | 0.10  |   0.25   |   0.39   | 0.70       |
+    +--------+--------+-------+----------+----------+------------+
+    | YEAR   | no     | 0.00  |   0.00   |  20.39   | 0.00***    |
+    +--------+--------+-------+----------+----------+------------+
+    | nb     |        | 1.33  |   0.00   |  50.00   | 0.00***    |
+    +--------+--------+-------+----------+----------+------------+
+    
+
 Paper
 -----
 

{metacountregressor-0.1.91 → metacountregressor-0.1.96}/metacountregressor.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: metacountregressor
-Version: 0.1.91
+Version: 0.1.96
 Summary: Extensions for a Python package for estimation of count models.
 Home-page: https://github.com/zahern/CountDataEstimation
 Author: Zeke Ahern
@@ -274,6 +274,8 @@ Let's begin by fitting very simple models and use the structure of these models
 
 
 ```python
+
+'''Setup Data'''
 df = pd.read_csv(
 "https://raw.githubusercontent.com/zahern/data/main/Ex-16-3.csv")
 X = df
@@ -281,25 +283,158 @@ y = df['FREQ']  # Frequency of crashes
 X['Offset'] = np.log(df['AADT']) # Explicitley define how to offset the data, no offset otherwise
 # Drop Y, selected offset term and  ID as there are no panels
 X = df.drop(columns=['FREQ', 'ID', 'AADT'])  
-
+'''Aguments for Solution'''
 arguments = {
-        'algorithm': 'hs', #alternatively input 'de', or 'sa'
-        'is_multi': 1,
+        'is_multi': 1, #is two objectives considered
         'test_percentage': 0.2, # used in multi-objective optimisation only. Saves 20% of data for testing.
         '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': 'name', # used for creeating a named folder where your models are saved into from the directory
+        'instance_number': 'hs_run', # used for creeating a named folder where your models are saved into from the directory
         'distribution': ['Normal'],
-        'Model': [0],  # or equivalently ['POS', 'NB']
+        'Model': [0, 1],  # or equivalently ['POS', 'NB']
         'transformations': ['no', 'sqrt', 'archsinh'],
         '_max_time': 10000
-    }
+} '''Arguments for the solution algorithm'''
+argument_hs = {
+    '_hms': 20, #harmony memory size,
+    '_mpai': 1, #adjustement inded
+    '_par': 0.3,
+    '_hmcr': .5
+}
 obj_fun = ObjectiveFunction(X, y, **arguments)
-results = harmony_search(obj_fun)
+results = harmony_search(obj_fun, None, argument_hs)
 print(results)
 ```
 
+## Example: Assistance by Differential Evololution and Simulated Annealing
+Similiar to the above example we only need to change the hyperparamaters, the obj_fun can remane the same
+
+
+```python
+argument_de = {'_AI': 2,
+            '_crossover_perc': .2,
+            '_max_iter': 1000,
+            '_pop_size': 25
+}
+de_results = differential_evolution(obj_fun, None, **argument_de)
+print(de_results)
+
+
+args_sa = {'alpha': .99,
+        'STEPS_PER_TEMP': 10,
+        'INTL_ACPT': 0.5,
+        '_crossover_perc': .3,
+        'MAX_ITERATIONS': 1000,
+        '_num_intl_slns': 25,
+}
+
+sa_results = simulated_annealing(obj_fun, None, **args_sa)
+print(sa_results)
+```
+
+## Comparing to statsmodels
+The following example illustrates how the output compares to well-known packages, including Statsmodels."
+
+
+```python
+# Load modules and data
+import statsmodels.api as sm
+
+data = sm.datasets.sunspots.load_pandas().data
+#print(data.exog)
+data_exog = data['YEAR']
+data_exog = sm.add_constant(data_exog)
+data_endog = data['SUNACTIVITY']
+
+# Instantiate a gamma family model with the default link function.
+import numpy as np
+
+gamma_model = sm.NegativeBinomial(data_endog, data_exog)
+gamma_results = gamma_model.fit()
+
+print(gamma_results.summary())
+
+
+
+
+#NOW LET's COMPARE THIS TO METACOUNTREGRESSOR
+
+
+
+
+ #Model Decisions, 
+manual_fit_spec = {
+    'fixed_terms': ['const','YEAR'],
+    'rdm_terms': [],
+    'rdm_cor_terms': [],
+    'grouped_terms': [],
+    'hetro_in_means': [],
+    'transformations': ['no', 'no'],
+    'dispersion': 1 #Negative Binomial 
+}
+
+
+#Arguments
+arguments = {
+    'algorithm': 'hs',
+    'test_percentage': 0,
+    'test_complexity': 6,
+    'instance_number': 'name',
+    'Manual_Fit': manual_fit_spec
+}
+obj_fun = ObjectiveFunction(data_exog, data_endog, **arguments)
+
+
+
+
+
+
+
+```
+
+    Optimization terminated successfully.
+             Current function value: 4.877748
+             Iterations: 22
+             Function evaluations: 71
+             Gradient evaluations: 70
+                         NegativeBinomial Regression Results                      
+    ==============================================================================
+    Dep. Variable:            SUNACTIVITY   No. Observations:                  309
+    Model:               NegativeBinomial   Df Residuals:                      307
+    Method:                           MLE   Df Model:                            1
+    Date:                Tue, 13 Aug 2024   Pseudo R-squ.:                0.004087
+    Time:                        14:13:22   Log-Likelihood:                -1507.2
+    converged:                       True   LL-Null:                       -1513.4
+    Covariance Type:            nonrobust   LLR p-value:                 0.0004363
+    ==============================================================================
+                     coef    std err          z      P>|z|      [0.025      0.975]
+    ------------------------------------------------------------------------------
+    const          0.2913      1.017      0.287      0.774      -1.701       2.284
+    YEAR           0.0019      0.001      3.546      0.000       0.001       0.003
+    alpha          0.7339      0.057     12.910      0.000       0.622       0.845
+    ==============================================================================
+    0.1.88
+    Setup Complete...
+    Benchmaking test with Seed 42
+    1
+    --------------------------------------------------------------------------------
+    Log-Likelihood:  -1509.0683662284273
+    --------------------------------------------------------------------------------
+    bic: 3035.84
+    --------------------------------------------------------------------------------
+    MSE: 10000000.00
+    +--------+--------+-------+----------+----------+------------+
+    | Effect | $\tau$ | Coeff | Std. Err | z-values | Prob |z|>Z |
+    +========+========+=======+==========+==========+============+
+    | const  | no     | 0.10  |   0.25   |   0.39   | 0.70       |
+    +--------+--------+-------+----------+----------+------------+
+    | YEAR   | no     | 0.00  |   0.00   |  20.39   | 0.00***    |
+    +--------+--------+-------+----------+----------+------------+
+    | nb     |        | 1.33  |   0.00   |  50.00   | 0.00***    |
+    +--------+--------+-------+----------+----------+------------+
+    
+
 ## Paper
 
 The following tutorial is in conjunction with our latest paper. A link the current paper can be found here [MetaCountRegressor](https://www.overleaf.com/read/mszwpwzcxsng#c5eb0c)