metacountregressor 0.1.136__tar.gz → 0.1.138__tar.gz

{metacountregressor-0.1.136 → metacountregressor-0.1.138}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: metacountregressor
-Version: 0.1.136
+Version: 0.1.138
 Summary: Extensions for a Python package for estimation of count models.
 Home-page: https://github.com/zahern/CountDataEstimation
 Author: Zeke Ahern

{metacountregressor-0.1.136 → metacountregressor-0.1.138}/metacountregressor/helperprocess.py

@@ -1,12 +1,29 @@
+from os.path import exists
+
 import numpy as np
 import pandas as pd
 import csv
 import matplotlib.pyplot as plt
 from scipy import stats as st
 from sklearn.preprocessing import StandardScaler
+from win32comext.shell.demos.IActiveDesktop import existing_item
 
 plt.style.use('https://github.com/dhaitz/matplotlib-stylesheets/raw/master/pitayasmoothie-dark.mplstyle')
 
+
+
+
+
+from itertools import product
+
+# Function to create a list of dictionaries from a parameter grid
+def generate_param_combinations(param_grid):
+    keys = param_grid.keys()
+    values = param_grid.values()
+    combinations = [dict(zip(keys, v)) for v in product(*values)]
+    return combinations
+
+
 ##Select the best Features Based on RF
 def select_features(X_train, y_train, n_f=16):
     try:
@@ -179,17 +196,38 @@ config = {
     }
 }
 '''
-def set_up_analyst_constraints(data_characteristic, variable_decisions_alt = None):
+def null_handler(vari):
+    if vari in locals():
+        return vari
+    else:
+        print(f'{vari} does not exist, setting None..')
+        return None
+
+
+def set_up_analyst_constraints(data_characteristic, model_terms,  variable_decisions_alt = None):
+
+
     name_data_characteristics = data_characteristic.columns.tolist()
-    distu = ['n', 'u', 't']
-    tra = ['no']
+    # Get non-None values as a list
+    non_none_terms = [value for value in model_terms.values() if value is not None]
+    # how to make name_data_characteristics - non_none_terms
+
+    result = [item for item in name_data_characteristics if item not in non_none_terms]
+    distu = ['Normal', 'Uniform', 'Triangular']
+    tra = ['no', 'sqrt', 'arcsinh']
+    if model_terms.get('grouped') is None:
+        print('cant have grouped rpm, removing level 4 from every item')
+        MAKE_ALL_4_FALSE = True
+    else:
+        MAKE_ALL_4_FALSE = False
+
     variable_decisions = {
         name: {
             'levels': list(range(6)),
             'distributions': distu,
             'transformations': tra
         }
-        for name in name_data_characteristics
+        for name in result
     }
     # Override elements in the original dictionary with the alt dictionary
     if variable_decisions_alt is not None:
@@ -208,7 +246,11 @@ def set_up_analyst_constraints(data_characteristic, variable_decisions_alt = Non
 
         # Add levels as True/False for Level 0 through Level 5
         for level in range(6):  # Assuming Level 0 to Level 5
-            row[f'Level {level}'] = level in details['levels']
+
+            if level == 4 and MAKE_ALL_4_FALSE:
+                row[f'Level {level}'] = False
+            else:
+                row[f'Level {level}'] = level in details['levels']
 
         # Add distributions and transformations directly
         row['distributions'] = details['distributions']
@@ -218,7 +260,9 @@ def set_up_analyst_constraints(data_characteristic, variable_decisions_alt = Non
 
     # Create the DataFrame
     df = pd.DataFrame(rows)
-    return  df
+
+    data_new = data_characteristic.rename(columns={v: k for k, v in model_terms.items() if v in data_characteristic.columns})
+    return  df, data_new
 
 # Function to guess Low, Medium, High ranges
 def guess_low_medium_high(column_name, series):

{metacountregressor-0.1.136 → metacountregressor-0.1.138}/metacountregressor/metaheuristics.py

@@ -787,7 +787,7 @@ class SimulatedAnnealing(object):
         self.accept = 0
         self.profiler = []
         self.update_t = self.cooling_linear_m
-        self.get_direcotory()
+        self.get_directory()
         self._crossover_perc = float(kwargs.get('_crossover_perc', 0.2)) or float(kwargs.get('_cr', 0.2))
         self._obj_fun = objective_function
         if objective_function.is_multi:  # TODO Define more specific objectives in the intialiser
@@ -801,7 +801,7 @@ class SimulatedAnnealing(object):
             self.pf = Pareto(self.obj_1, self.obj_2, False)
             self._sa_memory = list()
 
-    def get_direcotory(self):
+    def get_directory(self):
         # checking if the directory demo_folder2 
         # exist or not.
         if not os.path.isdir(self.instance_number):
@@ -1237,6 +1237,16 @@ class HarmonySearch(object):
             Initialize HS with the specified objective function. Note that this objective function must implement ObjectiveFunctionInterface.
         """
         self._obj_fun = objective_function
+        ## NEW CODE, TRYING TO EXCTACT OUT THE PARAMATERS
+        self._hms = kwargs.get('_hms', 20)
+        self._par = kwargs.get(_'par', .30)
+        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))
+
+
+
         # for printing basics metrics
         self.print_verbose = True
         # harmony_memory stores the best hms harmonies
@@ -1245,7 +1255,7 @@ class HarmonySearch(object):
         self._harmony_history = list()
         # saves the best fitness
         self.instance_number = str(objective_function.instance_number)
-        self.get_direcotory()
+        self.get_directory()
         self._harmony_trace_best = list()
         self._harmony_trace_incumbent = list()
         if self._obj_fun.is_multi:  # TODO Define more specific objectives in the intialiser
@@ -1261,7 +1271,7 @@ class HarmonySearch(object):
 
             self.pf = Pareto(self.obj_1, self.obj_2, False)
 
-    def get_direcotory(self):
+    def get_directory(self):
         # checking if the directory demo_folder2 
         # exist or not.
         if not os.path.isdir(self.instance_number):

{metacountregressor-0.1.136 → metacountregressor-0.1.138}/metacountregressor/solution.py

@@ -153,14 +153,14 @@ class ObjectiveFunction(object):
 
         self.MAE = None
         self.best_obj_1 = 1000000.0
-        self._obj_1 = 'bic'
-        self._obj_2 = 'MSE'
+        self._obj_1 = kwargs.get('_obj_1', 'bic') 
+        self._obj_2 = kwargs.get('_obj_2', 'MSE') 
         self.numerical_hessian_calc = 0  # calculates hessian by statsmodels otherwise scipy
         self.full_model = None
         self.GP_parameter = 0
-        self.is_multi = 0
+        self.is_multi = kwargs.get('is_multi', False)
         self.complexity_level = 6
-        self._max_iterations_improvement = 100
+        self._max_iterations_improvement = 10000
         self.generated_sln = set()
         self.ave_mae = 0
         # defalt paramaters for hs #TODO unpack into harmony search class
@@ -168,7 +168,7 @@ class ObjectiveFunction(object):
         self._hms = 20
         self._max_time = 60 * 60 * 24
         self._hmcr = .5
-        self._par = 0.3
+        self._par = 0.3 #dont think this gets useted
         self._mpai = 1
         self._max_imp = 100000
         self._WIC = 1000  # Number of Iterations without Multiobjective Improvement #tod chuck into solution
@@ -395,7 +395,7 @@ class ObjectiveFunction(object):
 
 
 
-        self.Ndraws = 200  # todo: change back
+        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

{metacountregressor-0.1.136 → metacountregressor-0.1.138}/metacountregressor.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: metacountregressor
-Version: 0.1.136
+Version: 0.1.138
 Summary: Extensions for a Python package for estimation of count models.
 Home-page: https://github.com/zahern/CountDataEstimation
 Author: Zeke Ahern