pyerualjetwork 4.2.4b2__py3-none-any.whl → 4.2.6__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.2.4b2"
+__version__ = "4.2.6"
 __update__ = "* Changes: https://github.com/HCB06/PyerualJetwork/blob/main/CHANGES\n* PyerualJetwork Homepage: https://github.com/HCB06/PyerualJetwork/tree/main\n* PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf\n* YouTube tutorials: https://www.youtube.com/@HasanCanBeydili"
 
 def print_version(__version__):

pyerualjetwork/plan.py

@@ -196,7 +196,6 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
         ```python
         genetic_optimizer = lambda *args, **kwargs: planeat.evolver(*args,
                                                                     activation_add_prob=0.85,
-                                                                    mutations=True,
                                                                     strategy='aggressive',
                                                                     **kwargs)
 

pyerualjetwork/plan_cuda.py

@@ -211,7 +211,6 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
         ```python
         genetic_optimizer = lambda *args, **kwargs: planeat_cuda.evolver(*args,
                                                                     activation_add_prob=0.85,
-                                                                    mutations=True,
                                                                     strategy='aggressive',
                                                                     **kwargs)
 

pyerualjetwork/planeat.py

@@ -15,6 +15,7 @@ ANAPLAN document: https://github.com/HCB06/Anaplan/blob/main/Welcome_to_Anaplan/
 import numpy as np
 import random
 import math
+import copy
 
 ### LIBRARY IMPORTS ###
 from .plan import feed_forward
@@ -79,11 +80,9 @@ def evolver(weights,
             policy='aggressive', 
             bad_genomes_selection_prob=None, 
             bar_status=True, 
-            strategy='normal_selective', 
-            target_fitness='max', 
+            strategy='normal_selective',
             bad_genomes_mutation_prob=None, 
-            activation_mutate_prob=0.5, 
-            save_best_genome=True, 
+            activation_mutate_prob=0.5,  
             fitness_bias=None, 
             cross_over_mode='tpm', 
             activation_mutate_add_prob=0.5, 
@@ -139,8 +138,6 @@ def evolver(weights,
 
             Default: 'aggressive'.
       
-      target_fitness (str, optional): Target fitness strategy for PLANEAT optimization. ('max' maximizes fitness, 'min' minimizes fitness.) Default: 'max'.
-      
       fitness_bias (float, optional): Fitness bias must be a probability value between 0 and 1 that determines the effect of fitness on the crossover process. Default: Determined by the `strategy`.
       
       bad_genomes_mutation_prob (float, optional): The probability of applying mutation to the bad genomes. 
@@ -150,9 +147,6 @@ def evolver(weights,
       activation_mutate_prob (float, optional): The probability of applying mutation to the activation functions. 
          Must be in the range [0, 1]. Default is 0.5 (50%).
       
-      save_best_genom (bool, optional): If True, ensures that the best genomes are saved and not mutated 
-         or altered during reproduction. Default is True.
-      
       cross_over_mode (str, optional): Specifies the crossover method to use. Options:
          - 'tpm': Two-Point Matrix Crossover.
          Default is 'tpm'.
@@ -270,10 +264,9 @@ def evolver(weights,
       raise ValueError("genome population size must be even number. for example: not 99, make 100 or 98.")
 
    
-### FITNESS IS SORTED IN ASCENDING (OR DESCENDING) ORDER, AND THE WEIGHT AND ACTIVATIONS OF EACH GENOME ARE SORTED ACCORDING TO THIS ORDER:
+### FITNESS IS SORTED IN ASCENDING ORDER, AND THE WEIGHT AND ACTIVATIONS OF EACH GENOME ARE SORTED ACCORDING TO THIS ORDER:
 
-   if target_fitness == 'max': sort_indices = np.argsort(fitness)
-   elif target_fitness == 'min': sort_indices = np.argsort(-fitness)
+   sort_indices = np.argsort(fitness)
 
    fitness = fitness[sort_indices]
    weights = weights[sort_indices]
@@ -284,11 +277,11 @@ def evolver(weights,
 
    good_weights = weights[slice_center:]
    bad_weights = weights[:slice_center]
-   best_weight = good_weights[-1]
+   best_weight = np.copy(good_weights[-1])
 
    good_activations = list(activation_potentiations[slice_center:])
    bad_activations = list(activation_potentiations[:slice_center])
-   best_activations = good_activations[-1]
+   best_activations =  copy.deepcopy(good_activations[-1])
 
    
 ### PLANEAT IS APPLIED ACCORDING TO THE SPECIFIED POLICY, STRATEGY, AND PROBABILITY CONFIGURATION:
@@ -296,16 +289,16 @@ def evolver(weights,
    bar_format = loading_bars()[0]
    
    if bar_status: progress = initialize_loading_bar(len(bad_weights), desc="GENERATION: " + str(what_gen), bar_format=bar_format, ncols=50)
-   normalized_fitness = abs(normalization(fitness, dtype=dtype))
+   normalized_fitness = normalization(fitness, dtype=dtype)
 
    best_fitness = normalized_fitness[-1]
    epsilon = np.finfo(float).eps
 
    child_W = np.copy(bad_weights)
-   child_act = bad_activations.copy()
+   child_act = copy.deepcopy(bad_activations)
 
    mutated_W = np.copy(bad_weights)
-   mutated_act = bad_activations.copy()
+   mutated_act = copy.deepcopy(bad_activations)
 
    for i in range(len(bad_weights)):
       
@@ -363,9 +356,8 @@ def evolver(weights,
 
       if bar_status: progress.update(1)
 
-   if save_best_genome:
-      child_W[-1] = best_weight
-      child_act[-1] = best_activations
+   child_W[0] = best_weight
+   child_act[0] = best_activations
 
    weights = np.vstack((child_W, mutated_W))
    activation_potentiations = child_act + mutated_act
@@ -399,9 +391,9 @@ def evolver(weights,
       print("  MEAN FITNESS: ", str(round(np.mean(fitness), 2)))
       print("  MIN FITNESS: ", str(round(min(fitness), 2)) + '\n')
 
-      print("  BEST GENOME ACTIVATION LENGTH: ", str(len(activation_potentiations[-1])))
-      print("  BEST GENOME INDEX: ", str(len(weights)-1))
-      print("  NOTE: Genomes are always sorted from the least successful to the most successful according to their performance ranking. Therefore, the genome at the last index is the king of the previous generation. " + '\n')
+      print("  BEST GENOME ACTIVATION LENGTH: ", str(len(best_activations)))
+      print("  BEST GENOME INDEX: ", str(0))
+      print("  NOTE: The returned genome at the first index is the best of the previous generation." + '\n')
       
 
    return weights, activation_potentiations
@@ -622,7 +614,7 @@ def cross_over(first_parent_W,
 
    if potential_activation_selection_add > activation_selection_add_prob:
       
-      threshold = threshold / succes
+      threshold = abs(threshold / succes)
       new_threshold = threshold
       
       while True:
@@ -644,7 +636,7 @@ def cross_over(first_parent_W,
 
    if potential_activation_selection_change_prob > activation_selection_change_prob:
       
-      threshold = threshold / succes
+      threshold = abs(threshold / succes)
       new_threshold = threshold
       
       while True:
@@ -726,27 +718,24 @@ def mutation(weight,
       row_end = weight.shape[0]
       col_end = weight.shape[1]
 
+      max_threshold = row_end * col_end
+
       threshold = threshold * genome_fitness
-      performance_control = 0
       new_threshold = threshold
       
-      while True:
+      for _ in range(max_threshold):
          
          selected_row = int(random.uniform(start, row_end))
          selected_col = int(random.uniform(start, col_end))
 
          weight[selected_row, selected_col] = random.uniform(-1, 1)
 
-         if row_end * col_end > new_threshold:
+         if max_threshold > new_threshold:
             new_threshold += threshold
-            performance_control += 1
-            pass
          
          else:
             break
 
-         if performance_control == row_end * col_end:
-            break
    
    activation_mutate_prob = 1 - activation_mutate_prob
    potential_activation_mutation = random.uniform(0, 1)

pyerualjetwork/planeat_cuda.py

@@ -16,6 +16,7 @@ import cupy as cp
 import numpy as np
 import random
 import math
+import copy
 
 
 ### LIBRARY IMPORTS ###
@@ -81,11 +82,9 @@ def evolver(weights,
             policy='aggressive', 
             bad_genomes_selection_prob=None, 
             bar_status=True, 
-            strategy='normal_selective', 
-            target_fitness='max', 
+            strategy='normal_selective',
             bad_genomes_mutation_prob=None, 
             activation_mutate_prob=0.5, 
-            save_best_genome=True, 
             fitness_bias=None, 
             cross_over_mode='tpm',
             activation_mutate_add_prob=0.5, 
@@ -141,8 +140,6 @@ def evolver(weights,
 
             Default: 'aggressive'.
       
-      target_fitness (str, optional): Target fitness strategy for PLANEAT optimization. ('max' maximizes fitness, 'min' minimizes fitness.) Default: 'max'.
-      
       fitness_bias (float, optional): Fitness bias must be a probability value between 0 and 1 that determines the effect of fitness on the crossover process. Default: Determined by the `strategy`.
       
       bad_genomes_mutation_prob (float, optional): The probability of applying mutation to the bad genomes. 
@@ -152,9 +149,6 @@ def evolver(weights,
       activation_mutate_prob (float, optional): The probability of applying mutation to the activation functions. 
          Must be in the range [0, 1]. Default is 0.5 (50%).
       
-      save_best_genome (bool, optional): If True, ensures that the best genomes are saved and not mutated 
-         or altered during reproduction. Default is True.
-      
       cross_over_mode (str, optional): Specifies the crossover method to use. Options:
          - 'tpm': Two-Point Matrix Crossover.
          Default is 'tpm'.
@@ -270,10 +264,9 @@ def evolver(weights,
    else:
       raise ValueError("genome population size must be even number. for example: not 99, make 100 or 98.")
 
-### FITNESS LIST IS SORTED IN ASCENDING (OR DESCENDING) ORDER, AND THE WEIGHT AND ACTIVATIONS OF EACH GENOME ARE SORTED ACCORDING TO THIS ORDER:
+### FITNESS LIST IS SORTED IN ASCENDING ORDER, AND THE WEIGHT AND ACTIVATIONS OF EACH GENOME ARE SORTED ACCORDING TO THIS ORDER:
 
-   if target_fitness == 'max': sort_indices = cp.argsort(fitness)
-   elif target_fitness == 'min': sort_indices = cp.argsort(-fitness)
+   sort_indices = cp.argsort(fitness)
 
    fitness = fitness[sort_indices]
    weights = weights[sort_indices]
@@ -284,11 +277,11 @@ def evolver(weights,
 
    good_weights = weights[slice_center:]
    bad_weights = weights[:slice_center]
-   best_weight = good_weights[-1]
+   best_weight = cp.copy(good_weights[-1])
 
    good_activations = list(activation_potentiations[slice_center:])
    bad_activations = list(activation_potentiations[:slice_center])
-   best_activations = good_activations[-1]
+   best_activations =  copy.deepcopy(good_activations[-1])
 
    
 ### PLANEAT IS APPLIED ACCORDING TO THE SPECIFIED POLICY, STRATEGY, AND PROBABILITY CONFIGURATION:
@@ -296,16 +289,16 @@ def evolver(weights,
    bar_format = loading_bars()[0]
    
    if bar_status: progress = initialize_loading_bar(len(bad_weights), desc="GENERATION: " + str(what_gen), bar_format=bar_format, ncols=50)
-   normalized_fitness = abs(normalization(fitness, dtype=dtype))
+   normalized_fitness = normalization(fitness, dtype=dtype)
 
    best_fitness = normalized_fitness[-1]
    epsilon = cp.finfo(float).eps
 
    child_W = cp.copy(bad_weights)
-   child_act = bad_activations.copy()
+   child_act = copy.deepcopy(bad_activations)
 
    mutated_W = cp.copy(bad_weights)
-   mutated_act = bad_activations.copy()
+   mutated_act = copy.deepcopy(bad_activations)
 
 
    for i in range(len(bad_weights)):
@@ -364,9 +357,8 @@ def evolver(weights,
             
       if bar_status: progress.update(1)
 
-   if save_best_genome:
-      child_W[-1] = best_weight
-      child_act[-1] = best_activations
+   child_W[0] = best_weight
+   child_act[0] = best_activations
 
    weights = cp.vstack((child_W, mutated_W))
    activation_potentiations = child_act + mutated_act
@@ -394,13 +386,13 @@ def evolver(weights,
       print("  ACTIVATION SELECTION RATE (THRESHOLD VALUE FOR SINGLE CROSS OVER):", str(activation_selection_rate) + '\n')
       
       print("*** Performance ***")
-      print("  MAX REWARD: ", str(cp.round(max(fitness), 2)))
-      print("  MEAN REWARD: ", str(cp.round(cp.mean(fitness), 2)))
-      print("  MIN REWARD: ", str(cp.round(min(fitness), 2)) + '\n')
+      print("  MAX FITNESS: ", str(cp.round(max(fitness), 2)))
+      print("  MEAN FITNESS: ", str(cp.round(cp.mean(fitness), 2)))
+      print("  MIN FITNESS: ", str(cp.round(min(fitness), 2)) + '\n')
 
-      print("  BEST GENOME ACTIVATION LENGTH: ", str(len(activation_potentiations)))
-      print("  BEST GENOME INDEX: ", str(len(weights)-1))
-      print("  NOTE: Genomes are always sorted from the least successful to the most successful according to their performance ranking. Therefore, the genome at the last index is the king of the previous generation. " + '\n')
+      print("  BEST GENOME ACTIVATION LENGTH: ", str(len(best_activations)))
+      print("  BEST GENOME INDEX: ", str(0))
+      print("  NOTE: The returned genome at the first index is the best of the previous generation." + '\n')
       
 
    return weights, activation_potentiations
@@ -626,7 +618,7 @@ def cross_over(first_parent_W,
 
    if potential_activation_selection_add > activation_selection_add_prob:
       
-      threshold = threshold / succes
+      threshold = abs(threshold / succes)
       new_threshold = threshold
       
       while True:
@@ -648,7 +640,7 @@ def cross_over(first_parent_W,
 
    if potential_activation_selection_change_prob > activation_selection_change_prob:
       
-      threshold = threshold / succes
+      threshold = abs(threshold / succes)
       new_threshold = threshold
       
       while True:
@@ -731,27 +723,23 @@ def mutation(weight,
       row_end = weight.shape[0]
       col_end = weight.shape[1]
       
+      max_threshold = row_end * col_end
+
       threshold = threshold * genome_fitness
       new_threshold = threshold
-      performance_control = 0
 
-      while True:
+      for _ in range(max_threshold):
          
          selected_row = int(random.uniform(start, row_end))
          selected_col = int(random.uniform(start, col_end))
 
          weight[selected_row, selected_col] = random.uniform(-1, 1)
 
-         if row_end * col_end > new_threshold:
+         if max_threshold > new_threshold:
             new_threshold += threshold
-            performance_control += 1
-            pass
          
          else:
             break
-
-         if performance_control >= row_end * col_end:
-            break
    
    activation_mutate_prob = 1 - activation_mutate_prob
    potential_activation_mutation = random.uniform(0, 1)

{pyerualjetwork-4.2.4b2.dist-info → pyerualjetwork-4.2.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.2.4b2
+Version: 4.2.6
 Summary: PyerualJetwork is a machine learning library supported with GPU(CUDA) acceleration written in Python for professionals and researchers including with PLAN algorithm, PLANEAT algorithm (genetic optimization). Also includes data pre-process and memory manegament
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com
@@ -38,7 +38,6 @@ GitHub Page: https://github.com/HCB06/PyerualJetwork
       Optimized for Visual Studio Code
       
       requires=[
-        'setuptools==75.6.0',
  	    'scipy==1.13.1',
 	    'tqdm==4.66.4',
 	    'seaborn==0.13.2',
@@ -52,8 +51,6 @@ GitHub Page: https://github.com/HCB06/PyerualJetwork
         ]
 
      matplotlib, seaborn, networkx (optional).
-     PyerualJetwork checks and install all dependencies with optional ones for every runing.
-     If your version is higher or lower, PyerualJetwork automaticly delete other versions and installs this versions.
           
 ##############################
 
@@ -61,7 +58,7 @@ ABOUT PYERUALJETWORK:
 
 PyerualJetwork is a machine learning library written in Python for professionals, incorporating advanced, unique, new, and modern techniques with optimized GPU acceleration. Its most important component is the PLAN (Potentiation Learning Artificial Neural Network) https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4862342. (THIS ARTICLE IS FIRST VERSION OF PLAN.) MODERN VERSION OF PLAN: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PLAN/PLAN.pdf
 Both the PLAN algorithm and the PyerualJetwork library were created by Author, and all rights are reserved by Author.
-PyerualJetwork is free to use for commercial business and individual users. PyerualJetwork is written in fully functional programming with non-oop elements. PyerualJetwork consists of many functions that complement each other, which facilitates the learning process and debugging during use.
+PyerualJetwork is free to use for commercial business and individual users.
 As of 12/21/2024, the library includes PLAN and PLANEAT module, but other machine learning modules are expected to be added in the future.
 
 PyerualJetwork ready for both eager execution(like PyTorch) and static graph(like Tensorflow) concepts because PyerualJetwork using only functions.

{pyerualjetwork-4.2.4b2.dist-info → pyerualjetwork-4.2.6.dist-info}/RECORD

@@ -1,4 +1,4 @@
-pyerualjetwork/__init__.py,sha256=WIsIQyJj1qNVLNGxNoKEKgttR8P1wrkdwmcIBcN5uIQ,641
+pyerualjetwork/__init__.py,sha256=P6B7ccTwijjEmfwBjrO7UilDfgAI_hTL-PjplThSqoE,639
 pyerualjetwork/activation_functions.py,sha256=WWOdMd5pI6ZKe-ieKCIsKAYPQODHuXYxx7tzhA5xjes,11767
 pyerualjetwork/activation_functions_cuda.py,sha256=KmXJ5Cdig46XAMYakXFPEOlxSxtFJjD21-i3nGtxPjE,11807
 pyerualjetwork/data_operations.py,sha256=pb5CqJ0Th6fCjTNMCtqQMiwH3KezTxAijacglsKUxmY,14730
@@ -11,14 +11,14 @@ pyerualjetwork/metrics.py,sha256=q7MkhnZDRbCjFBDDfUgrl8lBYnUT_1ro1LxeBq105pI,607
 pyerualjetwork/metrics_cuda.py,sha256=73h9GC7XwmnFCVzFEEiPQfF8CwHIz2wsCbxpZrJtYgw,5061
 pyerualjetwork/model_operations.py,sha256=RKqnh7-MByFosxqme4q4jC1lOndX26O-OVXYV6ZxoEE,12965
 pyerualjetwork/model_operations_cuda.py,sha256=XnKKq54ZLaqCm-NaJ6d8IToACKcKg2Ttq6moowVRRWo,13365
-pyerualjetwork/plan.py,sha256=YOBF2CqGu400Zk6xuraP0X8WzMNyejpZc5tdVV4dEvE,32219
-pyerualjetwork/plan_cuda.py,sha256=OKK0pmJYLQd5-dJ1aLiyWiZRBmoUp1zBkFxRcxnWBVI,33610
-pyerualjetwork/planeat.py,sha256=4XcmQhMHXA6hUWsDZXC2T3I18BeSP4V-GmPYToGR0kg,39638
-pyerualjetwork/planeat_cuda.py,sha256=xaDqH0kWwkmjx-YrBIuLoE1G26qk6rjuOvkH8oRWqyI,39598
+pyerualjetwork/plan.py,sha256=UzCTFCA9cTv9ITCtsqfJ1g02rCMyescoIV6j1amvYGw,32134
+pyerualjetwork/plan_cuda.py,sha256=hpXZl3h7B1qAVYW-gZebwKMZd4-ftAZ-u05teOJjsno,33525
+pyerualjetwork/planeat.py,sha256=cDr0QfOD4FFibcpgsnyQiSpRUwkfYHkBJGqxBnyzx9Q,38893
+pyerualjetwork/planeat_cuda.py,sha256=NiQfIAqlWC4iVmxKYnrQtKPz-7vAY1yoasOM3rRDvi0,38856
 pyerualjetwork/ui.py,sha256=wu2BhU1k-w3Kcho5Jtq4SEKe68ftaUeRGneUOSCVDjU,575
 pyerualjetwork/visualizations.py,sha256=1SKMZaJ80OD2qHUyMxW1IOv8zwmxzMPxclfbeq1Xr4g,28772
 pyerualjetwork/visualizations_cuda.py,sha256=KbMhfsLlxujy_i3QrwCf734Q-k6d7Zn_7CEbm3gzK9w,29186
-pyerualjetwork-4.2.4b2.dist-info/METADATA,sha256=cNXb8qCCtyy4izZNQsvfaBUfn1lQNR9SrBiyRjunxYs,7914
-pyerualjetwork-4.2.4b2.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-4.2.4b2.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-4.2.4b2.dist-info/RECORD,,
+pyerualjetwork-4.2.6.dist-info/METADATA,sha256=HISmko-Ho-pe_mZPtA2mBBcXkZYiITyCfPTAp_AT_Ps,7452
+pyerualjetwork-4.2.6.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-4.2.6.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-4.2.6.dist-info/RECORD,,