pyerualjetwork 4.2.3b0__py3-none-any.whl → 4.2.4__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.2.3b0"
+__version__ = "4.2.4"
 __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/planeat.py

@@ -81,10 +81,9 @@ def evolver(weights,
             bar_status=True, 
             strategy='normal_selective', 
             target_fitness='max', 
-            mutations=True, 
             bad_genomes_mutation_prob=None, 
             activation_mutate_prob=0.5, 
-            save_best_genom=True, 
+            save_best_genome=True, 
             fitness_bias=None, 
             cross_over_mode='tpm', 
             activation_mutate_add_prob=0.5, 
@@ -143,9 +142,6 @@ def evolver(weights,
       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`.
-
-      mutations (bool, optional): If True, mutations are applied to the bad genomes and potentially 
-         to the best genomes as well. Default is True.
       
       bad_genomes_mutation_prob (float, optional): The probability of applying mutation to the bad genomes. 
          Must be in the range [0, 1]. Also affects the mutation probability of the best genomes inversely. 
@@ -305,6 +301,12 @@ def evolver(weights,
    best_fitness = normalized_fitness[-1]
    epsilon = np.finfo(float).eps
 
+   child_W = np.copy(bad_weights)
+   child_act = bad_activations.copy()
+
+   mutated_W = np.copy(bad_weights)
+   mutated_act = bad_activations.copy()
+
    for i in range(len(bad_weights)):
       
       if policy == 'aggressive':
@@ -319,7 +321,7 @@ def evolver(weights,
          
       second_parent_W, second_parent_act, s_i = second_parent_selection(good_weights, bad_weights, good_activations, bad_activations, bad_genomes_selection_prob)
 
-      bad_weights[i], bad_activations[i] = cross_over(first_parent_W,
+      child_W[i], child_act[i] = cross_over(first_parent_W,
                                              second_parent_W,
                                              first_parent_act,
                                              second_parent_act,
@@ -333,41 +335,40 @@ def evolver(weights,
                                              second_parent_fitness=normalized_fitness[s_i],
                                              epsilon=epsilon
                                              )
-  
-
-      if mutations is True:
-         mutation_prob = random.uniform(0, 1)
-
-         if mutation_prob > bad_genomes_mutation_prob:
-            if (save_best_genom == True and not np.array_equal(good_weights[i], best_weight)) or save_best_genom == False:
-
-               good_weights[i], good_activations[i] = mutation(good_weights[i], 
-                                                               good_activations[i],
-                                                               activation_mutate_prob=activation_mutate_prob,
-                                                               activation_add_prob=activation_mutate_add_prob, 
-                                                               activation_delete_prob=activation_mutate_delete_prob, 
-                                                               activation_change_prob=activation_mutate_change_prob, 
-                                                               weight_mutate_prob=weight_mutate_prob, 
-                                                               threshold=weight_mutate_rate,
-                                                               genome_fitness=normalized_fitness[i]
-                                                               )
-            
-         elif mutation_prob < bad_genomes_mutation_prob:
-            bad_weights[i], bad_activations[i] = mutation(bad_weights[i], 
-                                                            bad_activations[i],
-                                                            activation_mutate_prob=activation_mutate_prob, 
-                                                            activation_add_prob=activation_mutate_add_prob, 
-                                                            activation_delete_prob=activation_mutate_delete_prob, 
-                                                            activation_change_prob=activation_mutate_change_prob, 
-                                                            weight_mutate_prob=weight_mutate_prob, 
-                                                            threshold=weight_mutate_rate, 
-                                                            genome_fitness=normalized_fitness[i]
-                                                            )
+
+      mutation_prob = random.uniform(0, 1)
+
+      if mutation_prob > bad_genomes_mutation_prob:
+            genome_W = good_weights[i]
+            genome_act = good_activations[i]
+
+            fitness_index = int(len(bad_weights) / 2 + i)
+
+      else:
+            genome_W = bad_weights[i]
+            genome_act = bad_activations[i]
+
+            fitness_index = i
+
+      mutated_W[i], mutated_act[i] = mutation(genome_W, 
+                                             genome_act,
+                                             activation_mutate_prob=activation_mutate_prob,
+                                             activation_add_prob=activation_mutate_add_prob,
+                                             activation_delete_prob=activation_mutate_delete_prob, 
+                                             activation_change_prob=activation_mutate_change_prob, 
+                                             weight_mutate_prob=weight_mutate_prob, 
+                                             threshold=weight_mutate_rate,
+                                             genome_fitness=normalized_fitness[fitness_index]
+                                             )
 
       if bar_status: progress.update(1)
 
-   weights = np.vstack((bad_weights, good_weights))
-   activation_potentiations = bad_activations + good_activations
+   if save_best_genome:
+      child_W[-1] = best_weight
+      child_act[-1] = best_activations
+
+   weights = np.vstack((child_W, mutated_W))
+   activation_potentiations = child_act + mutated_act
 
    ### INFO PRINTING CONSOLE
    
@@ -378,7 +379,6 @@ def evolver(weights,
       print("  STRATEGY: ", strategy)
       print("  CROSS OVER MODE: ", cross_over_mode)
       print("  POLICY: ", policy)
-      print("  MUTATIONS: ", str(mutations))
       print("  BAD GENOMES MUTATION PROB: ", str(bad_genomes_mutation_prob))
       print("  GOOD GENOMES MUTATION PROB: ", str(round(1 - bad_genomes_mutation_prob, 2)))
       print("  BAD GENOMES SELECTION PROB: ", str(bad_genomes_selection_prob))
@@ -737,7 +737,7 @@ def mutation(weight,
 
          weight[selected_row, selected_col] = random.uniform(-1, 1)
 
-         if int(row_end * col_end) > new_threshold:
+         if row_end * col_end > new_threshold:
             new_threshold += threshold
             performance_control += 1
             pass
@@ -745,7 +745,7 @@ def mutation(weight,
          else:
             break
 
-         if performance_control >= int(row_end * col_end):
+         if performance_control == row_end * col_end:
             break
    
    activation_mutate_prob = 1 - activation_mutate_prob

pyerualjetwork/planeat_cuda.py

@@ -83,10 +83,9 @@ def evolver(weights,
             bar_status=True, 
             strategy='normal_selective', 
             target_fitness='max', 
-            mutations=True, 
             bad_genomes_mutation_prob=None, 
             activation_mutate_prob=0.5, 
-            save_best_genom=True, 
+            save_best_genome=True, 
             fitness_bias=None, 
             cross_over_mode='tpm',
             activation_mutate_add_prob=0.5, 
@@ -145,9 +144,6 @@ def evolver(weights,
       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`.
-
-      mutations (bool, optional): If True, mutations are applied to the bad genomes and potentially 
-         to the best genomes as well. Default is True.
       
       bad_genomes_mutation_prob (float, optional): The probability of applying mutation to the bad genomes. 
          Must be in the range [0, 1]. Also affects the mutation probability of the best genomes inversely. 
@@ -156,7 +152,7 @@ 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 
+      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:
@@ -305,6 +301,13 @@ def evolver(weights,
    best_fitness = normalized_fitness[-1]
    epsilon = cp.finfo(float).eps
 
+   child_W = cp.copy(bad_weights)
+   child_act = bad_activations.copy()
+
+   mutated_W = cp.copy(bad_weights)
+   mutated_act = bad_activations.copy()
+
+
    for i in range(len(bad_weights)):
       
       if policy == 'aggressive':
@@ -319,7 +322,7 @@ def evolver(weights,
          
       second_parent_W, second_parent_act, s_i = second_parent_selection(good_weights, bad_weights, good_activations, bad_activations, bad_genomes_selection_prob)
 
-      bad_weights[i], bad_activations[i] = cross_over(first_parent_W,
+      child_W[i], child_act[i] = cross_over(first_parent_W,
                                              second_parent_W,
                                              first_parent_act,
                                              second_parent_act,
@@ -334,40 +337,39 @@ def evolver(weights,
                                              epsilon=epsilon
                                              )
   
+      mutation_prob = random.uniform(0, 1)
 
-      if mutations is True:
-         mutation_prob = random.uniform(0, 1)
-
-         if mutation_prob > bad_genomes_mutation_prob:
-            if (save_best_genom == True and not np.array_equal(good_weights[i], best_weight)) or save_best_genom == False:
-
-               good_weights[i], good_activations[i] = mutation(good_weights[i], 
-                                                               good_activations[i],
-                                                               activation_mutate_prob=activation_mutate_prob,
-                                                               activation_add_prob=activation_mutate_add_prob, 
-                                                               activation_delete_prob=activation_mutate_delete_prob, 
-                                                               activation_change_prob=activation_mutate_change_prob, 
-                                                               weight_mutate_prob=weight_mutate_prob, 
-                                                               threshold=weight_mutate_rate,
-                                                               genome_fitness=normalized_fitness[i]
-                                                               )
-            
-         elif mutation_prob < bad_genomes_mutation_prob:
-            bad_weights[i], bad_activations[i] = mutation(bad_weights[i], 
-                                                            bad_activations[i],
-                                                            activation_mutate_prob=activation_mutate_prob, 
-                                                            activation_add_prob=activation_mutate_add_prob, 
-                                                            activation_delete_prob=activation_mutate_delete_prob, 
-                                                            activation_change_prob=activation_mutate_change_prob, 
-                                                            weight_mutate_prob=weight_mutate_prob, 
-                                                            threshold=weight_mutate_rate, 
-                                                            genome_fitness=normalized_fitness[i]
-                                                            )
+      if mutation_prob > bad_genomes_mutation_prob:
+            genome_W = good_weights[i]
+            genome_act = good_activations[i]
+
+            fitness_index = int(len(bad_weights) / 2 + i)
+
+      else:
+            genome_W = bad_weights[i]
+            genome_act = bad_activations[i]
+
+            fitness_index = i
+
+      mutated_W[i], mutated_act[i] = mutation(genome_W, 
+                                             genome_act,
+                                             activation_mutate_prob=activation_mutate_prob,
+                                             activation_add_prob=activation_mutate_add_prob,
+                                             activation_delete_prob=activation_mutate_delete_prob, 
+                                             activation_change_prob=activation_mutate_change_prob, 
+                                             weight_mutate_prob=weight_mutate_prob, 
+                                             threshold=weight_mutate_rate,
+                                             genome_fitness=normalized_fitness[fitness_index]
+                                             )
             
       if bar_status: progress.update(1)
 
-   weights = cp.vstack((bad_weights, good_weights))
-   activation_potentiations = bad_activations + good_activations
+   if save_best_genome:
+      child_W[-1] = best_weight
+      child_act[-1] = best_activations
+
+   weights = cp.vstack((child_W, mutated_W))
+   activation_potentiations = child_act + mutated_act
 
    ### INFO PRINTING CONSOLE
    
@@ -378,7 +380,6 @@ def evolver(weights,
       print("  STRATEGY: ", strategy)
       print("  CROSS OVER MODE: ", cross_over_mode)
       print("  POLICY: ", policy)
-      print("  MUTATIONS: ", str(mutations))
       print("  BAD GENOMES MUTATION PROB: ", str(bad_genomes_mutation_prob))
       print("  GOOD GENOMES MUTATION PROB: ", str(round(1 - bad_genomes_mutation_prob, 2)))
       print("  WEIGHT MUTATE PROB: ", str(weight_mutate_prob))
@@ -741,7 +742,7 @@ def mutation(weight,
 
          weight[selected_row, selected_col] = random.uniform(-1, 1)
 
-         if int(row_end * col_end) > new_threshold:
+         if row_end * col_end > new_threshold:
             new_threshold += threshold
             performance_control += 1
             pass
@@ -749,7 +750,7 @@ def mutation(weight,
          else:
             break
 
-         if performance_control >= int(row_end * col_end):
+         if performance_control >= row_end * col_end:
             break
    
    activation_mutate_prob = 1 - activation_mutate_prob

pyerualjetwork/visualizations.py

@@ -753,12 +753,12 @@ def update_history_plots_for_learner(viz_objects, depth_list, loss_list, best_ac
     
     # Loss plot
     art1 = hist['ax'][0].plot(depth_list, loss_list, color='r', markersize=6, linewidth=2)
-    hist['ax'][0].set_title('Train Loss Over Depth')
+    hist['ax'][0].set_title('Train Loss Over Gen')
     hist['artist1'].append(art1)
     
     # Accuracy plot
     art2 = hist['ax'][1].plot(depth_list, best_acc_per_depth_list, color='g', markersize=6, linewidth=2)
-    hist['ax'][1].set_title('Train Accuracy Over Depth')
+    hist['ax'][1].set_title('Train Accuracy Over Gen')
     hist['artist2'].append(art2)
     
     # Activation shape plot
@@ -768,7 +768,7 @@ def update_history_plots_for_learner(viz_objects, depth_list, loss_list, best_ac
         translated_x_train += draw_activations(x, activation)
     
     art3 = hist['ax'][2].plot(x, translated_x_train, color='b', markersize=6, linewidth=2)
-    hist['ax'][2].set_title('Potentiation Shape Over Depth')
+    hist['ax'][2].set_title('Potentiation Shape Over Gen')
     hist['artist3'].append(art3)
 
 def display_visualizations_for_learner(viz_objects, best_weights, data, best_acc, test_loss, y_train, interval):

pyerualjetwork/visualizations_cuda.py

@@ -751,7 +751,7 @@ def update_history_plots_for_learner(viz_objects, depth_list, loss_list, best_ac
 
     # Loss plot
     art1 = hist['ax'][0].plot(depth_list, loss_list, color='r', markersize=6, linewidth=2)
-    hist['ax'][0].set_title('Train Loss Over Depth')
+    hist['ax'][0].set_title('Train Loss Over Gen')
     hist['artist1'].append(art1)
     
     # Accuracy plot
@@ -760,7 +760,7 @@ def update_history_plots_for_learner(viz_objects, depth_list, loss_list, best_ac
         best_acc_per_depth_list[i] = best_acc_per_depth_list[i].get()
 
     art2 = hist['ax'][1].plot(depth_list, best_acc_per_depth_list, color='g', markersize=6, linewidth=2)
-    hist['ax'][1].set_title('Train Accuracy Over Depth')
+    hist['ax'][1].set_title('Train Accuracy Over Gen')
     hist['artist2'].append(art2)
     
     # Activation shape plot
@@ -770,7 +770,7 @@ def update_history_plots_for_learner(viz_objects, depth_list, loss_list, best_ac
         translated_x_train += draw_activations(x, activation)
     
     art3 = hist['ax'][2].plot(x.get(), translated_x_train.get(), color='b', markersize=6, linewidth=2)
-    hist['ax'][2].set_title('Potentiation Shape Over Depth')
+    hist['ax'][2].set_title('Potentiation Shape Over Gen')
     hist['artist3'].append(art3)
 
 def display_visualizations_for_learner(viz_objects, best_weights, data, best_acc, test_loss, y_train, interval):

{pyerualjetwork-4.2.3b0.dist-info → pyerualjetwork-4.2.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.2.3b0
+Version: 4.2.4
 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

{pyerualjetwork-4.2.3b0.dist-info → pyerualjetwork-4.2.4.dist-info}/RECORD

@@ -1,4 +1,4 @@
-pyerualjetwork/__init__.py,sha256=pxhZHhRn7whU0FXI1Z6M_X2V4wLu4kG1I4ttJ__1HHo,641
+pyerualjetwork/__init__.py,sha256=OzpuhZgLGS0elbMyM1OUEWph9js8D_LtnlhDbKTb1YQ,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
@@ -13,12 +13,12 @@ pyerualjetwork/model_operations.py,sha256=RKqnh7-MByFosxqme4q4jC1lOndX26O-OVXYV6
 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=hMSyrSPipOxKgOqyoAiZtniVgxPQxc4rRsvEEMOS2Ng,40757
-pyerualjetwork/planeat_cuda.py,sha256=9uopmM-gTZpSb0EOExrOZPT8FF5BqDdEfCX0zYQb9QU,40712
+pyerualjetwork/planeat.py,sha256=4XcmQhMHXA6hUWsDZXC2T3I18BeSP4V-GmPYToGR0kg,39638
+pyerualjetwork/planeat_cuda.py,sha256=xaDqH0kWwkmjx-YrBIuLoE1G26qk6rjuOvkH8oRWqyI,39598
 pyerualjetwork/ui.py,sha256=wu2BhU1k-w3Kcho5Jtq4SEKe68ftaUeRGneUOSCVDjU,575
-pyerualjetwork/visualizations.py,sha256=6b_mbnKXfsf5hODeJwOI1QHuX9Yvy4Ain5QRN4bnZK0,28778
-pyerualjetwork/visualizations_cuda.py,sha256=19xkp3swKe4CBh2qIXSrdEn3DicC6FgOb5c0Uy0UyRg,29192
-pyerualjetwork-4.2.3b0.dist-info/METADATA,sha256=1Ljje9X_2j7SiRlRvvo8MVHFYZHWU15dJNGJvDToSyE,7914
-pyerualjetwork-4.2.3b0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-4.2.3b0.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-4.2.3b0.dist-info/RECORD,,
+pyerualjetwork/visualizations.py,sha256=1SKMZaJ80OD2qHUyMxW1IOv8zwmxzMPxclfbeq1Xr4g,28772
+pyerualjetwork/visualizations_cuda.py,sha256=KbMhfsLlxujy_i3QrwCf734Q-k6d7Zn_7CEbm3gzK9w,29186
+pyerualjetwork-4.2.4.dist-info/METADATA,sha256=szwh-uHCigwGGd0VCHcyVWixXmpfOncfs6VrMm6y1Vg,7912
+pyerualjetwork-4.2.4.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-4.2.4.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-4.2.4.dist-info/RECORD,,