pyerualjetwork 4.2.0b4__py3-none-any.whl → 4.2.0b6__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -48,7 +48,7 @@ for package_name in package_names:
 
 print(f"PyerualJetwork is ready to use with {err} errors")
 
-__version__ = "4.2.0b4"
+__version__ = "4.2.0b6"
 __update__ = "* Changes: https://github.com/HCB06/PyerualJetwork/blob/main/CHANGES\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

@@ -76,7 +76,7 @@ def evolver(weights,
             what_gen, 
             fitness, 
             show_info=False, 
-            policy='aggresive', 
+            policy='aggressive', 
             bad_genomes_selection_prob=None, 
             bar_status=True, 
             strategy='normal_selective', 
@@ -128,7 +128,7 @@ def evolver(weights,
 
       policy (str, optional): The selection policy that governs how genomes are selected for reproduction. Options:
             
-            - 'aggresive': Aggressive policy using very aggressive selection policy. 
+            - 'aggressive': Aggressive policy using very aggressive selection policy. 
                   Advantages: fast training. 
                   Disadvantages: may lead to fitness stuck in a local maximum or minimum.
 
@@ -138,7 +138,7 @@ def evolver(weights,
                   
                   Suggestions: Use hybrid and dynamic policy. When fitness appears stuck, switch to the 'explorer' policy.
 
-            Default: 'aggresive'.
+            Default: 'aggressive'.
       
       target_fitness (str, optional): Target fitness strategy for PLANEAT optimization. ('max' maximizes fitness, 'min' minimizes fitness.) Default: 'max'.
       
@@ -307,12 +307,9 @@ def evolver(weights,
    best_fitness = normalized_fitness[-1]
    epsilon = np.finfo(float).eps
 
-   child_W = np.empty(bad_weights[0].shape, dtype=dtype)
-   child_act = bad_activations.copy()
-
    for i in range(len(bad_weights)):
       
-      if policy == 'aggresive':
+      if policy == 'aggressive':
          first_parent_W = best_weight
          first_parent_act = best_activations
 
@@ -320,11 +317,11 @@ def evolver(weights,
          first_parent_W = good_weights[i]
          first_parent_act = good_activations[i]
 
-      else: raise ValueError("policy parameter must be: 'aggresive' or 'explorer'")
+      else: raise ValueError("policy parameter must be: 'aggressive' or 'explorer'")
          
       second_parent_W, second_parent_act, s_i = second_parent_selection(good_weights, bad_weights, good_activations, bad_activations, bad_genomes_selection_prob)
 
-      child_W[i], child_act[i] = cross_over(first_parent_W,
+      bad_weights[i], bad_activations[i] = cross_over(first_parent_W,
                                              second_parent_W,
                                              first_parent_act,
                                              second_parent_act,
@@ -373,8 +370,8 @@ def evolver(weights,
             
       if bar_status: progress.update(1)
 
-   weights = np.vstack((child_W, good_weights))
-   activation_potentiations = child_act + good_activations
+   weights = np.vstack((bad_weights, good_weights))
+   activation_potentiations = bad_activations + good_activations
 
    ### INFO PRINTING CONSOLE
    

pyerualjetwork/planeat_cuda.py

@@ -78,7 +78,7 @@ def evolver(weights,
             what_gen, 
             fitness, 
             show_info=False, 
-            policy='aggresive', 
+            policy='aggressive', 
             bad_genomes_selection_prob=None, 
             bar_status=True, 
             strategy='normal_selective', 
@@ -130,7 +130,7 @@ def evolver(weights,
 
       policy (str, optional): The selection policy that governs how genomes are selected for reproduction. Options:
             
-            - 'aggresive': Aggressive policy using very aggressive selection policy. 
+            - 'aggressive': Aggressive policy using very aggressive selection policy. 
                   Advantages: fast training. 
                   Disadvantages: may lead to fitness stuck in a local maximum or minimum.
 
@@ -140,7 +140,7 @@ def evolver(weights,
                   
                   Suggestions: Use hybrid and dynamic policy. When fitness appears stuck, switch to the 'explorer' policy.
 
-            Default: 'aggresive'.
+            Default: 'aggressive'.
       
       target_fitness (str, optional): Target fitness strategy for PLANEAT optimization. ('max' maximizes fitness, 'min' minimizes fitness.) Default: 'max'.
       
@@ -192,7 +192,7 @@ def evolver(weights,
 
    Raises:
       ValueError: 
-         - If `policy` is not one of the specified values ('aggresive', 'explorer').
+         - If `policy` is not one of the specified values ('aggressive', 'explorer').
          - If 'strategy' is not one of the specified values ('less_selective', 'normal_selective', 'more_selective')
          - If `cross_over_mode` is not one of the specified values ('tpm').
          - If `bad_genomes_mutation_prob`, `activation_mutate_prob`, or other probability parameters are not in the range 0 and 1.
@@ -224,7 +224,7 @@ def evolver(weights,
 
    Example:
       ```python
-      weights, activation_potentiations = planeat.evolver(weights, activation_potentiations, 1, fitness, show_info=True, strategy='normal_selective', policy='aggresive')
+      weights, activation_potentiations = planeat.evolver(weights, activation_potentiations, 1, fitness, show_info=True, strategy='normal_selective', policy='aggressive')
       ```
 
       - The function returns the updated weights and activations after processing based on the chosen strategy, policy, and mutation parameters.
@@ -306,13 +306,10 @@ def evolver(weights,
 
    best_fitness = normalized_fitness[-1]
    epsilon = cp.finfo(float).eps
-   
-   child_W = cp.empty(bad_weights[0].shape, dtype=dtype)
-   child_act = bad_activations.copy()
 
    for i in range(len(bad_weights)):
       
-      if policy == 'aggresive':
+      if policy == 'aggressive':
          first_parent_W = best_weight
          first_parent_act = best_activations
 
@@ -320,11 +317,11 @@ def evolver(weights,
          first_parent_W = good_weights[i]
          first_parent_act = good_activations[i]
 
-      else: raise ValueError("policy parameter must be: 'aggresive' or 'explorer'")
+      else: raise ValueError("policy parameter must be: 'aggressive' or 'explorer'")
          
       second_parent_W, second_parent_act, s_i = second_parent_selection(good_weights, bad_weights, good_activations, bad_activations, bad_genomes_selection_prob)
 
-      child_W[i], child_act[i] = cross_over(first_parent_W,
+      bad_weights[i], bad_activations[i] = cross_over(first_parent_W,
                                              second_parent_W,
                                              first_parent_act,
                                              second_parent_act,
@@ -373,8 +370,8 @@ def evolver(weights,
             
       if bar_status: progress.update(1)
 
-   weights = cp.vstack((child_W, good_weights))
-   activation_potentiations = child_act + good_activations
+   weights = cp.vstack((bad_weights, good_weights))
+   activation_potentiations = bad_activations + good_activations
 
    ### INFO PRINTING CONSOLE
    

{pyerualjetwork-4.2.0b4.dist-info → pyerualjetwork-4.2.0b6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.2.0b4
+Version: 4.2.0b6
 Summary: PyerualJetwork is a machine learning library written in Python for professionals, incorporating advanced, unique, new, and modern techniques.
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com

{pyerualjetwork-4.2.0b4.dist-info → pyerualjetwork-4.2.0b6.dist-info}/RECORD

@@ -1,4 +1,4 @@
-pyerualjetwork/__init__.py,sha256=VRFLz0qjl7ZNj1nm6TFjuEit1_lEp-qO6GuBhakW_wA,2177
+pyerualjetwork/__init__.py,sha256=Kw8tdzAvdhcMyujbsOF0VTVKE5wB-uqKBZ4AH8iNlcQ,2177
 pyerualjetwork/activation_functions.py,sha256=WWOdMd5pI6ZKe-ieKCIsKAYPQODHuXYxx7tzhA5xjes,11767
 pyerualjetwork/activation_functions_cuda.py,sha256=KmXJ5Cdig46XAMYakXFPEOlxSxtFJjD21-i3nGtxPjE,11807
 pyerualjetwork/data_operations.py,sha256=HjyW2QE18age6J8iG0jpbwqGOylL_nM-vE2CLbP9Wes,14690
@@ -13,12 +13,12 @@ pyerualjetwork/model_operations.py,sha256=hnhR8dtoICNJWIwGgJ65-LN3GYN_DYH4LMe6Yp
 pyerualjetwork/model_operations_cuda.py,sha256=XnKKq54ZLaqCm-NaJ6d8IToACKcKg2Ttq6moowVRRWo,13365
 pyerualjetwork/plan.py,sha256=EobwajGSIgbOujkzDKb-Kea0LGRHqpK3Xy1Le8VBAe8,34422
 pyerualjetwork/plan_cuda.py,sha256=iCcAHLzVw_VyjhkFHXzBWiedwbnpI1MCXNJgSDgZxWw,36065
-pyerualjetwork/planeat.py,sha256=Lr79cXaHsTYkLEA9zrrI0mIdLDy5l5Qa0_tlkqugxGE,41071
-pyerualjetwork/planeat_cuda.py,sha256=qHwISR1JOaTYklBKf59BQ-ixPDlludk61dJMrp-wNi0,41038
+pyerualjetwork/planeat.py,sha256=EtmOUCRmkXGuSj35fU5Y-gvBsRodVlMsEgvbrXIzY2A,40997
+pyerualjetwork/planeat_cuda.py,sha256=XkFbQF7pmPRWCQTacbmIab8yWkq-6S3dM-N1ehxzSvk,40963
 pyerualjetwork/ui.py,sha256=wu2BhU1k-w3Kcho5Jtq4SEKe68ftaUeRGneUOSCVDjU,575
 pyerualjetwork/visualizations.py,sha256=QaYSIyVkJZ8NqpBKArQKkI1y37nCQo_KIM98IMssnRc,28766
 pyerualjetwork/visualizations_cuda.py,sha256=F60vQ92AXlMgBka3InXnOtGoM25vQJAlBIU2AlYTwks,29200
-pyerualjetwork-4.2.0b4.dist-info/METADATA,sha256=B8Katp20szrJ7XPZSy4YfVNsdJSLUJsepiZ5dasYDww,7795
-pyerualjetwork-4.2.0b4.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-4.2.0b4.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-4.2.0b4.dist-info/RECORD,,
+pyerualjetwork-4.2.0b6.dist-info/METADATA,sha256=-m0uyY5sgobRog9idkhbeSHS5l9h_qDoKywhbG2sAes,7795
+pyerualjetwork-4.2.0b6.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-4.2.0b6.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-4.2.0b6.dist-info/RECORD,,