pyerualjetwork 4.2.9b7__py3-none-any.whl → 4.3.0__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.2.9b7"
+__version__ = "4.3.0"
 __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/activation_functions_cuda.py

@@ -224,7 +224,6 @@ def safe_add(current_sum, new_value):
         except OverflowError:
             return cp.array(current_sum) + cp.array(new_value)
     
-
 def apply_activation(Input, activation_list):
     """
         Applies a sequence of activation functions to the input.
@@ -308,7 +307,7 @@ def apply_activation(Input, activation_list):
             elif activation_list[i] == 'mod_sigmoid':
                 Input = safe_add(Input, mod_sigmoid(origin_input))
             elif activation_list[i] == 'linear':
-                Input += origin_input
+                Input = safe_add(Input, origin_input)
             elif activation_list[i] == 'quartic':
                 Input = safe_add(Input, quartic(origin_input))
             elif activation_list[i] == 'square_quartic':

pyerualjetwork/data_operations.py

@@ -55,9 +55,8 @@ def decode_one_hot(encoded_data):
         numpy.ndarray: Decoded categorical labels with shape (n_samples,).
     """
 
-    decoded_labels = np.argmax(encoded_data, axis=1)
-
-    return decoded_labels
+    if encoded_data.ndim == 1: return np.argmax(encoded_data)
+    else: return np.argmax(encoded_data, axis=1)
 
 
 def split(X, y, test_size, random_state=42, dtype=np.float32):

pyerualjetwork/plan.py

@@ -135,9 +135,9 @@ def fit(
     # Training process
     for index, inp in enumerate(x_train):
         inp = np.array(inp, copy=False).ravel()
-        y_decoded = decode_one_hot(y_train)
+        y_decoded = decode_one_hot(y_train[index])
         # Weight updates
-        STPW = feed_forward(inp, STPW, is_training=True, Class=y_decoded[index], activation_potentiation=activation_potentiation, LTD=LTD)
+        STPW = feed_forward(inp, STPW, is_training=True, Class=y_decoded, activation_potentiation=activation_potentiation, LTD=LTD)
         LTPW += normalization(STPW, dtype=dtype) if auto_normalization else STPW
         if val and index != 0:
             if index % math.ceil((val_count / len(x_train)) * 100) == 0:
@@ -349,8 +349,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
                 (strategy == 'recall' and recall_score >= best_recall)):
 
                 best_acc = acc
-                best_weights = weight_pop[j]
-                final_activations = act_pop[j]
+                best_weights = np.copy(weight_pop[j])
+                final_activations = act_pop[j].copy() if isinstance(act_pop[j], list) else act_pop[j]
                 best_model = model
 
                 final_activations = [final_activations[0]] if len(set(final_activations)) == 1 else final_activations # removing if all same
@@ -412,8 +412,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
                                                        y_pred_batch=train_model[get_preds_softmax()])
 
                     print('\nActivations: ', final_activations)
-                    print(f'Train Accuracy (%{batch_size * 100} of train samples):', train_model[get_acc()])
-                    print(f'Train Loss (%{batch_size * 100} of train samples): ', train_loss, '\n')
+                    print(f'Train Accuracy :', train_model[get_acc()])
+                    print(f'Train Loss : ', train_loss, '\n')
 
                     # Display final visualizations
                     display_visualizations_for_learner(viz_objects, best_weights, data, best_acc, 
@@ -434,8 +434,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
                                                        y_pred_batch=train_model[get_preds_softmax()])
 
                     print('\nActivations: ', final_activations)
-                    print(f'Train Accuracy (%{batch_size * 100} of train samples):', train_model[get_acc()])
-                    print(f'Train Loss (%{batch_size * 100} of train samples): ', train_loss, '\n')
+                    print(f'Train Accuracy :', train_model[get_acc()])
+                    print(f'Train Loss : ', train_loss, '\n')
 
                     # Display final visualizations
                     display_visualizations_for_learner(viz_objects, best_weights, data, best_acc, 
@@ -465,8 +465,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
                                                    y_pred_batch=train_model[get_preds_softmax()])
 
                 print('\nActivations: ', final_activations)
-                print(f'Train Accuracy (%{batch_size * 100} of train samples):', train_model[get_acc()])
-                print(f'Train Loss (%{batch_size * 100} of train samples): ', train_loss, '\n')
+                print(f'Train Accuracy :', train_model[get_acc()])
+                print(f'Train Loss : ', train_loss, '\n')
 
                 # Display final visualizations
                 display_visualizations_for_learner(viz_objects, best_weights, data, best_acc, 
@@ -484,8 +484,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
         train_loss = binary_crossentropy(y_true_batch=y_train, y_pred_batch=train_model[get_preds_softmax()])
 
     print('\nActivations: ', final_activations)
-    print(f'Train Accuracy (%{batch_size * 100} of train samples):', train_model[get_acc()])
-    print(f'Train Loss (%{batch_size * 100} of train samples): ', train_loss, '\n')
+    print(f'Train Accuracy :', train_model[get_acc()])
+    print(f'Train Loss : ', train_loss, '\n')
 
     # Display final visualizations
     display_visualizations_for_learner(viz_objects, best_weights, data, best_acc, train_loss, y_train, interval)

pyerualjetwork/plan_cuda.py

@@ -374,8 +374,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
                 (strategy == 'recall' and recall_score >= best_recall)):
 
                 best_acc = acc
-                best_weights = weight_pop[j]
-                final_activations = act_pop[j]
+                best_weights = cp.copy(weight_pop[j])
+                final_activations = act_pop[j].copy() if isinstance(act_pop[j], list) else act_pop[j]
                 best_model = model
 
                 final_activations = [final_activations[0]] if len(set(final_activations)) == 1 else final_activations # removing if all same
@@ -437,8 +437,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
                                                        y_pred_batch=train_model[get_preds_softmax()])
 
                     print('\nActivations: ', final_activations)
-                    print(f'Train Accuracy (%{batch_size * 100} of train samples):', train_model[get_acc()])
-                    print(f'Train Loss (%{batch_size * 100} of train samples): ', train_loss, '\n')
+                    print(f'Train Accuracy:', train_model[get_acc()])
+                    print(f'Train Loss: ', train_loss, '\n')
                 
                     # Display final visualizations
                     display_visualizations_for_learner(viz_objects, best_weights, data, best_acc, 
@@ -459,8 +459,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
                                                        y_pred_batch=train_model[get_preds_softmax()])
 
                     print('\nActivations: ', final_activations)
-                    print(f'Train Accuracy (%{batch_size * 100} of train samples):', train_model[get_acc()])
-                    print(f'Train Loss (%{batch_size * 100} of train samples): ', train_loss, '\n')
+                    print(f'Train Accuracy:', train_model[get_acc()])
+                    print(f'Train Loss: ', train_loss, '\n')
 
                     # Display final visualizations
                     display_visualizations_for_learner(viz_objects, best_weights, data, best_acc, 
@@ -490,8 +490,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
                                                    y_pred_batch=train_model[get_preds_softmax()])
 
                 print('\nActivations: ', final_activations)
-                print(f'Train Accuracy (%{batch_size * 100} of train samples):', train_model[get_acc()])
-                print(f'Train Loss (%{batch_size * 100} of train samples): ', train_loss, '\n')
+                print(f'Train Accuracy:', train_model[get_acc()])
+                print(f'Train Loss: ', train_loss, '\n')
 
                 # Display final visualizations
                 display_visualizations_for_learner(viz_objects, best_weights, data, best_acc, 
@@ -509,8 +509,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
         train_loss = binary_crossentropy(y_true_batch=y_train, y_pred_batch=train_model[get_preds_softmax()])
 
     print('\nActivations: ', final_activations)
-    print(f'Train Accuracy (%{batch_size * 100} of train samples):', train_model[get_acc()])
-    print(f'Train Loss (%{batch_size * 100} of train samples): ', train_loss, '\n')
+    print(f'Train Accuracy:', train_model[get_acc()])
+    print(f'Train Loss: ', train_loss, '\n')
 
     # Display final visualizations
     display_visualizations_for_learner(viz_objects, best_weights, data, best_acc, train_loss, y_train, interval)

pyerualjetwork/planeat.py

@@ -15,7 +15,6 @@ 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
@@ -279,7 +278,7 @@ def evolver(weights,
 
    good_activations = list(activation_potentiations[slice_center:])
    bad_activations = list(activation_potentiations[:slice_center])
-   best_activations =  copy.deepcopy(good_activations[-1])
+   best_activations = good_activations[-1].copy() if isinstance(good_activations[-1], list) else good_activations[-1]
 
    
 ### PLANEAT IS APPLIED ACCORDING TO THE SPECIFIED POLICY, STRATEGY, AND PROBABILITY CONFIGURATION:
@@ -293,10 +292,10 @@ def evolver(weights,
    epsilon = np.finfo(float).eps
 
    child_W = np.copy(bad_weights)
-   child_act = copy.deepcopy(bad_activations)
+   child_act = bad_activations.copy()
 
    mutated_W = np.copy(bad_weights)
-   mutated_act = copy.deepcopy(bad_activations)
+   mutated_act = bad_activations.copy()
 
    for i in range(len(bad_weights)):
       

pyerualjetwork/planeat_cuda.py

@@ -16,7 +16,6 @@ import cupy as cp
 import numpy as np
 import random
 import math
-import copy
 
 
 ### LIBRARY IMPORTS ###
@@ -279,7 +278,7 @@ def evolver(weights,
 
    good_activations = list(activation_potentiations[slice_center:])
    bad_activations = list(activation_potentiations[:slice_center])
-   best_activations =  copy.deepcopy(good_activations[-1])
+   best_activations = good_activations[-1].copy() if isinstance(good_activations[-1], list) else good_activations[-1]
 
    
 ### PLANEAT IS APPLIED ACCORDING TO THE SPECIFIED POLICY, STRATEGY, AND PROBABILITY CONFIGURATION:
@@ -293,10 +292,10 @@ def evolver(weights,
    epsilon = cp.finfo(float).eps
 
    child_W = cp.copy(bad_weights)
-   child_act = copy.deepcopy(bad_activations)
+   child_act = bad_activations.copy()
 
    mutated_W = cp.copy(bad_weights)
-   mutated_act = copy.deepcopy(bad_activations)
+   mutated_act = bad_activations.copy()
 
 
    for i in range(len(bad_weights)):

{pyerualjetwork-4.2.9b7.dist-info → pyerualjetwork-4.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.2.9b7
+Version: 4.3.0
 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
@@ -24,6 +24,7 @@ GitHub Page: https://github.com/HCB06/PyerualJetwork
 
 
       pip install pyerualjetwork
+      pip install pyerualjetwork==x.x.x-jetstorm
       
       from pyerualjetwork import plan
       from pyerualjetwork import planeat

{pyerualjetwork-4.2.9b7.dist-info → pyerualjetwork-4.3.0.dist-info}/RECORD

@@ -1,7 +1,7 @@
-pyerualjetwork/__init__.py,sha256=-UIV7CqxZoriiu5trhAYI1q_ztU6L6nky-nOFm1p9l0,641
+pyerualjetwork/__init__.py,sha256=bh-WncqbgotASiAnBwCZ2YoOPk21dSp2rlAQNn_wkcU,639
 pyerualjetwork/activation_functions.py,sha256=eLEesmMgDvkI1TqaLTpqtOgTaLbHEAyw-D57KIKd9G4,11775
-pyerualjetwork/activation_functions_cuda.py,sha256=ahUOF47g073epWrIrv4kGBqQjif1xcw3qfEhvLJEDp4,11789
-pyerualjetwork/data_operations.py,sha256=pb5CqJ0Th6fCjTNMCtqQMiwH3KezTxAijacglsKUxmY,14730
+pyerualjetwork/activation_functions_cuda.py,sha256=ztIw6rMR4t1289_TPIGYwE6qarl_YbSOGj5Ep3rUMqs,11803
+pyerualjetwork/data_operations.py,sha256=Flteouu6rfSo2uHMqBHuzO02dXmbNa-I5qWmUpGTZ5Y,14760
 pyerualjetwork/data_operations_cuda.py,sha256=UpoJoFhIwTU4xg9dVuLAxLAT4CkRaGsxvtJG9j1xrNo,17629
 pyerualjetwork/help.py,sha256=nQ_YbYA2RtuafhuvkreNpX0WWL1I_nzlelwCtvei0_Y,775
 pyerualjetwork/loss_functions.py,sha256=6PyBI232SQRGuFnG3LDGvnv_PUdWzT2_2mUODJiejGI,618
@@ -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=UzCTFCA9cTv9ITCtsqfJ1g02rCMyescoIV6j1amvYGw,32134
-pyerualjetwork/plan_cuda.py,sha256=hpXZl3h7B1qAVYW-gZebwKMZd4-ftAZ-u05teOJjsno,33525
-pyerualjetwork/planeat.py,sha256=t6qyuMB2c5n8lsAJooEpShzEnw2GvepBI0bpLMx0DUI,39440
-pyerualjetwork/planeat_cuda.py,sha256=UBdbAk87M5zEZzZlRBeOzW-q0Sy8c_XWl4zdrtDnyIs,39499
+pyerualjetwork/plan.py,sha256=ApMQC46_I8qtMqO4lLYLme--SGcMRg-GRo1-gSb3A3I,31894
+pyerualjetwork/plan_cuda.py,sha256=H_EuNNyxrY6-AiuRkOYC8J_UmbzoqJ9aeO0i9pgUDZI,33277
+pyerualjetwork/planeat.py,sha256=e-J-u5gJYijKznN6gn2DZoaCJJro84DOBYTy1rR5-y4,39470
+pyerualjetwork/planeat_cuda.py,sha256=QNHCQLkR0MNFqyN2iHAtC7cbf8qZiD3p_54YH3lnMFA,39529
 pyerualjetwork/ui.py,sha256=wu2BhU1k-w3Kcho5Jtq4SEKe68ftaUeRGneUOSCVDjU,575
 pyerualjetwork/visualizations.py,sha256=1SKMZaJ80OD2qHUyMxW1IOv8zwmxzMPxclfbeq1Xr4g,28772
 pyerualjetwork/visualizations_cuda.py,sha256=KbMhfsLlxujy_i3QrwCf734Q-k6d7Zn_7CEbm3gzK9w,29186
-pyerualjetwork-4.2.9b7.dist-info/METADATA,sha256=hqgQTjNLjoljou-abs6HJwbCoeHlnrkZTcmU91-rB7c,7454
-pyerualjetwork-4.2.9b7.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-4.2.9b7.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-4.2.9b7.dist-info/RECORD,,
+pyerualjetwork-4.3.0.dist-info/METADATA,sha256=QyBQvs-G2foB8Jhj-SnwHIOWaYfX6pbyBJUw19nPvwU,7502
+pyerualjetwork-4.3.0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-4.3.0.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-4.3.0.dist-info/RECORD,,