pyerualjetwork 4.3.7.dev1__tar.gz → 4.3.8__tar.gz

{pyerualjetwork-4.3.7.dev1 → pyerualjetwork-4.3.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.3.7.dev1
+Version: 4.3.8
 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
@@ -25,8 +25,6 @@ GitHub Page: https://github.com/HCB06/PyerualJetwork
 YouTube Tutorials: https://www.youtube.com/watch?v=6wMQstZ00is&list=PLNgNWpM7HbsBpCx2VTJ4SK9wcPyse-EHw
 
 	pip install pyerualjetwork
- 
-	'use this if your data small or memory management is a problem :'
 	
 	from pyerualjetwork import plan
 	from pyerualjetwork import planeat
@@ -38,26 +36,11 @@ YouTube Tutorials: https://www.youtube.com/watch?v=6wMQstZ00is&list=PLNgNWpM7Hbs
 	from pyerualjetwork import data_operations_cuda
 	from pyerualjetwork import model_operations_cuda
 	
-	'use this if your data large or memory management is not a problem : _afterburner package (afterburner package comes with powerful paralellism,
-	afterburner with cuda modules offers super-fast training but some memory managemant features and visualization features discarded.
-	Specially designed for LLM training and other massive model training)'
-	
-	from pyerualjetwork_afterburner import plan
-	from pyerualjetwork_afterburner import planeat
-	from pyerualjetwork_afterburner import data_operations
-	from pyerualjetwork_afterburner import model_operations
-	
-	from pyerualjetwork_afterburner import plan_cuda
-	from pyerualjetwork_afterburner import planeat_cuda
-	from pyerualjetwork_afterburner import data_operations_cuda
-	from pyerualjetwork_afterburner import model_operations_cuda
-
       Optimized for Visual Studio Code
       
       requires=[
  	    'scipy==1.13.1',
 	    'tqdm==4.66.4',
-	    'seaborn==0.13.2',
 	    'pandas==2.2.2',
 	    'networkx==3.3',
 	    'numpy==1.26.4',
@@ -67,7 +50,7 @@ YouTube Tutorials: https://www.youtube.com/watch?v=6wMQstZ00is&list=PLNgNWpM7Hbs
 	    'psutil==6.1.1'
         ]
 
-     matplotlib, seaborn, networkx (optional).
+     matplotlib, networkx (optional).
           
 ##############################
 

{pyerualjetwork-4.3.7.dev1 → pyerualjetwork-4.3.8}/README.md

@@ -16,8 +16,6 @@ GitHub Page: https://github.com/HCB06/PyerualJetwork
 YouTube Tutorials: https://www.youtube.com/watch?v=6wMQstZ00is&list=PLNgNWpM7HbsBpCx2VTJ4SK9wcPyse-EHw
 
 	pip install pyerualjetwork
- 
-	'use this if your data small or memory management is a problem :'
 	
 	from pyerualjetwork import plan
 	from pyerualjetwork import planeat
@@ -29,26 +27,11 @@ YouTube Tutorials: https://www.youtube.com/watch?v=6wMQstZ00is&list=PLNgNWpM7Hbs
 	from pyerualjetwork import data_operations_cuda
 	from pyerualjetwork import model_operations_cuda
 	
-	'use this if your data large or memory management is not a problem : _afterburner package (afterburner package comes with powerful paralellism,
-	afterburner with cuda modules offers super-fast training but some memory managemant features and visualization features discarded.
-	Specially designed for LLM training and other massive model training)'
-	
-	from pyerualjetwork_afterburner import plan
-	from pyerualjetwork_afterburner import planeat
-	from pyerualjetwork_afterburner import data_operations
-	from pyerualjetwork_afterburner import model_operations
-	
-	from pyerualjetwork_afterburner import plan_cuda
-	from pyerualjetwork_afterburner import planeat_cuda
-	from pyerualjetwork_afterburner import data_operations_cuda
-	from pyerualjetwork_afterburner import model_operations_cuda
-
       Optimized for Visual Studio Code
       
       requires=[
  	    'scipy==1.13.1',
 	    'tqdm==4.66.4',
-	    'seaborn==0.13.2',
 	    'pandas==2.2.2',
 	    'networkx==3.3',
 	    'numpy==1.26.4',
@@ -58,7 +41,7 @@ YouTube Tutorials: https://www.youtube.com/watch?v=6wMQstZ00is&list=PLNgNWpM7Hbs
 	    'psutil==6.1.1'
         ]
 
-     matplotlib, seaborn, networkx (optional).
+     matplotlib, networkx (optional).
           
 ##############################
 

{pyerualjetwork-4.3.7.dev1 → pyerualjetwork-4.3.8}/pyerualjetwork/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.3.7dev1"
+__version__ = "4.3.8"
 __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-4.3.8/pyerualjetwork/parallel.py

@@ -0,0 +1,118 @@
+import multiprocessing as mp
+from functools import partial
+import random
+from .planeat import mutation, cross_over, second_parent_selection
+
+def run_process(policy, best_weight, best_activations, good_weights, 
+                good_activations, bad_weights, bad_activations, best_fitness, 
+                normalized_fitness, child_W, child_act, mutated_W, mutated_act,
+                cross_over_mode, activation_selection_add_prob, 
+                activation_selection_change_prob, activation_selection_threshold, 
+                bad_genomes_selection_prob, fitness_bias, epsilon, 
+                bad_genomes_mutation_prob, activation_mutate_prob, 
+                activation_mutate_add_prob, activation_mutate_delete_prob, 
+                activation_mutate_change_prob, weight_mutate_prob, 
+                weight_mutate_threshold, activation_mutate_threshold):
+    
+    process_func = partial(process_single, policy=policy, best_weight=best_weight, 
+                           best_activations=best_activations, good_weights=good_weights, 
+                           good_activations=good_activations, bad_weights=bad_weights, 
+                           bad_activations=bad_activations, best_fitness=best_fitness, 
+                           normalized_fitness=normalized_fitness, child_W=child_W, 
+                           child_act=child_act, mutated_W=mutated_W, mutated_act=mutated_act,
+                           cross_over_mode=cross_over_mode,
+                           activation_selection_add_prob=activation_selection_add_prob,
+                           activation_selection_change_prob=activation_selection_change_prob,
+                           activation_selection_threshold=activation_selection_threshold,
+                           bad_genomes_selection_prob=bad_genomes_selection_prob,
+                           fitness_bias=fitness_bias,
+                           epsilon=epsilon,
+                           bad_genomes_mutation_prob=bad_genomes_mutation_prob,
+                           activation_mutate_prob=activation_mutate_prob,
+                           activation_mutate_add_prob=activation_mutate_add_prob,
+                           activation_mutate_delete_prob=activation_mutate_delete_prob,
+                           activation_mutate_change_prob=activation_mutate_change_prob,
+                           weight_mutate_prob=weight_mutate_prob,
+                           weight_mutate_threshold=weight_mutate_threshold,
+                           activation_mutate_threshold=activation_mutate_threshold)
+
+    with mp.Pool() as pool:
+        results = pool.map(process_func, range(len(bad_weights)))
+
+    for i, new_child_W, new_child_act, new_mutated_W, new_mutated_act in results:
+        child_W[i] = new_child_W
+        child_act[i] = new_child_act
+        mutated_W[i] = new_mutated_W
+        mutated_act[i] = new_mutated_act
+
+
+    return child_W, child_act, mutated_W, mutated_act
+
+
+def process_single(i, policy, best_weight, best_activations, 
+                   good_weights, good_activations, 
+                   bad_weights, bad_activations, 
+                   best_fitness, normalized_fitness, 
+                   cross_over_mode, 
+                   activation_selection_add_prob, activation_selection_change_prob,
+                   activation_selection_threshold, 
+                   bad_genomes_selection_prob, fitness_bias,
+                   epsilon, bad_genomes_mutation_prob, 
+                   activation_mutate_prob, activation_mutate_add_prob,
+                   activation_mutate_delete_prob, activation_mutate_change_prob,
+                   weight_mutate_prob, weight_mutate_threshold,
+                   activation_mutate_threshold):
+
+    if policy == 'aggressive':
+        first_parent_W = best_weight
+        first_parent_act = best_activations
+    elif policy == 'explorer':
+        first_parent_W = good_weights[i]
+        first_parent_act = good_activations[i]
+    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)
+
+    new_child_W, new_child_act = cross_over(
+        first_parent_W,
+        second_parent_W,
+        first_parent_act,
+        second_parent_act,
+        cross_over_mode=cross_over_mode,
+        activation_selection_add_prob=activation_selection_add_prob,
+        activation_selection_change_prob=activation_selection_change_prob,
+        activation_selection_threshold=activation_selection_threshold,
+        bad_genomes_selection_prob=bad_genomes_selection_prob,
+        first_parent_fitness=best_fitness,
+        fitness_bias=fitness_bias,
+        second_parent_fitness=normalized_fitness[s_i],
+        epsilon=epsilon
+    )
+
+    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
+
+    new_mutated_W, new_mutated_act = 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,
+        weight_mutate_threshold=weight_mutate_threshold,
+        genome_fitness=normalized_fitness[fitness_index],
+        activation_mutate_threshold=activation_mutate_threshold,
+        epsilon=epsilon
+    )
+    
+    return (i, new_child_W, new_child_act, new_mutated_W, new_mutated_act)

{pyerualjetwork-4.3.7.dev1/pyerualjetwork_afterburner → pyerualjetwork-4.3.8/pyerualjetwork}/plan.py

@@ -73,12 +73,12 @@ def fit(
     LTPW = np.zeros((len(y_train[0]), len(x_train[0].ravel()))).astype(dtype, copy=False) if W is None else W
     
     x_train = apply_activation(x_train, activation_potentiation)
-    LTPW += np.array(y_train, dtype=optimize_labels(y_train, cuda=False).dtype).T @ x_train
+    LTPW += y_train.T @ x_train
 
     return normalization(LTPW, dtype=dtype)
 
 
-def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=None, batch_size=1,
+def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=None, batch_size=1, pop_size=None,
            neural_web_history=False, show_current_activations=False,
            neurons_history=False, early_stop=False, loss='categorical_crossentropy', show_history=False,
            interval=33.33, target_acc=None, target_loss=None,
@@ -123,6 +123,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
 
         batch_size (float, optional): Batch size is used in the prediction process to receive train feedback by dividing the test data into chunks and selecting activations based on randomly chosen partitions. This process reduces computational cost and time while still covering the entire test set due to random selection, so it doesn't significantly impact accuracy. For example, a batch size of 0.08 means each train batch represents 8% of the train set. Default is 1. (%100 of train)
 
+        pop_size (int, optional): Population size of each generation. Default: count of activation functions
+
         early_stop (bool, optional): If True, implements early stopping during training.(If accuracy not improves in two gen stops learning.) Default is False.
 
         show_current_activations (bool, optional): Should it display the activations selected according to the current strategies during learning, or not? (True or False) This can be very useful if you want to cancel the learning process and resume from where you left off later. After canceling, you will need to view the live training activations in order to choose the activations to be given to the 'start_this' parameter. Default is False
@@ -156,14 +158,19 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
 
     data = 'Train'
 
-    activation_potentiation = all_activations()
+    except_this = ['spiral', 'circular']
+    activation_potentiation = [item for item in all_activations() if item not in except_this]
     activation_potentiation_len = len(activation_potentiation)
    
     # Pre-checks
 
+    if pop_size is None: pop_size = activation_potentiation_len
+
     x_train = x_train.astype(dtype, copy=False)
     y_train = optimize_labels(y_train, cuda=False)
 
+    if pop_size < activation_potentiation_len: raise ValueError(f"pop_size must be higher or equal to {activation_potentiation_len}")
+
     if gen is None:
         gen = activation_potentiation_len
 
@@ -192,16 +199,16 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
 
     progress = initialize_loading_bar(total=activation_potentiation_len, desc="", ncols=ncols, bar_format=bar_format_learner)
 
-    if fit_start is False:
-        weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), population_size=activation_potentiation_len, dtype=dtype)
+    if fit_start is False or pop_size > activation_potentiation_len:
+        weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), population_size=pop_size, dtype=dtype)
     
         if start_this_act is not None and start_this_W is not None:
             weight_pop[0] = start_this_W
             act_pop[0] = start_this_act
 
     else:
-        weight_pop = []
-        act_pop = []
+        weight_pop = [0] * pop_size
+        act_pop = [0] * pop_size
 
     for i in range(gen):
         postfix_dict["Gen"] = str(i+1) + '/' + str(gen)
@@ -211,14 +218,14 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
         progress.last_print_n = 0
         progress.update(0)
 
-        for j in range(activation_potentiation_len):
+        for j in range(pop_size):
 
             x_train_batch, y_train_batch = batcher(x_train, y_train, batch_size=batch_size)
             
-            if fit_start is True and i == 0:
-                act_pop.append(activation_potentiation[j])
+            if fit_start is True and i == 0 and j < activation_potentiation_len:
+                act_pop[j] = activation_potentiation[j]
                 W = fit(x_train_batch, y_train_batch, activation_potentiation=act_pop[-1], dtype=dtype)
-                weight_pop.append(W)
+                weight_pop[j] = W
             
             model = evaluate(x_train_batch, y_train_batch, W=weight_pop[j], activation_potentiation=act_pop[j])
             acc = model[get_acc()]

{pyerualjetwork-4.3.7.dev1/pyerualjetwork_afterburner → pyerualjetwork-4.3.8/pyerualjetwork}/plan_cuda.py

@@ -71,12 +71,12 @@ def fit(
     LTPW = cp.zeros((len(y_train[0]), len(x_train[0].ravel()))).astype(dtype, copy=False) if W is None else W
 
     x_train = apply_activation(x_train, activation_potentiation)
-    LTPW += cp.array(y_train, dtype=optimize_labels(y_train, cuda=True).dtype).T @ x_train
+    LTPW += y_train.T @ x_train
 
     return normalization(LTPW, dtype=dtype)
 
 
-def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=None, batch_size=1,
+def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=None, batch_size=1, pop_size=None,
            neural_web_history=False, show_current_activations=False,
            neurons_history=False, early_stop=False, loss='categorical_crossentropy', show_history=False,
            interval=33.33, target_acc=None, target_loss=None,
@@ -120,6 +120,8 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
 
         batch_size (float, optional): Batch size is used in the prediction process to receive train feedback by dividing the train data into chunks and selecting activations based on randomly chosen partitions. This process reduces computational cost and time while still covering the entire test set due to random selection, so it doesn't significantly impact accuracy. For example, a batch size of 0.08 means each train batch represents 8% of the train set. Default is 1. (%100 of train)
 
+        pop_size (int, optional): Population size of each generation. Default: count of activation functions
+
         early_stop (bool, optional): If True, implements early stopping during training.(If train accuracy not improves in two gen stops learning.) Default is False.
 
         show_current_activations (bool, optional): Should it display the activations selected according to the current strategies during learning, or not? (True or False) This can be very useful if you want to cancel the learning process and resume from where you left off later. After canceling, you will need to view the live training activations in order to choose the activations to be given to the 'start_this' parameter. Default is False
@@ -129,7 +131,7 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
         loss (str, optional): For visualizing and monitoring. PLAN neural networks doesn't need any loss function in training. options: ('categorical_crossentropy' or 'binary_crossentropy') Default is 'categorical_crossentropy'.
 
         interval (int, optional): The interval at which evaluations are conducted during training. (33.33 = 30 FPS, 16.67 = 60 FPS) Default is 100.
-
+    
         target_acc (int, optional): The target accuracy to stop training early when achieved. Default is None.
 
         target_loss (float, optional): The target loss to stop training early when achieved. Default is None.
@@ -155,12 +157,15 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
 
     data = 'Train'
 
-    activation_potentiation = all_activations() 
-
+    except_this = ['spiral', 'circular']
+    activation_potentiation = [item for item in all_activations() if item not in except_this]
     activation_potentiation_len = len(activation_potentiation)
 
+    if pop_size is None: pop_size = activation_potentiation_len
     y_train = optimize_labels(y_train, cuda=True)
 
+    if pop_size < activation_potentiation_len: raise ValueError(f"pop_size must be higher or equal to {activation_potentiation_len}")
+
     if memory == 'gpu':
         x_train = transfer_to_gpu(x_train, dtype=dtype)
         y_train = transfer_to_gpu(y_train, dtype=y_train.dtype)
@@ -201,16 +206,16 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
 
     progress = initialize_loading_bar(total=activation_potentiation_len, desc="", ncols=ncols, bar_format=bar_format_learner)
 
-    if fit_start is False:
-        weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), population_size=activation_potentiation_len, dtype=dtype)
+    if fit_start is False or pop_size > activation_potentiation_len:
+        weight_pop, act_pop = define_genomes(input_shape=len(x_train[0]), output_shape=len(y_train[0]), population_size=pop_size, dtype=dtype)
     
         if start_this_act is not None and start_this_W is not None:
             weight_pop[0] = start_this_W
             act_pop[0] = start_this_act
 
     else:
-        weight_pop = []
-        act_pop = []
+        weight_pop = [0] * pop_size
+        act_pop = [0] * pop_size
 
     for i in range(gen):
         postfix_dict["Gen"] = str(i+1) + '/' + str(gen)
@@ -220,17 +225,17 @@ def learner(x_train, y_train, optimizer, fit_start, strategy='accuracy', gen=Non
         progress.last_print_n = 0
         progress.update(0)
 
-        for j in range(activation_potentiation_len):
+        for j in range(pop_size):
 
             x_train_batch, y_train_batch = batcher(x_train, y_train, batch_size=batch_size)
 
             x_train_batch = cp.array(x_train_batch, dtype=dtype, copy=False)
             y_train_batch = cp.array(y_train_batch, dtype=dtype, copy=False)
 
-            if fit_start is True and i == 0:
-                act_pop.append(activation_potentiation[j])
+            if fit_start is True and i == 0 and j < activation_potentiation_len:
+                act_pop[j] = activation_potentiation[j]
                 W = fit(x_train_batch, y_train_batch, activation_potentiation=act_pop[-1], dtype=dtype)
-                weight_pop.append(W)
+                weight_pop[j] = W
     
             model = evaluate(x_train_batch, y_train_batch, W=weight_pop[j], activation_potentiation=act_pop[j])
             acc = model[get_acc()]

{pyerualjetwork-4.3.7.dev1/pyerualjetwork_afterburner → pyerualjetwork-4.3.8/pyerualjetwork}/planeat_cuda.py

@@ -722,7 +722,8 @@ def mutation(weight,
 
          new_threshold = threshold
          
-         all_acts = all_activations()
+         except_this = ['spiral', 'circular']
+         all_acts = [item for item in all_activations() if item not in except_this] # SPIRAL AND CIRCULAR ACTIVATION DISCARDED
          
          activation_add_prob = 1 - activation_add_prob
          activation_delete_prob = 1 - activation_delete_prob

{pyerualjetwork-4.3.7.dev1/pyerualjetwork_afterburner → pyerualjetwork-4.3.8/pyerualjetwork}/visualizations.py

@@ -2,7 +2,6 @@ import networkx as nx
 import matplotlib.pyplot as plt
 import numpy as np
 from scipy.spatial import ConvexHull
-import seaborn as sns
 from matplotlib.animation import ArtistAnimation
 
 def draw_neural_web(W, ax, G, return_objs=False):
@@ -323,7 +322,8 @@ def draw_activations(x_train, activation):
     except:
         print('\rWARNING: error in drawing some activation.', end='')
         return x_train
- 
+
+""" DISABLED
 def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activation_potentiation):
     
     from .metrics import metrics, confusion_matrix, roc_curve
@@ -451,7 +451,7 @@ def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activation_potentiation)
         print(f"Hata oluştu: {e}")
 
     plt.show()
-
+"""
 
 def plot_decision_boundary(x, y, activation_potentiation, W, artist=None, ax=None):
     
@@ -614,9 +614,9 @@ def update_neuron_history(LTPW, ax1, row, col, class_count, artist5, fig1, acc=F
 
     fig1.suptitle(suptitle_info, fontsize=16)
 
-
+""" DISABLED
 def initialize_visualization_for_fit(val, show_training, neurons_history, x_train, y_train):
-    """Initializes the visualization setup based on the parameters."""
+
     from .data_operations import find_closest_factors
     visualization_objects = {}
 
@@ -649,32 +649,33 @@ def initialize_visualization_for_fit(val, show_training, neurons_history, x_trai
         })
 
     return visualization_objects
-
+"""
         
-
+""" DISABLED
 def update_neural_web_for_fit(W, ax, G, artist):
-    """
-    The function `update_neural_web_for_fit` updates a neural web visualization for fitting.
-    """
+
     art5_1, art5_2, art5_3 = draw_neural_web(W=W, ax=ax, G=G, return_objs=True)
     art5_list = [art5_1] + [art5_2] + list(art5_3.values())
     artist.append(art5_list)
-
-
+"""
+    
+""" DISABLED
 def update_weight_visualization_for_fit(ax, LTPW, artist2):
-    """Updates the weight visualization plot."""
+
     art2 = ax.imshow(LTPW, interpolation='sinc', cmap='viridis')
     artist2.append([art2])
+"""
 
-
+""" DISABLED
 def update_decision_boundary_for_fit(ax, x_val, y_val, activation_potentiation, LTPW, artist1):
-    """Updates the decision boundary visualization."""
+
     art1_1, art1_2 = plot_decision_boundary(x_val, y_val, activation_potentiation, LTPW, artist=artist1, ax=ax)
     artist1.append([*art1_1.collections, art1_2])
+"""
 
-
+""" DISABLED
 def update_validation_history_for_fit(ax, val_list, artist3):
-    """Updates the validation accuracy history plot."""
+
     period = list(range(1, len(val_list) + 1))
     art3 = ax.plot(
         period, 
@@ -691,19 +692,21 @@ def update_validation_history_for_fit(ax, val_list, artist3):
     ax.set_ylabel('Validation Accuracy')
     ax.set_ylim([0, 1])
     artist3.append(art3)
-
-
+"""
+    
+""" DISABLED
 def display_visualization_for_fit(fig, artist_list, interval):
-    """Displays the animation for the given artist list."""
+
     ani = ArtistAnimation(fig, artist_list, interval=interval, blit=True)
     return ani
-
+"""
+    
 def show():
     plt.tight_layout()
     plt.show()
 
 def initialize_visualization_for_learner(show_history, neurons_history, neural_web_history, x_train, y_train):
-    """Initialize all visualization components"""
+
     from .data_operations import find_closest_factors
     viz_objects = {}
     
@@ -745,7 +748,7 @@ def initialize_visualization_for_learner(show_history, neurons_history, neural_w
     return viz_objects
 
 def update_history_plots_for_learner(viz_objects, depth_list, loss_list, best_acc_per_depth_list, x_train, final_activations):
-    """Update history visualization plots"""
+
     if 'history' not in viz_objects:
         return
     
@@ -772,7 +775,7 @@ def update_history_plots_for_learner(viz_objects, depth_list, loss_list, best_ac
     hist['artist3'].append(art3)
 
 def display_visualizations_for_learner(viz_objects, best_weights, data, best_acc, test_loss, y_train, interval):
-    """Display all final visualizations"""
+
     if 'history' in viz_objects:
         hist = viz_objects['history']
         for _ in range(30):

{pyerualjetwork-4.3.7.dev1/pyerualjetwork_afterburner → pyerualjetwork-4.3.8/pyerualjetwork}/visualizations_cuda.py

@@ -2,7 +2,6 @@ import networkx as nx
 import matplotlib.pyplot as plt
 import cupy as cp
 from scipy.spatial import ConvexHull
-import seaborn as sns
 from matplotlib.animation import ArtistAnimation
 
 def draw_neural_web(W, ax, G, return_objs=False):
@@ -325,7 +324,7 @@ def draw_activations(x_train, activation):
         print('\rWARNING: error in drawing some activation.', end='')
         return x_train
 
-
+""" DISABLED
 def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activation_potentiation):
     
     from .metrics_cuda import metrics, confusion_matrix, roc_curve
@@ -447,7 +446,7 @@ def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activation_potentiation)
     axs[1,1].set_title('Decision Boundary')
 
     plt.show()
-
+"""
 
 def plot_decision_boundary(x, y, activation_potentiation, W, artist=None, ax=None):
     
@@ -583,9 +582,8 @@ def update_neuron_history(LTPW, ax1, row, col, class_count, artist5, fig1, acc=F
 
     fig1.suptitle(suptitle_info, fontsize=16)
 
-
+""" DISABLED
 def initialize_visualization_for_fit(val, show_training, neurons_history, x_train, y_train):
-    """Initializes the visualization setup based on the parameters."""
     from .data_operations_cuda import find_closest_factors
     visualization_objects = {}
 
@@ -618,33 +616,34 @@ def initialize_visualization_for_fit(val, show_training, neurons_history, x_trai
         })
 
     return visualization_objects
+"""
+    
 
-
+""" DISABLED
 def update_weight_visualization_for_fit(ax, LTPW, artist2):
-    """Updates the weight visualization plot."""
     art2 = ax.imshow(LTPW.get(), interpolation='sinc', cmap='viridis')
     artist2.append([art2])
+"""
 
 def show():
     plt.tight_layout()
     plt.show()
 
+""" DISABLED
 def update_neural_web_for_fit(W, ax, G, artist):
-    """
-    The function `update_neural_web_for_fit` updates a neural web visualization for fitting.
-    """
     art5_1, art5_2, art5_3 = draw_neural_web(W=W, ax=ax, G=G, return_objs=True)
     art5_list = [art5_1] + [art5_2] + list(art5_3.values())
     artist.append(art5_list)
-    
+"""
+
+""" DISABLED
 def update_decision_boundary_for_fit(ax, x_val, y_val, activation_potentiation, LTPW, artist1):
-    """Updates the decision boundary visualization."""
     art1_1, art1_2 = plot_decision_boundary(x_val, y_val, activation_potentiation, LTPW, artist=artist1, ax=ax)
     artist1.append([*art1_1.collections, art1_2])
+"""
 
-
+""" DISABLED
 def update_validation_history_for_fit(ax, val_list, artist3):
-    """Updates the validation accuracy history plot."""
     val_list_cpu = []
     for i in range(len(val_list)):
         val_list_cpu.append(val_list[i].get())
@@ -664,13 +663,12 @@ def update_validation_history_for_fit(ax, val_list, artist3):
     ax.set_ylabel('Validation Accuracy')
     ax.set_ylim([0, 1])
     artist3.append(art3)
-
-
+"""
+""" DISABLED
 def display_visualization_for_fit(fig, artist_list, interval):
-    """Displays the animation for the given artist list."""
     ani = ArtistAnimation(fig, artist_list, interval=interval, blit=True)
     return ani
-
+"""
 def update_neuron_history_for_learner(LTPW, ax1, row, col, class_count, artist5, data, fig1, acc=False, loss=False):
 
     for j in range(len(class_count)):
@@ -699,7 +697,7 @@ def update_neuron_history_for_learner(LTPW, ax1, row, col, class_count, artist5,
     return artist5
 
 def initialize_visualization_for_learner(show_history, neurons_history, neural_web_history, x_train, y_train):
-    """Initialize all visualization components"""
+
     from .data_operations_cuda import find_closest_factors
     viz_objects = {}
     
@@ -741,7 +739,7 @@ def initialize_visualization_for_learner(show_history, neurons_history, neural_w
     return viz_objects
 
 def update_history_plots_for_learner(viz_objects, depth_list, loss_list, best_acc_per_depth_list, x_train, final_activations):
-    """Update history visualization plots"""
+
     if 'history' not in viz_objects:
         return
     
@@ -770,11 +768,11 @@ 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 Gen')
+    hist['ax'][2].set_title('Activation Shape Over Gen')
     hist['artist3'].append(art3)
 
 def display_visualizations_for_learner(viz_objects, best_weights, data, best_acc, test_loss, y_train, interval):
-    """Display all final visualizations"""
+
     if 'history' in viz_objects:
         hist = viz_objects['history']
         for _ in range(30):