pyerualjetwork 4.4__py3-none-any.whl → 4.5.1__py3-none-any.whl

pyerualjetwork/planeat.py

@@ -17,7 +17,7 @@ import random
 import math
 
 ### LIBRARY IMPORTS ###
-from .data_operations import normalization
+from .data_operations import normalization, non_neg_normalization
 from .ui import loading_bars, initialize_loading_bar
 from .activation_functions import apply_activation, all_activations
 
@@ -35,7 +35,7 @@ def define_genomes(input_shape, output_shape, population_size, dtype=np.float32)
       
       population_size (int): The number of genomes (individuals) in the population.
 
-      dtype (numpy.dtype): Data type for the arrays. np.float32 by default. Example: np.float64 or np.float16. [fp32 for balanced devices, fp64 for strong devices, fp16 for weak devices: not reccomended!] (optional)
+      dtype (numpy.dtype): Data type for the arrays. np.float32 by default. Example: np.float64 or np.float16.
 
    Returns:
       tuple: A tuple containing:
@@ -291,7 +291,7 @@ 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 = normalization(fitness, dtype=dtype)
+   normalized_fitness = non_neg_normalization(fitness, dtype=dtype)
 
    best_fitness = normalized_fitness[-1]
    epsilon = np.finfo(float).eps
@@ -708,28 +708,18 @@ def mutation(weight,
 
       if potential_weight_mutation > weight_mutate_prob:
 
-         start = 0
-         row_end = weight.shape[0]
-         col_end = weight.shape[1]
-
-         max_threshold = row_end * col_end
-
-         threshold = weight_mutate_threshold * (genome_fitness + epsilon)
-         new_threshold = threshold
-         
-         for _ in range(max_threshold):
+            row_end, col_end = weight.shape
+            max_threshold = row_end * col_end
+            threshold = weight_mutate_threshold / (genome_fitness + epsilon)
+   
+            n_mutations = min(int(threshold), max_threshold)
+                     
+            row_indices = np.random.randint(0, row_end, size=n_mutations)
+            col_indices = np.random.randint(0, col_end, size=n_mutations)
             
-            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)
-            new_threshold += threshold
-
-            if max_threshold > new_threshold:
-               pass
+            new_values = np.random.uniform(-1, 1, size=n_mutations)
             
-            else:
-               break
+            weight[row_indices, col_indices] = new_values
 
    activation_mutate_prob = 1 - activation_mutate_prob
    potential_activation_mutation = random.uniform(0, 1)

pyerualjetwork/planeat_cuda.py

@@ -19,7 +19,7 @@ import math
 
 
 ### LIBRARY IMPORTS ###
-from .data_operations_cuda import normalization
+from .data_operations_cuda import normalization, non_neg_normalization
 from .ui import loading_bars, initialize_loading_bar
 from .activation_functions_cuda import apply_activation, all_activations
 
@@ -37,7 +37,7 @@ def define_genomes(input_shape, output_shape, population_size, dtype=cp.float32)
       
       population_size (int): The number of genomes (individuals) in the population.
 
-      dtype (cupy.dtype): Data type for the arrays. np.float32 by default. Example: cp.float64 or cp.float16. [fp32 for balanced devices, fp64 for strong devices, fp16 for weak devices: not reccomended!] (optional)
+      dtype (cupy.dtype): Data type for the arrays. np.float32 by default. Example: cp.float64 or cp.float16.
 
    Returns:
       tuple: A tuple containing:
@@ -97,7 +97,7 @@ def evolver(weights,
             weight_mutate_prob=1, 
             dtype=cp.float32):
    """
-  Applies the evolving process of a population of genomes using selection, crossover, mutation, and activation function potentiation.
+   Applies the evolving process of a population of genomes using selection, crossover, mutation, and activation function potentiation.
    The function modifies the population's weights and activation functions based on a specified policy, mutation probabilities, and strategy.
 
    'selection' args effects cross-over.
@@ -292,7 +292,7 @@ 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 = normalization(fitness, dtype=dtype)
+   normalized_fitness = non_neg_normalization(fitness, dtype=dtype)
 
    best_fitness = normalized_fitness[-1]
    epsilon = cp.finfo(float).eps
@@ -709,28 +709,18 @@ def mutation(weight,
 
       if potential_weight_mutation > weight_mutate_prob:
 
-         start = 0
-         row_end = weight.shape[0]
-         col_end = weight.shape[1]
-         
-         max_threshold = row_end * col_end
-
-         threshold = weight_mutate_threshold * (genome_fitness + epsilon)
-         new_threshold = threshold
-
-         for _ in range(max_threshold):
+            row_end, col_end = weight.shape
+            max_threshold = row_end * col_end
+            threshold = weight_mutate_threshold / (genome_fitness + epsilon)
+   
+            n_mutations = min(int(threshold), max_threshold)
+                     
+            row_indices = cp.random.randint(0, row_end, size=n_mutations)
+            col_indices = cp.random.randint(0, col_end, size=n_mutations)
             
-            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)
-            new_threshold += threshold
-
-            if max_threshold > new_threshold:
-               pass
+            new_values = cp.random.uniform(-1, 1, size=n_mutations)
             
-            else:
-               break
+            weight[row_indices, col_indices] = new_values
 
    activation_mutate_prob = 1 - activation_mutate_prob
    potential_activation_mutation = random.uniform(0, 1)

pyerualjetwork/visualizations.py

@@ -9,27 +9,27 @@ def draw_neural_web(W, ax, G, return_objs=False):
     """
     Visualizes a neural web by drawing the neural network structure.
 
-    Parameters:
-    W : numpy.ndarray
-        A 2D array representing the connection weights of the neural network.
-    ax : matplotlib.axes.Axes
-        The matplotlib axes where the graph will be drawn.
-    G : networkx.Graph
-        The NetworkX graph representing the neural network structure.
-    return_objs : bool, optional
-        If True, returns the drawn objects (nodes and edges). Default is False.
+    Args:
+        W : numpy.ndarray
+            A 2D array representing the connection weights of the neural network.
+        ax : matplotlib.axes.Axes
+            The matplotlib axes where the graph will be drawn.
+        G : networkx.Graph
+            The NetworkX graph representing the neural network structure.
+        return_objs : bool, optional
+            If True, returns the drawn objects (nodes and edges). Default is False.
 
     Returns:
-    art1 : matplotlib.collections.PathCollection or None
-        Returns the node collection if return_objs is True; otherwise, returns None.
-    art2 : matplotlib.collections.LineCollection or None
-        Returns the edge collection if return_objs is True; otherwise, returns None.
-    art3 : matplotlib.collections.TextCollection or None
-        Returns the label collection if return_objs is True; otherwise, returns None.
+        art1 : matplotlib.collections.PathCollection or None
+            Returns the node collection if return_objs is True; otherwise, returns None.
+        art2 : matplotlib.collections.LineCollection or None
+            Returns the edge collection if return_objs is True; otherwise, returns None.
+        art3 : matplotlib.collections.TextCollection or None
+            Returns the label collection if return_objs is True; otherwise, returns None.
 
     Example:
-    art1, art2, art3 = draw_neural_web(W, ax, G, return_objs=True)
-    plt.show()
+        art1, art2, art3 = draw_neural_web(W, ax, G, return_objs=True)
+        plt.show()
     """
 
     for i in range(W.shape[0]):

pyerualjetwork/visualizations_cuda.py

@@ -9,27 +9,27 @@ def draw_neural_web(W, ax, G, return_objs=False):
     """
     Visualizes a neural web by drawing the neural network structure.
 
-    Parameters:
-    W : numpy.ndarray
-        A 2D array representing the connection weights of the neural network.
-    ax : matplotlib.axes.Axes
-        The matplotlib axes where the graph will be drawn.
-    G : networkx.Graph
-        The NetworkX graph representing the neural network structure.
-    return_objs : bool, optional
-        If True, returns the drawn objects (nodes and edges). Default is False.
+    Args:
+        W : numpy.ndarray
+            A 2D array representing the connection weights of the neural network.
+        ax : matplotlib.axes.Axes
+            The matplotlib axes where the graph will be drawn.
+        G : networkx.Graph
+            The NetworkX graph representing the neural network structure.
+        return_objs : bool, optional
+            If True, returns the drawn objects (nodes and edges). Default is False.
 
     Returns:
-    art1 : matplotlib.collections.PathCollection or None
-        Returns the node collection if return_objs is True; otherwise, returns None.
-    art2 : matplotlib.collections.LineCollection or None
-        Returns the edge collection if return_objs is True; otherwise, returns None.
-    art3 : matplotlib.collections.TextCollection or None
-        Returns the label collection if return_objs is True; otherwise, returns None.
+        art1 : matplotlib.collections.PathCollection or None
+            Returns the node collection if return_objs is True; otherwise, returns None.
+        art2 : matplotlib.collections.LineCollection or None
+            Returns the edge collection if return_objs is True; otherwise, returns None.
+        art3 : matplotlib.collections.TextCollection or None
+            Returns the label collection if return_objs is True; otherwise, returns None.
 
     Example:
-    art1, art2, art3 = draw_neural_web(W, ax, G, return_objs=True)
-    plt.show()
+        art1, art2, art3 = draw_neural_web(W, ax, G, return_objs=True)
+        plt.show()
     """
     W = W.get()
     for i in range(W.shape[0]):

{pyerualjetwork-4.4.dist-info → pyerualjetwork-4.5.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.4
+Version: 4.5.1
 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-4.5.1.dist-info/RECORD

@@ -0,0 +1,25 @@
+pyerualjetwork/__init__.py,sha256=Oe1PUj-kEsIW73oaiAxac3x_QQxSAFhOpUacNgzc6gs,1279
+pyerualjetwork/activation_functions.py,sha256=Ms0AGBqkJuCA42ht64MSQnO54Td_1eDGquedpoBDVbc,7642
+pyerualjetwork/activation_functions_cuda.py,sha256=5y1Ti3GDfDteQDCUmODwe7tAyDAUlDTKmIikChQ8d6g,7772
+pyerualjetwork/data_operations.py,sha256=SOPcuCUedAVKLZ10q4uX8XVgtFAgQ2gz6efVHR6ctw0,15166
+pyerualjetwork/data_operations_cuda.py,sha256=X0rUCxehqyVknjBToJ0zXCTGQwlAA7GEVAcqQ-YJYfQ,17267
+pyerualjetwork/fitness_functions.py,sha256=urRdeMvUhNgWxD4ZGHCRdQlIf9cTWYMvF3_aVBojRqY,1235
+pyerualjetwork/help.py,sha256=nQ_YbYA2RtuafhuvkreNpX0WWL1I_nzlelwCtvei0_Y,775
+pyerualjetwork/loss_functions.py,sha256=6PyBI232SQRGuFnG3LDGvnv_PUdWzT2_2mUODJiejGI,618
+pyerualjetwork/loss_functions_cuda.py,sha256=C93IZJcrOpT6HMK9x1O4AHJWXYTkN5WZiqdssPbvAPk,617
+pyerualjetwork/memory_operations.py,sha256=0yCOHcgiNyF4ccMcRlL1Q9F_byG4nzjhmkbpXE_yU6E,13401
+pyerualjetwork/metrics.py,sha256=q7MkhnZDRbCjFBDDfUgrl8lBYnUT_1ro1LxeBq105pI,6077
+pyerualjetwork/metrics_cuda.py,sha256=73h9GC7XwmnFCVzFEEiPQfF8CwHIz2wsCbxpZrJtYgw,5061
+pyerualjetwork/model_operations.py,sha256=BLRL_5s_KSs8iCiLsEwWvhRcGiWCP_TD9lsjYWM7Zek,12746
+pyerualjetwork/model_operations_cuda.py,sha256=b3Bkobbrhq28AmYZ0vGxf2Hf8V2LPvoiM0xaPAApqec,13254
+pyerualjetwork/plan.py,sha256=UyIvPmvHCHwczlc9KHolE4y6CPEeBfhnRN5yznSbnoM,23028
+pyerualjetwork/plan_cuda.py,sha256=iteqgv7x9Z2Pj4vGOZs6HXS3r0bNaF_smr7ZXaOdRnw,23990
+pyerualjetwork/planeat.py,sha256=_dnGRVBzdRUgvVCnHZ721tdXYV9PSvCz-aUnj--5VpU,38697
+pyerualjetwork/planeat_cuda.py,sha256=CXBF4vsTZ-fE-3W8Zc6Zxe_oKuyJS02FaHsOzSwzLV8,38731
+pyerualjetwork/ui.py,sha256=wu2BhU1k-w3Kcho5Jtq4SEKe68ftaUeRGneUOSCVDjU,575
+pyerualjetwork/visualizations.py,sha256=utnX9zQhzmtvBJLOLNGm2jecVVk4zHXABQdjb0XzJac,28352
+pyerualjetwork/visualizations_cuda.py,sha256=gnoaaazZ-nc9E1ImqXrZBRgQ4Rnpi2qh2yGJ2eLKMlE,28807
+pyerualjetwork-4.5.1.dist-info/METADATA,sha256=xjGpEBnY_JunoNvXCbD1oJfdYL7Wvzj0Nt7oWj61gZg,7505
+pyerualjetwork-4.5.1.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-4.5.1.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-4.5.1.dist-info/RECORD,,

pyerualjetwork-4.4.dist-info/RECORD

@@ -1,25 +0,0 @@
-pyerualjetwork/__init__.py,sha256=FyN5mW58VZsm76E1zSzF5opP6gHodZnkhPYS17xv9jc,1277
-pyerualjetwork/activation_functions.py,sha256=Ms0AGBqkJuCA42ht64MSQnO54Td_1eDGquedpoBDVbc,7642
-pyerualjetwork/activation_functions_cuda.py,sha256=5y1Ti3GDfDteQDCUmODwe7tAyDAUlDTKmIikChQ8d6g,7772
-pyerualjetwork/data_operations.py,sha256=Flteouu6rfSo2uHMqBHuzO02dXmbNa-I5qWmUpGTZ5Y,14760
-pyerualjetwork/data_operations_cuda.py,sha256=ZcjmLXE1-HVwedextYdJZ1rgrns1OfSekzFpr1a9m6o,17625
-pyerualjetwork/fitness_functions.py,sha256=9ZtCasBVjk3qQldi2pIzV6c5hTBJJyGCU0eVhJsoxPo,1145
-pyerualjetwork/help.py,sha256=nQ_YbYA2RtuafhuvkreNpX0WWL1I_nzlelwCtvei0_Y,775
-pyerualjetwork/loss_functions.py,sha256=6PyBI232SQRGuFnG3LDGvnv_PUdWzT2_2mUODJiejGI,618
-pyerualjetwork/loss_functions_cuda.py,sha256=C93IZJcrOpT6HMK9x1O4AHJWXYTkN5WZiqdssPbvAPk,617
-pyerualjetwork/memory_operations.py,sha256=I7QiZ--xSyRkFF0wcckPwZV7K9emEvyx5aJ3DiRHZFI,13468
-pyerualjetwork/metrics.py,sha256=q7MkhnZDRbCjFBDDfUgrl8lBYnUT_1ro1LxeBq105pI,6077
-pyerualjetwork/metrics_cuda.py,sha256=73h9GC7XwmnFCVzFEEiPQfF8CwHIz2wsCbxpZrJtYgw,5061
-pyerualjetwork/model_operations.py,sha256=MCSCNYiiICRVZITobtS3ZIWmH5Q9gjyELuH32sAdgg4,12649
-pyerualjetwork/model_operations_cuda.py,sha256=NT01BK5nrDYE7H1x3KnSI8gmx0QTGGB0mP_LqEb1uuU,13157
-pyerualjetwork/plan.py,sha256=VeoG3QU6vy9I7HG23aQS4qzo5_R-tAxwXdu0oT_2mBw,22973
-pyerualjetwork/plan_cuda.py,sha256=LKuNDDmUH_tcVvdBC29ASB6U2SKETC6lcWQiH-8vi1A,23965
-pyerualjetwork/planeat.py,sha256=oAu0a2rs6BQ2HUpLjKFR4m7xDbhUVOzLstop75u35Tg,38889
-pyerualjetwork/planeat_cuda.py,sha256=E_pJEsNKfiF97FvGZGSsxmdqzLAJub05enmneymozcg,38922
-pyerualjetwork/ui.py,sha256=wu2BhU1k-w3Kcho5Jtq4SEKe68ftaUeRGneUOSCVDjU,575
-pyerualjetwork/visualizations.py,sha256=1QSisYAaGnO5kug6qo1qOssTkQM-MgR7L8h4c3sczzU,28294
-pyerualjetwork/visualizations_cuda.py,sha256=PYRqj4QYUbuYMYcNwO8yaTPB-jK7E6kZHhTrAi0lwPU,28749
-pyerualjetwork-4.4.dist-info/METADATA,sha256=i89Z4ZNMY6mLus5DkDqYBXasOQaq33DAogrFR0dU0Fw,7503
-pyerualjetwork-4.4.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-4.4.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-4.4.dist-info/RECORD,,