pyerualjetwork 4.0.9__py3-none-any.whl → 4.1.1__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -47,7 +47,7 @@ for package_name in package_names:
 
 print(f"PyerualJetwork is ready to use with {err} errors")
 
-__version__ = "4.0.9"
+__version__ = "4.1.1"
 __update__ = "* Note: CUDA modules need cupy. Enter this command in your terminal: 'pip install cupy-cuda12x' or your cuda version.\n* Changes: https://github.com/HCB06/PyerualJetwork/blob/main/CHANGES\n* PyerualJetwork document: https://github.com/HCB06/Anaplan/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

@@ -18,9 +18,9 @@ def spiral_activation(x):
 
     spiral_x = r * cp.cos(theta + r)
     spiral_y = r * cp.sin(theta + r)
-    
 
-    spiral_output = cp.concatenate(([spiral_x[0]], spiral_y))
+
+    spiral_output = cp.concatenate([cp.array([spiral_x[0]]), spiral_y])
     
     return spiral_output
 

pyerualjetwork/data_operations_cuda.py

@@ -81,17 +81,22 @@ def decode_one_hot(encoded_data):
     return decoded_labels
 
 
-def split(X, y, test_size, random_state, dtype=cp.float32):
+def split(X, y, test_size, random_state=42, dtype=cp.float32, use_cpu=False):
     """
     Splits the given X (features) and y (labels) data into training and testing subsets.
 
     Args:
         X (cupy.ndarray): Features data.
+        
         y (cupy.ndarray): Labels data.
+        
         test_size (float or int): Proportion or number of samples for the test subset.
-        random_state (int or None): Seed for random state.
+        
+        random_state (int or None): Seed for random state. Default: 42.
+        
         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)
-
+        
+        use_cpu (bool): If True, output will be same cpu's split function. Default: False.
     Returns:
         tuple: x_train, x_test, y_train, y_test as ordered training and testing data subsets.
     """
@@ -118,11 +123,17 @@ def split(X, y, test_size, random_state, dtype=cp.float32):
     else:
         raise ValueError("test_size should be float or int.")
 
-    if random_state is not None:
-        cp.random.seed(random_state)
+    if use_cpu:
+        indices = np.arange(num_samples)
+        np.random.seed(random_state)
+        np.random.shuffle(indices)
+        indices = cp.array(indices)
+    else:
+        if random_state is not None:
+            cp.random.seed(random_state)
 
-    indices = cp.arange(num_samples)
-    cp.random.shuffle(indices)
+        indices = cp.arange(num_samples)
+        cp.random.shuffle(indices)
 
     test_indices = indices[:test_size]
     train_indices = indices[test_size:]
@@ -133,16 +144,22 @@ def split(X, y, test_size, random_state, dtype=cp.float32):
     return x_train, x_test, y_train, y_test
 
 
-def manuel_balancer(x_train, y_train, target_samples_per_class, dtype=cp.float32):
+def manuel_balancer(x_train, y_train, target_samples_per_class, dtype=cp.float32, use_cpu=False):
     """
     Generates synthetic examples to balance classes to the specified number of examples per class.
 
     Arguments:
+
     x_train -- Input dataset (examples) - cupy array format
+
     y_train -- Class labels (one-hot encoded) - cupy array format
+
     target_samples_per_class -- Desired number of samples per class
+
     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)
 
+    use_cpu (bool): If True, output will be same cpu's manuel_balancer function. Default: False.
+
     Returns:
     x_balanced -- Balanced input dataset (cupy array format)
     y_balanced -- Balanced class labels (one-hot encoded, cupy array format)
@@ -176,8 +193,13 @@ def manuel_balancer(x_train, y_train, target_samples_per_class, dtype=cp.float32
         num_samples = len(class_indices)
         
         if num_samples > target_samples_per_class:
-      
-            selected_indices = cp.random.choice(class_indices, target_samples_per_class, replace=False)
+            
+            if use_cpu:
+                selected_indices = np.random.choice(
+                    class_indices, target_samples_per_class, replace=False)
+            else:
+                selected_indices = cp.random.choice(class_indices, target_samples_per_class, replace=False)
+
             x_balanced.append(x_train[selected_indices])
             y_balanced.append(y_train[selected_indices])
             
@@ -193,13 +215,19 @@ def manuel_balancer(x_train, y_train, target_samples_per_class, dtype=cp.float32
                 additional_labels = cp.zeros((samples_to_add, y_train.shape[1]))
                 
                 for i in range(samples_to_add):
+                    
+                    if use_cpu:
+                        random_indices = np.random.choice(class_indices.get(), 2, replace=False)
+                    else:
+                        random_indices = cp.random.choice(class_indices, 2, replace=False)
 
-                    random_indices = cp.random.choice(class_indices, 2, replace=False)
                     sample1 = x_train[random_indices[0]]
                     sample2 = x_train[random_indices[1]]
 
-                    
-                    synthetic_sample = sample1 + (sample2 - sample1) * cp.random.rand()
+                    if use_cpu:
+                        synthetic_sample = sample1 + (sample2 - sample1) * np.random.rand()
+                    else:
+                        synthetic_sample = sample1 + (sample2 - sample1) * cp.random.rand()
 
                     additional_samples[i] = synthetic_sample
                     additional_labels[i] = y_train[class_indices[0]]
@@ -214,7 +242,7 @@ def manuel_balancer(x_train, y_train, target_samples_per_class, dtype=cp.float32
     return x_balanced, y_balanced
 
 
-def auto_balancer(x_train, y_train, dtype=cp.float32):
+def auto_balancer(x_train, y_train, dtype=cp.float32, use_cpu=False):
 
     """
    Function to balance the training data across different classes.
@@ -226,6 +254,8 @@ def auto_balancer(x_train, y_train, dtype=cp.float32):
    
    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)
 
+   use_cpu (bool): If True, output will be same cpu's auto_balancer function. Default: False.
+   
    Returns:
    tuple: A tuple containing balanced input data and labels.
     """
@@ -248,44 +278,50 @@ def auto_balancer(x_train, y_train, dtype=cp.float32):
     classes = cp.arange(y_train.shape[1])
     class_count = len(classes)
     
-    try:
-        ClassIndices = {i: cp.where(cp.array(y_train)[:, i] == 1)[
-            0] for i in range(class_count)}
-        classes = [len(ClassIndices[i]) for i in range(class_count)]
-
-        if len(set(classes)) == 1:
-            print(Fore.WHITE + "INFO: Data have already balanced. from: auto_balancer" + Style.RESET_ALL)
-            return x_train, y_train
-
-        MinCount = min(classes)
-
-        BalancedIndices = []
-        for i in tqdm(range(class_count),leave=False, ascii="▱▰",
-            bar_format= bar_format, desc='Balancing Data',ncols=70):
-            if len(ClassIndices[i]) > MinCount:
+   
+    ClassIndices = {i: cp.where(cp.array(y_train)[:, i] == 1)[
+        0] for i in range(class_count)}
+    classes = [len(ClassIndices[i]) for i in range(class_count)]
+
+    if len(set(classes)) == 1:
+        print(Fore.WHITE + "INFO: Data have already balanced. from: auto_balancer" + Style.RESET_ALL)
+        return x_train, y_train
+
+    MinCount = min(classes)
+
+    BalancedIndices = []
+    for i in tqdm(range(class_count),leave=False, ascii="▱▰",
+        bar_format= bar_format, desc='Balancing Data',ncols=70):
+        if len(ClassIndices[i]) > MinCount:
+            if use_cpu:
+                SelectedIndices = np.random.choice(
+                    ClassIndices[i].get(), MinCount, replace=False)
+            else:
                 SelectedIndices = cp.random.choice(
                     ClassIndices[i], MinCount, replace=False)
-            else:
-                SelectedIndices = ClassIndices[i]
-            BalancedIndices.extend(SelectedIndices)
-
-        BalancedInputs = [x_train[idx] for idx in BalancedIndices]
-        BalancedLabels = [y_train[idx] for idx in BalancedIndices]
+        else:
+            SelectedIndices = ClassIndices[i]
+        BalancedIndices.extend(SelectedIndices)
+            
+    BalancedInputs = [x_train[idx] for idx in BalancedIndices]
+    BalancedLabels = [y_train[idx] for idx in BalancedIndices]
 
+    if use_cpu:
+        permutation = np.random.permutation(len(BalancedInputs))
+    else:
         permutation = cp.random.permutation(len(BalancedInputs))
-        BalancedInputs = cp.array(BalancedInputs)[permutation]
-        BalancedLabels = cp.array(BalancedLabels)[permutation]
 
-        print(Fore.GREEN + "Data Succesfully Balanced from: " + str(len(x_train)
-                                                                                 ) + " to: " + str(len(BalancedInputs)) + ". from: auto_balancer " + Style.RESET_ALL)
-    except:
-        print(Fore.RED + "ERROR: Inputs and labels must be same length check parameters")
-        sys.exit()
+    BalancedInputs = cp.array(BalancedInputs)[permutation]
+    BalancedLabels = cp.array(BalancedLabels)[permutation]
 
+    print(Fore.GREEN + "Data Succesfully Balanced from: " + str(len(x_train)
+                                                                                ) + " to: " + str(len(BalancedInputs)) + ". from: auto_balancer " + Style.RESET_ALL)
+
+        
     return BalancedInputs, BalancedLabels
 
 
-def synthetic_augmentation(x_train, y_train, dtype=cp.float32):
+def synthetic_augmentation(x_train, y_train, dtype=cp.float32, use_cpu=False):
     """
     Generates synthetic examples to balance classes with fewer examples using CuPy.
     Arguments:
@@ -296,6 +332,8 @@ def synthetic_augmentation(x_train, y_train, dtype=cp.float32):
     
     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)
     
+    use_cpu (bool): If True, output will be same cpu's synthetic_augmentation function. Default: False.
+
     Returns:
     x_train_balanced -- Balanced input dataset (cupy array format)
     y_train_balanced -- Balanced class labels (one-hot encoded, cupy array format)
@@ -336,13 +374,21 @@ def synthetic_augmentation(x_train, y_train, dtype=cp.float32):
         
         if num_samples < max_class_count:
             while num_samples < max_class_count:
-                random_indices = cp.random.choice(
+                if use_cpu:
+                    random_indices = np.random.choice(
+                        class_indices, 2, replace=False)
+                else:
+                    random_indices = cp.random.choice(
                     cp.array(class_indices), 2, replace=False)
                 sample1 = x[random_indices[0]]
                 sample2 = x[random_indices[1]]
                 
-                synthetic_sample = sample1 + \
-                    (sample2 - sample1) * cp.random.rand()
+                if use_cpu:
+                    synthetic_sample = sample1 + \
+                        (sample2 - sample1) * np.random.rand()
+                else:
+                    synthetic_sample = sample1 + \
+                        (sample2 - sample1) * cp.random.rand()
                 
                 x_balanced.append(synthetic_sample)
                 y_balanced.append(y[class_indices[0]])
@@ -353,6 +399,7 @@ def synthetic_augmentation(x_train, y_train, dtype=cp.float32):
     
     return x_balanced, y_balanced
 
+
 def standard_scaler(x_train=None, x_test=None, scaler_params=None, dtype=cp.float32):
     """
     Standardizes training and test datasets. x_test may be None.

pyerualjetwork/model_operations_cuda.py

@@ -56,7 +56,7 @@ def save_model(model_name,
 
     class_count = W.shape[0]
 
-    if test_acc != None:
+    if test_acc is not None:
         test_acc= float(test_acc)
 
     if weights_type != 'txt' and weights_type != 'npy' and weights_type != 'mat' and weights_type != 'pkl':
@@ -70,7 +70,6 @@ def save_model(model_name,
     NeuronCount = 0
     SynapseCount = 0
 
-
     try:
             NeuronCount += cp.shape(W)[0] + cp.shape(W)[1]
             SynapseCount += cp.shape(W)[0] * cp.shape(W)[1]
@@ -91,6 +90,9 @@ def save_model(model_name,
 
                 scaler_params.append(' ')
 
+        scaler_params[0] = scaler_params[0].get()
+        scaler_params[1] = scaler_params[1].get()
+
     data = {'MODEL NAME': model_name,
             'MODEL TYPE': model_type,
             'CLASS COUNT': class_count,

pyerualjetwork/plan.py

@@ -145,7 +145,7 @@ def fit(
 
     # Training process
     for index, inp in enumerate(x_train):
-        inp = np.array(inp, copy=False, dtype=dtype).ravel()
+        inp = np.array(inp, copy=False).ravel()
         y_decoded = decode_one_hot(y_train)
         # Weight updates
         STPW = feed_forward(inp, STPW, is_training=True, Class=y_decoded[index], activation_potentiation=activation_potentiation, LTD=LTD)
@@ -231,7 +231,7 @@ def learner(x_train, y_train, x_test=None, y_test=None, strategy='accuracy', bat
         tuple: A list for model parameters: [Weight matrix, Test loss, Test Accuracy, [Activations functions]].
     
     """
-    print(Fore.WHITE + "\nRemember, optimization on large datasets can be very time-consuming and computationally expensive. Therefore, if you are working with such a dataset, our recommendation is to include activation function: ['circular'] in the 'except_this' parameter unless absolutely necessary, as they can significantly prolong the process. from: learner\n" + Fore.RESET)
+    print(Fore.WHITE + "\nRemember, optimization on large datasets can be very time-consuming and computationally expensive. Therefore, if you are working with such a dataset, our recommendation is to include activation function: ['circular', 'spiral'] in the 'except_this' parameter unless absolutely necessary, as they can significantly prolong the process. from: learner\n" + Fore.RESET)
 
     activation_potentiation = all_activations()
 

pyerualjetwork/plan_cuda.py

@@ -146,7 +146,7 @@ def fit(
 
     # Training process
     for index, inp in enumerate(x_train):
-        inp = cp.array(inp).ravel()
+        inp = cp.array(inp, copy=False).ravel()
         y_decoded = decode_one_hot(y_train)
         # Weight updates
         STPW = feed_forward(inp, STPW, is_training=True, Class=y_decoded[index], activation_potentiation=activation_potentiation, LTD=LTD)
@@ -232,7 +232,7 @@ def learner(x_train, y_train, x_test=None, y_test=None, strategy='accuracy', bat
         tuple: A list for model parameters: [Weight matrix, Preds, Accuracy, [Activations functions]]. You can acces this parameters in model_operations module. For example: model_operations.get_weights() for Weight matrix.
     
     """
-    print(Fore.WHITE + "\nRemember, optimization on large datasets can be very time-consuming and computationally expensive. Therefore, if you are working with such a dataset, our recommendation is to include activation function: ['circular'] in the 'except_this' parameter unless absolutely necessary, as they can significantly prolong the process. from: learner\n" + Fore.RESET)
+    print(Fore.WHITE + "\nRemember, optimization on large datasets can be very time-consuming and computationally expensive. Therefore, if you are working with such a dataset, our recommendation is to include activation function: ['circular', 'spiral'] in the 'except_this' parameter unless absolutely necessary, as they can significantly prolong the process. from: learner\n" + Fore.RESET)
 
     activation_potentiation = all_activations()
 
@@ -297,9 +297,9 @@ def learner(x_train, y_train, x_test=None, y_test=None, strategy='accuracy', bat
 
     # Initialize progress bar
     if batch_size == 1:
-        ncols = 90
+        ncols = 85
     else:
-        ncols = 103
+        ncols = 98
     progress = initialize_loading_bar(total=len(activation_potentiation), desc="", ncols=ncols, bar_format=bar_format_learner)
 
     # Initialize variables

pyerualjetwork/planeat.py

@@ -15,10 +15,10 @@ import random
 from tqdm import tqdm
 
 ### LIBRARY IMPORTS ###
-from plan import feed_forward
-from data_operations import normalization
-from ui import loading_bars
-from activation_functions import apply_activation, all_activations
+from .plan import feed_forward
+from .data_operations import normalization
+from .ui import loading_bars
+from .activation_functions import apply_activation, all_activations
 
 def define_genomes(input_shape, output_shape, population_size, dtype=np.float32):
    """

pyerualjetwork/planeat_cuda.py

@@ -16,10 +16,10 @@ import random
 from tqdm import tqdm
 
 ### LIBRARY IMPORTS ###
-from plan_cuda import feed_forward
-from data_operations_cuda import normalization
-from ui import loading_bars
-from activation_functions_cuda import apply_activation, all_activations
+from .plan_cuda import feed_forward
+from .data_operations_cuda import normalization
+from .ui import loading_bars
+from .activation_functions_cuda import apply_activation, all_activations
 
 def define_genomes(input_shape, output_shape, population_size, dtype=cp.float32):
    """

{pyerualjetwork-4.0.9.dist-info → pyerualjetwork-4.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.0.9
+Version: 4.1.1
 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-4.0.9.dist-info → pyerualjetwork-4.1.1.dist-info}/RECORD

@@ -1,23 +1,23 @@
-pyerualjetwork/__init__.py,sha256=uZmH51cnYfltC9nx5AYHXyAXxiWAXcLzjiCJ7K0uO_4,2542
+pyerualjetwork/__init__.py,sha256=-sXxmc1Kgkyw7AHtIrteMR-wA4vafdHZ5Ds7TFRbt3c,2542
 pyerualjetwork/activation_functions.py,sha256=UeuuagJWcSoFfmwikDU7O8ph--oySnWDJNqKbEh4SlE,12043
-pyerualjetwork/activation_functions_cuda.py,sha256=5F49gKkiRngo0hAaS1KfarxQ7wEyub13WAX_apxf8j8,12069
+pyerualjetwork/activation_functions_cuda.py,sha256=6pdCthpiGmnMwRfuduGsvwN8cNv3UKNUPOjscxyAWqE,12075
 pyerualjetwork/data_operations.py,sha256=rnOYLLK3YnRdWpEsEQABU0RE950lQQI7971eBLBpqOQ,16536
-pyerualjetwork/data_operations_cuda.py,sha256=8jooTsRCC-pEYvtw8c6CsfUUnztDy8DI8-yLf9aX27A,17108
+pyerualjetwork/data_operations_cuda.py,sha256=FBcZloHAyzuJnF2L1yJY1PS-3VJ8zlq5pgfxr8z0oKc,18768
 pyerualjetwork/help.py,sha256=pZs7hIhgFkovGLle97d9Qu9m5zKhMh7-OAIphIoSxBg,830
 pyerualjetwork/loss_functions.py,sha256=6PyBI232SQRGuFnG3LDGvnv_PUdWzT2_2mUODJiejGI,618
 pyerualjetwork/loss_functions_cuda.py,sha256=C93IZJcrOpT6HMK9x1O4AHJWXYTkN5WZiqdssPbvAPk,617
 pyerualjetwork/metrics.py,sha256=q7MkhnZDRbCjFBDDfUgrl8lBYnUT_1ro1LxeBq105pI,6077
 pyerualjetwork/metrics_cuda.py,sha256=TCwn5Z_4jQjqPCURX_xtcz9cjsYVzlahgKDA-qCgpU4,5072
 pyerualjetwork/model_operations.py,sha256=k_53BJladPm9fBWdlVpS6Uf5IQzpNlJWLH746DXGq_M,13036
-pyerualjetwork/model_operations_cuda.py,sha256=Guo0lFaaLiAXwKmnOi8Fz_bL_p38qR46CIhGOg_V1Sw,13138
-pyerualjetwork/plan.py,sha256=iF0zIaO2KrPYF8G__-Q2wMYbgQEIdRWap3BBMRZ1Fpo,34746
-pyerualjetwork/plan_cuda.py,sha256=Yke5vsmhrsKIpCOYoPNBqLzBHfjqsXuT7RrmMXNNmQc,34541
-pyerualjetwork/planeat.py,sha256=8cwWboJtXgFTKq6nFl1T9McbLDmBquKUr12y168PmcM,39513
-pyerualjetwork/planeat_cuda.py,sha256=boN-HFwm_D9cT1z0eAR8zgkiD_XOg-J2T2jNFvZweG4,39570
+pyerualjetwork/model_operations_cuda.py,sha256=-_klhwLo3z3bLIm5LXjgXGW657R203ty-Po-5wDuJBM,13244
+pyerualjetwork/plan.py,sha256=-3v0PNNlxL1gx8CTMdvD7HgtJSZt8lEPh7hceIILdDk,34743
+pyerualjetwork/plan_cuda.py,sha256=0Q7xF657xGd03W3Kjqev8Ig1IrolI_ZAlOJuuK0NugI,34562
+pyerualjetwork/planeat.py,sha256=6uEcCF4bV1_W1aQUTKQjfnDgWp6rP2oluKFo5Y37k7o,39517
+pyerualjetwork/planeat_cuda.py,sha256=GXYt_00rDKkDKJrhjE8hHOtu4U_pQZM1yZ6XrMpQo2c,39574
 pyerualjetwork/ui.py,sha256=wu2BhU1k-w3Kcho5Jtq4SEKe68ftaUeRGneUOSCVDjU,575
 pyerualjetwork/visualizations.py,sha256=DvbiQGlvlKNAgBJ3O3ukAi6uxSheha9SRFh5YX7ZxIA,26678
 pyerualjetwork/visualizations_cuda.py,sha256=dA0u85ZIyKqjtoSJ6p3EbEpJs4V4vS5W5ftR6eif8yg,26713
-pyerualjetwork-4.0.9.dist-info/METADATA,sha256=Lcj4n5zrTRr_NnHyPJhqu8CvNRLc7TgbD9qRF7Rt07s,6357
-pyerualjetwork-4.0.9.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-4.0.9.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-4.0.9.dist-info/RECORD,,
+pyerualjetwork-4.1.1.dist-info/METADATA,sha256=K05q0B1Ltsa7LpwTN0yJkFA3HBAimFvfX3vzLMRo0rA,6357
+pyerualjetwork-4.1.1.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-4.1.1.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-4.1.1.dist-info/RECORD,,