pyerualjetwork 2.2.3__py3-none-any.whl → 2.2.4__py3-none-any.whl

plan_bi/__init__.py

@@ -2,4 +2,4 @@
 
 # Bu dosya, plan modülünün ana giriş noktasıdır.
 
-from .plan_bi import auto_balancer, normalization, Softmax, Sigmoid, Relu, synaptic_pruning, synaptic_dividing, weight_identification, fex, cat, fit, evaluate, save_model, load_model, predict_model_ssd, predict_model_ram, get_weights, get_df, get_preds, get_acc, get_pot, synthetic_augmentation, standard_scaler, multiple_evaluate, encode_one_hot, split, metrics, decode_one_hot, roc_curve, confusion_matrix, plot_evaluate
+from .plan_bi import auto_balancer, normalization, Softmax, Sigmoid, Relu, weight_identification, fex, fit, evaluate, save_model, load_model, predict_model_ssd, predict_model_ram, get_weights, get_df, get_preds, get_acc, get_pot, synthetic_augmentation, standard_scaler, multiple_evaluate, encode_one_hot, split, metrics, decode_one_hot, roc_curve, confusion_matrix, plot_evaluate

plan_bi/plan_bi.py

@@ -59,7 +59,6 @@ def fit(
     x_train_size = len(x_train[0])
     
     W = weight_identification(len(layers) - 1,len(class_count),neurons,x_train_size)
-    Divides, Piece = synaptic_dividing(len(class_count),W)
     trained_W = [1] * len(W)
     print(Fore.GREEN + "Train Started with 0 ERROR" + Style.RESET_ALL,)
     start_time = time.time()
@@ -72,19 +71,6 @@ def fit(
             print(Fore.RED +"ERROR304: All input matrices or vectors in x_train list, must be same size. from: fit",infoPLAN + Style.RESET_ALL)
             return 'e'
         
-        
-        for Ulindex, Ul in enumerate(class_count):
-            
-            if Ul == y_train[index]:
-                for Windex, w in enumerate(W):
-                    for i, ul in enumerate(Ul):
-                        if ul == 1.0:
-                            k = i
-
-                    cs = Divides[int(k)][Windex][0]
-
-       
-                    W[Windex] = synaptic_pruning(w, cs, 'row', int(k), len(class_count), Piece[Windex], True)
 
         neural_layer = inp
         
@@ -94,7 +80,7 @@ def fit(
             neural_layer = normalization(neural_layer)
 
             if Layer == 'fex':
-                W[Lindex] = fex(neural_layer, W[Lindex], activation_potential, Piece[Windex], True, y)
+                W[Lindex] = fex(neural_layer, W[Lindex], activation_potential, True, y)
                 
         
         for i, w in enumerate(W):
@@ -173,114 +159,12 @@ def weight_identification(
     W[len(W) - 1] = np.eye(class_count)
 
     return W
-
-def synaptic_pruning(
-    w,            # list[num]: Weight matrix of the neural network.
-    cs,           # int: cs = cut_start, Synaptic connections between neurons.
-    key,          # int: key for identifying synaptic connections.
-    Class,        # int: Class label for the current training instance.
-    class_count, # int: Total number of classes in the dataset.
-    piece, #  int: Which set of neurons will information be transferred to?
-    is_training # bool: Flag indicating if the function is called during training (True or False).
-    
-) -> str:
-    infoPruning = """
-    Performs synaptic pruning in a neural network model.
-
-    Args:
-        w (list[num]): Weight matrix of the neural network.
-        cs (int): Synaptic connections between neurons.
-        key (str): key for identifying synaptic row or col connections.
-        Class (int): Class label for the current training instance.
-        class_count (int): Total number of classes in the dataset.
-        piece (int): Which set of neurons will information be transferred to?
-        is_training (bool): Flag indicating if the function is called during training (True or False).
-
-    Returns:
-        numpy array: Weight matrix.
-    """
-    
-    
-    Class += 1 # because index start 0
-    
-    if  Class != 1:
-              
-        ce = cs / Class # ce(cut_end) = cs(cut_start) / current_class
-        
-        if is_training == True:
-        
-            p = piece
-                
-            for i in range(Class - 3):
-                    
-                piece+=p
-                    
-            if Class!= 2:
-                 ce += piece
-            
-        w[int(ce)-1::-1,:] = 0
-        
-        w[cs:,:] = 0
-
-    else:
-        
-        if key == 'row':
-
-            w[cs:,:] = 0
-
-        elif key == 'col':
-
-            w[:,cs] = 0
-    
-        else:
-            print(Fore.RED + "ERROR103: synaptic_pruning func's key parameter must be 'row' or 'col' from: synaptic_pruning" + infoPruning)
-            return 'e'
-       
-    return w
-
-def synaptic_dividing(
-    class_count,    # int: Total number of classes in the dataset.
-    W              # list[num]: Weight matrix list of the neural network.
-) -> str:
-    """
-    Divides the synaptic weights of a neural network model based on class count.
-
-    Args:
-        class_count (int): Total number of classes in the dataset.
-        W (list[num]): Weight matrix of the neural network.
-
-    Returns:
-        list: a 3D list holds informations of divided net and list of neuron groups separated by classes.
-    """
-
-    
-    Piece = [1] * len(W)
-    Divides = [[[0] for _ in range(len(W))] for _ in range(class_count)]
-    
-    
-    for i in range(len(W)):
-            
-            Piece[i] = int(math.floor(W[i].shape[0] / class_count))
-
-    cs = 0 
-    # j = Classes, i = Weights, [0] = CutStart.
-
-    for i in range(len(W)):
-        for j in range(class_count):
-            cs = cs + Piece[i]
-            Divides[j][i][0] = cs
-            
-        j = 0
-        cs = 0
-        
-    return Divides, Piece
         
 
 def fex(
     Input,               # list[num]: Input data.
     w,                   # list[num]: Weight matrix of the neural network.
     activation_potential, # float: Threshold value for comparison.
-    piece, # int: Which set of neurons will information be transferred to?
     is_training, # bool: Flag indicating if the function is called during training (True or False).
     Class # if is during training then which class(label) ? is isnt then put None.
 ) -> tuple:
@@ -300,55 +184,21 @@ def fex(
 
     if is_training == True:
     
-        PruneIndex = np.where(Input < activation_potential)
-        w = synaptic_pruning(w, PruneIndex, 'col', 0, 0, piece, is_training)
-        
-        input_features_index = np.where(w[Class,:] == 1)
-        w[Class,input_features_index] = Input[input_features_index]
+        Input[Input < activation_potential] = 0
+        Input[Input > activation_potential] = 1
+
+        w[Class,:] = Input
         
         return w
     
     else:
         
-        PruneIndex = np.where(Input < activation_potential)
-        w = synaptic_pruning(w, PruneIndex, 'col', 0, 0, piece, is_training)
+        Input[Input < activation_potential] = 0
         
         neural_layer = np.dot(w, Input)
         
         return neural_layer
-
-def cat(
-    Input,               # list[num]: Input data.
-    w,                   # list[num]: Weight matrix of the neural network.
-    is_training, # (bool): Flag indicating if the function is called during training (True or False).
-    Class # (int): if is during training then which class(label) ? is isnt then put None.
-) -> tuple:
-    """
-    Applies categorization process to the input data using synaptic pruning if specified.
-
-    Args:
-        Input (list[num]): Input data.
-        w (list[num]): Weight matrix of the neural network.
-        is_training (bool): Flag indicating if the function is called during training (True or False).
-        Class (int): if is during training then which class(label) ? is isnt then put None.
-    Returns:
-        tuple: A tuple containing the neural layer (vector) result and the possibly updated weight matrix.
-    """
-   
-    
-    
-    if is_training == True:
-     
-        w[Class,Class] += 1
-        
-        return w
-        
-    else:
-        
-        neural_layer = np.dot(w, Input)
     
-        return neural_layer
-
 
 def normalization(
     Input  # num: Input data to be normalized.
@@ -469,7 +319,7 @@ def evaluate(
             neural_layer = normalization(neural_layer)
 
             if layers[index] == 'fex':
-                neural_layer = fex(neural_layer, W[index],  activation_potential, None, False, None)
+                neural_layer = fex(neural_layer, W[index],  activation_potential, False, None)
             if layers[index] == 'cat':
                 neural_layer = np.dot(W[index], neural_layer)
                 
@@ -912,7 +762,7 @@ def predict_model_ssd(Input, model_name, model_path):
             neural_layer = normalization(neural_layer)
                                 
             if layers[index] == 'fex':
-                neural_layer = fex(neural_layer, W[index],  activation_potential, None, False, None)
+                neural_layer = fex(neural_layer, W[index],  activation_potential, False, None)
             if layers[index] == 'cat':
                 neural_layer = np.dot(W[index], neural_layer)
     except:
@@ -956,7 +806,7 @@ def predict_model_ram(Input, activation_potential, scaler, W):
             neural_layer = normalization(neural_layer)
                                   
             if layers[index] == 'fex':
-                neural_layer = fex(neural_layer, W[index],  activation_potential, None, False, None)
+                neural_layer = fex(neural_layer, W[index],  activation_potential, False, None)
             if layers[index] == 'cat':
                 neural_layer = np.dot(W[index], neural_layer)
                 
@@ -1492,4 +1342,4 @@ def get_acc():
 
 def get_pot():
     
-    return 1
+    return 1

plan_di/__init__.py

@@ -2,4 +2,4 @@
 
 # Bu dosya, plan modülünün ana giriş noktasıdır.
 
-from .plan_di import auto_balancer, normalization, Softmax, Sigmoid, Relu, synaptic_pruning, synaptic_dividing, weight_identification, fex, fit, evaluate, save_model, load_model, predict_model_ssd, predict_model_ram, get_weights, get_df, get_preds, get_acc, synthetic_augmentation, standard_scaler, multiple_evaluate, encode_one_hot, split, metrics, decode_one_hot, roc_curve, confusion_matrix, plot_evaluate
+from .plan_di import auto_balancer, normalization, Softmax, Sigmoid, Relu, weight_identification, fex, fit, evaluate, save_model, load_model, predict_model_ssd, predict_model_ram, get_weights, get_df, get_preds, get_acc, synthetic_augmentation, standard_scaler, multiple_evaluate, encode_one_hot, split, metrics, decode_one_hot, roc_curve, confusion_matrix, plot_evaluate

plan_di/plan_di.py

@@ -1,3 +1,6 @@
+
+import time
+from colorama import Fore
 """
 Created on Thu Jun 12 00:00:00 2024
 
@@ -59,7 +62,6 @@ def fit(
     W = weight_identification(
         len(layers) - 1, len(class_count), neurons, x_train_size)
 
-    #Divides, Piece = synaptic_dividing(len(class_count), W)
     trained_W = [1] * len(W)
     print(Fore.GREEN + "Train Started with 0 ERROR" + Style.RESET_ALL)
     start_time = time.time()
@@ -72,20 +74,7 @@ def fit(
             print(Fore.RED + "ERROR304: All input matrices or vectors in x_train list, must be same size. from: fit",
                   infoPLAN + Style.RESET_ALL)
             return 'e'
-"""
-        for Ulindex, Ul in enumerate(class_count):
-
-            if Ul == y_train[index]:
-                for Windex, w in enumerate(W):
-                    for i, ul in enumerate(Ul):
-                        if ul == 1.0:
-                            k = i
 
-                    cs = Divides[int(k)][Windex][0]
-
-                    W[Windex] = synaptic_pruning(w, cs, 'row', int(
-                        k), len(class_count), Piece[Windex], True)
-"""
         neural_layer = inp
 
         for Lindex, Layer in enumerate(layers):
@@ -169,112 +158,10 @@ def weight_identification(
     return W
 
 
-def synaptic_pruning(
-    w,            # num: Weight matrix of the neural network.
-    cs,           # int: cs = cut_start, Synaptic connections between neurons.
-    key,          # int: key for identifying synaptic connections.
-    Class,        # int: Class label for the current training instance.
-    class_count,  # int: Total number of classes in the dataset.
-    piece,  # int: Which set of neurons will information be transferred to?
-    # bool: Flag indicating if the function is called during training (True or False).
-    is_training
-
-) -> str:
-    infoPruning = """
-    Performs synaptic pruning in a neural network model.
-
-    Args:
-        w (list[num]): Weight matrix of the neural network.
-        cs (list[num]): Synaptic connections between neurons.
-        key (str): key for identifying synaptic row or col connections.
-        Class (int): Class label for the current training instance.
-        class_count (int): Total number of classes in the dataset.
-        piece (int): Which set of neurons will information be transferred to?
-        is_training (bool): Flag indicating if the function is called during training (True or False).
-
-    Returns:
-        numpy array: Weight matrix.
-    """
-
-    Class += 1  # because index start 0
-
-    if Class != 1:
-
-        ce = cs / Class  # ce(cut_end) = cs(cut_start) / current_class
-
-        if is_training == True:
-
-            p = piece
-
-            for i in range(Class - 3):
-
-                piece += p
-
-            if Class != 2:
-                ce += piece
-
-        w[int(ce)-1::-1, :] = 0
-
-        w[cs:, :] = 0
-
-    else:
-
-        if key == 'row':
-
-            w[cs:, :] = 0
-
-        elif key == 'col':
-
-            w[:, cs] = 0
-
-        else:
-            print(Fore.RED + "ERROR103: synaptic_pruning func's key parameter must be 'row' or 'col' from: synaptic_pruning" + infoPruning)
-            return 'e'
-
-    return w
-
-
-def synaptic_dividing(
-    class_count,    # int: Total number of classes in the dataset.
-    W              # list[num]: Weight matrix of the neural network.
-) -> str:
-    """
-    Divides the synaptic weights of a neural network model based on class count.
-
-    Args:
-        class_count (int): Total number of classes in the dataset.
-        W (list[num]): Weight matrix of the neural network.
-
-    Returns:
-        list: a 3D list holds informations of divided net and list of neuron groups separated by classes.
-    """
-
-    Piece = [1] * len(W)
-
-    Divides = [[[0] for _ in range(len(W))] for _ in range(class_count)]
-
-    for i in range(len(W)):
-
-        Piece[i] = int(math.floor(W[i].shape[0] / class_count))
-
-    cs = 0
-
-    for i in range(len(W)):
-        for j in range(class_count):
-            cs = cs + Piece[i]
-            Divides[j][i][0] = cs
-
-        j = 0
-        cs = 0
-
-    return Divides, Piece
-
-
 def fex(
     Input,               # list[num]: Input data.
     w,                   # num: Weight matrix of the neural network.
-    # bool: Flag indicating if the function is called during training (True or False).
-    is_training,
+    is_training,        # bool: Flag indicating if the function is called during training (True or False).
     Class               # int: Which class is, if training.
 ) -> tuple:
     """
@@ -1428,4 +1315,5 @@ def get_preds():
 
 def get_acc():
 
-    return 2
+    return 2
+

{pyerualjetwork-2.2.3.dist-info → pyerualjetwork-2.2.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 2.2.3
+Version: 2.2.4
 Summary: Code improvements (Documentation in desc. Examples in GİTHUB: https://github.com/HCB06/PyerualJetwork)
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com

pyerualjetwork-2.2.4.dist-info/RECORD

@@ -0,0 +1,8 @@
+plan_bi/__init__.py,sha256=rzDe7yWvNlwDVE6xSw8Qk51itcxT6EDBj7iiOeycxMw,475
+plan_bi/plan_bi.py,sha256=rB2AFL6hbVmdlSY9zT9fpmLtn_6-jHH6U0CL3UTVBHY,45370
+plan_di/__init__.py,sha256=Omxc07PXPQZOrXBD3PJQT6sPdni6NMykyiQgKVL_IZ0,466
+plan_di/plan_di.py,sha256=HQqc_jheT9x8NkJ9_Fvqa8EN4ehkExVy3RqvqAwPwgU,42874
+pyerualjetwork-2.2.4.dist-info/METADATA,sha256=7pltYh2VTDavGRN0w2whJ1UX_eyDmKmEbb6jzyJGY4Q,325
+pyerualjetwork-2.2.4.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-2.2.4.dist-info/top_level.txt,sha256=aaXSOcnD62fbXG1x7tw4nV50Qxx9g9zDNLK7OD4BdPE,16
+pyerualjetwork-2.2.4.dist-info/RECORD,,

pyerualjetwork-2.2.3.dist-info/RECORD

@@ -1,8 +0,0 @@
-plan_bi/__init__.py,sha256=82q8bWRYqzwMrFuViQzBg7P19i6EqdV7VYBVxuQ-LV0,517
-plan_bi/plan_bi.py,sha256=fNJK07y9JDVLU0GORD_RHKBjTUnVzb5ciYcQFpyiSvc,50490
-plan_di/__init__.py,sha256=5BCC6Wut4J5lTadds5q3P10p01FKPD4pEeNwzkpL6qo,503
-plan_di/plan_di.py,sha256=mzTfunaEqbgQtBOVtd9tCRXT5ujupHwhilwWuk6fVGg,46270
-pyerualjetwork-2.2.3.dist-info/METADATA,sha256=iltDA-AwbGfBBSYtL3Tpxw8YMxUTHlzibrvPxZ0xPLA,325
-pyerualjetwork-2.2.3.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-2.2.3.dist-info/top_level.txt,sha256=aaXSOcnD62fbXG1x7tw4nV50Qxx9g9zDNLK7OD4BdPE,16
-pyerualjetwork-2.2.3.dist-info/RECORD,,