pyerualjetwork 2.4.8__py3-none-any.whl → 2.4.9__py3-none-any.whl

plan/__init__.py

@@ -0,0 +1,5 @@
+# pyerualjetwork/PLAN/__init__.py
+
+# Bu dosya, plan modülünün ana giriş noktasıdır.
+
+from .plan 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, manuel_balancer, weight_normalization

plan_di/plan_di.py → plan/plan.py

@@ -20,9 +20,9 @@ import seaborn as sns
 
 def fit(
     x_train: List[Union[int, float]],
-    # At least two.. and one hot encoded
     y_train: List[Union[int, float, str]], # At least two.. and one hot encoded
-    show_training
+    show_training,
+    activation_potential=None # (float): Input activation potential (optional)
 ) -> str:
 
     infoPLAN = """
@@ -32,11 +32,18 @@ def fit(
         x_train (list[num]): List of input data.
         y_train (list[num]): List of y_train. (one hot encoded)
         show_training (bool, str): True, None or 'final'
-    
+        activation_potential (float): Input activation potential (optional)
     Returns:
         list([num]): (Weight matrices list, train_predictions list, Train_acc).
         error handled ?: Process status ('e')
 """
+    
+    if activation_potential != None:
+    
+        if activation_potential < 0 or activation_potential > 1:
+            
+            print(Fore.RED + "ERROR101: ACTIVATION potential value must be in range 0-1. from: fit",infoPLAN)
+            return 'e'
 
     if len(x_train) != len(y_train):
         print(Fore.RED + "ERROR301: x_train list and y_train list must be same length. from: fit", infoPLAN)
@@ -83,14 +90,12 @@ def fit(
             neural_layer = normalization(neural_layer)
 
             if Layer == 'fex':
-                W[Lindex] = fex(neural_layer, W[Lindex], True, y[index])
+                W[Lindex] = fex(neural_layer, W[Lindex], True, y[index], activation_potential)
 
         for i, w in enumerate(W):
                 trained_W[i] = trained_W[i] + w
 
-                if show_training == True:
-            
-                    fig, ax = plt.subplots(1, len(class_count), figsize=(18, 14))
+                if show_training == True or 'final':
                     
                     try:
                         row = x_train[1].shape[0]
@@ -103,25 +108,29 @@ def fit(
                         try:
                             row, col = find_numbers(len(x_train[0]))
                             
-                        except:  
+                        except:
                         
                           print(Fore.RED + 'ERROR: Change show_training to None. Input length cannot be reshaped', infoPLAN + Style.RESET_ALL)
                           return 'e'
                         
                         
-                    for j in range(len(class_count)):
-             
-                        mat = trained_W[0][j,:].reshape(row, col)
-   
-                        ax[j].imshow(mat, interpolation='sinc', cmap='viridis')
-                        ax[j].set_aspect('equal')
-                        
-                        ax[j].set_xticks([])
-                        ax[j].set_yticks([])  
-                        ax[j].set_title(f'{j+1}. Neuron')
-               
-               
-                    plt.show()
+                    if show_training == True:
+                    
+                        fig, ax = plt.subplots(1, len(class_count), figsize=(18, 14))
+
+                        for j in range(len(class_count)):
+                 
+                            mat = trained_W[0][j,:].reshape(row, col)
+       
+                            ax[j].imshow(mat, interpolation='sinc', cmap='viridis')
+                            ax[j].set_aspect('equal')
+                            
+                            ax[j].set_xticks([])
+                            ax[j].set_yticks([])  
+                            ax[j].set_title(f'{j+1}. Neuron')
+                   
+                   
+                        plt.show()
          
         W = weight_identification(
             len(layers) - 1, len(class_count), neurons, x_train_size)
@@ -154,14 +163,9 @@ def fit(
         except:
         
             print(Fore.MAGENTA + 'WARNING: You try train showing but inputs is raveled. x_train inputs should be reshaped for training_show.', infoPLAN + Style.RESET_ALL)
-            
-            try:
-                row, col = find_numbers(len(x_train[0]))
-                           
-            except:  
-                print(Fore.RED + 'ERROR: Change show_training to None. Input length cannot be reshaped', infoPLAN + Style.RESET_ALL)
-                return 'e'
-            
+
+            row, col = find_numbers(len(x_train[0]))
+
         for j in range(len(class_count)):
 
             mat = trained_W[0][j,:].reshape(row, col)
@@ -266,7 +270,8 @@ def fex(
     Input,               # list[num]: Input data.
     w,                   # num: Weight matrix of the neural network.
     is_training,        # bool: Flag indicating if the function is called during training (True or False).
-    Class               # int: Which class is, if training.
+    Class,               # int: Which class is, if training.
+    activation_potential # float or None: Input activation potential (optional)
 ) -> tuple:
     """
     Applies feature extraction process to the input data using synaptic pruning.
@@ -276,22 +281,42 @@ def fex(
         w (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.
+        activation_potential (float or None): Threshold value for comparison. (optional)
 
     Returns:
         tuple: A tuple (vector) containing the neural layer result and the updated weight matrix.
     """
 
-    if is_training == True:
-
+    if is_training == True and activation_potential == None:
+        
         w[Class, :] = Input
 
         return w
 
-    else:
-
-        neural_layer = np.dot(w, Input)
-
-        return neural_layer
+    elif is_training == True and activation_potential != None:
+   
+            
+            Input[Input < activation_potential] = 0
+            Input[Input > activation_potential] = 1
+            
+            w[Class,:] = Input
+        
+            return w
+           
+    elif is_training == False and activation_potential == None:
+        
+            neural_layer = np.dot(w, Input)
+     
+            return neural_layer
+        
+    elif is_training == False and activation_potential != None:
+        
+            Input[Input < activation_potential] = 0
+            Input[Input > activation_potential] = 1
+        
+            neural_layer = np.dot(w, Input)
+        
+            return neural_layer
 
 
 
@@ -368,7 +393,8 @@ def evaluate(
     x_test,         # list[num]: Test input data.
     y_test,         # list[num]: Test labels.
     show_metrices,      # show_metrices (bool): (True or False)
-    W                  # list[num]: Weight matrix list of the neural network.
+    W,               # list[num]: Weight matrix list of the neural network.
+    activation_potential=None # activation_potential (float or None): Threshold value for comparison. (optional)
 ) -> tuple:
     infoTestModel = """
     Tests the neural network model with the given test data.
@@ -378,6 +404,7 @@ def evaluate(
         y_test (list[num]): Test labels.
         show_metrices (bool): (True or False)
         W (list[num]): Weight matrix list of the neural network.
+        activation_potential (float or None): Threshold value for comparison. (optional)
 
     Returns:
         tuple: A tuple containing the predicted labels and the accuracy of the model.
@@ -408,7 +435,7 @@ def evaluate(
                 neural_layer = normalization(neural_layer)
     
                 if Layer == 'fex':
-                    neural_layer = fex(neural_layer, W[index], False, None)
+                    neural_layer = fex(neural_layer, W[index], False, None, activation_potential)
                 elif Layer == 'cat':
                     neural_layer = np.dot(W[index], neural_layer)
     
@@ -483,7 +510,8 @@ def multiple_evaluate(
     x_test,         # list[num]: Test input data.
     y_test,         # list[num]: Test labels.
     show_metrices,      # show_metrices (bool): Visualize test progress ? (True or False)
-    MW                  # list[list[num]]: Weight matrix of the neural network.
+    MW,                  # list[list[num]]: Weight matrix of the neural network.
+    activation_potential=None # (float or None): Threshold value for comparison. (optional)
 ) -> tuple:
     infoTestModel = """
     Tests the neural network model with the given test data.
@@ -530,7 +558,7 @@ def multiple_evaluate(
                     neural_layer = normalization(neural_layer)
 
                     if Layer == 'fex':
-                        neural_layer = fex(neural_layer, W[index], False, None)
+                        neural_layer = fex(neural_layer, W[index], False, None, activation_potential)
                     elif Layer == 'cat':
                         neural_layer = np.dot(W[index], neural_layer)
 
@@ -614,7 +642,8 @@ def save_model(model_name,
                weights_format,
                model_path,
                scaler_params,
-               W
+               W,
+               activation_potential=None
                ):
 
     infosave_model = """
@@ -630,6 +659,7 @@ def save_model(model_name,
     model_path (str): Path where the model will be saved. For example: C:/Users/beydili/Desktop/denemePLAN/
     scaler_params (int, float): standard scaler params list: mean,std. If not used standard scaler then be: None.
     W: Weights of the model.
+    activation_potential (float or None): Threshold value for comparison. (optional)
     
     Returns:
     str: Message indicating if the model was saved successfully or encountered an error.
@@ -678,7 +708,8 @@ def save_model(model_name,
             'WEIGHTS TYPE': weights_type,
             'WEIGHTS FORMAT': weights_format,
             'MODEL PATH': model_path,
-            'STANDARD SCALER': scaler_params
+            'STANDARD SCALER': scaler_params,
+            'ACTIVATION POTENTIAL': activation_potential
             }
     try:
 
@@ -819,14 +850,18 @@ def predict_model_ssd(Input, model_name, model_path):
     Arguments:
     Input (list or ndarray): Input data for the model (single vector or single matrix).
     model_name (str): Name of the model.
-    model_path (str): Path where the model is saved.
     Returns:
     ndarray: Output from the model.
     """
     W, df = load_model(model_name, model_path)
 
     scaler_params = str(df['STANDARD SCALER'].iloc[0])
-
+    activation_potential = str(df['ACTIVATION POTENTIAL'].iloc[0])
+    
+    if activation_potential != 'None':
+        
+        activation_potential = float(activation_potential)
+        
     if scaler_params != None:
 
         Input = standard_scaler(None, Input, scaler_params)
@@ -845,7 +880,7 @@ def predict_model_ssd(Input, model_name, model_path):
             neural_layer = normalization(neural_layer)
 
             if Layer == 'fex':
-                neural_layer = fex(neural_layer, W[index], False, None)
+                neural_layer = fex(neural_layer, W[index], False, None, activation_potential)
             elif Layer == 'cat':
                 neural_layer = np.dot(W[index], neural_layer)
     except:
@@ -857,7 +892,7 @@ def predict_model_ssd(Input, model_name, model_path):
     return neural_layer
 
 
-def predict_model_ram(Input, scaler_params, W):
+def predict_model_ram(Input, scaler_params, W, activation_potential=None):
 
     infopredict_model_ram = """
     Function to make a prediction using a divided pruning learning artificial neural network (PLAN).
@@ -867,6 +902,7 @@ def predict_model_ram(Input, scaler_params, W):
     Input (list or ndarray): Input data for the model (single vector or single matrix).
     scaler_params (int, float): standard scaler params list: mean,std. If not used standard scaler then be: None.
     W (list of ndarrays): Weights of the model.
+    activation_potential (float or None): Threshold value for comparison. (optional)
 
     Returns:
     ndarray: Output from the model.
@@ -890,7 +926,7 @@ def predict_model_ram(Input, scaler_params, W):
             neural_layer = normalization(neural_layer)
 
             if Layer == 'fex':
-                neural_layer = fex(neural_layer, W[index], False, None)
+                neural_layer = fex(neural_layer, W[index], False, None, activation_potential)
             elif Layer == 'cat':
                 neural_layer = np.dot(W[index], neural_layer)
 

{pyerualjetwork-2.4.8.dist-info → pyerualjetwork-2.4.9.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 2.4.8
-Summary: show_training parameter added for fit function[True, 'final' or any]. Code improvements
+Version: 2.4.9
+Summary: plan_di and plan_bi merged to 'plan'. use 'import plan
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com
 Keywords: model evaluation,classifcation,pruning learning artficial neural networks

pyerualjetwork-2.4.9.dist-info/RECORD

@@ -0,0 +1,6 @@
+plan/__init__.py,sha256=gmaz8lnQfl18MbOQwabBUPmShajK5S99jfyY-hQe8tc,502
+plan/plan.py,sha256=vJRHBcDUPJNAE_5PGQBu0z7CiFFDXO7Cal3udtUIUAo,52965
+pyerualjetwork-2.4.9.dist-info/METADATA,sha256=GS9lnkixHFWcYP1L2bxp_LaOTcEC0tFeeiEo9mXB_20,276
+pyerualjetwork-2.4.9.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-2.4.9.dist-info/top_level.txt,sha256=G0Al3HuNJ88434XneyDtRKAIUaLCizOFYFYNhd7e2OM,5
+pyerualjetwork-2.4.9.dist-info/RECORD,,

pyerualjetwork-2.4.9.dist-info/top_level.txt

@@ -0,0 +1 @@
+plan

plan_bi/__init__.py

@@ -1,5 +0,0 @@
-# pyerualjetwork/PLAN/__init__.py
-
-# Bu dosya, plan modülünün ana giriş noktasıdır.
-
-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, manuel_balancer, weight_normalization