pyerualjetwork 2.6.6__tar.gz → 2.7.0__tar.gz

{pyerualjetwork-2.6.6 → pyerualjetwork-2.7.0}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 2.6.6
-Summary: Visual improvements, new option added for val paramater in fit function: 'final'. Removed: val_count parameter.
+Version: 2.7.0
+Summary: Optimized for Vs Code
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com
 Keywords: model evaluation,classifcation,potentiation learning artficial neural networks

{pyerualjetwork-2.6.6 → pyerualjetwork-2.7.0}/plan/plan.py

@@ -1,4 +1,3 @@
-
 # -*- coding: utf-8 -*-
 """
 Created on Tue Jun 18 23:32:16 2024
@@ -23,12 +22,13 @@ from tqdm import tqdm
 def fit(
     x_train: List[Union[int, float]],
     y_train: List[Union[int, float]], # At least two.. and one hot encoded
-    show_training,
-    show_count= None,
     val= None,
+    val_count = None,
+    activation_potentiation=None, # (float): Input activation_potentiation (optional)
     x_val= None,
     y_val= None,
-    activation_potentiation=None # (float): Input activation_potentiation (optional)
+    show_training = None,
+    show_count= None
 ) -> str:
 
     infoPLAN = """
@@ -37,33 +37,55 @@ def fit(
     Args:
         x_train (list[num]): List of input data.
         y_train (list[num]): List of target labels. (one hot encoded)
-        show_training (bool, str): True, None or'final'
-        show_count (None, int): How many learning steps in total will be displayed in a single figure? (Adjust according to your hardware) Default: 10 (optional)
-        val (None, True or 'final'): validation in training process ? None, True or 'final' Default: None
+        val (None, True or 'final'): validation in training process ? None, True or 'final' Default: None (optional)
         val_count (None, int): After how many examples learned will an accuracy test be performed? Default: 0.1 (%10) (optional)
-        x_val (list[num]): List of validation data. (optional) Default: x_train
-        y_val (list[num]): (list[num]): List of target labels. (one hot encoded) (optional) Default: y_train
         activation_potentiation (float): Input activation potentiation (for binary injection) (optional) in range: -1, 1
+        x_val (list[num]): List of validation data. (optional) Default: 10% of x_train (auto_balanced)
+        y_val (list[num]): (list[num]): List of target labels. (one hot encoded) (optional) Default: 10% of y_train (auto_balanced)
+        show_training (bool, str): True, None or'final'
+        show_count (None, int): How many learning steps in total will be displayed in a single figure? (Adjust according to your hardware) Default: 10 (optional)
     Returns:
         list([num]): (Weight matrices list, train_predictions list, Train_acc).
         error handled ?: Process status ('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)
+        print(Fore.RED + "ERROR301: x_train list and y_train list must be same length. from: fit", infoPLAN + Style.RESET_ALL)
         return 'e'
-    
-    if x_val == None and y_val == None:
-
-        x_val = x_train
-        y_val = y_train
 
     if val == True or val == 'final':
+
+        try:
+
+            if x_val == None and y_val == None:
+
+                x_train, x_val, y_train, y_val = split(x_train, y_train,test_size=0.1,random_state=42)
+
+                x_train, y_train = auto_balancer(x_train, y_train)
+                x_val, y_val = auto_balancer(x_val, y_val)
+
+                y_train, y_val = encode_one_hot(y_train, y_val)
+
+        except:
+            pass
+
+        if val == True:
+
+            if val_count == None:
+
+                val_count = 0.1
+
+            v_iter = 0
+
+        if val == 'final':
+
+            val_count = 0.99
         
-        val_bar = tqdm(total=1, desc="Training / Validating Accuracy", ncols=120)
-        
+        val_count = int(len(x_train) * val_count)
+        val_count_copy = val_count
+        val_bar = tqdm(total=1, desc="Validating Accuracy", ncols=120)
+        val_list = [] * val_count
 
     if show_count == None:
         
@@ -85,7 +107,6 @@ def fit(
 
     neurons = [len(class_count), len(class_count)]
     layers = ['fex']
-    val_list = []
 
     x_train[0] = np.array(x_train[0])
     x_train[0] = x_train[0].ravel()
@@ -98,8 +119,10 @@ def fit(
 
     y = decode_one_hot(y_train)
 
+    train_progress = tqdm(total=len(x_train),leave=False, desc="Training",ncols= 120)
+    
     for index, inp in enumerate(x_train):
-        
+
         progress = index / len(x_train) * 100
 
         inp = np.array(inp)
@@ -123,31 +146,28 @@ def fit(
                 LTPW[i] = LTPW[i] + w
 
             
-        if val == True:
+        if val == True and index == val_count:
             
-            if show_training == True:
-                try:
-                    plt.close(fig)
 
-                except:
-                    pass
+            val_count += val_count_copy
 
-            validation_model = evaluate(x_val, y_val, None, LTPW, activation_potentiation, None)
+            validation_model = evaluate(x_val, y_val, LTPW, activation_potentiation, None)
             
             val_acc = validation_model[get_acc()]
 
             val_list.append(val_acc)
             
-            if index == 0:
+            if v_iter == 0:
                 
                 val_bar.update(val_acc)
-            
-            if index != 0:
                 
-                val_acc = val_acc - val_list[index - 1]
+            
+            if v_iter != 0:
                 
+                val_acc = val_acc - val_list[v_iter - 1]
                 val_bar.update(val_acc)
                
+            v_iter += 1
 
         if show_training == True:
 
@@ -192,17 +212,18 @@ def fit(
                     title_info = 'Weight Matrix Of Fex Layer'
                     
                 
-            
+        
 
             progress_status = f"{progress:.1f}"
             fig.suptitle(suptitle_info + progress_status)
             plt.draw()
             plt.pause(0.1)
             
-                  
-        W = weight_identification(
+              
+        STPW = weight_identification(
             len(layers) - 1, len(class_count), neurons, x_train_size)
 
+        train_progress.update(1)
 
     if show_training == 'final':
             
@@ -233,9 +254,8 @@ def fit(
     
         val_list.append(val_acc)
         
-        val_bar.update(val_acc)
-                
-                
+        val_bar.update(val_acc) 
+
     return LTPW
 
 # FUNCTIONS -----
@@ -449,10 +469,10 @@ def Relu(
 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.
-    activation_potentiation=None, # activation_potentiation (float or None): Threshold value for comparison. (optional)
-    acc_bar_status = True
+    activation_potentiation=None, # activation_potentiation (float or None): Threshold value for comparison. (optional) Default: None
+    acc_bar_status=True,  # acc_bar_status (bool): Loading bar for accuracy (True or None) (optional) Default: True
+    show_metrices=None     # show_metrices (bool): (True or None) (optional) Default: None
 ) -> tuple:
     infoTestModel = """
     Tests the neural network model with the given test data.
@@ -460,10 +480,10 @@ def evaluate(
     Args:
         x_test (list[num]): Test input data.
         y_test (list[num]): Test labels.
-        show_metrices (bool): (True or False)
         W (list[num]): Weight matrix list of the neural network.
-        activation_potentiation (float or None): Threshold value for comparison. (optional)
-        acc_bar_status (bool): Loading bar for accuracy (True or None)
+        activation_potentiation (float or None): Threshold value for comparison. (optional) Default: None
+        acc_bar_status (bool): Loading bar for accuracy (True or None) (optional) Default: True
+        show_metrices (bool): (True or None) (optional) Default: None
 
     Returns:
         tuple: A tuple containing the predicted labels and the accuracy of the model.
@@ -479,25 +499,27 @@ def evaluate(
         
         for i, w in enumerate(W):
             Wc[i] = np.copy(w)
-            print('\rCopying weights.....', i+1, '/', len(W), end="")
             
-       # print(Fore.GREEN + "\n\nTest Started with 0 ERROR\n" + Style.RESET_ALL)
+            
         if acc_bar_status == True:
-            acc_bar = tqdm(total=1, desc="Test Accuracy", ncols=75)
+
+            test_progress = tqdm(total=len(x_test),leave=False, desc='Testing',ncols=120)
+            acc_bar = tqdm(total=1, desc="Test Accuracy", ncols=120)
+            
+        
         for inpIndex, Input in enumerate(x_test):
             Input = np.array(Input)
             Input = Input.ravel()
-            uni_start_time = time.time()
             neural_layer = Input
-    
+
             for index, Layer in enumerate(layers):
-    
+
                 neural_layer = normalization(neural_layer)
-    
+
                 if Layer == 'fex':
                     neural_layer = fex(neural_layer, W[index], False, None, activation_potentiation)
-    
-    
+
+
             for i, w in enumerate(Wc):
                 W[i] = np.copy(w)
             RealOutput = np.argmax(y_test[inpIndex])
@@ -505,20 +527,21 @@ def evaluate(
             if RealOutput == PredictedOutput:
                 true += 1
             acc = true / len(y_test)
-    
-    
+
+
             acc_list.append(acc)
             y_preds[inpIndex] = PredictedOutput
             
             if acc_bar_status == True:
+                test_progress.update(1)
                 if inpIndex == 0:
                     acc_bar.update(acc)
                     
                 else:
                     acc = acc - acc_list[inpIndex - 1]
                     acc_bar.update(acc)
-            
-        if show_metrices == True:   
+
+        if show_metrices == True:
             plot_evaluate(y_test, y_preds, acc_list)
         
         
@@ -530,7 +553,7 @@ def evaluate(
         print(Fore.RED + "ERROR: Are you sure weights are loaded ? from: evaluate" +
               infoTestModel + Style.RESET_ALL)
         return 'e'
-
+    
     return W, y_preds, acc
 
 
@@ -902,7 +925,7 @@ def predict_model_ssd(Input, model_name, model_path):
         
     except:
     
-        non_scaled = True
+        pass
         
 
     layers = ['fex']
@@ -931,7 +954,7 @@ def predict_model_ssd(Input, model_name, model_path):
     return neural_layer
 
 
-def predict_model_ram(Input, scaler_params, W, activation_potentiation=None):
+def predict_model_ram(Input, W, scaler_params=None, activation_potentiation=None):
 
     infopredict_model_ram = """
     Function to make a prediction using a divided potentiation learning artificial neural network (PLAN).
@@ -939,17 +962,19 @@ def predict_model_ram(Input, scaler_params, W, activation_potentiation=None):
 
     Arguments:
     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_potentiation (float or None): Threshold value for comparison. (optional)
+    scaler_params (int, float): standard scaler params list: mean,std. (optional) Default: None.
+    activation_potentiation (float or None): Threshold value for comparison. (optional) Default: None
 
     Returns:
     ndarray: Output from the model.
     """
-    
-    if scaler_params != None:
+    try:
+        if scaler_params != None:
 
-        Input = standard_scaler(None, Input, scaler_params)
+            Input = standard_scaler(None, Input, scaler_params)
+    except:
+            Input = standard_scaler(None, Input, scaler_params)
 
     layers = ['fex']
 
@@ -1005,7 +1030,7 @@ def auto_balancer(x_train, y_train):
         MinCount = min(classes)
 
         BalancedIndices = []
-        for i in range(class_count):
+        for i in tqdm(range(class_count),leave=False,desc='Balancing Data',ncols=120):
             if len(ClassIndices[i]) > MinCount:
                 SelectedIndices = np.random.choice(
                     ClassIndices[i], MinCount, replace=False)
@@ -1022,7 +1047,7 @@ def auto_balancer(x_train, y_train):
         print(Fore.RED + "ERROR: Inputs and labels must be same length check parameters" + infoauto_balancer)
         return 'e'
 
-    return BalancedInputs, BalancedLabels
+    return np.array(BalancedInputs), np.array(BalancedLabels)
 
 
 def synthetic_augmentation(x_train, y_train):
@@ -1052,7 +1077,7 @@ def synthetic_augmentation(x_train, y_train):
     x_balanced = list(x)
     y_balanced = list(y)
 
-    for class_label in range(class_count):
+    for class_label in tqdm(range(class_count), leave=False, desc='Augmenting Data',ncols= 120):
         class_indices = [i for i, label in enumerate(
             y) if np.argmax(label) == class_label]
         num_samples = len(class_indices)
@@ -1092,6 +1117,15 @@ def standard_scaler(x_train, x_test, scaler_params=None):
     tuple
       Standardized training and test datasets
   """
+    try:
+
+        x_train = x_train.tolist()
+        x_test = x_test.tolist()
+
+    except:
+
+        pass
+
     try:
             
         if scaler_params == None and x_test != None:
@@ -1175,7 +1209,6 @@ def split(X, y, test_size, random_state):
     Returns:
         tuple: x_train, x_test, y_train, y_test as ordered training and testing data subsets.
     """
-    # Size of the dataset
     num_samples = X.shape[0]
 
     if isinstance(test_size, float):
@@ -1392,7 +1425,6 @@ def plot_evaluate(y_test, y_preds, acc_list):
     
     # Confusion matrix
     cm = confusion_matrix(y_true, y_preds, len(Class))
-    # Subplot içinde düzenleme
     fig, axs = plt.subplots(2, 2, figsize=(16, 12))
     
     # Confusion Matrix
@@ -1511,16 +1543,19 @@ def manuel_balancer(x_train, y_train, target_samples_per_class):
     x_balanced -- Balanced input dataset (NumPy array format)
     y_balanced -- Balanced class labels (one-hot encoded, NumPy array format)
     """
-    start_time = time.time()
-    x_train = np.array(x_train)
-    y_train = np.array(y_train)
+    try:
+        x_train = np.array(x_train)
+        y_train = np.array(y_train)
+    except:
+        print(Fore.GREEN + "x_tarin and y_train already numpyarray." + Style.RESET_ALL)
+        pass
     classes = np.arange(y_train.shape[1])
     class_count = len(classes)
     
     x_balanced = []
     y_balanced = []
 
-    for class_label in range(class_count):
+    for class_label in tqdm(range(class_count),leave=False, desc='Augmenting Data',ncols= 120):
         class_indices = np.where(np.argmax(y_train, axis=1) == class_label)[0]
         num_samples = len(class_indices)
         
@@ -1542,8 +1577,7 @@ def manuel_balancer(x_train, y_train, target_samples_per_class):
                 additional_labels = np.zeros((samples_to_add, y_train.shape[1]))
                 
                 for i in range(samples_to_add):
-                    uni_start_time = time.time()
-                    
+
                     random_indices = np.random.choice(class_indices, 2, replace=False)
                     sample1 = x_train[random_indices[0]]
                     sample2 = x_train[random_indices[1]]
@@ -1554,41 +1588,10 @@ def manuel_balancer(x_train, y_train, target_samples_per_class):
                     additional_samples[i] = synthetic_sample
                     additional_labels[i] = y_train[class_indices[0]]
                     
-                    uni_end_time = time.time()
-                    calculating_est = round(
-               (uni_end_time - uni_start_time) * (samples_to_add - i), 3)
-    
-                    if calculating_est < 60:
-                        print('\rest......(sec):', calculating_est, '\n', end="")
-             
-                    elif calculating_est > 60 and calculating_est < 3600:
-                        print('\rest......(min):', calculating_est/60, '\n', end="")
-             
-                    elif calculating_est > 3600:
-                        print('\rest......(h):', calculating_est/3600, '\n', end="")
-             
-                    print('Augmenting: ', class_label, '/', class_count, '...', i, "/", samples_to_add, "\n", end="")
-
+                    
                 x_balanced.append(additional_samples)
                 y_balanced.append(additional_labels)
-                   
-
-    EndTime = time.time()
-
-    calculating_est = round(EndTime - start_time, 2)
- 
-    print(Fore.GREEN + " \nBalancing Finished with 0 ERROR\n" + Style.RESET_ALL)
- 
-    if calculating_est < 60:
-        print('Total balancing time(sec): ', calculating_est)
- 
-    elif calculating_est > 60 and calculating_est < 3600:
-        print('Total balancing time(min): ', calculating_est/60)
- 
-    elif calculating_est > 3600:
-        print('Total balancing time(h): ', calculating_est/3600)
     
-    # Stack the balanced arrays
     x_balanced = np.vstack(x_balanced)
     y_balanced = np.vstack(y_balanced)
 

{pyerualjetwork-2.6.6 → pyerualjetwork-2.7.0}/pyerualjetwork.egg-info/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 2.6.6
-Summary: Visual improvements, new option added for val paramater in fit function: 'final'. Removed: val_count parameter.
+Version: 2.7.0
+Summary: Optimized for Vs Code
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com
 Keywords: model evaluation,classifcation,potentiation learning artficial neural networks

{pyerualjetwork-2.6.6 → pyerualjetwork-2.7.0}/setup.py

@@ -5,10 +5,10 @@ from setuptools import setup, find_packages
 setup(
       
       name = "pyerualjetwork",
-      version = "2.6.6",
+      version = "2.7.0",
       author = "Hasan Can Beydili",
       author_email = "tchasancan@gmail.com",
-      description= "Visual improvements, new option added for val paramater in fit function: 'final'. Removed: val_count parameter.",
+      description= "Optimized for Vs Code",
       packages = find_packages(),
       keywords = ["model evaluation", "classifcation", 'potentiation learning artficial neural networks'],