pyerualjetwork 2.0.4__py3-none-any.whl → 2.0.6__py3-none-any.whl

plan/{plan.py → plan_di.py}

@@ -1,5 +1,5 @@
 """
-Created on Thu May 30 22:12:49 2024
+Created on Thu Jun 12 00:00:00 2024
 
 @author: hasan can beydili
 """
@@ -16,7 +16,6 @@ import seaborn as sns
 def fit(
     x_train: List[Union[int, float]],
     y_train: List[Union[int, float, str]], # At least two.. and one hot encoded
-    action_potential: Union[float],
 ) -> str:
         
     infoPLAN = """
@@ -25,18 +24,13 @@ def fit(
     Args:
         x_train (list[num]): List of input data.
         y_train (list[num]): List of y_train. (one hot encoded)
-        action_potential (float): Input ACTION potential 
+        activation_potential (float): Input activation potential 
     
     Returns:
-        list([num]): (Weight matrices list, train_predictions list, Trainacc).
+        list([num]): (Weight matrices list, train_predictions list, Train_acc).
         error handled ?: Process status ('e')
 """
 
-    if action_potential < 0 or action_potential > 1:
-        
-        print(Fore.RED + "ERROR101: ACTION 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)
        return 'e'
@@ -93,13 +87,15 @@ def fit(
         for Lindex, Layer in enumerate(layers):
             
             
-            neural_layer = normalization(neural_layer)
+           # neural_layer = normalization(neural_layer)
             
 
             if Layer == 'fex':
-                neural_layer,W[Lindex] = fex(neural_layer, W[Lindex], action_potential, Piece[Windex], 1)
+                y = np.argmax(y_train[index])
+
+                neural_layer,W[Lindex] = fex(neural_layer, W[Lindex], y , 1)
             elif Layer == 'cat':
-                neural_layer,W[Lindex] = cat(neural_layer, W[Lindex], action_potential, 1, Piece[Windex])
+                neural_layer,W[Lindex] = cat(neural_layer, W[Lindex], 1, Piece[Windex])
                 
         RealOutput = np.argmax(y_train[index])
         PredictedOutput = np.argmax(neural_layer)
@@ -319,8 +315,7 @@ def synaptic_dividing(
 def fex(
     Input,               # list[num]: Input data.
     w,                   # list[list[num]]: Weight matrix of the neural network.,
-    action_potential, # num: Threshold value for comparison.
-    piece, # ???
+    Class,               # Which class is, if training. num
     is_training # num: 1 or 0
 ) -> tuple:
     """
@@ -329,16 +324,16 @@ def fex(
     Args:
         Input (list[num]): Input data.
         w (list[list[num]]): Weight matrix of the neural network.
-        ACTION_threshold (str): Sign for threshold comparison ('<', '>', '==', '!=').
-        action_potential (num): Threshold value for comparison.
+        ACTIVATION_threshold (str): Sign for threshold comparison ('<', '>', '==', '!=').
+        activation_potential (num): Threshold value for comparison.
 
     Returns:
         tuple: A tuple (vector) containing the neural layer result and the updated weight matrix.
     """
-
-
-    PruneIndex = np.where(Input < action_potential)
-    w = synaptic_pruning(w, PruneIndex, 'col', 0, 0, piece, is_training)
+    
+    if is_training == 1:
+        
+        w[Class,:] = Input
 
     neural_layer = np.dot(w, Input)
     
@@ -347,7 +342,6 @@ def fex(
 def cat(
     Input,               # list[num]: Input data.
     w,                   # list[list[num]]: Weight matrix of the neural network.
-    action_potential,      # num: Threshold value for comparison.
     isTrain,
     piece              # int: Flag indicating if the function is called during training (1 for training, 0 otherwise).
 ) -> tuple:
@@ -357,8 +351,8 @@ def cat(
     Args:
         Input (list[num]): Input data.
         w (list[list[num]]): Weight matrix of the neural network.
-        ACTION_threshold (str): Sign for threshold comparison ('<', '>', '==', '!=').
-        action_potential (num): Threshold value for comparison.
+        ACTIVATION_threshold (str): Sign for threshold comparison ('<', '>', '==', '!=').
+        activation_potential (num): Threshold value for comparison.
         isTrain (int): Flag indicating if the function is called during training (1 for training, 0 otherwise).
 
     Returns:
@@ -453,7 +447,6 @@ def Relu(
 def evaluate(
     x_test,         # list[list[num]]: Test input data.
     y_test,         # list[num]: Test labels.
-    action_potential,    # list[num]: List of ACTION POTENTIALS for each layer.
     visualize,         # visualize Testing procces or not visualize ('y' or 'n')
     W                  # list[list[num]]: Weight matrix of the neural network.
 ) -> tuple:
@@ -463,7 +456,7 @@ def evaluate(
     Args:
         x_test (list[list[num]]): Test input data.
         y_test (list[num]): Test labels.
-        action_potential (float): Input ACTION potential 
+        activation_potential (float): Input activation potential 
         visualize (str): Visualize test progress ? ('y' or 'n')
         W (list[list[num]]): Weight matrix of the neural network.
 
@@ -492,12 +485,12 @@ def evaluate(
         
         for index, Layer in enumerate(layers):
             
-            neural_layer = normalization(neural_layer)
+           # neural_layer = normalization(neural_layer)
 
             if layers[index] == 'fex':
-                neural_layer = fex(neural_layer, W[index],  action_potential, 0, 0)[0]
+                neural_layer = fex(neural_layer, W[index], 0, 0)[0]
             if layers[index] == 'cat':
-                neural_layer = cat(neural_layer, W[index],  action_potential, 0, 0)[0]
+                neural_layer = cat(neural_layer, W[index], 0, 0)[0]
                 
         for i, w in enumerate(Wc):
             W[i] = np.copy(w)
@@ -572,7 +565,7 @@ def evaluate(
     
   except:
         
-        print(Fore.RED + "ERROR: Testing model parameters like 'action_potential' must be same as trained model. Check parameters. Are you sure weights are loaded ? from: evaluate" + infoTestModel + Style.RESET_ALL)
+        print(Fore.RED + "ERROR: Testing model parameters like 'activation_potential' must be same as trained model. Check parameters. Are you sure weights are loaded ? from: evaluate" + infoTestModel + Style.RESET_ALL)
         return 'e'
    
 
@@ -582,7 +575,6 @@ def evaluate(
 def save_model(model_name,
              model_type,
              class_count,
-             action_potential,
              test_acc,
              weights_type,
              weights_format,
@@ -591,13 +583,13 @@ def save_model(model_name,
  ):
     
     infosave_model = """
-    Function to save a deep learning model.
+    Function to save a pruning learning model.
 
     Arguments:
     model_name (str): Name of the model.
     model_type (str): Type of the model.(options: PLAN)
     class_count (int): Number of classes.
-    action_potential (list): List containing ACTION POTENTIALS.
+    activation_potential (float): Activation potential.
     test_acc (float): Test accuracy of the model.
     weights_type (str): Type of weights to save (options: 'txt', 'npy', 'mat').
     WeightFormat (str): Format of the weights (options: 'd', 'f', 'raw').
@@ -641,7 +633,6 @@ def save_model(model_name,
             'LAYERS': layers,
             'LAYER COUNT': len(layers),
             'CLASS COUNT': class_count,
-            'ACTION POTENTIAL': action_potential,
             'NEURON COUNT': NeuronCount,
             'SYNAPSE COUNT': SynapseCount,
             'TEST ACCURACY': test_acc,
@@ -738,7 +729,7 @@ def load_model(model_name,
              model_path,
 ):
    infoload_model = """
-   Function to load a deep learning model.
+   Function to load a pruning learning model.
 
    Arguments:
    model_name (str): Name of the model.
@@ -746,7 +737,7 @@ def load_model(model_name,
    log_type (str): Type of log to load (options: 'csv', 'txt', 'hdf5').
 
    Returns:
-   lists: W(list[num]), action_potential, df (DataFrame of the model)
+   lists: W(list[num]), activation_potential, df (DataFrame of the model)
     """
    pass
 
@@ -766,7 +757,6 @@ def load_model(model_name,
    layers = df['LAYERS'].tolist()
    layer_count = int(df['LAYER COUNT'].iloc[0])
    class_count = int(df['CLASS COUNT'].iloc[0])
-   action_potential = int(df['ACTION POTENTIAL'].iloc[0])
    NeuronCount = int(df['NEURON COUNT'].iloc[0])
    SynapseCount = int(df['SYNAPSE COUNT'].iloc[0])
    test_acc = int(df['TEST ACCURACY'].iloc[0])
@@ -788,13 +778,13 @@ def load_model(model_name,
            W[i] = sio.loadmat(model_path + model_name + str(i+1) + 'w.mat')
    else:
         raise ValueError(Fore.RED + "Incorrect weight type value. Value must be 'txt', 'npy' or 'mat' from: load_model."  + infoload_model + Style.RESET_ALL)
-   print(Fore.GREEN + "Model loaded succesfully" + Style.RESET_ALL)     
-   return W,action_potential,df
+   print(Fore.GREEN + "Model loaded succesfully" + Style.RESET_ALL)
+   return W,df
 
 def predict_model_ssd(Input,model_name,model_path):
     
     infopredict_model_ssd = """
-    Function to make a prediction using a divided pruning deep learning neural network (PLAN).
+    Function to make a prediction using a divided pruning learning artificial neural network (PLAN).
 
     Arguments:
     Input (list or ndarray): Input data for the model (single vector or single matrix).
@@ -803,7 +793,7 @@ def predict_model_ssd(Input,model_name,model_path):
     Returns:
     ndarray: Output from the model.
     """
-    W,action_potential = load_model(model_name,model_path)[0:2]
+    W = load_model(model_name,model_path)[0]
     
     layers = ['fex','cat']
     
@@ -816,12 +806,12 @@ def predict_model_ssd(Input,model_name,model_path):
         neural_layer = neural_layer.ravel()
         for index, Layer in enumerate(layers):                                                                          
 
-            neural_layer = normalization(neural_layer)
+          #  neural_layer = normalization(neural_layer)
                                 
             if layers[index] == 'fex':
-                neural_layer = fex(neural_layer, W[index], action_potential,0, 0)[0]
+                neural_layer = fex(neural_layer, W[index],0, 0)[0]
             if layers[index] == 'cat':
-                neural_layer = cat(neural_layer, W[index], action_potential, 0, 0)[0]
+                neural_layer = cat(neural_layer, W[index], 0, 0)[0]
     except:
        print(Fore.RED + "ERROR: The input was probably entered incorrectly. from: predict_model_ssd"  + infopredict_model_ssd + Style.RESET_ALL)
        return 'e'
@@ -830,15 +820,15 @@ def predict_model_ssd(Input,model_name,model_path):
     return neural_layer
 
 
-def predict_model_ram(Input,action_potential,W):
+def predict_model_ram(Input,W):
     
     infopredict_model_ram = """
-    Function to make a prediction using a pruning learning artificial neural network (PLAN)
+    Function to make a prediction using a divided pruning learning artificial neural network (PLAN).
     from weights and parameters stored in memory.
 
     Arguments:
     Input (list or ndarray): Input data for the model (single vector or single matrix).
-    action_potential (list): ACTION POTENTIAL.
+    activation_potential (float): Activation potential.
     W (list of ndarrays): Weights of the model.
 
     Returns:
@@ -856,12 +846,12 @@ def predict_model_ram(Input,action_potential,W):
         neural_layer = neural_layer.ravel()
         for index, Layer in enumerate(layers):                                                                          
 
-            neural_layer = normalization(neural_layer)
+          # neural_layer = normalization(neural_layer)
                                   
             if layers[index] == 'fex':
-                neural_layer = fex(neural_layer, W[index], action_potential,0, 0)[0]
+                neural_layer = fex(neural_layer, W[index],0, 0)[0]
             if layers[index] == 'cat':
-                neural_layer = cat(neural_layer, W[index], action_potential, 0, 0)[0]
+                neural_layer = cat(neural_layer, W[index], 0, 0)[0]
                 
     except:
         print(Fore.RED + "ERROR: Unexpected input or wrong model parameters from: predict_model_ram."  + infopredict_model_ram + Style.RESET_ALL)
@@ -941,21 +931,47 @@ def synthetic_augmentation(x, y, class_count):
         
         if num_samples < max_class_count:
             while num_samples < max_class_count:
-                # Select two random examples
+
                 random_indices = np.random.choice(class_indices, 2, replace=False)
                 sample1 = x[random_indices[0]]
                 sample2 = x[random_indices[1]]
                 
-                # Generate a new synthetic example between the two selected examples
                 synthetic_sample = sample1 + (np.array(sample2) - np.array(sample1)) * np.random.rand()
                 
                 x_balanced.append(synthetic_sample.tolist())
-                y_balanced.append(y[class_indices[0]])  # The new example has the same class label
+                y_balanced.append(y[class_indices[0]])
                 
                 num_samples += 1
     
     return np.array(x_balanced), np.array(y_balanced)
 
+def standard_scaler(x_train, x_test):
+  info_standard_scaler = """
+  Standardizes training and test datasets.
+
+  Args:
+    train_data: numpy.ndarray
+      Training data (n_samples, n_features)
+    test_data: numpy.ndarray
+      Test data (n_samples, n_features)
+
+  Returns:
+    tuple
+      Standardized training and test datasets
+  """
+  try:
+    mean = np.mean(x_train, axis=0)
+    std = np.std(x_train, axis=0)
+    
+    
+    train_data_scaled = (x_train - mean) / std
+    test_data_scaled = (x_test - mean) / std
+
+  except:
+      print(Fore.RED + "ERROR: x_train and x_test must be numpy array from standard_scaler" + info_standard_scaler)
+    
+  return train_data_scaled, test_data_scaled
+
    
 def get_weights():
         
@@ -963,7 +979,7 @@ def get_weights():
     
 def get_df():
         
-    return 2
+    return 1
     
 def get_preds():
         
@@ -975,4 +991,4 @@ def get_acc():
 
 def get_pot():
     
-    return 1
+    return 1

pyerualjetwork-2.0.6.dist-info/METADATA

@@ -0,0 +1,8 @@
+Metadata-Version: 2.1
+Name: pyerualjetwork
+Version: 2.0.6
+Summary: Advanced python deep learning library. New features: BINARY INJECTION (OLD) NOW ADDED NEW DIRECT FEATURE INJECTION. AND 'standard_scaler' func. Important Note: If there are any data smaller than 0 among the input data of the entry model, import plan_bi; otherwise, import plan_di. (Documentation in desc. Examples in GİTHUB: https://github.com/HCB06/PyerualJetwork)
+Author: Hasan Can Beydili
+Author-email: tchasancan@gmail.com
+Keywords: model evaluation,classifcation,pruning learning artficial neural networks
+

pyerualjetwork-2.0.6.dist-info/RECORD

@@ -0,0 +1,7 @@
+plan/__init__.py,sha256=x2SEXi2t_-OBAzOgX2v6sywjUp8Y9chprfl8KvgrU38,701
+plan/plan_bi.py,sha256=RL2Yu2NN3KoXU5OEnijkSEXabo2fsJt-ZpCvV_WiHFI,33909
+plan/plan_di.py,sha256=SMD9eSMnL69HFfDAaiabmNOuH8iesA1gkKVfkrz2fIA,32876
+pyerualjetwork-2.0.6.dist-info/METADATA,sha256=ros5qHE_hOSma-KaWuJp2hUGqTfjasOI2VuJrFbOi_E,588
+pyerualjetwork-2.0.6.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-2.0.6.dist-info/top_level.txt,sha256=G0Al3HuNJ88434XneyDtRKAIUaLCizOFYFYNhd7e2OM,5
+pyerualjetwork-2.0.6.dist-info/RECORD,,

pyerualjetwork-2.0.4.dist-info/METADATA

@@ -1,8 +0,0 @@
-Metadata-Version: 2.1
-Name: pyerualjetwork
-Version: 2.0.4
-Summary: Advanced python deep learning library. New features: More simple and practical, all functions and variables are snake_case. (Documentation in desc. Examples in GİTHUB: https://github.com/HCB06/PyerualJetwork)
-Author: Hasan Can Beydili
-Author-email: tchasancan@gmail.com
-Keywords: model evaluation,classifcation,pruning learning artficial neural networks
-

pyerualjetwork-2.0.4.dist-info/RECORD

@@ -1,6 +0,0 @@
-plan/__init__.py,sha256=TYPKx35TBM7X814H-RQmVK9DduX5GX0JdTW7_-b2ZUc,377
-plan/plan.py,sha256=-41P4Rj5_-PrYWYXcaavYHlu8AninycX3FJRs33JrQQ,33028
-pyerualjetwork-2.0.4.dist-info/METADATA,sha256=GVCzZR_GTYxGb4TYWyFj4ff4dusUzBmtwt4ceGnyI-w,431
-pyerualjetwork-2.0.4.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-2.0.4.dist-info/top_level.txt,sha256=G0Al3HuNJ88434XneyDtRKAIUaLCizOFYFYNhd7e2OM,5
-pyerualjetwork-2.0.4.dist-info/RECORD,,