pyerualjetwork 4.0.0__py3-none-any.whl → 4.0.2__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -56,8 +56,8 @@ days, seconds = divmod(remaining_time.total_seconds(), 86400)
 hours, seconds = divmod(seconds, 3600)
 minutes, seconds = divmod(seconds, 60)
 
-__version__ = "4.0.0"
-__update__ = f"\033[33m --- IMPORTANT NOTE! --- \n pyerualjetwork==4.0.0 inludes anaplan==2.6.1. Name changed. Full support starting January 10, 2025. TIME REMAINING TO FULL SUPPORT: {int(days)} days, {int(hours):02} hours, {int(minutes):02} minutes, {int(seconds):02} seconds\033[0m\n* Changes: https://github.com/HCB06/Anaplan/blob/main/CHANGES\n* Anaplan document: https://github.com/HCB06/Anaplan/blob/main/Anaplan/ANAPLAN_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf.\n* YouTube tutorials: https://www.youtube.com/@HasanCanBeydili"
+__version__ = "4.0.2"
+__update__ = f"\033[33m --- IMPORTANT NOTE! --- \n 'anaplan' name changed to 'pyerualjetwork'. Full 'pyerualjetwork' support starting January 10, 2025. TIME REMAINING TO END OF SUPPORT ANAPLAN: {int(days)} days, {int(hours):02} hours, {int(minutes):02} minutes, {int(seconds):02} seconds\033[0m\n* Changes: https://github.com/HCB06/Anaplan/blob/main/CHANGES\n* PyerualJetwork document: https://github.com/HCB06/Anaplan/blob/main/PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf.\n* YouTube tutorials: https://www.youtube.com/@HasanCanBeydili"
 
 def print_version(__version__):
     print(f"PyerualJetwork Version {__version__}" + '\n')

pyerualjetwork/model_operations.py

@@ -239,10 +239,12 @@ def load_model(model_name,
     return W, None, None, activation_potentiation, scaler_params
 
 
-def predict_model_ssd(Input, model_name, model_path):
+
+def predict_model_ssd(Input, model_name, model_path=''):
 
     """
-    Function to make a prediction using a divided potentiation learning artificial neural network (PLAN).
+    Function to make a prediction using a potentiation learning artificial neural network (PLAN).
+    from storage
 
     Arguments:
 
@@ -250,6 +252,8 @@ def predict_model_ssd(Input, model_name, model_path):
 
     model_name (str): Name of the model.
 
+    model_path (str): Path of the model. Default: ''
+
     Returns:
     ndarray: Output from the model.
     """
@@ -265,24 +269,52 @@ def predict_model_ssd(Input, model_name, model_path):
 
     Input = standard_scaler(None, Input, scaler_params)
 
-    Wc = np.copy(W)
-
     neural_layer = Input
     neural_layer = np.array(neural_layer)
     neural_layer = neural_layer.ravel()
 
+    try:
+        neural_layer = feed_forward(neural_layer, np.copy(W), is_training=False, Class='?', activation_potentiation=activation_potentiation)
+        return neural_layer
+    except:
+        print(Fore.RED + "ERROR: Unexpected Output or wrong model parameters from: predict_model_ssd." + Style.RESET_ALL)
+        sys.exit()
     
-    neural_layer = feed_forward(neural_layer, W, is_training=False, Class='?', activation_potentiation=activation_potentiation)
 
-    W = np.copy(Wc)
-    return neural_layer
+def reverse_predict_model_ssd(output, model_name, model_path=''):
+
+    """
+    reverse prediction function from storage
+    Arguments:
+
+    output (list or ndarray): output layer for the model (single probability vector, output layer of trained model).
+
+    model_name (str): Name of the model.
+
+    model_path (str): Path of the model. Default: ''
+
+    Returns:
+    ndarray: Input from the model.
+    """
+    
+    model = load_model(model_name, model_path)
+    
+    W = model[get_weights()]
+
+    try:
+        Input = np.dot(output, np.copy(W))
+        return Input
+    except:
+        print(Fore.RED + "ERROR: Unexpected Output or wrong model parameters from: reverse_predict_model_ssd." + Style.RESET_ALL)
+        sys.exit()
+    
 
 
 def predict_model_ram(Input, W, scaler_params=None, activation_potentiation=['linear']):
 
     """
-    Function to make a prediction using a divided potentiation learning artificial neural network (PLAN).
-    from weights and parameters stored in memory.
+    Function to make a prediction using a potentiation learning artificial neural network (PLAN).
+    from memory.
 
     Arguments:
 
@@ -302,8 +334,6 @@ def predict_model_ram(Input, W, scaler_params=None, activation_potentiation=['li
     from .plan import feed_forward
 
     Input = standard_scaler(None, Input, scaler_params)
-
-    Wc = np.copy(W)
     
     try:
         
@@ -311,15 +341,37 @@ def predict_model_ram(Input, W, scaler_params=None, activation_potentiation=['li
         neural_layer = np.array(neural_layer)
         neural_layer = neural_layer.ravel()
 
-        neural_layer = feed_forward(neural_layer, W, is_training=False, Class='?', activation_potentiation=activation_potentiation)
+        neural_layer = feed_forward(neural_layer, np.copy(W), is_training=False, Class='?', activation_potentiation=activation_potentiation)
 
-        W = np.copy(Wc)
         return neural_layer
     
     except:
         print(Fore.RED + "ERROR: Unexpected input or wrong model parameters from: predict_model_ram." + Style.RESET_ALL)
         sys.exit()
 
+def reverse_predict_model_ram(output, W):
+
+    """
+    reverse prediction function from memory
+
+    Arguments:
+
+    output (list or ndarray): output layer for the model (single probability vector, output layer of trained model).
+
+    W (list of ndarrays): Weights of the model.
+
+    Returns:
+    ndarray: Input from the model.
+    """
+
+    try:
+        Input = np.dot(output, np.copy(W))
+        return Input
+    
+    except:
+        print(Fore.RED + "ERROR: Unexpected Output or wrong model parameters from: reverse_predict_model_ram." + Style.RESET_ALL)
+        sys.exit()
+
 
 def get_weights():
 

pyerualjetwork/plan.py

@@ -47,7 +47,7 @@ bar_format_learner = loading_bars()[1]
 def fit(
     x_train,
     y_train,
-    val=None,
+    val=False,
     val_count=None,
     activation_potentiation=['linear'],
     x_val=None,
@@ -580,14 +580,11 @@ def evaluate(
 
     try:
 
-        Wc = [0] * len(W)  # Wc = Weight copy
         true_predict = 0
         y_preds = []
         y_preds_raw = []
         acc_list = []
 
-        Wc = np.copy(W)
-            
         
         if loading_bar_status == True:
 
@@ -600,10 +597,6 @@ def evaluate(
 
                 
             neural_layer = feed_forward(neural_layer, W, is_training=False, Class='?', activation_potentiation=activation_potentiation)
-
-
-            W = np.copy(Wc)
-            
             neural_layer = Softmax(neural_layer)
 
             max_value = max(neural_layer)
@@ -633,13 +626,10 @@ def evaluate(
         if show_metrics == True:
             
             loading_bar.close()
-            plot_evaluate(x_test, y_test, y_preds, acc_list, W=W, activation_potentiation=activation_potentiation)
-        
-            W = np.copy(Wc)
+            plot_evaluate(x_test, y_test, y_preds, acc_list, W=np.copy(W), activation_potentiation=activation_potentiation)
 
     except Exception as e:
 
-        print(Fore.RED + 'ERROR:' + str(e) + Style.RESET_ALL)
-        sys.exit()
+        raise(e)
 
     return W, y_preds, acc, None, None, y_preds_raw

{pyerualjetwork-4.0.0.dist-info → pyerualjetwork-4.0.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.0.0
+Version: 4.0.2
 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-4.0.0.dist-info → pyerualjetwork-4.0.2.dist-info}/RECORD

@@ -1,15 +1,15 @@
-pyerualjetwork/__init__.py,sha256=vTHUnMi8HRbKs_rQEDajOTcQiDqtaUVcj2g3y3YKAO8,2846
+pyerualjetwork/__init__.py,sha256=zatdprNpjP2p7jJdGJ4dwYgvgnO8h0CS6asMmuOY66Y,2878
 pyerualjetwork/activation_functions.py,sha256=iJpdsX8FqZ3lB3x-YG7d9-em8xHD0y1ciJLNWmI7Y6A,9941
 pyerualjetwork/data_operations.py,sha256=mph66_qGQHxhg_gQtTuOzP2PjTwJsxTGzmRmvrzlQn4,12747
 pyerualjetwork/help.py,sha256=5Du_Cja5iPvGeVS9dAoehKTJmRgb_7c6Qsn7Cy2ZfTs,823
 pyerualjetwork/loss_functions.py,sha256=6PyBI232SQRGuFnG3LDGvnv_PUdWzT2_2mUODJiejGI,618
 pyerualjetwork/metrics.py,sha256=q7MkhnZDRbCjFBDDfUgrl8lBYnUT_1ro1LxeBq105pI,6077
-pyerualjetwork/model_operations.py,sha256=f_k_wdPAYXVmzH01kQ2UTbcYO89DaU6_8UbK-XSX-z8,10492
-pyerualjetwork/plan.py,sha256=R8e8-S5F9eQOb9YZA6VQ9BCu94gJXMfn_nKkl4ZNpQE,31848
+pyerualjetwork/model_operations.py,sha256=eXFUVZUO6vf_uO4auevWzne1RYSvD6Efz_IdH77DGZc,11980
+pyerualjetwork/plan.py,sha256=PfsSNFe1qY_MIF1MoM_pbP-1s_HrADSLUsW9AI15nIk,31621
 pyerualjetwork/planeat.py,sha256=3l4c-sMqTY6mQvW9u2OarcccUYcMxqASQXgx1GjNZSA,38061
 pyerualjetwork/ui.py,sha256=wu2BhU1k-w3Kcho5Jtq4SEKe68ftaUeRGneUOSCVDjU,575
 pyerualjetwork/visualizations.py,sha256=DvbiQGlvlKNAgBJ3O3ukAi6uxSheha9SRFh5YX7ZxIA,26678
-pyerualjetwork-4.0.0.dist-info/METADATA,sha256=5JzOCtHCqNLV5_TT9Pp8Ld1fZYT-Qys0vIfYWNXq1n8,6430
-pyerualjetwork-4.0.0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-4.0.0.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-4.0.0.dist-info/RECORD,,
+pyerualjetwork-4.0.2.dist-info/METADATA,sha256=at2jKFwd4HUob3xaVeci1h7hLSW_xNbwsSS4-l1z5io,6430
+pyerualjetwork-4.0.2.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-4.0.2.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-4.0.2.dist-info/RECORD,,