pyerualjetwork 2.3.3__py3-none-any.whl → 2.3.4__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, 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
+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_post_process

plan_bi/plan_bi.py

@@ -126,15 +126,28 @@ def fit(
     layers.append('cat')
     trained_W.append(np.eye(len(class_count)))
     
-    for i in range(len(class_count)):
-
-        for j in range(len(layers)):
+    return trained_W
     
-            if layers[j] == 'fex':
+def weight_post_process(
+    W,
+    class_count
+) -> str:
+    """
+    Identifies the weights for a neural network model.
+
+    Args:
+            W (list(num)): Trained weight matrix list.
+            class_count (int): Class count of model.
+
+    Returns:
+        list([numpy_arrays],[...]): posttrained weight matices of the model. .
+    """
+
+    for i in range(len(class_count)):
         
-                trained_W[j][i,:] = normalization(trained_W[j][i,:])
+            W[0][i,:] = normalization(W[0][i,:])
     
-    return trained_W
+    return W
         
 # FUNCTIONS -----
 

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, 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
+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, manuel_balancer, weight_post_process

plan_di/plan_di.py

@@ -122,7 +122,7 @@ def fit(
     
     layers.append('cat')
     trained_W.append(np.eye(len(class_count)))
-    
+                
     for i in range(len(class_count)):
     
         for j in range(len(layers)):
@@ -131,11 +131,30 @@ def fit(
             
                 trained_W[j][i,:] = normalization(trained_W[j][i,:])
                 
-
     return trained_W
 
 # FUNCTIONS -----
 
+def weight_post_process(
+    W,
+    class_count
+) -> str:
+    """
+    Identifies the weights for a neural network model.
+
+    Args:
+            W (list(num)): Trained weight matrix list.
+            class_count (int): Class count of model.
+
+    Returns:
+        list([numpy_arrays],[...]): posttrained weight matices of the model. .
+    """
+
+    for i in range(len(class_count)):
+        
+            W[0][i,:] = normalization(W[0][i,:])
+    
+    return W
 
 def weight_identification(
     layer_count,      # int: Number of layers in the neural network.

pyerualjetwork-2.3.4.dist-info/METADATA

@@ -0,0 +1,8 @@
+Metadata-Version: 2.1
+Name: pyerualjetwork
+Version: 2.3.4
+Summary: Weights post process function added: [weight_post_process](optional after training before testing.), new function: manuel_balancer. And scaler_params added for scaled models.
+Author: Hasan Can Beydili
+Author-email: tchasancan@gmail.com
+Keywords: model evaluation,classifcation,pruning learning artficial neural networks
+

pyerualjetwork-2.3.4.dist-info/RECORD

@@ -0,0 +1,8 @@
+plan_bi/__init__.py,sha256=qY5Yz9iTpCDCzDANQEGCwvGXZkhdd6ang_2flxhkfvo,513
+plan_bi/plan_bi.py,sha256=THIWLSa3mYN0U5sbFnUZL6e7ui21irPDYAwxMfRm-Lk,50578
+plan_di/__init__.py,sha256=1vlfNLGMYLk2TZEXX8tXZFAAq6Tuj7AtA-dm9qJL5og,504
+plan_di/plan_di.py,sha256=aroAMxYc-gt9g2V1S-2mkomNtmM84Nwa0TjUTDwWJ24,48183
+pyerualjetwork-2.3.4.dist-info/METADATA,sha256=n6FWEgXUUt4LAx5-j3WoFfNA8zlJWHPsmAQ0BVqJb2E,396
+pyerualjetwork-2.3.4.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-2.3.4.dist-info/top_level.txt,sha256=aaXSOcnD62fbXG1x7tw4nV50Qxx9g9zDNLK7OD4BdPE,16
+pyerualjetwork-2.3.4.dist-info/RECORD,,

pyerualjetwork-2.3.3.dist-info/METADATA

@@ -1,8 +0,0 @@
-Metadata-Version: 2.1
-Name: pyerualjetwork
-Version: 2.3.3
-Summary: Weights now noramlized, new function: manuel_balancer. And scaler_params added for scaled models.
-Author: Hasan Can Beydili
-Author-email: tchasancan@gmail.com
-Keywords: model evaluation,classifcation,pruning learning artficial neural networks
-

pyerualjetwork-2.3.3.dist-info/RECORD

@@ -1,8 +0,0 @@
-plan_bi/__init__.py,sha256=m84PX8yNU6pVlQNyWOqamkQdx_-_aPFsfvtwEnC8U_w,492
-plan_bi/plan_bi.py,sha256=LRzft24OU7UIqtOKnuMnJkVxzFxZPEupec7I5zgGLGc,50303
-plan_di/__init__.py,sha256=cp43HHfPlIYVGFULVoiEwjFE8paMHCAgYLSic355gqs,483
-plan_di/plan_di.py,sha256=p_MTjHmyht1hc_9EfUx64bpuurYR706vfP_K1wRoRdA,47697
-pyerualjetwork-2.3.3.dist-info/METADATA,sha256=R9aTGNyJ4Nd8RIoIgKx78jy9XbxFkn1lZLa6EABmLug,319
-pyerualjetwork-2.3.3.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-2.3.3.dist-info/top_level.txt,sha256=aaXSOcnD62fbXG1x7tw4nV50Qxx9g9zDNLK7OD4BdPE,16
-pyerualjetwork-2.3.3.dist-info/RECORD,,