pyerualjetwork 1.2.8__tar.gz → 1.2.9__tar.gz

pyerualjetwork-1.2.9/PKG-INFO

@@ -0,0 +1,8 @@
+Metadata-Version: 2.1
+Name: pyerualjetwork
+Version: 1.2.9
+Summary: Advanced python deep learning library. New Visualize parameter added ('y' or 'n') for TrainPlan and TestPLAN funcs. (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
+Provides-Extra: visualization

{pyerualjetwork-1.2.8 → pyerualjetwork-1.2.9}/plan/plan.py

@@ -4,6 +4,8 @@ from colorama import Fore,Style
 from typing import List, Union
 import math
 from scipy.special import expit, softmax
+import matplotlib.pyplot as plt
+import seaborn as sns
 
 # BUILD -----
 def TrainPLAN(
@@ -15,7 +17,8 @@ def TrainPLAN(
     MembranThresholds: List[str],
     MembranPotentials: List[Union[int, float]],
     Normalizations: List[str],
-    Activations: List[str]
+    Activations: List[str],
+    Visualize: str
 ) -> str:
         
     infoPLAN = """
@@ -31,12 +34,18 @@ def TrainPLAN(
         MembranPotentials (list[num]): List of MembranPotentials.
         Normalizations (List[str]): Whether normalization will be performed at indexed layers ("y" or "n").
         Activations (list[str]): List of activation functions.
+        Visualize (str): Visualize Training procces or not visualize ('y' or 'n')
     
     Returns:
         list([num]): (Weight matrices list, TrainPredictions list, TrainAcc).
         error handled ?: Process status ('e')
 """
         
+    if Visualize != 'y' and Visualize != 'n':
+        print(Fore.RED + "ERROR109: Visualize parameter must be 'y' or 'n'. TrainPLAN",infoPLAN)
+        return 'e'
+        
+    
     LastNeuron = Neurons[-1:][0]
     if LastNeuron != ClassCount:
             print(Fore.RED + "ERROR108: Last layer of neuron count must be equal class count. from: TrainPLAN",infoPLAN)
@@ -142,7 +151,7 @@ def TrainPLAN(
     Divides = SynapticDividing(ClassCount,W)
     TrainedWs = [1] * len(W)
     print(Fore.GREEN + "Train Started with 0 ERROR" + Style.RESET_ALL,)
-    TrainPredictions = [1] * len(TrainLabels)
+    TrainPredictions = [None] * len(TrainLabels)
     true = 0
     StartTime = time.time()
     for index, inp in enumerate(TrainInputs):
@@ -192,6 +201,24 @@ def TrainPLAN(
         Acc = true / len(TrainLabels)
         TrainPredictions[index] = PredictedOutput
         
+        if Visualize == 'y':
+        
+            TrainLabelsVisual = np.copy(TrainLabels) 
+            TrainLabelsVisual = np.argmax(TrainLabelsVisual, axis=1)
+            
+            plt.figure(figsize=(12, 6))
+            sns.kdeplot(TrainLabelsVisual, label='Real Outputs', shade=True)
+            sns.kdeplot(TrainPredictions, label='Predictions', shade=True)
+            plt.legend()
+            plt.xlabel('Class')
+            plt.ylabel('Data size')
+            plt.title('Predictions and Real Outputs for Training KDE Plot')
+            plt.show()
+            
+            if index + 1 != len(TrainInputs):
+            
+                plt.close('all')
+        
         if index == 0:
             for i, w in enumerate(W):
                 TrainedWs[i] = w
@@ -537,7 +564,8 @@ def TestPLAN(
     MembranThresholds,     # list[str]: List of MEMBRAN THRESHOLDS for each layer.
     MembranPotentials,    # list[num]: List of MEMBRAN POTENTIALS for each layer.
     Normalizations,    # str: Whether normalization will be performed ("y" or "n").
-    Activations,         # str: Activation function list for the neural network.
+    Activations,       # str: Activation function list for the neural network.
+    Visualize,         # Visualize Testing procces or not visualize ('y' or 'n')
     W                  # list[list[num]]: Weight matrix of the neural network.
 ) -> tuple:
     infoTestModel =  """
@@ -561,7 +589,7 @@ def TestPLAN(
     try:
         Wc = [0] * len(W)
         true = 0
-        TestPredictions = [1] * len(TestLabels)
+        TestPredictions = [None] * len(TestLabels)
         for i, w in enumerate(W):
             Wc[i] = np.copy(w)
             print('\rCopying weights.....',i+1,'/',len(W),end = "")
@@ -596,6 +624,25 @@ def TestPLAN(
                 true += 1
             Acc = true / len(TestLabels)
             TestPredictions[inpIndex] = PredictedOutput
+            
+            if Visualize == 'y':
+            
+                TestLabelsVisual = np.copy(TestLabels) 
+                TestLabelsVisual = np.argmax(TestLabelsVisual, axis=1)
+                
+                plt.figure(figsize=(12, 6))
+                sns.kdeplot(TestLabelsVisual, label='Real Outputs', shade=True)
+                sns.kdeplot(TestPredictions, label='Predictions', shade=True)
+                plt.legend()
+                plt.xlabel('Class')
+                plt.ylabel('Data size')
+                plt.title('Predictions and Real Outputs for Testing KDE Plot')
+                plt.show()
+                
+                if inpIndex + 1 != len(TestInputs):
+                
+                    plt.close('all')
+            
             UniEndTime = time.time()
                 
             CalculatingEst = round((UniEndTime - UniStartTime) * (len(TestInputs) - inpIndex),3)
@@ -1045,4 +1092,4 @@ def GetPreds():
     
 def GetAcc():
         
-    return 2
+    return 2

pyerualjetwork-1.2.9/pyerualjetwork.egg-info/PKG-INFO

@@ -0,0 +1,8 @@
+Metadata-Version: 2.1
+Name: pyerualjetwork
+Version: 1.2.9
+Summary: Advanced python deep learning library. New Visualize parameter added ('y' or 'n') for TrainPlan and TestPLAN funcs. (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
+Provides-Extra: visualization

{pyerualjetwork-1.2.8 → pyerualjetwork-1.2.9}/pyerualjetwork.egg-info/SOURCES.txt

@@ -4,4 +4,5 @@ plan/plan.py
 pyerualjetwork.egg-info/PKG-INFO
 pyerualjetwork.egg-info/SOURCES.txt
 pyerualjetwork.egg-info/dependency_links.txt
+pyerualjetwork.egg-info/requires.txt
 pyerualjetwork.egg-info/top_level.txt

pyerualjetwork-1.2.9/pyerualjetwork.egg-info/requires.txt

@@ -0,0 +1,10 @@
+numpy
+scipy
+time
+math
+colorama
+typing
+
+[visualization]
+matplotlib
+seaborn

pyerualjetwork-1.2.9/setup.py

@@ -0,0 +1,27 @@
+from setuptools import setup, find_packages
+
+# Setting Up
+
+setup(
+      
+      name = "pyerualjetwork",
+      version = "1.2.9",
+      author = "Hasan Can Beydili",
+      author_email = "tchasancan@gmail.com",
+      description= "Advanced python deep learning library. New Visualize parameter added ('y' or 'n') for TrainPlan and TestPLAN funcs. (Documentation in desc. Examples in GİTHUB: https://github.com/HCB06/PyerualJetwork)",
+      packages = find_packages(),
+      keywords = ["model evaluation", "classifcation", 'pruning learning artficial neural networks'],
+      install_requires=[
+          'numpy',
+          'scipy',
+            'time',
+            'math',
+            'colorama',
+            'typing'
+            ],
+      
+       extras_require={
+          'visualization': ['matplotlib','seaborn']
+      }
+      
+      )

pyerualjetwork-1.2.8/PKG-INFO

@@ -1,7 +0,0 @@
-Metadata-Version: 2.1
-Name: pyerualjetwork
-Version: 1.2.8
-Summary: Advanced python deep learning library. 'ThresholdSigns' changed to 'MembranThresholds' and 'ThresholdValues' changed to 'MembranPotentials'. (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-1.2.8/pyerualjetwork.egg-info/PKG-INFO

@@ -1,7 +0,0 @@
-Metadata-Version: 2.1
-Name: pyerualjetwork
-Version: 1.2.8
-Summary: Advanced python deep learning library. 'ThresholdSigns' changed to 'MembranThresholds' and 'ThresholdValues' changed to 'MembranPotentials'. (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-1.2.8/setup.py

@@ -1,15 +0,0 @@
-from setuptools import setup, find_packages
-
-# Setting Up
-
-setup(
-      
-      name = "pyerualjetwork",
-      version = "1.2.8",
-      author = "Hasan Can Beydili",
-      author_email = "tchasancan@gmail.com",
-      description= "Advanced python deep learning library. 'ThresholdSigns' changed to 'MembranThresholds' and 'ThresholdValues' changed to 'MembranPotentials'. (Documentation in desc. Examples in GİTHUB: https://github.com/HCB06/PyerualJetwork)",
-      packages = find_packages(),
-      keywords = ["model evaluation", "classifcation", 'pruning learning artficial neural networks']
-      
-      )