pyerualjetwork 1.2.0__py3-none-any.whl → 1.2.2__py3-none-any.whl

plan/__init__.py

@@ -2,4 +2,4 @@
 
 # Bu dosya, plan modülünün ana giriş noktasıdır.
 
-from .plan import AutoBalancer, Normalization, Softmax, Sigmoid, Relu, SynapticPruning, SynapticDividing, WeightIdentification, Fex, Cat, TrainPLAN, TestPLAN, SavePLAN, LoadPLAN, PredictFromDiscPLAN, PredictFromRamPLAN
+from .plan import AutoBalancer, Normalization, Softmax, Sigmoid, Relu, SynapticPruning, SynapticDividing, WeightIdentification, Fex, Cat, TrainPLAN, TestPLAN, SavePLAN, LoadPLAN, PredictFromDiscPLAN, PredictFromRamPLAN, GetWeights, GetDf, GetPreds, GetAcc, GetAllFromLoad

plan/plan.py

@@ -3,10 +3,12 @@ import time
 from colorama import Fore,Style
 from typing import List, Union
 import math
+from scipy.special import expit, softmax
+
 # BUILD -----
 def TrainPLAN(
-    Inputs: List[Union[int, float]], 
-    Labels: List[Union[int, float, str]], # At least two.. and one hot encoded
+    TrainInputs: List[Union[int, float]], 
+    TrainLabels: List[Union[int, float, str]], # At least two.. and one hot encoded
     ClassCount: int,
     Layers: List[str],
     Neurons: List[Union[int, float]],
@@ -20,8 +22,8 @@ def TrainPLAN(
     Creates and configures a PLAN model.
     
     Args:
-        Inputs (list[num]): List of input data.
-        Labels (list[num]): List of labels. (one hot encoded)
+        TrainInputs (list[num]): List of input data.
+        TrainLabels (list[num]): List of TrainLabels. (one hot encoded)
         ClassCount (int): Number of classes.
         Layers (list[str]): List of layer names. (options: 'fex' (Feature Extraction), 'cat' (Catalyser))
         Neurons (list[num]): List of neuron counts for each layer.
@@ -45,8 +47,8 @@ def TrainPLAN(
             print(Fore.RED + "ERROR307: Normalization list length must be equal to length of ThresholdSigns List,ThresholdValues List,Layers List,Neurons List. from: TrainPLAN",infoPLAN)
             return 'e'
     
-    if len(Inputs) != len(Labels):
-        print(Fore.RED + "ERROR301: Inputs list and Labels list must be same length.",infoPLAN)
+    if len(TrainInputs) != len(TrainLabels):
+        print(Fore.RED + "ERROR301: TrainInputs list and TrainLabels list must be same length.",infoPLAN)
         return 'e'
     
     for i, Value in enumerate(ThresholdValues):
@@ -117,45 +119,45 @@ def TrainPLAN(
             print(Fore.RED + "ERROR109: at layer type 'fex', pairing with 'none' Threshold is not acceptlable. if you want to 'none' put '==' and make threshold value '0'. from: TrainPLAN ",infoPLAN)
             return 'e'
         
-    UniqueLabels = set()
-    for sublist in Labels:
+    UniqueTrainLabels = set()
+    for sublist in TrainLabels:
       
-        UniqueLabels.add(tuple(sublist))
+        UniqueTrainLabels.add(tuple(sublist))
     
     
-    UniqueLabels = list(UniqueLabels)
+    UniqueTrainLabels = list(UniqueTrainLabels)
     
-    Labels = [tuple(sublist) for sublist in Labels]
+    TrainLabels = [tuple(sublist) for sublist in TrainLabels]
     
     
-    if len(UniqueLabels) != ClassCount:
+    if len(UniqueTrainLabels) != ClassCount:
         print(Fore.RED + "ERROR106: Label variety length must be same Class Count. from: TrainPLAN",infoPLAN)
         return 'e'
     
-    Inputs[0] = np.array(Inputs[0])
-    Inputs[0] = Inputs[0].ravel()
-    InputSize = len(Inputs[0])
+    TrainInputs[0] = np.array(TrainInputs[0])
+    TrainInputs[0] = TrainInputs[0].ravel()
+    TrainInputsize = len(TrainInputs[0])
     
-    W = WeightIdentification(len(Layers) - 1,ClassCount,Neurons,InputSize)
+    W = WeightIdentification(len(Layers) - 1,ClassCount,Neurons,TrainInputsize)
     Divides = SynapticDividing(ClassCount,W)
     TrainedWs = [1] * len(W)
     print(Fore.GREEN + "Train Started with 0 ERROR" + Style.RESET_ALL,)
-    TrainPredictions = [1] * len(Labels)
+    TrainPredictions = [1] * len(TrainLabels)
     true = 0
     StartTime = time.time()
-    for index, inp in enumerate(Inputs):
+    for index, inp in enumerate(TrainInputs):
         UniStartTime = time.time()
         inp = np.array(inp)
         inp = inp.ravel()
         
-        if InputSize != len(inp):
-            print(Fore.RED +"ERROR304: All input matrices or vectors in inputs list, must be same size. from: TrainPLAN",infoPLAN + Style.RESET_ALL)
+        if TrainInputsize != len(inp):
+            print(Fore.RED +"ERROR304: All input matrices or vectors in TrainInputs list, must be same size. from: TrainPLAN",infoPLAN + Style.RESET_ALL)
             return 'e'
         
         
-        for Ulindex, Ul in enumerate(UniqueLabels):
+        for Ulindex, Ul in enumerate(UniqueTrainLabels):
             
-            if Ul == Labels[index]:
+            if Ul == TrainLabels[index]:
                 for Windex, w in enumerate(W):
                     for i, ul in enumerate(Ul):
                         if ul == 1.0:
@@ -183,12 +185,12 @@ def TrainPLAN(
             elif Layer == 'cat':
                 NeuralLayer,W[Lindex] = Cat(NeuralLayer, W[Lindex], ThresholdSigns[Lindex], ThresholdValues[Lindex],1)
                 
-        RealOutput = np.argmax(Labels[index])
+        RealOutput = np.argmax(TrainLabels[index])
         PredictedOutput = np.argmax(NeuralLayer)
         if RealOutput == PredictedOutput:
             true += 1
-        Acc = true / len(Labels)
-        TrainPredictions[index] = PredictedOutput+1
+        Acc = true / len(TrainLabels)
+        TrainPredictions[index] = PredictedOutput
         
         if index == 0:
             for i, w in enumerate(W):
@@ -199,12 +201,12 @@ def TrainPLAN(
                 TrainedWs[i] = TrainedWs[i] + w
             
                 
-        W = WeightIdentification(len(Layers) - 1,ClassCount,Neurons,InputSize)
+        W = WeightIdentification(len(Layers) - 1,ClassCount,Neurons,TrainInputsize)
          
                
         UniEndTime = time.time()
         
-        CalculatingEst = round((UniEndTime - UniStartTime) * (len(Inputs) - index),3)
+        CalculatingEst = round((UniEndTime - UniStartTime) * (len(TrainInputs) - index),3)
         
         if CalculatingEst < 60:
             print('\rest......(sec):',CalculatingEst,'\n',end= "")
@@ -253,7 +255,7 @@ def WeightIdentification(
     LayerCount,      # int: Number of layers in the neural network.
     ClassCount,      # int: Number of classes in the classification task.
     Neurons,         # list[num]: List of neuron counts for each layer.
-    InputSize        # int: Size of the input data.
+    TrainInputsize        # int: Size of the input data.
 ) -> str:
     """
     Identifies the weights for a neural network model.
@@ -262,7 +264,7 @@ def WeightIdentification(
         LayerCount (int): Number of layers in the neural network.
         ClassCount (int): Number of classes in the classification task.
         Neurons (list[num]): List of neuron counts for each layer.
-        InputSize (int): Size of the input data.
+        TrainInputsize (int): Size of the input data.
 
     Returns:
         list([numpy_arrays],[...]): Weight matices of the model. .
@@ -271,7 +273,7 @@ def WeightIdentification(
     
     Wlen = LayerCount + 1
     W = [None] * Wlen
-    W[0] = np.ones((Neurons[0],InputSize))
+    W[0] = np.ones((Neurons[0],TrainInputsize))
     ws = LayerCount - 1
     for w in range(ws):
         W[w + 1] = np.ones((Neurons[w + 1],Neurons[w]))
@@ -492,19 +494,8 @@ def Softmax(
     Returns:
         list[num]: Transformed data after applying softmax function.
     """
-
-
-    MaxX = np.max(x)
-    
-    x -= MaxX
-    
-    ExpX = np.exp(x)
-    
-    SumExpX = np.sum(ExpX)
     
-    SoftmaxX = ExpX / SumExpX
-    
-    return SoftmaxX
+    return softmax(x)
 
 
 def Sigmoid(
@@ -519,18 +510,7 @@ def Sigmoid(
     Returns:
         list[num]: Transformed data after applying sigmoid function.
     """
-
-    PositiveMask = x >= 0
-    NegativeMask = ~PositiveMask
-   
-    ExpXPositive = np.exp(-np.clip(x[PositiveMask], -709, None))
-    ExpXNegative = np.exp(np.clip(x[NegativeMask], None, 709))
-
-    SigmoidX = np.zeros_like(x, dtype=float)
-    SigmoidX[PositiveMask] = 1 / (1 + ExpXPositive)
-    SigmoidX[NegativeMask] = ExpXNegative / (1 + ExpXNegative)
-   
-    return SigmoidX
+    return expit(x)
 
 
 def Relu(
@@ -615,7 +595,7 @@ def TestPLAN(
             if RealOutput == PredictedOutput:
                 true += 1
             Acc = true / len(TestLabels)
-            TestPredictions[inpIndex] = PredictedOutput+1
+            TestPredictions[inpIndex] = PredictedOutput
             UniEndTime = time.time()
                 
             CalculatingEst = round((UniEndTime - UniStartTime) * (len(TestInputs) - inpIndex),3)
@@ -663,7 +643,7 @@ def TestPLAN(
         print(Fore.RED + "ERROR: Testing model parameters like 'Layers' 'ThresholdCounts' must be same as trained model. Check parameters. Are you sure weights are loaded ? from: TestPLAN" + infoTestModel + Style.RESET_ALL)
         return 'e'
    
-    return TestPredictions,Acc
+    return W,TestPredictions,Acc
 
 def SavePLAN(ModelName,
              ModelType,
@@ -677,7 +657,7 @@ def SavePLAN(ModelName,
              LogType,
              WeightsType,
              WeightsFormat,
-             SavePath,
+             ModelPath,
              W
  ):
     
@@ -697,7 +677,7 @@ def SavePLAN(ModelName,
     LogType (str): Type of log to save (options: 'csv', 'txt', 'hdf5').
     WeightsType (str): Type of weights to save (options: 'txt', 'npy', 'mat').
     WeightFormat (str): Format of the weights (options: 'd', 'f', 'raw').
-    SavePath (str): Path where the model will be saved. For example: C:/Users/beydili/Desktop/denemePLAN/
+    ModelPath (str): Path where the model will be saved. For example: C:/Users/beydili/Desktop/denemePLAN/
     W: Weights of the model.
     
     Returns:
@@ -748,7 +728,7 @@ def SavePLAN(ModelName,
             'SAVE DATE': datetime.now(),
             'WEIGHTS TYPE': WeightsType,
             'WEIGHTS FORMAT': WeightsFormat,
-            'SAVE PATH': SavePath
+            'SAVE PATH': ModelPath
             }
     try:
         
@@ -756,15 +736,15 @@ def SavePLAN(ModelName,
         
         if  LogType == 'csv':
         
-            df.to_csv(SavePath + ModelName + '.csv', sep='\t', index=False)
+            df.to_csv(ModelPath + ModelName + '.csv', sep='\t', index=False)
             
         elif LogType == 'txt':
             
-            df.to_csv(SavePath + ModelName + '.txt', sep='\t', index=False)
+            df.to_csv(ModelPath + ModelName + '.txt', sep='\t', index=False)
             
         elif LogType == 'hdf5':
             
-            df.to_hdf(SavePath + ModelName + '.h5', key='data', mode='w')
+            df.to_hdf(ModelPath + ModelName + '.h5', key='data', mode='w')
             
     except:
         
@@ -775,17 +755,17 @@ def SavePLAN(ModelName,
         if WeightsType == 'txt' and WeightsFormat == 'd':
             
             for i, w in enumerate(W):
-                np.savetxt(SavePath + ModelName +  str(i+1) + 'w.txt' ,  w, fmt='%d')
+                np.savetxt(ModelPath + ModelName +  str(i+1) + 'w.txt' ,  w, fmt='%d')
                 
         if WeightsType == 'txt' and WeightsFormat == 'f':
              
             for i, w in enumerate(W):
-                 np.savetxt(SavePath + ModelName +  str(i+1) + 'w.txt' ,  w, fmt='%f')
+                 np.savetxt(ModelPath + ModelName +  str(i+1) + 'w.txt' ,  w, fmt='%f')
         
         if WeightsType == 'txt' and WeightsFormat == 'raw':
             
             for i, w in enumerate(W):
-                np.savetxt(SavePath + ModelName +  str(i+1) + 'w.txt' ,  w)
+                np.savetxt(ModelPath + ModelName +  str(i+1) + 'w.txt' ,  w)
             
                 
         ###
@@ -794,17 +774,17 @@ def SavePLAN(ModelName,
         if WeightsType == 'npy' and WeightsFormat == 'd':
             
             for i, w in enumerate(W):
-                np.save(SavePath + ModelName + str(i+1) + 'w.npy', w.astype(int))
+                np.save(ModelPath + ModelName + str(i+1) + 'w.npy', w.astype(int))
         
         if WeightsType == 'npy' and WeightsFormat == 'f':
              
             for i, w in enumerate(W):
-                 np.save(SavePath + ModelName +  str(i+1) + 'w.npy' ,  w, w.astype(float))
+                 np.save(ModelPath + ModelName +  str(i+1) + 'w.npy' ,  w, w.astype(float))
         
         if WeightsType == 'npy' and WeightsFormat == 'raw':
             
             for i, w in enumerate(W):
-                np.save(SavePath + ModelName +  str(i+1) + 'w.npy' ,  w)
+                np.save(ModelPath + ModelName +  str(i+1) + 'w.npy' ,  w)
                 
            
         ###
@@ -814,19 +794,19 @@ def SavePLAN(ModelName,
             
             for i, w in enumerate(W):
                 w = {'w': w.astype(int)}
-                io.savemat(SavePath + ModelName + str(i+1) + 'w.mat', w)
+                io.savemat(ModelPath + ModelName + str(i+1) + 'w.mat', w)
     
         if WeightsType == 'mat' and WeightsFormat == 'f':
              
             for i, w in enumerate(W):
                 w = {'w': w.astype(float)}
-                io.savemat(SavePath + ModelName + str(i+1) + 'w.mat', w)
+                io.savemat(ModelPath + ModelName + str(i+1) + 'w.mat', w)
         
         if WeightsType == 'mat' and WeightsFormat == 'raw':
             
             for i, w in enumerate(W):
                 w = {'w': w}
-                io.savemat(SavePath + ModelName + str(i+1) + 'w.mat', w)
+                io.savemat(ModelPath + ModelName + str(i+1) + 'w.mat', w)
             
     except:
         
@@ -884,7 +864,7 @@ def LoadPLAN(ModelName,
    ClassCount = int(df['CLASS COUNT'].iloc[0])
    ThresholdSigns = df['THRESHOLD SIGNS'].tolist()
    ThresholdValues = df['THRESHOLD VALUES'].tolist()
-   Normalization = df['NORMALIZATION'].tolist()
+   Normalizations = df['NORMALIZATION'].tolist()
    Activations = df['ACTIVATIONS'].tolist()
    NeuronCount = int(df['NEURON COUNT'].iloc[0])
    SynapseCount = int(df['SYNAPSE COUNT'].iloc[0])
@@ -892,12 +872,12 @@ def LoadPLAN(ModelName,
    ModelType = str(df['MODEL TYPE'].iloc[0])
    WeightType = str(df['WEIGHTS TYPE'].iloc[0])
    WeightFormat = str(df['WEIGHTS FORMAT'].iloc[0])
-   SavePath = str(df['SAVE PATH'].iloc[0])
+   ModelPath = str(df['MODEL PATH'].iloc[0])
 
    W = [0] * LayerCount
    
    if WeightType == 'txt':
-       for i in range(LayerCount):    
+       for i in range(LayerCount):
            W[i] = np.loadtxt(LoadPath + ModelName + str(i+1) + 'w.txt')
    elif WeightType == 'npy':
        for i in range(LayerCount):    
@@ -923,7 +903,7 @@ def PredictFromDiscPLAN(Input,ModelName,ModelPath,LogType):
     Returns:
     ndarray: Output from the model.
     """
-    W,Layers,ThresholdSigns,ThresholdValues,Normalization,Activations = LoadPLAN(ModelName,ModelPath,
+    W,Layers,ThresholdSigns,ThresholdValues,Normalizations,Activations = LoadPLAN(ModelName,ModelPath,
                                                                                   LogType)[0:6]
     Wc = [0] * len(W)
     for i, w in enumerate(W):
@@ -1048,4 +1028,26 @@ def AutoBalancer(TrainInputs, TrainLabels, ClassCount):
         print(Fore.RED + "ERROR: Inputs and labels must be same length check parameters" + infoAutoBalancer)
         return 'e'
         
-   return BalancedInputs, BalancedLabels
+   return BalancedInputs, BalancedLabels
+   
+   
+def GetWeights():
+        
+    return[0]
+    
+def GetDf():
+        
+    return[6]
+    
+def GetPreds():
+        
+    return[1]
+    
+def GetAcc():
+        
+    return[2]
+
+def GetAllFromLoad():
+    
+    return[0],[1],[2],[3],[4],[5]
+    

pyerualjetwork-1.2.2.dist-info/METADATA

@@ -0,0 +1,8 @@
+Metadata-Version: 2.1
+Name: pyerualjetwork
+Version: 1.2.2
+Summary: Advanced python deep learning library.UPDATED TO 1.2.2 NEW FEATURES: GetWeights() func for TrainPLAN, TestPLAN and LoadPLAN, GetPreds() and GetAcc() funcs for TrainPLAN and TestPLAN, GetAllFromLoad() func for LoadPLAN, GetDf() for LoadPLAN (Documentation in desc. Examples in GİTHUB: HCB06)
+Author: Hasan Can Beydili
+Author-email: tchasancan@gmail.com
+Keywords: model evaluation,classifcation,pruning learning artficial neural networks
+

pyerualjetwork-1.2.2.dist-info/RECORD

@@ -0,0 +1,6 @@
+plan/__init__.py,sha256=_jNJho5JbgO70TN4ixL13C5XbdeLmsZapy97_yu-GB0,368
+plan/plan.py,sha256=29ZssCXXZ7WNGsrjE5M2hoCg1CXdIA-E2dtHYsEpVZU,40174
+pyerualjetwork-1.2.2.dist-info/METADATA,sha256=obGYRZ5kN8sd3vUZ6b630afF0EVanczg0p8sKQEv8E4,513
+pyerualjetwork-1.2.2.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
+pyerualjetwork-1.2.2.dist-info/top_level.txt,sha256=G0Al3HuNJ88434XneyDtRKAIUaLCizOFYFYNhd7e2OM,5
+pyerualjetwork-1.2.2.dist-info/RECORD,,

pyerualjetwork-1.2.0.dist-info/METADATA

@@ -1,8 +0,0 @@
-Metadata-Version: 2.1
-Name: pyerualjetwork
-Version: 1.2.0
-Summary: Advanced python deep learning library.(Documentation in desc. Examples in GİTHUB: HCB06)
-Author: Hasan Can Beydili
-Author-email: tchasancan@gmail.com
-Keywords: model evaluation,classifcation,pruning learning artficial neural networks
-

pyerualjetwork-1.2.0.dist-info/RECORD

@@ -1,6 +0,0 @@
-plan/__init__.py,sha256=cyb3DkUey_4zEApoFtf-UBMGwd8uFADSjy3osQUG_pY,315
-plan/plan.py,sha256=dp-ZuhbyatgwrLDwEfEtuFWmTV-twvaFvD8TIC8FSXE,40179
-pyerualjetwork-1.2.0.dist-info/METADATA,sha256=RKNNHxpHzKXhfgJ_M9VO0ln8sM076yc4H6rADoJQOJY,311
-pyerualjetwork-1.2.0.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
-pyerualjetwork-1.2.0.dist-info/top_level.txt,sha256=G0Al3HuNJ88434XneyDtRKAIUaLCizOFYFYNhd7e2OM,5
-pyerualjetwork-1.2.0.dist-info/RECORD,,