pyerualjetwork 3.3.1__py3-none-any.whl → 3.3.3__py3-none-any.whl

plan/plan.py

@@ -20,6 +20,7 @@ from scipy import io
 import scipy.io as sio
 from matplotlib.animation import ArtistAnimation
 import networkx as nx
+import sys
 
 # BUILD -----
 
@@ -41,7 +42,7 @@ def fit(
     infoPLAN = """
     Creates and configures a PLAN model.
     
-    Args:
+    fit Args:
         x_train (list[num]): List or numarray of input data.
         y_train (list[num]): List or numarray of target labels. (one hot encoded)
         val (None or True): validation in training process ? None or True default: None (optional)
@@ -66,7 +67,7 @@ def fit(
     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 + Style.RESET_ALL)
-        return 'e'
+        sys.exit()
 
     if val == True:
 
@@ -105,7 +106,7 @@ def fit(
 
             print(Fore.RED + "ERROR115: For showing training, val parameter must be True. from: fit",
                   infoPLAN + Style.RESET_ALL)
-            return 'e'
+            sys.exit()
 
 
     class_count = set()
@@ -124,10 +125,12 @@ def fit(
     else:
 
         layers = ['fex'] * visible_layer
+    
+    x_train_0 = np.array(x_train[0])
+
+    x_train__0_vec = x_train_0.ravel()
 
-    x_train[0] = np.array(x_train[0])
-    x_train[0] = x_train[0].ravel()
-    x_train_size = len(x_train[0])
+    x_train_size = len(x_train__0_vec)
     
     if visible_layer == None:
 
@@ -166,11 +169,11 @@ def fit(
 
         inp = np.array(inp)
         inp = inp.ravel()
-        
+
         if x_train_size != len(inp):
             print(Fore.RED + "ERROR304: All input matrices or vectors in x_train list, must be same size. from: fit",
                   infoPLAN + Style.RESET_ALL)
-            return 'e'
+            sys.exit()
 
         neural_layer = inp
 
@@ -341,7 +344,7 @@ def generate_fixed_positions(G, layout_type='circular'):
             pos[node] = (i % grid_size, i // grid_size)
     else:
         raise ValueError("Unsupported layout_type. Use 'circular' or 'grid'.")
-    
+
     return pos
 
 def weight_normalization(
@@ -366,11 +369,8 @@ def weight_normalization(
     return W
 
 def weight_identification(
-    layer_count,      # int: Number of layers in the neural network.
-    class_count,      # int: Number of classes in the classification task.
     fex_neurons,
     cat_neurons,         # list[num]: List of neuron counts for each layer.
-    x_train_size        # int: Size of the input data.
 ) -> str:
     """
     Identifies the weights for a neural network model.
@@ -576,15 +576,58 @@ def sine_square(x):
 def logarithmic(x):
     return np.log(x**2 + 1)
 
-def power(x, p):
-    return x**p
-
 def scaled_cubic(x, alpha=1.0):
     return alpha * x**3
 
 def sine_offset(x, beta=0.0):
     return np.sin(x + beta)
 
+def activations_list():
+    """
+    spiral,
+    sigmoid,
+    relu,
+    tanh,: good for general datasets
+    swish,
+    circular,
+    mod_circular,
+    tanh_circular,
+    leaky_relu,
+    softplus,
+    elu,
+    gelu, 
+    selu, 
+    sinakt, 
+    p_squared, 
+    sglu, 
+    dlrelu, 
+    exsig, 
+    acos, 
+    gla, 
+    srelu, 
+    qelu, 
+    isra, 
+    waveakt, 
+    arctan, 
+    bent_identity,: good for image datasets
+    sech, 
+    softsign, 
+    pwl, 
+    cubic, 
+    gaussian, 
+    sine, 
+    tanh_square, 
+    mod_sigmoid, 
+    quartic, 
+    square_quartic, 
+    cubic_quadratic, 
+    exp_cubic, 
+    sine_square,
+    logarithmic, 
+    scaled_cubic, 
+    sine_offset
+    """
+
 
 def fex(
     Input,               # list[num]: Input data.
@@ -619,135 +662,140 @@ def fex(
         if activation == 'sigmoid':
             Output += Sigmoid(Input)
 
-        if activation == 'swish':
+        elif activation == 'swish':
             Output += swish(Input)
 
-        if activation == 'circular':
+        elif activation == 'circular':
             Output += circular_activation(Input)
 
-        if activation == 'mod_circular':
+        elif activation == 'mod_circular':
             Output += modular_circular_activation(Input)
 
-        if activation == 'tanh_circular':
+        elif activation == 'tanh_circular':
             Output += tanh_circular_activation(Input)
 
-        if activation == 'leaky_relu':
+        elif activation == 'leaky_relu':
             Output += leaky_relu(Input)
 
-        if activation == 'relu':
+        elif activation == 'relu':
             Output += Relu(Input)
         
-        if activation == 'softplus':
+        elif activation == 'softplus':
             Output += softplus(Input)
 
-        if activation == 'elu':
+        elif activation == 'elu':
             Output += elu(Input)
 
-        if activation == 'gelu':
+        elif activation == 'gelu':
             Output += gelu(Input)
 
-        if activation == 'selu':
+        elif activation == 'selu':
             Output += selu(Input)    
 
-        if activation == 'softmax':
+        elif activation == 'softmax':
             Output += Softmax(Input)
 
-        if activation == 'tanh':
+        elif activation == 'tanh':
             Output += tanh(Input)
 
-        if activation == 'sinakt':
+        elif activation == 'sinakt':
             Output += sinakt(Input)
 
-        if activation == 'p_squared':
+        elif activation == 'p_squared':
             Output += p_squared(Input)
 
-        if activation == 'sglu':
+        elif activation == 'sglu':
             Output += sglu(Input, alpha=1.0)
 
-        if activation == 'dlrelu':
+        elif activation == 'dlrelu':
             Output += dlrelu(Input)
 
-        if activation == 'exsig':
+        elif activation == 'exsig':
             Output += exsig(Input)
 
-        if activation == 'acos':
+        elif activation == 'acos':
             Output += acos(Input, alpha=1.0, beta=0.0)
 
-        if activation == 'gla':
+        elif activation == 'gla':
             Output += gla(Input, alpha=1.0, mu=0.0)
 
-        if activation == 'srelu':
+        elif activation == 'srelu':
             Output += srelu(Input)
 
-        if activation == 'qelu':
+        elif activation == 'qelu':
             Output += qelu(Input)
 
-        if activation == 'isra':
+        elif activation == 'isra':
             Output += isra(Input)
 
-        if activation == 'waveakt':
+        elif activation == 'waveakt':
             Output += waveakt(Input) 
 
-        if activation == 'arctan':
+        elif activation == 'arctan':
             Output += arctan(Input) 
         
-        if activation == 'bent_identity':
+        elif activation == 'bent_identity':
             Output += bent_identity(Input)
 
-        if activation == 'sech':
+        elif activation == 'sech':
             Output += sech(Input)
 
-        if activation == 'softsign':
+        elif activation == 'softsign':
             Output += softsign(Input)
 
-        if activation == 'pwl':
+        elif activation == 'pwl':
             Output += pwl(Input)
 
-        if activation == 'cubic':
+        elif activation == 'cubic':
             Output += cubic(Input)
 
-        if activation == 'gaussian':
+        elif activation == 'gaussian':
             Output += gaussian(Input)
 
-        if activation == 'sine':
+        elif activation == 'sine':
             Output += sine(Input)
 
-        if activation == 'tanh_square':
+        elif activation == 'tanh_square':
             Output += tanh_square(Input)
 
-        if activation == 'mod_sigmoid':
+        elif activation == 'mod_sigmoid':
             Output += mod_sigmoid(Input)
 
-        if activation == None or activation == 'linear':
+        elif activation == None or activation == 'linear':
             Output += Input
 
-        if activation == 'quartic':
+        elif activation == 'quartic':
             Output += quartic(Input)
 
-        if activation == 'square_quartic':
+        elif activation == 'square_quartic':
             Output += square_quartic(Input)
 
-        if activation == 'cubic_quadratic':
+        elif activation == 'cubic_quadratic':
             Output += cubic_quadratic(Input)
 
-        if activation == 'exp_cubic':
+        elif activation == 'exp_cubic':
             Output += exp_cubic(Input)
 
-        if activation == 'sine_square':
+        elif activation == 'sine_square':
             Output += sine_square(Input)
 
-        if activation == 'logarithmic':
+        elif activation == 'logarithmic':
             Output += logarithmic(Input)
 
-        if activation == 'scaled_cubic':
+        elif activation == 'scaled_cubic':
             Output += scaled_cubic(Input, 1.0)
 
-        if activation == 'sine_offset':
+        elif activation == 'sine_offset':
             Output += sine_offset(Input, 1.0)
 
-        if activation == 'spiral':
+        elif activation == 'spiral':
             Output += spiral_activation(Input)
 
+        else:
+
+            print(Fore.RED + 'ERROR120:' + '"' + activation + '"'+ 'is not available. Please enter this code for avaliable activation function list: help(plan.activations_list)' + '' + Style.RESET_ALL)
+            sys.exit()
+
 
     Input = Output
 
@@ -805,13 +853,8 @@ def normalization(
         (num) Scaled input data after normalization.
     """
 
-    AbsVector = np.abs(Input)
-
-    MaxAbs = np.max(AbsVector)
-
-    ScaledInput = Input / MaxAbs
-
-    return ScaledInput
+    MaxAbs = np.max(np.abs(Input))  # Direkt maksimumu hesapla
+    return Input / MaxAbs  # Normalizasyonu geri döndür
 
 
 def evaluate(
@@ -912,10 +955,11 @@ def evaluate(
         
         for i, w in enumerate(Wc):
             W[i] = np.copy(w)
-    
+
     except:
 
         print(Fore.RED + 'ERROR:' + infoTestModel + Style.RESET_ALL)
+        sys.exit()
 
     return W, y_preds, acc
 
@@ -1041,7 +1085,8 @@ def multiple_evaluate(
     except:
 
         print(Fore.RED + "ERROR: Testing model parameters like 'activation_potentiation' must be same as trained model. Check parameters. Are you sure weights are loaded ? from: evaluate" + infoTestModel + Style.RESET_ALL)
-        return 'e'
+        
+        sys.exit()
 
     return W, y_preds, acc
 
@@ -1084,12 +1129,12 @@ def save_model(model_name,
     if weights_type != 'txt' and weights_type != 'npy' and weights_type != 'mat':
         print(Fore.RED + "ERROR110: Save Weight type (File Extension) Type must be 'txt' or 'npy' or 'mat' from: save_model" +
               infosave_model + Style.RESET_ALL)
-        return 'e'
+        sys.exit()
 
     if weights_format != 'd' and weights_format != 'f' and weights_format != 'raw':
         print(Fore.RED + "ERROR111: Weight Format Type must be 'd' or 'f' or 'raw' from: save_model" +
               infosave_model + Style.RESET_ALL)
-        return 'e'
+        sys.exit()
 
     NeuronCount = 0
     SynapseCount = 0
@@ -1103,7 +1148,7 @@ def save_model(model_name,
 
         print(Fore.RED + "ERROR: Weight matrices has a problem from: save_model" +
               infosave_model + Style.RESET_ALL)
-        return 'e'
+        sys.exit()
 
     if scaler_params != None:
 
@@ -1141,7 +1186,7 @@ def save_model(model_name,
 
         print(Fore.RED + "ERROR: Model log not saved probably model_path incorrect. Check the log parameters from: save_model" +
                     infosave_model + Style.RESET_ALL)
-        return 'e'
+        sys.exit()
 
     try:
 
@@ -1200,7 +1245,7 @@ def save_model(model_name,
     except:
 
         print(Fore.RED + "ERROR: Model Weights not saved. Check the Weight parameters. SaveFilePath expl: 'C:/Users/hasancanbeydili/Desktop/denemePLAN/' from: save_model" + infosave_model + Style.RESET_ALL)
-        return 'e'
+        sys.exit()
     print(df)
     message = (
         Fore.GREEN + "Model Saved Successfully\n" +
@@ -1307,7 +1352,7 @@ def predict_model_ssd(Input, model_name, model_path):
     except:
         print(Fore.RED + "ERROR: The input was probably entered incorrectly. from: predict_model_ssd" +
               infopredict_model_ssd + Style.RESET_ALL)
-        return 'e'
+        sys.exit()
     for i, w in enumerate(Wc):
         W[i] = np.copy(w)
     return neural_layer
@@ -1362,7 +1407,7 @@ def predict_model_ram(Input, W, scaler_params=None, activation_potentiation=[Non
     except:
         print(Fore.RED + "ERROR: Unexpected input or wrong model parameters from: predict_model_ram." +
             infopredict_model_ram + Style.RESET_ALL)
-    return 'e'
+        sys.exit()
 
 def auto_balancer(x_train, y_train):
 
@@ -1409,7 +1454,7 @@ def auto_balancer(x_train, y_train):
                                                                                  ) + " to: " + str(len(BalancedInputs)) + ". from: auto_balancer " + Style.RESET_ALL)
     except:
         print(Fore.RED + "ERROR: Inputs and labels must be same length check parameters" + infoauto_balancer)
-        return 'e'
+        sys.exit()
 
     return np.array(BalancedInputs), np.array(BalancedLabels)
 
@@ -1540,7 +1585,7 @@ def standard_scaler(x_train=None, x_test=None, scaler_params=None):
         print(
         Fore.RED + "ERROR: x_train and x_test must be list[numpyarray] from standard_scaler" + info_standard_scaler + Style.RESET_ALL)
     
-        return('e')
+        sys.exit()
 
 def encode_one_hot(y_train, y_test):
     """
@@ -1894,26 +1939,32 @@ def plot_evaluate(x_test, y_test, y_preds, acc_list, W, activation_potentiation)
                          np.arange(y_min, y_max, h))
     
     grid = np.c_[xx.ravel(), yy.ravel()]
-    grid_full = np.zeros((grid.shape[0], x_test.shape[1]))
-    grid_full[:, feature_indices] = grid
-    
-    Z = [None] * len(grid_full)
 
-    predict_progress = tqdm(total=len(grid_full),leave=False, desc="Predicts For Desicion Boundary",ncols= 120)
+    try:
 
-    for i in range(len(grid_full)):
+        grid_full = np.zeros((grid.shape[0], x_test.shape[1]))
+        grid_full[:, feature_indices] = grid
+        
+        Z = [None] * len(grid_full)
 
-        Z[i] = np.argmax(predict_model_ram(grid_full[i], W=W, activation_potentiation=activation_potentiation))
-        predict_progress.update(1)
+        predict_progress = tqdm(total=len(grid_full),leave=False, desc="Predicts For Decision Boundary",ncols= 120)
 
-    Z = np.array(Z)
-    Z = Z.reshape(xx.shape)
+        for i in range(len(grid_full)):
+
+            Z[i] = np.argmax(predict_model_ram(grid_full[i], W=W, activation_potentiation=activation_potentiation))
+            predict_progress.update(1)
+
+        Z = np.array(Z)
+        Z = Z.reshape(xx.shape)
 
-    axs[1,1].contourf(xx, yy, Z, alpha=0.8)
-    axs[1,1].scatter(x_test[:, feature_indices[0]], x_test[:, feature_indices[1]], c=decode_one_hot(y_test), edgecolors='k', marker='o', s=20, alpha=0.9)
-    axs[1,1].set_xlabel(f'Feature {0 + 1}')
-    axs[1,1].set_ylabel(f'Feature {1 + 1}')
-    axs[1,1].set_title('Decision Boundary')
+        axs[1,1].contourf(xx, yy, Z, alpha=0.8)
+        axs[1,1].scatter(x_test[:, feature_indices[0]], x_test[:, feature_indices[1]], c=decode_one_hot(y_test), edgecolors='k', marker='o', s=20, alpha=0.9)
+        axs[1,1].set_xlabel(f'Feature {0 + 1}')
+        axs[1,1].set_ylabel(f'Feature {1 + 1}')
+        axs[1,1].set_title('Decision Boundary')
+
+    except:
+        pass
 
     plt.show()
 
@@ -2052,8 +2103,8 @@ def manuel_balancer(x_train, y_train, target_samples_per_class):
         x_train = np.array(x_train)
         y_train = np.array(y_train)
     except:
-        print(Fore.GREEN + "x_tarin and y_train already numpyarray." + Style.RESET_ALL)
         pass
+
     classes = np.arange(y_train.shape[1])
     class_count = len(classes)
     

{pyerualjetwork-3.3.1.dist-info → pyerualjetwork-3.3.3.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 3.3.1
-Summary: fit function changes: LTD parameter included for Deep PLAN and professional visualizing for training. in the fit funciton, show_training=True
+Version: 3.3.3
+Summary: Code improvements
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com
 Keywords: model evaluation,classifcation,potentiation learning artficial neural networks

pyerualjetwork-3.3.3.dist-info/RECORD

@@ -0,0 +1,6 @@
+plan/__init__.py,sha256=LuFcY0nqAzpjTDWAZn7L7-wipwMpnREqVghPiva0Xjg,548
+plan/plan.py,sha256=Wf9sM9N_ibeaoiFKQGs940ysmQcb7ORLryw5I0oqT7Y,68803
+pyerualjetwork-3.3.3.dist-info/METADATA,sha256=PkJreUZLFg-dTz4-kxLeFLl-XH6wclatKeejotkjQws,244
+pyerualjetwork-3.3.3.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-3.3.3.dist-info/top_level.txt,sha256=G0Al3HuNJ88434XneyDtRKAIUaLCizOFYFYNhd7e2OM,5
+pyerualjetwork-3.3.3.dist-info/RECORD,,

pyerualjetwork-3.3.1.dist-info/RECORD

@@ -1,6 +0,0 @@
-plan/__init__.py,sha256=LuFcY0nqAzpjTDWAZn7L7-wipwMpnREqVghPiva0Xjg,548
-plan/plan.py,sha256=39AW4YIsz6htzmlVGLLUab1wpSQw6u2PeE9I488tSx4,67925
-pyerualjetwork-3.3.1.dist-info/METADATA,sha256=0QhZbV-1i7-9ynrRwLTEP6MaWzBzD9yc2uIZeMFkj5I,368
-pyerualjetwork-3.3.1.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-3.3.1.dist-info/top_level.txt,sha256=G0Al3HuNJ88434XneyDtRKAIUaLCizOFYFYNhd7e2OM,5
-pyerualjetwork-3.3.1.dist-info/RECORD,,