pyerualjetwork 5.31a0__py3-none-any.whl → 5.32__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -42,7 +42,7 @@ PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welco
 - Contact: tchasancan@gmail.com
 """
 
-__version__ = "5.31a0"
+__version__ = "5.32"
 __update__ = """* Changes: https://github.com/HCB06/PyerualJetwork/blob/main/CHANGES
 * PyerualJetwork Homepage: https://github.com/HCB06/PyerualJetwork/tree/main
 * PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf

pyerualjetwork/cpu/activation_functions.py

@@ -34,6 +34,7 @@ Module functions:
 - 'sine_offset': lambda x: sine_offset(x, 1.0),
 - 'spiral': spiral_activation,
 - 'circular': circular_activation
+- Softmax()
 """
 
 import numpy as np

pyerualjetwork/cpu/data_ops.py

@@ -284,9 +284,9 @@ def synthetic_augmentation(x, y, dtype=np.float32):
     """
     Generates synthetic examples to balance classes with fewer examples using numpy.
     Args:
-        x_train: numpy array format
+        x: numpy array format
 
-        y_train: numpy array format (one-hot encoded)
+        y: numpy array format (one-hot encoded)
         
         dtype (numpy.dtype): Data type for the arrays. cp.float32 by default. Example: cp.float64 or cp.float16.
         

pyerualjetwork/cpu/model_ops.py

@@ -62,7 +62,7 @@ def save_model(model_name,
                test_acc=None,
                model_path='',
                activations=['linear'],
-               activation_potentiation=[],
+               activation_potentiation=None,
                weights_type='npy',
                weights_format='raw',
                show_architecture=False,
@@ -174,7 +174,6 @@ def save_model(model_name,
     if len(activations) == 1 and model_type == 'PLAN':
         activations = [activations]
         activations.append('')
-        activations.append('')
 
     if model_type == 'PTNN':
         if len(activations) > len(activation_potentiation):
@@ -386,7 +385,7 @@ def predict_from_storage(Input, model_name, model_path=''):
     from storage
 
     Args:
-        Input (list or ndarray): Input data for the model (single vector or single matrix).
+        Input (list or ndarray): Input data for the model.
         
         model_name (str): Name of the model.
         
@@ -460,7 +459,7 @@ def reverse_predict_from_storage(output, model_name, model_path=''):
     reverse prediction function from storage
     Args:
 
-        output (list or ndarray): output layer for the model (single probability vector, output layer of trained model).
+        output (list or ndarray): output layer for the model .
 
         model_name (str): Name of the model.
 
@@ -490,7 +489,7 @@ def predict_from_memory(Input, W, scaler_params=None, activations=['linear'], ac
     from memory.
 
     Args:
-        Input (list or ndarray): Input data for the model (single vector or single matrix).
+        Input (list or ndarray): Input data for the model.
         
         W (list of ndarrays): Weights of the model.
         
@@ -564,7 +563,7 @@ def reverse_predict_from_memory(output, W):
 
     Args:
 
-        output (list or ndarray): output layer for the model (single probability vector, output layer of trained model).
+        output (list or ndarray): output layer for the model.
 
         W (list of ndarrays): Weights of the model.
 

pyerualjetwork/cpu/nn.py

@@ -4,7 +4,7 @@
 
 NN (Neural Networks) on CPU
 ============================
-This module hosts functions for training and evaluating artificial neural networks on CPU for labeled classification tasks (for now).
+This module hosts functions for training and evaluating artificial neural networks on CPU for labeled classification tasks.
 
 Currently, 3 types of models can be trained:
 
@@ -132,18 +132,29 @@ def learn(x_train, y_train, optimizer, gen, pop_size, fit_start=True, batch_size
     * This function also able to train classic MLP model architectures.
     * And my newest innovative architecture: PTNN (Potentiation Transfer Neural Network).
 
+    Examples:
+    
+        This creates a PLAN model: 
+            - ```learn(x_train, y_train, optimizer, pop_size=100, gen=100, fit_start=True) ```
+
+        This creates a MLP model(with 2 hidden layer): 
+            - ```learn(x_train, y_train, optimizer, pop_size=100, gen=100, fit_start=False, neurons=[64, 64], activation_functions=['tanh', 'tanh']) ```
+        
+        This creates a PTNN model(with 2 hidden layer & 1 aggregation layer(comes with PLAN)): 
+           -  ```learn(x_train, y_train, optimizer, pop_size=100, gen=[10, 100], fit_start=True, neurons=[64, 64], activation_functions=['tanh', 'tanh']) ```
+    
     :Args:
     :param x_train: (array-like): Training input data.
     :param y_train: (array-like): Labels for training data. one-hot encoded.
-    :param optimizer: (function): Optimization technique with hyperparameters. (PLAN, MLP & PTNN (all) using ENE for optimization. Gradient based technique's will added in the future.) Please use this: from pyerualjetwork.ene_cpu import evolver (and) optimizer = lambda *args, **kwargs: evolver(*args, 'here give your hyperparameters for example:  activation_add_prob=0.85', **kwargs) Example:
+    :param optimizer: (function): Optimization technique with hyperparameters. (PLAN, MLP & PTNN (all) using ENE for optimization. Gradient based technique's will added in the future.) Please use this: from pyerualjetwork.cpu.ene import evolver (and) optimizer = lambda *args, **kwargs: evolver(*args, 'here give your hyperparameters for example:  activation_add_prob=0.85', **kwargs) Example:
     ```python
-             optimizer = lambda *args, **kwargs: ene_cpu.evolver(*args,
+             optimizer = lambda *args, **kwargs: ene.evolver(*args,
                                                             activation_add_prob=0.05,
                                                             strategy='aggressive',
                                                             policy='more_selective',
                                                             **kwargs)
 
-             model = neu_cpu.learn(x_train,
+             model = nn.learn(x_train,
                             y_train,
                             optimizer,
                             fit_start=True,

pyerualjetwork/cuda/activation_functions.py

@@ -34,6 +34,7 @@ Module functions:
 - 'sine_offset': lambda x: sine_offset(x, 1.0),
 - 'spiral': spiral_activation,
 - 'circular': circular_activation
+- Softmax()
 """
 
 import cupy as cp

pyerualjetwork/cuda/model_ops.py

@@ -64,7 +64,7 @@ def save_model(model_name,
                test_acc=None,
                model_path='',
                activations=['linear'],
-               activation_potentiation=[],
+               activation_potentiation=None,
                weights_type='npy',
                weights_format='raw',
                show_architecture=False,
@@ -189,7 +189,6 @@ def save_model(model_name,
     if len(activations) == 1 and model_type == 'PLAN':
         activations = [activations]
         activations.append('')
-        activations.append('')
 
     if model_type == 'PTNN':
         if len(activations) > len(activation_potentiation):
@@ -407,7 +406,7 @@ def predict_from_storage(Input, model_name, model_path='', dtype=cp.float32):
     from storage
 
     Args:
-        Input (list or ndarray or cupyarray): Input data for the model (single vector or single matrix).
+        Input (list or ndarray or cupyarray): Input data for the model.
         
         model_name (str): Name of the model.
         
@@ -485,7 +484,7 @@ def reverse_predict_from_storage(output, model_name, model_path='', dtype=cp.flo
     reverse prediction function from storage
     Args:
 
-        output (list or ndarray): output layer for the model (single probability vector, output layer of trained model).
+        output (list or ndarray): output layer for the model.
 
         model_name (str): Name of the model.
 
@@ -518,7 +517,7 @@ def predict_from_memory(Input, W, scaler_params=None, activations=['linear'], ac
     from memory.
 
     Args:
-        Input (list or ndarray): Input data for the model (single vector or single matrix).
+        Input (list or ndarray): Input data for the model.
         
         W (list of ndarrays): Weights of the model.
         
@@ -586,7 +585,7 @@ def reverse_predict_from_memory(output, W, dtype=cp.float32):
 
     Args:
 
-        output (list or ndarray): output layer for the model (single probability vector, output layer of trained model).
+        output (list or ndarray): output layer for the model.
 
         W (list of ndarrays): Weights of the model.
 

pyerualjetwork/cuda/nn.py

@@ -127,19 +127,30 @@ def learn(x_train, y_train, optimizer, gen, pop_size, fit_start=True, batch_size
     * This function also able to train classic MLP model architectures.
     * And my newest innovative architecture: PTNN (Potentiation Transfer Neural Network).
 
+    Examples:
+    
+        This creates a PLAN model: 
+            - ```learn(x_train, y_train, optimizer, pop_size=100, gen=100, fit_start=True) ```
+
+        This creates a MLP model(with 2 hidden layer): 
+            - ```learn(x_train, y_train, optimizer, pop_size=100, gen=100, fit_start=False, neurons=[64, 64], activation_functions=['tanh', 'tanh']) ```
+        
+        This creates a PTNN model(with 2 hidden layer & 1 aggregation layer(comes with PLAN)): 
+           -  ```learn(x_train, y_train, optimizer, pop_size=100, gen=[10, 100], fit_start=True, neurons=[64, 64], activation_functions=['tanh', 'tanh']) ```
+
     :Args:
     :param x_train: (array-like): Training input data.
     :param y_train: (array-like): Labels for training data.
-    :param optimizer: (function): Optimization technique with hyperparameters. (PLAN, MLP & PTNN (all) using ENE for optimization. Gradient based technique's will added in the future.) Please use this: from pyerualjetwork.ene_cuda import evolver (and) optimizer = lambda *args, **kwargs: evolver(*args, 'here give your hyperparameters for example:  activation_add_prob=0.85', **kwargs) Example:
+    :param optimizer: (function): Optimization technique with hyperparameters. (PLAN, MLP & PTNN (all) using ENE for optimization. Gradient based technique's will added in the future.) Please use this: from pyerualjetwork.cuda.ene import evolver (and) optimizer = lambda *args, **kwargs: evolver(*args, 'here give your hyperparameters for example:  activation_add_prob=0.85', **kwargs) Example:
     ```python
     
-            optimizer = lambda *args, **kwargs: ene_cuda.evolver(*args,
+            optimizer = lambda *args, **kwargs: ene.evolver(*args,
                                                     activation_add_prob=0.05,
                                                     strategy='aggressive',
                                                     policy='more_selective',
                                                     **kwargs)
 
-             model = neu_cuda.learn(x_train,
+             model = nn.learn(x_train,
                             y_train,
                             optimizer,
                             fit_start=True,

{pyerualjetwork-5.31a0.dist-info → pyerualjetwork-5.32.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 5.31a0
+Version: 5.32
 Summary: PyereualJetwork is a GPU-accelerated machine learning library in Python for professionals and researchers. It features PLAN, MLP, Deep Learning training, and ENE (Eugenic NeuroEvolution) for genetic optimization, applicable to genetic algorithms or Reinforcement Learning (RL). The library includes data pre-processing, visualizations, model saving/loading, prediction, evaluation, training, and detailed or simplified memory management.
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com
@@ -24,17 +24,14 @@ GitHub Page: https://github.com/HCB06/PyerualJetwork
 
 YouTube Tutorials: https://www.youtube.com/watch?v=6wMQstZ00is&list=PLNgNWpM7HbsBpCx2VTJ4SK9wcPyse-EHw
 
-	pip install pyerualjetwork
+	installation: 
+	'pip install pyerualjetwork'
 	
-	from pyerualjetwork import neu_cpu
-	from pyerualjetwork import ene_cpu
-	from pyerualjetwork import data_operations_cpu
-	from pyerualjetwork import model_operations_cpu
-	
-	from pyerualjetwork import neu_cuda
-	from pyerualjetwork import ene_cuda
-	from pyerualjetwork import data_operations_cuda
-	from pyerualjetwork import model_operations_cuda
+	package modules:
+	'from pyerualjetwork.cpu import nn, ene, data_ops, model_ops, memory_ops'
+	'from pyerualjetwork.cuda import nn, ene, data_ops, model_ops, memory_ops'
+
+	please read docstrings.
 	
 	PyerualJetwork has Issue Solver. This operation provides users ready-to-use functions to identify potential issues
  	caused by version incompatibilities in major updates, ensuring users are not affected by such problems. 
@@ -74,10 +71,10 @@ PyerualJetwork is free to use for commercial business and individual users.
 PyerualJetwork ready for both eager execution(like PyTorch) and static graph(like Tensorflow) concepts because PyerualJetwork using only functions.
 For example:
 
-fit function only fits given training data(suitable for dynamic graph) but learner function learns and optimize entire architecture(suitable for static graph). Or more deeper eager executions PyerualJetwork have: feed_forward function, list of activation functions, loss functions. You can create your unique model architecture. Move your data to GPU or CPU or manage how much should in GPU, Its all up to you.
+plan_fit function only fits given training data(suitable for dynamic graph) but learn function learns and optimize entire architecture(suitable for static graph). Or more deeper eager executions PyerualJetwork have: cross_over function, mutation function, list of activation functions, loss functions. You can create your unique model architecture. Move your data to GPU or CPU or manage how much should in GPU, Its all up to you.
 <br><br>
 
-PyerualJetworket includes PLAN, MLP & ENE.<br>
+PyerualJetworket includes PLAN, MLP, PTNN & ENE.<br>
 
 PLAN VISION:<br>
 
@@ -122,6 +119,6 @@ HOW DO I IMPORT IT TO MY PROJECT?
 
 Anaconda users can access the 'Anaconda Prompt' terminal from the Start menu and add the necessary library modules to the Python module search queue by typing "pip install pyerualjetwork" and pressing enter. If you are not using Anaconda, you can simply open the 'cmd' Windows command terminal from the Start menu and type "pip install PyerualJetwork". (Visual Studio Code reccomended) After installation, it's important to periodically open the terminal of the environment you are using and stay up to date by using the command "pip install PyerualJetwork --upgrade".
 
-After installing the module using "pip" you can now call the library module in your project environment. Use: “from pyerualjetwork import neu_cpu”. Now, you can call the necessary functions from the neu module.
+After installing the module using "pip" you can now call the library module in your project environment. Use: “from pyerualjetwork.cpu import nn. Now, you can call the necessary functions from the nn module.
 
 The PLAN algorithm & ENE algorithm will not be explained in this document. This document focuses on how professionals can integrate and use PyerualJetwork in their systems. However, briefly, the PLAN algorithm can be described as a classification algorithm. PLAN algorithm achieves this task with an incredibly energy-efficient, fast, and hyperparameter-free user-friendly approach. For more detailed information, you can check out ![PYERUALJETWORK USER MANUEL](https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf) file.

{pyerualjetwork-5.31a0.dist-info → pyerualjetwork-5.32.dist-info}/RECORD

@@ -1,28 +1,28 @@
-pyerualjetwork/__init__.py,sha256=zbvGfbx7pzsUEYgU57GPX7-Y_ZYWC89Irqo3gbvT57g,2706
+pyerualjetwork/__init__.py,sha256=X-alwoq6f9sVQjlVKzJMev51yAFgX4qoqSKrMGEd2b8,2704
 pyerualjetwork/fitness_functions.py,sha256=D9JVCr9DFid_xXgBD4uCKxdW2k10MVDE5HZRSOK4Igg,1237
 pyerualjetwork/help.py,sha256=Nyi0gHAN9ZnO4wgQLeENt0n7tSCZ3hJmjaJ853eGjCE,831
 pyerualjetwork/issue_solver.py,sha256=3pZTGotS29sy3pIuGQoJFUePibtSzS-tNoU80T_Usgk,3131
 pyerualjetwork/memory_ops.py,sha256=TUFh9SYWCKL6N-vNdWId_EwU313TuZomQCHOrltrD-4,14280
 pyerualjetwork/ui.py,sha256=JBTFYz5R24XwNKhA3GSW-oYAoiIBxAE3kFGXkvm5gqw,656
 pyerualjetwork/cpu/__init__.py,sha256=0yAYner_-v7SmT3P7JV2itU8xJUQdQpb40dhAMQiZkc,829
-pyerualjetwork/cpu/activation_functions.py,sha256=BVr-iP7lOl_fm91Z3Aqr22Z9gigMZSPVwtAPWlfAcQs,6676
-pyerualjetwork/cpu/data_ops.py,sha256=-XeMLRTQ5g7GMJdKYVMKJA7bSj6PbKEEpbQDRRhAIT4,16166
+pyerualjetwork/cpu/activation_functions.py,sha256=zZSoOQ452Ykp_RsHVxklxesJmmFgufyIB4F3WQjudEQ,6689
+pyerualjetwork/cpu/data_ops.py,sha256=5biKr7pqLbJOayHYgGdQV1K5GqKbcOvrbbuAyByuDC8,16154
 pyerualjetwork/cpu/ene.py,sha256=ZLCaCxkpAmFLdxDS2OH-S8fT4jKq4HNVCHgpIufb8lg,44322
 pyerualjetwork/cpu/loss_functions.py,sha256=6PyBI232SQRGuFnG3LDGvnv_PUdWzT2_2mUODJiejGI,618
 pyerualjetwork/cpu/metrics.py,sha256=WhZ8iEqWehaygPRADUlhA5j_Qv3UwqV_eMxpyRVkeVs,6070
-pyerualjetwork/cpu/model_ops.py,sha256=Rr6UvK8XSXEQm2mDNmBSkrKP_hIBhadkfEg4HPg2cTM,20508
-pyerualjetwork/cpu/nn.py,sha256=Xx7BlUMetRVgr9V59JVu6mnmASWejHMO71X5RAP4mVQ,31390
+pyerualjetwork/cpu/model_ops.py,sha256=sWsP_7Gfa8_DJ2X7AUrOkeXnz2Eej6573grQQ3CooXM,20295
+pyerualjetwork/cpu/nn.py,sha256=B8V32y0j4a85JBz11Ke_hE8hUp8kv0gQ6LDtaCiASzk,32010
 pyerualjetwork/cpu/visualizations.py,sha256=rOQsc-W8b71z7ovXSoF49lx4fmpvlaHLsyj9ejWnhnI,28164
 pyerualjetwork/cuda/__init__.py,sha256=NbqvAS4jlMdoFdXa5_hi5ukXQ5zAZR_5BQ4QAqtiKug,879
-pyerualjetwork/cuda/activation_functions.py,sha256=M-B8Vwo1IIDEWBkrL7RRzRuORhS7hcz9YgJ_uFM-UKs,6753
+pyerualjetwork/cuda/activation_functions.py,sha256=FmoSAxDr9SGO4nkE6ZflXK4pmvZ0sL3Epe1Lz-3GOVI,6766
 pyerualjetwork/cuda/data_ops.py,sha256=SiNodFNmWyTPY_KnKuAi9biPRdpTAYY3XM01bRSUPCs,18510
 pyerualjetwork/cuda/ene.py,sha256=aSCPr9VFdgK2cxxfwuP7z0jbJL9gkKNM0rgu8ihLarQ,44830
 pyerualjetwork/cuda/loss_functions.py,sha256=C93IZJcrOpT6HMK9x1O4AHJWXYTkN5WZiqdssPbvAPk,617
 pyerualjetwork/cuda/metrics.py,sha256=PjDBoRvr6va8vRvDIJJGBO4-I4uumrk3NCM1Vz4NJTo,5054
-pyerualjetwork/cuda/model_ops.py,sha256=n7x47ahEy_M8DVNQ4LU1Lc2XEYcFPG1RauUcfogJ9H8,21234
-pyerualjetwork/cuda/nn.py,sha256=xkTdnuKnKg2nieV_m0rH8XwJrxSD_39xFIcpaYtx9k0,32516
+pyerualjetwork/cuda/model_ops.py,sha256=iQPuxmthKxP2GTFLHJppxoU64C6mEpkDW-DsfwFGiuY,21020
+pyerualjetwork/cuda/nn.py,sha256=7rbaIEcmssaFgcionWVRmKijlgFyftVjf-MMNaLO_28,33140
 pyerualjetwork/cuda/visualizations.py,sha256=9l5BhXqXoeopdhLvVGvjH1TKYZb9JdKOsSE2IYD02zs,28569
-pyerualjetwork-5.31a0.dist-info/METADATA,sha256=FF31w7QXSvNcz8qm5aGsUnjX6gkHG895M4yGCPoRoOM,8135
-pyerualjetwork-5.31a0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-5.31a0.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-5.31a0.dist-info/RECORD,,
+pyerualjetwork-5.32.dist-info/METADATA,sha256=1wsSwMOifBtpBpAZE3UnFKdK8P4Bq3DUX8N_sdi-Pe4,8020
+pyerualjetwork-5.32.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-5.32.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-5.32.dist-info/RECORD,,