oikan 0.0.3.5__py3-none-any.whl → 0.0.3.7__py3-none-any.whl

oikan/model.py

@@ -41,10 +41,12 @@ class OIKAN(ABC):
         Whether to display training progress.
     evaluate_nn : bool, optional (default=False)
         Whether to evaluate neural network performance before full training.
+    random_state: int, optional (default=None)
+        Random seed for reproducibility.
     """
     def __init__(self, hidden_sizes=[64, 64], activation='relu', augmentation_factor=10, 
                  alpha=0.1, sigma=0.1, epochs=100, lr=0.001, batch_size=32, 
-                 verbose=False, evaluate_nn=False, top_k=5):
+                 verbose=False, evaluate_nn=False, top_k=5, random_state=None):
         if not isinstance(hidden_sizes, list) or not all(isinstance(x, int) and x > 0 for x in hidden_sizes):
             raise InvalidParameterError("hidden_sizes must be a list of positive integers")
         if activation not in ['relu', 'tanh', 'leaky_relu', 'elu', 'swish', 'gelu']:
@@ -78,6 +80,11 @@ class OIKAN(ABC):
         self.neural_net = None
         self.symbolic_model = None
         self.evaluation_done = False
+        self.random_state = random_state
+        
+        if self.random_state is not None:
+            torch.manual_seed(self.random_state)
+            np.random.seed(self.random_state)
 
     @abstractmethod
     def fit(self, X, y):
@@ -312,11 +319,15 @@ class OIKAN(ABC):
 
     def _generate_augmented_data(self, X):
         """Generates augmented data by adding Gaussian noise."""
+        if self.augmentation_factor == 1:
+            return np.array([]).reshape(0, X.shape[1])
+            
         X_aug = []
-        for _ in range(self.augmentation_factor):
+        for _ in range(self.augmentation_factor - 1):
             noise = np.random.normal(0, self.sigma, X.shape)
             X_perturbed = X + noise
             X_aug.append(X_perturbed)
+
         return np.vstack(X_aug)
 
     def _perform_symbolic_regression(self, X, y):
@@ -438,16 +449,33 @@ class OIKANRegressor(OIKAN):
         """
         X = np.asarray(X)
         y = np.asarray(y).reshape(-1, 1)
-        self._train_neural_net(X, y, output_size=1, loss_fn=nn.MSELoss())
-        if self.verbose:
-            print(f"Original data: features shape: {X.shape} | target shape: {y.shape}")
-        X_aug = self._generate_augmented_data(X)
-        self.neural_net.eval()
-        with torch.no_grad():
-            y_aug = self.neural_net(torch.tensor(X_aug, dtype=torch.float32)).detach().numpy()
+        
+        if self.augmentation_factor > 1:
+            self._train_neural_net(X, y, output_size=1, loss_fn=nn.MSELoss())
+            
+            if self.verbose:
+                print(f"Original data: features shape: {X.shape} | target shape: {y.shape}")
+            
+            X_aug = self._generate_augmented_data(X)
+            
+            self.neural_net.eval()
+            with torch.no_grad():
+                y_aug = self.neural_net(torch.tensor(X_aug, dtype=torch.float32)).detach().numpy()
+            
+            if self.verbose:
+                print(f"Augmented data: features shape: {X_aug.shape} | target shape: {y_aug.shape}")
+            
+            X_combined = np.vstack([X, X_aug])
+            y_combined = np.vstack([y, y_aug])
+        else:
+            if self.verbose:
+                print("Skipping neural network training (augmentation_factor=1)")
+            X_combined = X
+            y_combined = y
+            
+        self._perform_symbolic_regression(X_combined, y_combined)
         if self.verbose:
-            print(f"Augmented data: features shape: {X_aug.shape} | target shape: {y_aug.shape}")
-        self._perform_symbolic_regression(X_aug, y_aug)
+            print("OIKANRegressor model training completed successfully!")
 
     def predict(self, X):
         """
@@ -490,16 +518,33 @@ class OIKANClassifier(OIKAN):
         self.classes_ = le.classes_
         n_classes = len(self.classes_)
         y_onehot = nn.functional.one_hot(torch.tensor(y_encoded), num_classes=n_classes).float()
-        self._train_neural_net(X, y_onehot, output_size=n_classes, loss_fn=nn.CrossEntropyLoss())
-        if self.verbose:
-            print(f"Original data: features shape: {X.shape} | target shape: {y.shape}")
-        X_aug = self._generate_augmented_data(X)
-        self.neural_net.eval()
-        with torch.no_grad():
-            logits_aug = self.neural_net(torch.tensor(X_aug, dtype=torch.float32)).detach().numpy()
+        
+        if self.augmentation_factor > 1:
+            self._train_neural_net(X, y_onehot, output_size=n_classes, loss_fn=nn.CrossEntropyLoss())
+            
+            if self.verbose:
+                print(f"Original data: features shape: {X.shape} | target shape: {y.shape}")
+            
+            X_aug = self._generate_augmented_data(X)
+            
+            self.neural_net.eval()
+            with torch.no_grad():
+                logits_aug = self.neural_net(torch.tensor(X_aug, dtype=torch.float32)).detach().numpy()
+            
+            if self.verbose:
+                print(f"Augmented data: features shape: {X_aug.shape} | target shape: {logits_aug.shape}")
+            
+            X_combined = np.vstack([X, X_aug])
+            y_combined = np.vstack([y_onehot.numpy(), logits_aug])
+        else:
+            if self.verbose:
+                print("Skipping neural network training (augmentation_factor=1)")
+            X_combined = X
+            y_combined = y_onehot.numpy()
+            
+        self._perform_symbolic_regression(X_combined, y_combined)
         if self.verbose:
-            print(f"Augmented data: features shape: {X_aug.shape} | target shape: {logits_aug.shape}")
-        self._perform_symbolic_regression(X_aug, logits_aug)
+            print("OIKANClassifier model training completed successfully!")
 
     def predict(self, X):
         """

oikan/neural.py

@@ -1,4 +1,5 @@
 import torch.nn as nn
+import torch
 
 class TabularNet(nn.Module):
     """

{oikan-0.0.3.5.dist-info → oikan-0.0.3.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: oikan
-Version: 0.0.3.5
+Version: 0.0.3.7
 Summary: OIKAN: Neuro-Symbolic ML for Scientific Discovery
 Author: Arman Zhalgasbayev
 License: MIT
@@ -34,7 +34,11 @@ OIKAN is a neuro-symbolic machine learning framework inspired by Kolmogorov-Arno
 [![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
 [![GitHub issues](https://img.shields.io/github/issues/silvermete0r/OIKAN.svg)](https://github.com/silvermete0r/oikan/issues)
 [![Docs](https://img.shields.io/badge/docs-passing-brightgreen)](https://silvermete0r.github.io/oikan/)
+
 [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/silvermete0r/oikan)
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/silvermete0r/oikan/blob/main/examples/oikan-v0-0-3-get-started-template-notebook.ipynb)
+[![Open In Kaggle](https://kaggle.com/static/images/open-in-kaggle.svg)](https://www.kaggle.com/code/armanzhalgasbayev/oikan-v0-0-3-get-started-template-notebook)
+[![Static Badge](https://img.shields.io/badge/oikan-violet?style=flat&label=awesome)](https://github.com/silvermete0r/awesome-oikan)
 
 > **Important Disclaimer**: OIKAN is an experimental research project. It is not intended for production use or real-world applications. This framework is designed for research purposes, experimentation, and academic exploration of neuro-symbolic machine learning concepts.
 
@@ -111,9 +115,20 @@ cd OIKAN
 pip install -e .  # Install in development mode
 ```
 
+#### System Requirements
+
+| Requirement       | Details                              |
+|-------------------|--------------------------------------|
+| Python            | Version 3.7 or higher               |
+| Operating System  | Platform independent (Windows/macOS/Linux) |
+| Memory            | Recommended minimum 4GB RAM         |
+| Disk Space        | ~100MB for installation (including dependencies) |
+| GPU               | Optional (for faster training)      |
+| Dependencies      | torch, numpy, scikit-learn, sympy, tqdm   |
+
 ### Regression Example
 ```python
-from oikan.model import OIKANRegressor
+from oikan import OIKANRegressor
 from sklearn.metrics import mean_squared_error
 
 # Initialize model
@@ -128,7 +143,8 @@ model = OIKANRegressor(
     lr=0.001, # Learning rate
     batch_size=32, # Batch size for training
     verbose=True, # Verbose output during training
-    evaluate_nn=True # Validate neural network performance before full process
+    evaluate_nn=True, # Validate neural network performance before full process
+    random_state=42 # Random seed for reproducibility
 )
 
 # Fit the model
@@ -162,7 +178,7 @@ loaded_model.load("outputs/model.json")
 
 ### Classification Example
 ```python
-from oikan.model import OIKANClassifier
+from oikan import OIKANClassifier
 from sklearn.metrics import accuracy_score
 
 # Initialize model
@@ -177,7 +193,8 @@ model = OIKANClassifier(
     lr=0.001, # Learning rate
     batch_size=32, # Batch size for training
     verbose=True, # Verbose output during training
-    evaluate_nn=True # Validate neural network performance before full process
+    evaluate_nn=True, # Validate neural network performance before full process
+    random_state=42 # Random seed for reproducibility
 )
 
 # Fit the model
@@ -211,6 +228,12 @@ loaded_model.load("outputs/model.json")
 
 ### Architecture Diagram
 
+#### High-Level Architecture:
+
+![OIKAN v0.0.3 High-Level Architecture](https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan_v0.0.3_high_level_architecture.png)
+
+#### UML Diagram:
+
 ![OIKAN v0.0.3(2) Architecture](https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan-v0.0.3(2)-architecture-oop.png)
 
 ## OIKAN Symbolic Model Compilers

oikan-0.0.3.7.dist-info/RECORD

@@ -0,0 +1,10 @@
+oikan/__init__.py,sha256=zEzhm1GYLT4vNaIQ4CgZcNpUk3uo8SWnoaHYtHW_XSQ,628
+oikan/exceptions.py,sha256=GhHWqy2Q5LVBcteTy4ngnqxr7FOoLNyD8dNt1kfRXyw,901
+oikan/model.py,sha256=TC2-R00GOjFb7ePzKTqeYkOiVlqUK7KP0mXsnJhg9ik,24736
+oikan/neural.py,sha256=PZjaffSuABuCNxu-7PinU1GR6ji0Y6xRgSQ3n5HRDxI,1572
+oikan/utils.py,sha256=7UCm9obO-8Q2zhetdAkukMDOZvGSBWUL_dSF04XqM7k,8808
+oikan-0.0.3.7.dist-info/licenses/LICENSE,sha256=75ASVmU-XIpN-M4LbVmJ_ibgbzbvRLVti8FhnR0BTf8,1096
+oikan-0.0.3.7.dist-info/METADATA,sha256=nrel6O7TXdbtJHSNCzvqPq_IELeQWx0azfrU4Jq6sps,12749
+oikan-0.0.3.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+oikan-0.0.3.7.dist-info/top_level.txt,sha256=XwnwKwTJddZwIvtrUsAz-l-58BJRj6HjAGWrfYi_3QY,6
+oikan-0.0.3.7.dist-info/RECORD,,

{oikan-0.0.3.5.dist-info → oikan-0.0.3.7.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.4.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

oikan-0.0.3.5.dist-info/RECORD

@@ -1,10 +0,0 @@
-oikan/__init__.py,sha256=zEzhm1GYLT4vNaIQ4CgZcNpUk3uo8SWnoaHYtHW_XSQ,628
-oikan/exceptions.py,sha256=GhHWqy2Q5LVBcteTy4ngnqxr7FOoLNyD8dNt1kfRXyw,901
-oikan/model.py,sha256=Ke5FdHOr1YwnUCJieXN2VjTXhxAGxHWzCfNgw0_WYbA,23157
-oikan/neural.py,sha256=wxmGgzmtpwJ3lvH6u6D4i4BiAzg018czrIdw49phSCY,1558
-oikan/utils.py,sha256=7UCm9obO-8Q2zhetdAkukMDOZvGSBWUL_dSF04XqM7k,8808
-oikan-0.0.3.5.dist-info/licenses/LICENSE,sha256=75ASVmU-XIpN-M4LbVmJ_ibgbzbvRLVti8FhnR0BTf8,1096
-oikan-0.0.3.5.dist-info/METADATA,sha256=sUzI5w2hfUd70B4s1K5vULOvQpQbkvb239NTfS2gAPU,11388
-oikan-0.0.3.5.dist-info/WHEEL,sha256=DnLRTWE75wApRYVsjgc6wsVswC54sMSJhAEd4xhDpBk,91
-oikan-0.0.3.5.dist-info/top_level.txt,sha256=XwnwKwTJddZwIvtrUsAz-l-58BJRj6HjAGWrfYi_3QY,6
-oikan-0.0.3.5.dist-info/RECORD,,