oikan 0.0.3.5__tar.gz → 0.0.3.6__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (16) hide show
  1. {oikan-0.0.3.5 → oikan-0.0.3.6}/PKG-INFO +28 -5
  2. {oikan-0.0.3.5 → oikan-0.0.3.6}/README.md +27 -4
  3. {oikan-0.0.3.5 → oikan-0.0.3.6}/oikan/model.py +12 -1
  4. {oikan-0.0.3.5 → oikan-0.0.3.6}/oikan/neural.py +1 -0
  5. {oikan-0.0.3.5 → oikan-0.0.3.6}/oikan.egg-info/PKG-INFO +28 -5
  6. {oikan-0.0.3.5 → oikan-0.0.3.6}/pyproject.toml +1 -1
  7. {oikan-0.0.3.5 → oikan-0.0.3.6}/LICENSE +0 -0
  8. {oikan-0.0.3.5 → oikan-0.0.3.6}/oikan/__init__.py +0 -0
  9. {oikan-0.0.3.5 → oikan-0.0.3.6}/oikan/exceptions.py +0 -0
  10. {oikan-0.0.3.5 → oikan-0.0.3.6}/oikan/utils.py +0 -0
  11. {oikan-0.0.3.5 → oikan-0.0.3.6}/oikan.egg-info/SOURCES.txt +0 -0
  12. {oikan-0.0.3.5 → oikan-0.0.3.6}/oikan.egg-info/dependency_links.txt +0 -0
  13. {oikan-0.0.3.5 → oikan-0.0.3.6}/oikan.egg-info/requires.txt +0 -0
  14. {oikan-0.0.3.5 → oikan-0.0.3.6}/oikan.egg-info/top_level.txt +0 -0
  15. {oikan-0.0.3.5 → oikan-0.0.3.6}/setup.cfg +0 -0
  16. {oikan-0.0.3.5 → oikan-0.0.3.6}/setup.py +0 -0
{oikan-0.0.3.5 → oikan-0.0.3.6}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: oikan
3
- Version: 0.0.3.5
3
+ Version: 0.0.3.6
4
4
  Summary: OIKAN: Neuro-Symbolic ML for Scientific Discovery
5
5
  Author: Arman Zhalgasbayev
6
6
  License: MIT
@@ -34,7 +34,11 @@ OIKAN is a neuro-symbolic machine learning framework inspired by Kolmogorov-Arno
34
34
  [![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
35
35
  [![GitHub issues](https://img.shields.io/github/issues/silvermete0r/OIKAN.svg)](https://github.com/silvermete0r/oikan/issues)
36
36
  [![Docs](https://img.shields.io/badge/docs-passing-brightgreen)](https://silvermete0r.github.io/oikan/)
37
+
37
38
  [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/silvermete0r/oikan)
39
+ [![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)
40
+ [![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)
41
+ [![Static Badge](https://img.shields.io/badge/oikan-violet?style=flat&label=awesome)](https://github.com/silvermete0r/awesome-oikan)
38
42
 
39
43
  > **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.
40
44
 
@@ -111,9 +115,20 @@ cd OIKAN
111
115
  pip install -e . # Install in development mode
112
116
  ```
113
117
 
118
+ #### System Requirements
119
+
120
+ | Requirement | Details |
121
+ |-------------------|--------------------------------------|
122
+ | Python | Version 3.7 or higher |
123
+ | Operating System | Platform independent (Windows/macOS/Linux) |
124
+ | Memory | Recommended minimum 4GB RAM |
125
+ | Disk Space | ~100MB for installation (including dependencies) |
126
+ | GPU | Optional (for faster training) |
127
+ | Dependencies | torch, numpy, scikit-learn, sympy, tqdm |
128
+
114
129
  ### Regression Example
115
130
  ```python
116
- from oikan.model import OIKANRegressor
131
+ from oikan import OIKANRegressor
117
132
  from sklearn.metrics import mean_squared_error
118
133
 
119
134
  # Initialize model
@@ -128,7 +143,8 @@ model = OIKANRegressor(
128
143
  lr=0.001, # Learning rate
129
144
  batch_size=32, # Batch size for training
130
145
  verbose=True, # Verbose output during training
131
- evaluate_nn=True # Validate neural network performance before full process
146
+ evaluate_nn=True, # Validate neural network performance before full process
147
+ random_state=42 # Random seed for reproducibility
132
148
  )
133
149
 
134
150
  # Fit the model
@@ -162,7 +178,7 @@ loaded_model.load("outputs/model.json")
162
178
 
163
179
  ### Classification Example
164
180
  ```python
165
- from oikan.model import OIKANClassifier
181
+ from oikan import OIKANClassifier
166
182
  from sklearn.metrics import accuracy_score
167
183
 
168
184
  # Initialize model
@@ -177,7 +193,8 @@ model = OIKANClassifier(
177
193
  lr=0.001, # Learning rate
178
194
  batch_size=32, # Batch size for training
179
195
  verbose=True, # Verbose output during training
180
- evaluate_nn=True # Validate neural network performance before full process
196
+ evaluate_nn=True, # Validate neural network performance before full process
197
+ random_state=42 # Random seed for reproducibility
181
198
  )
182
199
 
183
200
  # Fit the model
@@ -211,6 +228,12 @@ loaded_model.load("outputs/model.json")
211
228
 
212
229
  ### Architecture Diagram
213
230
 
231
+ #### High-Level Architecture:
232
+
233
+ ![OIKAN v0.0.3 High-Level Architecture](https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan_v0.0.3_high_level_architecture.png)
234
+
235
+ #### UML Diagram:
236
+
214
237
  ![OIKAN v0.0.3(2) Architecture](https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan-v0.0.3(2)-architecture-oop.png)
215
238
 
216
239
  ## OIKAN Symbolic Model Compilers
{oikan-0.0.3.5 → oikan-0.0.3.6}/README.md RENAMED
@@ -15,7 +15,11 @@ OIKAN is a neuro-symbolic machine learning framework inspired by Kolmogorov-Arno
15
15
  [![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
16
16
  [![GitHub issues](https://img.shields.io/github/issues/silvermete0r/OIKAN.svg)](https://github.com/silvermete0r/oikan/issues)
17
17
  [![Docs](https://img.shields.io/badge/docs-passing-brightgreen)](https://silvermete0r.github.io/oikan/)
18
+
18
19
  [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/silvermete0r/oikan)
20
+ [![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)
21
+ [![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)
22
+ [![Static Badge](https://img.shields.io/badge/oikan-violet?style=flat&label=awesome)](https://github.com/silvermete0r/awesome-oikan)
19
23
 
20
24
  > **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.
21
25
 
@@ -92,9 +96,20 @@ cd OIKAN
92
96
  pip install -e . # Install in development mode
93
97
  ```
94
98
 
99
+ #### System Requirements
100
+
101
+ | Requirement | Details |
102
+ |-------------------|--------------------------------------|
103
+ | Python | Version 3.7 or higher |
104
+ | Operating System | Platform independent (Windows/macOS/Linux) |
105
+ | Memory | Recommended minimum 4GB RAM |
106
+ | Disk Space | ~100MB for installation (including dependencies) |
107
+ | GPU | Optional (for faster training) |
108
+ | Dependencies | torch, numpy, scikit-learn, sympy, tqdm |
109
+
95
110
  ### Regression Example
96
111
  ```python
97
- from oikan.model import OIKANRegressor
112
+ from oikan import OIKANRegressor
98
113
  from sklearn.metrics import mean_squared_error
99
114
 
100
115
  # Initialize model
@@ -109,7 +124,8 @@ model = OIKANRegressor(
109
124
  lr=0.001, # Learning rate
110
125
  batch_size=32, # Batch size for training
111
126
  verbose=True, # Verbose output during training
112
- evaluate_nn=True # Validate neural network performance before full process
127
+ evaluate_nn=True, # Validate neural network performance before full process
128
+ random_state=42 # Random seed for reproducibility
113
129
  )
114
130
 
115
131
  # Fit the model
@@ -143,7 +159,7 @@ loaded_model.load("outputs/model.json")
143
159
 
144
160
  ### Classification Example
145
161
  ```python
146
- from oikan.model import OIKANClassifier
162
+ from oikan import OIKANClassifier
147
163
  from sklearn.metrics import accuracy_score
148
164
 
149
165
  # Initialize model
@@ -158,7 +174,8 @@ model = OIKANClassifier(
158
174
  lr=0.001, # Learning rate
159
175
  batch_size=32, # Batch size for training
160
176
  verbose=True, # Verbose output during training
161
- evaluate_nn=True # Validate neural network performance before full process
177
+ evaluate_nn=True, # Validate neural network performance before full process
178
+ random_state=42 # Random seed for reproducibility
162
179
  )
163
180
 
164
181
  # Fit the model
@@ -192,6 +209,12 @@ loaded_model.load("outputs/model.json")
192
209
 
193
210
  ### Architecture Diagram
194
211
 
212
+ #### High-Level Architecture:
213
+
214
+ ![OIKAN v0.0.3 High-Level Architecture](https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan_v0.0.3_high_level_architecture.png)
215
+
216
+ #### UML Diagram:
217
+
195
218
  ![OIKAN v0.0.3(2) Architecture](https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan-v0.0.3(2)-architecture-oop.png)
196
219
 
197
220
  ## OIKAN Symbolic Model Compilers
{oikan-0.0.3.5 → oikan-0.0.3.6}/oikan/model.py RENAMED
@@ -41,10 +41,12 @@ class OIKAN(ABC):
41
41
  Whether to display training progress.
42
42
  evaluate_nn : bool, optional (default=False)
43
43
  Whether to evaluate neural network performance before full training.
44
+ random_state: int, optional (default=None)
45
+ Random seed for reproducibility.
44
46
  """
45
47
  def __init__(self, hidden_sizes=[64, 64], activation='relu', augmentation_factor=10,
46
48
  alpha=0.1, sigma=0.1, epochs=100, lr=0.001, batch_size=32,
47
- verbose=False, evaluate_nn=False, top_k=5):
49
+ verbose=False, evaluate_nn=False, top_k=5, random_state=None):
48
50
  if not isinstance(hidden_sizes, list) or not all(isinstance(x, int) and x > 0 for x in hidden_sizes):
49
51
  raise InvalidParameterError("hidden_sizes must be a list of positive integers")
50
52
  if activation not in ['relu', 'tanh', 'leaky_relu', 'elu', 'swish', 'gelu']:
@@ -78,6 +80,11 @@ class OIKAN(ABC):
78
80
  self.neural_net = None
79
81
  self.symbolic_model = None
80
82
  self.evaluation_done = False
83
+ self.random_state = random_state
84
+
85
+ if self.random_state is not None:
86
+ torch.manual_seed(self.random_state)
87
+ np.random.seed(self.random_state)
81
88
 
82
89
  @abstractmethod
83
90
  def fit(self, X, y):
@@ -448,6 +455,8 @@ class OIKANRegressor(OIKAN):
448
455
  if self.verbose:
449
456
  print(f"Augmented data: features shape: {X_aug.shape} | target shape: {y_aug.shape}")
450
457
  self._perform_symbolic_regression(X_aug, y_aug)
458
+ if self.verbose:
459
+ print("OIKANRegressor model training completed successfully!")
451
460
 
452
461
  def predict(self, X):
453
462
  """
@@ -500,6 +509,8 @@ class OIKANClassifier(OIKAN):
500
509
  if self.verbose:
501
510
  print(f"Augmented data: features shape: {X_aug.shape} | target shape: {logits_aug.shape}")
502
511
  self._perform_symbolic_regression(X_aug, logits_aug)
512
+ if self.verbose:
513
+ print("OIKANClassifier model training completed successfully!")
503
514
 
504
515
  def predict(self, X):
505
516
  """
{oikan-0.0.3.5 → oikan-0.0.3.6}/oikan/neural.py RENAMED
@@ -1,4 +1,5 @@
1
1
  import torch.nn as nn
2
+ import torch
2
3
 
3
4
  class TabularNet(nn.Module):
4
5
  """
{oikan-0.0.3.5 → oikan-0.0.3.6}/oikan.egg-info/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: oikan
3
- Version: 0.0.3.5
3
+ Version: 0.0.3.6
4
4
  Summary: OIKAN: Neuro-Symbolic ML for Scientific Discovery
5
5
  Author: Arman Zhalgasbayev
6
6
  License: MIT
@@ -34,7 +34,11 @@ OIKAN is a neuro-symbolic machine learning framework inspired by Kolmogorov-Arno
34
34
  [![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
35
35
  [![GitHub issues](https://img.shields.io/github/issues/silvermete0r/OIKAN.svg)](https://github.com/silvermete0r/oikan/issues)
36
36
  [![Docs](https://img.shields.io/badge/docs-passing-brightgreen)](https://silvermete0r.github.io/oikan/)
37
+
37
38
  [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/silvermete0r/oikan)
39
+ [![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)
40
+ [![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)
41
+ [![Static Badge](https://img.shields.io/badge/oikan-violet?style=flat&label=awesome)](https://github.com/silvermete0r/awesome-oikan)
38
42
 
39
43
  > **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.
40
44
 
@@ -111,9 +115,20 @@ cd OIKAN
111
115
  pip install -e . # Install in development mode
112
116
  ```
113
117
 
118
+ #### System Requirements
119
+
120
+ | Requirement | Details |
121
+ |-------------------|--------------------------------------|
122
+ | Python | Version 3.7 or higher |
123
+ | Operating System | Platform independent (Windows/macOS/Linux) |
124
+ | Memory | Recommended minimum 4GB RAM |
125
+ | Disk Space | ~100MB for installation (including dependencies) |
126
+ | GPU | Optional (for faster training) |
127
+ | Dependencies | torch, numpy, scikit-learn, sympy, tqdm |
128
+
114
129
  ### Regression Example
115
130
  ```python
116
- from oikan.model import OIKANRegressor
131
+ from oikan import OIKANRegressor
117
132
  from sklearn.metrics import mean_squared_error
118
133
 
119
134
  # Initialize model
@@ -128,7 +143,8 @@ model = OIKANRegressor(
128
143
  lr=0.001, # Learning rate
129
144
  batch_size=32, # Batch size for training
130
145
  verbose=True, # Verbose output during training
131
- evaluate_nn=True # Validate neural network performance before full process
146
+ evaluate_nn=True, # Validate neural network performance before full process
147
+ random_state=42 # Random seed for reproducibility
132
148
  )
133
149
 
134
150
  # Fit the model
@@ -162,7 +178,7 @@ loaded_model.load("outputs/model.json")
162
178
 
163
179
  ### Classification Example
164
180
  ```python
165
- from oikan.model import OIKANClassifier
181
+ from oikan import OIKANClassifier
166
182
  from sklearn.metrics import accuracy_score
167
183
 
168
184
  # Initialize model
@@ -177,7 +193,8 @@ model = OIKANClassifier(
177
193
  lr=0.001, # Learning rate
178
194
  batch_size=32, # Batch size for training
179
195
  verbose=True, # Verbose output during training
180
- evaluate_nn=True # Validate neural network performance before full process
196
+ evaluate_nn=True, # Validate neural network performance before full process
197
+ random_state=42 # Random seed for reproducibility
181
198
  )
182
199
 
183
200
  # Fit the model
@@ -211,6 +228,12 @@ loaded_model.load("outputs/model.json")
211
228
 
212
229
  ### Architecture Diagram
213
230
 
231
+ #### High-Level Architecture:
232
+
233
+ ![OIKAN v0.0.3 High-Level Architecture](https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan_v0.0.3_high_level_architecture.png)
234
+
235
+ #### UML Diagram:
236
+
214
237
  ![OIKAN v0.0.3(2) Architecture](https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan-v0.0.3(2)-architecture-oop.png)
215
238
 
216
239
  ## OIKAN Symbolic Model Compilers
{oikan-0.0.3.5 → oikan-0.0.3.6}/pyproject.toml RENAMED
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
4
4
 
5
5
  [project]
6
6
  name = "oikan"
7
- version = "0.0.3.5"
7
+ version = "0.0.3.6"
8
8
  description = "OIKAN: Neuro-Symbolic ML for Scientific Discovery"
9
9
  readme = "README.md"
10
10
  authors = [{name = "Arman Zhalgasbayev"}]
{oikan-0.0.3.5 → oikan-0.0.3.6}/LICENSE RENAMED
File without changes
{oikan-0.0.3.5 → oikan-0.0.3.6}/oikan/__init__.py RENAMED
File without changes
{oikan-0.0.3.5 → oikan-0.0.3.6}/oikan/exceptions.py RENAMED
File without changes
{oikan-0.0.3.5 → oikan-0.0.3.6}/oikan/utils.py RENAMED
File without changes
{oikan-0.0.3.5 → oikan-0.0.3.6}/setup.cfg RENAMED
File without changes
{oikan-0.0.3.5 → oikan-0.0.3.6}/setup.py RENAMED
File without changes