oikan 0.0.3.3__tar.gz → 0.0.3.4__tar.gz

{oikan-0.0.3.3 → oikan-0.0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: oikan
-Version: 0.0.3.3
+Version: 0.0.3.4
 Summary: OIKAN: Neuro-Symbolic ML for Scientific Discovery
 Author: Arman Zhalgasbayev
 License: MIT
@@ -14,6 +14,7 @@ Requires-Dist: torch
 Requires-Dist: numpy
 Requires-Dist: scikit-learn
 Requires-Dist: tqdm
+Requires-Dist: sympy
 Dynamic: license-file
 
 <!-- logo in the center -->
@@ -118,7 +119,6 @@ model = OIKANRegressor(
     hidden_sizes=[32, 32], # Hidden layer sizes
     activation='relu', # Activation function (other options: 'tanh', 'leaky_relu', 'elu', 'swish', 'gelu')
     augmentation_factor=5, # Augmentation factor for data generation
-    polynomial_degree=2, # Degree of polynomial basis functions
     alpha=0.1, # L1 regularization strength (Symbolic regression)
     sigma=0.1, # Standard deviation of Gaussian noise for data augmentation
     top_k=5, # Number of top features to select (Symbolic regression)
@@ -140,7 +140,7 @@ mse = mean_squared_error(y_test, y_pred)
 print("Mean Squared Error:", mse)
 
 # Get symbolic formula
-formula = model.get_formula()
+formula = model.get_formula() # default: type='original' -> returns all formula without pruning | other options: 'sympied' -> simplified formula using sympy; 'latex' -> LaTeX format
 print("Symbolic Formula:", formula)
 
 # Get feature importances
@@ -168,7 +168,6 @@ model = OIKANClassifier(
     hidden_sizes=[32, 32], # Hidden layer sizes
     activation='relu', # Activation function (other options: 'tanh', 'leaky_relu', 'elu', 'swish', 'gelu')
     augmentation_factor=10, # Augmentation factor for data generation
-    polynomial_degree=2, # Degree of polynomial basis functions
     alpha=0.1, # L1 regularization strength (Symbolic regression)
     sigma=0.1, # Standard deviation of Gaussian noise for data augmentation
     top_k=5, # Number of top features to select (Symbolic regression)
@@ -190,7 +189,7 @@ accuracy = model.score(X_test, y_test)
 print("Accuracy:", accuracy)
 
 # Get symbolic formulas for each class
-formulas = model.get_formula()
+formulas = model.get_formula() # default: type='original' -> returns all formula without pruning | other options: 'sympied' -> simplified formula using sympy; 'latex' -> LaTeX format
 for i, formula in enumerate(formulas):
     print(f"Class {i} Formula:", formula)
    
@@ -212,6 +211,60 @@ loaded_model.load("outputs/model.json")
 
 ![OIKAN v0.0.3(1) Architecture](https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan-v0.0.3(1)-architecture-oop.png)
 
+## OIKAN Symbolic Model Compilers
+
+OIKAN provides a set of symbolic model compilers to convert the symbolic formulas generated by the OIKAN model into different programming languages. 
+
+*Currently, we support: `Python`, `C++`, `C`, `JavaScript`, `Rust`, and `Go`. This allows users to easily integrate the generated formulas into their applications or systems.*
+
+All compilers: [model_compilers/](model_compilers)
+
+### Example of Python Compiler
+
+1. Regression Model:
+```python
+import numpy as np
+import json
+
+def predict(X, symbolic_model):
+    X = np.asarray(X)
+    X_transformed = evaluate_basis_functions(X, symbolic_model['basis_functions'], 
+                                            symbolic_model['n_features'])
+    return np.dot(X_transformed, symbolic_model['coefficients'])
+
+if __name__ == "__main__":
+    with open('outputs/california_housing_model.json', 'r') as f:
+        symbolic_model = json.load(f)
+    X = np.random.rand(10, symbolic_model['n_features'])
+    y_pred = predict(X, symbolic_model)
+    print(y_pred)
+```
+
+2. Classification Model:
+```python
+import numpy as np
+import json
+
+def predict(X, symbolic_model):
+    X = np.asarray(X)
+    X_transformed = evaluate_basis_functions(X, symbolic_model['basis_functions'], 
+                                            symbolic_model['n_features'])
+    logits = np.dot(X_transformed, np.array(symbolic_model['coefficients_list']).T)
+    probabilities = np.exp(logits) / np.sum(np.exp(logits), axis=1, keepdims=True)
+    return np.argmax(probabilities, axis=1)
+
+if __name__ == "__main__":
+    with open('outputs/iris_model.json', 'r') as f:
+        symbolic_model = json.load(f)
+    X = np.array([[5.1, 3.5, 1.4, 0.2],
+                  [7.0, 3.2, 4.7, 1.4],
+                  [6.3, 3.3, 6.0, 2.5]])
+    y_pred = predict(X, symbolic_model)
+    print(y_pred)
+```
+
+
+
 ## Contributing
 
 We welcome contributions! Key areas of interest:

{oikan-0.0.3.3 → oikan-0.0.3.4}/README.md

@@ -100,7 +100,6 @@ model = OIKANRegressor(
     hidden_sizes=[32, 32], # Hidden layer sizes
     activation='relu', # Activation function (other options: 'tanh', 'leaky_relu', 'elu', 'swish', 'gelu')
     augmentation_factor=5, # Augmentation factor for data generation
-    polynomial_degree=2, # Degree of polynomial basis functions
     alpha=0.1, # L1 regularization strength (Symbolic regression)
     sigma=0.1, # Standard deviation of Gaussian noise for data augmentation
     top_k=5, # Number of top features to select (Symbolic regression)
@@ -122,7 +121,7 @@ mse = mean_squared_error(y_test, y_pred)
 print("Mean Squared Error:", mse)
 
 # Get symbolic formula
-formula = model.get_formula()
+formula = model.get_formula() # default: type='original' -> returns all formula without pruning | other options: 'sympied' -> simplified formula using sympy; 'latex' -> LaTeX format
 print("Symbolic Formula:", formula)
 
 # Get feature importances
@@ -150,7 +149,6 @@ model = OIKANClassifier(
     hidden_sizes=[32, 32], # Hidden layer sizes
     activation='relu', # Activation function (other options: 'tanh', 'leaky_relu', 'elu', 'swish', 'gelu')
     augmentation_factor=10, # Augmentation factor for data generation
-    polynomial_degree=2, # Degree of polynomial basis functions
     alpha=0.1, # L1 regularization strength (Symbolic regression)
     sigma=0.1, # Standard deviation of Gaussian noise for data augmentation
     top_k=5, # Number of top features to select (Symbolic regression)
@@ -172,7 +170,7 @@ accuracy = model.score(X_test, y_test)
 print("Accuracy:", accuracy)
 
 # Get symbolic formulas for each class
-formulas = model.get_formula()
+formulas = model.get_formula() # default: type='original' -> returns all formula without pruning | other options: 'sympied' -> simplified formula using sympy; 'latex' -> LaTeX format
 for i, formula in enumerate(formulas):
     print(f"Class {i} Formula:", formula)
    
@@ -194,6 +192,60 @@ loaded_model.load("outputs/model.json")
 
 ![OIKAN v0.0.3(1) Architecture](https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan-v0.0.3(1)-architecture-oop.png)
 
+## OIKAN Symbolic Model Compilers
+
+OIKAN provides a set of symbolic model compilers to convert the symbolic formulas generated by the OIKAN model into different programming languages. 
+
+*Currently, we support: `Python`, `C++`, `C`, `JavaScript`, `Rust`, and `Go`. This allows users to easily integrate the generated formulas into their applications or systems.*
+
+All compilers: [model_compilers/](model_compilers)
+
+### Example of Python Compiler
+
+1. Regression Model:
+```python
+import numpy as np
+import json
+
+def predict(X, symbolic_model):
+    X = np.asarray(X)
+    X_transformed = evaluate_basis_functions(X, symbolic_model['basis_functions'], 
+                                            symbolic_model['n_features'])
+    return np.dot(X_transformed, symbolic_model['coefficients'])
+
+if __name__ == "__main__":
+    with open('outputs/california_housing_model.json', 'r') as f:
+        symbolic_model = json.load(f)
+    X = np.random.rand(10, symbolic_model['n_features'])
+    y_pred = predict(X, symbolic_model)
+    print(y_pred)
+```
+
+2. Classification Model:
+```python
+import numpy as np
+import json
+
+def predict(X, symbolic_model):
+    X = np.asarray(X)
+    X_transformed = evaluate_basis_functions(X, symbolic_model['basis_functions'], 
+                                            symbolic_model['n_features'])
+    logits = np.dot(X_transformed, np.array(symbolic_model['coefficients_list']).T)
+    probabilities = np.exp(logits) / np.sum(np.exp(logits), axis=1, keepdims=True)
+    return np.argmax(probabilities, axis=1)
+
+if __name__ == "__main__":
+    with open('outputs/iris_model.json', 'r') as f:
+        symbolic_model = json.load(f)
+    X = np.array([[5.1, 3.5, 1.4, 0.2],
+                  [7.0, 3.2, 4.7, 1.4],
+                  [6.3, 3.3, 6.0, 2.5]])
+    y_pred = predict(X, symbolic_model)
+    print(y_pred)
+```
+
+
+
 ## Contributing
 
 We welcome contributions! Key areas of interest:

{oikan-0.0.3.3 → oikan-0.0.3.4}/oikan/model.py

@@ -7,7 +7,7 @@ from sklearn.linear_model import ElasticNet
 from abc import ABC, abstractmethod
 import json
 from .neural import TabularNet
-from .utils import evaluate_basis_functions, get_features_involved
+from .utils import evaluate_basis_functions, get_features_involved, sympify_formula, get_latex_formula
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import r2_score, accuracy_score
 from .exceptions import *
@@ -25,8 +25,6 @@ class OIKAN(ABC):
         Activation function for the neural network ('relu', 'tanh', 'leaky_relu', 'elu', 'swish', 'gelu').
     augmentation_factor : int, optional (default=10)
         Number of augmented samples per original sample.
-    polynomial_degree : int, optional (default=2)
-        Maximum degree of polynomial features for symbolic regression.
     alpha : float, optional (default=0.1)
         L1 regularization strength for Lasso in symbolic regression.
     sigma : float, optional (default=0.1)
@@ -45,7 +43,7 @@ class OIKAN(ABC):
         Whether to evaluate neural network performance before full training.
     """
     def __init__(self, hidden_sizes=[64, 64], activation='relu', augmentation_factor=10, 
-                 polynomial_degree=2, alpha=0.1, sigma=0.1, epochs=100, lr=0.001, batch_size=32, 
+                 alpha=0.1, sigma=0.1, epochs=100, lr=0.001, batch_size=32, 
                  verbose=False, evaluate_nn=False, top_k=5):
         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")
@@ -53,8 +51,6 @@ class OIKAN(ABC):
             raise InvalidParameterError(f"Unsupported activation function: {activation}")
         if not isinstance(augmentation_factor, int) or augmentation_factor < 1:
             raise InvalidParameterError("augmentation_factor must be a positive integer")
-        if not isinstance(polynomial_degree, int) or polynomial_degree < 1:
-            raise InvalidParameterError("polynomial_degree must be a positive integer")
         if not isinstance(top_k, int) or top_k < 1:
             raise InvalidParameterError("top_k must be a positive integer")
         if not 0 < lr < 1:
@@ -71,7 +67,6 @@ class OIKAN(ABC):
         self.hidden_sizes = hidden_sizes
         self.activation = activation
         self.augmentation_factor = augmentation_factor
-        self.polynomial_degree = polynomial_degree
         self.alpha = alpha
         self.sigma = sigma
         self.epochs = epochs
@@ -92,23 +87,53 @@ class OIKAN(ABC):
     def predict(self, X):
         pass
 
-    def get_formula(self):
-        """Returns the symbolic formula(s) as a string (regression) or list of strings (classification)."""
+    def get_formula(self, type='original'): 
+        """
+        Returns the symbolic formula(s) as a string (regression) or list of strings (classification). 
+        
+        Parameter:
+        --------
+        type : str, optional (default='original') other options: 'sympied', 'latex'
+            'original' returns the original formula with coefficients, 'sympied' returns sympy simplified formula.
+        """
+        if type.lower() not in ['original', 'sympied', 'latex']:
+            raise InvalidParameterError("Invalid type. Choose 'original', 'sympied', 'latex'.")
         if self.symbolic_model is None:
             raise ValueError("Model not fitted yet.")
         basis_functions = self.symbolic_model['basis_functions']
-        if 'coefficients' in self.symbolic_model:
-            coefficients = self.symbolic_model['coefficients']
-            formula = " + ".join([f"{coefficients[i]:.5f}*{basis_functions[i]}" 
-                                for i in range(len(coefficients)) if coefficients[i] != 0])
-            return formula if formula else "0"
+        if type.lower() == 'original':
+            if 'coefficients' in self.symbolic_model:
+                coefficients = self.symbolic_model['coefficients']
+                formula = " + ".join([f"{coefficients[i]:.6f}*{basis_functions[i]}" 
+                                    for i in range(len(coefficients)) if coefficients[i] != 0])
+                return formula if formula else "0"
+            else:
+                formulas = []
+                for c, coef in enumerate(self.symbolic_model['coefficients_list']):
+                    formula = " + ".join([f"{coef[i]:.6f}*{basis_functions[i]}" 
+                                        for i in range(len(coef)) if coef[i] != 0])
+                    formulas.append(f"Class {self.classes_[c]}: {formula if formula else '0'}")
+                return formulas
+        elif type.lower() == 'sympied':
+            if 'coefficients' in self.symbolic_model:
+                formula = sympify_formula(self.symbolic_model['basis_functions'], self.symbolic_model['coefficients'], self.symbolic_model['n_features'])
+                return formula
+            else: 
+                formulas = []
+                for c, coef in enumerate(self.symbolic_model['coefficients_list']):
+                    formula = sympify_formula(self.symbolic_model['basis_functions'], coef, self.symbolic_model['n_features'])
+                    formulas.append(f"Class {self.classes_[c]}: {formula}")
+                return formulas
         else:
-            formulas = []
-            for c, coef in enumerate(self.symbolic_model['coefficients_list']):
-                formula = " + ".join([f"{coef[i]:.5f}*{basis_functions[i]}" 
-                                    for i in range(len(coef)) if coef[i] != 0])
-                formulas.append(f"Class {self.classes_[c]}: {formula if formula else '0'}")
-            return formulas
+            if 'coefficients' in self.symbolic_model:
+                formula = get_latex_formula(self.symbolic_model['basis_functions'], self.symbolic_model['coefficients'], self.symbolic_model['n_features'])
+                return formula
+            else: 
+                formulas = []
+                for c, coef in enumerate(self.symbolic_model['coefficients_list']):
+                    formula = get_latex_formula(self.symbolic_model['basis_functions'], coef, self.symbolic_model['n_features'])
+                    formulas.append(f"Class {self.classes_[c]}: {formula}")
+                return formulas
 
     def feature_importances(self):
         """
@@ -163,7 +188,6 @@ class OIKAN(ABC):
             # Convert numpy arrays and other non-serializable types to lists
             model_data = {
                 'n_features': self.symbolic_model['n_features'],
-                'degree': self.symbolic_model['degree'],
                 'basis_functions': self.symbolic_model['basis_functions']
             }
             
@@ -200,7 +224,6 @@ class OIKAN(ABC):
                 
             self.symbolic_model = {
                 'n_features': model_data['n_features'],
-                'degree': model_data['degree'],
                 'basis_functions': model_data['basis_functions']
             }
             
@@ -222,7 +245,6 @@ class OIKAN(ABC):
         
         input_size = X.shape[1]
         self.neural_net = TabularNet(input_size, self.hidden_sizes, output_size, self.activation)
-        optimizer = optim.Adam(self.neural_net.parameters(), lr=self.lr)
         
         # Train on the training set
         self._train_neural_net(X_train, y_train, output_size, loss_fn)
@@ -378,7 +400,6 @@ class OIKAN(ABC):
             selected_indices = np.where(np.abs(coef_refined) > 1e-6)[0]
             self.symbolic_model = {
                 'n_features': X.shape[1],
-                'degree': self.polynomial_degree, 
                 'basis_functions': [basis_functions_refined[i] for i in selected_indices],
                 'coefficients': coef_refined[selected_indices].tolist()
             }
@@ -398,7 +419,6 @@ class OIKAN(ABC):
                 coefficients_list.append(coef_selected)
             self.symbolic_model = {
                 'n_features': X.shape[1],
-                'degree': self.polynomial_degree,
                 'basis_functions': basis_functions,
                 'coefficients_list': coefficients_list
             }

oikan-0.0.3.4/oikan/utils.py

@@ -0,0 +1,256 @@
+import numpy as np
+import sympy as sp
+import json
+from functools import lru_cache
+
+def evaluate_basis_functions(X, basis_functions, n_features):
+    """
+    Evaluates basis functions on the input data.
+    
+    Parameters:
+    -----------
+    X : array-like of shape (n_samples, n_features)
+        Input data.
+    basis_functions : list
+        List of basis function strings (e.g., '1', 'x0', 'x0^2', 'x0 x1', 'log1p_x0').
+    n_features : int
+        Number of input features.
+    
+    Returns:
+    --------
+    X_transformed : ndarray of shape (n_samples, n_basis_functions)
+        Transformed data matrix.
+    """
+    X_transformed = np.zeros((X.shape[0], len(basis_functions)))
+    for i, func in enumerate(basis_functions):
+        if func == '1':
+            X_transformed[:, i] = 1
+        elif func.startswith('log1p_x'):
+            idx = int(func.split('_')[1][1:])
+            X_transformed[:, i] = np.log1p(np.abs(X[:, idx]))
+        elif func.startswith('exp_x'):
+            idx = int(func.split('_')[1][1:])
+            X_transformed[:, i] = np.exp(np.clip(X[:, idx], -10, 10))
+        elif func.startswith('sin_x'):
+            idx = int(func.split('_')[1][1:])
+            X_transformed[:, i] = np.sin(X[:, idx])
+        elif '^' in func:
+            var, power = func.split('^')
+            idx = int(var[1:])
+            X_transformed[:, i] = X[:, idx] ** int(power)
+        elif ' ' in func:
+            vars = func.split(' ')
+            result = np.ones(X.shape[0])
+            for var in vars:
+                idx = int(var[1:])
+                result *= X[:, idx]
+            X_transformed[:, i] = result
+        else:
+            idx = int(func[1:])
+            X_transformed[:, i] = X[:, idx]
+    return X_transformed
+
+def get_features_involved(basis_function):
+    """
+    Extracts the feature indices involved in a basis function string.
+    
+    Parameters:
+    -----------
+    basis_function : str
+        String representation of the basis function, e.g., 'x0', 'x0^2', 'x0 x1', 'log1p_x0'.
+    
+    Returns:
+    --------
+    set : Set of feature indices involved.
+    """
+    if basis_function == '1':
+        return set()
+    features = set()
+    if '_' in basis_function:  # Handle non-linear functions like 'log1p_x0'
+        parts = basis_function.split('_')
+        if len(parts) == 2 and parts[1].startswith('x'):
+            idx = int(parts[1][1:])
+            features.add(idx)
+    elif '^' in basis_function:  # Handle powers, e.g., 'x0^2'
+        var = basis_function.split('^')[0]
+        idx = int(var[1:])
+        features.add(idx)
+    elif ' ' in basis_function:  # Handle interactions, e.g., 'x0 x1'
+        for part in basis_function.split():
+            idx = int(part[1:])
+            features.add(idx)
+    elif basis_function.startswith('x'):
+        idx = int(basis_function[1:])
+        features.add(idx)
+    return features
+
+@lru_cache(maxsize=1000)
+def _cached_sympify_formula(basis_functions_tuple, coefficients_tuple, n_features, threshold):
+    """
+    Internal function to perform SymPy formula simplification with caching.
+    
+    Parameters:
+    -----------
+    basis_functions_tuple : tuple
+        Tuple of basis function strings.
+    coefficients_tuple : tuple
+        Tuple of coefficients.
+    n_features : int
+        Number of input features.
+    threshold : float
+        Coefficients with absolute value below this are excluded.
+    
+    Returns:
+    --------
+    str
+        Simplified formula as a string, or '0' if empty.
+    """
+    # Convert tuples back to lists
+    basis_functions = list(basis_functions_tuple)
+    coefficients = list(coefficients_tuple)
+    
+    # Define symbolic variables
+    x = sp.symbols(f'x0:{n_features}')
+    expr = 0
+    
+    # Build the expression
+    for coef, func in zip(coefficients, basis_functions):
+        if abs(coef) < threshold:
+            continue  # Skip negligible coefficients
+        if func == '1':
+            term = coef
+        elif func.startswith('log1p_x'):
+            idx = int(func.split('_')[1][1:])
+            term = coef * sp.log(1 + sp.Abs(x[idx]))
+        elif func.startswith('exp_x'):
+            idx = int(func.split('_')[1][1:])
+            term = coef * sp.exp(x[idx])
+        elif func.startswith('sin_x'):
+            idx = int(func.split('_')[1][1:])
+            term = coef * sp.sin(x[idx])
+        elif '^' in func:
+            var, power = func.split('^')
+            idx = int(var[1:])
+            term = coef * x[idx]**int(power)
+        elif ' ' in func:
+            vars = func.split(' ')
+            term = coef
+            for var in vars:
+                idx = int(var[1:])
+                term *= x[idx]
+        else:
+            idx = int(func[1:])
+            term = coef * x[idx]
+        expr += term
+    
+    # Simplify the expression
+    simplified_expr = sp.simplify(expr)
+    
+    # Convert to string with rounded coefficients
+    def format_term(term):
+        if term.is_Mul:
+            coeff = 1
+            factors = []
+            for factor in term.args:
+                if factor.is_Number:
+                    coeff *= float(factor)
+                else:
+                    factors.append(str(factor))
+            if abs(coeff) < threshold:
+                return None
+            return f"{coeff:.5f}*{'*'.join(factors)}" if factors else f"{coeff:.5f}"
+        elif term.is_Add:
+            return None  # Handle in recursion
+        elif term.is_Number:
+            return f"{float(term):.5f}" if abs(float(term)) >= threshold else None
+        else:
+            return f"{1.0:.5f}*{term}" if abs(1.0) >= threshold else None
+
+    terms = []
+    if simplified_expr.is_Add:
+        for term in simplified_expr.args:
+            formatted = format_term(term)
+            if formatted:
+                terms.append(formatted)
+    else:
+        formatted = format_term(simplified_expr)
+        if formatted:
+            terms.append(formatted)
+    
+    formula = " + ".join(terms).replace("+ -", "- ")
+    return formula if formula else "0"
+
+def sympify_formula(basis_functions, coefficients, n_features, threshold=0.00005):
+    """
+    Simplifies a symbolic formula using SymPy with caching.
+    
+    Parameters:
+    -----------
+    basis_functions : list
+        List of basis function strings (e.g., 'x0', 'x0^2', 'x0 x1', 'exp_x0').
+    coefficients : list
+        List of coefficients corresponding to each basis function.
+    n_features : int
+        Number of input features.
+    threshold : float, optional (default=0.00005)
+        Coefficients with absolute value below this are excluded.
+    
+    Returns:
+    --------
+    str
+        Simplified formula as a string, or '0' if empty.
+    """
+    # Convert inputs to hashable types
+    basis_functions_tuple = tuple(basis_functions)
+    coefficients_tuple = tuple(coefficients)
+    
+    # Call cached function
+    return _cached_sympify_formula(basis_functions_tuple, coefficients_tuple, n_features, threshold)
+
+@lru_cache(maxsize=1000)
+def _cached_get_latex_formula(formula):
+    """
+    Internal function to convert a simplified formula to LaTeX with caching.
+    
+    Parameters:
+    -----------
+    formula : str
+        Simplified formula string.
+    
+    Returns:
+    --------
+    str
+        LaTeX formula as a string.
+    """
+    return sp.latex(sp.sympify(formula))
+
+def get_latex_formula(basis_functions, coefficients, n_features, threshold=0.00005):
+    """
+    Generates a LaTeX formula from the basis functions and coefficients with caching.
+    
+    Parameters:
+    -----------
+    basis_functions : list
+        List of basis function strings (e.g., 'x0', 'x0^2', 'x0 x1', 'exp_x0').
+    coefficients : list
+        List of coefficients corresponding to each basis function.
+    n_features : int
+        Number of input features.
+    threshold : float, optional (default=0.00005)
+        Coefficients with absolute value below this are excluded.
+    
+    Returns:
+    --------
+    str
+        LaTeX formula as a string, or '0' if empty.
+    """
+    # Get simplified formula (cached)
+    formula = sympify_formula(basis_functions, coefficients, n_features, threshold)
+    # Convert to LaTeX (cached)
+    return _cached_get_latex_formula(formula)
+
+if __name__ == "__main__":
+    with open('outputs/california_housing_model.json', 'r') as f:
+        model = json.load(f)
+    print('Sympified formula:', sympify_formula(model['basis_functions'], model['coefficients'], model['n_features']))
+    print('LaTeX formula:', get_latex_formula(model['basis_functions'], model['coefficients'], model['n_features']))

{oikan-0.0.3.3 → oikan-0.0.3.4}/oikan.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: oikan
-Version: 0.0.3.3
+Version: 0.0.3.4
 Summary: OIKAN: Neuro-Symbolic ML for Scientific Discovery
 Author: Arman Zhalgasbayev
 License: MIT
@@ -14,6 +14,7 @@ Requires-Dist: torch
 Requires-Dist: numpy
 Requires-Dist: scikit-learn
 Requires-Dist: tqdm
+Requires-Dist: sympy
 Dynamic: license-file
 
 <!-- logo in the center -->
@@ -118,7 +119,6 @@ model = OIKANRegressor(
     hidden_sizes=[32, 32], # Hidden layer sizes
     activation='relu', # Activation function (other options: 'tanh', 'leaky_relu', 'elu', 'swish', 'gelu')
     augmentation_factor=5, # Augmentation factor for data generation
-    polynomial_degree=2, # Degree of polynomial basis functions
     alpha=0.1, # L1 regularization strength (Symbolic regression)
     sigma=0.1, # Standard deviation of Gaussian noise for data augmentation
     top_k=5, # Number of top features to select (Symbolic regression)
@@ -140,7 +140,7 @@ mse = mean_squared_error(y_test, y_pred)
 print("Mean Squared Error:", mse)
 
 # Get symbolic formula
-formula = model.get_formula()
+formula = model.get_formula() # default: type='original' -> returns all formula without pruning | other options: 'sympied' -> simplified formula using sympy; 'latex' -> LaTeX format
 print("Symbolic Formula:", formula)
 
 # Get feature importances
@@ -168,7 +168,6 @@ model = OIKANClassifier(
     hidden_sizes=[32, 32], # Hidden layer sizes
     activation='relu', # Activation function (other options: 'tanh', 'leaky_relu', 'elu', 'swish', 'gelu')
     augmentation_factor=10, # Augmentation factor for data generation
-    polynomial_degree=2, # Degree of polynomial basis functions
     alpha=0.1, # L1 regularization strength (Symbolic regression)
     sigma=0.1, # Standard deviation of Gaussian noise for data augmentation
     top_k=5, # Number of top features to select (Symbolic regression)
@@ -190,7 +189,7 @@ accuracy = model.score(X_test, y_test)
 print("Accuracy:", accuracy)
 
 # Get symbolic formulas for each class
-formulas = model.get_formula()
+formulas = model.get_formula() # default: type='original' -> returns all formula without pruning | other options: 'sympied' -> simplified formula using sympy; 'latex' -> LaTeX format
 for i, formula in enumerate(formulas):
     print(f"Class {i} Formula:", formula)
    
@@ -212,6 +211,60 @@ loaded_model.load("outputs/model.json")
 
 ![OIKAN v0.0.3(1) Architecture](https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan-v0.0.3(1)-architecture-oop.png)
 
+## OIKAN Symbolic Model Compilers
+
+OIKAN provides a set of symbolic model compilers to convert the symbolic formulas generated by the OIKAN model into different programming languages. 
+
+*Currently, we support: `Python`, `C++`, `C`, `JavaScript`, `Rust`, and `Go`. This allows users to easily integrate the generated formulas into their applications or systems.*
+
+All compilers: [model_compilers/](model_compilers)
+
+### Example of Python Compiler
+
+1. Regression Model:
+```python
+import numpy as np
+import json
+
+def predict(X, symbolic_model):
+    X = np.asarray(X)
+    X_transformed = evaluate_basis_functions(X, symbolic_model['basis_functions'], 
+                                            symbolic_model['n_features'])
+    return np.dot(X_transformed, symbolic_model['coefficients'])
+
+if __name__ == "__main__":
+    with open('outputs/california_housing_model.json', 'r') as f:
+        symbolic_model = json.load(f)
+    X = np.random.rand(10, symbolic_model['n_features'])
+    y_pred = predict(X, symbolic_model)
+    print(y_pred)
+```
+
+2. Classification Model:
+```python
+import numpy as np
+import json
+
+def predict(X, symbolic_model):
+    X = np.asarray(X)
+    X_transformed = evaluate_basis_functions(X, symbolic_model['basis_functions'], 
+                                            symbolic_model['n_features'])
+    logits = np.dot(X_transformed, np.array(symbolic_model['coefficients_list']).T)
+    probabilities = np.exp(logits) / np.sum(np.exp(logits), axis=1, keepdims=True)
+    return np.argmax(probabilities, axis=1)
+
+if __name__ == "__main__":
+    with open('outputs/iris_model.json', 'r') as f:
+        symbolic_model = json.load(f)
+    X = np.array([[5.1, 3.5, 1.4, 0.2],
+                  [7.0, 3.2, 4.7, 1.4],
+                  [6.3, 3.3, 6.0, 2.5]])
+    y_pred = predict(X, symbolic_model)
+    print(y_pred)
+```
+
+
+
 ## Contributing
 
 We welcome contributions! Key areas of interest:

{oikan-0.0.3.3 → oikan-0.0.3.4}/oikan.egg-info/requires.txt

@@ -2,3 +2,4 @@ torch
 numpy
 scikit-learn
 tqdm
+sympy

{oikan-0.0.3.3 → oikan-0.0.3.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "oikan"
-version = "0.0.3.3"
+version = "0.0.3.4"
 description = "OIKAN: Neuro-Symbolic ML for Scientific Discovery"
 readme = "README.md"
 authors = [{name = "Arman Zhalgasbayev"}]
@@ -12,7 +12,8 @@ dependencies = [
     "torch",
     "numpy",
     "scikit-learn",
-    "tqdm" 
+    "tqdm",
+    "sympy"
 ]
 requires-python = ">=3.7"
 license = {text = "MIT"}

{oikan-0.0.3.3 → oikan-0.0.3.4}/setup.py

@@ -7,6 +7,7 @@ setup(
         "torch",
         "numpy",
         "scikit-learn",
-        "tqdm"
+        "tqdm",
+        "sympy"
     ]
 )

oikan-0.0.3.3/oikan/utils.py

@@ -1,82 +0,0 @@
-import numpy as np
-
-def evaluate_basis_functions(X, basis_functions, n_features):
-    """
-    Evaluates basis functions on the input data.
-    
-    Parameters:
-    -----------
-    X : array-like of shape (n_samples, n_features)
-        Input data.
-    basis_functions : list
-        List of basis function strings (e.g., '1', 'x0', 'x0^2', 'x0 x1', 'log1p_x0').
-    n_features : int
-        Number of input features.
-    
-    Returns:
-    --------
-    X_transformed : ndarray of shape (n_samples, n_basis_functions)
-        Transformed data matrix.
-    """
-    X_transformed = np.zeros((X.shape[0], len(basis_functions)))
-    for i, func in enumerate(basis_functions):
-        if func == '1':
-            X_transformed[:, i] = 1
-        elif func.startswith('log1p_x'):
-            idx = int(func.split('_')[1][1:])
-            X_transformed[:, i] = np.log1p(np.abs(X[:, idx]))
-        elif func.startswith('exp_x'):
-            idx = int(func.split('_')[1][1:])
-            X_transformed[:, i] = np.exp(np.clip(X[:, idx], -10, 10))
-        elif func.startswith('sin_x'):
-            idx = int(func.split('_')[1][1:])
-            X_transformed[:, i] = np.sin(X[:, idx])
-        elif '^' in func:
-            var, power = func.split('^')
-            idx = int(var[1:])
-            X_transformed[:, i] = X[:, idx] ** int(power)
-        elif ' ' in func:
-            vars = func.split(' ')
-            result = np.ones(X.shape[0])
-            for var in vars:
-                idx = int(var[1:])
-                result *= X[:, idx]
-            X_transformed[:, i] = result
-        else:
-            idx = int(func[1:])
-            X_transformed[:, i] = X[:, idx]
-    return X_transformed
-
-def get_features_involved(basis_function):
-    """
-    Extracts the feature indices involved in a basis function string.
-    
-    Parameters:
-    -----------
-    basis_function : str
-        String representation of the basis function, e.g., 'x0', 'x0^2', 'x0 x1', 'log1p_x0'.
-    
-    Returns:
-    --------
-    set : Set of feature indices involved.
-    """
-    if basis_function == '1':
-        return set()
-    features = set()
-    if '_' in basis_function:  # Handle non-linear functions like 'log1p_x0'
-        parts = basis_function.split('_')
-        if len(parts) == 2 and parts[1].startswith('x'):
-            idx = int(parts[1][1:])
-            features.add(idx)
-    elif '^' in basis_function:  # Handle powers, e.g., 'x0^2'
-        var = basis_function.split('^')[0]
-        idx = int(var[1:])
-        features.add(idx)
-    elif ' ' in basis_function:  # Handle interactions, e.g., 'x0 x1'
-        for part in basis_function.split():
-            idx = int(part[1:])
-            features.add(idx)
-    elif basis_function.startswith('x'):
-        idx = int(basis_function[1:])
-        features.add(idx)
-    return features