oikan 0.0.3.6__py3-none-any.whl → 0.0.3.8__py3-none-any.whl

oikan/model.py

@@ -12,6 +12,7 @@ from sklearn.model_selection import train_test_split
 from sklearn.metrics import r2_score, accuracy_score
 from .exceptions import *
 import sys
+from tqdm import tqdm
 
 class OIKAN(ABC):
     """
@@ -319,11 +320,15 @@ 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):
@@ -349,14 +354,23 @@ class OIKAN(ABC):
         if np.any(np.isinf(X)) or np.any(np.isinf(y)):
             raise NumericalInstabilityError("Input data contains infinite values")
 
-        # Stage 1: Coarse Model
+        if self.verbose:
+            print("\nStage 1: Coarse Model Fitting")
+            
         coarse_degree = 2  # Fixed low degree for coarse model
         poly_coarse = PolynomialFeatures(degree=coarse_degree, include_bias=True)
+        
+        if self.verbose:
+            print("Generating polynomial features...")
         X_poly_coarse = poly_coarse.fit_transform(X)
+        
+        if self.verbose:
+            print("Fitting coarse elastic net model...")
         model_coarse = ElasticNet(alpha=self.alpha, fit_intercept=False)
         model_coarse.fit(X_poly_coarse, y)
 
-        # Compute feature importances for original features
+        if self.verbose:
+            print("Computing feature importances...")
         basis_functions_coarse = poly_coarse.get_feature_names_out()
         if len(y.shape) == 1 or y.shape[1] == 1:
             coef_coarse = model_coarse.coef_.flatten()
@@ -364,7 +378,7 @@ class OIKAN(ABC):
             coef_coarse = np.sum(np.abs(model_coarse.coef_), axis=0)
 
         importances = np.zeros(X.shape[1])
-        for i, func in enumerate(basis_functions_coarse):
+        for i, func in enumerate(tqdm(basis_functions_coarse, disable=not self.verbose, desc="Analyzing features")):
             features_involved = get_features_involved(func)
             for idx in features_involved:
                 importances[idx] += np.abs(coef_coarse[i])
@@ -375,11 +389,13 @@ class OIKAN(ABC):
         # Select top K features
         top_k_indices = np.argsort(importances)[::-1][:self.top_k]
 
-        # Stage 2: Refined Model
-        # ~ generate additional non-linear features for top K features
+        if self.verbose:
+            print(f"\nStage 2: Refined Model with top {self.top_k} features")
+            print("Generating additional non-linear features...")
+
         additional_features = []
         additional_names = []
-        for i in top_k_indices:
+        for i in tqdm(top_k_indices, disable=not self.verbose, desc="Generating features"):
             # Higher-degree polynomial
             additional_features.append(X[:, i]**3)
             additional_names.append(f'x{i}^3')
@@ -391,15 +407,18 @@ class OIKAN(ABC):
             additional_features.append(np.sin(X[:, i]))
             additional_names.append(f'sin_x{i}')
         
-        # Combine features
+        if self.verbose:
+            print("Combining features and fitting final model...")
         X_additional = np.column_stack(additional_features)
         X_refined = np.hstack([X_poly_coarse, X_additional])
         basis_functions_refined = list(basis_functions_coarse) + additional_names
 
-        # Fit refined model
         model_refined = ElasticNet(alpha=self.alpha, fit_intercept=False)
         model_refined.fit(X_refined, y)
 
+        if self.verbose:
+            print("Building final symbolic model...")
+
         # Store symbolic model
         if len(y.shape) == 1 or y.shape[1] == 1:
             # Regression
@@ -414,7 +433,7 @@ class OIKAN(ABC):
             # Classification
             coefficients_list = []
             selected_indices = set()
-            for c in range(y.shape[1]):
+            for c in tqdm(range(y.shape[1]), disable=not self.verbose, desc="Processing classes"):
                 coef = model_refined.coef_[c]
                 indices = np.where(np.abs(coef) > 1e-6)[0]
                 selected_indices.update(indices)
@@ -445,16 +464,32 @@ 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.verbose:
-            print(f"Augmented data: features shape: {X_aug.shape} | target shape: {y_aug.shape}")
-        self._perform_symbolic_regression(X_aug, y_aug)
+        
+        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} | size: {X.nbytes / (1024 * 1024):.2f} MB")
+            
+            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} | size: {X_aug.nbytes / (1024 * 1024):.2f} MB")
+            
+            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)")
+                print(f"Data: features shape: {X.shape} | target shape: {y.shape} | size: {X.nbytes / (1024 * 1024):.2f} MB")
+            X_combined = X
+            y_combined = y
+            
+        self._perform_symbolic_regression(X_combined, y_combined)
         if self.verbose:
             print("OIKANRegressor model training completed successfully!")
 
@@ -499,16 +534,32 @@ 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.verbose:
-            print(f"Augmented data: features shape: {X_aug.shape} | target shape: {logits_aug.shape}")
-        self._perform_symbolic_regression(X_aug, logits_aug)
+        
+        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} | size: {X.nbytes / (1024 * 1024):.2f} MB")
+            
+            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} | size: {X_aug.nbytes / (1024 * 1024):.2f} MB")
+            
+            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)")
+                print(f"Data: features shape: {X.shape} | target shape: {y.shape} | size: {X.nbytes / (1024 * 1024):.2f} MB")
+            X_combined = X
+            y_combined = y_onehot.numpy()
+            
+        self._perform_symbolic_regression(X_combined, y_combined)
         if self.verbose:
             print("OIKANClassifier model training completed successfully!")
 

{oikan-0.0.3.6.dist-info → oikan-0.0.3.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: oikan
-Version: 0.0.3.6
+Version: 0.0.3.8
 Summary: OIKAN: Neuro-Symbolic ML for Scientific Discovery
 Author: Arman Zhalgasbayev
 License: MIT

oikan-0.0.3.8.dist-info/RECORD

@@ -0,0 +1,10 @@
+oikan/__init__.py,sha256=zEzhm1GYLT4vNaIQ4CgZcNpUk3uo8SWnoaHYtHW_XSQ,628
+oikan/exceptions.py,sha256=GhHWqy2Q5LVBcteTy4ngnqxr7FOoLNyD8dNt1kfRXyw,901
+oikan/model.py,sha256=K-cBAUvfw3B8wxWjNSUC1CadU1iVUb8erapUpD9KzKw,25822
+oikan/neural.py,sha256=PZjaffSuABuCNxu-7PinU1GR6ji0Y6xRgSQ3n5HRDxI,1572
+oikan/utils.py,sha256=7UCm9obO-8Q2zhetdAkukMDOZvGSBWUL_dSF04XqM7k,8808
+oikan-0.0.3.8.dist-info/licenses/LICENSE,sha256=75ASVmU-XIpN-M4LbVmJ_ibgbzbvRLVti8FhnR0BTf8,1096
+oikan-0.0.3.8.dist-info/METADATA,sha256=jmDvzPj-d_JH4yAZiBf45-mjItUVRepX1Xv2cMqqAkA,12749
+oikan-0.0.3.8.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+oikan-0.0.3.8.dist-info/top_level.txt,sha256=XwnwKwTJddZwIvtrUsAz-l-58BJRj6HjAGWrfYi_3QY,6
+oikan-0.0.3.8.dist-info/RECORD,,

oikan-0.0.3.6.dist-info/RECORD

@@ -1,10 +0,0 @@
-oikan/__init__.py,sha256=zEzhm1GYLT4vNaIQ4CgZcNpUk3uo8SWnoaHYtHW_XSQ,628
-oikan/exceptions.py,sha256=GhHWqy2Q5LVBcteTy4ngnqxr7FOoLNyD8dNt1kfRXyw,901
-oikan/model.py,sha256=vnn5THWhndj5-P2Vsa78CErsT24LVmjMd8CnWeW09Kg,23663
-oikan/neural.py,sha256=PZjaffSuABuCNxu-7PinU1GR6ji0Y6xRgSQ3n5HRDxI,1572
-oikan/utils.py,sha256=7UCm9obO-8Q2zhetdAkukMDOZvGSBWUL_dSF04XqM7k,8808
-oikan-0.0.3.6.dist-info/licenses/LICENSE,sha256=75ASVmU-XIpN-M4LbVmJ_ibgbzbvRLVti8FhnR0BTf8,1096
-oikan-0.0.3.6.dist-info/METADATA,sha256=P-07jTsmYsaANnQOjh_mzmjLk1Q9rqN665CBp_FKYjU,12749
-oikan-0.0.3.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-oikan-0.0.3.6.dist-info/top_level.txt,sha256=XwnwKwTJddZwIvtrUsAz-l-58BJRj6HjAGWrfYi_3QY,6
-oikan-0.0.3.6.dist-info/RECORD,,