ilovetools 0.2.12__tar.gz → 0.2.14__tar.gz

{ilovetools-0.2.12/ilovetools.egg-info → ilovetools-0.2.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ilovetools
-Version: 0.2.12
+Version: 0.2.14
 Summary: A comprehensive Python utility library with modular tools for AI/ML, data processing, and daily programming needs
 Home-page: https://github.com/AliMehdi512/ilovetools
 Author: Ali Mehdi
@@ -11,7 +11,7 @@ Project-URL: Repository, https://github.com/AliMehdi512/ilovetools
 Project-URL: Issues, https://github.com/AliMehdi512/ilovetools/issues
 Project-URL: Bug Reports, https://github.com/AliMehdi512/ilovetools/issues
 Project-URL: Source, https://github.com/AliMehdi512/ilovetools
-Keywords: utilities,tools,ai,ml,data-processing,automation,gradient-descent,optimization
+Keywords: utilities,tools,ai,ml,data-processing,automation,gradient-descent,optimization,regularization,loss-functions
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: Topic :: Software Development :: Libraries :: Python Modules

{ilovetools-0.2.12 → ilovetools-0.2.14}/ilovetools/__init__.py

@@ -2,8 +2,8 @@
 ilovetools - A comprehensive Python utility library
 """
 
-__version__ = "0.2.7.1"
-# release marker: 0.2.7.1
+__version__ = "0.2.13"
+# release marker: 0.2.13
 __author__ = "Ali Mehdi"
 __email__ = "ali.mehdi.dev579@gmail.com"
 

{ilovetools-0.2.12 → ilovetools-0.2.14}/ilovetools/ml/__init__.py

@@ -347,7 +347,7 @@ from .neural_network import (
     mse_loss,
     binary_crossentropy,
     categorical_crossentropy,
-    huber_loss,
+    huber_loss as nn_huber_loss,
     # Weight Initialization
     xavier_init,
     he_init,
@@ -401,6 +401,59 @@ from .gradient_descent import (
     compute_learning_rate,
 )
 
+from .regularization import (
+    # L1/L2 Regularization
+    l1_regularization,
+    l2_regularization,
+    elastic_net_regularization,
+    l1_penalty,
+    l2_penalty,
+    elastic_net_penalty,
+    # Dropout
+    dropout,
+    dropout_mask,
+    inverted_dropout,
+    # Early Stopping
+    early_stopping_monitor as reg_early_stopping_monitor,
+    should_stop_early,
+    # Weight Constraints
+    max_norm_constraint,
+    unit_norm_constraint,
+    non_negative_constraint,
+    # Regularization Utilities
+    compute_regularization_loss,
+    apply_weight_decay,
+)
+
+from .loss_functions import (
+    # Regression Losses
+    mean_squared_error_loss,
+    mean_absolute_error_loss,
+    root_mean_squared_error_loss,
+    huber_loss,
+    log_cosh_loss,
+    quantile_loss,
+    mean_squared_logarithmic_error,
+    # Classification Losses
+    binary_crossentropy_loss,
+    categorical_crossentropy_loss,
+    sparse_categorical_crossentropy_loss,
+    hinge_loss,
+    squared_hinge_loss,
+    categorical_hinge_loss,
+    focal_loss,
+    kullback_leibler_divergence,
+    # Segmentation Losses
+    dice_loss,
+    dice_coefficient,
+    iou_loss,
+    tversky_loss,
+    focal_tversky_loss,
+    # Utilities
+    combined_loss,
+    weighted_loss,
+)
+
 __all__ = [
     # Metrics (full names)
     'accuracy_score',
@@ -710,7 +763,7 @@ __all__ = [
     'mse_loss',
     'binary_crossentropy',
     'categorical_crossentropy',
-    'huber_loss',
+    'nn_huber_loss',
     # Neural Network - Weight Initialization
     'xavier_init',
     'he_init',
@@ -759,4 +812,51 @@ __all__ = [
     'check_convergence',
     'line_search',
     'compute_learning_rate',
+    # Regularization - L1/L2
+    'l1_regularization',
+    'l2_regularization',
+    'elastic_net_regularization',
+    'l1_penalty',
+    'l2_penalty',
+    'elastic_net_penalty',
+    # Regularization - Dropout
+    'dropout',
+    'dropout_mask',
+    'inverted_dropout',
+    # Regularization - Early Stopping
+    'reg_early_stopping_monitor',
+    'should_stop_early',
+    # Regularization - Weight Constraints
+    'max_norm_constraint',
+    'unit_norm_constraint',
+    'non_negative_constraint',
+    # Regularization - Utilities
+    'compute_regularization_loss',
+    'apply_weight_decay',
+    # Loss Functions - Regression
+    'mean_squared_error_loss',
+    'mean_absolute_error_loss',
+    'root_mean_squared_error_loss',
+    'huber_loss',
+    'log_cosh_loss',
+    'quantile_loss',
+    'mean_squared_logarithmic_error',
+    # Loss Functions - Classification
+    'binary_crossentropy_loss',
+    'categorical_crossentropy_loss',
+    'sparse_categorical_crossentropy_loss',
+    'hinge_loss',
+    'squared_hinge_loss',
+    'categorical_hinge_loss',
+    'focal_loss',
+    'kullback_leibler_divergence',
+    # Loss Functions - Segmentation
+    'dice_loss',
+    'dice_coefficient',
+    'iou_loss',
+    'tversky_loss',
+    'focal_tversky_loss',
+    # Loss Functions - Utilities
+    'combined_loss',
+    'weighted_loss',
 ]