unifiedbooster 0.2.1__tar.gz → 0.3.0__tar.gz

unifiedbooster-0.3.0/LICENSE

@@ -0,0 +1,7 @@
+Copyright <2024> <T. Moudiki>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

{unifiedbooster-0.2.1 → unifiedbooster-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unifiedbooster
-Version: 0.2.1
+Version: 0.3.0
 Summary: Unified interface for Gradient Boosted Decision Trees
 Home-page: https://github.com/thierrymoudiki/unifiedbooster
 Author: T. Moudiki
@@ -16,6 +16,7 @@ Classifier: Programming Language :: Python :: 3.6
 Classifier: Programming Language :: Python :: 3.7
 Classifier: Programming Language :: Python :: 3.8
 Requires-Python: >=3.6
+License-File: LICENSE
 Requires-Dist: Cython
 Requires-Dist: numpy
 Requires-Dist: scikit-learn

unifiedbooster-0.3.0/README.md

@@ -0,0 +1,93 @@
+# unifiedbooster
+
+Unified interface for Gradient Boosted Decision Trees algorithms
+
+![PyPI](https://img.shields.io/pypi/v/unifiedbooster) [![PyPI - License](https://img.shields.io/pypi/l/unifiedbooster)](https://github.com/thierrymoudiki/unifiedbooster/blob/main/LICENSE) [![Downloads](https://pepy.tech/badge/unifiedbooster)](https://pepy.tech/project/unifiedbooster) 
+[![Documentation](https://img.shields.io/badge/documentation-is_here-green)](https://techtonique.github.io/unifiedbooster/)
+
+## Examples 
+
+### classification 
+
+```python
+import unifiedbooster as ub
+from sklearn.datasets import load_iris, load_breast_cancer, load_wine
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+
+datasets = [load_iris(), load_breast_cancer(), load_wine()]
+
+for dataset in datasets:
+
+  X, y = dataset.data, dataset.target
+  X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+  # Initialize the unified regressor (example with XGBoost)
+  regressor1 = ub.GBDTClassifier(model_type='xgboost')
+  regressor2 = ub.GBDTClassifier(model_type='catboost')
+  regressor3 = ub.GBDTClassifier(model_type='lightgbm')
+
+  # Fit the model
+  regressor1.fit(X_train, y_train)
+  regressor2.fit(X_train, y_train)
+  regressor3.fit(X_train, y_train)
+
+  # Predict on the test set
+  y_pred1 = regressor1.predict(X_test)
+  y_pred2 = regressor2.predict(X_test)
+  y_pred3 = regressor3.predict(X_test)
+
+  # Evaluate the model
+  accuracy1 = accuracy_score(y_test, y_pred1)
+  accuracy2 = accuracy_score(y_test, y_pred2)
+  accuracy3 = accuracy_score(y_test, y_pred3)
+  print("-------------------------")
+  print(f"Classification Accuracy xgboost: {accuracy1:.2f}")
+  print(f"Classification Accuracy catboost: {accuracy2:.2f}")
+  print(f"Classification Accuracy lightgbm: {accuracy3:.2f}")
+```
+
+### regression 
+
+```python
+import numpy as np
+import unifiedbooster as ub
+from sklearn.datasets import fetch_california_housing, load_diabetes
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import mean_squared_error
+
+
+datasets = [fetch_california_housing(), load_diabetes()]
+
+for dataset in datasets:
+
+  # Load dataset
+  X, y = dataset.data, dataset.target
+
+  # Split dataset into training and testing sets
+  X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+  # Initialize the unified regressor (example with XGBoost)
+  regressor1 = ub.GBDTRegressor(model_type='xgboost')
+  regressor2 = ub.GBDTRegressor(model_type='catboost')
+  regressor3 = ub.GBDTRegressor(model_type='lightgbm')
+
+  # Fit the model
+  regressor1.fit(X_train, y_train)
+  regressor2.fit(X_train, y_train)
+  regressor3.fit(X_train, y_train)
+
+  # Predict on the test set
+  y_pred1 = regressor1.predict(X_test)
+  y_pred2 = regressor2.predict(X_test)
+  y_pred3 = regressor3.predict(X_test)
+
+  # Evaluate the model
+  mse1 = np.sqrt(mean_squared_error(y_test, y_pred1))
+  mse2 = np.sqrt(mean_squared_error(y_test, y_pred2))
+  mse3 = np.sqrt(mean_squared_error(y_test, y_pred3))
+  print("-------------------------")
+  print(f"Regression Root Mean Squared Error xgboost: {mse1:.2f}")
+  print(f"Regression Root Mean Squared Error catboost: {mse2:.2f}")
+  print(f"Regression Root Mean Squared Error lightgbm: {mse3:.2f}")
+```

{unifiedbooster-0.2.1 → unifiedbooster-0.3.0}/setup.py

@@ -10,7 +10,7 @@ from os import path
 
 subprocess.check_call(['pip', 'install', 'Cython'])
 
-__version__ = "0.2.1"
+__version__ = "0.3.0"
 
 here = path.abspath(path.dirname(__file__))
 

{unifiedbooster-0.2.1 → unifiedbooster-0.3.0}/unifiedbooster/__init__.py

@@ -1,4 +1,5 @@
+from .gbdt import GBDT
 from .gbdt_classification import GBDTClassifier
 from .gbdt_regression import GBDTRegressor
 
-__all__ = ["GBDTClassifier", "GBDTRegressor"]
+__all__ = ["GBDT", "GBDTClassifier", "GBDTRegressor"]

unifiedbooster-0.3.0/unifiedbooster/gbdt.py

@@ -0,0 +1,151 @@
+import numpy as np
+from sklearn.base import BaseEstimator
+
+
+class GBDT(BaseEstimator):
+    """Gradient Boosted Decision Trees (GBDT) base class
+
+    Attributes:
+
+        model_type: str
+            type of gradient boosting algorithm: 'xgboost', 'lightgbm',
+            'catboost', 'gradientboosting'
+
+        n_estimators: int
+            maximum number of trees that can be built
+
+        learning_rate: float
+            shrinkage rate; used for reducing the gradient step
+
+        rowsample: float
+            subsample ratio of the training instances
+
+        colsample: float
+            percentage of features to use at each node split
+
+        verbose: int
+            controls verbosity (default=0)
+
+        seed: int
+            reproducibility seed
+
+        **kwargs: dict
+            additional parameters to be passed to the class
+    """
+
+    def __init__(
+        self,
+        model_type="xgboost",
+        n_estimators=100,
+        learning_rate=0.1,
+        max_depth=3,
+        rowsample=1.0,
+        colsample=1.0,
+        verbose=0,
+        seed=123,
+        **kwargs
+    ):
+
+        self.model_type = model_type
+        self.n_estimators = n_estimators
+        self.learning_rate = learning_rate
+        self.max_depth = max_depth
+        self.rowsample = rowsample
+        self.colsample = colsample
+        self.verbose = verbose
+        self.seed = seed
+
+        if self.model_type == "xgboost":
+            self.params = {
+                "n_estimators": self.n_estimators,
+                "learning_rate": self.learning_rate,
+                "subsample": self.rowsample,
+                "colsample_bynode": self.colsample,
+                "max_depth": self.max_depth,
+                "verbosity": self.verbose,
+                "seed": self.seed,
+                **kwargs,
+            }
+        elif self.model_type == "lightgbm":
+            verbose = self.verbose - 1 if self.verbose == 0 else self.verbose
+            self.params = {
+                "n_estimators": self.n_estimators,
+                "learning_rate": self.learning_rate,
+                "subsample": self.rowsample,
+                "feature_fraction_bynode": self.colsample,
+                "max_depth": self.max_depth,
+                "verbose": verbose,  # keep this way
+                "seed": self.seed,
+                **kwargs,
+            }
+        elif self.model_type == "catboost":
+            self.params = {
+                "iterations": self.n_estimators,
+                "learning_rate": self.learning_rate,
+                "subsample": self.rowsample,
+                "rsm": self.colsample,
+                "depth": self.max_depth,
+                "verbose": self.verbose,
+                "random_seed": self.seed,
+                "bootstrap_type": "Bernoulli",
+                **kwargs,
+            }
+        elif self.model_type == "gradientboosting":
+            self.params = {
+                "n_estimators": self.n_estimators,
+                "learning_rate": self.learning_rate,
+                "subsample": self.rowsample,
+                "max_features": self.colsample,
+                "max_depth": self.max_depth,
+                "verbose": self.verbose,
+                "random_state": self.seed,
+                **kwargs,
+            }
+
+    def fit(self, X, y, **kwargs):
+        """Fit custom model to training data (X, y).
+
+        Parameters:
+
+            X: {array-like}, shape = [n_samples, n_features]
+                Training vectors, where n_samples is the number
+                of samples and n_features is the number of features.
+
+            y: array-like, shape = [n_samples]
+                Target values.
+
+            **kwargs: additional parameters to be passed to
+                        self.cook_training_set or self.obj.fit
+
+        Returns:
+
+            self: object
+        """
+
+        if getattr(self, "type_fit") == "classification":
+            self.classes_ = np.unique(y)  # for compatibility with sklearn
+            self.n_classes_ = len(
+                self.classes_
+            )  # for compatibility with sklearn
+        if getattr(self, "model_type") == "gradientboosting":
+            self.model.max_features = int(self.model.max_features * X.shape[1])
+        return getattr(self, "model").fit(X, y, **kwargs)
+
+    def predict(self, X):
+        """Predict test data X.
+
+        Parameters:
+
+            X: {array-like}, shape = [n_samples, n_features]
+                Training vectors, where n_samples is the number
+                of samples and n_features is the number of features.
+
+            **kwargs: additional parameters to be passed to
+                    self.cook_test_set
+
+        Returns:
+
+            model predictions: {array-like}
+        """
+
+        return getattr(self, "model").predict(X)

{unifiedbooster-0.2.1 → unifiedbooster-0.3.0}/unifiedbooster/gbdt_classification.py

@@ -1,8 +1,13 @@
 from .gbdt import GBDT
 from sklearn.base import ClassifierMixin
 from xgboost import XGBClassifier
-from catboost import CatBoostClassifier
+
+try:
+    from catboost import CatBoostClassifier
+except:
+    print("catboost package can't be built")
 from lightgbm import LGBMClassifier
+from sklearn.ensemble import GradientBoostingClassifier
 
 
 class GBDTClassifier(GBDT, ClassifierMixin):
@@ -10,8 +15,12 @@ class GBDTClassifier(GBDT, ClassifierMixin):
 
     Attributes:
 
+        model_type: str
+            type of gradient boosting algorithm: 'xgboost', 'lightgbm',
+            'catboost', 'gradientboosting'
+
         n_estimators: int
-            maximum number of trees that can be built 
+            maximum number of trees that can be built
 
         learning_rate: float
             shrinkage rate; used for reducing the gradient step
@@ -24,9 +33,12 @@ class GBDTClassifier(GBDT, ClassifierMixin):
 
         verbose: int
             controls verbosity (default=0)
-        
-        seed: int 
-            reproducibility seed 
+
+        seed: int
+            reproducibility seed
+
+        **kwargs: dict
+            additional parameters to be passed to the class
 
     Examples:
 
@@ -68,39 +80,59 @@ class GBDTClassifier(GBDT, ClassifierMixin):
     ```
     """
 
-    def __init__(self, 
-                 model_type='xgboost', 
-                 n_estimators=100, 
-                 learning_rate=0.1, 
-                 max_depth=3, 
-                 rowsample=1.0,  
-                 colsample=1.0,
-                 verbose=0,
-                 seed=123,
-                 **kwargs):
-        
+    def __init__(
+        self,
+        model_type="xgboost",
+        n_estimators=100,
+        learning_rate=0.1,
+        max_depth=3,
+        rowsample=1.0,
+        colsample=1.0,
+        verbose=0,
+        seed=123,
+        **kwargs,
+    ):
+
         self.type_fit = "classification"
-                        
+
         super().__init__(
-            model_type=model_type, 
-            n_estimators=n_estimators, 
-            learning_rate=learning_rate, 
-            max_depth=max_depth, 
+            model_type=model_type,
+            n_estimators=n_estimators,
+            learning_rate=learning_rate,
+            max_depth=max_depth,
             rowsample=rowsample,
-            colsample=colsample,    
-            verbose=verbose,    
-            seed=seed,          
-            **kwargs
+            colsample=colsample,
+            verbose=verbose,
+            seed=seed,
+            **kwargs,
         )
 
-        if model_type == 'xgboost':
+        if model_type == "xgboost":
             self.model = XGBClassifier(**self.params)
-        elif model_type == 'catboost':            
+        elif model_type == "catboost":
             self.model = CatBoostClassifier(**self.params)
-        elif model_type == 'lightgbm':
+        elif model_type == "lightgbm":
             self.model = LGBMClassifier(**self.params)
+        elif model_type == "gradientboosting":
+            self.model = GradientBoostingClassifier(**self.params)
         else:
             raise ValueError(f"Unknown model_type: {model_type}")
-            
+
     def predict_proba(self, X):
-        return self.model.predict_proba(X)
+        """Predict probabilities for test data X.
+
+        Args:
+
+            X: {array-like}, shape = [n_samples, n_features]
+                Training vectors, where n_samples is the number
+                of samples and n_features is the number of features.
+
+            **kwargs: additional parameters to be passed to
+                    self.cook_test_set
+
+        Returns:
+
+            probability estimates for test data: {array-like}
+        """
+
+        return self.model.predict_proba(X)

{unifiedbooster-0.2.1 → unifiedbooster-0.3.0}/unifiedbooster/gbdt_regression.py

@@ -1,8 +1,13 @@
 from .gbdt import GBDT
 from sklearn.base import RegressorMixin
 from xgboost import XGBRegressor
-from catboost import CatBoostRegressor
+
+try:
+    from catboost import CatBoostRegressor
+except:
+    print("catboost package can't be built")
 from lightgbm import LGBMRegressor
+from sklearn.ensemble import GradientBoostingRegressor
 
 
 class GBDTRegressor(GBDT, RegressorMixin):
@@ -10,8 +15,12 @@ class GBDTRegressor(GBDT, RegressorMixin):
 
     Attributes:
 
+        model_type: str
+            type of gradient boosting algorithm: 'xgboost', 'lightgbm',
+            'catboost', 'gradientboosting'
+
         n_estimators: int
-            maximum number of trees that can be built 
+            maximum number of trees that can be built
 
         learning_rate: float
             shrinkage rate; used for reducing the gradient step
@@ -24,9 +33,12 @@ class GBDTRegressor(GBDT, RegressorMixin):
 
         verbose: int
             controls verbosity (default=0)
-        
-        seed: int 
-            reproducibility seed 
+
+        seed: int
+            reproducibility seed
+
+        **kwargs: dict
+            additional parameters to be passed to the class
 
     Examples:
 
@@ -68,36 +80,40 @@ class GBDTRegressor(GBDT, RegressorMixin):
     ```
     """
 
-    def __init__(self, 
-                 model_type='xgboost', 
-                 n_estimators=100, 
-                 learning_rate=0.1, 
-                 max_depth=3, 
-                 rowsample=1.0,
-                 colsample=1.0,    
-                 verbose=0,    
-                 seed=123,          
-                 **kwargs):
-        
+    def __init__(
+        self,
+        model_type="xgboost",
+        n_estimators=100,
+        learning_rate=0.1,
+        max_depth=3,
+        rowsample=1.0,
+        colsample=1.0,
+        verbose=0,
+        seed=123,
+        **kwargs,
+    ):
+
         self.type_fit = "regression"
-                        
+
         super().__init__(
-            model_type=model_type, 
-            n_estimators=n_estimators, 
-            learning_rate=learning_rate, 
-            max_depth=max_depth, 
+            model_type=model_type,
+            n_estimators=n_estimators,
+            learning_rate=learning_rate,
+            max_depth=max_depth,
             rowsample=rowsample,
-            colsample=colsample,    
-            verbose=verbose,    
-            seed=seed,          
-            **kwargs
+            colsample=colsample,
+            verbose=verbose,
+            seed=seed,
+            **kwargs,
         )
 
-        if model_type == 'xgboost':
+        if model_type == "xgboost":
             self.model = XGBRegressor(**self.params)
-        elif model_type == 'catboost':            
+        elif model_type == "catboost":
             self.model = CatBoostRegressor(**self.params)
-        elif model_type == 'lightgbm':
+        elif model_type == "lightgbm":
             self.model = LGBMRegressor(**self.params)
+        elif model_type == "gradientboosting":
+            self.model = GradientBoostingRegressor(**self.params)
         else:
             raise ValueError(f"Unknown model_type: {model_type}")

{unifiedbooster-0.2.1 → unifiedbooster-0.3.0}/unifiedbooster.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unifiedbooster
-Version: 0.2.1
+Version: 0.3.0
 Summary: Unified interface for Gradient Boosted Decision Trees
 Home-page: https://github.com/thierrymoudiki/unifiedbooster
 Author: T. Moudiki
@@ -16,6 +16,7 @@ Classifier: Programming Language :: Python :: 3.6
 Classifier: Programming Language :: Python :: 3.7
 Classifier: Programming Language :: Python :: 3.8
 Requires-Python: >=3.6
+License-File: LICENSE
 Requires-Dist: Cython
 Requires-Dist: numpy
 Requires-Dist: scikit-learn

{unifiedbooster-0.2.1 → unifiedbooster-0.3.0}/unifiedbooster.egg-info/SOURCES.txt

@@ -1,3 +1,4 @@
+LICENSE
 README.md
 setup.py
 unifiedbooster/__init__.py

unifiedbooster-0.2.1/README.md

@@ -1 +0,0 @@
-# unifiedbooster

unifiedbooster-0.2.1/unifiedbooster/gbdt.py

@@ -1,69 +0,0 @@
-import numpy as np 
-from sklearn.base import BaseEstimator
-
-
-class GBDT(BaseEstimator):
-    def __init__(self, 
-                 model_type='xgboost', 
-                 n_estimators=100, 
-                 learning_rate=0.1, 
-                 max_depth=3, 
-                 rowsample=1.0,
-                 colsample=1.0,    
-                 verbose=0,    
-                 seed=123,          
-                 **kwargs):  
-        
-        self.model_type = model_type
-        self.n_estimators = n_estimators
-        self.learning_rate = learning_rate
-        self.max_depth = max_depth
-        self.rowsample = rowsample
-        self.colsample = colsample        
-        self.verbose = verbose 
-        self.seed = seed         
-
-        if self.model_type == "xgboost": 
-            self.params = {
-                'n_estimators': self.n_estimators,
-                'learning_rate': self.learning_rate,
-                'subsample': self.rowsample, 
-                'colsample_bynode': self.colsample,                
-                'max_depth': self.max_depth,
-                'verbosity': self.verbose, 
-                'seed': self.seed,
-                **kwargs
-            }
-        elif self.model_type == "lightgbm":
-             verbose = self.verbose - 1 if self.verbose==0 else self.verbose
-             self.params = {
-                'n_estimators': self.n_estimators, 
-                'learning_rate': self.learning_rate, 
-                'subsample': self.rowsample, 
-                'feature_fraction_bynode': self.colsample,                
-                'max_depth': self.max_depth,
-                'verbose': verbose, # keep this way
-                'seed': self.seed,
-                **kwargs
-            }
-        elif self.model_type == "catboost":
-             self.params = {
-                'iterations': self.n_estimators, 
-                'learning_rate': self.learning_rate, 
-                'subsample': self.rowsample, 
-                'rsm': self.colsample, 
-                'depth': self.max_depth, 
-                'verbose': self.verbose,
-                'random_seed': self.seed, 
-                'bootstrap_type': 'Bernoulli',
-                **kwargs
-            }           
-        
-    def fit(self, X, y, **kwargs):
-        if getattr(self, "type_fit") == "classification":
-            self.classes_ = np.unique(y) # for compatibility with sklearn
-            self.n_classes_ = len(self.classes_)  # for compatibility with sklearn        
-        return getattr(self, "model").fit(X, y, **kwargs)
-    
-    def predict(self, X):
-        return getattr(self, "model").predict(X)