Added liblinear solver in the LogisticRegression initialization. Adde…

…d training accuracy and testing accuracy print in the function __VotingClassifier__(). In the main function called ensemble.__VotingClassifier__(). And finaly, added requirements.txt file as I tested it with the lates scikit-learn version. Signed-off-by: Bikash Karmokar <[email protected]>
FernandoLpz · Nov 18, 2021 · da20b08 · da20b08
1 parent ec2cbcd
commit da20b08
Show file tree

Hide file tree

Showing 5 changed files with 209 additions and 58 deletions.
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1,141 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# pycharm
+.idea
diff --git a/blending.py b/blending.py
@@ -9,6 +9,7 @@
 from sklearn.naive_bayes import GaussianNB
 from sklearn.linear_model import LogisticRegression
 
+
 class Ensemble:
     def __init__(self):
         self.x_train = None
@@ -19,31 +20,32 @@ def __init__(self):
     def load_data(self):
         x, y = load_breast_cancer(return_X_y=True)
         self.x_train, self.x_test, self.y_train, self.y_test = train_test_split(x, y, test_size=0.15, random_state=23)
-        self.x_train, self.x_val, self.y_train, self.y_val = train_test_split(self.x_train, self.y_train, test_size=0.3, random_state=23)
-
+        self.x_train, self.x_val, self.y_train, self.y_val = train_test_split(self.x_train, self.y_train, test_size=0.3,
+                                                                              random_state=23)
+
     def BlendingClassifier(self):
 
         # Define weak learners
         weak_learners = [('dt', DecisionTreeClassifier()),
-                        ('knn', KNeighborsClassifier()),
-                        ('rf', RandomForestClassifier()),
-                        ('gb', GradientBoostingClassifier()),
-                        ('gn', GaussianNB())]
-        
-        # Finaler learner or meta model
+                         ('knn', KNeighborsClassifier()),
+                         ('rf', RandomForestClassifier()),
+                         ('gb', GradientBoostingClassifier()),
+                         ('gn', GaussianNB())]
+
+        # Final learner or meta model
         final_learner = LogisticRegression()
 
         train_meta_model = None
         test_meta_model = None
 
         # Start stacking
         for clf_id, clf in weak_learners:
-            
+
             # Predictions for each classifier based on k-fold
             val_predictions, test_predictions = self.train_level_0(clf)
-            
+
             # Stack predictions which will form 
-            # the inputa data for the data model
+            # the input data for the data model
             if isinstance(train_meta_model, np.ndarray):
                 train_meta_model = np.vstack((train_meta_model, val_predictions))
             else:
@@ -55,25 +57,24 @@ def BlendingClassifier(self):
                 test_meta_model = np.vstack((test_meta_model, test_predictions))
             else:
                 test_meta_model = test_predictions
-        
+
         # Transpose train_meta_model
         train_meta_model = train_meta_model.T
 
         # Transpose test_meta_model
         test_meta_model = test_meta_model.T
-        
+
         # Training level 1
         self.train_level_1(final_learner, train_meta_model, test_meta_model)
 
-
     def train_level_0(self, clf):
         # Train with base x_train
         clf.fit(self.x_train, self.y_train)
-        
+
         # Generate predictions for the holdout set (validation)
         # These predictions will build the input for the meta model
         val_predictions = clf.predict(self.x_val)
-        
+
         # Generate predictions for original test set
         # These predictions will be used to test the meta model
         test_predictions = clf.predict(self.x_test)
@@ -83,13 +84,13 @@ def train_level_0(self, clf):
     def train_level_1(self, final_learner, train_meta_model, test_meta_model):
         # Train is carried out with final learner or meta model
         final_learner.fit(train_meta_model, self.y_val)
-       
+
         # Getting train and test accuracies from meta_model
-        print(f"Train accuracy: {final_learner.score(train_meta_model,  self.y_val)}")
+        print(f"Train accuracy: {final_learner.score(train_meta_model, self.y_val)}")
         print(f"Test accuracy: {final_learner.score(test_meta_model, self.y_test)}")
-        
+
 
 if __name__ == "__main__":
     ensemble = Ensemble()
     ensemble.load_data()
-    ensemble.BlendingClassifier()
+    ensemble.BlendingClassifier()
diff --git a/requirements.txt b/requirements.txt
diff --git a/stacking.py b/stacking.py
@@ -9,6 +9,7 @@
 from sklearn.naive_bayes import GaussianNB
 from sklearn.linear_model import LogisticRegression
 
+
 class Ensemble:
     def __init__(self):
         self.x_train = None
@@ -20,17 +21,17 @@ def __init__(self):
     def load_data(self):
         x, y = load_breast_cancer(return_X_y=True)
         self.x_train, self.x_test, self.y_train, self.y_test = train_test_split(x, y, test_size=0.3, random_state=23)
-    
+
     def StackingClassifier(self):
 
         # Define weak learners
         weak_learners = [('dt', DecisionTreeClassifier()),
-                        ('knn', KNeighborsClassifier()),
-                        ('rf', RandomForestClassifier()),
-                        ('gb', GradientBoostingClassifier()),
-                        ('gn', GaussianNB())]
-        
-        # Finaler learner or meta model
+                         ('knn', KNeighborsClassifier()),
+                         ('rf', RandomForestClassifier()),
+                         ('gb', GradientBoostingClassifier()),
+                         ('gn', GaussianNB())]
+
+        # Final learner or meta model
         final_learner = LogisticRegression()
 
         train_meta_model = None
@@ -40,12 +41,12 @@ def StackingClassifier(self):
         for clf_id, clf in weak_learners:
             # Predictions for each classifier based on k-fold
             predictions_clf = self.k_fold_cross_validation(clf)
-            
+
             # Predictions for test set for each classifier based on train of level 0
             test_predictions_clf = self.train_level_0(clf)
-            
+
             # Stack predictions which will form 
-            # the inputa data for the data model
+            # the input data for the data model
             if isinstance(train_meta_model, np.ndarray):
                 train_meta_model = np.vstack((train_meta_model, predictions_clf))
             else:
@@ -57,19 +58,18 @@ def StackingClassifier(self):
                 test_meta_model = np.vstack((test_meta_model, test_predictions_clf))
             else:
                 test_meta_model = test_predictions_clf
-        
+
         # Transpose train_meta_model
         train_meta_model = train_meta_model.T
 
         # Transpose test_meta_model
         test_meta_model = test_meta_model.T
-        
+
         # Training level 1
         self.train_level_1(final_learner, train_meta_model, test_meta_model)
 
-
     def k_fold_cross_validation(self, clf):
-        
+
         predictions_clf = None
 
         # Number of samples per fold
@@ -87,14 +87,16 @@ def k_fold_cross_validation(self, clf):
                 test = self.x_train[(batch_size * fold): (batch_size * (fold + 1)), :]
                 batch_start = batch_size * fold
                 batch_finish = batch_size * (fold + 1)
-            
+
             # test & training samples for each fold iteration
             fold_x_test = self.x_train[batch_start:batch_finish, :]
-            fold_x_train = self.x_train[[index for index in range(self.x_train.shape[0]) if index not in range(batch_start, batch_finish)], :]
+            fold_x_train = self.x_train[[index for index in range(self.x_train.shape[0]) if
+                                         index not in range(batch_start, batch_finish)], :]
 
             # test & training targets for each fold iteration
             fold_y_test = self.y_train[batch_start:batch_finish]
-            fold_y_train = self.y_train[[index for index in range(self.x_train.shape[0]) if index not in range(batch_start, batch_finish)]]
+            fold_y_train = self.y_train[
+                [index for index in range(self.x_train.shape[0]) if index not in range(batch_start, batch_finish)]]
 
             # Fit current classifier
             clf.fit(fold_x_train, fold_y_train)
@@ -113,18 +115,18 @@ def train_level_0(self, clf):
         clf.fit(self.x_train, self.y_train)
         # Get predictions from full real test set
         y_pred = clf.predict(self.x_test)
-        
+
         return y_pred
 
     def train_level_1(self, final_learner, train_meta_model, test_meta_model):
         # Train is carried out with final learner or meta model
         final_learner.fit(train_meta_model, self.y_train)
         # Getting train and test accuracies from meta_model
-        print(f"Train accuracy: {final_learner.score(train_meta_model,  self.y_train)}")
+        print(f"Train accuracy: {final_learner.score(train_meta_model, self.y_train)}")
         print(f"Test accuracy: {final_learner.score(test_meta_model, self.y_test)}")
-        
+
 
 if __name__ == "__main__":
     ensemble = Ensemble()
     ensemble.load_data()
-    ensemble.StackingClassifier()
+    ensemble.StackingClassifier()