Add stacking param tuning

docs/sources/CHANGELOG.md

@@ -15,7 +15,7 @@ The CHANGELOG for the current development version is available at
 
 ##### New Features
 
-- Added `evaluate.permutation_test`, a permutation test for hypothesis testing (or A/B testing) to test if two samples come from the same distribution. Or in other words, a procedure to test the null hypothesis that that two groups are not significantly different (e.g., a treatment and a control group). 
+- Added `evaluate.permutation_test`, a permutation test for hypothesis testing (or A/B testing) to test if two samples come from the same distribution. Or in other words, a procedure to test the null hypothesis that that two groups are not significantly different (e.g., a treatment and a control group).
 - Added `'leverage'` and `'conviction` as evaluation metrics to the `frequent_patterns.association_rules` function. [#246](https://github.com/rasbt/mlxtend/pull/246) & [#247](https://github.com/rasbt/mlxtend/pull/247)
 - Added a `loadings_` attribute to `PrincipalComponentAnalysis` to compute the factor loadings of the features on the principal components. [#251](https://github.com/rasbt/mlxtend/pull/251)
 
@@ -27,6 +27,7 @@ The CHANGELOG for the current development version is available at
 ##### Bug Fixes
 
 - the "S" vector from SVD in `PrincipalComponentAnalysis` are now scaled so that the eigenvalues via `solver='eigen'` and `solver='svd'` now store eigenvalues that have the same magnitudes. [#251](https://github.com/rasbt/mlxtend/pull/251)
+- The parameters for `StackingClassifier`, `StackingCVClassifier`, `StackingRegressor`, `StackingCVRegressor`, and `EnsembleVoteClassifier` can now be tuned using scikit-learn's `GridSearchCV` ([#254](https://github.com/rasbt/mlxtend/pull/254) via [James Bourbeau](https://github.com/jrbourbeau))
 
 ### Version 0.8.0 (2017-09-09)
 

mlxtend/classifier/ensemble_vote.py

@@ -252,6 +252,13 @@ def get_params(self, deep=True):
             for name, step in six.iteritems(self.named_clfs):
                 for key, value in six.iteritems(step.get_params(deep=True)):
                     out['%s__%s' % (name, key)] = value
+
+            for key, value in six.iteritems(super(EnsembleVoteClassifier,
+                                            self).get_params(deep=False)):
+                if key == 'clfs':
+                    continue
+                else:
+                    out['%s' % key] = value
             return out
 
     def _predict(self, X):

mlxtend/classifier/stacking_classification.py

@@ -125,6 +125,7 @@ def fit(self, X, y):
 
     def get_params(self, deep=True):
         """Return estimator parameter names for GridSearch support."""
+
         if not deep:
             return super(StackingClassifier, self).get_params(deep=False)
         else:
@@ -137,6 +138,14 @@ def get_params(self, deep=True):
             for name, step in six.iteritems(self.named_meta_classifier):
                 for key, value in six.iteritems(step.get_params(deep=True)):
                     out['%s__%s' % (name, key)] = value
+
+            for key, value in six.iteritems(super(StackingClassifier,
+                                            self).get_params(deep=False)):
+                if key in ('classifiers', 'meta-classifier'):
+                    continue
+                else:
+                    out['%s' % key] = value
+
             return out
 
     def _predict_meta_features(self, X):

mlxtend/classifier/stacking_cv_classification.py

@@ -242,6 +242,14 @@ def get_params(self, deep=True):
             for name, step in six.iteritems(self.named_meta_classifier):
                 for key, value in six.iteritems(step.get_params(deep=True)):
                     out['%s__%s' % (name, key)] = value
+
+            for key, value in six.iteritems(super(StackingCVClassifier,
+                                            self).get_params(deep=False)):
+                if key in ('classifiers', 'meta-classifier'):
+                    continue
+                else:
+                    out['%s' % key] = value
+
             return out
 
     def predict(self, X):

mlxtend/classifier/tests/test_ensemble_vote_classifier.py

@@ -77,11 +77,12 @@ def test_EnsembleVoteClassifier_gridsearch_enumerate_names():
 
     clf1 = LogisticRegression(random_state=1)
     clf2 = RandomForestClassifier(random_state=1)
-    eclf = EnsembleVoteClassifier(clfs=[clf1, clf1, clf2], voting='soft')
+    eclf = EnsembleVoteClassifier(clfs=[clf1, clf1, clf2])
 
     params = {'logisticregression-1__C': [1.0, 100.0],
               'logisticregression-2__C': [1.0, 100.0],
-              'randomforestclassifier__n_estimators': [5, 20]}
+              'randomforestclassifier__n_estimators': [5, 20],
+              'voting': ['hard', 'soft']}
 
     grid = GridSearchCV(estimator=eclf, param_grid=params, cv=5)
     grid = grid.fit(iris.data, iris.target)

mlxtend/classifier/tests/test_stacking_classifier.py

@@ -148,7 +148,8 @@ def test_gridsearch_enumerate_names():
 
     params = {'meta-logisticregression__C': [1.0, 100.0],
               'randomforestclassifier-1__n_estimators': [5, 10],
-              'randomforestclassifier-2__n_estimators': [5, 20]}
+              'randomforestclassifier-2__n_estimators': [5, 20],
+              'use_probas': [True, False]}
 
     grid = GridSearchCV(estimator=sclf, param_grid=params, cv=5)
     grid = grid.fit(iris.data, iris.target)

mlxtend/classifier/tests/test_stacking_cv_classifier.py

@@ -93,7 +93,8 @@ def test_gridsearch_enumerate_names():
 
     params = {'meta-logisticregression__C': [1.0, 100.0],
               'randomforestclassifier-1__n_estimators': [5, 10],
-              'randomforestclassifier-2__n_estimators': [5, 20]}
+              'randomforestclassifier-2__n_estimators': [5, 20],
+              'use_probas': [True, False]}
 
     grid = GridSearchCV(estimator=sclf, param_grid=params, cv=5)
     grid = grid.fit(iris.data, iris.target)

mlxtend/regressor/stacking_cv_regression.py

@@ -179,4 +179,12 @@ def get_params(self, deep=True):
             for name, step in six.iteritems(self.named_meta_regressor):
                 for key, value in six.iteritems(step.get_params(deep=True)):
                     out['%s__%s' % (name, key)] = value
+
+            for key, value in six.iteritems(super(StackingCVRegressor,
+                                            self).get_params(deep=False)):
+                if key in ('regressors', 'meta-regressor'):
+                    continue
+                else:
+                    out['%s' % key] = value
+
             return out

mlxtend/regressor/stacking_regression.py

@@ -128,6 +128,14 @@ def get_params(self, deep=True):
             for name, step in six.iteritems(self.named_meta_regressor):
                 for key, value in six.iteritems(step.get_params(deep=True)):
                     out['%s__%s' % (name, key)] = value
+
+            for key, value in six.iteritems(super(StackingRegressor,
+                                            self).get_params(deep=False)):
+                if key in ('regressors', 'meta-regressor'):
+                    continue
+                else:
+                    out['%s' % key] = value
+
             return out
 
     def _predict_meta_features(self, X):

mlxtend/regressor/tests/test_cv_stacking_regression.py

@@ -92,7 +92,8 @@ def test_gridsearch_numerate_regr():
     params = {'ridge-1__alpha': [0.01, 1.0],
               'ridge-2__alpha': [0.01, 1.0],
               'svr__C': [0.01, 1.0],
-              'meta-svr__C': [0.01, 1.0]}
+              'meta-svr__C': [0.01, 1.0],
+              'use_features_in_secondary': [True, False]}
 
     grid = GridSearchCV(estimator=stack,
                         param_grid=params,