sort feature indices

rasbt · Oct 12, 2017 · 1550820 · 1550820
1 parent bb9af54
commit 1550820
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 4 deletions.
diff --git a/docs/sources/CHANGELOG.md b/docs/sources/CHANGELOG.md
@@ -19,11 +19,13 @@ The CHANGELOG for the current development version is available at
 - 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)
 - Allow grid search over classifiers/regressors in ensemble and stacking estimators [#259](https://github.com/rasbt/mlxtend/pull/259)
+- Added a `recursive_floating` parameter to the `SequentialFeatureSelector` to enable the continuation of the floating inclusion/exclusion as described in Novovicova & Kittler (1994) [#262](https://github.com/rasbt/mlxtend/pull/262)
 
 ##### Changes
 
 - The `'support'` column returned by `frequent_patterns.association_rules` was changed to compute the support of "antecedant union consequent", and new `antecedant support'` and `'consequent support'` column were added to avoid ambiguity. [#245](https://github.com/rasbt/mlxtend/pull/245)
 - Allow the `OnehotTransactions` to be cloned via scikit-learn's `clone` function, which is required by e.g., scikit-learn's `FeatureUnion` or `GridSearchCV` (via [Iaroslav Shcherbatyi](https://github.com/iaroslav-ai)). [#249](https://github.com/rasbt/mlxtend/pull/249)
+- All feature indix tuples in `SequentialFeatureSelector` or now in sorted order [#262](https://github.com/rasbt/mlxtend/pull/262)
 
 ##### Bug Fixes
 

diff --git a/mlxtend/feature_selection/sequential_feature_selector.py b/mlxtend/feature_selection/sequential_feature_selector.py
@@ -358,6 +358,9 @@ def fit(self, X, y):
                 # floating can lead to multiple same-sized subsets
                 if k not in self.subsets_ or (k_score >
                                               self.subsets_[k]['avg_score']):
+
+                    k_idx = tuple(sorted(k_idx))
+
                     self.subsets_[k] = {
                         'feature_idx': k_idx,
                         'cv_scores': cv_scores,
@@ -424,7 +427,6 @@ def fit(self, X, y):
 
         self.k_feature_idx_ = k_idx
         self.k_score_ = k_score
-        self.subsets_plus_ = dict()
         self.fitted = True
         return self
 

diff --git a/mlxtend/feature_selection/tests/test_sequential_feature_selector.py b/mlxtend/feature_selection/tests/test_sequential_feature_selector.py
@@ -500,7 +500,7 @@ def test_regression_sbfs():
                 cv=10,
                 verbose=0)
     sfs_r = sfs_r.fit(X, y)
-    assert sfs_r.k_feature_idx_ == (10, 12, 7), sfs_r.k_feature_idx_
+    assert sfs_r.k_feature_idx_ == (7, 10, 12), sfs_r.k_feature_idx_
 
 
 def test_regression_sbfs_recursive_floating():
@@ -516,7 +516,7 @@ def test_regression_sbfs_recursive_floating():
                 recursive_floating=True,
                 verbose=0)
     sfs_r = sfs_r.fit(X, y)
-    assert sfs_r.k_feature_idx_ == (10, 12, 7), sfs_r.k_feature_idx_
+    assert sfs_r.k_feature_idx_ == (7, 10, 12), sfs_r.k_feature_idx_
 
 
 def test_regression_in_range():
@@ -741,4 +741,4 @@ def test_max_feature_subset_parsimonious():
               cv=10)
 
     sfs = sfs.fit(X, y)
-    assert sfs.k_feature_idx_ == (10, 11, 12, 5)
+    assert sfs.k_feature_idx_ == (5, 10, 11, 12)