COSMIT pep8

amueller · amueller · commit 070007fd8813 · 2012-01-08T20:12:40.000+01:00
diff --git a/sklearn/decomposition/dict_learning.py b/sklearn/decomposition/dict_learning.py
@@ -1012,7 +1012,7 @@ class MiniBatchDictionaryLearning(BaseEstimator, SparseCodingMixin):
         Lasso solution (linear_model.Lasso). Lars will be faster if
         the estimated components are sparse.
 
-    transform_algorithm : {'lasso_lars', 'lasso_cd', 'lars', 'omp', \ 
+    transform_algorithm : {'lasso_lars', 'lasso_cd', 'lars', 'omp', \
     'threshold'}
         Algorithm used to transform the data.
         lars: uses the least angle regression method (linear_model.lars_path)
diff --git a/sklearn/feature_selection/__init__.py b/sklearn/feature_selection/__init__.py
@@ -16,4 +16,3 @@
 
 from .rfe import RFE
 from .rfe import RFECV
-
diff --git a/sklearn/grid_search.py b/sklearn/grid_search.py
@@ -401,4 +401,3 @@ def best_estimator(self):
                 ' Please use GridSearchCV.best_score_ instead.')
     def best_score(self):
         return self.best_score_
-
diff --git a/sklearn/linear_model/tests/test_base.py b/sklearn/linear_model/tests/test_base.py
@@ -49,4 +49,3 @@ def test_linear_regression_sparse(random_state=0):
     ols.fit(X, y.ravel())
     assert_array_almost_equal(beta, ols.coef_ + ols.intercept_)
     assert_array_almost_equal(ols.residues_, 0)
-
