FIX: SMOTENC should use half of the median of the std. dev. (#491)

Author: glemaitre

doc/over_sampling.rst

@@ -188,9 +188,9 @@ features or a boolean mask marking these features::
   >>> print(sorted(Counter(y_resampled).items()))
   [(0, 30), (1, 30)]
   >>> print(X_resampled[-5:])
-  [['B' 0.1989993778979113 0]
-   ['A' -0.3657680728116921 1]
-   ['B' 0.8790828729585258 0]
+  [['B' 0.5246469549655818 0]
+   ['A' -0.3657680728116921 0]
+   ['B' 0.9344237230779993 0]
    ['A' 0.3710891618824609 0]
    ['A' 0.3327240726719727 0]]
 

doc/whats_new/v0.0.4.rst

@@ -1,5 +1,19 @@
 .. _changes_0_4:
 
+Version 0.4.2
+=============
+
+Changelog
+---------
+
+Bug fixes
+.........
+
+- Fix a bug in :class:`imblearn.over_sampling.SMOTENC` in which the the median
+  of the standard deviation instead of half of the median of the standard
+  deviation.
+  By :user:`Guillaume Lemaitre <glemaitre>` in :issue:`491`.
+
 Version 0.4
 ===========
 

imblearn/over_sampling/_smote.py

@@ -974,7 +974,7 @@ def _fit_resample(self, X, y):
         # distance is computed between 2 samples, the difference will be equal
         # to the median of the standard deviation as in the original paper.
         X_ohe.data = (np.ones_like(X_ohe.data, dtype=X_ohe.dtype) *
-                      self.median_std_)
+                      self.median_std_ / 2)
         X_encoded = sparse.hstack((X_continuous, X_ohe), format='csr')
 
         X_resampled, y_resampled = super(SMOTENC, self)._fit_resample(