Skip to content

Commit 2c0628f

Browse files
authored
DOC mention the multi-class scheme used (scikit-learn-contrib#311)
1 parent 1e3fdfe commit 2c0628f

15 files changed

+33
-18
lines changed

imblearn/combine/smote_enn.py

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -132,7 +132,8 @@ class SMOTEENN(SamplerMixin):
132132
-----
133133
The method is presented in [1]_.
134134
135-
Supports mutli-class resampling.
135+
Supports mutli-class resampling. Refer to SMOTE and ENN regarding the
136+
scheme which used.
136137
137138
Examples
138139
--------

imblearn/combine/smote_tomek.py

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -102,7 +102,8 @@ class SMOTETomek(SamplerMixin):
102102
-----
103103
The methos is presented in [1]_.
104104
105-
Supports mutli-class resampling.
105+
Supports mutli-class resampling. Refer to SMOTE and TomekLinks regarding
106+
the scheme which used.
106107
107108
Examples
108109
--------

imblearn/ensemble/balance_cascade.py

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -90,7 +90,8 @@ class BalanceCascade(BaseEnsembleSampler):
9090
-----
9191
The method is described in [1]_.
9292
93-
Supports mutli-class resampling.
93+
Supports mutli-class resampling. A one-vs.-rest scheme is used as
94+
originally proposed in [1]_.
9495
9596
Examples
9697
--------

imblearn/ensemble/easy_ensemble.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -59,7 +59,7 @@ class EasyEnsemble(BaseEnsembleSampler):
5959
-----
6060
The method is described in [1]_.
6161
62-
Supports mutli-class resampling.
62+
Supports mutli-class resampling by sampling each class independently.
6363
6464
Examples
6565
--------

imblearn/over_sampling/adasyn.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -63,10 +63,10 @@ class ADASYN(BaseOverSampler):
6363
6464
Notes
6565
-----
66-
Supports mutli-class resampling.
67-
6866
The implementation is based on [1]_.
6967
68+
Supports mutli-class resampling. A one-vs.-rest scheme is used.
69+
7070
Examples
7171
--------
7272

imblearn/over_sampling/random_over_sampler.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -46,7 +46,7 @@ class RandomOverSampler(BaseOverSampler):
4646
4747
Notes
4848
-----
49-
Supports mutli-class resampling.
49+
Supports mutli-class resampling by sampling each class independently.
5050
5151
Examples
5252
--------

imblearn/over_sampling/smote.py

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -99,7 +99,8 @@ class SMOTE(BaseOverSampler):
9999
-----
100100
See the original papers: [1]_, [2]_, [3]_ for more details.
101101
102-
Supports mutli-class resampling.
102+
Supports mutli-class resampling. A one-vs.-rest scheme is used as
103+
originally proposed in [1]_.
103104
104105
Examples
105106
--------

imblearn/under_sampling/prototype_generation/cluster_centroids.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -58,7 +58,7 @@ class ClusterCentroids(BaseUnderSampler):
5858
5959
Notes
6060
-----
61-
Supports mutli-class resampling.
61+
Supports mutli-class resampling by sampling each class independently.
6262
6363
Examples
6464
--------

imblearn/under_sampling/prototype_selection/condensed_nearest_neighbour.py

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -75,7 +75,8 @@ class CondensedNearestNeighbour(BaseCleaningSampler):
7575
-----
7676
The method is based on [1]_.
7777
78-
Supports mutli-class resampling.
78+
Supports mutli-class resampling. A one-vs.-rest scheme is used when
79+
sampling a class as proposed in [1]_.
7980
8081
Examples
8182
--------

imblearn/under_sampling/prototype_selection/edited_nearest_neighbours.py

Lines changed: 6 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -84,7 +84,8 @@ class EditedNearestNeighbours(BaseCleaningSampler):
8484
-----
8585
The method is based on [1]_.
8686
87-
Supports mutli-class resampling.
87+
Supports mutli-class resampling. A one-vs.-rest scheme is used when
88+
sampling a class as proposed in [1]_.
8889
8990
Examples
9091
--------
@@ -272,7 +273,8 @@ class RepeatedEditedNearestNeighbours(BaseCleaningSampler):
272273
273274
Notes
274275
-----
275-
The method is based on [1]_.
276+
The method is based on [1]_. A one-vs.-rest scheme is used when
277+
sampling a class as proposed in [1]_.
276278
277279
Supports mutli-class resampling.
278280
@@ -482,7 +484,8 @@ class AllKNN(BaseCleaningSampler):
482484
-----
483485
The method is based on [1]_.
484486
485-
Supports mutli-class resampling.
487+
Supports mutli-class resampling. A one-vs.-rest scheme is used when
488+
sampling a class as proposed in [1]_.
486489
487490
Examples
488491
--------

0 commit comments

Comments
 (0)