Modified the level of the random_state in the class hierarchy (#178)

Author: glemaitre

imblearn/base.py

@@ -25,7 +25,7 @@ class SamplerMixin(six.with_metaclass(ABCMeta, BaseEstimator)):
 
     _estimator_type = 'sampler'
 
-    def __init__(self, ratio='auto'):
+    def __init__(self, ratio='auto', random_state=None):
         """Initialize this object and its instance variables.
 
         Parameters
@@ -36,13 +36,20 @@ def __init__(self, ratio='auto'):
             of samples in the minority class over the the number of samples
             in the majority class.
 
+    random_state : int, RandomState instance or None, optional (default=None)
+        If int, random_state is the seed used by the random number generator;
+        If RandomState instance, random_state is the random number generator;
+        If None, the random number generator is the RandomState instance used
+        by np.random.
+
         Returns
         -------
         None
 
         """
 
         self.ratio = ratio
+        self.random_state = random_state
         self.logger = logging.getLogger(__name__)
 
     def fit(self, X, y):

imblearn/combine/smote_enn.py

@@ -115,8 +115,7 @@ def __init__(self, ratio='auto', random_state=None,
                  size_ngh=None, n_neighbors=3, kind_enn='all', n_jobs=-1,
                  **kwargs):
 
-        super(SMOTEENN, self).__init__(ratio=ratio)
-        self.random_state = random_state
+        super(SMOTEENN, self).__init__(ratio=ratio, random_state=random_state)
         self.k = k
         self.m = m
         self.out_step = out_step

imblearn/combine/smote_tomek.py

@@ -101,8 +101,8 @@ class SMOTETomek(BaseBinarySampler):
     def __init__(self, ratio='auto', random_state=None,
                  k=5, m=10, out_step=0.5, kind_smote='regular',
                  n_jobs=-1, **kwargs):
-        super(SMOTETomek, self).__init__(ratio=ratio)
-        self.random_state = random_state
+        super(SMOTETomek, self).__init__(ratio=ratio,
+                                         random_state=random_state)
         self.k = k
         self.m = m
         self.out_step = out_step

imblearn/ensemble/balance_cascade.py

@@ -102,9 +102,9 @@ class BalanceCascade(BaseBinarySampler):
     def __init__(self, ratio='auto', return_indices=False, random_state=None,
                  n_max_subset=None, classifier='knn', bootstrap=True,
                  **kwargs):
-        super(BalanceCascade, self).__init__(ratio=ratio)
+        super(BalanceCascade, self).__init__(ratio=ratio,
+                                             random_state=random_state)
         self.return_indices = return_indices
-        self.random_state = random_state
         self.classifier = classifier
         self.n_max_subset = n_max_subset
         self.bootstrap = bootstrap

imblearn/ensemble/easy_ensemble.py

@@ -90,9 +90,9 @@ class EasyEnsemble(BaseMulticlassSampler):
 
     def __init__(self, ratio='auto', return_indices=False,
                  random_state=None, replacement=False, n_subsets=10):
-        super(EasyEnsemble, self).__init__(ratio=ratio)
+        super(EasyEnsemble, self).__init__(ratio=ratio,
+                                           random_state=random_state)
         self.return_indices = return_indices
-        self.random_state = random_state
         self.replacement = replacement
         self.n_subsets = n_subsets
 

imblearn/over_sampling/adasyn.py

@@ -84,13 +84,8 @@ class ADASYN(BaseBinarySampler):
 
     """
 
-    def __init__(self,
-                 ratio='auto',
-                 random_state=None,
-                 k=5,
-                 n_jobs=1):
-        super(ADASYN, self).__init__(ratio=ratio)
-        self.random_state = random_state
+    def __init__(self, ratio='auto', random_state=None, k=5, n_jobs=1):
+        super(ADASYN, self).__init__(ratio=ratio, random_state=random_state)
         self.k = k
         self.n_jobs = n_jobs
         self.nearest_neighbour = NearestNeighbors(n_neighbors=self.k + 1,

imblearn/over_sampling/random_over_sampler.py

@@ -72,8 +72,8 @@ def __init__(self,
                  ratio='auto',
                  random_state=None):
 
-        super(RandomOverSampler, self).__init__(ratio=ratio)
-        self.random_state = random_state
+        super(RandomOverSampler, self).__init__(ratio=ratio,
+                                                random_state=random_state)
 
     def _sample(self, X, y):
         """Resample the dataset.

imblearn/over_sampling/smote.py

@@ -102,17 +102,9 @@ class SMOTE(BaseBinarySampler):
 
     """
 
-    def __init__(self,
-                 ratio='auto',
-                 random_state=None,
-                 k=5,
-                 m=10,
-                 out_step=0.5,
-                 kind='regular',
-                 n_jobs=-1,
-                 **kwargs):
-        super(SMOTE, self).__init__(ratio=ratio)
-        self.random_state = random_state
+    def __init__(self, ratio='auto', random_state=None, k=5, m=10,
+                 out_step=0.5, kind='regular', n_jobs=-1, **kwargs):
+        super(SMOTE, self).__init__(ratio=ratio, random_state=random_state)
         self.kind = kind
         self.k = k
         self.m = m

imblearn/under_sampling/cluster_centroids.py

@@ -80,8 +80,8 @@ class ClusterCentroids(BaseMulticlassSampler):
     """
 
     def __init__(self, ratio='auto', random_state=None, n_jobs=-1, **kwargs):
-        super(ClusterCentroids, self).__init__(ratio=ratio)
-        self.random_state = random_state
+        super(ClusterCentroids, self).__init__(ratio=ratio,
+                                               random_state=random_state)
         self.n_jobs = n_jobs
         self.kwargs = kwargs
 

imblearn/under_sampling/condensed_nearest_neighbour.py

@@ -97,10 +97,9 @@ class CondensedNearestNeighbour(BaseMulticlassSampler):
     def __init__(self, return_indices=False, random_state=None,
                  size_ngh=None, n_neighbors=1, n_seeds_S=1, n_jobs=-1,
                  **kwargs):
-        super(CondensedNearestNeighbour, self).__init__()
-
+        super(CondensedNearestNeighbour, self).__init__(
+            random_state=random_state)
         self.return_indices = return_indices
-        self.random_state = random_state
         self.size_ngh = size_ngh
         self.n_neighbors = n_neighbors
         self.n_seeds_S = n_seeds_S