MAINT deprecate random_state and make hash deterministic (#374)

Author: glemaitre

doc/under_sampling.rst

@@ -112,7 +112,7 @@ samples. :class:`NearMiss` implements 3 different types of heuristic which can
 be selected with the parameter ``version``::
 
   >>> from imblearn.under_sampling import NearMiss
-  >>> nm1 = NearMiss(random_state=0, version=1)
+  >>> nm1 = NearMiss(version=1)
   >>> X_resampled_nm1, y_resampled = nm1.fit_sample(X, y)
   >>> print(sorted(Counter(y_resampled).items()))
   [(0, 64), (1, 64), (2, 64)]
@@ -247,7 +247,7 @@ the sample inspected to keep it in the dataset::
   >>> sorted(Counter(y).items())
   [(0, 64), (1, 262), (2, 4674)]
   >>> from imblearn.under_sampling import EditedNearestNeighbours
-  >>> enn = EditedNearestNeighbours(random_state=0)
+  >>> enn = EditedNearestNeighbours()
   >>> X_resampled, y_resampled = enn.fit_sample(X, y)
   >>> print(sorted(Counter(y_resampled).items()))
   [(0, 64), (1, 213), (2, 4568)]
@@ -261,7 +261,7 @@ the decision to keep a given sample or not.
 Generally, repeating the algorithm will delete more data::
 
    >>> from imblearn.under_sampling import RepeatedEditedNearestNeighbours
-   >>> renn = RepeatedEditedNearestNeighbours(random_state=0)
+   >>> renn = RepeatedEditedNearestNeighbours()
    >>> X_resampled, y_resampled = renn.fit_sample(X, y)
    >>> print(sorted(Counter(y_resampled).items()))
    [(0, 64), (1, 208), (2, 4551)]
@@ -271,7 +271,7 @@ Generally, repeating the algorithm will delete more data::
 internal nearest neighbors algorithm is increased at each iteration::
 
   >>> from imblearn.under_sampling import AllKNN
-  >>> allknn = AllKNN(random_state=0)
+  >>> allknn = AllKNN()
   >>> X_resampled, y_resampled = allknn.fit_sample(X, y)
   >>> print(sorted(Counter(y_resampled).items()))
   [(0, 64), (1, 220), (2, 4601)]
@@ -338,7 +338,7 @@ between the :class:`EditedNearestNeighbours` and the output a 3 nearest
 neighbors classifier. The class can be used as::
 
   >>> from imblearn.under_sampling import NeighbourhoodCleaningRule
-  >>> ncr = NeighbourhoodCleaningRule(random_state=0)
+  >>> ncr = NeighbourhoodCleaningRule()
   >>> X_resampled, y_resampled = ncr.fit_sample(X, y)
   >>> print(sorted(Counter(y_resampled).items()))
   [(0, 64), (1, 234), (2, 4666)]

examples/under-sampling/plot_illustration_tomek_links.py

@@ -67,7 +67,7 @@ def make_plot_despine(ax):
 # samples. If ``ratio='auto'`` only the sample from the majority class will be
 # removed. If ``ratio='all'`` both samples will be removed.
 
-sampler = TomekLinks(random_state=0)
+sampler = TomekLinks()
 
 fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 6))
 

imblearn/base.py

@@ -131,9 +131,8 @@ class BaseSampler(SamplerMixin):
     instead.
     """
 
-    def __init__(self, ratio='auto', random_state=None):
+    def __init__(self, ratio='auto'):
         self.ratio = ratio
-        self.random_state = random_state
         self.logger = logging.getLogger(__name__)
 
     def fit(self, X, y):

imblearn/combine/smote_enn.py

@@ -125,8 +125,7 @@ def _validate_estimator(self):
                                  ' Got {} instead.'.format(type(self.enn)))
         # Otherwise create a default EditedNearestNeighbours
         else:
-            self.enn_ = EditedNearestNeighbours(ratio='all',
-                                                random_state=self.random_state)
+            self.enn_ = EditedNearestNeighbours(ratio='all')
 
     def fit(self, X, y):
         """Find the classes statistics before to perform sampling.

imblearn/combine/smote_tomek.py

@@ -134,8 +134,7 @@ def _validate_estimator(self):
                                  'Got {} instead.'.format(type(self.tomek)))
         # Otherwise create a default TomekLinks
         else:
-            self.tomek_ = TomekLinks(ratio='all',
-                                     random_state=self.random_state)
+            self.tomek_ = TomekLinks(ratio='all')
 
     def fit(self, X, y):
         """Find the classes statistics before to perform sampling.

imblearn/ensemble/balance_cascade.py

@@ -113,8 +113,8 @@ def __init__(self,
                  random_state=None,
                  n_max_subset=None,
                  estimator=None):
-        super(BalanceCascade, self).__init__(ratio=ratio,
-                                             random_state=random_state)
+        super(BalanceCascade, self).__init__(ratio=ratio)
+        self.random_state = random_state
         self.return_indices = return_indices
         self.estimator = estimator
         self.n_max_subset = n_max_subset

imblearn/ensemble/easy_ensemble.py

@@ -101,8 +101,8 @@ def __init__(self,
                  random_state=None,
                  replacement=False,
                  n_subsets=10):
-        super(EasyEnsemble, self).__init__(ratio=ratio,
-                                           random_state=random_state)
+        super(EasyEnsemble, self).__init__(ratio=ratio)
+        self.random_state = random_state
         self.return_indices = return_indices
         self.replacement = replacement
         self.n_subsets = n_subsets

imblearn/over_sampling/adasyn.py

@@ -104,7 +104,8 @@ def __init__(self,
                  random_state=None,
                  n_neighbors=5,
                  n_jobs=1):
-        super(ADASYN, self).__init__(ratio=ratio, random_state=random_state)
+        super(ADASYN, self).__init__(ratio=ratio)
+        self.random_state = random_state
         self.n_neighbors = n_neighbors
         self.n_jobs = n_jobs
 

imblearn/over_sampling/base.py

@@ -5,8 +5,6 @@
 #          Christos Aridas
 # License: MIT
 
-from sklearn.utils import check_X_y
-
 from ..base import BaseSampler
 
 

imblearn/over_sampling/random_over_sampler.py

@@ -76,8 +76,8 @@ class RandomOverSampler(BaseOverSampler):
     """
 
     def __init__(self, ratio='auto', random_state=None):
-        super(RandomOverSampler, self).__init__(
-            ratio=ratio, random_state=random_state)
+        super(RandomOverSampler, self).__init__(ratio=ratio)
+        self.random_state = random_state
 
     def _sample(self, X, y):
         """Resample the dataset.