example RENN added

Author: dvro

examples/under-sampling/plot_repeated_edited_nearest_neighbours.py

@@ -0,0 +1,74 @@
+"""
+=========================
+Repeated Edited nearest-neighbours
+=========================
+
+An illustration of the repeated edited nearest-neighbours method.
+
+"""
+
+print(__doc__)
+
+import matplotlib.pyplot as plt
+import seaborn as sns
+sns.set()
+
+# Define some color for the plotting
+almost_black = '#262626'
+palette = sns.color_palette()
+
+from sklearn.datasets import make_classification
+from sklearn.decomposition import PCA
+
+from unbalanced_dataset.under_sampling import EditedNearestNeighbours, \
+    RepeatedEditedNearestNeighbours
+
+# Generate the dataset
+X, y = make_classification(n_classes=2, class_sep=1.25, weights=[0.3, 0.7],
+                           n_informative=3, n_redundant=1, flip_y=0,
+                           n_features=5, n_clusters_per_class=1,
+                           n_samples=5000, random_state=10)
+
+# Instanciate a PCA object for the sake of easy visualisation
+pca = PCA(n_components=2)
+# Fit and transform x to visualise inside a 2D feature space
+X_vis = pca.fit_transform(X)
+
+# Three subplots, unpack the axes array immediately
+f, (ax1, ax2, ax3) = plt.subplots(1, 3)
+
+ax1.scatter(X_vis[y == 0, 0], X_vis[y == 0, 1], label="Class #0", alpha=.5,
+            edgecolor=almost_black, facecolor=palette[0], linewidth=0.15)
+ax1.scatter(X_vis[y == 1, 0], X_vis[y == 1, 1], label="Class #1", alpha=.5,
+            edgecolor=almost_black, facecolor=palette[2], linewidth=0.15)
+ax1.set_title('Original set')
+
+# Apply the ENN
+print('ENN')
+enn = EditedNearestNeighbours()
+X_resampled, y_resampled = enn.fit_transform(X, y)
+X_res_vis = pca.transform(X_resampled)
+
+ax2.scatter(X_res_vis[y_resampled == 0, 0], X_res_vis[y_resampled == 0, 1],
+            label="Class #0", alpha=.5, edgecolor=almost_black,
+            facecolor=palette[0], linewidth=0.15)
+ax2.scatter(X_res_vis[y_resampled == 1, 0], X_res_vis[y_resampled == 1, 1],
+            label="Class #1", alpha=.5, edgecolor=almost_black,
+            facecolor=palette[2], linewidth=0.15)
+ax2.set_title('Edited nearest neighbours')
+
+# Apply the RENN
+print('RENN')
+renn = RepeatedEditedNearestNeighbours()
+X_resampled, y_resampled = renn.fit_transform(X, y)
+X_res_vis = pca.transform(X_resampled)
+
+ax3.scatter(X_res_vis[y_resampled == 0, 0], X_res_vis[y_resampled == 0, 1],
+            label="Class #0", alpha=.5, edgecolor=almost_black,
+            facecolor=palette[0], linewidth=0.15)
+ax3.scatter(X_res_vis[y_resampled == 1, 0], X_res_vis[y_resampled == 1, 1],
+            label="Class #1", alpha=.5, edgecolor=almost_black,
+            facecolor=palette[2], linewidth=0.15)
+ax3.set_title('Repeated Edited nearest neighbours')
+
+plt.show()

unbalanced_dataset/under_sampling/__init__.py

@@ -12,6 +12,7 @@
 from .one_sided_selection import OneSidedSelection
 from .neighbourhood_cleaning_rule import NeighbourhoodCleaningRule
 from .edited_nearest_neighbours import EditedNearestNeighbours
+from .edited_nearest_neighbours import RepeatedEditedNearestNeighbours
 from .instance_hardness_threshold import InstanceHardnessThreshold
 
 __all__ = ['UnderSampler',
@@ -23,4 +24,5 @@
            'OneSidedSelection',
            'NeighbourhoodCleaningRule',
            'EditedNearestNeighbours',
+           'RepeatedEditedNearestNeighbours',
            'InstanceHardnessThreshold']

unbalanced_dataset/under_sampling/edited_nearest_neighbours.py

@@ -324,7 +324,7 @@ class RepeatedEditedNearestNeighbours(UnderSampler):
     """
 
     def __init__(self, return_indices=False, random_state=None, verbose=True,
-                 size_ngh=3, max_iter=None, kind_sel='all', n_jobs=-1):
+                 size_ngh=3, max_iter=100, kind_sel='all', n_jobs=-1):
         """Initialisation of RENN object.
 
         Parameters
@@ -366,7 +366,7 @@ def __init__(self, return_indices=False, random_state=None, verbose=True,
         super(RepeatedEditedNearestNeighbours, self).__init__(
             return_indices=return_indices,
             random_state=random_state,
-            verbose=False)
+            verbose=verbose)
 
         self.size_ngh = size_ngh
         possible_kind_sel = ('all', 'mode')
@@ -435,27 +435,29 @@ def transform(self, X, y):
         # Check the consistency of X and y
         X, y = check_X_y(X, y)
 
-        X_resampled, y_resampled = X.copy(), y.copy()
-        len_ = y.shape[0]
-        current_len_ = len_ - 1
+        X_, y_ = X, y
 
         if self.return_indices:
-            idx_under = np.arange(len_, dtype=int)
+            idx_under = np.arange(len(X.shape[0]), dtype=int)
+
+        prev_len = y.shape[0]
 
-        n_iter = 0
-        while current_len_ < len_ and 
-                (self.max_iter is None or n_iter < self.max_iter):
+        for n_iter in range(self.max_iter):
+            prev_len = y_.shape[0]
             if self.return_indices:
-                X_resampled, y_resampled, idx_ = self.enn_.transform(X_resampled, y_resampled)
+                X_, y_, idx_ = self.enn_.transform(X_, y_)
                 idx_under = idx_under[idx_]
             else:
-                X_resampled, y_resampled = self.enn_.transform(X_resampled, y_resampled)
+                X_, y_ = self.enn_.transform(X_, y_)
 
-            n_iter += 1
-            len_, current_len_ = current_len_, y_resampled.shape[0]
+            if prev_len == y_.shape[0]:
+                break
 
         if self.verbose:
-            print("Under-sampling performed: {}".format(Counter(y_resampled)))
+            print("Under-sampling performed: {}".format(Counter(y_)))
+
+        #X_resampled, y_resampled = X_.copy(), y_.copy()
+        X_resampled, y_resampled = X_, y_
 
         # Check if the indices of the samples selected should be returned too
         if self.return_indices: