Fix the mistake shown in landscape

glemaitre · May 20, 2016 · 1e53be0 · 1e53be0
1 parent aa6761a
commit 1e53be0
Show file tree

Hide file tree

Showing 5 changed files with 7 additions and 13 deletions.
diff --git a/unbalanced_dataset/ensemble/balance_cascade.py b/unbalanced_dataset/ensemble/balance_cascade.py
@@ -266,9 +266,9 @@ def transform(self, X, y):
                 idx_under.append(np.concatenate((idx_min, idx_sel_from_maj),
                                                 axis=0))
 
-            if (not ((self.classifier_name == 'knn') or
-                     (self.classifier_name == 'linear-svm')) and
-                self.bootstrap):
+            if (not (self.classifier_name == 'knn' or
+                     self.classifier_name == 'linear-svm') and
+                    self.bootstrap):
                 # Apply a bootstrap on x_data
                 curr_sample_weight = np.ones((y_data.size,), dtype=np.float64)
                 indices = np.random.randint(0, y_data.size, y_data.size)

diff --git a/unbalanced_dataset/ensemble/ensemble_sampler.py b/unbalanced_dataset/ensemble/ensemble_sampler.py
@@ -2,8 +2,6 @@
 from __future__ import print_function
 from __future__ import division
 
-from collections import Counter
-
 from abc import ABCMeta, abstractmethod
 
 from ..base_sampler import BaseSampler

diff --git a/unbalanced_dataset/over_sampling/smote.py b/unbalanced_dataset/over_sampling/smote.py
@@ -406,7 +406,6 @@ def transform(self, X, y):
 
         # Start by separating minority class features and target values.
         X_min = X[y == self.min_c_]
-        y_min = y[y == self.min_c_]
 
         # If regular SMOTE is to be performed
         if self.kind == 'regular':
@@ -448,8 +447,7 @@ def transform(self, X, y):
 
             return X_resampled, y_resampled
 
-        if (self.kind == 'borderline1' or
-            self.kind == 'borderline2'):
+        if self.kind == 'borderline1' or self.kind == 'borderline2':
 
             if self.verbose:
                 print("Finding the {} nearest neighbours...".format(self.m))
@@ -638,7 +636,7 @@ def transform(self, X, y):
 
             # Concatenate the newly generated samples to the original data set
             if (np.count_nonzero(danger_bool) > 0 and
-                np.count_nonzero(safety_bool) > 0):
+                    np.count_nonzero(safety_bool) > 0):
                 X_resampled = np.concatenate((X, X_new_1, X_new_2), axis=0)
                 y_resampled = np.concatenate((y, y_new_1, y_new_2), axis=0)
             # not any support vectors in danger

diff --git a/unbalanced_dataset/under_sampling/nearmiss.py b/unbalanced_dataset/under_sampling/nearmiss.py
@@ -2,8 +2,6 @@
 from __future__ import print_function
 from __future__ import division
 
-import multiprocessing
-
 import numpy as np
 
 from collections import Counter

diff --git a/unbalanced_dataset/under_sampling/tomek_links.py b/unbalanced_dataset/under_sampling/tomek_links.py
@@ -205,8 +205,8 @@ def transform(self, X, y):
         # Check if the indices of the samples selected should be returned too
         if self.return_indices:
             # Return the indices of interest
-            return X[np.logical_not(links)], y[np.logical_not(links)],
-            np.nonzero(np.logical_not(links))[0]
+            return (X[np.logical_not(links)], y[np.logical_not(links)],
+                    np.nonzero(np.logical_not(links))[0])
         else:
             # Return data set without majority Tomek links.
             return X[np.logical_not(links)], y[np.logical_not(links)]