LMNN: fix mistake and improve performances (#78)

Fix mistake in LMNN

Issue in function _find_impostors:
 - the squared euclidean distance is used to compute the margins in variable "margin_radii"
 - the euclidean distance is used (through the function sklearn.metrics.pairwise.pairwise_distances) to compute distances between samples of different labels in variable "dist"
 - the issue is that the impostors are found by testing "dist < margin_radii" which is wrong because "dist" represent distances, and "margin_radii" represent squared distances.

I propose to solve this problem by computing always the squared distances.

Author: toto6

metric_learn/lmnn.py

@@ -14,8 +14,8 @@
 import warnings
 from collections import Counter
 from six.moves import xrange
-from sklearn.metrics import pairwise_distances
 from sklearn.utils.validation import check_X_y, check_array
+from sklearn.metrics import euclidean_distances
 
 from .base_metric import BaseMetricLearner
 
@@ -185,7 +185,7 @@ def _select_targets(self):
     target_neighbors = np.empty((self.X_.shape[0], self.k), dtype=int)
     for label in self.labels_:
       inds, = np.nonzero(self.label_inds_ == label)
-      dd = pairwise_distances(self.X_[inds])
+      dd = euclidean_distances(self.X_[inds], squared=True)
       np.fill_diagonal(dd, np.inf)
       nn = np.argsort(dd)[..., :self.k]
       target_neighbors[inds] = inds[nn]
@@ -198,7 +198,7 @@ def _find_impostors(self, furthest_neighbors):
     for label in self.labels_[:-1]:
       in_inds, = np.nonzero(self.label_inds_ == label)
       out_inds, = np.nonzero(self.label_inds_ > label)
-      dist = pairwise_distances(Lx[out_inds], Lx[in_inds])
+      dist = euclidean_distances(Lx[out_inds], Lx[in_inds], squared=True)
       i1,j1 = np.nonzero(dist < margin_radii[out_inds][:,None])
       i2,j2 = np.nonzero(dist < margin_radii[in_inds])
       i = np.hstack((i1,i2))