@@ -131,7 +131,7 @@ def subsampled_neighbors(self, X):
131131 the distance between them.
132132
133133 random_state : int or numpy.RandomState, default=None
134- A pseudo random number generator object or a seed for it if int.
134+ A pseudo random number generator object or a seed for it if int.
135135 See :term: `Glossary <random_state>`.
136136
137137 Returns
@@ -152,12 +152,13 @@ def subsampled_neighbors(self, X):
152152 # Sample edges
153153 rows = np .repeat (np .arange (n ), n_neighbors )
154154 cols = self .random_state_ .randint (self .n_train_ , size = n * n_neighbors )
155-
155+
156156 # No edges sampled
157157 if n_neighbors < 1 :
158158 return csr_matrix ((n , self .n_train_ ))
159159
160- distances = paired_distances (X [rows ], self .fit_X_ [cols ], metric = self .metric )
160+ distances = paired_distances (X [rows ], self .fit_X_ [cols ],
161+ metric = self .metric )
161162
162163 # Keep only neighbors within epsilon-neighborhood
163164 if self .eps is not None :
@@ -177,7 +178,7 @@ def subsampled_neighbors(self, X):
177178 cols [start :stop ] = cols [start :stop ][dist_order ]
178179
179180 # Sort column indices and label duplicates
180- # When consecutive elements in sorted array are equal,
181+ # When consecutive elements in sorted array are equal,
181182 # it means there is a duplicate
182183 col_order = np .argsort (cols [start :stop ], kind = 'mergesort' )
183184 cols_tmp = cols [start :stop ][col_order ]
@@ -192,7 +193,6 @@ def subsampled_neighbors(self, X):
192193
193194 neighborhood = csr_matrix ((distances , cols , indptr ),
194195 shape = (n , self .n_train_ ))
195-
196196 return neighborhood
197197
198198 def _more_tags (self ):
0 commit comments