Merge branch 'master' of github.com:scikit-learn/scikit-learn

Author: agramfort

scikits/learn/neighbors.py

@@ -120,17 +120,17 @@ class from an array representing our data set and ask who's
         >>> neigh = NeighborsClassifier(n_neighbors=1)
         >>> neigh.fit(samples, labels)
         NeighborsClassifier(n_neighbors=1, window_size=1, algorithm='auto')
-        >>> print neigh.kneighbors([1., 1., 1.])
-        (array([[ 0.5]]), array([[2]]))
+        >>> print neigh.kneighbors([1., 1., 1.]) # doctest: +ELLIPSIS
+        (array([[ 0.5]]), array([[2]]...))
 
         As you can see, it returns [[0.5]], and [[2]], which means that the
         element is at distance 0.5 and is the third element of samples
         (indexes start at 0). You can also query for multiple points:
 
         >>> X = [[0., 1., 0.], [1., 0., 1.]]
-        >>> neigh.kneighbors(X, return_distance=False)
+        >>> neigh.kneighbors(X, return_distance=False) # doctest: +ELLIPSIS
         array([[1],
-               [2]])
+               [2]]...)
 
         """
         self._set_params(**params)

scikits/learn/src/ball_tree.pyx

@@ -1,3 +1,8 @@
+""" Cython bindings for the C++ BallTree code.
+"""
+# Author: Thouis Jones
+# License: BSD
+
 from libcpp.vector cimport vector
 
 import numpy as np
@@ -12,25 +17,30 @@ cdef extern from "BallTreePoint.h":
 
 ctypedef Point *Point_p
 
+
 cdef extern from "BallTree.h":
     cdef cppclass cBallTree "BallTree<Point>":
         cBallTree(vector[Point_p] *, int)
         double query(Point *, vector[long int] &) except +
     double Euclidean_Dist(Point *, Point *) except +
 
+
 cdef Point *make_point(vals):
     pt = new Point(vals.size)
     for idx, v in enumerate(vals.flat):
         SET(pt, idx, v)
     return pt
 
+
+################################################################################
 # Cython wrapper
 cdef class BallTree:
     cdef cBallTree *bt_ptr
     cdef vector[Point_p] *ptdata
     cdef int num_points
     cdef int num_dims
     cdef public object data
+
     def __cinit__(self, arr, leafsize=20):
         # copy points into ptdata
         num_points, num_dims = self.num_points, self.num_dims = arr.shape
@@ -39,6 +49,7 @@ cdef class BallTree:
             self.ptdata.push_back(make_point(arr[i, :]))
         self.bt_ptr = new cBallTree(self.ptdata, leafsize)
         self.data = arr.copy()
+
     def __dealloc__(self):
         cdef Point *temp
         for idx in range(self.ptdata.size()):
@@ -47,6 +58,7 @@ cdef class BallTree:
             del temp
         del self.ptdata
         del self.bt_ptr
+
     def query(self, x, k=1, return_distance=True):
         x = np.atleast_2d(x)
         assert x.shape[-1] == self.num_dims