压缩距离矩阵到全距离矩阵
由pdist返回的压缩距离矩阵可以使用以下公式转换为完整距离矩阵scipy.spatial.distance.squareform
:
>>> import numpy as np
>>> from scipy.spatial.distance import pdist, squareform
>>> points = np.array([[0,1],[1,1],[3,5], [15, 5]])
>>> dist_condensed = pdist(points)
>>> dist_condensed
array([ 1. , 5. , 15.5241747 , 4.47213595,
14.56021978, 12. ])
使用squareform
转换到全矩阵:
>>> dist = squareform(dist_condensed)
array([[ 0. , 1. , 5. , 15.5241747 ],
[ 1. , 0. , 4.47213595, 14.56021978],
[ 5. , 4.47213595, 0. , 12. ],
[ 15.5241747 , 14.56021978, 12. , 0. ]])
点i,j之间的距离存储在dist [i,j]中:
>>> dist[2, 0]
5.0
>>> np.linalg.norm(points[2] - points[0])
5.0
简明指数
可以将用于访问方矩阵元素的索引转换为压缩矩阵中的索引:
def square_to_condensed(i, j, n):
assert i != j, "no diagonal elements in condensed matrix"
if i < j:
i, j = j, i
return n*j - j*(j+1)//2 + i - 1 - j
例:
>>> square_to_condensed(1, 2, len(points))
3
>>> dist_condensed[3]
4.4721359549995796
>>> dist[1,2]
4.4721359549995796
缩略索引
另外,没有sqaureform的另一个方向是可能的,这在运行时和内存消耗方面更好:
import math
def calc_row_idx(k, n):
return int(math.ceil((1/2.) * (- (-8*k + 4 *n**2 -4*n - 7)**0.5 + 2*n -1) - 1))
def elem_in_i_rows(i, n):
return i * (n - 1 - i) + (i*(i + 1))//2
def calc_col_idx(k, i, n):
return int(n - elem_in_i_rows(i + 1, n) + k)
def condensed_to_square(k, n):
i = calc_row_idx(k, n)
j = calc_col_idx(k, i, n)
return i, j
例:
>>> condensed_to_square(3, 4)
(1.0, 2.0)
使用Squareform进行运行时比较
>>> import numpy as np
>>> from scipy.spatial.distance import pdist, squareform
>>> points = np.random.random((10**4,3))
>>> %timeit dist_condensed = pdist(points)
1 loops, best of 3: 555 ms per loop
事实证明,创建方形形式确实很慢:
>>> dist_condensed = pdist(points)
>>> %timeit dist = squareform(dist_condensed)
1 loops, best of 3: 2.25 s per loop
如果我们要搜索具有最大距离的两个点,则在全矩阵中搜索为O(n)而在压缩形式中仅搜索O(n / 2)也就不足为奇了:
>>> dist = squareform(dist_condensed)
>>> %timeit dist_condensed.argmax()
10 loops, best of 3: 45.2 ms per loop
>>> %timeit dist.argmax()
10 loops, best of 3: 93.3 ms per loop
在两种情况下,几乎都不需要花费两点就可以得到两点的理想值,但是计算浓缩指数当然会有些开销:
>>> idx_flat = dist.argmax()
>>> idx_condensed = dist.argmax()
>>> %timeit list(np.unravel_index(idx_flat, dist.shape))
100000 loops, best of 3: 2.28 µs per loop
>>> %timeit condensed_to_square(idx_condensed, len(points))
100000 loops, best of 3: 14.7 µs per loop