python - Matplotlib 三角测量停止处理切换坐标

Question

当我在一组点上切换 x 和 y 坐标时，出现以下奇怪的错误

  File "min_working_example.py", line 8, in <module>
    triang = tria.Triangulation(coords[:,1],coords[:,0])
  File "/usr/lib/pymodules/python2.7/matplotlib/tri/triangulation.py", line 72, in __init__
    dt = delaunay.Triangulation(self.x, self.y)
  File "/usr/lib/pymodules/python2.7/matplotlib/delaunay/triangulate.py", line 123, in __init__
    self.hull = self._compute_convex_hull()
  File "/usr/lib/pymodules/python2.7/matplotlib/delaunay/triangulate.py", line 158, in _compute_convex_hull
    hull.append(edges.pop(hull[-1]))
KeyError: 0

我在这里附上了一组要点和一个可能产生此错误的最小工作示例。这是 matplotlib 1.3 在 ubuntu 13.10 上的版本来自存储库。奇怪的是，似乎只有这个数据集有问题。

谢谢，亚布拉马尼亚

代码:

from pylab import *
import matplotlib.tri as tria

coords = loadtxt("data.txt")

fig = figure()
ax = fig.add_subplot(111)
triang = tria.Triangulation(coords[:,0],coords[:,1])
ax.triplot(triang)
savefig('a.png')
triang2 = tria.Triangulation(coords[:,1],coords[:,0])

数据


-6.500000000000004663e-01 -8.660254037844383745e-01

-6.500000000000003553e-01 -6.062177826491067512e-01
-6.500000000000003553e-01 -3.464101615137751833e-01
-6.500000000000002442e-01 -8.660254037844355990e-02
-6.500000000000001332e-01 1.732050807568880635e-01
-6.500000000000000222e-01 4.330127018922196869e-01
-6.499999999999999112e-01 6.928203230275513658e-01
-6.499999999999998002e-01 9.526279441628826561e-01
-4.250000000000004885e-01 -9.959292143521041307e-01
-4.250000000000003220e-01 -7.361215932167725073e-01
-4.250000000000002665e-01 -4.763139720814408840e-01
-4.250000000000001554e-01 -2.165063509461093161e-01
-4.250000000000000444e-01 4.330127018922230731e-02
-4.249999999999999334e-01 3.031088913245539307e-01
-4.249999999999998224e-01 5.629165124598856096e-01
-4.249999999999997669e-01 8.227241335952174550e-01
-2.000000000000003442e-01 -8.660254037844382635e-01
-2.000000000000002331e-01 -6.062177826491067512e-01
-2.000000000000001499e-01 -3.464101615137751278e-01
-2.000000000000000389e-01 -8.660254037844355990e-02
-1.999999999999999556e-01 1.732050807568881190e-01
-1.999999999999998446e-01 4.330127018922196869e-01
-1.999999999999997613e-01 6.928203230275513658e-01
 2.499999999999980016e-02 -7.361215932167725073e-01
 2.499999999999985567e-02 -4.763139720814409950e-01
 2.499999999999999445e-02 -2.165063509461093716e-01
 2.500000000000007772e-02 4.330127018922225179e-02
 2.500000000000017486e-02 3.031088913245538752e-01
  2.500000000000029976e-02 5.629165124598854986e-01
 2.499999999999998335e-01 -6.062177826491067512e-01
  2.499999999999999722e-01 -3.464101615137752388e-01
  2.500000000000001110e-01 -8.660254037844355990e-02
  2.500000000000002220e-01 1.732050807568880080e-01
  2.500000000000002776e-01 4.330127018922196314e-01
  4.749999999999999778e-01 -4.763139720814410505e-01
  4.750000000000000888e-01 -2.165063509461093993e-01
  4.750000000000001998e-01 4.330127018922216853e-02
  4.750000000000003109e-01 3.031088913245537642e-01
  7.000000000000000666e-01 -3.464101615137752388e-01
  7.000000000000001776e-01 -8.660254037844367092e-02
  7.000000000000002887e-01 1.732050807568879525e-01
  9.250000000000002665e-01 -2.165063509461093716e-01
  9.250000000000004885e-01 4.330127018922221710e-02
  1.150000000000000355e+00 -8.660254037844382358e-02

Answer 1

我可以用 matplotlib v1.3 确认这个错误(已知 matplotlib.delaunay 会受到这些问题的影响)，但现在使用更强大的库 qhull 的当前主人不能。

https://github.com/matplotlib/matplotlib/pull/2504

所以我猜 v1.4 版本很快就会解决这个问题。

在当前 master 获得的图表下方。