Question

我正在尝试执行以下代码:(这是一个用Python编写的Kmeans算法的简单代码。两步程序一直持续到簇和质心的赋值不再变化。收敛有保证但是解决方案可能是局部最小值。实际上，算法运行多次并取平均值。

import numpy as np
import random
from numpy import *

points = [[1,1],[1.5,2],[3,4],[5,7],[3.5,5],[4.5,5], [3.5,4]]


def cluster(points,center):
  clusters = {}

  for x in points:

    z= min([(i[0], np.linalg.norm(x-center[i[0]]))  for i in enumerate(center)], key=lambda t:t[1])

    try:
      clusters[z].append(x)
    except KeyError:
      clusters[z]=[x]

  return clusters

def update(oldcenter,clusters):

 d=[]
 r=[]
 newcenter=[]

 for k in clusters:
  if k[0]==0: 
   d.append(clusters[(k[0],k[1])])

  else:
   r.append(clusters[(k[0],k[1])])

 c=np.mean(d, axis=0)
 u=np.mean(r,axis=0)
 newcenter.append(c)
 newcenter.append(u)

 return newcenter

def shouldStop(oldcenter,center, iterations):
    MAX_ITERATIONS=4
    if iterations > MAX_ITERATIONS: return True
    return (oldcenter == center)

def kmeans():   
  points = np.array([[1,1],[1.5,2],[3,4],[5,7],[3.5,5],[4.5,5], [3.5,4]])
  clusters={}
  iterations = 0
  oldcenter=([[],[]])   
  center= ([[1,1],[5,7]])                        

  while not shouldStop(oldcenter, center, iterations):
        # Save old centroids for convergence test. Book keeping.
        oldcenter=center
        iterations += 1
        clusters=cluster(points,center)  
        center=update(oldcenter,clusters)

  return (center,clusters)

kmeans()

但现在我卡住了。有人可以帮帮我吗？

Traceback (most recent call last):
  File "has_converged.py", line 64, in <module>
    (center,clusters)=kmeans()
  File "has_converged.py", line 55, in kmeans
    while not shouldStop(oldcenter, center, iterations):
  File "has_converged.py", line 46, in shouldStop
    return (oldcenter == center)
ValueError: The truth value of an array with more than one element is ambiguous.
 Use a.any() or a.all()

Answer 1

如错误所示，您无法在NumPy中将两个数组与==进行比较：

>>> a = np.random.randn(5)
>>> b = np.random.randn(5)
>>> a
array([-0.28636246,  0.75874234,  1.29656196,  1.19471939,  1.25924266])
>>> b
array([-0.13541816,  1.31538069,  1.29514837, -1.2661043 ,  0.07174764])
>>> a == b
array([False, False, False, False, False], dtype=bool)

==的结果是一个逐元素的布尔数组。您可以使用all方法判断此数组是否全部为真：

>>> (a == b).all()
False

那就是说，检查质心是否以这种方式改变是unreliable because of rounding。您可能希望改为使用np.allclose。

“ValueError：具有多个元素的数组的真值是不明确的”

1 个答案: