Windows7下运行KMeans遇‘无法检测物理核心数’问题求助

问题 #

在64位Windows 7系统上运行Python 3.8.10，执行以下sklearn KMeans示例代码：

from sklearn.cluster import KMeans
import numpy as np

X = np.array([[1, 2], [1, 4], [1, 0],
              [10, 2], [10, 4], [10, 0]])

kmeans = KMeans(n_clusters=2, random_state=0, n_init="auto").fit(X)
kmeans.labels_
kmeans.predict([[0, 0], [12, 3]])
kmeans.cluster_centers_

出现如下警告且代码无法运行：

Warning (from warnings module):
File "C:\Users\Maria\AppData\Local\Programs\Python\Python38\lib\site-packages\joblib\externals\loky\backend\context.py", line 136
warnings.warn(
UserWarning: Could not find the number of physical cores for the following reason:
[WinError 2] El sistema no puede encontrar el archivo especificado
Returning the number of logical cores instead. You can silence this warning by setting LOKY_MAX_CPU_COUNT to the number of cores you want to use.
File "C:\Users\Maria\AppData\Local\Programs\Python\Python38\lib\site-packages\joblib\externals\loky\backend\context.py", line 257, in _count_physical_cores
cpu_info = subprocess.run(
File "C:\Users\Maria\AppData\Local\Programs\Python\Python38\lib\subprocess.py", line 493, in run
with Popen(*popenargs, **kwargs) as process:
File "C:\Users\Maria\AppData\Local\Programs\Python\Python38\lib\subprocess.py", line 858, in init
self._execute_child(args, executable, preexec_fn, close_fds,
File "C:\Users\Maria\AppData\Local\Programs\Python\Python38\lib\subprocess.py", line 1311, in _execute_child
hp, ht, pid, tid = _winapi.CreateProcess(executable, args,

已尝试将LOKY_MAX_CPU_COUNT设置为2（PC核心数），但问题仍未解决，求解决思路。

解决思路 #

• 确认环境变量设置对不对
  得保证LOKY_MAX_CPU_COUNT是系统级或者当前Python环境的环境变量，不能只在代码里临时瞎设。试试这么验证：

  1. 右键「计算机」→「属性」→「高级系统设置」→「环境变量」，在系统变量里加LOKY_MAX_CPU_COUNT，值设为2，重启Python或者IDE再跑代码。
  2. 如果想临时设置，得在代码最开头就加：

     import os
     os.environ["LOKY_MAX_CPU_COUNT"] = "2"
     

     记住要放在导入sklearn和joblib之前。

• 降级loky版本
  新版本loky在Win7上可能有兼容问题，试试降到2.5.1版本：

  pip install loky==2.5.1
  

• 让KMeans单线程跑
  初始化KMeans的时候指定n_jobs=1，跳过loky的核心检测逻辑：

  kmeans = KMeans(n_clusters=2, random_state=0, n_init="auto", n_jobs=1).fit(X)
  

• 检查系统文件有没有损坏
  报错里的WinError 2是说找不到指定文件，大概率是系统里的wmic.exe丢了或者坏了（loky靠它查核心数）。可以从正常的Win7系统里复制wmic.exe到C:\Windows\System32，或者跑系统修复命令：

  sfc /scannow
  

内容的提问来源于stack exchange，提问作者abeh