sklearn KMeans聚类报错

最新推荐文章于 2026-03-23 00:20:08 发布

原创最新推荐文章于 2026-03-23 00:20:08 发布 · 1.4k 阅读

本内容遵循CC 4.0 BY-SA版权协议

在尝试使用sklearn的MiniBatchKMeans进行聚类时，遇到了一个与threadpoolctl模块相关的错误。该错误源于NoneType对象没有split属性，这通常意味着threadpoolctl库可能未正确安装或版本不兼容。解决方案是通过pip更新threadpoolctl库。

在调用sklearn的聚类方法MiniBatchKMeans时

from sklearn.cluster import KMeans, MiniBatchKMeans

报错：

  File "cluster/train_cluster.py", line 30, in train_cluster
    kmeans = MiniBatchKMeans(n_clusters=n_clusters,verbose=verbose, batch_size=4096, max_iter=80).fit(features)
  File "E:\tools\Anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py", line 1694, in fit
    self._check_mkl_vcomp(X, self.batch_size)
  File "E:\tools\Anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py", line 874, in _check_mkl_vcomp
    modules = threadpool_info()
  File "E:\tools\Anaconda3\lib\site-packages\threadpoolctl.py", line 124, in threadpool_info
    return _ThreadpoolInfo(user_api=_ALL_USER_APIS).todicts()
  File "E:\tools\Anaconda3\lib\site-packages\threadpoolctl.py", line 340, in __init__
    self._load_modules()
    self._find_modules_with_enum_process_module_ex()
  File "E:\tools\Anaconda3\lib\site-packages\threadpoolctl.py", line 485, in _find_modules_with_enum_process_module_ex
    self._make_module_from_path(filepath)
  File "E:\tools\Anaconda3\lib\site-packages\threadpoolctl.py", line 515, in _make_module_from_path
    module = module_class(filepath, prefix, user_api, internal_api)
  File "E:\tools\Anaconda3\lib\site-packages\threadpoolctl.py", line 606, in __init__
    self.version = self.get_version()
  File "E:\tools\Anaconda3\lib\site-packages\threadpoolctl.py", line 646, in get_version
    config = get_config().split()
AttributeError: 'NoneType' object has no attribute 'split'