KNN分类模型报错：'NoneType' object has no attribute 'split'

安全阿岳

2026-7-10

问题：KNeighborsClassifier调用predict时触发AttributeError

此前使用Logistic Regression和Decision Tree Classifier均正常运行，但使用KNN分类模型时，调用predict方法出现AttributeError。

代码片段

from sklearn.neighbors import KNeighborsClassifier
KNN = KNeighborsClassifier().fit(X_train,Y_train)
train_preds5 = KNN.predict(X_train)
print("Model accuracy on train is: ", accuracy_score(Y_train, train_preds5))

报错信息

AttributeError                            Traceback (most recent call last)
Cell In[87], line 5
      3 KNN = KNeighborsClassifier().fit(X_train,Y_train)
      4 #predict on train 
----> 5 train_preds5 = KNN.predict(X_train)
      6 #accuracy on train
      7 print("Model accuracy on train is: ", accuracy_score(Y_train, train_preds5))

File ~\anaconda3\Lib\site-packages\sklearn\neighbors\_classification.py:234, in KNeighborsClassifier.predict(self, X)
    218 """Predict the class labels for the provided data.
    219 
    220 Parameters
   (...)
    229     Class labels for each data sample.
    230 """
    231 if self.weights == "uniform":
    232     # In that case, we do not need the distances to perform
    233     # the weighting so we do not compute them.
---> 234     neigh_ind = self.kneighbors(X, return_distance=False)
    235     neigh_dist = None
    236 else:

File ~\anaconda3\Lib\site-packages\sklearn\neighbors\_base.py:824, in KNeighborsMixin.kneighbors(self, X, n_neighbors, return_distance)
    817 use_pairwise_distances_reductions = (
    818     self._fit_method == "brute"
    819     and ArgKmin.is_usable_for(
    820         X if X is not None else self._fit_X, self._fit_X, self.effective_metric_
    821     )
    822 )
    823 if use_pairwise_distances_reductions:
---> 824     results = ArgKmin.compute(
    825         X=X,
    826         Y=self._fit_X,
    827         k=n_neighbors,
    828         metric=self.effective_metric_,
    829         metric_kwargs=self.effective_metric_params_,
    830         strategy="auto",
    831         return_distance=return_distance,
    832     )
    834 elif (
    835     self._fit_method == "brute" and self.metric == "precomputed" and issparse(X)
    836 ):
    837     results = _kneighbors_from_graph(
    838         X, n_neighbors=n_neighbors, return_distance=return_distance
    839     )

File ~\anaconda3\Lib\site-packages\sklearn\metrics\_pairwise_distances_reduction\_dispatcher.py:277, in ArgKmin.compute(cls, X, Y, k, metric, chunk_size, metric_kwargs, strategy, return_distance)
    196 """Compute the argkmin reduction.
    197 
    198 Parameters
   (...)
    274 returns.
    275 """
    276 if X.dtype == Y.dtype == np.float64:
---> 277     return ArgKmin64.compute(
    278         X=X,
    279         Y=Y,
    280         k=k,
    281         metric=metric,
    282         chunk_size=chunk_size,
    283         metric_kwargs=metric_kwargs,
    284         strategy=strategy,
    285         return_distance=return_distance,
    286     )
    288 if X.dtype == Y.dtype == np.float32:
    289     return ArgKmin32.compute(
    290         X=X,
    291         Y=Y,
   (...)
    297         return_distance=return_distance,
    298     )

File sklearn\metrics\_pairwise_distances_reduction\_argkmin.pyx:95, in sklearn.metrics._pairwise_distances_reduction._argkmin.ArgKmin64.compute()

File ~\anaconda3\Lib\site-packages\sklearn\utils\fixes.py:139, in threadpool_limits(limits, user_api)
    137     return controller.limit(limits=limits, user_api=user_api)
    138 else:
---> 139     return threadpoolctl.threadpool_limits(limits=limits, user_api=user_api)

File ~\anaconda3\Lib\site-packages\threadpoolctl.py:171, in threadpool_limits.__init__(self, limits, user_api)
    167 def __init__(self, limits=None, user_api=None):
    168     self._limits, self._user_api, self._prefixes = \
    169         self._check_params(limits, user_api)
---> 171     self._original_info = self._set_threadpool_limits()

File ~\anaconda3\Lib\site-packages\threadpoolctl.py:268, in threadpool_limits._set_threadpool_limits(self)
    265 if self._limits is None:
    266     return None
---> 268 modules = _ThreadpoolInfo(prefixes=self._prefixes,
    269                           user_api=self._user_api)
    270 for module in modules:
    271     # self._limits is a dict {key: num_threads} where key is either
    272     # a prefix or a user_api. If a module matches both, the limit
    273     # corresponding to the prefix is chosed.
    274     if module.prefix in self._limits:

File ~\anaconda3\Lib\site-packages\threadpoolctl.py:340, in _ThreadpoolInfo.__init__(self, user_api, prefixes, modules)
    337     self.user_api = [] if user_api is None else user_api
    339     self.modules = []
---> 340     self._load_modules()
    341     self._warn_if_incompatible_openmp()
    342 else:

File ~\anaconda3\Lib\site-packages\threadpoolctl.py:373, in _ThreadpoolInfo._load_modules(self)
    371     self._find_modules_with_dyld()
    372 elif sys.platform == "win32":
---> 373     self._find_modules_with_enum_process_module_ex()
    374 else:
    375     self._find_modules_with_dl_iterate_phdr()

File ~\anaconda3\Lib\site-packages\threadpoolctl.py:485, in _ThreadpoolInfo._find_modules_with_enum_process_module_ex(self)
    482         filepath = buf.value
    484         # Store the module if it is supported and selected
---> 485         self._make_module_from_path(filepath)
    486 finally:
    487     kernel_32.CloseHandle(h_process)

File ~\anaconda3\Lib\site-packages\threadpoolctl.py:515, in _ThreadpoolInfo._make_module_from_path(self, filepath)
    513 if prefix in self.prefixes or user_api in self.user_api:
    514     module_class = globals()[module_class]
---> 515     module = module_class(filepath, prefix, user_api, internal_api)
    516     self.modules.append(module)

File ~\anaconda3\Lib\site-packages\threadpoolctl.py:606, in _Module.__init__(self, filepath, prefix, user_api, internal_api)
    604 self.internal_api = internal_api
    605 self._dynlib = ctypes.CDLL(filepath, mode=_RTLD_NOLOAD)
---> 606 self.version = self.get_version()
    607 self.num_threads = self.get_num_threads()
    608 self._get_extra_info()

File ~\anaconda3\Lib\site-packages\threadpoolctl.py:646, in _OpenBLASModule.get_version(self)
    643 get_config = getattr(self._dynlib, "openblas_get_config",
    644                      lambda: None)
    645 get_config.restype = ctypes.c_char_p
---> 646 config = get_config().split()
    647 if config[0] == b"OpenBLAS":
    648     return config[1].decode("utf-8")

AttributeError: 'NoneType' object has no attribute 'split'

期望输出训练集准确率，但触发上述属性错误。

解决方案

这个错误本质是threadpoolctl库在读取OpenBLAS版本时出现问题，和KNN模型本身无关，以下是几种可行的修复方法：

临时禁用线程池限制：在代码开头添加以下代码，跳过threadpoolctl的线程限制逻辑：
```
import os
os.environ["OMP_NUM_THREADS"] = "1"
os.environ["OPENBLAS_NUM_THREADS"] = "1"
```
降级/升级threadpoolctl库：
卸载当前版本，安装指定版本：
```
pip uninstall threadpoolctl -y
pip install threadpoolctl==3.1.0
```
3.1.0版本修复了部分Windows环境下OpenBLAS版本读取的bug。

指定KNN的计算方法为brute并禁用距离优化：
初始化KNN时显式设置algorithm='brute'，并关闭pairwise距离优化：

from sklearn.neighbors import KNeighborsClassifier
from sklearn.utils._openmp_helpers import _openmp_effective_n_threads

# 临时设置线程数
_openmp_effective_n_threads.cache_clear()
KNN = KNeighborsClassifier(algorithm='brute').fit(X_train,Y_train)
train_preds5 = KNN.predict(X_train)
print("Model accuracy on train is: ", accuracy_score(Y_train, train_preds5))

更新Anaconda环境：
如果使用Anaconda，更新整个环境的依赖包，修复OpenBLAS和threadpoolctl的兼容性问题：
```
conda update --all
```

内容的提问来源于stack exchange，提问作者Karthik Kumar P