AttributeError: ‘NoneType‘ object has no attribute ‘split‘问题解决方法

1. 问题描述

在用KMeans算法训练数据的时候，报了以下错误：

说明，df_1hs是一个普通的DataFrame格式数据，

详细报错

runfile('E:/09-code/02-wind_profile/wind_profile_cluster.py', wdir='E:/09-code/02-wind_profile')
2022-06-24 09:42:43,296 - INFO       - wind_profile_cluster.py - <module>:73 - start calculate SSE.
Traceback (most recent call last):
  File "D:\Anaconda\lib\site-packages\IPython\core\interactiveshell.py", line 3418, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-2-24f780d27a62>", line 1, in <module>
    runfile('E:/09-code/02-wind_profile/wind_profile_cluster.py', wdir='E:/09-code/02-wind_profile')
  File "D:\pycharm\PyCharm Community Edition 2020.2\plugins\python-ce\helpers\pydev\_pydev_bundle\pydev_umd.py", line 197, in runfile
    pydev_imports.execfile(filename, global_vars, local_vars)  # execute the script
  File "D:\pycharm\PyCharm Community Edition 2020.2\plugins\python-ce\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "E:/09-code/02-wind_profile/wind_profile_cluster.py", line 77, in <module>
    kmModel.fit(df_1h3)
  File "D:\Anaconda\lib\site-packages\sklearn\cluster\_kmeans.py", line 1068, in fit
    labels, inertia, centers, n_iter_ = kmeans_single(
  File "D:\Anaconda\lib\site-packages\sklearn\cluster\_kmeans.py", line 568, in _kmeans_single_lloyd
    with threadpool_limits(limits=1, user_api="blas"):
  File "D:\Anaconda\lib\site-packages\threadpoolctl.py", line 171, in __init__
    self._original_info = self._set_threadpool_limits()
  File "D:\Anaconda\lib\site-packages\threadpoolctl.py", line 268, in _set_threadpool_limits
    modules = _ThreadpoolInfo(prefixes=self._prefixes,
  File "D:\Anaconda\lib\site-packages\threadpoolctl.py", line 340, in __init__
    self._load_modules()
  File "D:\Anaconda\lib\site-packages\threadpoolctl.py", line 373, in _load_modules
    self._find_modules_with_enum_process_module_ex()
  File "D:\Anaconda\lib\site-packages\threadpoolctl.py", line 485, in _find_modules_with_enum_process_module_ex
    self._make_module_from_path(filepath)
  File "D:\Anaconda\lib\site-packages\threadpoolctl.py", line 515, in _make_module_from_path
    module = module_class(filepath, prefix, user_api, internal_api)
  File "D:\Anaconda\lib\site-packages\threadpoolctl.py", line 606, in __init__
    self.version = self.get_version()
  File "D:\Anaconda\lib\site-packages\threadpoolctl.py", line 646, in get_version
    config = get_config().split()
AttributeError: 'NoneType' object has no attribute 'split'

2. 解决途径

• 有人说加上 data = data.encode()，我尝试加上，报错：AttributeError: ‘DataFrame’ object has no attribute ‘encode’ ，然而我遇到的问题显然和他们不完全一样，尝试之后无果而终。

3. 问题解决

• 将 KMeans 的 n_clusters=1 时，报错。

>>> model = KMeans(n_clusters=1)
>>> model.fit(df_1h3)

Traceback (most recent call last):
  File "D:\Anaconda\lib\site-packages\IPython\core\interactiveshell.py", line 3418, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-13-88f018a4fbd5>", line 1, in <module>
    model.fit(df_1h3)
……
  File "D:\Anaconda\lib\site-packages\threadpoolctl.py", line 606, in __init__
    self.version = self.get_version()
  File "D:\Anaconda\lib\site-packages\threadpoolctl.py", line 646, in get_version
    config = get_config().split()
AttributeError: 'NoneType' object has no attribute 'split'

• 将 n_cluster=3 时，没有报错。

>>> model = KMeans(n_clusters=3)
>>> model.fit(df_1h3)
Out[7]: KMeans(n_clusters=3)
>>> model.labels_
Out[8]: array([1, 2, 1, ..., 0, 0, 0])

说明，新版 KMeans算法的 n_cluster必须是大于 1 的，试想，如果n_cluster=1，即聚类结果为1，那么失去了聚类的意义。

4. 其它方法

说明：本方法只适用于部分情况，若尝试后无果，可以试试将numpy、sklearn更换版本

>>> pip install numpy==1.22.4
>>> pip install sklearn==1.1.1

参考链接
[1] https://blog.csdn.net/file_data/article/details/99640009 ;
[2] https://www.cnblogs.com/shijieli/p/10791247.html ；