I don't know what is wrong but suddenly KMeans
from sklearn
is not working anymore and I don't know what I am doing wrong. Has anyone encountered this problem yet or knows how I can fix it?
from sklearn.cluster import KMeans
kmeanModel = KMeans(n_clusters=k, random_state=0)
kmeanModel.fit(allLocations)
allLocations
looks like this:
array([[12.40236 , 51.38086 ],
[12.40999 , 51.38494 ],
[12.40599 , 51.37284 ],
[12.28692 , 51.32039 ],
[12.41349 , 51.34443 ], ...])
and allLocations.dtype
gives dtype('float64')
.
The scikit-learn version is 1.0.2 and the NumPy version is 1.22.2 and I am using Jupyter Notebook.
The Error says:
'NoneType' object has no attribute 'split'
The whole Error looks like this:
AttributeError Traceback (most recent call last)
<ipython-input-30-db8e8220c8b9> in <module>
12 for k in K:
13 kmeanModel = KMeans(n_clusters=k, random_state=0)
---> 14 kmeanModel.fit(allLocations)
15 distortions.append(kmeanModel.inertia_)
16 #Plotting the distortions
~\anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py in fit(self, X, y, sample_weight)
1169 if self._algorithm == "full":
1170 kmeans_single = _kmeans_single_lloyd
-> 1171 self._check_mkl_vcomp(X, X.shape[0])
1172 else:
1173 kmeans_single = _kmeans_single_elkan
~\anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py in _check_mkl_vcomp(self, X, n_samples)
1026 active_threads = int(np.ceil(n_samples / CHUNK_SIZE))
1027 if active_threads < self._n_threads:
-> 1028 modules = threadpool_info()
1029 has_vcomp = "vcomp" in [module["prefix"] for module in modules]
1030 has_mkl = ("mkl", "intel") in [
~\anaconda3\lib\site-packages\sklearn\utils\fixes.py in threadpool_info()
323 return controller.info()
324 else:
--> 325 return threadpoolctl.threadpool_info()
326
327
~\anaconda3\lib\site-packages\threadpoolctl.py in threadpool_info()
122 In addition, each module may contain internal_api specific entries.
123 """
--> 124 return _ThreadpoolInfo(user_api=_ALL_USER_APIS).todicts()
125
126
~\anaconda3\lib\site-packages\threadpoolctl.py in __init__(self, user_api, prefixes, modules)
338
339 self.modules = []
--> 340 self._load_modules()
341 self._warn_if_incompatible_openmp()
342 else:
~\anaconda3\lib\site-packages\threadpoolctl.py in _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()
~\anaconda3\lib\site-packages\threadpoolctl.py in _find_modules_with_enum_process_module_ex(self)
483
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)
~\anaconda3\lib\site-packages\threadpoolctl.py in _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)
517
~\anaconda3\lib\site-packages\threadpoolctl.py in __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()
~\anaconda3\lib\site-packages\threadpoolctl.py in get_version(self)
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'
CodePudding user response:
you should set test and train and import train and test split
CodePudding user response:
I started getting the same error recently. It might have had something to do with a macOS upgrade from Sierra to Catalina, but I found that it was having an issue calculating kMeans when n_clusters = 1. In the following code, I changed my range to be 2:10 instead of 1:10, and it started working.
K = range(2,10)
for k in K:
kmeanModel = KMeans(n_clusters=k)
kmeanModel.fit(data)
distortions.append(kmeanModel.inertia_)