import numpy as np
from sklearn import cluster

locations = np.random.random((250000, 2)) * 5
kmean = cluster.KMeans(n_clusters=6000, n_init=10, max_iter=150,
                       verbose=True, n_jobs=20, copy_x=False,
                       precompute_distances=False)
kmean.fit(locations)
print (kmean.cluster_centers_)

Iteration 35, inertia 156.384475435
center shift 7.768886e-03 within tolerance 2.084699e-04
Traceback (most recent call last):
  File "test_kmeans.py", line 8, in <module>
    kmean.fit(locations)
  File "/mnt/home.dokt/borovji3/vEnv/local/lib/python2.7/site-packages/sklearn/cluster/k_means_.py", line 889, in fit
    return_n_iter=True)
  File "/mnt/home.dokt/borovji3/vEnv/local/lib/python2.7/site-packages/sklearn/cluster/k_means_.py", line 362, in k_means
    for seed in seeds)
  File "/mnt/home.dokt/borovji3/vEnv/local/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.py", line 768, in __call__  
    self.retrieve()
  File "/mnt/home.dokt/borovji3/vEnv/local/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.py", line 719, in retrieve  
    raise exception
sklearn.externals.joblib.my_exceptions.JoblibMemoryError: JoblibMemoryError
___________________________________________________________________________
Multiprocessing exception:
...........................................................................
/mnt/datagrid/personal/borovec/Dropbox/Workspace/Uplus_fraud-monitoring/test_kmeans.py in <module>()
      3
      4 locations = np.random.random((250000, 2)) * 5
      5 kmean = cluster.KMeans(n_clusters=6000, n_init=10, max_iter=150,
      6                        verbose=True, n_jobs=20, copy_x=False,
      7                        precompute_distances=False)
----> 8 kmean.fit(locations)
      9 print (kmean.cluster_centers_)
     10
     11
     12

...........................................................................
/mnt/home.dokt/borovji3/vEnv/local/lib/python2.7/site-packages/sklearn/cluster/k_means_.py in fit(self=KMeans(algorithm='auto', copy_x=False, init='k-m...
    random_state=None, tol=0.0001, verbose=True), X=array([[-1.86344999,  0.05621132],
       [ 0.88...-1.20243728],
       [ 0.97877704,  1.24561138]]), y=None)

    884                 X, n_clusters=self.n_clusters, init=self.init,
    885                 n_init=self.n_init, max_iter=self.max_iter, verbose=self.verbose,
    886                 precompute_distances=self.precompute_distances,
    887                 tol=self.tol, random_state=random_state, copy_x=self.copy_x,
    888                 n_jobs=self.n_jobs, algorithm=self.algorithm,
--> 889                 return_n_iter=True)
    890         return self
    891
    892     def fit_predict(self, X, y=None):
    893         """Compute cluster centers and predict cluster index for each sample.

...........................................................................
/mnt/home.dokt/borovji3/vEnv/local/lib/python2.7/site-packages/sklearn/cluster/k_means_.py in k_means(X=array([[-1.86344999,  0.05621132],
       [ 0.88...-1.20243728],
       [ 0.97877704,  1.24561138]]), n_clusters=6000, init='k-means++', precompute_distances=False, n_init=10, max_iter=150, verbose=True, tol=0.00020846993669604294, random_state=<mtrand.RandomState object>, copy_x=False, n_jobs=20, algorithm='elkan', return_n_iter=True)
    357                                    verbose=verbose, tol=tol,
    358                                    precompute_distances=precompute_distances,
    359                                    x_squared_norms=x_squared_norms,
    360                                    # Change seed to ensure variety
    361                                    random_state=seed)
--> 362             for seed in seeds)
        seeds = array([ 968587040,  226617041, 2063896048,  6552...  393005117,  134324550,   14152465, 2054736812])
    363         # Get results with the lowest inertia
    364         labels, inertia, centers, n_iters = zip(*results)
    365         best = np.argmin(inertia)
    366         best_labels = labels[best]

...........................................................................
/mnt/home.dokt/borovji3/vEnv/local/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.py in __call__(self=Parallel(n_jobs=20), iterable=<generator object <genexpr>>)
    763             if pre_dispatch == "all" or n_jobs == 1:
    764                 # The iterable was consumed all at once by the above for loop.
    765                 # No need to wait for async callbacks to trigger to
    766                 # consumption.
    767                 self._iterating = False
--> 768             self.retrieve()
        self.retrieve = <bound method Parallel.retrieve of Parallel(n_jobs=20)>
    769             # Make sure that we get a last message telling us we are done
    770             elapsed_time = time.time() - self._start_time
    771             self._print('Done %3i out of %3i | elapsed: %s finished',
    772                         (len(self._output), len(self._output),

---------------------------------------------------------------------------
Sub-process traceback:
---------------------------------------------------------------------------
MemoryError                                        Tue Oct 17 16:11:14 2017
PID: 18062            Python 2.7.9: /mnt/home.dokt/borovji3/vEnv/bin/python
...........................................................................
/mnt/home.dokt/borovji3/vEnv/local/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.py in __call__(self=<sklearn.externals.joblib.parallel.BatchedCalls object>)
    126     def __init__(self, iterator_slice):
    127         self.items = list(iterator_slice)
    128         self._size = len(self.items)
    129
    130     def __call__(self):
--> 131         return [func(*args, **kwargs) for func, args, kwargs in self.items]
        func = <function _kmeans_single_elkan>
        args = (memmap([[-1.86344999,  0.05621132],
        [ 0....1.20243728],
        [ 0.97877704,  1.24561138]]), 6000)
        kwargs = {'init': 'k-means++', 'max_iter': 150, 'precompute_distances': False, 'random_state': 134324550, 'tol': 0.00020846993669604294, 'verbose': True, 'x_squared_norms': memmap([ 3.47560557,  1.66662896,  0.19072331, ...,  1.87283488,
         3.21604332,  2.50955219])}
        self.items = [(<function _kmeans_single_elkan>, (memmap([[-1.86344999,  0.05621132],
        [ 0....1.20243728],
        [ 0.97877704,  1.24561138]]), 6000), {'init': 'k-means++', 'max_iter': 150, 'precompute_distances': False, 'random_state': 134324550, 'tol': 0.00020846993669604294, 'verbose': True, 'x_squared_norms': memmap([ 3.47560557,  1.66662896,  0.19072331, ...,  1.87283488,
         3.21604332,  2.50955219])})]
    132
    133     def __len__(self):
    134         return self._size
    135

...........................................................................
/mnt/home.dokt/borovji3/vEnv/local/lib/python2.7/site-packages/sklearn/cluster/k_means_.py in _kmeans_single_elkan(X=array([[-1.86344999,  0.05621132],
       [ 0.88...-1.20243728],
       [ 0.97877704,  1.24561138]]), n_clusters=6000, max_iter=150, init='k-means++', verbose=True, x_squared_norms=memmap([ 3.47560557,  1.66662896,  0.19072331, ...,  1.87283488,
         3.21604332,  2.50955219]), random_state=<mtrand.RandomState object>, tol=0.00020846993669604294, precompute_distances=False)
    394                               x_squared_norms=x_squared_norms)
    395     centers = np.ascontiguousarray(centers)
    396     if verbose:
    397         print('Initialization complete')
    398     centers, labels, n_iter = k_means_elkan(X, n_clusters, centers, tol=tol,
--> 399                                             max_iter=max_iter, verbose=verbose)
        max_iter = 150
        verbose = True
    400     inertia = np.sum((X - centers[labels]) ** 2, dtype=np.float64)
    401     return labels, inertia, centers, n_iter
    402
    403

...........................................................................
/mnt/home.dokt/borovji3/vEnv/local/lib/python2.7/site-packages/sklearn/cluster/_k_means_elkan.so in sklearn.cluster._k_means_elkan.k_means_elkan (sklearn/cluster/_k_means_elkan.c:6961)()
    225
    226
    227
    228
    229
--> 230
    231
    232
    233
    234

MemoryError:
___________________________________________________________________________