0

我接受，我是python的新手。

我从https://sds-platform-private.s3-us-east-2.amazonaws.com/uploads/P14-Part3-Classification.zipdataset = pd.read_csv('Friday-WorkingHours-Afternoon-DDos.pcap_ISCX.csv')获得了 KNN 算法代码 我修改了 指向我的 CICIDS 链接 的数据集行 IDS 2017 数据集。

我使用 jupyter notebook 来运行代码。

在执行代码片段时：

X_set, y_set = X_train, y_train
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
             alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
                c = ListedColormap(('red', 'green'))(i), label = j)
plt.title('K-NN (Training set)')
plt.xlabel('Xaxis')
plt.ylabel('Yaxis')
plt.legend()
plt.show()

I get this error:

---------------------------------------------------------------------------
MemoryError                               Traceback (most recent call last)
<ipython-input-8-db5b0d75197c> in <module>
      3 X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
      4                      np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
----> 5 plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
      6              alpha = 0.75, cmap = ListedColormap(('red', 'green')))
      7 plt.xlim(X1.min(), X1.max())

~\anaconda3\lib\site-packages\sklearn\neighbors\_classification.py in predict(self, X)
    173         X = check_array(X, accept_sparse='csr')
    174 
--> 175         neigh_dist, neigh_ind = self.kneighbors(X)
    176         classes_ = self.classes_
    177         _y = self._y

~\anaconda3\lib\site-packages\sklearn\neighbors\_base.py in kneighbors(self, X, n_neighbors, return_distance)
    660                 delayed_query = delayed(_tree_query_parallel_helper)
    661                 parallel_kwargs = {"prefer": "threads"}
--> 662             chunked_results = Parallel(n_jobs, **parallel_kwargs)(
    663                 delayed_query(
    664                     self._tree, X[s], n_neighbors, return_distance)

~\anaconda3\lib\site-packages\joblib\parallel.py in __call__(self, iterable)
   1046             # remaining jobs.
   1047             self._iterating = False
-> 1048             if self.dispatch_one_batch(iterator):
   1049                 self._iterating = self._original_iterator is not None
   1050 

~\anaconda3\lib\site-packages\joblib\parallel.py in dispatch_one_batch(self, iterator)
    864                 return False
    865             else:
--> 866                 self._dispatch(tasks)
    867                 return True
    868 

~\anaconda3\lib\site-packages\joblib\parallel.py in _dispatch(self, batch)
    782         with self._lock:
    783             job_idx = len(self._jobs)
--> 784             job = self._backend.apply_async(batch, callback=cb)
    785             # A job can complete so quickly than its callback is
    786             # called before we get here, causing self._jobs to

~\anaconda3\lib\site-packages\joblib\_parallel_backends.py in apply_async(self, func, callback)
    206     def apply_async(self, func, callback=None):
    207         """Schedule a func to be run"""
--> 208         result = ImmediateResult(func)
    209         if callback:
    210             callback(result)

~\anaconda3\lib\site-packages\joblib\_parallel_backends.py in __init__(self, batch)
    570         # Don't delay the application, to avoid keeping the input
    571         # arguments in memory
--> 572         self.results = batch()
    573 
    574     def get(self):

~\anaconda3\lib\site-packages\joblib\parallel.py in __call__(self)
    260         # change the default number of processes to -1
    261         with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262             return [func(*args, **kwargs)
    263                     for func, args, kwargs in self.items]
    264 

~\anaconda3\lib\site-packages\joblib\parallel.py in <listcomp>(.0)
    260         # change the default number of processes to -1
    261         with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262             return [func(*args, **kwargs)
    263                     for func, args, kwargs in self.items]
    264 

~\anaconda3\lib\site-packages\sklearn\neighbors\_base.py in _tree_query_parallel_helper(tree, *args, **kwargs)
    490     under PyPy.
    491     """
--> 492     return tree.query(*args, **kwargs)
    493 
    494 

sklearn\neighbors\_binary_tree.pxi in sklearn.neighbors._kd_tree.BinaryTree.query()

~\anaconda3\lib\site-packages\sklearn\utils\validation.py in inner_f(*args, **kwargs)
     70                           FutureWarning)
     71         kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 72         return f(**kwargs)
     73     return inner_f
     74 

~\anaconda3\lib\site-packages\sklearn\utils\validation.py in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator)
    596                     array = array.astype(dtype, casting="unsafe", copy=False)
    597                 else:
--> 598                     array = np.asarray(array, order=order, dtype=dtype)
    599             except ComplexWarning:
    600                 raise ValueError("Complex data not supported\n"

~\anaconda3\lib\site-packages\numpy\core\_asarray.py in asarray(a, dtype, order)
     81 
     82     """
---> 83     return array(a, dtype, copy=False, order=order)
     84 
     85 

MemoryError: Unable to allocate 2.41 GiB for an array with shape (161771019, 2) and data type float64```

WHAT COULD GO WRONG?
4

0 回答 0