我正在开发Windows 10 64位12gb RAM Core i5。
现在使用大约 30k 的亚马逊数据集进行 IM 测试
训练数据中246621项,测试数据中的 61656
项我尝试在scikit learn中使用其他机器学习工作正常,但使用Knn时出现内存错误问题。
我的代码
knn = KNeighborsClassifier(n_neighbors=5).fit(X_train_tfidf, y_train)
prediction['knn'] = knn.predict(X_test_tfidf)
accuracy_score(y_test, prediction['knn'])*100
我的错误
MemoryError Traceback (most recent call last)
<ipython-input-13-4d958e7f8f5b> in <module>()
1 knn = KNeighborsClassifier(n_neighbors=5).fit(X_train_tfidf, y_train)
----> 2 prediction['knn'] = knn.predict(X_test_tfidf)
3 accuracy_score(y_test, prediction['knn'])*100
~Anaconda3libsite-packagessklearnneighborsclassification.py in predict(self, X)
143 X = check_array(X, accept_sparse='csr')
144
--> 145 neigh_dist, neigh_ind = self.kneighbors(X)
146
147 classes_ = self.classes_
~Anaconda3libsite-packagessklearnneighborsbase.py in kneighbors(self, X, n_neighbors, return_distance)
355 if self.effective_metric_ == 'euclidean':
356 dist = pairwise_distances(X, self._fit_X, 'euclidean',
--> 357 n_jobs=n_jobs, squared=True)
358 else:
359 dist = pairwise_distances(
~Anaconda3libsite-packagessklearnmetricspairwise.py in pairwise_distances(X, Y, metric, n_jobs, **kwds)
1245 func = partial(distance.cdist, metric=metric, **kwds)
1246
-> 1247 return _parallel_pairwise(X, Y, func, n_jobs, **kwds)
1248
1249
~Anaconda3libsite-packagessklearnmetricspairwise.py in _parallel_pairwise(X, Y, func, n_jobs, **kwds)
1088 if n_jobs == 1:
1089 # Special case to avoid picklability checks in delayed
-> 1090 return func(X, Y, **kwds)
1091
1092 # TODO: in some cases, backend='threading' may be appropriate
~Anaconda3libsite-packagessklearnmetricspairwise.py in euclidean_distances(X, Y, Y_norm_squared, squared, X_norm_squared)
244 YY = row_norms(Y, squared=True)[np.newaxis, :]
245
--> 246 distances = safe_sparse_dot(X, Y.T, dense_output=True)
247 distances *= -2
248 distances += XX
~Anaconda3libsite-packagessklearnutilsextmath.py in safe_sparse_dot(a, b, dense_output)
133 """
134 if issparse(a) or issparse(b):
--> 135 ret = a * b
136 if dense_output and hasattr(ret, "toarray"):
137 ret = ret.toarray()
~Anaconda3libsite-packagesscipysparsebase.py in __mul__(self, other)
367 if self.shape[1] != other.shape[0]:
368 raise ValueError('dimension mismatch')
--> 369 return self._mul_sparse_matrix(other)
370
371 # If it's a list or whatever, treat it like a matrix
~Anaconda3libsite-packagesscipysparsecompressed.py in _mul_sparse_matrix(self, other)
538 maxval=nnz)
539 indptr = np.asarray(indptr, dtype=idx_dtype)
--> 540 indices = np.empty(nnz, dtype=idx_dtype)
541 data = np.empty(nnz, dtype=upcast(self.dtype, other.dtype))
542
MemoryError:
您可以尝试增加 KNeighborsClassifier 文档中提出的leaf_size
leaf_size:整数,可选(默认值 = 30(
Leaf size passed to BallTree or KDTree. This can affect the speed of the construction and query, as well as the memory required to store
树。最佳值取决于问题的性质。
首先设置algorithm = "kd_tree"
然后尝试例如leaf_size = 300