Untitled
unknown
plain_text
2 years ago
1.3 kB
5
Indexable
--------------------------------------------------------------------------- MemoryError Traceback (most recent call last) Input In [18], in <cell line: 11>() 9 cv = CountVectorizer(stop_words='english') 10 X_cv = cv.fit_transform(X_text) ---> 11 X_cv_df = pd.DataFrame(X_cv.toarray(), columns=cv.get_feature_names_out()) 12 X_cv_df = X_cv_df.values.reshape(X.shape[0], -1) 14 # Split data into training and test sets File /Analytics/venv/CAPEANALYTICS/lib/python3.8/site-packages/scipy/sparse/compressed.py:1039, in _cs_matrix.toarray(self, order, out) 1037 if out is None and order is None: 1038 order = self._swap('cf')[0] -> 1039 out = self._process_toarray_args(order, out) 1040 if not (out.flags.c_contiguous or out.flags.f_contiguous): 1041 raise ValueError('Output array must be C or F contiguous') File /Analytics/venv/CAPEANALYTICS/lib/python3.8/site-packages/scipy/sparse/base.py:1202, in spmatrix._process_toarray_args(self, order, out) 1200 return out 1201 else: -> 1202 return np.zeros(self.shape, dtype=self.dtype, order=order) MemoryError: Unable to allocate 18.5 GiB for an array with shape (41880, 59141) and data type int64
Editor is loading...