Concatenate sparse matrices in Python using SciPy/Numpy

问题:

What would be the most efficient way to concatenate sparse matrices in Python using SciPy/Numpy?

Here I used the following:

>>> np.hstack((X, X2)) array([ '         with 1135520 stored elements in Compressed Sparse Row format>,         '         with 1135520 stored elements in Compressed Sparse Row format>],         dtype=object) 

I would like to use both predictors in a regression, but the current format is obviously not what I'm looking for. Would it be possible to get the following:

    '      with 2271040 stored elements in Compressed Sparse Row format> 

It is too large to be converted to a deep format.

回答1:

You can use the scipy.sparse.hstack:

from scipy.sparse import hstack hstack((X, X2)) 

Using the numpy.hstack will create an array with two sparse matrix objects.

文章来源: Concatenate sparse matrices in Python using SciPy/Numpy