csr 矩阵 编码_如何合并列表和CSR矩阵

的列，您可以使用scipy.sparse.hstack到水平堆叠这两个(逐列)。我们只需要在列表转换为列向量(稀疏矩阵来说的)，或者与单个列的二维数组 -

scipy.sparse.hstack((tweets, csr_matrix(lex).T))

scipy.sparse.hstack((tweets, np.asarray(lex)[:,None]))

采样运行 -

In [189]: from scipy.sparse import csr_matrix

In [194]: import scipy as sp

In [190]: a = np.random.randint(0,4,(5,10))

In [192]: a

Out[192]:

array([[2, 1, 1, 1, 0, 3, 1, 3, 2, 1],

[0, 2, 1, 2, 3, 0, 1, 1, 2, 3],

[0, 1, 1, 1, 2, 3, 0, 1, 0, 1],

[0, 0, 3, 0, 3, 0, 1, 0, 3, 1],

[1, 0, 2, 3, 3, 3, 2, 2, 0, 1]])

In [193]: b = [9,8,7,6,5] # equivalent to lex

In [191]: A = csr_matrix(a) # equivalent to tweets

In [195]: sp.sparse.hstack((A, csr_matrix(b).T))

Out[195]:

<5x11 sparse matrix of type ''

with 42 stored elements in COOrdinate format>

In [197]: _.toarray() # verify values by converting to dense array

Out[197]:

array([[2, 1, 1, 1, 0, 3, 1, 3, 2, 1, 9],

[0, 2, 1, 2, 3, 0, 1, 1, 2, 3, 8],

[0, 1, 1, 1, 2, 3, 0, 1, 0, 1, 7],

[0, 0, 3, 0, 3, 0, 1, 0, 3, 1, 6],

[1, 0, 2, 3, 3, 3, 2, 2, 0, 1, 5]])