在 HDF5 (PyTables) 中存储 numpy 稀疏矩阵

Question

我在使用 PyTables 存储 numpy csr_matrix 时遇到问题。我收到此错误：

TypeError: objects of type ``csr_matrix`` are not supported in this context, sorry; supported objects are: NumPy array, record or scalar; homogeneous list or tuple, integer, float, complex or string

我的代码：

f = tables.openFile(path,'w')

atom = tables.Atom.from_dtype(self.count_vector.dtype)
ds = f.createCArray(f.root, 'count', atom, self.count_vector.shape)
ds[:] = self.count_vector
f.close()

有什么想法吗？

谢谢

Answer 1

CSR 矩阵可以从其data、indices 和indptr 属性完全重构。这些只是常规的 numpy 数组，因此将它们作为 3 个单独的数组存储在 pytables 中应该没有问题，然后将它们传递回csr_matrix 的构造函数。请参阅scipy docs。

编辑：Pietro 的回答指出shape 成员也应该被存储

Answer 2

DaveP 的答案几乎是正确的...但可能会导致非常稀疏的矩阵出现问题：如果最后一列或最后一行为空，则它们将被删除。因此，为了确保一切正常，“shape”属性也必须存储。

这是我经常使用的代码：

import tables as tb
from numpy import array
from scipy import sparse

def store_sparse_mat(m, name, store='store.h5'):
    msg = "This code only works for csr matrices"
    assert(m.__class__ == sparse.csr.csr_matrix), msg
    with tb.openFile(store,'a') as f:
        for par in ('data', 'indices', 'indptr', 'shape'):
            full_name = '%s_%s' % (name, par)
            try:
                n = getattr(f.root, full_name)
                n._f_remove()
            except AttributeError:
                pass

            arr = array(getattr(m, par))
            atom = tb.Atom.from_dtype(arr.dtype)
            ds = f.createCArray(f.root, full_name, atom, arr.shape)
            ds[:] = arr

def load_sparse_mat(name, store='store.h5'):
    with tb.openFile(store) as f:
        pars = []
        for par in ('data', 'indices', 'indptr', 'shape'):
            pars.append(getattr(f.root, '%s_%s' % (name, par)).read())
    m = sparse.csr_matrix(tuple(pars[:3]), shape=pars[3])
    return m

使其适应 csc 矩阵很简单。

Answer 3

我已经更新了 Pietro Battiston 对 Python 3.6 和 PyTables 3.x 的出色回答，因为一些 PyTables 函数名称在从 2.x 升级时发生了变化。

import numpy as np
from scipy import sparse
import tables

def store_sparse_mat(M, name, filename='store.h5'):
    """
    Store a csr matrix in HDF5

    Parameters
    ----------
    M : scipy.sparse.csr.csr_matrix
        sparse matrix to be stored

    name: str
        node prefix in HDF5 hierarchy

    filename: str
        HDF5 filename
    """
    assert(M.__class__ == sparse.csr.csr_matrix), 'M must be a csr matrix'
    with tables.open_file(filename, 'a') as f:
        for attribute in ('data', 'indices', 'indptr', 'shape'):
            full_name = f'{name}_{attribute}'

            # remove existing nodes
            try:  
                n = getattr(f.root, full_name)
                n._f_remove()
            except AttributeError:
                pass

            # add nodes
            arr = np.array(getattr(M, attribute))
            atom = tables.Atom.from_dtype(arr.dtype)
            ds = f.create_carray(f.root, full_name, atom, arr.shape)
            ds[:] = arr

def load_sparse_mat(name, filename='store.h5'):
    """
    Load a csr matrix from HDF5

    Parameters
    ----------
    name: str
        node prefix in HDF5 hierarchy

    filename: str
        HDF5 filename

    Returns
    ----------
    M : scipy.sparse.csr.csr_matrix
        loaded sparse matrix
    """
    with tables.open_file(filename) as f:

        # get nodes
        attributes = []
        for attribute in ('data', 'indices', 'indptr', 'shape'):
            attributes.append(getattr(f.root, f'{name}_{attribute}').read())

    # construct sparse matrix
    M = sparse.csr_matrix(tuple(attributes[:3]), shape=attributes[3])
    return M