在HDF5中存储numpy稀疏矩阵（PyTables）

Question

我在用PyTables存储numpy csr_矩阵时遇到问题。我得到这个错误：

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

我已经为Python 3.6和PyTables3.x更新了Pietro Battiston的优秀答案，因为在从2.x升级的过程中，一些PyTables函数名已经更改

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