Skip to content

Implement to_scipy_sparse_matrix generic #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jkanche merged 1 commit into from
Jan 31, 2024
Merged

Implement to_scipy_sparse_matrix generic #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 28 additions & 1 deletion src/hdf5array/Hdf5CompressedSparseMatrixSeed.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,12 @@
from typing import Optional, Sequence, Tuple, Callable
from typing import Optional, Sequence, Tuple, Callable, Literal
from delayedarray import extract_dense_array, extract_sparse_array, chunk_shape, DelayedArray, wrap, is_sparse, SparseNdarray, is_masked
from h5py import File
import numpy
from numpy import ndarray, dtype, integer, zeros, issubdtype, array
from bisect import bisect_left

from biocutils.package_utils import is_package_installed

__author__ = "LTLA"
__copyright__ = "LTLA"
__license__ = "MIT"
Expand Down Expand Up @@ -458,3 +460,28 @@ def wrap_Hdf5CompressedSparseMatrixSeed(x: Hdf5CompressedSparseMatrixSeed):
def is_masked_Hdf5CompressedSparseMatrixSeed(x: Hdf5CompressedSparseMatrixSeed) -> bool:
"""See :py:meth:`~delayedarray.is_masked.is_masked`."""
return False

if is_package_installed("scipy"):
import scipy.sparse
from delayedarray.to_scipy_sparse_matrix import to_scipy_sparse_matrix

@to_scipy_sparse_matrix.register
def to_scipy_sparse_matrix_from_Hdf5CompressedSparseMatrix(x: Hdf5CompressedSparseMatrix, format: Literal["coo", "csr", "csc"] = "csc") -> scipy.sparse.spmatrix:
"""See :py:func:`delayedarray.to_scipy_sparse_matrix.to_scipy_sparse_matrix`."""

with File(x.path, "r") as handle:
_data = handle[x.data_name][:]
_indices = handle[x.indices_name][:]
_indptr = handle[x.indptr_name][:]

if x.by_column:
_matrix = scipy.sparse.csc_matrix((_data, _indices, _indptr), shape=x.shape, dtype=x.dtype)
else:
_matrix = scipy.sparse.csr_matrix((_data, _indices, _indptr), shape=x.shape, dtype=x.dtype)

if format == "csc":
return _matrix.tocsc()
elif format == "csr":
return _matrix.tocsr()
else:
return _matrix.tocoo()
15 changes: 15 additions & 0 deletions tests/test_Hdf5CompressedSparseMatrix.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,3 +122,18 @@ def test_Hdf5CompressedSparseMatrix_properties():

rewrap = delayedarray.wrap(arr.seed)
assert isinstance(rewrap, Hdf5CompressedSparseMatrix)

def test_Hdf5CompressedSparseMatrix_to_sparse():
shape = (100, 200)
y = scipy.sparse.random(*shape, 0.1).tocsr()
path, group = _mockup(y)
arr = Hdf5CompressedSparseMatrix(path, group, shape=shape, by_column=False)

_to_csr = delayedarray.to_scipy_sparse_matrix(arr, "csr")
assert isinstance(_to_csr, scipy.sparse.csr_matrix)

_to_csc = delayedarray.to_scipy_sparse_matrix(arr, "csc")
assert isinstance(_to_csc, scipy.sparse.csc_matrix)

_to_coo = delayedarray.to_scipy_sparse_matrix(arr, "coo")
assert isinstance(_to_coo, scipy.sparse.coo_matrix)