def _sparse_dot_vector(mv_a, mv_b, cast=False, dprint=print, scalar=1.):
"""
Multiply a sparse matrix by a dense vector.
The matrix must be CSR or CSC format.
The vector must be (N,) or (N, 1) shape.
Returns a dense vector of (N,) or (N, 1) shape (depending on vector)
:param mv_a: Left (A) matrix or vector
:type mv_a: np.ndarray, sp.spmatrix.csr, sp.spmatrix.csc
:param mv_b: Right (B) matrix or vector
:type mv_b: np.ndarray, sp.spmatrix.csr, sp.spmatrix.csc
:param scalar: A value to multiply the result matrix by. Defaults to 1.
:type scalar: float
:param cast: Convert values to compatible floats if True. Raise an error if they are not compatible if False.
Defaults to False.
:type cast: bool
:param dprint: A function that will handle debug strings. Defaults to print.
:type dprint: function
:return: A (dot) B as a dense matrix
:rtype: np.ndarray
"""
_sanity_check(mv_a, mv_b, allow_vector=True)
mv_a, mv_b = _type_check(mv_a, mv_b, cast=cast, dprint=dprint)
if _is_dense_vector(mv_b):
return _sparse_dense_vector_mult(mv_a, mv_b, scalar=scalar)
elif _is_dense_vector(mv_a):
return _sparse_dense_vector_mult(mv_b, mv_a.T, scalar=scalar, transpose=True).T
def _dense_dot_dense(matrix_a,
matrix_b,
cast=False,
dprint=print,
scalar=1.,
out=None,
out_scalar=None):
_sanity_check(matrix_a, matrix_b, allow_vector=True)
# Check for edge condition inputs which result in empty outputs
if _empty_output_check(matrix_a, matrix_b):
dprint(
"Skipping multiplication because A (dot) B must yield an empty matrix"
)
final_dtype = np.float64 if matrix_a.dtype != matrix_b.dtype or matrix_a.dtype != np.float32 else np.float32
return _out_matrix((matrix_a.shape[0], matrix_b.shape[1]),
final_dtype,
out_arr=out)
matrix_a, matrix_b = _type_check(matrix_a,
matrix_b,
cast=cast,
dprint=dprint)
a_dbl, b_dbl = matrix_a.dtype == np.float64, matrix_b.dtype == np.float64
return _dense_matmul(matrix_a,
matrix_b,
a_dbl or b_dbl,
scalar=scalar,
out=out,
out_scalar=out_scalar)
def _sparse_dot_vector(mv_a,
mv_b,
cast=False,
dprint=print,
scalar=1.,
out=None,
out_scalar=None):
"""
Multiply a sparse matrix by a dense vector.
The matrix must be CSR or CSC format.
The vector must be (N,) or (N, 1) shape.
Returns a dense vector of (N,) or (N, 1) shape (depending on vector)
:param mv_a: Left (A) matrix or vector
:type mv_a: np.ndarray, sp.spmatrix.csr, sp.spmatrix.csc
:param mv_b: Right (B) matrix or vector
:type mv_b: np.ndarray, sp.spmatrix.csr, sp.spmatrix.csc
:param scalar: A value to multiply the result matrix by. Defaults to 1.
:type scalar: float
:param cast: Convert values to compatible floats if True. Raise an error if they are not compatible if False.
Defaults to False.
:type cast: bool
:param dprint: A function that will handle debug strings. Defaults to print.
:type dprint: function
:param out: Add the dot product to this array if provided.
:type out: np.ndarray, None
:param out_scalar: Multiply the out array by this scalar if provided.
:type out_scalar: float, None
:return: A (dot) B as a dense matrix
:rtype: np.ndarray
"""
_sanity_check(mv_a, mv_b, allow_vector=True)
mv_a, mv_b = _type_check(mv_a, mv_b, cast=cast, dprint=dprint)
if _is_dense_vector(mv_b):
return _sparse_dense_vector_mult(mv_a,
mv_b,
scalar=scalar,
out=out,
out_scalar=out_scalar)
elif _is_dense_vector(mv_a) and out is None:
return _sparse_dense_vector_mult(mv_b,
mv_a.T,
scalar=scalar,
transpose=True).T
elif _is_dense_vector(mv_a) and out is not None:
_ = _sparse_dense_vector_mult(mv_b,
mv_a.T,
scalar=scalar,
transpose=True,
out=out.T,
out_scalar=out_scalar,
out_t=True)
return out
else:
raise ValueError("Neither mv_a or mv_b is a dense vector")
def _sparse_dot_dense(matrix_a, matrix_b, cast=False, dprint=print, scalar=1.):
"""
Multiply together a dense and a sparse matrix.
If the sparse matrix is not CSR, it may need to be reordered, depending on the order of the dense array.
:param matrix_a: Left (A) matrix
:type matrix_a: np.ndarray, sp.spmatrix.csr, sp.spmatrix.csc
:param matrix_b: Right (B) matrix
:type matrix_b: np.ndarray, sp.spmatrix.csr, sp.spmatrix.csc
:param scalar: A value to multiply the result matrix by. Defaults to 1.
:type scalar: float
:param cast: Convert values to compatible floats if True. Raise an error if they are not compatible if False.
Defaults to False.
:type cast: bool
:param dprint: A function that will handle debug strings. Defaults to print.
:type dprint: function
:return: A (dot) B as a dense matrix
:rtype: np.ndarray
"""
_sanity_check(matrix_a, matrix_b)
# Check for edge condition inputs which result in empty outputs
if _empty_output_check(matrix_a, matrix_b):
dprint(
"Skipping multiplication because A (dot) B must yield an empty matrix"
)
final_dtype = np.float64 if matrix_a.dtype != matrix_b.dtype or matrix_a.dtype != np.float32 else np.float32
return np.zeros((matrix_a.shape[0], matrix_b.shape[1]),
dtype=final_dtype)
matrix_a, matrix_b = _type_check(matrix_a,
matrix_b,
cast=cast,
dprint=dprint)
if sum([_spsparse.isspmatrix(matrix_a),
_spsparse.isspmatrix(matrix_b)]) != 1:
raise ValueError(
"_sparse_dot_dense takes one sparse and one dense array")
elif _spsparse.isspmatrix(matrix_a):
return _sparse_dense_matmul(matrix_a, matrix_b, scalar=scalar)
elif _spsparse.isspmatrix(matrix_b):
return _dense_sparse_matmul(matrix_a, matrix_b, scalar=scalar)
def _sparse_dot_sparse(matrix_a,
matrix_b,
cast=False,
reorder_output=False,
dense=False,
dprint=print):
"""
Multiply together two scipy sparse matrixes using the intel Math Kernel Library.
This currently only supports float32 and float64 data
:param matrix_a: Sparse matrix A in CSC/CSR format
:type matrix_a: scipy.sparse.spmatrix
:param matrix_b: Sparse matrix B in CSC/CSR format
:type matrix_b: scipy.sparse.spmatrix
:param cast: Should the data be coerced into float64 if it isn't float32 or float64
If set to True and any other dtype is passed, the matrix data will be modified in-place
If set to False and any dtype that isn't float32 or float64 is passed, a ValueError will be raised
Defaults to False
:param reorder_output: Should the array indices be reordered using MKL
If set to True, the object in C will be ordered and then exported into python
If set to False, the array column indices will not be ordered.
The scipy sparse dot product does not yield ordered column indices so this defaults to False
:type reorder_output: bool
:param dense: Should the matrix multiplication yield a dense numpy array
This does not require any copy and is memory efficient if the output array density is > 50%
:type dense: bool
:param dprint: Should debug and timing messages be printed. Defaults to false.
:type dprint: function
:return: Sparse matrix that is the result of A * B in CSR format
:rtype: scipy.sparse.csr_matrix
"""
# Check for allowed sparse matrix types
if is_csr(matrix_a) and (is_csc(matrix_b) or is_csr(matrix_b)):
default_output = _spsparse.csr_matrix
output_type = "csr"
elif is_csc(matrix_a) and (is_csc(matrix_b) or is_csr(matrix_b)):
default_output = _spsparse.csc_matrix
output_type = "csc"
else:
raise ValueError(
"Both input matrices to dot_product_mkl must be CSR or CSC; COO and BSR are not supported"
)
# Override output if dense flag is set
default_output = default_output if not dense else np.zeros
# Check to make sure that this multiplication can work and check dtypes
_sanity_check(matrix_a, matrix_b)
# Check for edge condition inputs which result in empty outputs
if _empty_output_check(matrix_a, matrix_b):
dprint(
"Skipping multiplication because A (dot) B must yield an empty matrix"
)
final_dtype = np.float64 if matrix_a.dtype != matrix_b.dtype or matrix_a.dtype != np.float32 else np.float32
return default_output((matrix_a.shape[0], matrix_b.shape[1]),
dtype=final_dtype)
# Check dtypes
matrix_a, matrix_b = _type_check(matrix_a,
matrix_b,
cast=cast,
dprint=dprint)
t0 = time.time()
# Create intel MKL objects
mkl_a, a_dbl = _create_mkl_sparse(matrix_a)
mkl_b, b_dbl = _create_mkl_sparse(matrix_b)
t1 = time.time()
dprint("Created MKL sparse handles: {0:.6f} seconds".format(t1 - t0))
# Call spmmd for dense output directly if the dense flag is set
if dense:
dense_arr = _matmul_mkl_dense(mkl_a, mkl_b,
(matrix_a.shape[0], matrix_b.shape[1]),
a_dbl or b_dbl)
t2 = time.time()
dprint("Multiplied matrices: {0:.6f} seconds".format(t2 - t1))
_destroy_mkl_handle(mkl_a)
_destroy_mkl_handle(mkl_b)
return dense_arr
# Call spmm for sparse output if the dense flag is not set and then export the sparse matrix to python
else:
# Dot product
mkl_c = _matmul_mkl(mkl_a, mkl_b)
_destroy_mkl_handle(mkl_a)
_destroy_mkl_handle(mkl_b)
t2 = time.time()
dprint("Multiplied matrices: {0:.6f} seconds".format(t2 - t1))
# Reorder
if reorder_output:
_order_mkl_handle(mkl_c)
dprint("Reordered indicies: {0:.6f} seconds".format(time.time() -
t2))
t2 = time.time()
# Extract
python_c = _export_mkl(mkl_c, a_dbl or b_dbl, output_type=output_type)
_destroy_mkl_handle(mkl_c)
dprint("Created python handle: {0:.6f} seconds".format(time.time() -
t2))
return python_c