All geek questions in one place

Effective slicing of symmetric sparse matrices

I have a list of sparse symmetric matrices sigmasuch that

len(sigma) = N

and for all i,j,k,

sigma[i].shape[0] == sigma[i].shape[1] = m  # Square
sigma[i][j,k] == sigma[i][k,j]  # Symmetric

I have an index array Psuch that

P.shape[0] = N
P.shape[1] = k

My goal is to extract tight sub-matrices k x k sigma[i]using indexing given P[i,:]. This can be done as follows:

sub_matrices = np.empty([N,k,k])
for i in range(N):
    sub_matrices[i,:,:] = sigma[i][np.ix_(P[i,:], P[i,:])].todense()

Please note that although ksmall, N(and m) are very large. If sparse symmetric matrices are stored in CSR format, this takes a very long time. I believe that there should be a better solution. For example, is there a sparse format that lends itself well to symmetric matrices that need to be cut into both dimensions?

Python, C, Cython.

EXTRA

, Cython :

cimport cython
import numpy as np
cimport numpy as np

@cython.boundscheck(False) # turn off bounds-checking for entire function
cpdef sparse_slice_fast_cy(sigma,
                           long[:,:] P,
                           double[:,:,:] sub_matrices):
    """
    Inputs:
        sigma: A list (N,) of sparse sp.csr_matrix (m x m)
        P: A 2D array of integers (N, k)
        sub_matrices: A 3D array of doubles (N, k, k) containing the slicing
    """
    # Create variables for keeping code tidy
    cdef long N = P.shape[0]
    cdef long k = P.shape[1]

    cdef long i
    cdef long j
    cdef long index_pointer 
    cdef long sparse_row_pointer

    # Create objects for holding sparse matrix data
    cdef double[:] data
    cdef long[:] indices
    cdef long[:] indptr

    # Object for the ordered P
    cdef long[:] perm

    # Make sure sub_matrices is all 0
    sub_matrices[:] = 0

    for i in range(N):
        # Sort the P
        perm = np.argsort(P[i,:])

        # Get the sparse matrix values
        data     = sigma[i].data
        indices  = sigma[i].indices.astype(long)
        indptr   = sigma[i].indptr.astype(long)

        for j in range(k):
            # Loop over row P[i, perm[j]] in sigma searching for values
            # in P[i, :] vector i.e. compare
            #     sigma[P[i, perm[j], :]
            # against
            #     P[i,:]

            # To do this we need our sparse row vector with columns 
            #     indices[indptr[P[i, perm[j]]], indptr[P[i, perm[j]]+1]]
            # and data/values
            #     data[indptr[P[i, perm[j]]], indptr[P[i, perm[j]]+1]]
            # which comes from the csr matrix format.
            # We also need our sorted indexing vector
            #     P[i, perm[:]]

            # We begin by pointing at the top of both
            # our vectors and gradually move down them. In the event of 
            # an equality we add the data to sub_matrices[i,:,:] and 
            # increment the INDEXING VECTOR pointer, not the sparse
            # row vector pointer, as there can be multiple values that 
            # are the same in the indexing vector but not the sparse row
            # column vector (only 1 column can appear in 1 row!).
            index_pointer = 0
            sparse_row_pointer = indptr[P[i, perm[j]]]

            while ((index_pointer < k) and (sparse_row_pointer < indptr[P[i, perm[j]] + 1])):
                if indices[sparse_row_pointer] == P[i, perm[index_pointer]]:
                    # We can add data to sub_matrices
                    sub_matrices[i, perm[j], perm[index_pointer]] = \
                           data[sparse_row_pointer]

                    # Only increment the index pointer
                    index_pointer += 1
                elif indices[sparse_row_pointer] > P[i, perm[index_pointer]]:
                    # Need to increment index pointer
                    index_pointer += 1
                else:
                    # Need to increment sparse row pointer
                    sparse_row_pointer += 1

, np.argsort , C. , N. , Python, , prange.

, , , Cython, -, , , .

ead Cython

cimport cython
import numpy as np
cimport numpy as np

@cython.boundscheck(False) # turn off bounds-checking for entire function
cpdef sparse_slice_fast_cy(sigma,
                           np.ndarray[np.int32_t, ndim=2] P,
                           np.float64_t[:,:,:] sub_matrices,
                           int symmetric):
    """
    Inputs:
        sigma: A list (N,) of sparse sp.csr_matrix (m x m)
        P: A 2D array of integers (N, k)
        sub_matrices: A 3D array of doubles (N, k, k) containing the slicing
        symmetric: 1 if the sigma matrices are symmetric
    """
    # Create variables for keeping code tidy
    cdef np.int32_t N = P.shape[0]
    cdef np.int32_t k = P.shape[1]

    cdef np.int32_t i
    cdef np.int32_t j
    cdef np.int32_t index_pointer 
    cdef np.int32_t sparse_row_pointer

    # Create objects for holding sparse matrix data
    cdef np.float64_t[:] data
    cdef np.int32_t[:] indices

    cdef np.int32_t[:] indptr

    # Object for the ordered P
    cdef np.int32_t[:,:] perm = np.argsort(P, axis=1).astype(np.int32)

    # Make sure sub_matrices is all 0
    sub_matrices[:] = 0

    for i in range(N):
        # Get the sparse matrix values
        data     = sigma[i].data
        indices  = sigma[i].indices
        indptr   = sigma[i].indptr

        for j in range(k):
            # Loop over row P[i, perm[j]] in sigma searching for values
            # in P[i, :] vector i.e. compare
            #     sigma[P[i, perm[j], :]
            # against
            #     P[i,:]

            # To do this we need our sparse row vector with columns 
            #     indices[indptr[P[i, perm[j]]], indptr[P[i, perm[j]]+1]]
            # and data/values
            #     data[indptr[P[i, perm[j]]], indptr[P[i, perm[j]]+1]]
            # which comes from the csr matrix format.
            # We also need our sorted indexing vector
            #     P[i, perm[:]]

            # We begin by pointing at the top of both
            # our vectors and gradually move down them. In the event of 
            # an equality we add the data to sub_matrices[i,:,:] and 
            # increment the INDEXING VECTOR pointer, not the sparse
            # row vector pointer, as there can be multiple values that 
            # are the same in the indexing vector but not the sparse row
            # column vector (only 1 column can appear in 1 row!).

            if symmetric:
                index_pointer = j  # Only search upper triangular
            else:
                index_pointer = 0
            sparse_row_pointer = indptr[P[i, perm[i, j]]]

            while ((index_pointer < k) and (sparse_row_pointer < indptr[P[i, perm[i, j]] + 1])):
                if indices[sparse_row_pointer] == P[i, perm[i, index_pointer]]:
                    # We can add data to sub_matrices
                    sub_matrices[i, perm[i, j], perm[i, index_pointer]] = \
                           data[sparse_row_pointer]

                    if symmetric:
                        sub_matrices[i, perm[i, index_pointer], perm[i, j]] = \
                               data[sparse_row_pointer]

                    # Only increment the index pointer
                    index_pointer += 1
                elif indices[sparse_row_pointer] > P[i, perm[i, index_pointer]]:
                    # Need to increment index pointer
                    index_pointer += 1
                else:
                    # Need to increment sparse row pointer
                    sparse_row_pointer += 1

​​ , , , , :

# See https://stackoverflow.com/questions/48805636/efficient-slicing-of-symmetric-sparse-matrices
cimport cython
import numpy as np
cimport numpy as np
from libc.stdlib cimport malloc, free
from cython.parallel import prange

@cython.boundscheck(False) # turn off bounds-checking for entire function
cpdef sparse_slice_fast_cy(sigma,
                           np.ndarray[np.int32_t, ndim=2] P,
                           np.float64_t[:,:,:] sub_matrices,
                           int symmetric):
    """
    Inputs:
        sigma: A list (N,) of sparse sp.csr_matrix (m x m)
        P: A 2D array of integers (N, k)
        sub_matrices: A 3D array of doubles (N, k, k) containing the slicing
        symmetric: 1 if the sigma matrices are symmetric
    """
    # Create variables for keeping code tidy
    cdef np.int32_t N = P.shape[0]
    cdef np.int32_t k = P.shape[1]

    cdef np.int32_t i
    cdef np.int32_t j
    cdef np.int32_t index_pointer 
    cdef np.int32_t sparse_row_pointer

    # Create objects for holding sparse matrix data
    cdef np.float64_t[:] data_mem_view
    cdef np.int32_t[:] indices_mem_view
    cdef np.int32_t[:] indptr_mem_view

    cdef np.float64_t **data = <np.float64_t **> malloc(N * sizeof(np.float64_t *))
    cdef np.int32_t **indices = <np.int32_t **> malloc(N * sizeof(np.int32_t *))
    cdef np.int32_t **indptr = <np.int32_t **> malloc(N * sizeof(np.int32_t *))

    for i in range(N):
        data_mem_view = sigma[i].data
        data[i] = &(data_mem_view[0])

        indices_mem_view = sigma[i].indices
        indices[i] = &(indices_mem_view[0])

        indptr_mem_view = sigma[i].indptr
        indptr[i] = &(indptr_mem_view[0])

    # Object for the ordered P
    cdef np.int32_t[:,:] perm = np.argsort(P, axis=1).astype(np.int32)

    # Make sure sub_matrices is all 0
    sub_matrices[:] = 0

    for i in prange(N, nogil=True):
        for j in range(k):
            # Loop over row P[i, perm[j]] in sigma searching for values
            # in P[i, :] vector i.e. compare
            #     sigma[P[i, perm[j], :]
            # against
            #     P[i,:]
            # To do this we need our sparse row vector with columns 
            #     indices[indptr[P[i, perm[j]]], indptr[P[i, perm[j]]+1]]
            # and data/values
            #     data[indptr[P[i, perm[j]]], indptr[P[i, perm[j]]+1]]
            # which comes from the csr matrix format.
            # We also need our sorted indexing vector
            #     P[i, perm[:]]

            # We begin by pointing at the top of both
            # our vectors and gradually move down them. In the event of 
            # an equality we add the data to sub_matrices[i,:,:] and 
            # increment the INDEXING VECTOR pointer, not the sparse
            # row vector pointer, as there can be multiple values that 
            # are the same in the indexing vector but not the sparse row
            # column vector (only 1 column can appear in 1 row!).

            if symmetric:
                index_pointer = j  # Only search upper triangular
            else:
                index_pointer = 0
            sparse_row_pointer = indptr[i][P[i, perm[i, j]]]

            while ((index_pointer < k) and 
                   (sparse_row_pointer < indptr[i][P[i, perm[i, j]] + 1])):
                if indices[i][sparse_row_pointer] == P[i, perm[i, index_pointer]]:
                    # We can add data to sub_matrices
                    sub_matrices[i, perm[i, j], perm[i, index_pointer]] = \
                           data[i][sparse_row_pointer]

                    if symmetric:
                        sub_matrices[i, perm[i, index_pointer], perm[i, j]] = \
                               data[i][sparse_row_pointer]

                    # Only increment the index pointer
                    index_pointer = index_pointer + 1
                elif indices[i][sparse_row_pointer] > P[i, perm[i, index_pointer]]:
                    # Need to increment index pointer
                    index_pointer = index_pointer + 1
                else:
                    # Need to increment sparse row pointer
                    sparse_row_pointer = sparse_row_pointer + 1

    # Free malloc'd data
    free(data)
    free(indices)
    free(indptr)

Test

cythonize -i sparse_slice.pyx

sparse_slice.pyx - . script:

import time
import numpy as np
import scipy as sp
import scipy.sparse
from sparse_slice import sparse_slice_fast_cy

k = 100
N = 20000
m = 10000
samples = 20

# Create sigma matrices
## The sampling of random sparse takes a while so just do a few and 
## then populate with these.
now = time.time()
sigma_samples = []
for i in range(samples):
    sigma_samples.append(sp.sparse.rand(m, m, density=0.001, format='csr'))
    sigma_samples[-1] = sigma_samples[-1] + sigma_samples[-1].T  # Symmetric

## Now make the sigma list from these.
sigma = []
for i in range(N):
    j = np.random.randint(samples)
    sigma.append(sigma_samples[j])
print('Time to make sigma: {}'.format(time.time() - now))

# Create indexer
now = time.time()
P = np.empty([N, k]).astype(int)
for i in range(N):
    P[i, :] = np.random.choice(np.arange(m), k, replace=True)
print('Time to make P: {}'.format(time.time() - now))

# Create objects for holding the slices
sub_matrices_slow = np.empty([N, k, k])
sub_matrices_fast = np.empty([N, k, k])

# Run both slicings
## Slow
now = time.time()
for i in range(N):
    sub_matrices_slow[i,:,:] = sigma[i][np.ix_(P[i,:], P[i,:])].todense()
print('Time to make sub_matrices_slow: {}'.format(time.time() - now))

## Fast
symmetric = 1
now = time.time()
sparse_slice_fast_cy(sigma, P.astype(np.int32), sub_matrices_fast, symmetric)
print('Time to make sub_matrices_fast: {}'.format(time.time() - now))

assert(np.all((sub_matrices_slow - sub_matrices_fast)**2 < 1e-6))
+4
1

, :

A) i -loop:

# Object for the ordered P
cdef long[:,:] perm = np.argsort(P, axis=1)

, P np.ndarray[np.int64_t, ndim=2] P ( ), . perm[i,X] perm[X].

B)

cdef np.int32_t[:] indices
cdef np.int32_t[:] indptr

".astype", ..

for i in range(N):
    data     = sigma[i].data
    indices  = sigma[i].indices
    indptr   = sigma[i].indptr

, sigma[i] O(m), : O(N*(m+k^2)) `O (N * k ^ 2) - , .

.

prange i -loop, sigma[i] , data, indices indptr . , , - , - .

, :

  ...
  index_pointer = j #only upper triangle!
  ....
  ....
     # We can add data to sub_matrices
     #upper triangle sub-matrix:
     sub_matrices[i, perm[j], perm[index_pointer]] = \
                       data[sparse_row_pointer]
     #lower triangle sub-matrix:
     sub_matrices[i, perm[index_pointer], perm[j]] = \
                       data[sparse_row_pointer]
  ....

B) , ...

Edit:

:

 /usr/bin/time -f "peak_used_memory:%M(in Kb)" python test.py

N=2000 (python3.6 + cython0.27.1):

                             peak memory usage
only slow                       245Mb
only fast                       245Mb
slow+fast no check              402Mb
slow+fast+assert                576Mb

, 50 , 200 , , 176 assert. N.

, , cython .

( ) , . .

perm - . ,

  • / , P .
  • , .

, 20-30% .

cython , c-, , C, python.

, , .

,

cdef np.int64_t[:,:] perm = np.argsort(P, axis=1)

.

+2

Source: https://habr.com/ru/post/1693683/

More articles:


All Articles