Вот три сравнительно быстрых решения:
from scipy import sparse
import numpy as np
def pp():
m = np.maximum.reduceat(a.indices==i,a.indptr[:-1])
cnt = np.count_nonzero(m)
m = m.repeat(np.diff(a.indptr))
return np.bincount(a.indices[m],a.data[m],a.shape[1])/cnt
def qq():
idx = a.indptr.searchsorted(*(a.indices==i).nonzero(),"right")-1
return np.bincount(
np.concatenate([a.indices[a.indptr[i]:a.indptr[i+1]] for i in idx]),
np.concatenate([a.data[a.indptr[i]:a.indptr[i+1]] for i in idx]),
a.shape[1]) / len(idx)
def mm():
idx = (a@(np.arange(a.shape[1])==i))!=0
return idx/np.count_nonzero(idx)@a
def OP():
# a) create a mask of rows containing True if this column was > 0 or False otherwise
mask = (a[:, i] > 0).transpose().toarray()[0]
# b) now get the indices of these rows as list
indices_of_row = list(np.where(mask > 0)[0])
if len(indices_of_row) == 0:
return
# c) use the indices of these rows to create the mean vector
return a[indices_of_row,].mean(axis=0)
from timeit import timeit
n = 1000
a = sparse.random(n,n, format="csr")
i = np.random.randint(0,n)
print("mask ",timeit(pp,number=1000),"ms")
print("concat",timeit(qq,number=1000),"ms")
print("matmul",timeit(mm,number=1000),"ms")
print("OP ",timeit(OP,number=1000),"ms")
assert np.allclose(pp(),OP())
assert np.allclose(qq(),OP())
assert np.allclose(mm(),OP())
Пример выполнения:
mask 0.08981675305403769 ms
concat 0.04179211403243244 ms
matmul 0.14177833893336356 ms
OP 0.9761617160402238 ms