使用Cython可能是一个不错的选择。
import numpy as np
cimport numpy as np
cimport cython
from cython.parallel import prange
DTYPE_f64 = np.float64
ctypedef np.float64_t DTYPE_f64_t
@cython.boundscheck(False)
@cython.wraparound(False)
@cython.nonecheck(False)
cdef int count_above_cython(DTYPE_f64_t [:] arr_view, DTYPE_f64_t thresh) nogil:
cdef int length, i, total
total = 0
length = arr_view.shape[0]
for i in prange(length):
if arr_view[i] >= thresh:
total += 1
return total
@cython.boundscheck(False)
@cython.wraparound(False)
@cython.nonecheck(False)
def count_above(np.ndarray arr, DTYPE_f64_t thresh):
cdef DTYPE_f64_t [:] arr_view = arr.ravel()
cdef int total
with nogil:
total = count_above_cython(arr_view, thresh)
return total
不同提出的方法的时间安排。
myarr = np.random.random((1000,1000))
thresh = 0.33
In [6]: %timeit count_above(myarr, thresh)
1000 loops, best of 3: 693 µs per loop
In [9]: %timeit np.count_nonzero(myarr >= thresh)
100 loops, best of 3: 4.45 ms per loop
In [11]: %timeit np.sum(myarr >= thresh)
100 loops, best of 3: 4.86 ms per loop
In [12]: %timeit np.size(np.where(np.reshape(myarr,-1) >= thresh))
10 loops, best of 3: 61.6 ms per loop
使用更大的数组:
In [13]: myarr = np.random.random(10**8)
In [14]: %timeit count_above(myarr, thresh)
10 loops, best of 3: 63.4 ms per loop
In [15]: %timeit np.count_nonzero(myarr >= thresh)
1 loops, best of 3: 473 ms per loop
In [16]: %timeit np.sum(myarr >= thresh)
1 loops, best of 3: 511 ms per loop
In [17]: %timeit np.size(np.where(np.reshape(myarr,-1) >= thresh))
1 loops, best of 3: 6.07 s per loop