import numpy as np
def alt(a, end, window, start=0, step=1):
bin_starts = np.arange(start, end+1-window, step)
bin_ends = bin_starts + window
last_index = np.searchsorted(a, bin_ends, side='right')
first_index = np.searchsorted(a, bin_starts, side='left')
return last_index - first_index
def sliding_count(a, end, window, start=0, step=1):
bins = [(x, x + window) for x in range(start, (end + 1) - window, step)]
counts = np.zeros(len(bins))
for i, rng in enumerate(bins):
count = len(a[np.where(np.logical_and(a>=rng[0], a<=rng[1]))])
counts[i] = count
return counts
a = np.array([1, 5, 8, 11, 14, 19])
end = 20
window = 10
print(sliding_count(a, end, window))
# [3. 4. 3. 3. 4. 4. 3. 3. 3. 3. 3.]
print(alt(a, end, window))
# [3 4 3 3 4 4 3 3 3 3 3]
alt 的工作原理:
生成 bin 的起始值和结束值:
In [73]: bin_starts = np.arange(start, end+1-window, step); bin_starts
Out[73]: array([ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
In [74]: bin_ends = bin_starts + window; bin_ends
Out[74]: array([10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20])
由于a是有序的,你可以使用np.searchsorted来查找第一个和最后一个索引
在bin_starts 和bin_ends 中,a 中的每个值都适合:
In [75]: last_index = np.searchsorted(a, bin_ends, side='right'); last_index
Out[75]: array([3, 4, 4, 4, 5, 5, 5, 5, 5, 6, 6])
In [76]: first_index = np.searchsorted(a, bin_starts, side='left'); first_index
Out[76]: array([0, 0, 1, 1, 1, 1, 2, 2, 2, 3, 3])
count 只是索引的区别:
In [77]: last_index - first_index
Out[77]: array([3, 4, 3, 3, 4, 4, 3, 3, 3, 3, 3])
这是perfplot 比较alt 与sliding_count 的性能作为a 长度的函数:
import perfplot
def make_array(N):
a = np.random.randint(10, size=N)
a = a.cumsum()
return a
def using_sliding(a):
return sliding_count(a, end, window)
def using_alt(a):
return alt(a, end, window)
perfplot.show(
setup=make_array,
kernels=[using_sliding, using_alt],
n_range=[2**k for k in range(22)],
logx=True,
logy=True,
xlabel='len(a)')
Perfplot 还会检查 using_sliding 返回的值是否等于 using_alt 返回的值。
Matt Timmermans' idea, "subtract position_in_a from the count for that bin" 触发了这个解决方案。