我认为你可以做类似的事情
def rcount(a):
without_reset = (a == 1).cumsum()
reset_at = (a == 0)
overcount = np.maximum.accumulate(without_reset * reset_at)
result = without_reset - overcount
return result
这给了我
>>> a = np.array([0.1, 0.2, 1.0, 1.0, 1.0, 0.9, 0.6, 1.0, 0.0, 1.0])
>>> rcount(a)
array([0, 0, 1, 2, 3, 3, 3, 4, 0, 1])
之所以有效,是因为我们可以使用累积最大值来计算“超数”:
>>> without_reset * reset_at
array([0, 0, 0, 0, 0, 0, 0, 0, 4, 0])
>>> np.maximum.accumulate(without_reset * reset_at)
array([0, 0, 0, 0, 0, 0, 0, 0, 4, 4])
健全性测试:
def manual(arr):
out = []
count = 0
for x in arr:
if x == 1:
count += 1
if x == 0:
count = 0
out.append(count)
return out
def test():
for w in [1, 2, 10, 10**4]:
for trial in range(100):
for vals in [0,1],[0,1,2]:
b = np.random.choice(vals, size=w)
assert (rcount(b) == manual(b)).all()
print("hooray!")
然后
>>> test()
hooray!