您想贴上标签，还好，SciPy有一个，
scipy.ndimage.label-
In [43]: from scipy.ndimage import labelIn [47]: out = label(arr)[0]In [48]: np.where(arr==0,np.nan,out-1)Out[48]: array([nan, nan, nan, 0., 0., 0., nan, nan, nan, 1., 1., nan, nan, nan, 2., 2., 2., 2.])
还有一些NumPy的 工作 -
def rank_chunks(arr): m = np.r_[False,arr.astype(bool)] idx = np.flatnonzero(m[:-1] < m[1:]) id_ar = np.zeros(len(arr),dtype=float) id_ar[idx[1:]] = 1 out = id_ar.cumsum() out[arr==0] = np.nan return out
另一个与
masking+
np.repeat-
def rank_chunks_v2(arr): m = np.r_[False,arr.astype(bool),False] idx = np.flatnonzero(m[:-1] != m[1:]) l = idx[1::2]-idx[::2] out = np.full(len(arr),np.nan,dtype=float) out[arr!=0] = np.repeat(np.arange(len(l)),l) return out
时间（将给定的输入平铺到1Mx）-
In [153]: arr_big = np.tile(arr,1000000)In [154]: %timeit np.where(arr_big==0,np.nan,label(arr_big)[0]-1) ...: %timeit rank_chunks(arr_big) ...: %timeit rank_chunks_v2(arr_big)1 loop, best of 3: 312 ms per loop1 loop, best of 3: 263 ms per loop1 loop, best of 3: 229 ms per loop
