Read unique items along the axis of a NumPy array

Question

I have a three dimensional array like

A = np.array ([[[1,1],
[1,0]],

[[1,2],
[1,0]],

[[1,0],
[0,0]]])

Now, I would like to get an array that has a non-zero value at a given position if only a unique non-zero value (or zero) is encountered at this position. It must have zero if only zero or more than one non-zero value occurs in this position. In the above example, I would like

[[1,0],
[1,0]]

So

• in A[:,0,0]there is only 1s
• in A[:,0,1]is 0, 1and 2therefore more than one non-zero value
• in A[:,1,0]is 0and 1therefore 1saved
• in A[:,1,1]there is only 0s

, np.count_nonzero(A, axis=0), 1 2, . np.unique, , , , .

np.count_unique(A, axis=0), , . [[1, 3],[2, 1]], , 3 , .

---

, , - , ,

[[len(np.unique(A[:, i, j])) for j in range(A.shape[2])] for i in range(A.shape[1])]

?

Answer 1

, A , . : 3D, 2D , 2D . , :

def nunique_axis0_maskcount_app1(A):
    m,n = A.shape[1:]
    mask = np.zeros((A.max()+1,m,n),dtype=bool)
    mask[A,np.arange(m)[:,None],np.arange(n)] = 1
    return mask.sum(0)

def nunique_axis0_maskcount_app2(A):
    m,n = A.shape[1:]
    A.shape = (-1,m*n)
    maxn = A.max()+1
    N = A.shape[1]
    mask = np.zeros((maxn,N),dtype=bool)
    mask[A,np.arange(N)] = 1
    A.shape = (-1,m,n)
    return mask.sum(0).reshape(m,n)

-

In [154]: A = np.random.randint(0,100,(100,100,100))

# @B. M. soln
In [155]: %timeit f(A)
10 loops, best of 3: 28.3 ms per loop

# @B. M. soln using slicing : (B[1:] != B[:-1]).sum(0)+1
In [156]: %timeit f2(A)
10 loops, best of 3: 26.2 ms per loop

In [157]: %timeit nunique_axis0_maskcount_app1(A)
100 loops, best of 3: 12 ms per loop

In [158]: %timeit nunique_axis0_maskcount_app2(A)
100 loops, best of 3: 9.14 ms per loop

---

Numba

, nunique_axis0_maskcount_app2, C numba, -

from numba import njit

@njit
def nunique_loopy_func(mask, N, A, p, count):
    for j in range(N):
        mask[:] = True
        mask[A[0,j]] = False
        c = 1
        for i in range(1,p):
            if mask[A[i,j]]:
                c += 1
            mask[A[i,j]] = False
        count[j] = c
    return count

def nunique_axis0_numba(A):
    p,m,n = A.shape
    A.shape = (-1,m*n)
    maxn = A.max()+1
    N = A.shape[1]
    mask = np.empty(maxn,dtype=bool)
    count = np.empty(N,dtype=int)
    out = nunique_loopy_func(mask, N, A, p, count).reshape(m,n)
    A.shape = (-1,m,n)
    return out

-

In [328]: np.random.seed(0)

In [329]: A = np.random.randint(0,100,(100,100,100))

In [330]: %timeit nunique_axis0_maskcount_app2(A)
100 loops, best of 3: 11.1 ms per loop

# @B.M. numba soln
In [331]: %timeit countunique2(A,A.max()+1)
100 loops, best of 3: 3.43 ms per loop

# Numba soln posted in this post
In [332]: %timeit nunique_axis0_numba(A)
100 loops, best of 3: 2.76 ms per loop

Answer 2

np.diff, numpy .

def diffcount(A):
    B=A.copy()
    B.sort(axis=0)
    C=np.diff(B,axis=0)>0
    D=C.sum(axis=0)+1
    return D

# [[1 3]
#  [2 1]]

:

In [62]: A=np.random.randint(0,100,(100,100,100))

In [63]: %timeit diffcount(A)
46.8 ms ± 769 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)

In [64]: timeit [[len(np.unique(A[:, i, j])) for j in range(A.shape[2])]\
for i in range(A.shape[1])]
149 ms ± 700 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)

, , , ln(A.shape[0]) .

- :

In [81]: %timeit np.apply_along_axis(lambda a:len(set(a)),axis=0,A) 
183 ms ± 1.17 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)

, .

:

def countunique(A,Amax):
    res=np.empty(A.shape[1:],A.dtype)
    c=np.empty(Amax+1,A.dtype)
    for i in range(A.shape[1]):
        for j in range(A.shape[2]):
            T=A[:,i,j]
            for k in range(c.size): c[k]=0 
            for x in T:
                c[x]=1
            res[i,j]= c.sum()
    return res 

python:

In [70]: %timeit countunique(A,100)
429 ms ± 18.7 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

python. numba:

import numba    
countunique2=numba.jit(countunique)  

In [71]: %timeit countunique2(A,100)
3.63 ms ± 70.8 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)

.