Find unique rows in numpy.array

Question

I need to find unique rows in a numpy.array.

For example:

>>> a # I have
array([[1, 1, 1, 0, 0, 0],
       [0, 1, 1, 1, 0, 0],
         


        

Answer 1

I've compared the suggested alternative for speed and found that, surprisingly, the void view unique solution is even a bit faster than numpy's native unique with the axis argument. If you're looking for speed, you'll want

numpy.unique(
    a.view(numpy.dtype((numpy.void, a.dtype.itemsize*a.shape[1])))
    ).view(a.dtype).reshape(-1, a.shape[1])

---

Code to reproduce the plot:

import numpy
import perfplot


def unique_void_view(a):
    return numpy.unique(
        a.view(numpy.dtype((numpy.void, a.dtype.itemsize*a.shape[1])))
        ).view(a.dtype).reshape(-1, a.shape[1])


def lexsort(a):
    ind = numpy.lexsort(a.T)
    return a[ind[
        numpy.concatenate((
            [True], numpy.any(a[ind[1:]] != a[ind[:-1]], axis=1)
            ))
        ]]


def vstack(a):
    return numpy.vstack({tuple(row) for row in a})


def unique_axis(a):
    return numpy.unique(a, axis=0)


perfplot.show(
    setup=lambda n: numpy.random.randint(2, size=(n, 20)),
    kernels=[unique_void_view, lexsort, vstack, unique_axis],
    n_range=[2**k for k in range(15)],
    logx=True,
    logy=True,
    xlabel='len(a)',
    equality_check=None
    )