mtrand.pyx error

[pamdla]

import numpy as np

from pymoo.algorithms.moo.nsga3 import NSGA3
from pymoo.factory import get_problem, get_reference_directions
from pymoo.optimize import minimize
from pymoo.problems.multi import TNK
from pymoo.visualization.scatter import Scatter
from pysamoo.algorithms.gpsaf import GPSAF

problem = TNK()

ref_dirs = get_reference_directions("das-dennis", 2, n_points=20)

# create the algorithm object

## 1
algorithm = NSGA3(pop_size=20,
                  n_offsprings=10,
                  ref_dirs=ref_dirs)

## 2
algorithm = GPSAF(algorithm,
                  alpha=10,
                  beta=50,
                  n_max_doe=100,
                  )

## 3
res = minimize(
    problem,
    algorithm,
    ('n_evals', 200),
    seed=1,
    verbose=True)

The full example codes are above.

When I test ##1 with ##3 there is no error, but if continuing using ##2 after ##1, then ##3 will prompt error like this:

File "mtrand.pyx", line 950, in numpy.random.mtrand.RandomState.choice
ValueError: 'a' cannot be empty unless no samples are taken

The install numpy is 1.25.1, then I reinstall numpy to 1.20.0, still the error is there.

any suggestion?

[blankjul]

what pymoo version are you using? Does the error also occur with only NSGA2?

[blankjul]

Feel free to repost in the pysamoo framework as this is related to GPSAF.