def get_obj_value(self, x, seed_index=0):
""" returns one realization from x^2+noise """
# create a random number generator
rng = RVGs.RNG(seed=seed_index)
accum_penalty = 0 # accumulated penalty
# test the feasibility
if x[1] < 1:
accum_penalty += self._penalty * pow(x[1] - 1, 2)
x[1] = 1
return (x[0] + 1) * (x[0] + 1) + x[1] * x[1] + self._err.sample(
rng) + accum_penalty
import SimPy.RandomVariateGenerators as rndSupport
from tests.ProbDistributions import RVGtests as Tests
# use numpy random number generator
rng = rndSupport.RNG(1)
print('')
# tests
Tests.test_rng(rng)
Tests.test_bernoulli(rng, p=.2)
Tests.test_beta(rng, a=2, b=5, loc=1, scale=2)
Tests.test_beta(rng, a=0.2, b=0.1, loc=0.5, scale=0.25)
Tests.test_beta_binomial(rng, n=100, a=2, b=3, loc=1)
Tests.test_binomial(rng, n=1000, p=.2, loc=1)
Tests.test_dirichlet(rng, a=[1, 2, 3])
Tests.test_empirical(rng, prob=[0.2, 0.3, 0.5])
Tests.test_exponential(rng, scale=10, loc=1)
Tests.test_gamma(rng, a=2, scale=4, loc=1)
Tests.test_gamma_poisson(rng, a=2, gamma_scale=5, loc=1)
Tests.test_geometric(rng, p=.2, loc=1)
Tests.test_johnsonsb(rng, a=10, b=5, loc=10, scale=100)
Tests.test_johnsonsu(rng, a=10, b=3, loc=1, scale=2)
Tests.test_lognormal(rng, mu=0.2, sigma=0.1, loc=1)
Tests.test_multinomial(rng, n=100, pvals=[.2, 0.3, 0.5])
Tests.test_negative_binomial(rng, n=10, p=.2, loc=1)
Tests.test_non_homogeneous_exponential(rng, rates=[1, 1])
Tests.test_normal(rng, loc=5, scale=1.2)
Tests.test_poisson(rng, mu=2)
Tests.test_triangular(rng, c=0.2, loc=6, scale=7)
Tests.test_uniform(rng, loc=2, scale=7)
def get_obj_value(self, x, seed_index=0):
""" returns one realization from x^2+noise """
# create a random number generator
rng = RVGs.RNG(seed=seed_index)
return (x[0] + 1) * (x[0] + 1) + x[1] * x[1] + self._err.sample(rng)
[55, 1, 0.035], # 55-59, female
[60, 0, 0.029], # 60-64, male
[60, 1, 0.031], # 60-64, female
[65, 0, 0.024], # 65-69, male
[65, 1, 0.027], # 65-69, female
[70, 0, 0.018], # 70-74, male
[70, 1, 0.027], # 70-74, female
[75, 0, 0.012], # 75-79, male
[75, 1, 0.015], # 75-79, female
[80, 0, 0.008], # 80-84, male
[80, 1, 0.011], # 80-84, female
[85, 0, 0.007], # >= 85, male
[85, 1, 0.013] # >= 85, female
]
rng = RVGs.RNG(seed=1)
probDf = df.DataFrameWithEmpiricalDist(rows=rows,
list_x_min=[0, 0],
list_x_max=[85, 1],
list_x_delta=[5, 'int'])
# get a sample
print('Get a sampled index:', probDf.sample_indices(rng=rng))
print('Get a sampled index:', probDf.sample_values(rng=rng))
print('')
# testing to make sure sample by index works
counts = [0] * len(rows)
for i in range(5000):
idx = probDf.sample_indices(rng=rng)
counts[idx[0] * 2 + idx[1]] += 1
