def test_mcmc_random_seed(stan_model, two_group_sample_data):
y1, y2 = two_group_sample_data
mcmc1 = get_mcmc(stan_model, y1, y2, rand_seed=1).extract()
mcmc2 = get_mcmc(stan_model, y1, y2, rand_seed=1).extract()
np.testing.assert_equal(mcmc1, mcmc2)
def test_mcmc_aggregation(stan_model, two_group_sample_data):
y1, y2 = two_group_sample_data
w1 = w2 = 6 * [2]
mcmc_short = get_mcmc(stan_model, y1, y2, w1=w1, w2=w2, rand_seed=1)
mcmc_long = get_mcmc(stan_model, 2 * y1, 2 * y2, rand_seed=1)
for parameter in mcmc_short.extract().keys():
assert np.isclose(mcmc_short.extract()[parameter],
mcmc_long.extract()[parameter]).all()
def fit(self, y1, y2, w1=None, w2=None):
self.mcmc_ = get_mcmc(self.model, y1, y2, w1, w2, **self.kwargs)
self.data_ = az.from_pystan(
posterior=self.mcmc_,
posterior_predictive=['y1_pred', 'y2_pred'],
observed_data=['y1', 'y2'],
log_likelihood='log_lik',
coords={
'group_mu': ['Group 1', 'Group 2'],
'group_sigma': ['Group 1', 'Group 2']
},
dims={
'mu': ['group_mu'],
'sigma': ['group_sigma']
})
def test_mcmc(stan_model, two_group_sample_data):
y1, y2 = two_group_sample_data
mcmc = get_mcmc(stan_model, y1, y2, rand_seed=1)
row_ind_1 = list(mcmc.summary()['summary_rownames']).index('mu[1]')
row_ind_2 = list(mcmc.summary()['summary_rownames']).index('mu[2]')
col_ind_m = list(mcmc.summary()['summary_colnames']).index('mean')
col_ind_rh = list(mcmc.summary()['summary_colnames']).index('Rhat')
assert np.isclose(mcmc.summary()['summary'][row_ind_1, col_ind_m],
np.mean(y1),
atol=0.1)
assert np.isclose(mcmc.summary()['summary'][row_ind_2, col_ind_m],
np.mean(y2),
atol=0.1)
assert np.isclose(mcmc.summary()['summary'][:, col_ind_rh], 1.0,
atol=0.1).all()
import numpy as np from bab.mcmc import get_mcmc, get_stan_model from bab.make_data import make_data from bab.power import get_power from bab.model import BayesAB y1, y2 = make_data(0, 1, 1, 2, 10, percent_outliers=0, sd_outlier_factor=2.0, rand_seed=1) stan_model = get_stan_model() mcmc = get_mcmc(stan_model, y1, y2) get_power(stan_model, y1, y2, (-1., 1.), (0., 1.), 1., 1., n_sim=10) model = BayesAB() model.fit(2 * np.random.randn(10) + 3, np.random.randn(10))
def get_power(stan_model,
y1,
y2,
rope_m,
rope_sd,
max_hdi_width_m,
max_hdi_width_sd,
cred_mass=0.95,
n_sim=200,
precision=2,
rand_seed=None):
"""
:param stan_model: StanModel instance
:param y1: iterable, prospective samples of group one
:param y2: iterable, prospective samples of group two
:param rope_m: iterable, of length two, such as (-1, 1),
specifying the limit of the ROPE on the difference of means.
:param rope_sd: iterable, of length two, such as (-1, 1),
specifying the limit of the ROPE on the difference of standard deviations.
:param max_hdi_width_m: float, maximum desired width of the 95% HDI on the difference of means.
:param max_hdi_width_sd: float, maximum desired width of the 95% HDI on the difference of standard deviations.
:param cred_mass: (optional) float, fraction of credible mass.
:param n_sim: (optional) int, number of simulated experiments used to estimate the power.
:param precision: (optional) int, number of decimals to round the power statistics to.
:param rand_seed: int (optional), random seed
:return: power, dict
"""
if rand_seed is not None:
np.random.seed(int(rand_seed))
sample_size = len(y1)
mcmc_chain = get_mcmc(stan_model, y1, y2, rand_seed=rand_seed).extract()
step_idx = _get_step_indices(mcmc_chain, n_sim)
goal_tally = {
'HDIm > ROPE': 0,
'HDIm < ROPE': 0,
'HDIm in ROPE': 0,
'HDIm width < max': 0,
'HDIsd > ROPE': 0,
'HDIsd < ROPE': 0,
'HDIsd in ROPE': 0,
'HDIsd width < max': 0
}
power = {
'HDIm > ROPE': [0, 0, 0],
'HDIm < ROPE': [0, 0, 0],
'HDIm in ROPE': [0, 0, 0],
'HDIm width < max': [0, 0, 0],
'HDIsd > ROPE': [0, 0, 0],
'HDIsd < ROPE': [0, 0, 0],
'HDIsd in ROPE': [0, 0, 0],
'HDIsd width < max': [0, 0, 0]
}
n_sim = 0
for step in step_idx:
n_sim += 1
y1_sim, y2_sim = _generate_simulated_data(mcmc_chain, sample_size,
step)
sim_chain = get_mcmc(stan_model, y1_sim, y2_sim,
rand_seed=rand_seed).extract()
goal_tally = _update_goal_tally(goal_tally, max_hdi_width_m,
max_hdi_width_sd, rope_m, rope_sd,
sim_chain)
_assess_and_tally_goals(cred_mass, goal_tally, n_sim, power)
_log_progress(n_sim, power, step_idx)
for k, v in power.items():
power[k] = [round(e, precision) for e in v]
return power