def _get_thresholds(stratifications: List[Tuple], means: pd.DataFrame,
sds: pd.DataFrame, weights_df: pd.DataFrame,
draw: int) -> pd.Series:
col = f'draw_{draw}'
thresholds = pd.Series(0, index=means.index, name=col)
ts = time.time()
print(f'Start: {ts}')
for i, stratification in enumerate(stratifications):
mu = means.loc[stratification, col]
sigma = sds.loc[stratification, col]
threshold = 0
if mu and sigma:
weights = weights_df.loc[stratification].reset_index()
weights = (weights[weights['parameter'] != 'glnorm'].
loc[:, ['parameter', 'value']].set_index(
'parameter').to_dict()['value'])
weights = {k: [v] for k, v in weights.items()}
ens_dist = EnsembleDistribution(weights=weights, mean=mu, sd=sigma)
threshold = minimize(lambda x: (ens_dist.ppf(x) - 7)**2, [0.5],
bounds=Bounds(0, 1.0),
method='Nelder-Mead').x[0]
print(f'mu: {mu}, sigma: {sigma}, threshold: {threshold}')
thresholds.loc[stratification] = threshold
tf = time.time()
print(f'End: {tf}')
print(f'Duration: {tf - ts}')
return thresholds
def find_rr(weights,
mean,
standard_dev,
attributable_fraction,
sample_size=10000):
target = 1 / (1 - attributable_fraction)
dist = EnsembleDistribution(weights, mean=mean, sd=standard_dev)
q = .98 * np.random.random(sample_size) + 0.01
x_ = dist.ppf(q)
def loss(guess):
y = np.maximum(x_ - tmrel, 0) / scale
mean_rr = 1 / sample_size * np.sum(guess**y)
return (mean_rr - target)**2
return optimize.minimize(loss, 2)