def sample_posterior(self):
""" sample the posterior distribution of the mortality probability """
# find values of mortality probability at which the posterior should be evaluated
self._mortalitySamples = np.random.uniform(low=CalibSets.POST_L,
high=CalibSets.POST_U,
size=CalibSets.POST_N)
# create a multi cohort
multiCohort = SurvivalCls.MultiCohort(
ids=self._cohortIDs,
mortality_probs=self._mortalitySamples,
pop_sizes=[CalibSets.SIM_POP_SIZE] * CalibSets.POST_N)
# simulate the multi cohort
multiCohort.simulate(CalibSets.TIME_STEPS)
# calculate the likelihood of each simulated cohort
for cohort_id in self._cohortIDs:
# get the average survival time for this cohort
mean = multiCohort.get_cohort_mean_survival(cohort_id)
#survivaltimes = multiCohort.get_survival_times(cohort_id)
fiveyearlist = multiCohort.get_five_year_survival(cohort_id)
fiveyearrate = sum(fiveyearlist) / CalibSets.OBS_N
# construct a gaussian likelihood
# with mean calculated from the simulated data and standard deviation from the clinical study.
# evaluate this pdf (probability density function) at the mean reported in the clinical study.
weight = stat.binom.pmf(k=CalibSets.OBS_FIVE_YEAR_RATE,
n=CalibSets.OBS_N,
p=fiveyearrate)
# store the weight
self._weights.append(weight)
# normalize the likelihood weights
sum_weights = np.sum(self._weights)
self._normalizedWeights = np.divide(self._weights, sum_weights)
# re-sample mortality probability (with replacement) according to likelihood weights
self._mortalityResamples = np.random.choice(
a=self._mortalitySamples,
size=CalibSets.NUM_SIM_COHORTS,
replace=True,
p=self._normalizedWeights)
# produce the list to report the results
for i in range(0, len(self._mortalitySamples)):
self._csvRows.append([
self._cohortIDs[i], self._normalizedWeights[i],
self._mortalitySamples[i]
])
# write the calibration result into a csv file
InOutSupport.write_csv('CalibrationResults.csv', self._csvRows)
def simulate(self,
num_of_simulated_cohorts,
cohort_size,
time_steps,
cohort_ids=None):
""" simulate the specified number of cohorts based on their associated likelihood weight
:param num_of_simulated_cohorts: number of cohorts to simulate
:param cohort_size: the population size of cohorts
:param time_steps: simulation length
:param cohort_ids: ids of cohort to simulate
"""
# resample cohort IDs and mortality probabilities based on their likelihood weights
# sample (with replacement) from indices [0, 1, 2, ..., number of weights] based on the likelihood weights
sampled_row_indices = np.random.choice(a=range(0, len(self._weights)),
size=num_of_simulated_cohorts,
replace=True,
p=self._weights)
# use the sampled indices to populate the list of cohort IDs and mortality probabilities
resampled_ids = []
resampled_probs = []
for i in sampled_row_indices:
resampled_ids.append(self._cohortIDs[i])
resampled_probs.append(self._mortalityProbs[i])
# simulate the desired number of cohorts
if cohort_ids is None:
# if cohort ids are not provided, use the ids stored in the calibration results
self._multiCohorts = SurvivalCls.MultiCohort(
ids=resampled_ids,
pop_sizes=[cohort_size] * num_of_simulated_cohorts,
mortality_probs=resampled_probs)
else:
# if cohort ids are provided, use them instead of the ids stored in the calibration results
self._multiCohorts = SurvivalCls.MultiCohort(
ids=cohort_ids,
pop_sizes=[cohort_size] * num_of_simulated_cohorts,
mortality_probs=resampled_probs)
# simulate all cohorts
self._multiCohorts.simulate(time_steps)
