Why is posterior same as prior despite observing data?

Questions
2

Hi, it’s best to not use python if statements in PyMC

There are numerous ways to achieve what you want, here is one

with pm.Model() as model:
    weekend = pm.Bernoulli('weekend', 2/7)
    weekday_rate = 10
    weekend_rate = 3
    rate = weekend*weekend_rate + (1-weekend)*weekday_rate
    bus = pm.Poisson('buses', mu=rate, observed=4)
    trace = pm.sample(1000)

print('Is Weekday? {:.3f}'.format(np.mean(trace['weekend']==0)))
print('Is Weekend? {:.3f}'.format(np.mean(trace['weekend']==1)))
2 Likes