infer_bernoulli_bayes

Python_modules.mmcomplexity.infer_bernoulli_bayes(num_successes, num_trials, beta_prior=(1, 1))

Given num_trials independent observations from a Bernoulli random variable with num_successes successes, returns the posterior distribution over the Bernoulli parameter in the form of a Beta distribution. May take hyperparameters of a Beta distribution for the prior.

To compute the posterior, the sufficient statistics are updated.

Args:

num_successes (int): number of successes num_trials (int): number of observations beta_prior (tuple): corresponds to the usual parameters of a Beta distribution, a and b (or alpha, beta)

defaults to (1,1), which is a flat prior

Raises:

ValueError: if num_trials < num_successes or a hyperparameter is negative or num_trials < 0

Returns:

scipy.stats.beta: frozen distribution, see

doc.