def calc_empirical_cdf(subject_answers, num_clusters):
"""Find fraction of subjects in each cluster. Add some mass to clusters with no subjects.
Args:
subject_answers: the cluster which each subject is in, i.e. the constructed answer the subject is endorsing.
num_clusters: number of possible clusters, since some clusters may be empty.
Returns:
list where each element is the (adjusted) fraction of subjects endorsing each constructed answer. Should sum to 1.
"""
num_occupying = [len(np.where(subject_answers == c)[0]) for c in range(num_clusters)]
num_occupying = jmutils.eliminate_zero_probs(num_occupying)
return num_occupying
def calc_predictions_cdf(meta_params, distribution_cdf, boundaries):
"""Calculate fraction of subjects each subject expects to fall within each answer. Ensures some prob mass in every cluster.
Args:
meta_parms: list where each element gives the induced parameters for each subject's meta distribution.
distribution_cdf: function which takes points to calculate cdf between and two parameters of distribution.
boundaries: list where each element is a tuple giving the lower and upper boundary for an answer.
Returns:
list where each sublist corresponds to a subject and gives the fraction of subjects expected to fall within each answer.
"""
predictions = []
for params in meta_params:
subject_predictions = [distribution_cdf(boundary[0], boundary[1], params[0], params[1]) for boundary in boundaries]
subject_predictions = jmutils.eliminate_zero_probs(subject_predictions)
predictions.append(subject_predictions)
return predictions
