Class SampleAggregator

libpgm/sampleaggregator.py:31–108

This class is a machine for aggregating data from sample sequences. It contains the method *aggregate*.

class SampleAggregator(object):
    '''
    This class is a machine for aggregating data from sample sequences. It contains the method *aggregate*.
    
    '''
    def __init__(self):
        self.seq = None
        '''The sequence inputted.'''
        self.avg = None
        '''The average of all the entries in *seq*, represented as a dict where each vertex has an entry whose value is a dict of {key, value} pairs, where each key is a possible outcome of that vertex and its value is the approximate frequency.'''


    def aggregate(self, samplerstatement):
        '''
        Generate a sequence of samples using *samplerstatement* and return the average of its results. 
        
        Arguments:
            1. *samplerstatement* -- The statement of a function (with inputs) that would output a sequence of samples. For example: ``bn.randomsample(50)`` where ``bn`` is an instance of the :doc:`DiscreteBayesianNetwork <discretebayesiannetwork>` class.
        
        This function stores the output of *samplerstatement* in the attribute *seq*, and then averages *seq* and stores the approximate distribution found in the attribute *avg*. It then returns *avg*. 
       
        Usage example: this would print the average of 10 data points::

            import json

            from libpgm.nodedata import NodeData
            from libpgm.graphskeleton import GraphSkeleton
            from libpgm.discretebayesiannetwork import DiscreteBayesianNetwork
            from libpgm.sampleaggregator import SampleAggregator

            # load nodedata and graphskeleton
            nd = NodeData()
            skel = GraphSkeleton()
            nd.load("../tests/unittestdict.txt")
            skel.load("../tests/unittestdict.txt")

            # topologically order graphskeleton
            skel.toporder()

            # load bayesian network
            bn = DiscreteBayesianNetwork(skel, nd)

            # build aggregator
            agg = SampleAggregator()

            # average samples
            result = agg.aggregate(bn.randomsample(10))

            # output
            print json.dumps(result, indent=2)

        ''&#x27;
        
        # get sequence
        seq = samplerstatement
        
        # denominator
        denom = len(seq)