privacykit/risk/risk.py

"""
    Health Information Privacy Lab
    @TODO:
        sample = args['sample'] if 'sample' in args else pd.DataFrame(self._df)
        if not args  or 'cols' not in args:
            merged_groups = pd.merge(xi,yi,on=cols,how='inner')
            handle_population= Population()            
            handle_population.set('merged_groups',merged_groups)
            
            r['pop. marketer'] = handle_population.marketer()            
            r['pitman risk'] = handle_population.pitman()
            r['pop. group size'] = np.unique(yi.population_group_size).size
        #
        # At this point we have both columns for either sample,population or both
        #
        r['field count'] = len(cols)
        return pd.DataFrame([r])

class Risk :
    """
    This class is an abstraction of how we chose to structure risk computation i.e in 2 sub classes:
        - Sample        computes risk associated with a sample dataset only
        - Population    computes risk associated with a population
    """
    def __init__(self):
        self.cache = {}        
    def set(self,key,value):        
        if id not in self.cache :
            self.cache[id] = {}
        self.cache[key] = value

class Sample(Risk):
    """
    This class will compute risk for the sample dataset: the marketer and prosecutor risk are computed by default.
    This class can optionally add pitman risk if the population size is known.
    """
    def __init__(self):
        Risk.__init__(self)
    def marketer(self):

        sample_row_count = r.sample_group_size.sum() 
        #
        # @TODO : make sure the above line is size (not sum)
        # sample_row_count = r.sample_group_size.size
        return r.apply(lambda row: (row.sample_group_size / np.float64(row.population_group_size)) /np.float64(sample_row_count) ,axis=1).sum()