Merge branch 'dev' of hiplab/privacykit into master

README.md

@@ -3,6 +3,8 @@
 This framework computes re-identification risk of a dataset by extending pandas. It works like a pandas **add-on** 
 The framework will compute the following risk measures: marketer, prosecutor, journalist and pitman risk. References for the risk measures can be found on [http://ehelthinformation.ca] (http://www.ehealthinformation.ca/wp-content/uploads/2014/08/2009-De-identification-PA-whitepaper1.pdf) and [https://www.scb.se/contentassets](https://www.scb.se/contentassets/ff271eeeca694f47ae99b942de61df83/applying-pitmans-sampling-formula-to-microdata-disclosure-risk-assessment.pdf)
 
+
+
 There are two modes available :
     
 **explore:**
@@ -16,10 +18,10 @@ Here the assumption is that we are clear on the sets of attributes to be used an
 
 ### Four risk measures are computed :
 
-    - Marketer risk
-    - Prosecutor risk
-    - Journalist risk
-    - Pitman Risk
+- Marketer risk
+- Prosecutor risk
+- Journalist risk
+- Pitman Risk [Video tutorial,by Dr. Weiyi Xia](https://www.loom.com/share/173e109ecac64d37a54f09b103bc6681) and [Publication by Dr. Nobuaki Hoshino](https://www.scb.se/contentassets/ff271eeeca694f47ae99b942de61df83/applying-pitmans-sampling-formula-to-microdata-disclosure-risk-assessment.pdf)
 
 ### Usage:
 
@@ -27,19 +29,19 @@ Install this package using pip as follows :
 
 Stable :
     
-    pip install git+https://hiplab.mc.vanderbilt.edu/git/steve/deid-risk.git
+    pip install git+https://dev.the-phi.com/git/healthcareio/privacykit.git@release
     
     
 Latest Development (not fully tested):
     
-    pip install git+https://hiplab.mc.vanderbilt.edu/git/steve/deid-risk.git@risk
+    pip install git+https://dev.the-phi.com/git/healthcareio/privacykit.git@dev
     
 The framework will depend on pandas and numpy (for now). Below is a basic sample to get started quickly.
 
 
     import numpy as np
     import pandas as pd
-    import risk
+    import privacykit
 
     mydf = pd.DataFrame({"x":np.random.choice( np.random.randint(1,10),50),"y":np.random.choice( np.random.randint(1,10),50),"z":np.random.choice( np.random.randint(1,10),50),"r":np.random.choice( np.random.randint(1,10),50)  })
     print (mydf.risk.evaluate())

privacykit/risk.py

@@ -43,6 +43,10 @@ from datetime import datetime
 import sys
 
 from itertools import combinations
+# class Compute:
+#     pass
+# class Population(Compute):
+#     pass
 
 @pd.api.extensions.register_dataframe_accessor("risk")
 class deid :
@@ -57,6 +61,16 @@ class deid :
         #
         values = df.apply(lambda col: col.unique().size / df.shape[0])
         self._dinfo = dict(zip(df.columns.tolist(),values))
+        # self.sample = self._df
+        self.init(sample=self._df)
+    def init(self,**_args):
+        _sample = _args['sample'] if 'sample' in _args else self._df
+        _columns = [] if 'columns' not in _args else _args['columns']
+        if _columns :
+            self._compute = Compute(sample = _sample,columns=_columns)
+        else:
+            self._comput = Compute(sample=_sample)
+        self._pcompute= Population()  
 
     def explore(self,**args):
         """
@@ -107,40 +121,45 @@ class deid :
         for size in np.arange(2,len(columns)) :
             p = list(combinations(columns,size))            
             p = (np.array(p)[ np.random.choice( len(p), _policy_count)].tolist())
-            flag = 'Policy_'+str(_index)
-            _index += 1
+            
+            
             for cols in p :
+                flag = 'Policy_'+str(_index)
                 r = self.evaluate(sample=sample,cols=cols,flag = flag)
                 p =  pd.DataFrame(1*sample.columns.isin(cols)).T
                 p.columns = sample.columns
                 o = pd.concat([o,r.join(p)])
-        
-           
-        # for i in np.arange(RUNS):
-        #     if 'strict' not in args or ('strict' in args and args['strict'] is False):
-        #         n = np.random.randint(2,k)
-        #     else:
-        #         n = args['field_count']
-        #     cols = np.random.choice(columns,n,replace=False).tolist()            
-        #     params = {'sample':sample,'cols':cols}
-        #     if pop is not None :
-        #         params['pop'] = pop
-        #     if pop_size > 0  :
-        #         params['pop_size'] = pop_size
 
-        #     r = self.evaluate(**params)
-        #     #
-        #     # let's put the policy in place
-        #     p =  pd.DataFrame(1*sample.columns.isin(cols)).T
-        #     p.columns = sample.columns
-        #     # o = o.append(r.join(p))
-        #     o = pd.concat([o,r.join(p)])
+                o['attributes'] = ','.join(cols)
+                # o['attr'] = ','.join(r.apply())
+                _index += 1
+        #
+        # We rename flags to policies and adequately number them, we also have a column to summarize the attributes attr
+        #
+           
+      
 
             
         o.index = np.arange(o.shape[0]).astype(np.int64)
-
+        o = o.rename(columns={'flag':'policies'})
         return o
-    def evaluate(self, **args):
+    def evaluate(self,**_args):
+        _measure = {}
+
+        self.init(**_args)
+        _names = ['marketer','journalist','prosecutor'] #+ (['pitman'] if 'pop_size' in _args else [])
+        for label in _names :
+            _pointer = getattr(self,label)
+            _measure[label] = _pointer(**_args)
+        
+        _measure['fields'] = self._compute.cache['count']['fields']
+        _measure['groups'] = self._compute.cache['count']['groups']
+        _measure['rows'] = self._compute.cache['count']['rows']
+        if 'attr' in _args :
+            _measure = dict(_args['attr'],**_measure)
+
+        return pd.DataFrame([_measure])
+    def _evaluate(self, **args):
         """
         This function has the ability to evaluate risk associated with either a population or a sample dataset
         :sample sample dataset
@@ -170,7 +189,7 @@ class deid :
         r = {"flag":flag}
         # if sample :
         
-        handle_sample   = Sample()        
+        handle_sample   = Compute()        
         xi              = sample.groupby(cols,as_index=False).count().values
         
         handle_sample.set('groups',xi)
@@ -226,7 +245,83 @@ class deid :
         #
         r['field count'] = len(cols)
         return pd.DataFrame([r])
+    
+    def marketer(self,**_args):
+        """
+        This function delegates the calls to compute marketer risk of a given dataset or sample
+        :sample     optional sample dataset
+        :columns    optional columns of the dataset, if non is provided and inference will be made using non-unique columns
+        """
+        if 'pop' not in _args :
+            if not 'sample' in _args and not 'columns' in _args :
+                # _handler =  self._compute
+                pass
+            else:
+                
+                self.init(**_args)
+                # _handler = Compute(**_args)
+            _handler =  self._compute
 
+        else:
+            #
+            # Computing population estimates for the population
+            self._pcompute.init(**_args)
+            handler = self._pcompute
+        return _handler.marketer()
+    def journalist(self,**_args):
+        """
+        This function delegates the calls to compute journalist risk of a given dataset or sample
+        :sample     optional sample dataset
+        :columns    optional columns of the dataset, if non is provided and inference will be made using non-unique columns
+        """
+        if 'pop' not in _args :
+            if not 'sample' in _args and not 'columns' in _args :
+                _handler =  self._compute
+            else:
+                self.init(**_args)
+                # _handler = Compute(**_args)
+            _handler = self._compute
+                # return _compute.journalist()
+        else:
+            self._pcompute.init(**_args)
+            _handler = self._pcompute
+        return _handler.journalist()
+    def prosecutor(self,**_args):
+        """
+        This function delegates the calls to compute prosecutor risk of a given dataset or sample
+        :sample     optional sample dataset
+        :columns    optional columns of the dataset, if non is provided and inference will be made using non-unique columns
+        """
+        if 'pop' not in _args :
+            if not 'sample' in _args and not 'columns' in _args :
+                # _handler =  self._compute
+                pass
+            else:
+                self.init(**_args)
+                # _handler = Compute(**_args)
+            _handler =  self._compute
+                
+        else:
+            self._pcompute.init(**_args)
+            _handler = self._pcompute
+        return _handler.prosecutor()
+    def pitman(self,**_args):
+        
+        if 'population' not in _args :
+            pop_size = int(_args['pop_size'])
+            self._compute.set('pop_size',pop_size)
+            _handler =  self._compute;
+        else:
+            self._pcompute.init(**_args)
+            _handler = self._pcompute
+        
+        return _handler.pitman()
+        
+        # xi = pd.DataFrame({"sample_group_size":sample.groupby(cols,as_index=False).count()}).reset_index()
+        # yi = pd.DataFrame({"population_group_size":args['pop'].groupby(cols,as_index=False).size()}).reset_index()
+        # merged_groups = pd.merge(xi,yi,on=cols,how='inner')
+        # handle_population= Population()            
+        # handle_population.set('merged_groups',merged_groups)
 class Risk :
     """
     This class is an abstraction of how we chose to structure risk computation i.e in 2 sub classes:
@@ -240,24 +335,44 @@ class Risk :
             self.cache[id] = {}
         self.cache[key] = value
 
-class Sample(Risk):
+class Compute(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 __init__(self,**_args):
+        super().__init__()
+        self._sample = _args['sample'] if 'sample' in _args else pd.DataFrame()
+        self._columns= _args['columns'] if 'columns' in _args else None
+        self.cache['count']  = {'groups':0,'fields':0,'rows':0}
+        if not self._columns :
+            values = self._sample.apply(lambda col: col.unique().size / self._sample.shape[0])            
+            self._dinfo = dict(zip(self._sample.columns.tolist(),values))
+            self._columns = [key for key in self._dinfo if self._dinfo[key] < 1]
+        #
+        # At this point we have all the columns that are valid candidates even if the user didn't specify them
+        self.cache['count']['fields'] = len(self._columns)
+        if self._sample.shape[0] > 0 and self._columns:
+            _sample = _args ['sample']
+            _groups = self._sample.groupby(self._columns,as_index=False).count().values
+            self.set('groups',_groups)
+    
+            self.cache['count']['groups']  = len(_groups)
+            self.cache['count']['rows']    = np.sum([_g[-1] for _g in _groups])
+            
     def marketer(self):
         """
         computing marketer risk for sample dataset
         """
         
-            
+        
         groups = self.cache['groups']
         # group_count = groups.size
         # row_count   = groups.sum()
-        group_count = len(groups)
-        row_count = np.sum([_g[-1] for _g in groups])
+        # group_count = len(groups)
+        group_count = self.cache['count']['groups']
+        # row_count = np.sum([_g[-1] for _g in groups])
+        row_count = self.cache['count']['rows']
         return group_count / np.float64(row_count)
 
     def prosecutor(self):
@@ -272,40 +387,52 @@ class Sample(Risk):
     def unique_ratio(self):
         groups = self.cache['groups']        
         # row_count = groups.sum()
-        row_count = np.sum([_g[-1] for _g in groups])
+        # row_count = np.sum([_g[-1] for _g in groups])
+        row_count = self.cache['count']['rows']
         # return groups[groups == 1].sum() / np.float64(row_count)
         values = [_g[-1] for _g in groups if _g[-1] == 1]
         
         return np.sum(values) / np.float64(row_count)
-
+    def journalist(self):
+        return self.unique_ratio()
     def pitman(self):
         """
         This function will approximate pitman de-identification risk based on pitman sampling
         """
+        
         groups = self.cache['groups']
+        print (self.cache['pop_size'])
         si = groups[groups == 1].size
         # u = groups.size
         u = len(groups)
         alpha = np.divide(si , np.float64(u) )
-        row_count = np.sum([_g[-1] for _g in groups])
+        # row_count = np.sum([_g[-1] for _g in groups])
+        row_count = self.cache['count']['rows']
+
         # f = np.divide(groups.sum(), np.float64(self.cache['pop_size']))
         f = np.divide(row_count, np.float64(self.cache['pop_size']))
         return np.power(f,1-alpha)
 
-class Population(Sample):
+class Population(Compute):
     """
     This class will compute risk for datasets that have population information or datasets associated with them.
     This computation includes pitman risk (it requires minimal information about population)
     """
-    def __init__(self,**args):
-        Sample.__init__(self)
+    def __init__(self,**_args):
+        super().__init__(**_args)
+
+    def init(self,**_args):
+        xi = pd.DataFrame({"sample_group_size":self._sample.groupby(self._columns,as_index=False).count()}).reset_index()
+        yi = pd.DataFrame({"population_group_size":_args['population'].groupby(self._columns,as_index=False).size()}).reset_index()
+        merged_groups = pd.merge(xi,yi,on=self._columns,how='inner')                   
+        self.set('merged_groups',merged_groups)
 
     def set(self,key,value):
-        Sample.set(self,key,value)
+        self.set(self,key,value)
         if key == 'merged_groups' :  
                
-            Sample.set(self,'pop_size',np.float64(value.population_group_size.sum()) )
-            Sample.set(self,'groups',value.sample_group_size)
+            self.set(self,'pop_size',np.float64(value.population_group_size.sum()) )
+            self.set(self,'groups',value.sample_group_size)
     """
     This class will measure risk and account for the existance of a population
     :merged_groups {sample_group_size, population_group_size} is a merged dataset with group sizes of both population and sample
@@ -314,6 +441,7 @@ class Population(Sample):
         """
         This function requires
         """
+        
         r = self.cache['merged_groups']
         sample_row_count = r.sample_group_size.sum() 
         #

setup.py

@@ -4,11 +4,11 @@ This is a build file for the
 from setuptools import setup, find_packages
  
 setup(
-    name = "risk",
-    version = "0.8.1",
+    name = "privacykit",
+    version = "0.9.0",
     author = "Healthcare/IO - The Phi Technology LLC & Health Information Privacy Lab",
     author_email = "info@the-phi.com",
     license = "MIT",
-    packages=['risk'],
+    packages=['privacykit'],
     install_requires = ['numpy','pandas']
     )