hiplab/privacykit
hiplab
/
privacykit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

adding simple assessment of a table in a single run given a list of quasi identifiers

This commit is contained in:
Steve L. Nyemba -- The Architect 2018-10-02 12:00:23 -05:00
parent 8807a4ef49
commit cb58675cd3
1 changed files with 34 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
src/pandas_risk.py
View File

@ -35,24 +35,31 @@ class deid :
""" """
@param id name of patient field @param id name of patient field
@params num_runs number of runs (default will be 100) @params num_runs number of runs (default will be 100)
@params quasi_id list of quasi identifiers to be used (this will only perform a single run)
""" """
id = args['id'] id = args['id']
if 'quasi_id' in args :
num_runs = 1
columns = list(set(args['quasi_id'])- set(id) )
else :
num_runs = args['num_runs'] if 'num_runs' in args else 100 num_runs = args['num_runs'] if 'num_runs' in args else 100
columns = list(set(self._df.columns) - set([id]))
r = pd.DataFrame() r = pd.DataFrame()
columns = list(set(self._df.columns) - set([id]))
k = len(columns) k = len(columns)
for i in range(0,num_runs) : for i in range(0,num_runs) :
# #
# let's chose a random number of columns and compute marketer and prosecutor risk # let's chose a random number of columns and compute marketer and prosecutor risk
# Once the fields are selected we run a groupby clause # Once the fields are selected we run a groupby clause
# #
if 'quasi_id' not in args :
n = np.random.randint(2,k) #-- number of random fields we are picking n = np.random.randint(2,k) #-- number of random fields we are picking
ii = np.random.choice(k,n,replace=False) ii = np.random.choice(k,n,replace=False)
cols = np.array(columns)[ii].tolist() cols = np.array(columns)[ii].tolist()
else:
cols = columns
n = len(cols)
x_ = self._df.groupby(cols).count()[id].values x_ = self._df.groupby(cols).count()[id].values
r = r.append( r = r.append(
pd.DataFrame( pd.DataFrame(
@ -72,20 +79,22 @@ class deid :
return r return r
# import pandas as pd import pandas as pd
# import numpy as np import numpy as np
# from io import StringIO from io import StringIO
# csv = """ csv = """
# id,sex,age,profession,drug_test id,sex,age,profession,drug_test
# 1,M,37,doctor,- 1,M,37,doctor,-
# 2,F,28,doctor,+ 2,F,28,doctor,+
# 3,M,37,doctor,- 3,M,37,doctor,-
# 4,M,28,doctor,+ 4,M,28,doctor,+
# 5,M,28,doctor,- 5,M,28,doctor,-
# 6,M,37,doctor,- 6,M,37,doctor,-
# """ """
# f = StringIO() f = StringIO()
# f.write(unicode(csv)) f.write(unicode(csv))
# f.seek(0) f.seek(0)
# df = pd.read_csv(f) df = pd.read_csv(f)
# print df.deid.risk(id='id',num_runs=2) print df.deid.risk(id='id',num_runs=2)
print " *** "
print df.deid.risk(id='id',quasi_id=['sex','age','profession'])