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

Merge branch 'master' into dev

This commit is contained in:
Steve Nyemba 2019-03-08 18:28:59 -06:00
parent 5e453f8371 cfd9fffc7e
commit f1020e8169
2 changed files with 14 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
risk/__init__.py
View File

@ -66,4 +66,8 @@ Basic examples that illustrate usage of the the framework are in the notebook fo
""" """
from risk import deid import sys
if sys.version_info.major == 2:
from risk import deid
else:
from risk.risk import deid

12
risk/risk.py
View File

@ -57,8 +57,10 @@ class deid :
This function will perform experimentation by performing a random policies (combinations of attributes) This function will perform experimentation by performing a random policies (combinations of attributes)
This function is intended to explore a variety of policies and evaluate their associated risk. This function is intended to explore a variety of policies and evaluate their associated risk.
@param pop|sample data-frame with popublation reference :pop|sample data-frame with population or sample reference
@param id key field that uniquely identifies patient/customer ... :field_count number of fields to randomly select
:strict if set the field_count is exact otherwise field_count is range from 2-field_count
:num_runs number of runs (by default 5)
""" """
pop= args['pop'] if 'pop' in args else None pop= args['pop'] if 'pop' in args else None
@ -76,7 +78,7 @@ class deid :
sample = args['sample'] if 'sample' in args else pd.DataFrame(self._df) sample = args['sample'] if 'sample' in args else pd.DataFrame(self._df)
k = sample.columns.size if 'field_count' not in args else int(args['field_count']) + 1 k = sample.columns.size if 'field_count' not in args else int(args['field_count']) +1
if 'id' in args : if 'id' in args :
id = args['id'] id = args['id']
columns = list(set(sample.columns.tolist()) - set([id])) columns = list(set(sample.columns.tolist()) - set([id]))
@ -85,8 +87,10 @@ class deid :
o = pd.DataFrame() o = pd.DataFrame()
for i in np.arange(RUNS): 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) n = np.random.randint(2,k)
else:
n = args['field_count']
cols = np.random.choice(columns,n,replace=False).tolist() cols = np.random.choice(columns,n,replace=False).tolist()
params = {'sample':sample,'cols':cols} params = {'sample':sample,'cols':cols}
if pop is not None : if pop is not None :