def test_check_thresholds_gauss(self):
# check tau for various privacy parameters
epsilons = [0.1, 2.0]
max_contribs = [1, 3]
deltas = [10E-5, 10E-15]
query = "SELECT COUNT(*) FROM PUMS.PUMS GROUP BY married"
reader = PandasReader(df, schema)
qp = QueryParser(schema)
q = qp.query(query)
for eps in epsilons:
for d in max_contribs:
for delta in deltas:
# using slightly different formulations of same formula from different papers
# make sure private_reader round-trips
gaus_scale = math.sqrt(d) * math.sqrt(
2 * math.log(1.25 / delta)) / eps
gaus_rho = 1 + gaus_scale * math.sqrt(
2 * math.log(d / math.sqrt(2 * math.pi * delta)))
schema_c = copy.copy(schema)
schema_c["PUMS.PUMS"].max_ids = d
private_reader = PrivateReader(reader, schema_c, eps,
delta)
assert (private_reader._options.max_contrib == d)
r = private_reader.execute_ast(q)
assert (math.isclose(private_reader.tau,
gaus_rho,
rel_tol=0.03,
abs_tol=2))
def preprocess_df_from_query(schema, df, query_string):
"""
Returns a dataframe with user_id | tuple based on query grouping keys.
"""
qp = QueryParser(schema)
q = qp.query(query_string)
queries = qp.queries(query_string)
query_ast = queries[0]
group_cols = [ge.expression.name for ge in query_ast.agg.groupingExpressions]
table_name = q.source.find_node(Table).name
key_col = schema[table_name].key_cols()[0].name
preprocessed_df = pd.DataFrame()
preprocessed_df[key_col] = df[key_col]
preprocessed_df["group_cols"] = tuple(df[group_cols].values.tolist())
return preprocessed_df
