def test_group_by_exact_order_expr_desc(self):
reader = PandasReader(df, schema)
rs = reader.execute(
"SELECT COUNT(*) * 5 AS c, married AS m FROM PUMS.PUMS GROUP BY married ORDER BY c DESC"
)
assert (rs[1][0] == 549 * 5)
assert (rs[2][0] == 451 * 5)
def run_agg_query(self, df, metadata, query, confidence, get_exact=True):
"""
Run the query using the private reader and input query
Get query response back
"""
reader = PandasReader(df, metadata)
actual = 0.0
# VAR not supported in Pandas Reader. So not needed to fetch actual on every aggregation
if (get_exact):
actual = reader.execute(query)[1:][0][0]
private_reader = PrivateReader(reader, metadata, self.epsilon)
query_ast = private_reader.parse_query_string(query)
noisy_values = []
low_bounds = []
high_bounds = []
for idx in range(self.repeat_count):
res = private_reader._execute_ast(query_ast, True)
# Disabled because confidence interval not available in report
#interval = res.report[res.colnames[0]].intervals[confidence]
#low_bounds.append(interval[0].low)
#high_bounds.append(interval[0].high)
noisy_values.append(res[1:][0][0])
return np.array(noisy_values), actual, low_bounds, high_bounds
def test_empty_result_typed(self):
reader = PandasReader(df, schema)
rs = reader.execute("SELECT age as a FROM PUMS.PUMS WHERE age > 100")
trs = reader._to_df(rs)
assert(len(trs) == 0)
def test_empty_result(self):
reader = PandasReader(df, schema)
rs = reader.execute("SELECT age as a FROM PUMS.PUMS WHERE age > 100")
assert(len(rs) == 1)
def test_count_exact(self):
reader = PandasReader(df, schema)
rs = reader.execute("SELECT COUNT(*) AS c FROM PUMS.PUMS")
assert(rs[1][0] == 1000)
def run_agg_query_df(self,
df,
metadata,
query,
confidence,
file_name="d1"):
"""
Run the query using the private reader and input query
Get query response back for multiple dimensions and aggregations
"""
# Getting exact result
reader = PandasReader(df, metadata)
exact_res = reader.execute(query)[1:]
private_reader = PrivateReader(reader, metadata, self.epsilon)
query_ast = private_reader.parse_query_string(query)
# Distinguishing dimension and measure columns
sample_res = private_reader._execute_ast(query_ast, True)
headers = sample_res[0]
dim_cols = []
num_cols = []
out_syms = query_ast.all_symbols()
out_types = [s[1].type() for s in out_syms]
out_col_names = [s[0] for s in out_syms]
for col, ctype in zip(out_col_names, out_types):
if (ctype == "string"):
dim_cols.append(col)
else:
num_cols.append(col)
# Repeated query and store results
res = []
for idx in range(self.repeat_count):
dim_rows = []
num_rows = []
singleres = private_reader._execute_ast_df(query_ast, True)
#values = singleres[col]
for col in dim_cols:
dim_rows.append(singleres[col].tolist())
for col in num_cols:
values = singleres[col].tolist()
num_rows.append(list(zip(values)))
res.extend(list(zip(*dim_rows, *num_rows)))
exact_df = pd.DataFrame(exact_res, columns=headers)
noisy_df = pd.DataFrame(res, columns=headers)
# Add a dummy dimension column for cases where no dimensions available for merging D1 and D2
if (len(dim_cols) == 0):
dim_cols.append("__dim__")
if (dim_cols[0] == "__dim__"):
exact_df[dim_cols[0]] = ["key"] * len(exact_df)
noisy_df[dim_cols[0]] = ["key"] * len(noisy_df)
return noisy_df, exact_df, dim_cols, num_cols
