def fit(self, data_instance):
# local
data = self._select_columns(data_instance)
n, normed = self._standardized(data)
self.local_corr = table_dot(normed, normed)
self.local_corr /= n
if self.model_param.cross_parties:
with SPDZ("pearson",
local_party=self.local_party,
all_parties=self.parties,
use_mix_rand=self.model_param.use_mix_rand) as spdz:
source = [normed, self.other_party]
if self.local_party.role == "guest":
x, y = FixedPointTensor.from_source(
"x", source[0]), FixedPointTensor.from_source(
"y", source[1])
else:
y, x = FixedPointTensor.from_source(
"y", source[0]), FixedPointTensor.from_source(
"x", source[1])
m1 = len(x.value.first()[1])
m2 = len(y.value.first()[1])
self.shapes.append(m1)
self.shapes.append(m2)
self.corr = spdz.dot(x, y, "corr").get() / n
else:
self.shapes.append(self.local_corr.shape[0])
self.parties = [self.local_party]
self._callback()
def fit(self, data_instance):
# local
data = self._select_columns(data_instance)
n, normed = self._standardized(data)
self.local_corr = table_dot(normed, normed)
self.local_corr /= n
if self.model_param.calc_local_vif:
self.local_vif = self._vif_from_pearson_matrix(self.local_corr)
self._summary["local_corr"] = self.local_corr.tolist()
self._summary["num_local_features"] = n
if self.model_param.cross_parties:
with SPDZ(
"pearson",
local_party=self.local_party,
all_parties=self.parties,
use_mix_rand=self.model_param.use_mix_rand,
) as spdz:
source = [normed, self.other_party]
if self.local_party.role == "guest":
x, y = (
FixedPointTensor.from_source("x", source[0]),
FixedPointTensor.from_source("y", source[1]),
)
else:
y, x = (
FixedPointTensor.from_source("y", source[0]),
FixedPointTensor.from_source("x", source[1]),
)
m1 = len(x.value.first()[1])
m2 = len(y.value.first()[1])
self.shapes.append(m1)
self.shapes.append(m2)
self.corr = spdz.dot(x, y, "corr").get() / n
self._summary["corr"] = self.corr.tolist()
self._summary["num_remote_features"] = (
m2 if self.local_party.role == "guest" else m1)
else:
self.shapes.append(self.local_corr.shape[0])
self.parties = [self.local_party]
self._callback()
self.set_summary(self._summary)
def fit(self, data_instance):
data = self._select_columns(data_instance)
n, normed = self._standardized(data)
self.local_corr = table_dot(normed, normed)
with SPDZ("pearson") as spdz:
source = [normed, self._other_party]
if self._local_party.role == "guest":
x, y = FixedPointTensor.from_source(
"x",
source[0]), FixedPointTensor.from_source("y", source[1])
else:
y, x = FixedPointTensor.from_source(
"y",
source[0]), FixedPointTensor.from_source("x", source[1])
m1 = len(x.value.first()[1])
m2 = len(y.value.first()[1])
self.shapes.append(m1)
self.shapes.append(m2)
self.corr = spdz.dot(x, y, "corr").get() / n
self.local_corr /= n
self._callback()
def _test_spdz(self):
table_list = []
table_int_data_x, table_float_data_x = None, None
table_int_data_y, table_float_data_y = None, None
if self.local_party.role == "guest":
table_int_data_x = session.parallelize(
self.int_data_x,
include_key=False,
partition=self.data_partition)
table_int_data_x = table_int_data_x.mapValues(
lambda x: np.array([x]))
table_float_data_x = session.parallelize(
self.float_data_x,
include_key=False,
partition=self.data_partition)
table_float_data_x = table_float_data_x.mapValues(
lambda x: np.array([x]))
else:
table_int_data_y = session.parallelize(
self.int_data_y,
include_key=False,
partition=self.data_partition)
table_int_data_y = table_int_data_y.mapValues(
lambda y: np.array([y]))
table_float_data_y = session.parallelize(
self.float_data_y,
include_key=False,
partition=self.data_partition)
table_float_data_y = table_float_data_y.mapValues(
lambda y: np.array([y]))
for tensor_type in ["numpy", "table"]:
table = PrettyTable()
table.set_style(ORGMODE)
field_name = [
"DataType", "One time consumption",
f"{self.data_num} times consumption", "relative acc",
"log2 acc", "operations per second"
]
self._summary["field_name"] = field_name
table.field_names = field_name
with SPDZ(local_party=self.local_party,
all_parties=self.parties) as spdz:
for op_type in self.op_test_list:
start_time = time.time()
for epoch in range(self.test_round):
LOGGER.info(
f"test spdz, tensor_type: {tensor_type}, op_type: {op_type}, epoch: {epoch}"
)
tag = "_".join([tensor_type, op_type, str(epoch)])
spdz.set_flowid(tag)
if self.local_party.role == "guest":
if tensor_type == "table":
if op_type.startswith("int"):
fixed_point_x = TableTensor.from_source(
"int_x_" + tag, table_int_data_x)
fixed_point_y = TableTensor.from_source(
"int_y_" + tag, self.other_party)
else:
fixed_point_x = TableTensor.from_source(
"float_x_" + tag, table_float_data_x)
fixed_point_y = TableTensor.from_source(
"float_y_" + tag, self.other_party)
else:
if op_type.startswith("int"):
fixed_point_x = NumpyTensor.from_source(
"int_x_" + tag, self.int_data_x)
fixed_point_y = NumpyTensor.from_source(
"int_y_" + tag, self.other_party)
else:
fixed_point_x = NumpyTensor.from_source(
"float_x_" + tag, self.float_data_x)
fixed_point_y = NumpyTensor.from_source(
"float_y_" + tag, self.other_party)
else:
if tensor_type == "table":
if op_type.startswith("int"):
fixed_point_y = TableTensor.from_source(
"int_y_" + tag, table_int_data_y)
fixed_point_x = TableTensor.from_source(
"int_x_" + tag, self.other_party)
else:
fixed_point_y = TableTensor.from_source(
"float_y_" + tag, table_float_data_y)
fixed_point_x = TableTensor.from_source(
"float_x_" + tag, self.other_party)
else:
if op_type.startswith("int"):
fixed_point_y = NumpyTensor.from_source(
"int_y_" + tag, self.int_data_y)
fixed_point_x = NumpyTensor.from_source(
"int_x_" + tag, self.other_party)
else:
fixed_point_y = NumpyTensor.from_source(
"float_y_" + tag, self.float_data_y)
fixed_point_x = NumpyTensor.from_source(
"float_x_" + tag, self.other_party)
ret = self.calculate_ret(op_type, tensor_type,
fixed_point_x, fixed_point_y)
total_time = time.time() - start_time
self.output_table(op_type, table, tensor_type, total_time,
ret)
table_list.append(table)
self.tracker.log_component_summary(self._summary)
for table in table_list:
LOGGER.info(table)