def make_asymmetric_dsl(config,
namespace,
guest_param,
host_param,
dataset='breast',
is_multi_host=False,
host_dense_output=True):
parties = config.parties
guest = parties.guest[0]
hosts = parties.host
if dataset == 'breast':
guest_table_name = 'breast_hetero_guest'
host_table_name = 'breast_hetero_host'
elif dataset == 'default_credit':
guest_table_name = 'default_credit_hetero_guest'
host_table_name = 'default_credit_hetero_host'
else:
raise ValueError(f"dataset: {dataset} cannot be recognized")
guest_train_data = {
"name": guest_table_name,
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": host_table_name,
"namespace": f"experiment{namespace}"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
if is_multi_host:
pipeline.set_roles(guest=guest, host=hosts)
else:
pipeline.set_roles(guest=guest, host=hosts[0])
# define Reader components to read in data
reader_0 = Reader(name="reader_0")
# configure Reader for guest
reader_0.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
# configure Reader for host
reader_0.get_party_instance(
role='host', party_id=hosts[0]).component_param(table=host_train_data)
if is_multi_host:
reader_0.get_party_instance(
role='host',
party_id=hosts[1]).component_param(table=host_train_data)
# define DataIO components
dataio_0 = DataIO(name="dataio_0") # start component numbering at 0
# get DataIO party instance of guest
dataio_0_guest_party_instance = dataio_0.get_party_instance(role='guest',
party_id=guest)
# configure DataIO for guest
dataio_0_guest_party_instance.component_param(with_label=True,
output_format="dense")
# get and configure DataIO party instance of host
if host_dense_output:
output_format = 'dense'
else:
output_format = 'sparse'
if is_multi_host:
dataio_0.get_party_instance(role='host', party_id=hosts). \
component_param(with_label=False,
output_format=output_format)
else:
dataio_0.get_party_instance(role='host', party_id=hosts[0]). \
component_param(with_label=False,
output_format=output_format)
# define Intersection components
intersection_0 = Intersection(name="intersection_0")
hetero_feature_binning_0 = HeteroFeatureBinning(
name="hetero_feature_binning_0")
hetero_feature_binning_0.get_party_instance(
role='guest', party_id=guest).component_param(**guest_param)
if is_multi_host:
hetero_feature_binning_0.get_party_instance(
role='host', party_id=hosts).component_param(**host_param)
else:
hetero_feature_binning_0.get_party_instance(
role='host', party_id=hosts[0]).component_param(**host_param)
# add components to pipeline, in order of task execution
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
# set data input sources of intersection components
pipeline.add_component(intersection_0,
data=Data(data=dataio_0.output.data))
# set train & validate data of hetero_lr_0 component
pipeline.add_component(hetero_feature_binning_0,
data=Data(data=intersection_0.output.data))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
# fit model
# pipeline.fit(backend=backend, work_mode=work_mode)
return pipeline
def main(config="../../config.yaml", namespace=""):
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
backend = config.backend
work_mode = config.work_mode
guest_train_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
pipeline = PipeLine().set_initiator(role='guest',
party_id=guest).set_roles(guest=guest,
host=host)
reader_0 = Reader(name="reader_0")
reader_0.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
reader_0.get_party_instance(
role='host', party_id=host).component_param(table=host_train_data)
dataio_0 = DataIO(name="dataio_0")
dataio_0.get_party_instance(
role='guest', party_id=guest).component_param(with_label=True)
dataio_0.get_party_instance(
role='host', party_id=host).component_param(with_label=False)
intersection_0 = Intersection(name="intersection_0")
param = {
"name": "hetero_feature_binning_0",
"method": "quantile",
"compress_thres": 10000,
"head_size": 10000,
"error": 0.001,
"bin_num": 10,
"bin_indexes": -1,
"bin_names": None,
"category_indexes": None,
"category_names": None,
"adjustment_factor": 0.5,
"local_only": False,
"transform_param": {
"transform_cols": [0, 1, 2],
"transform_names": None,
"transform_type": "woe"
}
}
hetero_feature_binning_0 = HeteroFeatureBinning(**param)
hetero_feature_binning_0.get_party_instance(
role="host", party_id=host).component_param(
transform_param={"transform_type": None})
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(intersection_0,
data=Data(data=dataio_0.output.data))
pipeline.add_component(hetero_feature_binning_0,
data=Data(data=intersection_0.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)