def main(config="../../config.yaml",
param="./xgb_config_binary.yaml",
namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
if isinstance(param, str):
param = JobConfig.load_from_file(param)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
# data sets
guest_train_data = {
"name": param['data_guest_train'],
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": param['data_host_train'],
"namespace": f"experiment{namespace}"
}
guest_validate_data = {
"name": param['data_guest_val'],
"namespace": f"experiment{namespace}"
}
host_validate_data = {
"name": param['data_host_val'],
"namespace": f"experiment{namespace}"
}
# init pipeline
pipeline = PipeLine().set_initiator(role="guest",
party_id=guest).set_roles(
guest=guest,
host=host,
)
# set data reader and data-io
reader_0, reader_1 = Reader(name="reader_0"), Reader(name="reader_1")
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)
reader_1.get_party_instance(
role="guest",
party_id=guest).component_param(table=guest_validate_data)
reader_1.get_party_instance(
role="host", party_id=host).component_param(table=host_validate_data)
dataio_0, dataio_1 = DataIO(name="dataio_0"), DataIO(name="dataio_1")
dataio_0.get_party_instance(role="guest", party_id=guest).component_param(
with_label=True, output_format="dense")
dataio_0.get_party_instance(
role="host", party_id=host).component_param(with_label=False)
dataio_1.get_party_instance(role="guest", party_id=guest).component_param(
with_label=True, output_format="dense")
dataio_1.get_party_instance(
role="host", party_id=host).component_param(with_label=False)
# data intersect component
intersect_0 = Intersection(name="intersection_0")
intersect_1 = Intersection(name="intersection_1")
# secure boost component
hetero_secure_boost_0 = HeteroSecureBoost(
name="hetero_secure_boost_0",
num_trees=param['tree_num'],
task_type=param['task_type'],
objective_param={"objective": param['loss_func']},
encrypt_param={"method": "Paillier"},
tree_param={"max_depth": param['tree_depth']},
validation_freqs=1,
learning_rate=param['learning_rate'])
hetero_secure_boost_1 = HeteroSecureBoost(name="hetero_secure_boost_1")
# evaluation component
evaluation_0 = Evaluation(name="evaluation_0",
eval_type=param['eval_type'])
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(dataio_1,
data=Data(data=reader_1.output.data),
model=Model(dataio_0.output.model))
pipeline.add_component(intersect_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(intersect_1, data=Data(data=dataio_1.output.data))
pipeline.add_component(hetero_secure_boost_0,
data=Data(train_data=intersect_0.output.data,
validate_data=intersect_1.output.data))
pipeline.add_component(hetero_secure_boost_1,
data=Data(test_data=intersect_1.output.data),
model=Model(hetero_secure_boost_0.output.model))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_secure_boost_0.output.data))
pipeline.compile()
pipeline.fit()
sbt_0_data = pipeline.get_component(
"hetero_secure_boost_0").get_output_data().get("data")
sbt_1_data = pipeline.get_component(
"hetero_secure_boost_1").get_output_data().get("data")
sbt_0_score = extract_data(sbt_0_data, "predict_result")
sbt_0_label = extract_data(sbt_0_data, "label")
sbt_1_score = extract_data(sbt_1_data, "predict_result")
sbt_1_label = extract_data(sbt_1_data, "label")
sbt_0_score_label = extract_data(sbt_0_data,
"predict_result",
keep_id=True)
sbt_1_score_label = extract_data(sbt_1_data,
"predict_result",
keep_id=True)
metric_summary = parse_summary_result(
pipeline.get_component("evaluation_0").get_summary())
if param['eval_type'] == "regression":
desc_sbt_0 = regression_metric.Describe().compute(sbt_0_score)
desc_sbt_1 = regression_metric.Describe().compute(sbt_1_score)
metric_summary["script_metrics"] = {
"hetero_sbt_train": desc_sbt_0,
"hetero_sbt_validate": desc_sbt_1
}
elif param['eval_type'] == "binary":
metric_sbt = {
"score_diversity_ratio":
classification_metric.Distribution.compute(sbt_0_score_label,
sbt_1_score_label),
"ks_2samp":
classification_metric.KSTest.compute(sbt_0_score, sbt_1_score),
"mAP_D_value":
classification_metric.AveragePrecisionScore().compute(
sbt_0_score, sbt_1_score, sbt_0_label, sbt_1_label)
}
metric_summary["distribution_metrics"] = {"hetero_sbt": metric_sbt}
elif param['eval_type'] == "multi":
metric_sbt = {
"score_diversity_ratio":
classification_metric.Distribution.compute(sbt_0_score_label,
sbt_1_score_label)
}
metric_summary["distribution_metrics"] = {"hetero_sbt": metric_sbt}
data_summary = {
"train": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
},
"test": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
}
}
return data_summary, metric_summary
def main(config="../../config.yaml", namespace=""):
# obtain config
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
# data sets
guest_train_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
guest_validate_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_validate_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
# init pipeline
pipeline = PipeLine().set_initiator(role="guest",
party_id=guest).set_roles(
guest=guest,
host=host,
)
# set data reader and data-io
reader_0, reader_1 = Reader(name="reader_0"), Reader(name="reader_1")
reader_0.get_party_instance(
role="guest", party_id=guest).algorithm_param(table=guest_train_data)
reader_0.get_party_instance(
role="host", party_id=host).algorithm_param(table=host_train_data)
reader_1.get_party_instance(
role="guest",
party_id=guest).algorithm_param(table=guest_validate_data)
reader_1.get_party_instance(
role="host", party_id=host).algorithm_param(table=host_validate_data)
dataio_0, dataio_1 = DataIO(name="dataio_0"), DataIO(name="dataio_1")
dataio_0.get_party_instance(role="guest", party_id=guest).algorithm_param(
with_label=True, output_format="dense")
dataio_0.get_party_instance(
role="host", party_id=host).algorithm_param(with_label=False)
dataio_1.get_party_instance(role="guest", party_id=guest).algorithm_param(
with_label=True, output_format="dense")
dataio_1.get_party_instance(
role="host", party_id=host).algorithm_param(with_label=False)
# data intersect component
intersect_0 = Intersection(name="intersection_0")
intersect_1 = Intersection(name="intersection_1")
# secure boost component
hetero_fast_secure_boost_0 = HeteroFastSecureBoost(
name="hetero_fast_secure_boost_0",
num_trees=3,
task_type='classification',
objective_param={"objective": "cross_entropy"},
encrypt_param={"method": "iterativeAffine"},
guest_depth=1,
host_depth=2,
tree_param={"max_depth": 3},
validation_freqs=1,
work_mode='layered')
# evaluation component
evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary")
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(dataio_1,
data=Data(data=reader_1.output.data),
model=Model(dataio_0.output.model))
pipeline.add_component(intersect_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(intersect_1, data=Data(data=dataio_1.output.data))
pipeline.add_component(hetero_fast_secure_boost_0,
data=Data(train_data=intersect_0.output.data,
validate_data=intersect_1.output.data))
pipeline.add_component(
evaluation_0, data=Data(data=hetero_fast_secure_boost_0.output.data))
pipeline.compile()
pipeline.fit(backend=backend, work_mode=work_mode)
print("fitting hetero secureboost done, result:")
print(pipeline.get_component("hetero_fast_secure_boost_0").get_summary())
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
# data sets
guest_train_data = {
"name": "vehicle_scale_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "vehicle_scale_hetero_host",
"namespace": f"experiment{namespace}"
}
guest_validate_data = {
"name": "vehicle_scale_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_validate_data = {
"name": "vehicle_scale_hetero_host",
"namespace": f"experiment{namespace}"
}
# init pipeline
pipeline = PipeLine().set_initiator(role="guest",
party_id=guest).set_roles(
guest=guest,
host=host,
)
# set data reader and data-io
reader_0, reader_1 = Reader(name="reader_0"), Reader(name="reader_1")
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)
reader_1.get_party_instance(
role="guest",
party_id=guest).component_param(table=guest_validate_data)
reader_1.get_party_instance(
role="host", party_id=host).component_param(table=host_validate_data)
data_transform_0, data_transform_1 = DataTransform(
name="data_transform_0"), DataTransform(name="data_transform_1")
data_transform_0.get_party_instance(
role="guest", party_id=guest).component_param(with_label=True,
output_format="dense")
data_transform_0.get_party_instance(
role="host", party_id=host).component_param(with_label=False)
data_transform_1.get_party_instance(
role="guest", party_id=guest).component_param(with_label=True,
output_format="dense")
data_transform_1.get_party_instance(
role="host", party_id=host).component_param(with_label=False)
# data intersect component
intersect_0 = Intersection(name="intersection_0")
intersect_1 = Intersection(name="intersection_1")
# secure boost component
hetero_secure_boost_0 = HeteroSecureBoost(
name="hetero_secure_boost_0",
num_trees=3,
task_type="classification",
objective_param={"objective": "cross_entropy"},
encrypt_param={"method": "Paillier"},
tree_param={"max_depth": 3},
validation_freqs=1)
# evaluation component
evaluation_0 = Evaluation(name="evaluation_0", eval_type="multi")
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
pipeline.add_component(data_transform_1,
data=Data(data=reader_1.output.data),
model=Model(data_transform_0.output.model))
pipeline.add_component(intersect_0,
data=Data(data=data_transform_0.output.data))
pipeline.add_component(intersect_1,
data=Data(data=data_transform_1.output.data))
pipeline.add_component(hetero_secure_boost_0,
data=Data(train_data=intersect_0.output.data,
validate_data=intersect_1.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_secure_boost_0.output.data))
pipeline.compile()
pipeline.fit()
print("fitting hetero secureboost done, result:")
print(pipeline.get_component("hetero_secure_boost_0").get_summary())
def main(config="../../config.yaml", param="./lr_config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
arbiter = parties.arbiter[0]
backend = config.backend
work_mode = config.work_mode
if isinstance(param, str):
param = JobConfig.load_from_file(param)
assert isinstance(param, dict)
data_set = param.get("data_guest").split('/')[-1]
if data_set == "default_credit_hetero_guest.csv":
guest_data_table = 'default_credit_hetero_guest'
host_data_table = 'default_credit_hetero_host'
elif data_set == 'breast_hetero_guest.csv':
guest_data_table = 'breast_hetero_guest'
host_data_table = 'breast_hetero_host'
elif data_set == 'give_credit_hetero_guest.csv':
guest_data_table = 'give_credit_hetero_guest'
host_data_table = 'give_credit_hetero_host'
elif data_set == 'epsilon_5k_hetero_guest.csv':
guest_data_table = 'epsilon_5k_hetero_guest'
host_data_table = 'epsilon_5k_hetero_host'
else:
raise ValueError(f"Cannot recognized data_set: {data_set}")
guest_train_data = {
"name": guest_data_table,
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": host_data_table,
"namespace": f"experiment{namespace}"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=host, arbiter=arbiter)
# 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=host).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
dataio_0.get_party_instance(
role='host', party_id=host).component_param(with_label=False)
# define Intersection component
intersection_0 = Intersection(name="intersection_0")
lr_param = {
"validation_freqs": None,
"early_stopping_rounds": None,
}
config_param = {
"penalty": param["penalty"],
"max_iter": param["max_iter"],
"alpha": param["alpha"],
"learning_rate": param["learning_rate"],
"optimizer": param["optimizer"],
"batch_size": param["batch_size"],
"early_stop": "diff",
"tol": 1e-5,
"floating_point_precision": param.get("floating_point_precision"),
"init_param": {
"init_method": param.get("init_method", 'random_uniform'),
"random_seed": param.get("random_seed", 103)
}
}
lr_param.update(config_param)
print(f"lr_param: {lr_param}, data_set: {data_set}")
hetero_lr_0 = HeteroLR(name='hetero_lr_0', **lr_param)
hetero_lr_1 = HeteroLR(name='hetero_lr_1')
evaluation_0 = Evaluation(name='evaluation_0', eval_type="binary")
# 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))
pipeline.add_component(intersection_0,
data=Data(data=dataio_0.output.data))
pipeline.add_component(hetero_lr_0,
data=Data(train_data=intersection_0.output.data))
pipeline.add_component(hetero_lr_1,
data=Data(test_data=intersection_0.output.data),
model=Model(hetero_lr_0.output.model))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_lr_0.output.data))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
# fit model
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
lr_0_data = pipeline.get_component("hetero_lr_0").get_output_data().get(
"data")
lr_1_data = pipeline.get_component("hetero_lr_1").get_output_data().get(
"data")
lr_0_score = extract_data(lr_0_data, "predict_result")
lr_0_label = extract_data(lr_0_data, "label")
lr_1_score = extract_data(lr_1_data, "predict_result")
lr_1_label = extract_data(lr_1_data, "label")
lr_0_score_label = extract_data(lr_0_data, "predict_result", keep_id=True)
lr_1_score_label = extract_data(lr_1_data, "predict_result", keep_id=True)
result_summary = parse_summary_result(
pipeline.get_component("evaluation_0").get_summary())
metric_lr = {
"score_diversity_ratio":
classification_metric.Distribution.compute(lr_0_score_label,
lr_1_score_label),
"ks_2samp":
classification_metric.KSTest.compute(lr_0_score, lr_1_score),
"mAP_D_value":
classification_metric.AveragePrecisionScore().compute(
lr_0_score, lr_1_score, lr_0_label, lr_1_label)
}
result_summary["distribution_metrics"] = {"hetero_lr": metric_lr}
data_summary = {
"train": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
},
"test": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
}
}
return data_summary, result_summary
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
arbiter = parties.arbiter[0]
guest_train_data = {
"name": "breast_homo_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "breast_homo_host",
"namespace": f"experiment{namespace}"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=host, arbiter=arbiter)
# 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=host).component_param(table=host_train_data)
# define DataTransform components
data_transform_0 = DataTransform(
name="data_transform_0", with_label=True,
output_format="dense") # start component numbering at 0
scale_0 = FeatureScale(name='scale_0')
param = {
"penalty": "L2",
"optimizer": "sgd",
"tol": 1e-05,
"alpha": 0.01,
"max_iter": 3,
"early_stop": "diff",
"batch_size": 320,
"learning_rate": 0.15,
"decay": 1.0,
"decay_sqrt": True,
"init_param": {
"init_method": "zeros"
},
"encrypt_param": {
"method": None
},
"cv_param": {
"n_splits": 5,
"shuffle": True,
"random_seed": 33,
"need_cv": True
}
}
homo_lr_0 = HomoLR(name='homo_lr_0', **param)
# add components to pipeline, in order of task execution
pipeline.add_component(reader_0)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
# set data input sources of intersection components
pipeline.add_component(scale_0,
data=Data(data=data_transform_0.output.data))
pipeline.add_component(homo_lr_0,
data=Data(train_data=scale_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()
# query component summary
print(
json.dumps(pipeline.get_component("homo_lr_0").get_summary(),
indent=4,
ensure_ascii=False))
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
# data sets
guest_train_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
guest_validate_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_validate_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
# init pipeline
pipeline = PipeLine().set_initiator(role="guest",
party_id=guest).set_roles(
guest=guest,
host=host,
)
# set data reader and data-io
reader_0, reader_1 = Reader(name="reader_0"), Reader(name="reader_1")
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)
reader_1.get_party_instance(
role="guest",
party_id=guest).component_param(table=guest_validate_data)
reader_1.get_party_instance(
role="host", party_id=host).component_param(table=host_validate_data)
data_transform_0, data_transform_1 = DataTransform(
name="data_transform_0"), DataTransform(name="data_transform_1")
data_transform_0.get_party_instance(
role="guest", party_id=guest).component_param(with_label=True,
output_format="dense")
data_transform_0.get_party_instance(
role="host", party_id=host).component_param(with_label=False)
data_transform_1.get_party_instance(
role="guest", party_id=guest).component_param(with_label=True,
output_format="dense")
data_transform_1.get_party_instance(
role="host", party_id=host).component_param(with_label=False)
# data intersect component
intersect_0 = Intersection(name="intersection_0")
intersect_1 = Intersection(name="intersection_1")
# secure boost component
hetero_secure_boost_0 = HeteroSecureBoost(
name="hetero_secure_boost_0",
num_trees=3,
task_type="classification",
objective_param={"objective": "cross_entropy"},
encrypt_param={"method": "Paillier"},
tree_param={"max_depth": 3},
validation_freqs=1,
EINI_inference=True,
EINI_random_mask=True)
# evaluation component
evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary")
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
pipeline.add_component(data_transform_1,
data=Data(data=reader_1.output.data),
model=Model(data_transform_0.output.model))
pipeline.add_component(intersect_0,
data=Data(data=data_transform_0.output.data))
pipeline.add_component(intersect_1,
data=Data(data=data_transform_1.output.data))
pipeline.add_component(hetero_secure_boost_0,
data=Data(train_data=intersect_0.output.data,
validate_data=intersect_1.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_secure_boost_0.output.data))
pipeline.compile()
pipeline.fit()
print("fitting hetero secureboost done, result:")
print(pipeline.get_component("hetero_secure_boost_0").get_summary())
print('start to predict')
# predict
# deploy required components
pipeline.deploy_component(
[data_transform_0, intersect_0, hetero_secure_boost_0, evaluation_0])
predict_pipeline = PipeLine()
# add data reader onto predict pipeline
predict_pipeline.add_component(reader_0)
# add selected components from train pipeline onto predict pipeline
# specify data source
predict_pipeline.add_component(
pipeline,
data=Data(predict_input={
pipeline.data_transform_0.input.data: reader_0.output.data
}))
# run predict model
predict_pipeline.predict()
predict_result = predict_pipeline.get_component(
"hetero_secure_boost_0").get_output_data()
print("Showing 10 data of predict result")
for ret in predict_result["data"][:10]:
print(ret)
def main(config="../../config.yaml", namespace=""):
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
hosts = parties.host[0]
guest_train_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
# guest_train_data = {"name": "default_credit_hetero_guest", "namespace": f"experiment{namespace}"}
# host_train_data = {"name": "default_credit_hetero_host", "namespace": f"experiment{namespace}"}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=hosts)
# 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).component_param(table=host_train_data)
data_transform_0 = DataTransform(name="data_transform_0",
output_format='dense')
# get DataTransform party instance of guest
data_transform_0_guest_party_instance = data_transform_0.get_party_instance(
role='guest', party_id=guest)
# configure DataTransform for guest
data_transform_0_guest_party_instance.component_param(with_label=True)
# get and configure DataTransform party instance of host
data_transform_0.get_party_instance(
role='host', party_id=hosts).component_param(with_label=False)
# define Intersection components
intersection_0 = Intersection(name="intersection_0")
pipeline.add_component(reader_0)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
pipeline.add_component(intersection_0,
data=Data(data=data_transform_0.output.data))
lr_param = {
"penalty": "L2",
"optimizer": "rmsprop",
"tol": 0.0001,
"alpha": 0.01,
"early_stop": "diff",
"batch_size": -1,
"learning_rate": 0.15,
"init_param": {
"init_method": "zeros",
"fit_intercept": True
},
"encrypt_param": {
"key_length": 1024
},
"reveal_strategy": "respectively",
"reveal_every_iter": True,
"callback_param": {
"callbacks": ["ModelCheckpoint"],
"metrics": None,
"use_first_metric_only": False,
"save_freq": 1
}
}
hetero_sshe_lr_0 = HeteroSSHELR(name="hetero_sshe_lr_0",
max_iter=3,
**lr_param)
hetero_sshe_lr_1 = HeteroSSHELR(name="hetero_sshe_lr_1",
max_iter=30,
**lr_param)
pipeline.add_component(hetero_sshe_lr_0,
data=Data(train_data=intersection_0.output.data))
pipeline.add_component(hetero_sshe_lr_1,
data=Data(train_data=intersection_0.output.data),
model=Model(model=hetero_sshe_lr_0.output.model))
evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary")
pipeline.add_component(evaluation_0,
data=Data(data=hetero_sshe_lr_1.output.data))
pipeline.compile()
# fit model
pipeline.fit()
# query component summary
prettify(pipeline.get_component("hetero_sshe_lr_0").get_summary())
prettify(pipeline.get_component("hetero_sshe_lr_1").get_summary())
prettify(pipeline.get_component("evaluation_0").get_summary())
return pipeline
def main(config="../../config.yaml",
param="./hetero_nn_breast_config.yaml",
namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
if isinstance(param, str):
param = JobConfig.load_from_file(param)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
backend = config.backend
work_mode = config.work_mode
guest_train_data = {
"name": param["guest_table_name"],
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": param["host_table_name"],
"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")
hetero_nn_0 = HeteroNN(name="hetero_nn_0",
epochs=param["epochs"],
interactive_layer_lr=param["learning_rate"],
batch_size=param["batch_size"],
early_stop="diff")
hetero_nn_0.add_bottom_model(
Dense(units=param["bottom_layer_units"],
input_shape=(10, ),
activation="tanh",
kernel_initializer=initializers.RandomUniform(minval=-1,
maxval=1,
seed=123)))
hetero_nn_0.set_interactve_layer(
Dense(units=param["interactive_layer_units"],
input_shape=(param["bottom_layer_units"], ),
activation="relu",
kernel_initializer=initializers.RandomUniform(minval=-1,
maxval=1,
seed=123)))
hetero_nn_0.add_top_model(
Dense(units=param["top_layer_units"],
input_shape=(param["interactive_layer_units"], ),
activation=param["top_act"],
kernel_initializer=initializers.RandomUniform(minval=-1,
maxval=1,
seed=123)))
opt = getattr(optimizers, param["opt"])(lr=param["learning_rate"])
hetero_nn_0.compile(optimizer=opt,
metrics=param["metrics"],
loss=param["loss"])
hetero_nn_1 = HeteroNN(name="hetero_nn_1")
if param["loss"] == "categorical_crossentropy":
eval_type = "multi"
else:
eval_type = "binary"
evaluation_0 = Evaluation(name="evaluation_0", eval_type=eval_type)
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_nn_0,
data=Data(train_data=intersection_0.output.data))
pipeline.add_component(hetero_nn_1,
data=Data(test_data=intersection_0.output.data),
model=Model(hetero_nn_0.output.model))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_nn_0.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
nn_0_data = pipeline.get_component("hetero_nn_0").get_output_data().get(
"data")
nn_1_data = pipeline.get_component("hetero_nn_1").get_output_data().get(
"data")
nn_0_score = extract_data(nn_0_data, "predict_result")
nn_0_label = extract_data(nn_0_data, "label")
nn_1_score = extract_data(nn_1_data, "predict_result")
nn_1_label = extract_data(nn_1_data, "label")
nn_0_score_label = extract_data(nn_0_data, "predict_result", keep_id=True)
nn_1_score_label = extract_data(nn_1_data, "predict_result", keep_id=True)
metric_summary = parse_summary_result(
pipeline.get_component("evaluation_0").get_summary())
if eval_type == "binary":
metric_nn = {
"score_diversity_ratio":
classification_metric.Distribution.compute(nn_0_score_label,
nn_1_score_label),
"ks_2samp":
classification_metric.KSTest.compute(nn_0_score, nn_1_score),
"mAP_D_value":
classification_metric.AveragePrecisionScore().compute(
nn_0_score, nn_1_score, nn_0_label, nn_1_label)
}
metric_summary["distribution_metrics"] = {"hetero_nn": metric_nn}
elif eval_type == "multi":
metric_nn = {
"score_diversity_ratio":
classification_metric.Distribution.compute(nn_0_score_label,
nn_1_score_label)
}
metric_summary["distribution_metrics"] = {"hetero_nn": metric_nn}
data_summary = {
"train": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
},
"test": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
}
}
return data_summary, metric_summary
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
arbiter = parties.arbiter[0]
guest_train_data = {
"name": "breast_hetero_guest",
"namespace": "experiment"
}
guest_eval_data = {
"name": "breast_hetero_guest",
"namespace": "experiment"
}
guest_test_data = {
"name": "breast_hetero_guest",
"namespace": "experiment"
}
host_train_data = {
"name": "breast_hetero_host_tag_value",
"namespace": "experiment"
}
host_eval_data = {
"name": "breast_hetero_host_tag_value",
"namespace": "experiment"
}
host_test_data = {
"name": "breast_hetero_host_tag_value",
"namespace": "experiment"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=host, arbiter=arbiter)
# define Reader components to read in data
reader_0 = Reader(name="reader_0")
reader_1 = Reader(name="reader_1")
reader_2 = Reader(name="reader_2")
# configure Reader for guest
reader_0.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
reader_1.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_eval_data)
reader_2.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_test_data)
# configure Reader for host
reader_0.get_party_instance(
role='host', party_id=host).component_param(table=host_train_data)
reader_1.get_party_instance(
role='host', party_id=host).component_param(table=host_eval_data)
reader_2.get_party_instance(
role='host', party_id=host).component_param(table=host_test_data)
# define DataIO components
dataio_0 = DataIO(name="dataio_0") # start component numbering at 0
dataio_1 = DataIO(name="dataio_1") # start component numbering at 1
dataio_2 = DataIO(name="dataio_2") # start component numbering at 2
param = {
"with_label": True,
"label_name": "y",
"label_type": "int",
"output_format": "dense",
"missing_fill": True,
"missing_fill_method": "mean",
"outlier_replace": False,
"outlier_replace_method": "designated",
"outlier_replace_value": 0.66,
"outlier_impute": "-9999"
}
# 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(**param)
# get and configure DataIO party instance of host
dataio_1.get_party_instance(role='guest',
party_id=guest).component_param(**param)
dataio_2.get_party_instance(role='guest',
party_id=guest).component_param(**param)
param = {
"input_format": "tag",
"with_label": False,
"tag_with_value": True,
"delimitor": ";",
"output_format": "dense"
}
dataio_0.get_party_instance(role='host',
party_id=host).component_param(**param)
dataio_1.get_party_instance(role='host',
party_id=host).component_param(**param)
dataio_2.get_party_instance(role='host',
party_id=host).component_param(**param)
# define Intersection components
intersection_0 = Intersection(name="intersection_0",
intersect_method="raw")
intersection_1 = Intersection(name="intersection_1",
intersect_method="raw")
intersection_2 = Intersection(name="intersection_2",
intersect_method="raw")
param = {
"name": 'hetero_feature_binning_0',
"method": 'optimal',
"optimal_binning_param": {
"metric_method": "iv",
"init_bucket_method": "quantile"
},
"bin_indexes": -1
}
hetero_feature_binning_0 = HeteroFeatureBinning(**param)
statistic_0 = DataStatistics(name='statistic_0')
param = {
"name": 'hetero_feature_selection_0',
"filter_methods": ["unique_value", "iv_filter", "statistic_filter"],
"unique_param": {
"eps": 1e-6
},
"iv_param": {
"metrics": ["iv", "iv"],
"filter_type": ["top_k", "threshold"],
"take_high": [True, True],
"threshold": [10, 0.1]
},
"statistic_param": {
"metrics": ["coefficient_of_variance", "skewness"],
"filter_type": ["threshold", "threshold"],
"take_high": [True, False],
"threshold": [0.001, -0.01]
},
"select_col_indexes": -1
}
hetero_feature_selection_0 = HeteroFeatureSelection(**param)
hetero_feature_selection_1 = HeteroFeatureSelection(
name='hetero_feature_selection_1')
hetero_feature_selection_2 = HeteroFeatureSelection(
name='hetero_feature_selection_2')
param = {"name": "hetero_scale_0", "method": "standard_scale"}
hetero_scale_0 = FeatureScale(**param)
hetero_scale_1 = FeatureScale(name='hetero_scale_1')
hetero_scale_2 = FeatureScale(name='hetero_scale_2')
param = {
"penalty": "L2",
"optimizer": "nesterov_momentum_sgd",
"tol": 1e-4,
"alpha": 0.01,
"max_iter": 5,
"early_stop": "diff",
"batch_size": -1,
"learning_rate": 0.15,
"init_param": {
"init_method": "zeros"
},
"validation_freqs": None,
"early_stopping_rounds": None
}
hetero_lr_0 = HeteroLR(name='hetero_lr_0', **param)
hetero_lr_1 = HeteroLR(name='hetero_lr_1')
evaluation_0 = Evaluation(name='evaluation_0')
# add components to pipeline, in order of task execution
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(reader_2)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(dataio_1,
data=Data(data=reader_1.output.data),
model=Model(dataio_0.output.model))
pipeline.add_component(dataio_2,
data=Data(data=reader_2.output.data),
model=Model(dataio_1.output.model))
# set data input sources of intersection components
pipeline.add_component(intersection_0,
data=Data(data=dataio_0.output.data))
pipeline.add_component(intersection_1,
data=Data(data=dataio_1.output.data))
pipeline.add_component(intersection_2,
data=Data(data=dataio_2.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))
pipeline.add_component(statistic_0,
data=Data(data=intersection_0.output.data))
pipeline.add_component(
hetero_feature_selection_0,
data=Data(data=intersection_0.output.data),
model=Model(isometric_model=[
hetero_feature_binning_0.output.model, statistic_0.output.model
]))
pipeline.add_component(hetero_feature_selection_1,
data=Data(data=intersection_1.output.data),
model=Model(
hetero_feature_selection_0.output.model))
pipeline.add_component(hetero_feature_selection_2,
data=Data(data=intersection_2.output.data),
model=Model(
hetero_feature_selection_1.output.model))
pipeline.add_component(
hetero_scale_0, data=Data(data=hetero_feature_selection_0.output.data))
pipeline.add_component(
hetero_scale_1,
data=Data(data=hetero_feature_selection_1.output.data),
model=Model(hetero_scale_0.output.model))
pipeline.add_component(
hetero_scale_2,
data=Data(data=hetero_feature_selection_2.output.data),
model=Model(hetero_scale_1.output.model))
# set train & validate data of hetero_lr_0 component
pipeline.add_component(hetero_lr_0,
data=Data(train_data=hetero_scale_0.output.data,
validate_data=hetero_scale_1.output.data))
pipeline.add_component(hetero_lr_1,
data=Data(test_data=hetero_scale_2.output.data),
model=Model(hetero_lr_0.output.model))
pipeline.add_component(
evaluation_0,
data=Data(data=[hetero_lr_0.output.data, hetero_lr_1.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()
# query component summary
print(pipeline.get_component("hetero_lr_0").get_summary())
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
arbiter = parties.arbiter[0]
guest_train_data_0 = {
"name": "breast_hetero_guest",
"namespace": "experiment"
}
guest_train_data_1 = {
"name": "breast_hetero_guest",
"namespace": "experiment"
}
guest_test_data_0 = {
"name": "breast_hetero_guest",
"namespace": "experiment"
}
guest_test_data_1 = {
"name": "breast_hetero_guest",
"namespace": "experiment"
}
host_train_data_0 = {
"name": "breast_hetero_host_tag_value",
"namespace": "experiment"
}
host_train_data_1 = {
"name": "breast_hetero_host_tag_value",
"namespace": "experiment"
}
host_test_data_0 = {
"name": "breast_hetero_host_tag_value",
"namespace": "experiment"
}
host_test_data_1 = {
"name": "breast_hetero_host_tag_value",
"namespace": "experiment"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=host, arbiter=arbiter)
# define Reader components to read in data
reader_0 = Reader(name="reader_0")
reader_1 = Reader(name="reader_1")
reader_2 = Reader(name="reader_2")
reader_3 = Reader(name="reader_3")
# configure Reader for guest
reader_0.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data_0)
reader_1.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data_1)
reader_2.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_test_data_0)
reader_3.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_test_data_1)
# configure Reader for host
reader_0.get_party_instance(
role='host', party_id=host).component_param(table=host_train_data_0)
reader_1.get_party_instance(
role='host', party_id=host).component_param(table=host_train_data_1)
reader_2.get_party_instance(
role='host', party_id=host).component_param(table=host_test_data_0)
reader_3.get_party_instance(
role='host', party_id=host).component_param(table=host_test_data_1)
param = {"name": "union_0", "keep_duplicate": True}
union_0 = Union(**param)
param = {"name": "union_1", "keep_duplicate": True}
union_1 = Union(**param)
param = {
"input_format": "tag",
"with_label": False,
"tag_with_value": True,
"delimitor": ";",
"output_format": "dense"
}
# define DataIO components
dataio_0 = DataIO(name="dataio_0") # start component numbering at 0
dataio_1 = DataIO(name="dataio_1") # start component numbering at 1
# 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
dataio_0.get_party_instance(role='host',
party_id=host).component_param(**param)
dataio_1.get_party_instance(
role='guest', party_id=guest).component_param(with_label=True)
dataio_1.get_party_instance(role='host',
party_id=host).component_param(**param)
# define Intersection components
intersection_0 = Intersection(name="intersection_0")
intersection_1 = Intersection(name="intersection_1")
param = {
"name": 'hetero_feature_binning_0',
"method": 'optimal',
"optimal_binning_param": {
"metric_method": "iv"
},
"bin_indexes": -1
}
hetero_feature_binning_0 = HeteroFeatureBinning(**param)
statistic_0 = DataStatistics(name='statistic_0')
param = {
"name": 'hetero_feature_selection_0',
"filter_methods": ["manually", "iv_filter", "statistic_filter"],
"manually_param": {
"filter_out_indexes": [1, 2],
"filter_out_names": ["x2", "x3"]
},
"iv_param": {
"metrics": ["iv", "iv"],
"filter_type": ["top_k", "threshold"],
"take_high": [True, True],
"threshold": [10, 0.01]
},
"statistic_param": {
"metrics": ["coefficient_of_variance", "skewness"],
"filter_type": ["threshold", "threshold"],
"take_high": [True, True],
"threshold": [0.001, -0.01]
},
"select_col_indexes": -1
}
hetero_feature_selection_0 = HeteroFeatureSelection(**param)
hetero_feature_selection_1 = HeteroFeatureSelection(
name='hetero_feature_selection_1')
param = {"name": "hetero_scale_0", "method": "standard_scale"}
hetero_scale_0 = FeatureScale(**param)
hetero_scale_1 = FeatureScale(name='hetero_scale_1')
param = {
"penalty": "L2",
"validation_freqs": None,
"early_stopping_rounds": None,
"max_iter": 5
}
hetero_lr_0 = HeteroLR(name='hetero_lr_0', **param)
evaluation_0 = Evaluation(name='evaluation_0')
# add components to pipeline, in order of task execution
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(reader_2)
pipeline.add_component(reader_3)
pipeline.add_component(
union_0, data=Data(data=[reader_0.output.data, reader_1.output.data]))
pipeline.add_component(
union_1, data=Data(data=[reader_2.output.data, reader_3.output.data]))
pipeline.add_component(dataio_0, data=Data(data=union_0.output.data))
pipeline.add_component(dataio_1,
data=Data(data=union_1.output.data),
model=Model(dataio_0.output.model))
# set data input sources of intersection components
pipeline.add_component(intersection_0,
data=Data(data=dataio_0.output.data))
pipeline.add_component(intersection_1,
data=Data(data=dataio_1.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))
pipeline.add_component(statistic_0,
data=Data(data=intersection_0.output.data))
pipeline.add_component(
hetero_feature_selection_0,
data=Data(data=intersection_0.output.data),
model=Model(isometric_model=[
hetero_feature_binning_0.output.model, statistic_0.output.model
]))
pipeline.add_component(hetero_feature_selection_1,
data=Data(data=intersection_1.output.data),
model=Model(
hetero_feature_selection_0.output.model))
pipeline.add_component(
hetero_scale_0, data=Data(data=hetero_feature_selection_0.output.data))
pipeline.add_component(
hetero_scale_1,
data=Data(data=hetero_feature_selection_1.output.data),
model=Model(hetero_scale_0.output.model))
# set train & validate data of hetero_lr_0 component
pipeline.add_component(hetero_lr_0,
data=Data(train_data=hetero_scale_0.output.data,
validate_data=hetero_scale_1.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=[hetero_lr_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()
# query component summary
print(pipeline.get_component("hetero_lr_0").get_summary())
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
arbiter = parties.arbiter[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}"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=host, arbiter=arbiter)
# 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).algorithm_param(table=guest_train_data)
# configure Reader for host
reader_0.get_party_instance(
role='host', party_id=host).algorithm_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.algorithm_param(with_label=True,
output_format="dense")
# get and configure DataIO party instance of host
dataio_0.get_party_instance(
role='host', party_id=host).algorithm_param(with_label=False)
# define Intersection components
intersection_0 = Intersection(name="intersection_0")
param = {"k": 3, "max_iter": 10}
hetero_kmeans_0 = HeteroKmeans(name='hetero_kmeans_0', **param)
evaluation_0 = Evaluation(name='evaluation_0', eval_type='clustering')
# 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_kmeans_0,
data=Data(train_data=intersection_0.output.data))
print(f"data: {hetero_kmeans_0.output.data.data[0]}")
pipeline.add_component(evaluation_0,
data=Data(data=hetero_kmeans_0.output.data.data[0]))
# 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)
# query component summary
print(pipeline.get_component("hetero_kmeans_0").get_summary())
def main(config="../../config.yaml", namespace=""):
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
hosts = parties.host[0]
guest_train_data = {
"name": "vehicle_scale_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "vehicle_scale_hetero_host",
"namespace": f"experiment{namespace}"
}
guest_eval_data = {
"name": "vehicle_scale_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_eval_data = {
"name": "vehicle_scale_hetero_host",
"namespace": f"experiment{namespace}"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=hosts)
# 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).component_param(table=host_train_data)
reader_1 = Reader(name="reader_1")
reader_1.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_eval_data)
reader_1.get_party_instance(
role='host', party_id=hosts).component_param(table=host_eval_data)
data_transform_0 = DataTransform(name="data_transform_0",
output_format='dense')
data_transform_1 = DataTransform(name="data_transform_1",
output_format='dense')
# get DataTransform party instance of guest
data_transform_0_guest_party_instance = data_transform_0.get_party_instance(
role='guest', party_id=guest)
# configure DataTransform for guest
data_transform_0_guest_party_instance.component_param(with_label=True)
# get and configure DataTransform party instance of host
data_transform_0.get_party_instance(
role='host', party_id=hosts).component_param(with_label=False)
# define Intersection components
intersection_0 = Intersection(name="intersection_0")
intersection_1 = Intersection(name="intersection_1")
selection_param = {
"select_col_indexes": -1,
"filter_methods": ["manually"]
}
hetero_feature_selection_0 = HeteroFeatureSelection(
name="hetero_feature_selection_0", **selection_param)
hetero_feature_selection_0.get_party_instance(
role='guest', party_id=guest).component_param(
manually_param={"left_col_indexes": [0]})
hetero_feature_selection_1 = HeteroFeatureSelection(
name="hetero_feature_selection_1")
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
pipeline.add_component(data_transform_1,
data=Data(data=reader_1.output.data),
model=Model(data_transform_0.output.model))
pipeline.add_component(intersection_0,
data=Data(data=data_transform_0.output.data))
pipeline.add_component(intersection_1,
data=Data(data=data_transform_1.output.data))
pipeline.add_component(hetero_feature_selection_0,
data=Data(data=intersection_0.output.data))
pipeline.add_component(hetero_feature_selection_1,
data=Data(data=intersection_1.output.data),
model=Model(
hetero_feature_selection_0.output.model))
lr_param = {
"name": "hetero_sshe_lr_0",
"penalty": None,
"optimizer": "sgd",
"tol": 0.0001,
"alpha": 0.01,
"max_iter": 1,
"early_stop": "diff",
"batch_size": -1,
"learning_rate": 0.15,
"init_param": {
"init_method": "random_uniform"
},
"reveal_strategy": "encrypted_reveal_in_host",
"reveal_every_iter": False
}
hetero_sshe_lr_0 = HeteroSSHELR(**lr_param)
pipeline.add_component(
hetero_sshe_lr_0,
data=Data(train_data=hetero_feature_selection_0.output.data,
validate_data=hetero_feature_selection_1.output.data))
evaluation_data = [hetero_sshe_lr_0.output.data]
hetero_sshe_lr_1 = HeteroSSHELR(name='hetero_sshe_lr_1')
pipeline.add_component(
hetero_sshe_lr_1,
data=Data(test_data=hetero_feature_selection_1.output.data),
model=Model(hetero_sshe_lr_0.output.model))
evaluation_data.append(hetero_sshe_lr_1.output.data)
evaluation_0 = Evaluation(name="evaluation_0", eval_type="multi")
pipeline.add_component(evaluation_0, data=Data(data=evaluation_data))
pipeline.compile()
# fit model
pipeline.fit()
# query component summary
prettify(pipeline.get_component("hetero_sshe_lr_0").get_summary())
prettify(pipeline.get_component("evaluation_0").get_summary())
return pipeline
def main(config="../../config.yaml", namespace=""):
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
hosts = parties.host[0]
guest_train_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
guest_eval_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_eval_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=hosts)
# 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).component_param(table=host_train_data)
reader_1 = Reader(name="reader_1")
reader_1.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_eval_data)
reader_1.get_party_instance(
role='host', party_id=hosts).component_param(table=host_eval_data)
data_transform_0 = DataTransform(name="data_transform_0",
output_format='dense')
data_transform_1 = DataTransform(name="data_transform_1",
output_format='dense')
# get DataTransform party instance of guest
data_transform_0_guest_party_instance = data_transform_0.get_party_instance(
role='guest', party_id=guest)
# configure DataTransform for guest
data_transform_0_guest_party_instance.component_param(with_label=True)
# get and configure DataTransform party instance of host
data_transform_0.get_party_instance(
role='host', party_id=hosts).component_param(with_label=False)
# define Intersection components
intersection_0 = Intersection(name="intersection_0")
intersection_1 = Intersection(name="intersection_1")
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
pipeline.add_component(data_transform_1,
data=Data(data=reader_1.output.data),
model=Model(data_transform_0.output.model))
pipeline.add_component(intersection_0,
data=Data(data=data_transform_0.output.data))
pipeline.add_component(intersection_1,
data=Data(data=data_transform_1.output.data))
lr_param = {
"name": "hetero_sshe_lr_0",
"penalty": "L2",
"optimizer": "rmsprop",
"tol": 0.0001,
"alpha": 0.01,
"max_iter": 30,
"early_stop": "diff",
"batch_size": -1,
"callback_param": {
"callbacks": ["EarlyStopping", "PerformanceEvaluate"],
"validation_freqs": 1,
"early_stopping_rounds": 3
},
"learning_rate": 0.15,
"init_param": {
"init_method": "zeros"
},
"reveal_strategy": "respectively",
"reveal_every_iter": True
}
hetero_sshe_lr_0 = HeteroSSHELR(**lr_param)
pipeline.add_component(hetero_sshe_lr_0,
data=Data(train_data=intersection_0.output.data,
validate_data=intersection_1.output.data))
evaluation_data = [hetero_sshe_lr_0.output.data]
hetero_sshe_lr_1 = HeteroSSHELR(name='hetero_sshe_lr_1')
pipeline.add_component(hetero_sshe_lr_1,
data=Data(test_data=intersection_1.output.data),
model=Model(hetero_sshe_lr_0.output.model))
evaluation_data.append(hetero_sshe_lr_1.output.data)
evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary")
pipeline.add_component(evaluation_0, data=Data(data=evaluation_data))
pipeline.compile()
# fit model
pipeline.fit()
# query component summary
prettify(pipeline.get_component("hetero_sshe_lr_0").get_summary())
prettify(pipeline.get_component("evaluation_0").get_summary())
return pipeline
