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]
guest_train_data = {
"name": "nus_wide_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "nus_wide_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)
data_transform_0 = DataTransform(name="data_transform_0")
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)
hetero_ftl_0 = HeteroFTL(name='hetero_ftl_0',
epochs=10,
alpha=1,
batch_size=-1,
mode='plain')
hetero_ftl_0.add_nn_layer(
Dense(units=32,
activation='sigmoid',
kernel_initializer=initializers.RandomNormal(stddev=1.0),
bias_initializer=initializers.Zeros()))
hetero_ftl_0.compile(optimizer=optimizers.Adam(lr=0.01))
evaluation_0 = Evaluation(name='evaluation_0', eval_type="binary")
pipeline.add_component(reader_0)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
pipeline.add_component(hetero_ftl_0,
data=Data(train_data=data_transform_0.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_ftl_0.output.data))
pipeline.compile()
pipeline.fit()
# predict
# deploy required components
pipeline.deploy_component([data_transform_0, hetero_ftl_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()
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": 30,
"early_stop": "diff",
"batch_size": -1,
"learning_rate": 0.15,
"decay": 1,
"decay_sqrt": True,
"init_param": {
"init_method": "zeros"
},
"encrypt_param": {
"method": None
},
"cv_param": {
"n_splits": 4,
"shuffle": True,
"random_seed": 33,
"need_cv": False
}
}
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))
evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary")
evaluation_0.get_party_instance(role='host', party_id=host).component_param(need_run=False)
pipeline.add_component(evaluation_0, data=Data(data=homo_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()
deploy_components = [data_transform_0, scale_0, homo_lr_0]
pipeline.deploy_component(components=deploy_components)
#
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}))
predict_pipeline.compile()
predict_pipeline.predict()
dsl_json = predict_pipeline.get_predict_dsl()
conf_json = predict_pipeline.get_predict_conf()
# import json
json.dump(dsl_json, open('./h**o-lr-normal-predict-dsl.json', 'w'), indent=4)
json.dump(conf_json, open('./h**o-lr-normal-predict-conf.json', 'w'), indent=4)
# query component summary
print(json.dumps(pipeline.get_component("homo_lr_0").get_summary(), indent=4, ensure_ascii=False))
print(json.dumps(pipeline.get_component("evaluation_0").get_summary(), indent=4, ensure_ascii=False))
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 = {
"name": "hetero_sshe_lr_0",
"penalty": "L1",
"optimizer": "rmsprop",
"tol": 0.0001,
"alpha": 0.01,
"max_iter": 30,
"early_stop": "diff",
"batch_size": -1,
"learning_rate": 0.15,
"init_param": {
"init_method": "zeros",
"fit_intercept": True
},
"encrypt_param": {
"key_length": 1024
},
"reveal_every_iter": True,
"reveal_strategy": "respectively"
}
hetero_sshe_lr_0 = HeteroSSHELR(**lr_param)
pipeline.add_component(hetero_sshe_lr_0,
data=Data(train_data=intersection_0.output.data))
evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary")
pipeline.add_component(evaluation_0,
data=Data(data=hetero_sshe_lr_0.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("evaluation_0").get_summary())
pipeline.deploy_component(
[data_transform_0, intersection_0, hetero_sshe_lr_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()
return pipeline
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
hosts = parties.host
guest_train_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = [{
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}, {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}]
pipeline = PipeLine().set_initiator(role='guest',
party_id=guest).set_roles(guest=guest,
host=hosts)
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=hosts[0]).component_param(table=host_train_data[0])
reader_0.get_party_instance(
role='host',
party_id=hosts[1]).component_param(table=host_train_data[1])
data_transform_0 = DataTransform(name="data_transform_0")
data_transform_0.get_party_instance(
role='guest', party_id=guest).component_param(with_label=False,
output_format="dense")
data_transform_0.get_party_instance(
role='host', party_id=hosts[0]).component_param(with_label=False,
output_format="dense")
data_transform_0.get_party_instance(
role='host', party_id=hosts[1]).component_param(with_label=False,
output_format="dense")
param = {
"intersect_method": "raw",
"sync_intersect_ids": True,
"only_output_key": True,
"raw_params": {
"use_hash": True,
"hash_method": "sha256",
"salt": "12345",
"join_role": "guest"
}
}
intersect_0 = Intersection(name="intersect_0", **param)
pipeline.add_component(reader_0)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
pipeline.add_component(intersect_0,
data=Data(data=data_transform_0.output.data))
pipeline.compile()
pipeline.fit()
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
hosts = parties.host
guest_train_data = {
"name": "breast_homo_test",
"namespace": f"experiment_sid{namespace}"
}
host_train_data = {
"name": "breast_homo_test",
"namespace": f"experiment_sid{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",
with_match_id=True)
# get and configure DataTransform party instance of guest
data_transform_0.get_party_instance(
role="guest", party_id=guest).component_param(with_label=False,
output_format="dense")
# 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 FeldmanVerifiableSum components
feldmanverifiablesum_0 = FeldmanVerifiableSum(
name="feldmanverifiablesum_0")
feldmanverifiablesum_0.get_party_instance(
role="guest", party_id=guest).component_param(sum_cols=[1, 2, 3],
q_n=6)
feldmanverifiablesum_0.get_party_instance(
role="host", party_id=hosts).component_param(sum_cols=[1, 2, 3], q_n=6)
# 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))
pipeline.add_component(feldmanverifiablesum_0,
data=Data(data=data_transform_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()
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}"
}
# 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(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)
data_transform_0 = DataTransform(name="data_transform_0")
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 intersect component
intersect_0 = Intersection(name="intersection_0")
# 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,
cv_param={
"need_cv": True,
"n_splits": 5,
"shuffle": False,
"random_seed": 103
})
pipeline.add_component(reader_0)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
pipeline.add_component(intersect_0,
data=Data(data=data_transform_0.output.data))
pipeline.add_component(hetero_secure_boost_0,
data=Data(train_data=intersect_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", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
guest_train_data = {
"name": "expect",
"namespace": f"experiment{namespace}"
}
host_train_data = {"name": "actual", "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)
reader_1 = Reader(name="reader_1")
reader_1.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
reader_1.get_party_instance(
role='host', party_id=host).component_param(table=host_train_data)
data_transform_0 = DataTransform(name="data_transform_0")
data_transform_1 = DataTransform(name="data_transform_1")
data_transform_0.get_party_instance(
role='guest', party_id=guest).component_param(with_label=False,
output_format="dense")
data_transform_1.get_party_instance(
role='guest', party_id=guest).component_param(with_label=False,
output_format="dense")
data_transform_0.get_party_instance(
role='host', party_id=host).component_param(with_label=False,
output_format="dense")
data_transform_1.get_party_instance(
role='host', party_id=host).component_param(with_label=False,
output_format="dense")
psi_0 = PSI(name='psi_0', max_bin_num=20)
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(psi_0,
data=Data(
train_data=data_transform_0.output.data,
validate_data=data_transform_1.output.data))
pipeline.compile()
pipeline.fit()
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
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
guest_train_data = {
"name": "vehicle_scale_hetero_guest",
"namespace": f"experiment{namespace}"
}
guest_validate_data = {
"name": "vehicle_scale_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "vehicle_scale_hetero_host",
"namespace": f"experiment{namespace}"
}
host_validate_data = {
"name": "vehicle_scale_hetero_host",
"namespace": f"experiment{namespace}"
}
pipeline = PipeLine().set_initiator(role='guest',
party_id=guest).set_roles(guest=guest,
host=host)
data_transform_0, data_transform_1 = DataTransform(
name="data_transform_0"), DataTransform(name='data_transform_1')
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)
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,
output_format="dense")
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_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=True,
output_format="dense")
intersection_0 = Intersection(name="intersection_0")
intersection_1 = Intersection(name="intersection_1")
param = {
"method": "quantile",
"optimal_binning_param": {
"metric_method": "gini",
"min_bin_pct": 0.05,
"max_bin_pct": 0.8,
"init_bucket_method": "quantile",
"init_bin_nums": 100,
"mixture": True
},
"compress_thres": 10000,
"head_size": 10000,
"error": 0.001,
"bin_num": 10,
"bin_indexes": -1,
"bin_names": None,
"category_indexes": [0, 1, 2],
"category_names": None,
"adjustment_factor": 0.5,
"local_only": False,
"transform_param": {
"transform_cols": -1,
"transform_names": None,
"transform_type": "bin_num"
}
}
hetero_feature_binning_0 = HeteroFeatureBinning(
name="hetero_feature_binning_0", **param)
hetero_feature_binning_1 = HeteroFeatureBinning(
name='hetero_feature_binning_1')
pipeline.add_component(reader_0)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
pipeline.add_component(reader_1)
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_binning_0,
data=Data(data=intersection_0.output.data))
pipeline.add_component(hetero_feature_binning_1,
data=Data(data=intersection_1.output.data),
model=Model(hetero_feature_binning_0.output.model))
pipeline.compile()
pipeline.fit()
# predict
# deploy required components
pipeline.deploy_component(
[data_transform_0, intersection_0, hetero_feature_binning_0])
predict_pipeline = PipeLine()
# add data reader onto predict pipeline
predict_pipeline.add_component(reader_1)
# 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_1.output.data
}))
# run predict model
predict_pipeline.predict()
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 DataTransform components
data_transform_0 = DataTransform(
name="data_transform_0") # start component numbering at 0
# 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, output_format="dense")
# get and configure DataTransform party instance of host
if host_dense_output:
output_format = 'dense'
else:
output_format = 'sparse'
if is_multi_host:
data_transform_0.get_party_instance(role='host', party_id=hosts). \
component_param(with_label=False,
output_format=output_format)
else:
data_transform_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(data_transform_0,
data=Data(data=reader_0.output.data))
# set data input sources of intersection components
pipeline.add_component(intersection_0,
data=Data(data=data_transform_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(work_mode=work_mode)
return pipeline
def make_add_one_hot_dsl(config, namespace, bin_param, is_multi_host=False):
parties = config.parties
guest = parties.guest[0]
hosts = parties.host
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
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)
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[0]).component_param(table=host_eval_data)
if is_multi_host:
reader_1.get_party_instance(
role='host',
party_id=hosts[1]).component_param(table=host_eval_data)
# define DataTransform components
data_transform_0 = DataTransform(
name="data_transform_0") # start component numbering at 0
data_transform_1 = DataTransform(name="data_transform_1")
# 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, output_format="dense")
# get and configure DataTransform party instance of host
data_transform_0.get_party_instance(
role='host', party_id=hosts[0]).component_param(with_label=False)
if is_multi_host:
data_transform_0.get_party_instance(
role='host', party_id=hosts[1]).component_param(with_label=False)
# define Intersection components
intersection_0 = Intersection(name="intersection_0")
intersection_1 = Intersection(name="intersection_1")
hetero_feature_binning_0 = HeteroFeatureBinning(**bin_param)
hetero_feature_binning_1 = HeteroFeatureBinning(
name='hetero_feature_binning_1')
one_hot_encoder_0 = OneHotEncoder(name='one_hot_encoder_0',
transform_col_indexes=-1,
transform_col_names=None,
need_run=True)
# add components to pipeline, in order of task execution
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
# set data_transform_1 to replicate model from data_transform_0
pipeline.add_component(data_transform_1,
data=Data(data=reader_1.output.data),
model=Model(data_transform_0.output.model))
# set data input sources of intersection components
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))
# 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(hetero_feature_binning_1,
data=Data(data=intersection_1.output.data),
model=Model(hetero_feature_binning_0.output.model))
pipeline.add_component(
one_hot_encoder_0,
data=Data(data=hetero_feature_binning_0.output.data))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
# pipeline.fit(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]
hosts = parties.host[0]
arbiter = parties.arbiter[0]
guest_train_data = {
"name": "vehicle_scale_homo_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "vehicle_scale_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=hosts, 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=hosts).component_param(table=host_train_data)
data_transform_0 = DataTransform(name="data_transform_0",
output_format='dense',
with_label=True)
pipeline.add_component(reader_0)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
lr_param = {
"penalty": "L2",
"optimizer": "sgd",
"tol": 1e-05,
"alpha": 0.01,
"early_stop": "diff",
"batch_size": -1,
"learning_rate": 0.15,
"decay": 1,
"decay_sqrt": True,
"init_param": {
"init_method": "zeros"
},
"encrypt_param": {
"method": "Paillier"
},
"cv_param": {
"n_splits": 4,
"shuffle": True,
"random_seed": 33,
"need_cv": False
},
"callback_param": {
"callbacks": ["ModelCheckpoint", "EarlyStopping"]
}
}
homo_lr_0 = HomoLR(name="homo_lr_0", max_iter=1, **lr_param)
homo_lr_1 = HomoLR(name="homo_lr_1")
pipeline.add_component(homo_lr_0,
data=Data(train_data=data_transform_0.output.data))
pipeline.add_component(homo_lr_1,
data=Data(test_data=data_transform_0.output.data),
model=Model(model=homo_lr_0.output.model))
evaluation_0 = Evaluation(name="evaluation_0", eval_type="multi")
pipeline.add_component(
evaluation_0,
data=Data(data=[homo_lr_0.output.data, homo_lr_1.output.data]))
pipeline.compile()
# fit model
pipeline.fit()
# query component summary
prettify(pipeline.get_component("evaluation_0").get_summary())
return pipeline
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": 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,
arbiter=arbiter)
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)
data_transform_0 = DataTransform(name="data_transform_0")
data_transform_0.get_party_instance(
role='guest', party_id=guest).component_param(with_label=True,
label_name="y",
label_type="int",
output_format="dense")
data_transform_0.get_party_instance(
role='host', party_id=host).component_param(with_label=False)
intersection_0 = Intersection(name="intersection_0")
sample_weight_0 = SampleWeight(name="sample_weight_0")
sample_weight_0.get_party_instance(
role='guest', party_id=guest).component_param(need_run=True,
class_weight="balanced")
sample_weight_0.get_party_instance(
role='host', party_id=host).component_param(need_run=False)
sample_weight_1 = SampleWeight(name="sample_weight_1")
hetero_lr_0 = HeteroLR(name="hetero_lr_0",
optimizer="nesterov_momentum_sgd",
tol=0.001,
alpha=0.01,
max_iter=20,
early_stop="weight_diff",
batch_size=-1,
learning_rate=0.15,
init_param={"init_method": "zeros"})
evaluation_0 = Evaluation(name="evaluation_0",
eval_type="binary",
pos_label=1)
# evaluation_0.get_party_instance(role='host', party_id=host).component_param(need_run=False)
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))
pipeline.add_component(sample_weight_0,
data=Data(data=intersection_0.output.data))
pipeline.add_component(sample_weight_1,
data=Data(data=intersection_0.output.data),
model=Model(model=sample_weight_0.output.model))
pipeline.add_component(hetero_lr_0,
data=Data(train_data=sample_weight_1.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_lr_0.output.data))
pipeline.compile()
pipeline.fit()
# predict
# deploy required components
pipeline.deploy_component(
[data_transform_0, intersection_0, sample_weight_0, hetero_lr_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()
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": 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=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)
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=host).component_param(table=host_eval_data)
# define DataTransform components
data_transform_0 = DataTransform(
name="data_transform_0") # start component numbering at 0
data_transform_1 = DataTransform(name="data_transform_1")
# 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, output_format="dense")
# get and configure DataTransform party instance of host
data_transform_0.get_party_instance(
role='host', party_id=host).component_param(with_label=False)
# define Intersection components
intersection_0 = Intersection(name="intersection_0")
intersection_1 = Intersection(name="intersection_1")
param = {"k": 3, "max_iter": 10}
hetero_kmeans_0 = HeteroKmeans(name='hetero_kmeans_0', **param)
hetero_kmeans_1 = HeteroKmeans(name='hetero_kmeans_1')
evaluation_0 = Evaluation(name='evaluation_0', eval_type='clustering')
evaluation_1 = Evaluation(name='evaluation_1', eval_type='clustering')
# add components to pipeline, in order of task execution
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))
# set data input sources of intersection components
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))
# set train & validate data of hetero_lr_0 component
pipeline.add_component(hetero_kmeans_0,
data=Data(train_data=intersection_0.output.data))
pipeline.add_component(hetero_kmeans_1,
data=Data(train_data=intersection_1.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]))
pipeline.add_component(evaluation_1,
data=Data(data=hetero_kmeans_1.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()
# query component summary
print(pipeline.get_component("hetero_kmeans_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 = {
"name": "breast_homo_guest",
"namespace": f"experiment_sid{namespace}"
}
host_train_data = {
"name": "breast_homo_host",
"namespace": f"experiment_sid{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_match_id=True,
with_label=True,
output_format="dense") # start component numbering at 0
scale_0 = FeatureScale(name='scale_0')
sample_weight_0 = SampleWeight(name="sample_weight_0",
class_weight={
"0": 1,
"1": 2
})
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": "Paillier"
},
"cv_param": {
"n_splits": 5,
"shuffle": True,
"random_seed": 33,
"need_cv": False
}
}
homo_lr_0 = HomoLR(name='homo_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(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(sample_weight_0,
data=Data(data=scale_0.output.data))
pipeline.add_component(homo_lr_0,
data=Data(train_data=sample_weight_0.output.data))
pipeline.add_component(evaluation_0, data=Data(data=homo_lr_0.output.data))
evaluation_0.get_party_instance(
role='host', party_id=host).component_param(need_run=False)
# 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("evaluation_0").get_summary(),
indent=4,
ensure_ascii=False))
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]
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)
data_transform_0 = DataTransform(name="data_transform_0")
data_transform_0.get_party_instance(
role='guest', party_id=guest).component_param(with_label=True)
data_transform_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(data_transform_0,
data=Data(data=reader_0.output.data))
pipeline.add_component(intersection_0,
data=Data(data=data_transform_0.output.data))
pipeline.add_component(hetero_feature_binning_0,
data=Data(data=intersection_0.output.data))
pipeline.compile()
pipeline.fit()
pipeline.deploy_component(
[data_transform_0, intersection_0, hetero_feature_binning_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()
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]
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)
data_transform_0 = DataTransform(name="data_transform_0")
data_transform_0.get_party_instance(
role='guest', party_id=guest).component_param(with_label=False,
output_format="dense")
data_transform_0.get_party_instance(
role='host', party_id=host).component_param(with_label=False,
output_format="dense")
param = {
"intersect_method": "rsa",
"sync_intersect_ids": False,
"only_output_key": True,
"rsa_params": {
"hash_method": "sha256",
"final_hash_method": "sha256",
"key_length": 2048
}
}
intersect_0 = Intersection(name="intersect_0", **param)
cache_loader_0 = CacheLoader(name="cache_loader_0",
job_id="",
component_name="intersect_0",
cache_name="cache")
pipeline.add_component(reader_0)
pipeline.add_component(cache_loader_0)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
pipeline.add_component(intersect_0,
data=Data(data=data_transform_0.output.data),
cache=Cache(cache_loader_0.output.cache))
pipeline.compile()
pipeline.fit()
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": 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).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") # start component numbering at 0
# 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, output_format="dense")
# get and configure DataTransform party instance of host
data_transform_0.get_party_instance(role='host', party_id=host).component_param(with_label=False)
# define Intersection components
intersection_0 = Intersection(name="intersection_0")
param = {
"name": 'hetero_feature_binning_0',
"method": 'optimal',
"optimal_binning_param": {
"metric_method": "iv"
},
"bin_indexes": -1
}
hetero_feature_binning_0 = HeteroFeatureBinning(**param)
param = {
"name": 'hetero_feature_selection_0',
"filter_methods": ["manually", "iv_filter"],
"manually_param": {
"filter_out_indexes": [1]
},
"iv_param": {
"metrics": ["iv", "iv"],
"filter_type": ["top_k", "threshold"],
"take_high": [True, True],
"threshold": [10, 0.001]
},
"select_col_indexes": -1
}
hetero_feature_selection_0 = HeteroFeatureSelection(**param)
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(data_transform_0, data=Data(data=reader_0.output.data))
# set data input sources of intersection components
pipeline.add_component(intersection_0, data=Data(data=data_transform_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))
pipeline.add_component(hetero_feature_selection_0, data=Data(data=intersection_0.output.data),
model=Model(isometric_model=hetero_feature_binning_0.output.model))
pipeline.add_component(hetero_kmeans_0, data=Data(train_data=hetero_feature_selection_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()
# query component summary
print(pipeline.get_component("hetero_kmeans_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 = {
"name": "breast_hetero_mini_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "breast_hetero_mini_host",
"namespace": f"experiment{namespace}"
}
pipeline = PipeLine().set_initiator(
role='guest', party_id=guest).set_roles(guest=guest,
host=host,
arbiter=arbiter)
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)
data_transform_0 = DataTransform(name="data_transform_0")
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)
intersection_0 = Intersection(name="intersection_0")
hetero_lr_0 = HeteroLR(name="hetero_lr_0",
early_stop="diff",
max_iter=5,
penalty="None",
optimizer="sgd",
tol=0.001,
batch_size=-1,
learning_rate=0.15,
decay=0.0,
decay_sqrt=False,
init_param={"init_method": "zeros"},
encrypted_mode_calculator_param={"mode": "fast"},
stepwise_param={
"score_name": "AIC",
"direction": "backward",
"need_stepwise": True,
"max_step": 2,
"nvmin": 2
})
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))
pipeline.add_component(hetero_lr_0,
data=Data(train_data=intersection_0.output.data))
pipeline.compile()
pipeline.fit()
def make_feature_engineering_dsl(config, namespace, lr_param, is_multi_host=False, has_validate=False,
is_cv=False, is_ovr=False):
parties = config.parties
guest = parties.guest[0]
if is_multi_host:
hosts = parties.host
else:
hosts = parties.host[0]
arbiter = parties.arbiter[0]
if is_ovr:
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}"}
else:
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}"}
train_line = []
# 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, 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=hosts).component_param(table=host_train_data)
# define DataTransform components
data_transform_0 = DataTransform(name="data_transform_0") # start component numbering at 0
# 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, output_format="dense")
# get and configure DataTransform party instance of host
data_transform_0.get_party_instance(role='host', party_id=hosts).component_param(with_label=False)
train_line.append(data_transform_0)
# 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))
train_line.append(intersection_0)
feature_scale_0 = FeatureScale(name='feature_scale_0', method="standard_scale",
need_run=True)
pipeline.add_component(feature_scale_0, data=Data(data=intersection_0.output.data))
train_line.append(feature_scale_0)
binning_param = {
"method": "quantile",
"compress_thres": 10000,
"head_size": 10000,
"error": 0.001,
"bin_num": 10,
"bin_indexes": -1,
"adjustment_factor": 0.5,
"local_only": False,
"need_run": True,
"transform_param": {
"transform_cols": -1,
"transform_type": "bin_num"
}
}
hetero_feature_binning_0 = HeteroFeatureBinning(name='hetero_feature_binning_0',
**binning_param)
pipeline.add_component(hetero_feature_binning_0, data=Data(data=feature_scale_0.output.data))
train_line.append(hetero_feature_binning_0)
selection_param = {
"select_col_indexes": -1,
"filter_methods": [
"manually",
"iv_value_thres",
"iv_percentile"
],
"manually_param": {
"filter_out_indexes": None
},
"iv_value_param": {
"value_threshold": 1.0
},
"iv_percentile_param": {
"percentile_threshold": 0.9
},
"need_run": True
}
hetero_feature_selection_0 = HeteroFeatureSelection(name='hetero_feature_selection_0',
**selection_param)
pipeline.add_component(hetero_feature_selection_0, data=Data(data=hetero_feature_binning_0.output.data),
model=Model(isometric_model=[hetero_feature_binning_0.output.model]))
train_line.append(hetero_feature_selection_0)
onehot_param = {
"transform_col_indexes": -1,
"transform_col_names": None,
"need_run": True
}
one_hot_encoder_0 = OneHotEncoder(name='one_hot_encoder_0', **onehot_param)
pipeline.add_component(one_hot_encoder_0, data=Data(data=hetero_feature_selection_0.output.data))
train_line.append(one_hot_encoder_0)
last_cpn = None
if has_validate:
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)
pipeline.add_component(reader_1)
last_cpn = reader_1
for cpn in train_line:
cpn_name = cpn.name
new_name = "_".join(cpn_name.split('_')[:-1] + ['1'])
validate_cpn = type(cpn)(name=new_name)
if hasattr(cpn.output, "model"):
pipeline.add_component(validate_cpn, data=Data(data=last_cpn.output.data),
model=Model(cpn.output.model))
else:
pipeline.add_component(validate_cpn, data=Data(data=last_cpn.output.data))
last_cpn = validate_cpn
hetero_lr_0 = HeteroLR(**lr_param)
if has_validate:
pipeline.add_component(hetero_lr_0, data=Data(train_data=one_hot_encoder_0.output.data,
validate_data=last_cpn.output.data))
else:
pipeline.add_component(hetero_lr_0, data=Data(train_data=one_hot_encoder_0.output.data))
if is_cv:
pipeline.compile()
return pipeline
evaluation_data = [hetero_lr_0.output.data]
if has_validate:
hetero_lr_1 = HeteroLR(name='hetero_lr_1')
pipeline.add_component(hetero_lr_1, data=Data(test_data=last_cpn.output.data),
model=Model(hetero_lr_0.output.model))
evaluation_data.append(hetero_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()
return pipeline
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": "mock_string",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "mock_string",
"namespace": f"experiment{namespace}"
}
guest_eval_data = {
"name": "mock_string",
"namespace": f"experiment{namespace}"
}
host_eval_data = {
"name": "mock_string",
"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)
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=host).component_param(table=host_eval_data)
# define DataTransform components
data_transform_0 = DataTransform(
name="data_transform_0",
with_label=True,
output_format="dense",
label_name='y',
data_type="str") # start component numbering at 0
data_transform_1 = DataTransform(name="data_transform_1")
homo_onehot_param = {
"transform_col_indexes": -1,
"transform_col_names": [],
"need_alignment": True
}
homo_onehot_0 = HomoOneHotEncoder(name='homo_onehot_0',
**homo_onehot_param)
homo_onehot_1 = HomoOneHotEncoder(name='homo_onehot_1')
scale_0 = FeatureScale(name='scale_0', method="standard_scale")
scale_1 = FeatureScale(name='scale_1')
homo_lr_param = {
"penalty": "L2",
"optimizer": "sgd",
"tol": 1e-05,
"alpha": 0.01,
"max_iter": 3,
"early_stop": "diff",
"batch_size": 500,
"learning_rate": 0.15,
"decay": 1,
"decay_sqrt": True,
"init_param": {
"init_method": "zeros"
},
"encrypt_param": {
"method": "Paillier"
},
"cv_param": {
"n_splits": 4,
"shuffle": True,
"random_seed": 33,
"need_cv": False
}
}
homo_lr_0 = HomoLR(name='homo_lr_0', **homo_lr_param)
homo_lr_1 = HomoLR(name='homo_lr_1')
# add components to pipeline, in order of task execution
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
# set data_transform_1 to replicate model from data_transform_0
pipeline.add_component(data_transform_1,
data=Data(data=reader_1.output.data),
model=Model(data_transform_0.output.model))
pipeline.add_component(homo_onehot_0,
data=Data(data=data_transform_0.output.data))
pipeline.add_component(homo_onehot_1,
data=Data(data=data_transform_1.output.data),
model=Model(homo_onehot_0.output.model))
pipeline.add_component(scale_0, data=Data(data=homo_onehot_0.output.data))
pipeline.add_component(scale_1,
data=Data(data=homo_onehot_1.output.data),
model=Model(scale_0.output.model))
pipeline.add_component(homo_lr_0,
data=Data(train_data=scale_0.output.data))
pipeline.add_component(homo_lr_1,
data=Data(test_data=scale_1.output.data),
model=Model(homo_lr_0.output.model))
evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary")
evaluation_0.get_party_instance(
role='host', party_id=host).component_param(need_run=False)
pipeline.add_component(
evaluation_0,
data=Data(data=[homo_lr_0.output.data, homo_lr_1.output.data]))
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))
print(
json.dumps(pipeline.get_component("evaluation_0").get_summary(),
indent=4,
ensure_ascii=False))
def make_normal_dsl(config, namespace, lr_param, is_multi_host=False, has_validate=False,
is_cv=False, is_ovr=False, is_dense=True, need_evaluation=True):
parties = config.parties
guest = parties.guest[0]
if is_multi_host:
hosts = parties.host
else:
hosts = parties.host[0]
arbiter = parties.arbiter[0]
if is_ovr:
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}"}
else:
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}"}
train_line = []
# 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, 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=hosts).component_param(table=host_train_data)
# define DataTransform components
if is_dense:
data_transform_0 = DataTransform(name="data_transform_0", output_format='dense')
else:
data_transform_0 = DataTransform(name="data_transform_0", output_format='sparse')
# 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)
train_line.append(data_transform_0)
# 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))
train_line.append(intersection_0)
last_cpn = None
if has_validate:
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)
pipeline.add_component(reader_1)
last_cpn = reader_1
for cpn in train_line:
cpn_name = cpn.name
new_name = "_".join(cpn_name.split('_')[:-1] + ['1'])
validate_cpn = type(cpn)(name=new_name)
if hasattr(cpn.output, "model"):
pipeline.add_component(validate_cpn, data=Data(data=last_cpn.output.data),
model=Model(cpn.output.model))
else:
pipeline.add_component(validate_cpn, data=Data(data=last_cpn.output.data))
last_cpn = validate_cpn
hetero_lr_0 = HeteroLR(**lr_param)
if has_validate:
pipeline.add_component(hetero_lr_0, data=Data(train_data=intersection_0.output.data,
validate_data=last_cpn.output.data))
else:
pipeline.add_component(hetero_lr_0, data=Data(train_data=intersection_0.output.data))
if is_cv:
pipeline.compile()
return pipeline
evaluation_data = [hetero_lr_0.output.data]
if has_validate:
hetero_lr_1 = HeteroLR(name='hetero_lr_1')
pipeline.add_component(hetero_lr_1, data=Data(test_data=last_cpn.output.data),
model=Model(hetero_lr_0.output.model))
evaluation_data.append(hetero_lr_1.output.data)
if need_evaluation:
evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary")
pipeline.add_component(evaluation_0, data=Data(data=evaluation_data))
pipeline.compile()
return pipeline
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
hosts = parties.host
arbiter = parties.arbiter[0]
guest_train_data = {
"name": "motor_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = [{
"name": "motor_hetero_host",
"namespace": f"experiment{namespace}"
}, {
"name": "motor_hetero_host",
"namespace": f"experiment{namespace}"
}]
pipeline = PipeLine().set_initiator(
role='guest', party_id=guest).set_roles(guest=guest,
host=hosts,
arbiter=arbiter)
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=hosts[0]).component_param(table=host_train_data[0])
reader_0.get_party_instance(
role='host',
party_id=hosts[1]).component_param(table=host_train_data[1])
data_transform_0 = DataTransform(name="data_transform_0")
data_transform_0.get_party_instance(
role='guest', party_id=guest).component_param(with_label=True,
label_name="motor_speed",
label_type="float",
output_format="dense")
data_transform_0.get_party_instance(
role='host', party_id=hosts).component_param(with_label=False)
intersection_0 = Intersection(name="intersection_0")
hetero_linr_0 = HeteroLinR(
name="hetero_linr_0",
penalty="None",
optimizer="sgd",
tol=0.001,
alpha=0.01,
max_iter=20,
early_stop="weight_diff",
batch_size=-1,
learning_rate=0.15,
decay=0.0,
decay_sqrt=False,
init_param={"init_method": "zeros"},
encrypted_mode_calculator_param={"mode": "fast"},
cv_param={
"n_splits": 5,
"shuffle": False,
"random_seed": 42,
"need_cv": True
})
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))
pipeline.add_component(hetero_linr_0,
data=Data(train_data=intersection_0.output.data))
pipeline.compile()
pipeline.fit()
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}"
}
guest_validate_data = {
"name": "breast_homo_test",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "breast_homo_host",
"namespace": f"experiment{namespace}"
}
host_validate_data = {
"name": "breast_homo_test",
"namespace": f"experiment{namespace}"
}
pipeline = PipeLine().set_initiator(
role='guest', party_id=guest).set_roles(guest=guest,
host=host,
arbiter=arbiter)
data_transform_0, data_transform_1 = DataTransform(
name="data_transform_0"), DataTransform(name='data_transform_1')
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)
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=True,
output_format="dense")
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_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=True,
output_format="dense")
homo_secureboost_0 = HomoSecureBoost(
name="homo_secureboost_0",
num_trees=3,
task_type='classification',
objective_param={"objective": "cross_entropy"},
tree_param={"max_depth": 3},
validation_freqs=1,
backend="memory")
evaluation_0 = Evaluation(name='evaluation_0', eval_type='binary')
pipeline.add_component(reader_0)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
pipeline.add_component(reader_1)
pipeline.add_component(data_transform_1,
data=Data(data=reader_1.output.data),
model=Model(data_transform_0.output.model))
pipeline.add_component(homo_secureboost_0,
data=Data(
train_data=data_transform_0.output.data,
validate_data=data_transform_1.output.data))
pipeline.add_component(evaluation_0,
data=Data(homo_secureboost_0.output.data))
pipeline.compile()
pipeline.fit()
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},
cipher_compress_error=8,
validation_freqs=1)
# 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())
def make_single_predict_pipeline(config,
namespace,
selection_param,
is_multi_host=False,
**kwargs):
parties = config.parties
guest = parties.guest[0]
if is_multi_host:
hosts = parties.host
else:
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)
# define DataTransform components
data_transform_0 = DataTransform(
name="data_transform_0") # start component numbering at 0
# 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, output_format="dense")
# 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))
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_1 = DataTransform(name="data_transform_1")
intersection_1 = Intersection(name="intersection_1")
pipeline.add_component(reader_1)
pipeline.add_component(data_transform_1,
data=Data(data=reader_1.output.data),
model=Model(data_transform_0.output.model))
pipeline.add_component(intersection_1,
data=Data(data=data_transform_1.output.data))
sample_0 = FederatedSample(name='sample_0', fractions=0.9)
pipeline.add_component(sample_0,
data=Data(data=intersection_0.output.data))
if "binning_param" not in kwargs:
raise ValueError("Binning_param is needed")
hetero_feature_binning_0 = HeteroFeatureBinning(**kwargs['binning_param'])
pipeline.add_component(hetero_feature_binning_0,
data=Data(data=sample_0.output.data))
hetero_feature_binning_1 = HeteroFeatureBinning(
name='hetero_feature_binning_1')
pipeline.add_component(hetero_feature_binning_1,
data=Data(data=intersection_1.output.data),
model=Model(hetero_feature_binning_0.output.model))
hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param)
pipeline.add_component(
hetero_feature_selection_0,
data=Data(data=hetero_feature_binning_0.output.data),
model=Model(isometric_model=[hetero_feature_binning_0.output.model]))
hetero_feature_selection_1 = HeteroFeatureSelection(
name='hetero_feature_selection_1')
pipeline.add_component(
hetero_feature_selection_1,
data=Data(data=hetero_feature_binning_1.output.data),
model=Model(hetero_feature_selection_0.output.model))
scale_0 = FeatureScale(name='scale_0')
scale_1 = FeatureScale(name='scale_1')
pipeline.add_component(
scale_0, data=Data(data=hetero_feature_selection_0.output.data))
pipeline.add_component(
scale_1,
data=Data(data=hetero_feature_selection_1.output.data),
model=Model(scale_0.output.model))
pipeline.compile()
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}"
}
# 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")
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]})
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))
pipeline.add_component(hetero_feature_selection_0,
data=Data(data=intersection_0.output.data))
lr_param = {
"name": "hetero_sshe_lr_0",
"penalty": None,
"optimizer": "sgd",
"tol": 0.0001,
"alpha": 0.01,
"max_iter": 30,
"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))
evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary")
pipeline.add_component(evaluation_0,
data=Data(data=hetero_sshe_lr_0.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("evaluation_0").get_summary())
return pipeline
def make_normal_dsl(config,
namespace,
selection_param,
is_multi_host=False,
host_dense_output=True,
**kwargs):
parties = config.parties
guest = parties.guest[0]
if is_multi_host:
hosts = parties.host
else:
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)
# define DataTransform components
data_transform_0 = DataTransform(
name="data_transform_0") # start component numbering at 0
# 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, output_format="dense")
# 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))
last_cpn = intersection_0
selection_include_model = []
if 'binning_param' in kwargs:
hetero_feature_binning_0 = HeteroFeatureBinning(
**kwargs['binning_param'])
pipeline.add_component(hetero_feature_binning_0,
data=Data(data=last_cpn.output.data))
selection_include_model.append(hetero_feature_binning_0)
# last_cpn = hetero_feature_binning_0
if 'statistic_param' in kwargs:
# print(f"param: {kwargs['statistic_param']}, kwargs: {kwargs}")
statistic_0 = DataStatistics(**kwargs['statistic_param'])
pipeline.add_component(statistic_0,
data=Data(data=last_cpn.output.data))
# last_cpn = statistic_0
selection_include_model.append(statistic_0)
if 'psi_param' in kwargs:
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_1 = DataTransform(name="data_transform_1")
intersection_1 = Intersection(name="intersection_1")
pipeline.add_component(reader_1)
pipeline.add_component(data_transform_1,
data=Data(data=reader_1.output.data),
model=Model(data_transform_0.output.model))
pipeline.add_component(intersection_1,
data=Data(data=data_transform_1.output.data))
psi_0 = PSI(**kwargs['psi_param'])
pipeline.add_component(psi_0,
data=Data(
train_data=intersection_0.output.data,
validate_data=intersection_1.output.data))
# last_cpn = statistic_0
selection_include_model.append(psi_0)
if 'sbt_param' in kwargs:
secureboost_0 = HeteroSecureBoost(**kwargs['sbt_param'])
pipeline.add_component(
secureboost_0, data=Data(train_data=intersection_0.output.data))
selection_include_model.append(secureboost_0)
if "fast_sbt_param" in kwargs:
fast_sbt_0 = HeteroFastSecureBoost(**kwargs['fast_sbt_param'])
pipeline.add_component(
fast_sbt_0, data=Data(train_data=intersection_0.output.data))
selection_include_model.append(fast_sbt_0)
hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param)
pipeline.add_component(
hetero_feature_selection_0,
data=Data(data=intersection_0.output.data),
model=Model(
isometric_model=[x.output.model for x in selection_include_model]))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
return pipeline
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": 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,
arbiter=arbiter)
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)
data_transform_0 = DataTransform(name="data_transform_0")
data_transform_0.get_party_instance(
role='guest', party_id=guest).component_param(with_label=True,
missing_fill=True,
outlier_replace=True)
data_transform_0.get_party_instance(
role='host', party_id=host).component_param(with_label=False,
missing_fill=True,
outlier_replace=True)
intersection_0 = Intersection(name="intersection_0")
federated_sample_0 = FederatedSample(name="federated_sample_0",
mode="stratified",
method="upsample",
fractions=[[0, 1.5], [1, 2.0]])
feature_scale_0 = FeatureScale(name="feature_scale_0",
method="min_max_scale",
mode="cap",
feat_upper=1,
feat_lower=0)
hetero_feature_binning_0 = HeteroFeatureBinning(
name="hetero_feature_binning_0")
hetero_feature_selection_0 = HeteroFeatureSelection(
name="hetero_feature_selection_0")
one_hot_0 = OneHotEncoder(name="one_hot_0")
hetero_lr_0 = HeteroLR(name="hetero_lr_0",
penalty="L2",
optimizer="rmsprop",
tol=1e-5,
init_param={"init_method": "random_uniform"},
alpha=0.01,
max_iter=10,
early_stop="diff",
batch_size=320,
learning_rate=0.15)
evaluation_0 = Evaluation(name="evaluation_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))
pipeline.add_component(federated_sample_0,
data=Data(data=intersection_0.output.data))
pipeline.add_component(feature_scale_0,
data=Data(data=federated_sample_0.output.data))
pipeline.add_component(hetero_feature_binning_0,
data=Data(data=feature_scale_0.output.data))
pipeline.add_component(
hetero_feature_selection_0,
data=Data(data=hetero_feature_binning_0.output.data))
pipeline.add_component(
one_hot_0, data=Data(data=hetero_feature_selection_0.output.data))
pipeline.add_component(hetero_lr_0,
data=Data(train_data=one_hot_0.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_lr_0.output.data))
pipeline.compile()
pipeline.fit()
print(pipeline.get_component("evaluation_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]
host = 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}"
}
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)
data_transform_0 = DataTransform(name="data_transform_0")
data_transform_0.get_party_instance(
role='guest', party_id=guest).component_param(with_label=True)
data_transform_0.get_party_instance(
role='host', party_id=host).component_param(with_label=False)
intersection_0 = Intersection(name="intersection_0")
param = {
"model_id": "guest-10000#host-9999#model",
"model_version": "202108301602196678300",
"component_name": "hetero_feature_binning_0",
"step_index": None
}
model_loader_0 = ModelLoader(name="model_loader_0", **param)
selection_param = {
"name": "hetero_feature_selection_0",
"select_col_indexes": -1,
"select_names": [],
"filter_methods": ["iv_filter"],
"iv_param": {
"metrics": ["iv", "iv", "iv"],
"filter_type": ["threshold", "top_k", "top_percentile"],
"take_high": True,
"threshold": [0.03, 15, 0.7],
"host_thresholds": [[0.15], None, None],
"select_federated": True
}
}
hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param)
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))
pipeline.add_component(model_loader_0)
pipeline.add_component(
hetero_feature_selection_0,
data=Data(data=intersection_0.output.data),
model=Model(isometric_model=model_loader_0.output.model))
pipeline.compile()
pipeline.fit()
