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": "vehicle_scale_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_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,
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)
dataio_0 = DataIO(name="dataio_0")
dataio_0.get_party_instance(role='guest', party_id=guest).component_param(
with_label=True,
output_format="dense",
label_type="int",
label_name="y")
dataio_0.get_party_instance(
role='host', party_id=host).component_param(with_label=False)
intersection_0 = Intersection(name="intersection_0",
intersect_method="rsa",
sync_intersect_ids=True,
only_output_key=False)
hetero_lr_0 = HeteroLR(name="hetero_lr_0",
penalty="L2",
optimizer="nesterov_momentum_sgd",
tol=0.0001,
alpha=0.0001,
max_iter=30,
batch_size=-1,
early_stop="diff",
learning_rate=0.15,
init_param={"init_method": "zeros"})
local_baseline_0 = LocalBaseline(name="local_baseline_0",
model_name="LogisticRegression",
model_opts={
"penalty": "l2",
"tol": 0.0001,
"C": 1.0,
"fit_intercept": True,
"solver": "lbfgs",
"max_iter": 5,
"multi_class": "ovr"
})
local_baseline_0.get_party_instance(
role='guest', party_id=guest).component_param(need_run=True)
local_baseline_0.get_party_instance(
role='host', party_id=host).component_param(need_run=False)
evaluation_0 = Evaluation(name="evaluation_0",
eval_type="multi",
pos_label=1)
evaluation_0.get_party_instance(
role='guest', party_id=guest).component_param(need_run=True)
evaluation_0.get_party_instance(
role='host', party_id=host).component_param(need_run=False)
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(local_baseline_0,
data=Data(train_data=intersection_0.output.data))
pipeline.add_component(
evaluation_0,
data=Data(
data=[hetero_lr_0.output.data, local_baseline_0.output.data]))
pipeline.compile()
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
# predict
pipeline.deploy_component(
[dataio_0, intersection_0, hetero_lr_0, local_baseline_0])
predict_pipeline = PipeLine()
predict_pipeline.add_component(reader_0)
predict_pipeline.add_component(
pipeline,
data=Data(
predict_input={pipeline.dataio_0.input.data: reader_0.output.data
}))
predict_pipeline.add_component(
evaluation_0,
data=Data(
data=[hetero_lr_0.output.data, local_baseline_0.output.data]))
predict_pipeline.predict(job_parameters)
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}"
}
guest_eval_data = {
"name": "breast_homo_guest",
"namespace": f"experiment{namespace}"
}
host_eval_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)
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") # start component numbering at 0
data_transform_1 = DataTransform(
name="data_transform_1") # start component numbering at 0
scale_0 = FeatureScale(name='scale_0')
scale_1 = FeatureScale(name='scale_1')
param = {
"penalty": "L2",
"optimizer": "sgd",
"tol": 1e-05,
"alpha": 0.01,
"max_iter": 3,
"early_stop": "diff",
"batch_size": 320,
"learning_rate": 0.15,
"callback_param": {
"callbacks": ["EarlyStopping"],
"validation_freqs": 1
},
"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(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(scale_0,
data=Data(data=data_transform_0.output.data))
pipeline.add_component(scale_1,
data=Data(data=data_transform_1.output.data),
model=Model(scale_0.output.model))
pipeline.add_component(homo_lr_0,
data=Data(train_data=scale_0.output.data,
validate_data=scale_1.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()
# 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", 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]
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()
pipeline.fit()
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", param="./vehicle_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]
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 == "vehicle_scale_hetero_guest.csv":
guest_data_table = 'vehicle_scale_hetero_guest'
host_data_table = 'vehicle_scale_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 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 component
intersection_0 = Intersection(name="intersection_0")
lr_param = {
}
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",
"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="multi")
# 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(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.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
pipeline.fit()
# query component summary
result_summary = parse_summary_result(pipeline.get_component("evaluation_0").get_summary())
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_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)
metric_lr = {
"score_diversity_ratio": classification_metric.Distribution.compute(lr_0_score_label, lr_1_score_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]
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")
hetero_pearson_0 = HeteroPearson(name='hetero_pearson_0',
column_indexes=-1)
hetero_binning_0 = HeteroFeatureBinning(name='hetero_binning_0')
selection_param = {
"name": "hetero_feature_selection_0",
"select_col_indexes": -1,
"select_names": [],
"filter_methods": ["vif_filter", "correlation_filter"],
"vif_param": {
"threshold": 5
},
"correlation_param": {
"threshold": 0.5,
"select_federated": False
}
}
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(hetero_binning_0,
data=Data(data=intersection_0.output.data))
pipeline.add_component(hetero_pearson_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_pearson_0.output.model, hetero_binning_0.output.model
]))
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]
backend = config.backend
work_mode = config.work_mode
guest_train_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_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")
# configure Reader for guest
reader_0.get_party_instance(
role='guest', party_id=guest).algorithm_param(table=guest_train_data)
reader_1.get_party_instance(
role='guest', party_id=guest).algorithm_param(table=guest_test_data)
# configure Reader for host
reader_0.get_party_instance(
role='host', party_id=host).algorithm_param(table=host_train_data)
reader_1.get_party_instance(
role='host', party_id=host).algorithm_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
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.algorithm_param(**param)
# get and configure DataIO party instance of host
dataio_1.get_party_instance(role='guest',
party_id=guest).algorithm_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).algorithm_param(**param)
dataio_1.get_party_instance(role='host',
party_id=host).algorithm_param(**param)
# define Intersection components
intersection_0 = Intersection(name="intersection_0",
intersect_method="raw")
intersection_1 = Intersection(name="intersection_1",
intersect_method="raw")
param = {
'name': 'sample_0',
"mode": "stratified",
"method": "downsample",
"fractions": [[0, 0.5], [1, 0.8]],
"need_run": True
}
sample_0 = FederatedSample(**param)
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')
param = {"name": "hetero_scale_0", "method": "standard_scale"}
hetero_scale_0 = FeatureScale(**param)
hetero_scale_1 = FeatureScale(name='hetero_scale_1')
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)
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(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))
# set data input sources of intersection components
pipeline.add_component(intersection_0,
data=Data(data=dataio_0.output.data))
pipeline.add_component(sample_0,
data=Data(data=intersection_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=sample_0.output.data))
pipeline.add_component(statistic_0, data=Data(data=sample_0.output.data))
pipeline.add_component(
hetero_feature_selection_0,
data=Data(data=sample_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(backend=backend, work_mode=work_mode)
# 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 = [{"name": "motor_hetero_guest", "namespace": f"experiment{namespace}"},
{"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=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[0])
reader_0.get_party_instance(role='host', party_id=host).component_param(table=host_train_data[0])
reader_1 = Reader(name="reader_1")
reader_1.get_party_instance(role='guest', party_id=guest).component_param(table=guest_train_data[1])
reader_1.get_party_instance(role='host', party_id=host).component_param(table=host_train_data[1])
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=True, label_name="motor_speed",
label_type="float", 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, label_name="motor_speed",
label_type="float", output_format="dense")
data_transform_1.get_party_instance(role='host', party_id=host).component_param(with_label=False)
intersection_0 = Intersection(name="intersection_0")
intersect_1 = Intersection(name="intersection_1")
hetero_linr_0 = HeteroLinR(name="hetero_linr_0", penalty="L2", 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"},
callback_param={"callbacks": ["EarlyStopping", "PerformanceEvaluate"],
"validation_freqs": 1,
"early_stopping_rounds": 5,
"metrics": [
"mean_absolute_error",
"root_mean_squared_error"
],
"use_first_metric_only": False,
"save_freq": 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(intersect_1, data=Data(data=data_transform_1.output.data))
pipeline.add_component(hetero_linr_0, data=Data(train_data=intersection_0.output.data,
validate_data=intersect_1.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]
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')
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"],
"threshold": [2, 10, 0.9],
"mul_class_merge_type": ["max", "min", "average"]
}}
hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param)
hetero_feature_selection_1 = HeteroFeatureSelection(name="hetero_feature_selection_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.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))
pipeline.add_component(hetero_feature_selection_1, data=Data(data=hetero_feature_binning_1.output.data),
model=Model(hetero_feature_selection_0.output.model))
pipeline.compile()
pipeline.fit()
# predict
# deploy required components
pipeline.deploy_component([data_transform_0, intersection_0, hetero_feature_selection_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 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).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", with_label=True,
output_format="dense") # start component numbering at 0
dataio_0.get_party_instance(
role="host", party_id=host).component_param(with_label=False)
intersect_0 = Intersection(name='intersect_0')
scale_0 = FeatureScale(name='scale_0')
sample_weight_0 = SampleWeight(name="sample_weight_0",
class_weight={
"0": 1,
"1": 2
})
sample_weight_0.get_party_instance(
role="host", party_id=host).component_param(need_run=False)
param = {
"penalty": "L2",
"optimizer": "rmsprop",
"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"
},
"cv_param": {
"n_splits": 5,
"shuffle": True,
"random_seed": 33,
"need_cv": False
}
}
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(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(intersect_0, data=Data(data=dataio_0.output.data))
# set data input sources of intersection components
pipeline.add_component(scale_0, data=Data(data=intersect_0.output.data))
pipeline.add_component(sample_weight_0,
data=Data(data=scale_0.output.data))
pipeline.add_component(hetero_lr_0,
data=Data(train_data=sample_weight_0.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
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
# query component summary
print(
json.dumps(pipeline.get_component("evaluation_0").get_summary(),
indent=4,
ensure_ascii=False))
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]
arbiter = parties.arbiter[0]
guest_train_data = {
"name": param['data_guest_train'],
"namespace": f"experiment{namespace}"
}
guest_validate_data = {
"name": param['data_guest_val'],
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": param['data_host_train'],
"namespace": f"experiment{namespace}"
}
host_validate_data = {
"name": param['data_host_val'],
"namespace": f"experiment{namespace}"
}
pipeline = PipeLine().set_initiator(
role='guest', party_id=guest).set_roles(guest=guest,
host=host,
arbiter=arbiter)
dataio_0, dataio_1 = DataIO(name="dataio_0"), DataIO(name='dataio_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)
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=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)
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=True, output_format="dense")
homo_secureboost_0 = HomoSecureBoost(
name="homo_secureboost_0",
num_trees=param['tree_num'],
task_type=param['task_type'],
objective_param={"objective": param['loss_func']},
tree_param={"max_depth": param['tree_depth']},
validation_freqs=1,
subsample_feature_rate=1,
learning_rate=param['learning_rate'],
bin_num=50)
homo_secureboost_1 = HomoSecureBoost(name="homo_secureboost_1")
evaluation_0 = Evaluation(name='evaluation_0',
eval_type=param['eval_type'])
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(reader_1)
pipeline.add_component(dataio_1,
data=Data(data=reader_1.output.data),
model=Model(dataio_0.output.model))
pipeline.add_component(homo_secureboost_0,
data=Data(train_data=dataio_0.output.data,
validate_data=dataio_1.output.data))
pipeline.add_component(homo_secureboost_1,
data=Data(test_data=dataio_1.output.data),
model=Model(homo_secureboost_0.output.model))
pipeline.add_component(evaluation_0,
data=Data(homo_secureboost_0.output.data))
pipeline.compile()
pipeline.fit()
sbt_0_data = pipeline.get_component(
"homo_secureboost_0").get_output_data().get("data")
sbt_1_data = pipeline.get_component(
"homo_secureboost_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"] = {
"sbt_train": desc_sbt_0,
"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"] = {"homo_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"] = {"homo_sbt": metric_sbt}
data_summary = {
"train": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
},
"test": {
"guest": guest_validate_data["name"],
"host": host_validate_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]
backend = config.backend
work_mode = config.work_mode
guest_train_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
pipeline = PipeLine().set_initiator(
role='guest', party_id=guest).set_roles(guest=guest,
host=host,
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)
dataio_0 = DataIO(name="dataio_0")
dataio_0.get_party_instance(role='guest', party_id=guest).component_param(
with_label=True, missing_fill=True, outlier_replace=True)
dataio_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")
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)
hetero_lr_1 = HeteroLR(name="hetero_lr_1",
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,
cv_param={
"n_splits": 5,
"shuffle": True,
"random_seed": 103,
"need_cv": True
})
hetero_secureboost_0 = HeteroSecureBoost(name="hetero_secureboost_0",
num_trees=5,
cv_param={
"shuffle": False,
"need_cv": True
})
hetero_secureboost_1 = HeteroSecureBoost(name="hetero_secureboost_1",
num_trees=5)
evaluation_0 = Evaluation(name="evaluation_0")
evaluation_1 = Evaluation(name="evaluation_1")
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(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(hetero_lr_1,
data=Data(train_data=one_hot_0.output.data))
pipeline.add_component(hetero_secureboost_0,
data=Data(train_data=one_hot_0.output.data))
pipeline.add_component(hetero_secureboost_1,
data=Data(train_data=one_hot_0.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_lr_0.output.data))
pipeline.add_component(evaluation_1,
data=Data(data=hetero_secureboost_1.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
print(pipeline.get_component("evaluation_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_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)
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)
reader_2 = Reader(name="reader_2")
reader_2.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
reader_2.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)
data_transform_1 = DataTransform(name="data_transform_1")
data_transform_2 = DataTransform(name="data_transform_2")
intersection_0 = Intersection(name="intersection_0")
intersection_1 = Intersection(name="intersection_1")
intersection_2 = Intersection(name="intersection_2")
union_0 = Union(name="union_0")
federated_sample_0 = FederatedSample(name="federated_sample_0",
mode="stratified",
method="downsample",
fractions=[[0, 1.0], [1, 1.0]])
feature_scale_0 = FeatureScale(name="feature_scale_0")
feature_scale_1 = FeatureScale(name="feature_scale_1")
hetero_feature_binning_0 = HeteroFeatureBinning(
name="hetero_feature_binning_0")
hetero_feature_binning_1 = HeteroFeatureBinning(
name="hetero_feature_binning_1")
hetero_feature_selection_0 = HeteroFeatureSelection(
name="hetero_feature_selection_0")
hetero_feature_selection_1 = HeteroFeatureSelection(
name="hetero_feature_selection_1")
one_hot_0 = OneHotEncoder(name="one_hot_0")
one_hot_1 = OneHotEncoder(name="one_hot_1")
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=3,
early_stop="diff",
batch_size=320,
learning_rate=0.15)
hetero_lr_1 = HeteroLR(name="hetero_lr_1")
hetero_lr_2 = HeteroLR(name="hetero_lr_2",
penalty="L2",
optimizer="rmsprop",
tol=1e-5,
init_param={"init_method": "random_uniform"},
alpha=0.01,
max_iter=3,
early_stop="diff",
batch_size=320,
learning_rate=0.15,
cv_param={
"n_splits": 5,
"shuffle": True,
"random_seed": 103,
"need_cv": True
})
hetero_sshe_lr_0 = HeteroSSHELR(
name="hetero_sshe_lr_0",
reveal_every_iter=True,
reveal_strategy="respectively",
penalty="L2",
optimizer="rmsprop",
tol=1e-5,
batch_size=320,
learning_rate=0.15,
init_param={"init_method": "random_uniform"},
alpha=0.01,
max_iter=3)
hetero_sshe_lr_1 = HeteroSSHELR(name="hetero_sshe_lr_1")
local_baseline_0 = LocalBaseline(name="local_baseline_0",
model_name="LogisticRegression",
model_opts={
"penalty": "l2",
"tol": 0.0001,
"C": 1.0,
"fit_intercept": True,
"solver": "lbfgs",
"max_iter": 5,
"multi_class": "ovr"
})
local_baseline_0.get_party_instance(
role='guest', party_id=guest).component_param(need_run=True)
local_baseline_0.get_party_instance(
role='host', party_id=host).component_param(need_run=False)
local_baseline_1 = LocalBaseline(name="local_baseline_1")
hetero_secureboost_0 = HeteroSecureBoost(name="hetero_secureboost_0",
num_trees=3)
hetero_secureboost_1 = HeteroSecureBoost(name="hetero_secureboost_1")
hetero_secureboost_2 = HeteroSecureBoost(name="hetero_secureboost_2",
num_trees=3,
cv_param={
"shuffle": False,
"need_cv": True
})
hetero_linr_0 = HeteroLinR(name="hetero_linr_0",
penalty="L2",
optimizer="sgd",
tol=0.001,
alpha=0.01,
max_iter=3,
early_stop="weight_diff",
batch_size=-1,
learning_rate=0.15,
decay=0.0,
decay_sqrt=False,
init_param={"init_method": "zeros"},
floating_point_precision=23)
hetero_linr_1 = HeteroLinR(name="hetero_linr_1")
hetero_sshe_linr_0 = HeteroSSHELinR(name="hetero_sshe_linr_0",
max_iter=5,
early_stop="weight_diff",
batch_size=-1)
hetero_sshe_linr_1 = HeteroSSHELinR(name="hetero_sshe_linr_1")
hetero_poisson_0 = HeteroPoisson(name="hetero_poisson_0",
early_stop="weight_diff",
max_iter=10,
alpha=100.0,
batch_size=-1,
learning_rate=0.01,
optimizer="rmsprop",
exposure_colname="exposure",
decay_sqrt=False,
tol=0.001,
init_param={"init_method": "zeros"},
penalty="L2")
hetero_poisson_1 = HeteroPoisson(name="hetero_poisson_1")
hetero_sshe_poisson_0 = HeteroSSHEPoisson(name="hetero_sshe_poisson_0",
max_iter=5)
hetero_sshe_poisson_1 = HeteroSSHEPoisson(name="hetero_sshe_poisson_1")
evaluation_0 = Evaluation(name="evaluation_0")
evaluation_1 = Evaluation(name="evaluation_1")
evaluation_2 = Evaluation(name="evaluation_2")
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(reader_2)
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(model=data_transform_0.output.model))
pipeline.add_component(data_transform_2,
data=Data(data=reader_2.output.data),
model=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(intersection_2,
data=Data(data=data_transform_2.output.data))
pipeline.add_component(
union_0,
data=Data(
data=[intersection_0.output.data, intersection_2.output.data]))
pipeline.add_component(federated_sample_0,
data=Data(data=intersection_1.output.data))
pipeline.add_component(feature_scale_0,
data=Data(data=union_0.output.data))
pipeline.add_component(feature_scale_1,
data=Data(data=federated_sample_0.output.data),
model=Model(model=feature_scale_0.output.model))
pipeline.add_component(hetero_feature_binning_0,
data=Data(data=feature_scale_0.output.data))
pipeline.add_component(
hetero_feature_binning_1,
data=Data(data=feature_scale_1.output.data),
model=Model(model=hetero_feature_binning_0.output.model))
pipeline.add_component(
hetero_feature_selection_0,
data=Data(data=hetero_feature_binning_0.output.data))
pipeline.add_component(
hetero_feature_selection_1,
data=Data(data=hetero_feature_binning_1.output.data),
model=Model(model=hetero_feature_selection_0.output.model))
pipeline.add_component(
one_hot_0, data=Data(data=hetero_feature_selection_0.output.data))
pipeline.add_component(
one_hot_1,
data=Data(data=hetero_feature_selection_1.output.data),
model=Model(model=one_hot_0.output.model))
pipeline.add_component(hetero_lr_0,
data=Data(train_data=one_hot_0.output.data))
pipeline.add_component(hetero_lr_1,
data=Data(test_data=one_hot_1.output.data),
model=Model(model=hetero_lr_0.output.model))
pipeline.add_component(hetero_lr_2,
data=Data(train_data=one_hot_0.output.data))
pipeline.add_component(local_baseline_0,
data=Data(train_data=one_hot_0.output.data))
pipeline.add_component(local_baseline_1,
data=Data(test_data=one_hot_1.output.data),
model=Model(model=local_baseline_0.output.model))
pipeline.add_component(hetero_sshe_lr_0,
data=Data(train_data=one_hot_0.output.data))
pipeline.add_component(hetero_sshe_lr_1,
data=Data(test_data=one_hot_1.output.data),
model=Model(model=hetero_sshe_lr_0.output.model))
pipeline.add_component(hetero_secureboost_0,
data=Data(train_data=one_hot_0.output.data))
pipeline.add_component(
hetero_secureboost_1,
data=Data(test_data=one_hot_1.output.data),
model=Model(model=hetero_secureboost_0.output.model))
pipeline.add_component(hetero_secureboost_2,
data=Data(train_data=one_hot_0.output.data))
pipeline.add_component(hetero_linr_0,
data=Data(train_data=one_hot_0.output.data))
pipeline.add_component(hetero_linr_1,
data=Data(test_data=one_hot_1.output.data),
model=Model(model=hetero_linr_0.output.model))
pipeline.add_component(hetero_sshe_linr_0,
data=Data(train_data=one_hot_0.output.data))
pipeline.add_component(hetero_sshe_linr_1,
data=Data(test_data=one_hot_1.output.data),
model=Model(model=hetero_sshe_linr_0.output.model))
pipeline.add_component(hetero_poisson_0,
data=Data(train_data=one_hot_0.output.data))
pipeline.add_component(hetero_poisson_1,
data=Data(test_data=one_hot_1.output.data),
model=Model(model=hetero_poisson_0.output.model))
pipeline.add_component(
evaluation_0,
data=Data(data=[
hetero_lr_0.output.data, hetero_lr_1.output.data,
hetero_sshe_lr_0.output.data, hetero_sshe_lr_1.output.data,
local_baseline_0.output.data, local_baseline_1.output.data
]))
pipeline.add_component(hetero_sshe_poisson_0,
data=Data(train_data=one_hot_0.output.data))
pipeline.add_component(
hetero_sshe_poisson_1,
data=Data(test_data=one_hot_1.output.data),
model=Model(model=hetero_sshe_poisson_0.output.model))
pipeline.add_component(
evaluation_1,
data=Data(data=[
hetero_linr_0.output.data, hetero_linr_1.output.data,
hetero_sshe_linr_0.output.data, hetero_linr_1.output.data
]))
pipeline.add_component(
evaluation_2,
data=Data(data=[
hetero_poisson_0.output.data, hetero_poisson_1.output.data,
hetero_sshe_poisson_0.output.data,
hetero_sshe_poisson_1.output.data
]))
pipeline.compile()
pipeline.fit()
print(pipeline.get_component("evaluation_0").get_summary())
print(pipeline.get_component("evaluation_1").get_summary())
print(pipeline.get_component("evaluation_2").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]
backend = config.backend
work_mode = config.work_mode
guest_train_data = [{
"name": "tag_value_1",
"namespace": f"experiment{namespace}"
}, {
"name": "tag_value_2",
"namespace": f"experiment{namespace}"
}, {
"name": "tag_value_3",
"namespace": f"experiment{namespace}"
}]
pipeline = PipeLine().set_initiator(role='guest',
party_id=guest).set_roles(guest=guest)
reader_0 = Reader(name="reader_0")
reader_0.get_party_instance(
role='guest',
party_id=guest).component_param(table=guest_train_data[0])
reader_1 = Reader(name="reader_1")
reader_1.get_party_instance(
role='guest',
party_id=guest).component_param(table=guest_train_data[1])
reader_2 = Reader(name="reader_2")
reader_2.get_party_instance(
role='guest',
party_id=guest).component_param(table=guest_train_data[2])
union_0 = Union(name="union_0",
allow_missing=False,
keep_duplicate=True,
need_run=True)
dataio_0 = DataIO(name="dataio_0",
input_format="tag",
with_label=False,
tag_with_value=True,
delimitor=",",
output_format="dense")
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(reader_2)
pipeline.add_component(
union_0,
data=Data(data=[
reader_0.output.data, reader_1.output.data, reader_2.output.data
]))
pipeline.add_component(dataio_0, data=Data(data=union_0.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
def main(config="../../config.yaml", namespace=""):
if isinstance(config, str):
config = load_job_config(config)
backend = config.backend
work_mode = config.work_mode
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)
dataio_0 = DataIO(name="dataio_0", output_format='dense')
# 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)
# get and configure DataIO party instance of host
dataio_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(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(intersection_0,
data=Data(data=dataio_0.output.data))
statistic_param = {
"name": "statistic_0",
"statistics": ["95%", "coefficient_of_variance", "stddev"],
"column_indexes": -1,
"column_names": []
}
statistic_0 = DataStatistics(**statistic_param)
pipeline.add_component(statistic_0,
data=Data(data=intersection_0.output.data))
pipeline.compile()
# fit model
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
# query component summary
prettify(pipeline.get_component("statistic_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": "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=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 components
intersection_0 = Intersection(name="intersection_0",
intersect_method="rsa",
sync_intersect_ids=True,
only_output_key=False)
param = {
"penalty": "L2",
"optimizer": "nesterov_momentum_sgd",
"tol": 0.0001,
"alpha": 0.01,
"max_iter": 5,
"early_stop": "weight_diff",
"batch_size": -1,
"learning_rate": 0.15,
"init_param": {
"init_method": "random_uniform"
},
"sqn_param": {
"update_interval_L": 3,
"memory_M": 5,
"sample_size": 5000,
"random_seed": None
}
}
hetero_lr_0 = HeteroLR(name="hetero_lr_0", **param)
# define Scorecard component
scorecard_0 = Scorecard(name="scorecard_0")
scorecard_0.get_party_instance(
role="guest", party_id=guest).component_param(need_run=True,
method="credit",
offset=500,
factor=20,
factor_base=2,
upper_limit_ratio=3,
lower_limit_value=0)
scorecard_0.get_party_instance(
role="host", party_id=host).component_param(need_run=False)
# 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))
pipeline.add_component(hetero_lr_0,
data=Data(train_data=intersection_0.output.data))
pipeline.add_component(scorecard_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)
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": "dvisits_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "dvisits_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="doctorco",
label_type="float",
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_poisson_0 = HeteroPoisson(
name="hetero_poisson_0",
early_stop="weight_diff",
max_iter=3,
alpha=100.0,
batch_size=-1,
learning_rate=0.01,
optimizer="rmsprop",
exposure_colname="exposure",
decay_sqrt=False,
tol=0.001,
callback_param={"callbacks": ["ModelCheckpoint"]},
init_param={"init_method": "zeros"},
penalty="L2",
encrypted_mode_calculator_param={"mode": "fast"})
hetero_poisson_1 = HeteroPoisson(
name="hetero_poisson_1",
early_stop="weight_diff",
max_iter=10,
alpha=100.0,
batch_size=-1,
learning_rate=0.01,
optimizer="rmsprop",
exposure_colname="exposure",
decay_sqrt=False,
tol=0.001,
penalty="L2",
encrypted_mode_calculator_param={"mode": "fast"})
evaluation_0 = Evaluation(name="evaluation_0",
eval_type="regression",
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(hetero_poisson_0,
data=Data(train_data=intersection_0.output.data))
pipeline.add_component(hetero_poisson_1,
data=Data(train_data=intersection_0.output.data),
model=Model(model=hetero_poisson_0.output.model))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_poisson_1.output.data))
pipeline.compile()
pipeline.fit()
def main(config="../../config.yaml", param="./vechile_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)
"""
guest = 9999
host = 10000
arbiter = 9999
backend = 0
work_mode = 1
param = {"penalty": "L2", "max_iter": 5}
"""
data_set = param.get("data_guest").split('/')[-1]
if data_set == "vehicle_scale_hetero_guest.csv":
guest_data_table = 'vehicle_scale_hetero_guest'
host_data_table = 'vehicle_scale_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).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 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",
"init_param": {
"init_method": param.get("init_method", 'random_uniform')
}
}
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)
evaluation_0 = Evaluation(name='evaluation_0', eval_type="multi")
# 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(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(backend=backend, work_mode=work_mode)
# query component summary
print(pipeline.get_component("evaluation_0").get_summary())
result_summary = pipeline.get_component("evaluation_0").get_summary()
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]
backend = config.backend
work_mode = config.work_mode
guest_train_data = {"name": "ionosphere_scale_guest", "namespace": f"experiment{namespace}"}
guest_validate_data = {"name": "ionosphere_scale_guest", "namespace": f"experiment{namespace}"}
host_train_data = {"name": "ionosphere_scale_host", "namespace": f"experiment{namespace}"}
host_validate_data = {"name": "ionosphere_scale_host", "namespace": f"experiment{namespace}"}
pipeline = PipeLine().set_initiator(role='guest', party_id=guest).set_roles(guest=guest, host=host, arbiter=arbiter)
dataio_0, dataio_1 = DataIO(name="dataio_0"), DataIO(name='dataio_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)
dataio_0.get_party_instance(role='guest', party_id=guest).component_param(with_label=True, output_format="dense",
label_name="label")
dataio_0.get_party_instance(role='host', party_id=host).component_param(with_label=True, output_format="dense",
label_name="label")
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_1.get_party_instance(role='guest', party_id=guest).component_param(with_label=True, output_format="dense",
label_name="label")
dataio_1.get_party_instance(role='host', party_id=host).component_param(with_label=True, output_format="dense",
label_name="label")
homo_secureboost_0 = HomoSecureBoost(name="homo_secureboost_0",
num_trees=3,
task_type='classification',
objective_param={"objective": "cross_entropy"},
use_missing=True,
tree_param={
"max_depth": 3,
"use_missing": True
},
validation_freqs=1
)
evaluation_0 = Evaluation(name='evaluation_0', eval_type='binary')
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(reader_1)
pipeline.add_component(dataio_1, data=Data(data=reader_1.output.data), model=Model(dataio_0.output.model))
pipeline.add_component(homo_secureboost_0, data=Data(train_data=dataio_0.output.data,
validate_data=dataio_1.output.data
))
pipeline.add_component(evaluation_0, data=Data(homo_secureboost_0.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
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": "heart_nonscaled_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "heart_nonscaled_hetero_host",
"namespace": f"experiment{namespace}"
}
guest_eval_data = {
"name": "heart_nonscaled_hetero_test",
"namespace": f"experiment{namespace}"
}
host_eval_data = {
"name": "heart_nonscaled_hetero_test",
"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)
reader_1 = Reader(name="reader_1")
reader_1.get_party_instance(
role='guest', party_id=guest).algorithm_param(table=guest_eval_data)
reader_1.get_party_instance(
role='host', party_id=host).algorithm_param(table=host_eval_data)
# define DataIO components
dataio_0 = DataIO(name="dataio_0",
with_label=True,
output_format="dense",
label_name='target') # start component numbering at 0
dataio_1 = DataIO(name="dataio_1")
homo_onehot_param = {
"transform_col_indexes": [1, 2, 5, 6, 8, 10, 11, 12],
"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(dataio_0, data=Data(data=reader_0.output.data))
# set dataio_1 to replicate model from dataio_0
pipeline.add_component(dataio_1,
data=Data(data=reader_1.output.data),
model=Model(dataio_0.output.model))
pipeline.add_component(homo_onehot_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(homo_onehot_1,
data=Data(data=dataio_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).algorithm_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(backend=backend, work_mode=work_mode)
# 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=""):
# 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}"
}
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)
dataio_0 = DataIO(name="dataio_0")
dataio_0.get_party_instance(role='guest', party_id=guest).component_param(
with_label=True,
label_name="y",
label_type="int",
output_format="dense")
dataio_0.get_party_instance(
role='host', party_id=host).component_param(with_label=False)
intersection_0 = Intersection(name="intersection_0")
binning_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": -1,
"transform_names": None,
"transform_type": "bin_num"
}
}
selection_param = {
"name": "hetero_feature_selection_0",
"select_col_indexes": -1,
"select_names": [],
"filter_methods": ["iv_value_thres"],
"iv_value_param": {
"value_threshold": 0.1
}
}
hetero_feature_binning_0 = HeteroFeatureBinning(**binning_param)
hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param)
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={
"0": 1,
"1": 2
})
sample_weight_0.get_party_instance(
role='host', party_id=host).component_param(need_run=False)
feature_scale_0 = FeatureScale(name="feature_scale_0",
method="standard_scale",
need_run=True)
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(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(intersection_0,
data=Data(data=dataio_0.output.data))
pipeline.add_component(sample_weight_0,
data=Data(data=intersection_0.output.data))
pipeline.add_component(hetero_feature_binning_0,
data=Data(data=sample_weight_0.output.data))
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]))
pipeline.add_component(feature_scale_0,
data=Data(hetero_feature_selection_0.output.data))
pipeline.add_component(hetero_lr_0,
data=Data(train_data=feature_scale_0.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_lr_0.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
def main():
# parties config
guest = 9999
host = 10000
arbiter = 10000
# 0 for eggroll, 1 for spark
backend = Backend.EGGROLL
# 0 for standalone, 1 for cluster
work_mode = WorkMode.STANDALONE
# use the work mode below for cluster deployment
# work_mode = WorkMode.CLUSTER
# specify input data name & namespace in database
guest_train_data = {
"name": "breast_hetero_guest",
"namespace": "experiment"
}
host_train_data = {"name": "breast_hetero_host", "namespace": "experiment"}
guest_eval_data = {
"name": "breast_hetero_guest",
"namespace": "experiment"
}
host_eval_data = {"name": "breast_hetero_host", "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")
# 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 component
dataio_0 = DataIO(name="dataio_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")
# define HeteroLR component
hetero_lr_0 = HeteroLR(name="hetero_lr_0",
early_stop="diff",
learning_rate=0.15,
optimizer="rmsprop",
max_iter=10)
# 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_lr_0,
data=Data(train_data=intersection_0.output.data))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
# fit model
pipeline.fit(backend=backend, work_mode=work_mode)
# query component summary
import json
print(
json.dumps(pipeline.get_component("hetero_lr_0").get_summary(),
indent=4))
# predict
# deploy required components
pipeline.deploy_component([dataio_0, intersection_0, hetero_lr_0])
# initiate predict pipeline
predict_pipeline = PipeLine()
# define new data reader
reader_1 = Reader(name="reader_1")
reader_1.get_party_instance(
role="guest", party_id=guest).algorithm_param(table=guest_eval_data)
reader_1.get_party_instance(
role="host", party_id=host).algorithm_param(table=host_eval_data)
# define evaluation component
evaluation_0 = Evaluation(name="evaluation_0")
evaluation_0.get_party_instance(
role="guest", party_id=guest).algorithm_param(need_run=True,
eval_type="binary")
evaluation_0.get_party_instance(
role="host", party_id=host).algorithm_param(need_run=False)
# 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.dataio_0.input.data: reader_1.output.data
}))
# add evaluation component to predict pipeline
predict_pipeline.add_component(
evaluation_0, data=Data(data=pipeline.hetero_lr_0.output.data))
# run predict model
predict_pipeline.predict(backend=backend, work_mode=work_mode)
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}"
}
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 DataIO components
dataio_0 = DataIO(name="dataio_0") # start component numbering at 0
dataio_1 = DataIO(name="dataio_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(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(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))
# 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_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
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
# 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]
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_0 = {
"intersect_method": "rsa",
"rsa_params": {
"hash_method": "sha256",
"final_hash_method": "sha256",
"key_length": 2048
},
"run_cache": True
}
param_1 = {
"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_0)
intersect_1 = Intersection(name="intersect_1", **param_1)
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(intersect_1,
data=Data(data=data_transform_0.output.data),
cache=Cache(intersect_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]
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=4,
tree_num_per_party=1, task_type='classification',
objective_param={"objective": "cross_entropy"},
encrypt_param={"method": "iterativeAffine"},
tree_param={"max_depth": 3},
validation_freqs=1,
work_mode='mix')
# evaluation component
evaluation_0 = Evaluation(name="evaluation_0", eval_type="multi")
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]
guest_train_data = {
"name": "motor_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "motor_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,
label_name="motor_speed",
label_type="float",
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,
sample_weight_name="pm")
sample_weight_0.get_party_instance(
role='host', party_id=host).component_param(need_run=False)
hetero_linr_0 = HeteroSSHELinR(name="hetero_linr_0",
penalty="L2",
optimizer="rmsprop",
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"},
reveal_every_iter=True,
reveal_strategy="respectively")
evaluation_0 = Evaluation(name="evaluation_0",
eval_type="regression",
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(hetero_linr_0,
data=Data(train_data=sample_weight_0.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_linr_0.output.data))
pipeline.compile()
pipeline.fit()
# predict
# deploy required components
pipeline.deploy_component(
[data_transform_0, intersection_0, hetero_linr_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", param="param_conf.yaml", namespace=""):
num_host = 1
if isinstance(config, str):
config = load_job_config(config)
if isinstance(param, str):
param = JobConfig.load_from_file(param)
epoch = param["epoch"]
lr = param["lr"]
batch_size = param.get("batch_size", -1)
optimizer_name = param.get("optimizer", "Adam")
encode_label = param.get("encode_label", True)
loss = param.get("loss", "categorical_crossentropy")
metrics = param.get("metrics", ["accuracy"])
layers = param["layers"]
data = getattr(dataset, param.get("dataset", "vehicle"))
guest_train_data = data["guest"]
host_train_data = data["host"][:num_host]
for d in [guest_train_data, *host_train_data]:
d["namespace"] = f"{d['namespace']}{namespace}"
hosts = config.parties.host[:num_host]
pipeline = PipeLine() \
.set_initiator(role='guest', party_id=config.parties.guest[0]) \
.set_roles(guest=config.parties.guest[0], host=hosts, arbiter=config.parties.arbiter)
reader_0 = Reader(name="reader_0")
reader_0.get_party_instance(role='guest', party_id=config.parties.guest[0]).component_param(table=guest_train_data)
for i in range(num_host):
reader_0.get_party_instance(role='host', party_id=hosts[i]) \
.component_param(table=host_train_data[i])
dataio_0 = DataIO(name="dataio_0", with_label=True)
dataio_0.get_party_instance(role='guest', party_id=config.parties.guest[0]) \
.component_param(with_label=True, output_format="dense")
dataio_0.get_party_instance(role='host', party_id=hosts).component_param(with_label=True)
homo_nn_0 = HomoNN(name="homo_nn_0", encode_label=encode_label, max_iter=epoch, batch_size=batch_size,
early_stop={"early_stop": "diff", "eps": 0.0})
for layer_config in layers:
layer = getattr(tensorflow.keras.layers, layer_config["name"])
layer_params = layer_config["params"]
homo_nn_0.add(layer(**layer_params))
homo_nn_0.compile(optimizer=getattr(optimizers, optimizer_name)(learning_rate=lr), metrics=metrics,
loss=loss)
homo_nn_1 = HomoNN(name="homo_nn_1")
if param["loss"] == "categorical_crossentropy":
eval_type = "multi"
else:
eval_type = "binary"
evaluation_0 = Evaluation(name='evaluation_0', eval_type="multi", metrics=["accuracy", "precision", "recall"])
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(homo_nn_0, data=Data(train_data=dataio_0.output.data))
pipeline.add_component(homo_nn_1, data=Data(test_data=dataio_0.output.data),
model=Model(homo_nn_0.output.model))
pipeline.add_component(evaluation_0, data=Data(data=homo_nn_0.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=config.backend, work_mode=config.work_mode)
pipeline.fit(job_parameters)
metric_summary = parse_summary_result(pipeline.get_component("evaluation_0").get_summary())
nn_0_data = pipeline.get_component("homo_nn_0").get_output_data().get("data")
nn_1_data = pipeline.get_component("homo_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)
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"] = {"homo_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"] = {"homo_nn": metric_nn}
data_summary = dict(
train={"guest": guest_train_data["name"], **{f"host_{i}": host_train_data[i]["name"] for i in range(num_host)}},
test={"guest": guest_train_data["name"], **{f"host_{i}": host_train_data[i]["name"] for i in range(num_host)}}
)
return data_summary, metric_summary
def main(config="../../config.yaml", param="./linr_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]
if isinstance(param, str):
param = JobConfig.load_from_file(param)
guest_train_data = {"name": "motor_hetero_guest", "namespace": f"experiment{namespace}"}
host_train_data = {"name": "motor_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",
label_name=param["label_name"], label_type="float")
# 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 component
intersection_0 = Intersection(name="intersection_0")
param = {
"penalty": param["penalty"],
"max_iter": param["max_iter"],
"optimizer": param["optimizer"],
"learning_rate": param["learning_rate"],
"init_param": param["init_param"],
"batch_size": param["batch_size"],
"alpha": param["alpha"]
}
hetero_linr_0 = HeteroLinR(name='hetero_linr_0', **param)
hetero_linr_1 = HeteroLinR(name='hetero_linr_1')
evaluation_0 = Evaluation(name='evaluation_0', eval_type="regression",
metrics=["r2_score",
"mean_squared_error",
"root_mean_squared_error",
"explained_variance"])
# 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(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.add_component(hetero_linr_1,data=Data(test_data=intersection_0.output.data),
model=Model(hetero_linr_0.output.model))
pipeline.add_component(evaluation_0, data=Data(data=hetero_linr_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()
metric_summary = parse_summary_result(pipeline.get_component("evaluation_0").get_summary())
data_linr_0 = extract_data(pipeline.get_component("hetero_linr_0").get_output_data().get("data"), "predict_result")
data_linr_1 = extract_data(pipeline.get_component("hetero_linr_1").get_output_data().get("data"), "predict_result")
desc_linr_0 = regression_metric.Describe().compute(data_linr_0)
desc_linr_1 = regression_metric.Describe().compute(data_linr_1)
metric_summary["script_metrics"] = {"linr_train": desc_linr_0,
"linr_validate": desc_linr_1}
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]
backend = config.backend
work_mode = config.work_mode
guest_train_data = {"name": "breast_hetero_guest", "namespace": f"experiment{namespace}"}
host_train_data = {"name": "breast_hetero_host", "namespace": f"experiment{namespace}"}
pipeline = PipeLine().set_initiator(role='guest', party_id=guest).set_roles(guest=guest, host=host, 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)
dataio_0 = DataIO(name="dataio_0")
dataio_0.get_party_instance(role='guest', party_id=guest).component_param(with_label=True, label_name="y",
label_type="int", output_format="dense")
dataio_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,
sample_weight_name="x0")
sample_weight_0.get_party_instance(role='host', party_id=host).component_param(need_run=False)
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(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(intersection_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(sample_weight_0, data=Data(data=intersection_0.output.data))
pipeline.add_component(hetero_lr_0, data=Data(train_data=sample_weight_0.output.data))
pipeline.add_component(evaluation_0, data=Data(data=hetero_lr_0.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
# predict
# deploy required components
pipeline.deploy_component([dataio_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.dataio_0.input.data: reader_0.output.data}))
# run predict model
predict_pipeline.predict(job_parameters)
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")
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": "L2",
"optimizer": "sgd",
"tol": 0.0001,
"alpha": 0.01,
"max_iter": 30,
"early_stop": "weight_diff",
"batch_size": -1,
"learning_rate": 0.15,
"init_param": {
"init_method": "zeros",
"fit_intercept": False
},
"encrypt_param": {
"key_length": 1024
},
"reveal_every_iter": False,
"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=""):
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": None
},
"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
