def test_regression(self):
print('testing regression metric')
regression_metric.R2Score().compute(self.reg_score, self.reg_label)
regression_metric.MSE().compute(self.reg_score, self.reg_label)
regression_metric.RMSE().compute(self.reg_score, self.reg_label)
regression_metric.ExplainedVariance().compute(self.reg_score, self.reg_label)
regression_metric.Describe().compute(self.reg_score)
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]
backend = config.backend
work_mode = config.work_mode
# data sets
guest_train_data = {"name": param['data_guest_train'], "namespace": f"experiment{namespace}"}
host_train_data = {"name": param['data_host_train'], "namespace": f"experiment{namespace}"}
guest_validate_data = {"name": param['data_guest_val'], "namespace": f"experiment{namespace}"}
host_validate_data = {"name": param['data_host_val'], "namespace": f"experiment{namespace}"}
# init pipeline
pipeline = PipeLine().set_initiator(role="guest", party_id=guest).set_roles(guest=guest, host=host,)
# set data reader and data-io
reader_0, reader_1 = Reader(name="reader_0"), Reader(name="reader_1")
reader_0.get_party_instance(role="guest", party_id=guest).component_param(table=guest_train_data)
reader_0.get_party_instance(role="host", party_id=host).component_param(table=host_train_data)
reader_1.get_party_instance(role="guest", party_id=guest).component_param(table=guest_validate_data)
reader_1.get_party_instance(role="host", party_id=host).component_param(table=host_validate_data)
dataio_0, dataio_1 = DataIO(name="dataio_0"), DataIO(name="dataio_1")
dataio_0.get_party_instance(role="guest", party_id=guest).component_param(with_label=True, output_format="dense")
dataio_0.get_party_instance(role="host", party_id=host).component_param(with_label=False)
dataio_1.get_party_instance(role="guest", party_id=guest).component_param(with_label=True, output_format="dense")
dataio_1.get_party_instance(role="host", party_id=host).component_param(with_label=False)
# data intersect component
intersect_0 = Intersection(name="intersection_0")
intersect_1 = Intersection(name="intersection_1")
# secure boost component
hetero_fast_sbt_0 = HeteroFastSecureBoost(name="hetero_fast_sbt_0",
num_trees=param['tree_num'],
task_type=param['task_type'],
objective_param={"objective": param['loss_func']},
encrypt_param={"method": "iterativeAffine"},
tree_param={"max_depth": param['tree_depth']},
validation_freqs=1,
subsample_feature_rate=1,
learning_rate=param['learning_rate'],
guest_depth=param['guest_depth'],
host_depth=param['host_depth'],
tree_num_per_party=param['tree_num_per_party'],
work_mode=param['work_mode']
)
hetero_fast_sbt_1 = HeteroFastSecureBoost(name="hetero_fast_sbt_1")
# evaluation component
evaluation_0 = Evaluation(name="evaluation_0", eval_type=param['eval_type'])
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(dataio_1, data=Data(data=reader_1.output.data), model=Model(dataio_0.output.model))
pipeline.add_component(intersect_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(intersect_1, data=Data(data=dataio_1.output.data))
pipeline.add_component(hetero_fast_sbt_0, data=Data(train_data=intersect_0.output.data,
validate_data=intersect_1.output.data))
pipeline.add_component(hetero_fast_sbt_1, data=Data(test_data=intersect_1.output.data),
model=Model(hetero_fast_sbt_0.output.model))
pipeline.add_component(evaluation_0, data=Data(data=hetero_fast_sbt_0.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
sbt_0_data = pipeline.get_component("hetero_fast_sbt_0").get_output_data().get("data")
sbt_1_data = pipeline.get_component("hetero_fast_sbt_1").get_output_data().get("data")
sbt_0_score = extract_data(sbt_0_data, "predict_result")
sbt_0_label = extract_data(sbt_0_data, "label")
sbt_1_score = extract_data(sbt_1_data, "predict_result")
sbt_1_label = extract_data(sbt_1_data, "label")
sbt_0_score_label = extract_data(sbt_0_data, "predict_result", keep_id=True)
sbt_1_score_label = extract_data(sbt_1_data, "predict_result", keep_id=True)
metric_summary = parse_summary_result(pipeline.get_component("evaluation_0").get_summary())
if param['eval_type'] == "regression":
desc_sbt_0 = regression_metric.Describe().compute(sbt_0_score)
desc_sbt_1 = regression_metric.Describe().compute(sbt_1_score)
metric_summary["script_metrics"] = {"hetero_fast_sbt_train": desc_sbt_0,
"hetero_fast_sbt_validate": desc_sbt_1}
elif param['eval_type'] == "binary":
metric_sbt = {
"score_diversity_ratio": classification_metric.Distribution.compute(sbt_0_score_label, sbt_1_score_label),
"ks_2samp": classification_metric.KSTest.compute(sbt_0_score, sbt_1_score),
"mAP_D_value": classification_metric.AveragePrecisionScore().compute(sbt_0_score, sbt_1_score, sbt_0_label,
sbt_1_label)}
metric_summary["distribution_metrics"] = {"hetero_fast_sbt": metric_sbt}
elif param['eval_type'] == "multi":
metric_sbt = {
"score_diversity_ratio": classification_metric.Distribution.compute(sbt_0_score_label, sbt_1_score_label)}
metric_summary["distribution_metrics"] = {"hetero_fast_sbt": metric_sbt}
data_summary = {"train": {"guest": guest_train_data["name"], "host": host_train_data["name"]},
"test": {"guest": guest_train_data["name"], "host": host_train_data["name"]}
}
return data_summary, metric_summary
def main(config="../../config.yaml",
param="./sshe_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"],
"early_stop": param["early_stop"],
"reveal_strategy": param["reveal_strategy"],
"tol": 1e-6,
"reveal_every_iter": True
}
hetero_sshe_linr_0 = HeteroSSHELinR(name='hetero_sshe_linr_0', **param)
hetero_sshe_linr_1 = HeteroSSHELinR(name='hetero_sshe_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_sshe_linr_0,
data=Data(train_data=intersection_0.output.data))
pipeline.add_component(hetero_sshe_linr_1,
data=Data(test_data=intersection_0.output.data),
model=Model(hetero_sshe_linr_0.output.model))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_sshe_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_sshe_linr_0").get_output_data().get(
"data"), "predict_result")
data_linr_1 = extract_data(
pipeline.get_component("hetero_sshe_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",
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