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": "vehicle_scale_hetero_guest", "namespace": f"experiment{namespace}"}
host_train_data = {"name": "vehicle_scale_hetero_host", "namespace": f"experiment{namespace}"}
# init pipeline
pipeline = PipeLine().set_initiator(role="guest", party_id=guest).set_roles(guest=guest, host=host,)
# set data reader and data-io
reader_0 = Reader(name="reader_0")
reader_0.get_party_instance(role="guest", party_id=guest).component_param(table=guest_train_data)
reader_0.get_party_instance(role="host", party_id=host).component_param(table=host_train_data)
dataio_0 = DataIO(name="dataio_0")
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)
# data intersect component
intersect_0 = Intersection(name="intersection_0")
# secure boost component
hetero_secure_boost_0 = HeteroSecureBoost(name="hetero_secure_boost_0",
num_trees=3,
task_type="classification",
objective_param={"objective": "cross_entropy"},
encrypt_param={"method": "iterativeAffine"},
tree_param={"max_depth": 3},
validation_freqs=1,
cv_param={
"need_cv": True,
"n_splits": 5,
"shuffle": False,
"random_seed": 103
}
)
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(intersect_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(hetero_secure_boost_0, data=Data(train_data=intersect_0.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
print("fitting hetero secureboost done, result:")
print(pipeline.get_component("hetero_secure_boost_0").get_summary())
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
guest_train_data = {
"name": "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)
# 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).component_param(table=guest_train_data)
reader_1.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_test_data)
# configure Reader for host
reader_0.get_party_instance(
role='host', party_id=host).component_param(table=host_train_data)
reader_1.get_party_instance(
role='host', party_id=host).component_param(table=host_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.component_param(**param)
# get and configure DataIO party instance of host
dataio_1.get_party_instance(role='guest',
party_id=guest).component_param(**param)
param = {
"input_format": "tag",
"with_label": False,
"tag_with_value": True,
"delimitor": ";",
"output_format": "dense"
}
dataio_0.get_party_instance(role='host',
party_id=host).component_param(**param)
dataio_1.get_party_instance(role='host',
party_id=host).component_param(**param)
# define Intersection components
intersection_0 = Intersection(name="intersection_0",
intersect_method="raw")
intersection_1 = Intersection(name="intersection_1",
intersect_method="raw")
param = {
"name": 'hetero_feature_binning_0',
"method": 'optimal',
"optimal_binning_param": {
"metric_method": "iv",
"init_bucket_method": "quantile"
},
"bin_indexes": -1
}
hetero_feature_binning_0 = HeteroFeatureBinning(**param)
statistic_0 = DataStatistics(name='statistic_0')
param = {
"name":
'hetero_feature_selection_0',
"filter_methods":
["manually", "unique_value", "iv_filter", "statistic_filter"],
"manually_param": {
"filter_out_indexes": [1, 2],
"filter_out_names": ["x2", "x3"]
},
"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 = {
"task_type": "classification",
"learning_rate": 0.1,
"num_trees": 10,
"subsample_feature_rate": 0.5,
"n_iter_no_change": False,
"tol": 0.0002,
"bin_num": 50,
"objective_param": {
"objective": "cross_entropy"
},
"encrypt_param": {
"method": "paillier"
},
"predict_param": {
"threshold": 0.5
},
"tree_param": {
"max_depth": 2
},
"cv_param": {
"n_splits": 5,
"shuffle": False,
"random_seed": 103,
"need_cv": False
},
"validation_freqs": 2,
"early_stopping_rounds": 5,
"metrics": ["auc", "ks"]
}
hetero_secureboost_0 = HeteroSecureBoost(name='hetero_secureboost_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(intersection_1,
data=Data(data=dataio_1.output.data))
pipeline.add_component(hetero_feature_binning_0,
data=Data(data=intersection_0.output.data))
pipeline.add_component(statistic_0,
data=Data(data=intersection_0.output.data))
pipeline.add_component(
hetero_feature_selection_0,
data=Data(data=intersection_0.output.data),
model=Model(isometric_model=[
hetero_feature_binning_0.output.model, statistic_0.output.model
]))
pipeline.add_component(hetero_feature_selection_1,
data=Data(data=intersection_1.output.data),
model=Model(
hetero_feature_selection_0.output.model))
# set train & validate data of hetero_secureboost_0 component
pipeline.add_component(
hetero_secureboost_0,
data=Data(train_data=hetero_feature_selection_0.output.data,
validate_data=hetero_feature_selection_1.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_secureboost_0.output.data))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
# fit model
pipeline.fit()
# query component summary
print(pipeline.get_component("hetero_secureboost_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]
backend = config.backend
work_mode = config.work_mode
# data sets
guest_train_data = {"name": "student_hetero_guest", "namespace": f"experiment{namespace}"}
host_train_data = {"name": "student_hetero_host", "namespace": f"experiment{namespace}"}
guest_validate_data = {"name": "student_hetero_guest", "namespace": f"experiment{namespace}"}
host_validate_data = {"name": "student_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_secure_boost_0 = HeteroSecureBoost(name="hetero_secure_boost_0",
num_trees=5,
task_type="regression",
objective_param={"objective": "lse"},
encrypt_param={"method": "iterativeAffine"},
tree_param={"max_depth": 3},
validation_freqs=1,
early_stopping_rounds=1)
# evaluation component
evaluation_0 = Evaluation(name="evaluation_0", eval_type="regression")
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(dataio_1, data=Data(data=reader_1.output.data), model=Model(dataio_0.output.model))
pipeline.add_component(intersect_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(intersect_1, data=Data(data=dataio_1.output.data))
pipeline.add_component(hetero_secure_boost_0, data=Data(train_data=intersect_0.output.data,
validate_data=intersect_1.output.data))
pipeline.add_component(evaluation_0, data=Data(data=hetero_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_secure_boost_0").get_summary())
def make_normal_dsl(config,
namespace,
selection_param,
is_multi_host=False,
host_dense_output=True,
**kwargs):
parties = config.parties
guest = parties.guest[0]
if is_multi_host:
hosts = parties.host
else:
hosts = parties.host[0]
guest_train_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
guest_eval_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_eval_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=hosts)
# define Reader components to read in data
reader_0 = Reader(name="reader_0")
# configure Reader for guest
reader_0.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
# configure Reader for host
reader_0.get_party_instance(
role='host', party_id=hosts).component_param(table=host_train_data)
# define 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=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))
last_cpn = intersection_0
selection_include_model = []
if 'binning_param' in kwargs:
hetero_feature_binning_0 = HeteroFeatureBinning(
**kwargs['binning_param'])
pipeline.add_component(hetero_feature_binning_0,
data=Data(data=last_cpn.output.data))
selection_include_model.append(hetero_feature_binning_0)
# last_cpn = hetero_feature_binning_0
if 'statistic_param' in kwargs:
# print(f"param: {kwargs['statistic_param']}, kwargs: {kwargs}")
statistic_0 = DataStatistics(**kwargs['statistic_param'])
pipeline.add_component(statistic_0,
data=Data(data=last_cpn.output.data))
# last_cpn = statistic_0
selection_include_model.append(statistic_0)
if 'psi_param' in kwargs:
reader_1 = Reader(name="reader_1")
reader_1.get_party_instance(
role='guest',
party_id=guest).component_param(table=guest_eval_data)
reader_1.get_party_instance(
role='host', party_id=hosts).component_param(table=host_eval_data)
dataio_1 = DataIO(name="dataio_1")
intersection_1 = Intersection(name="intersection_1")
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(intersection_1,
data=Data(data=dataio_1.output.data))
psi_0 = PSI(**kwargs['psi_param'])
pipeline.add_component(psi_0,
data=Data(
train_data=intersection_0.output.data,
validate_data=intersection_1.output.data))
# last_cpn = statistic_0
selection_include_model.append(psi_0)
if 'sbt_param' in kwargs:
secureboost_0 = HeteroSecureBoost(**kwargs['sbt_param'])
pipeline.add_component(
secureboost_0, data=Data(train_data=intersection_0.output.data))
selection_include_model.append(secureboost_0)
if "fast_sbt_param" in kwargs:
fast_sbt_0 = HeteroFastSecureBoost(**kwargs['fast_sbt_param'])
pipeline.add_component(
fast_sbt_0, data=Data(train_data=intersection_0.output.data))
selection_include_model.append(fast_sbt_0)
hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param)
pipeline.add_component(
hetero_feature_selection_0,
data=Data(data=intersection_0.output.data),
model=Model(
isometric_model=[x.output.model for x in selection_include_model]))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
return pipeline
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
# data sets
guest_train_data = {
"name": "vehicle_scale_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "vehicle_scale_hetero_host",
"namespace": f"experiment{namespace}"
}
guest_validate_data = {
"name": "vehicle_scale_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_validate_data = {
"name": "vehicle_scale_hetero_host",
"namespace": f"experiment{namespace}"
}
# init pipeline
pipeline = PipeLine().set_initiator(role="guest",
party_id=guest).set_roles(
guest=guest,
host=host,
)
# set data reader and data-io
reader_0, reader_1 = Reader(name="reader_0"), Reader(name="reader_1")
reader_0.get_party_instance(
role="guest", party_id=guest).component_param(table=guest_train_data)
reader_0.get_party_instance(
role="host", party_id=host).component_param(table=host_train_data)
reader_1.get_party_instance(
role="guest",
party_id=guest).component_param(table=guest_validate_data)
reader_1.get_party_instance(
role="host", party_id=host).component_param(table=host_validate_data)
data_transform_0, data_transform_1 = DataTransform(
name="data_transform_0"), DataTransform(name="data_transform_1")
data_transform_0.get_party_instance(
role="guest", party_id=guest).component_param(with_label=True,
output_format="dense")
data_transform_0.get_party_instance(
role="host", party_id=host).component_param(with_label=False)
data_transform_1.get_party_instance(
role="guest", party_id=guest).component_param(with_label=True,
output_format="dense")
data_transform_1.get_party_instance(
role="host", party_id=host).component_param(with_label=False)
# data intersect component
intersect_0 = Intersection(name="intersection_0")
intersect_1 = Intersection(name="intersection_1")
# secure boost component
hetero_secure_boost_0 = HeteroSecureBoost(
name="hetero_secure_boost_0",
num_trees=3,
task_type="classification",
objective_param={"objective": "cross_entropy"},
encrypt_param={"method": "paillier"},
tree_param={"max_depth": 3},
validation_freqs=1)
# evaluation component
evaluation_0 = Evaluation(name="evaluation_0", eval_type="multi")
evaluation_1 = Evaluation(name="evaluation_1", eval_type="multi")
# transformer
transformer_0 = SBTTransformer(name='sbt_transformer_0', dense_format=True)
# local baseline
def get_local_baseline(idx):
return LocalBaseline(name="local_baseline_{}".format(idx),
model_name="LogisticRegression",
model_opts={
"penalty": "l2",
"tol": 0.0001,
"C": 1.0,
"fit_intercept": True,
"solver": "lbfgs",
"max_iter": 50
})
local_baseline_0 = get_local_baseline(0)
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 = get_local_baseline(1)
local_baseline_1.get_party_instance(
role='guest', party_id=guest).component_param(need_run=True)
local_baseline_1.get_party_instance(
role='host', party_id=host).component_param(need_run=False)
evaluation_1.get_party_instance(
role='host', party_id=host).component_param(need_run=False)
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(data_transform_0,
data=Data(data=reader_0.output.data))
pipeline.add_component(data_transform_1,
data=Data(data=reader_1.output.data),
model=Model(data_transform_0.output.model))
pipeline.add_component(intersect_0,
data=Data(data=data_transform_0.output.data))
pipeline.add_component(intersect_1,
data=Data(data=data_transform_1.output.data))
pipeline.add_component(hetero_secure_boost_0,
data=Data(train_data=intersect_0.output.data,
validate_data=intersect_1.output.data))
pipeline.add_component(
transformer_0,
data=Data(data=intersect_0.output.data),
model=Model(isometric_model=hetero_secure_boost_0.output.model))
pipeline.compile()
pipeline.fit()
# # Copyright 2019 The FATE Authors. All Rights Reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # from pipeline.component.hetero_secureboost import HeteroSecureBoost a = HeteroSecureBoost(name="hetero_secureboost_0") print(a.output.data) print(a.output.model)
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_secure_boost_0 = HeteroSecureBoost(
name="hetero_secure_boost_0",
num_trees=param['tree_num'],
task_type=param['task_type'],
objective_param={"objective": param['loss_func']},
encrypt_param={"method": "iterativeAffine"},
tree_param={"max_depth": param['tree_depth']},
validation_freqs=1,
learning_rate=param['learning_rate'])
hetero_secure_boost_1 = HeteroSecureBoost(name="hetero_secure_boost_1")
# evaluation component
evaluation_0 = Evaluation(name="evaluation_0",
eval_type=param['eval_type'])
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(dataio_1,
data=Data(data=reader_1.output.data),
model=Model(dataio_0.output.model))
pipeline.add_component(intersect_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(intersect_1, data=Data(data=dataio_1.output.data))
pipeline.add_component(hetero_secure_boost_0,
data=Data(train_data=intersect_0.output.data,
validate_data=intersect_1.output.data))
pipeline.add_component(hetero_secure_boost_1,
data=Data(test_data=intersect_1.output.data),
model=Model(hetero_secure_boost_0.output.model))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_secure_boost_0.output.data))
pipeline.compile()
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
sbt_0_data = pipeline.get_component(
"hetero_secure_boost_0").get_output_data().get("data")
sbt_1_data = pipeline.get_component(
"hetero_secure_boost_1").get_output_data().get("data")
sbt_0_score = extract_data(sbt_0_data, "predict_result")
sbt_0_label = extract_data(sbt_0_data, "label")
sbt_1_score = extract_data(sbt_1_data, "predict_result")
sbt_1_label = extract_data(sbt_1_data, "label")
sbt_0_score_label = extract_data(sbt_0_data,
"predict_result",
keep_id=True)
sbt_1_score_label = extract_data(sbt_1_data,
"predict_result",
keep_id=True)
metric_summary = parse_summary_result(
pipeline.get_component("evaluation_0").get_summary())
if param['eval_type'] == "regression":
desc_sbt_0 = regression_metric.Describe().compute(sbt_0_score)
desc_sbt_1 = regression_metric.Describe().compute(sbt_1_score)
metric_summary["script_metrics"] = {
"hetero_sbt_train": desc_sbt_0,
"hetero_sbt_validate": desc_sbt_1
}
elif param['eval_type'] == "binary":
metric_sbt = {
"score_diversity_ratio":
classification_metric.Distribution.compute(sbt_0_score_label,
sbt_1_score_label),
"ks_2samp":
classification_metric.KSTest.compute(sbt_0_score, sbt_1_score),
"mAP_D_value":
classification_metric.AveragePrecisionScore().compute(
sbt_0_score, sbt_1_score, sbt_0_label, sbt_1_label)
}
metric_summary["distribution_metrics"] = {"hetero_sbt": metric_sbt}
elif param['eval_type'] == "multi":
metric_sbt = {
"score_diversity_ratio":
classification_metric.Distribution.compute(sbt_0_score_label,
sbt_1_score_label)
}
metric_summary["distribution_metrics"] = {"hetero_sbt": metric_sbt}
data_summary = {
"train": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
},
"test": {
"guest": guest_train_data["name"],
"host": host_train_data["name"]
}
}
return data_summary, metric_summary
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
backend = config.backend
work_mode = config.work_mode
# data sets
guest_train_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
guest_validate_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_validate_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
# init pipeline
pipeline = PipeLine().set_initiator(role="guest",
party_id=guest).set_roles(
guest=guest,
host=host,
)
# set data reader and data-io
reader_0, reader_1 = Reader(name="reader_0"), Reader(name="reader_1")
reader_0.get_party_instance(
role="guest", party_id=guest).algorithm_param(table=guest_train_data)
reader_0.get_party_instance(
role="host", party_id=host).algorithm_param(table=host_train_data)
reader_1.get_party_instance(
role="guest",
party_id=guest).algorithm_param(table=guest_validate_data)
reader_1.get_party_instance(
role="host", party_id=host).algorithm_param(table=host_validate_data)
dataio_0, dataio_1 = DataIO(name="dataio_0"), DataIO(name="dataio_1")
dataio_0.get_party_instance(role="guest", party_id=guest).algorithm_param(
with_label=True, output_format="dense")
dataio_0.get_party_instance(
role="host", party_id=host).algorithm_param(with_label=False)
dataio_1.get_party_instance(role="guest", party_id=guest).algorithm_param(
with_label=True, output_format="dense")
dataio_1.get_party_instance(
role="host", party_id=host).algorithm_param(with_label=False)
# data intersect component
intersect_0 = Intersection(name="intersection_0")
intersect_1 = Intersection(name="intersection_1")
# secure boost component
hetero_secure_boost_0 = HeteroSecureBoost(
name="hetero_secure_boost_0",
num_trees=5,
task_type="classification",
objective_param={"objective": "cross_entropy"},
encrypt_param={"method": "iterativeAffine"},
tree_param={"max_depth": 3},
validation_freqs=1)
# evaluation component
evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary")
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(dataio_1,
data=Data(data=reader_1.output.data),
model=Model(dataio_0.output.model))
pipeline.add_component(intersect_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(intersect_1, data=Data(data=dataio_1.output.data))
pipeline.add_component(hetero_secure_boost_0,
data=Data(train_data=intersect_0.output.data,
validate_data=intersect_1.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_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_secure_boost_0").get_summary())
print('start to predict')
# predict
# deploy required components
pipeline.deploy_component([dataio_0, intersect_0, hetero_secure_boost_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(backend=backend, work_mode=work_mode)
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).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_secure_boost_0 = HeteroSecureBoost(
name="hetero_secure_boost_0",
num_trees=param['tree_num'],
task_type=param['task_type'],
objective_param={"objective": param['loss_func']},
encrypt_param={"method": "iterativeAffine"},
tree_param={"max_depth": param['tree_depth']},
validation_freqs=1,
learning_rate=param['learning_rate'])
# evaluation component
evaluation_0 = Evaluation(name="evaluation_0",
eval_type=param['eval_type'])
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(dataio_1,
data=Data(data=reader_1.output.data),
model=Model(dataio_0.output.model))
pipeline.add_component(intersect_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(intersect_1, data=Data(data=dataio_1.output.data))
pipeline.add_component(hetero_secure_boost_0,
data=Data(train_data=intersect_0.output.data,
validate_data=intersect_1.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=hetero_secure_boost_0.output.data))
pipeline.compile()
pipeline.fit(backend=backend, work_mode=work_mode)
return {}, pipeline.get_component("evaluation_0").get_summary()