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": '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": ["x3", "x4"]
},
"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(intersection_1,
data=Data(data=dataio_1.output.data))
# set train & validate data of hetero_lr_0 component
pipeline.add_component(hetero_feature_binning_0,
data=Data(data=intersection_0.output.data))
pipeline.add_component(statistic_0,
data=Data(data=intersection_0.output.data))
pipeline.add_component(
hetero_feature_selection_0,
data=Data(data=intersection_0.output.data),
model=Model(isometric_model=[
hetero_feature_binning_0.output.model, statistic_0.output.model
]))
pipeline.add_component(hetero_feature_selection_1,
data=Data(data=intersection_1.output.data),
model=Model(
hetero_feature_selection_0.output.model))
pipeline.add_component(
hetero_scale_0, data=Data(data=hetero_feature_selection_0.output.data))
pipeline.add_component(
hetero_scale_1,
data=Data(data=hetero_feature_selection_1.output.data),
model=Model(hetero_scale_0.output.model))
# set train & validate data of hetero_lr_0 component
pipeline.add_component(hetero_lr_0,
data=Data(train_data=hetero_scale_0.output.data,
validate_data=hetero_scale_1.output.data))
pipeline.add_component(evaluation_0,
data=Data(data=[hetero_lr_0.output.data]))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
# fit model
pipeline.fit(backend=backend, work_mode=work_mode)
# query component summary
print(pipeline.get_component("hetero_lr_0").get_summary())
# # 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.scale import FeatureScale a = FeatureScale(name="scale_0") print(a.output.data)
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
arbiter = parties.arbiter[0]
backend = config.backend
work_mode = config.work_mode
guest_train_data = {
"name": "breast_homo_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "breast_homo_host",
"namespace": f"experiment{namespace}"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=host, arbiter=arbiter)
# define Reader components to read in data
reader_0 = Reader(name="reader_0")
# configure Reader for guest
reader_0.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
# configure Reader for host
reader_0.get_party_instance(
role='host', party_id=host).component_param(table=host_train_data)
# define DataIO components
dataio_0 = DataIO(name="dataio_0", with_label=True,
output_format="dense") # start component numbering at 0
scale_0 = FeatureScale(name='scale_0')
param = {
"penalty": "L2",
"optimizer": "sgd",
"tol": 1e-05,
"alpha": 0.01,
"max_iter": 30,
"early_stop": "diff",
"batch_size": -1,
"learning_rate": 0.15,
"decay": 1,
"decay_sqrt": True,
"init_param": {
"init_method": "zeros"
},
"encrypt_param": {
"method": None
},
"cv_param": {
"n_splits": 4,
"shuffle": True,
"random_seed": 33,
"need_cv": False
}
}
homo_lr_0 = HomoLR(name='homo_lr_0', **param)
# add components to pipeline, in order of task execution
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
# set data input sources of intersection components
pipeline.add_component(scale_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(homo_lr_0,
data=Data(train_data=scale_0.output.data))
evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary")
evaluation_0.get_party_instance(
role='host', party_id=host).component_param(need_run=False)
pipeline.add_component(evaluation_0, data=Data(data=homo_lr_0.output.data))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
# fit model
job_parameters = JobParameters(backend=backend, work_mode=work_mode)
pipeline.fit(job_parameters)
# query component summary
print(
json.dumps(pipeline.get_component("homo_lr_0").get_summary(),
indent=4,
ensure_ascii=False))
print(
json.dumps(pipeline.get_component("evaluation_0").get_summary(),
indent=4,
ensure_ascii=False))
def make_normal_dsl(config, namespace):
parties = config.parties
guest = parties.guest[0]
hosts = parties.host[0]
arbiter = parties.arbiter[0]
guest_train_data = {"name": "breast_homo_guest", "namespace": f"experiment{namespace}"}
host_train_data = {"name": "breast_homo_host", "namespace": f"experiment{namespace}"}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=hosts, arbiter=arbiter)
# define Reader components to read in data
reader_0 = Reader(name="reader_0")
# configure Reader for guest
reader_0.get_party_instance(role='guest', party_id=guest).component_param(table=guest_train_data)
# configure Reader for host
reader_0.get_party_instance(role='host', party_id=hosts).component_param(table=host_train_data)
# define 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=True)
scale_0 = FeatureScale(name='scale_0')
homo_sbt_0 = HomoSecureBoost(name="homo_secureboost_0",
num_trees=3,
task_type='classification',
objective_param={"objective": "cross_entropy"},
tree_param={
"max_depth": 3
},
validation_freqs=1
)
# define Intersection components
pipeline.add_component(reader_0)
pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data))
pipeline.add_component(scale_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(homo_sbt_0, data=Data(train_data=scale_0.output.data))
selection_param = {
"name": "hetero_feature_selection_0",
"select_col_indexes": -1,
"select_names": [],
"filter_methods": [
"homo_sbt_filter"
],
"sbt_param": {
"metrics": "feature_importance",
"filter_type": "threshold",
"take_high": True,
"threshold": 0.03
}}
feature_selection_0 = HeteroFeatureSelection(**selection_param)
param = {
"penalty": "L2",
"optimizer": "sgd",
"tol": 1e-05,
"alpha": 0.01,
"max_iter": 30,
"early_stop": "diff",
"batch_size": -1,
"learning_rate": 0.15,
"decay": 1,
"decay_sqrt": True,
"init_param": {
"init_method": "zeros"
},
"encrypt_param": {
"method": None
},
"cv_param": {
"n_splits": 4,
"shuffle": True,
"random_seed": 33,
"need_cv": False
}
}
homo_lr_0 = HomoLR(name='homo_lr_0', **param)
pipeline.add_component(feature_selection_0, data=Data(data=scale_0.output.data),
model=Model(isometric_model=homo_sbt_0.output.model))
pipeline.add_component(homo_lr_0, data=Data(train_data=feature_selection_0.output.data))
evaluation_0 = Evaluation(name='evaluation_0')
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()
return pipeline
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
arbiter = parties.arbiter[0]
guest_train_data_0 = {"name": "breast_hetero_guest", "namespace": "experiment"}
guest_train_data_1 = {"name": "breast_hetero_guest", "namespace": "experiment"}
guest_test_data_0 = {"name": "breast_hetero_guest", "namespace": "experiment"}
guest_test_data_1 = {"name": "breast_hetero_guest", "namespace": "experiment"}
host_train_data_0 = {"name": "breast_hetero_host_tag_value", "namespace": "experiment"}
host_train_data_1 = {"name": "breast_hetero_host_tag_value", "namespace": "experiment"}
host_test_data_0 = {"name": "breast_hetero_host_tag_value", "namespace": "experiment"}
host_test_data_1 = {"name": "breast_hetero_host_tag_value", "namespace": "experiment"}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=host, arbiter=arbiter)
# define Reader components to read in data
reader_0 = Reader(name="reader_0")
reader_1 = Reader(name="reader_1")
reader_2 = Reader(name="reader_2")
reader_3 = Reader(name="reader_3")
# configure Reader for guest
reader_0.get_party_instance(role='guest', party_id=guest).component_param(table=guest_train_data_0)
reader_1.get_party_instance(role='guest', party_id=guest).component_param(table=guest_train_data_1)
reader_2.get_party_instance(role='guest', party_id=guest).component_param(table=guest_test_data_0)
reader_3.get_party_instance(role='guest', party_id=guest).component_param(table=guest_test_data_1)
# configure Reader for host
reader_0.get_party_instance(role='host', party_id=host).component_param(table=host_train_data_0)
reader_1.get_party_instance(role='host', party_id=host).component_param(table=host_train_data_1)
reader_2.get_party_instance(role='host', party_id=host).component_param(table=host_test_data_0)
reader_3.get_party_instance(role='host', party_id=host).component_param(table=host_test_data_1)
param = {
"name": "union_0",
"keep_duplicate": True
}
union_0 = Union(**param)
param = {
"name": "union_1",
"keep_duplicate": True
}
union_1 = Union(**param)
param = {
"input_format": "tag",
"with_label": False,
"tag_with_value": True,
"delimitor": ";",
"output_format": "dense"
}
# define DataIO components
dataio_0 = DataIO(name="dataio_0") # start component numbering at 0
dataio_1 = DataIO(name="dataio_1") # start component numbering at 1
# get DataIO party instance of guest
dataio_0_guest_party_instance = dataio_0.get_party_instance(role='guest', party_id=guest)
# configure DataIO for guest
dataio_0_guest_party_instance.component_param(with_label=True, output_format="dense")
# get and configure DataIO party instance of host
dataio_0.get_party_instance(role='host', party_id=host).component_param(**param)
dataio_1.get_party_instance(role='guest', party_id=guest).component_param(with_label=True)
dataio_1.get_party_instance(role='host', party_id=host).component_param(**param)
# define Intersection components
intersection_0 = Intersection(name="intersection_0")
intersection_1 = Intersection(name="intersection_1")
param = {
"name": 'hetero_feature_binning_0',
"method": 'optimal',
"optimal_binning_param": {
"metric_method": "iv"
},
"bin_indexes": -1
}
hetero_feature_binning_0 = HeteroFeatureBinning(**param)
statistic_0 = DataStatistics(name='statistic_0')
param = {
"name": 'hetero_feature_selection_0',
"filter_methods": ["manually", "iv_filter", "statistic_filter"],
"manually_param": {
"filter_out_indexes": [1, 2],
"filter_out_names": ["x2", "x3"]
},
"iv_param": {
"metrics": ["iv", "iv"],
"filter_type": ["top_k", "threshold"],
"take_high": [True, True],
"threshold": [10, 0.01]
},
"statistic_param": {
"metrics": ["coefficient_of_variance", "skewness"],
"filter_type": ["threshold", "threshold"],
"take_high": [True, True],
"threshold": [0.001, -0.01]
},
"select_col_indexes": -1
}
hetero_feature_selection_0 = HeteroFeatureSelection(**param)
hetero_feature_selection_1 = HeteroFeatureSelection(name='hetero_feature_selection_1')
param = {
"name": "hetero_scale_0",
"method": "standard_scale"
}
hetero_scale_0 = FeatureScale(**param)
hetero_scale_1 = FeatureScale(name='hetero_scale_1')
param = {
"penalty": "L2",
"validation_freqs": None,
"early_stopping_rounds": None,
"max_iter": 5
}
hetero_lr_0 = HeteroLR(name='hetero_lr_0', **param)
evaluation_0 = Evaluation(name='evaluation_0')
# add components to pipeline, in order of task execution
pipeline.add_component(reader_0)
pipeline.add_component(reader_1)
pipeline.add_component(reader_2)
pipeline.add_component(reader_3)
pipeline.add_component(union_0, data=Data(data=[reader_0.output.data, reader_1.output.data]))
pipeline.add_component(union_1, data=Data(data=[reader_2.output.data, reader_3.output.data]))
pipeline.add_component(dataio_0, data=Data(data=union_0.output.data))
pipeline.add_component(dataio_1, data=Data(data=union_1.output.data), model=Model(dataio_0.output.model))
# set data input sources of intersection components
pipeline.add_component(intersection_0, data=Data(data=dataio_0.output.data))
pipeline.add_component(intersection_1, data=Data(data=dataio_1.output.data))
# set train & validate data of hetero_lr_0 component
pipeline.add_component(hetero_feature_binning_0, data=Data(data=intersection_0.output.data))
pipeline.add_component(statistic_0, data=Data(data=intersection_0.output.data))
pipeline.add_component(hetero_feature_selection_0, data=Data(data=intersection_0.output.data),
model=Model(isometric_model=[hetero_feature_binning_0.output.model,
statistic_0.output.model]))
pipeline.add_component(hetero_feature_selection_1, data=Data(data=intersection_1.output.data),
model=Model(hetero_feature_selection_0.output.model))
pipeline.add_component(hetero_scale_0, data=Data(data=hetero_feature_selection_0.output.data))
pipeline.add_component(hetero_scale_1, data=Data(data=hetero_feature_selection_1.output.data),
model=Model(hetero_scale_0.output.model))
# set train & validate data of hetero_lr_0 component
pipeline.add_component(hetero_lr_0, data=Data(train_data=hetero_scale_0.output.data,
validate_data=hetero_scale_1.output.data))
pipeline.add_component(evaluation_0, data=Data(data=[hetero_lr_0.output.data]))
# compile pipeline once finished adding modules, this step will form conf and dsl files for running job
pipeline.compile()
# fit model
pipeline.fit()
# query component summary
print(pipeline.get_component("hetero_lr_0").get_summary())
def make_single_predict_pipeline(config,
namespace,
selection_param,
is_multi_host=False,
**kwargs):
parties = config.parties
guest = parties.guest[0]
if is_multi_host:
hosts = parties.host
else:
hosts = parties.host[0]
guest_train_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
guest_eval_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_eval_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=hosts)
# define Reader components to read in data
reader_0 = Reader(name="reader_0")
# configure Reader for guest
reader_0.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
# configure Reader for host
reader_0.get_party_instance(
role='host', party_id=hosts).component_param(table=host_train_data)
# define 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))
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))
sample_0 = FederatedSample(name='sample_0', fractions=0.9)
pipeline.add_component(sample_0,
data=Data(data=intersection_0.output.data))
if "binning_param" not in kwargs:
raise ValueError("Binning_param is needed")
hetero_feature_binning_0 = HeteroFeatureBinning(**kwargs['binning_param'])
pipeline.add_component(hetero_feature_binning_0,
data=Data(data=sample_0.output.data))
hetero_feature_binning_1 = HeteroFeatureBinning(
name='hetero_feature_binning_1')
pipeline.add_component(hetero_feature_binning_1,
data=Data(data=intersection_1.output.data),
model=Model(hetero_feature_binning_0.output.model))
hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param)
pipeline.add_component(
hetero_feature_selection_0,
data=Data(data=hetero_feature_binning_0.output.data),
model=Model(isometric_model=[hetero_feature_binning_0.output.model]))
hetero_feature_selection_1 = HeteroFeatureSelection(
name='hetero_feature_selection_1')
pipeline.add_component(
hetero_feature_selection_1,
data=Data(data=hetero_feature_binning_1.output.data),
model=Model(hetero_feature_selection_0.output.model))
scale_0 = FeatureScale(name='scale_0')
scale_1 = FeatureScale(name='scale_1')
pipeline.add_component(
scale_0, data=Data(data=hetero_feature_selection_0.output.data))
pipeline.add_component(
scale_1,
data=Data(data=hetero_feature_selection_1.output.data),
model=Model(scale_0.output.model))
pipeline.compile()
return pipeline
def make_feature_engineering_dsl(config,
namespace,
lr_param,
is_multi_host=False,
has_validate=False,
is_cv=False,
is_ovr=False):
parties = config.parties
guest = parties.guest[0]
if is_multi_host:
hosts = parties.host
else:
hosts = parties.host[0]
arbiter = parties.arbiter[0]
if is_ovr:
guest_train_data = {
"name": "vehicle_scale_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "vehicle_scale_hetero_host",
"namespace": f"experiment{namespace}"
}
guest_eval_data = {
"name": "vehicle_scale_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_eval_data = {
"name": "vehicle_scale_hetero_host",
"namespace": f"experiment{namespace}"
}
else:
guest_train_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_train_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
guest_eval_data = {
"name": "breast_hetero_guest",
"namespace": f"experiment{namespace}"
}
host_eval_data = {
"name": "breast_hetero_host",
"namespace": f"experiment{namespace}"
}
train_line = []
# initialize pipeline
pipeline = PipeLine()
# set job initiator
pipeline.set_initiator(role='guest', party_id=guest)
# set participants information
pipeline.set_roles(guest=guest, host=hosts, arbiter=arbiter)
# define Reader components to read in data
reader_0 = Reader(name="reader_0")
# configure Reader for guest
reader_0.get_party_instance(
role='guest', party_id=guest).component_param(table=guest_train_data)
# configure Reader for host
reader_0.get_party_instance(
role='host', party_id=hosts).component_param(table=host_train_data)
# define 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)
train_line.append(dataio_0)
# 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))
train_line.append(intersection_0)
feature_scale_0 = FeatureScale(name='feature_scale_0',
method="standard_scale",
need_run=True)
pipeline.add_component(feature_scale_0,
data=Data(data=intersection_0.output.data))
train_line.append(feature_scale_0)
binning_param = {
"method": "quantile",
"compress_thres": 10000,
"head_size": 10000,
"error": 0.001,
"bin_num": 10,
"bin_indexes": -1,
"adjustment_factor": 0.5,
"local_only": False,
"need_run": True,
"transform_param": {
"transform_cols": -1,
"transform_type": "bin_num"
}
}
hetero_feature_binning_0 = HeteroFeatureBinning(
name='hetero_feature_binning_0', **binning_param)
pipeline.add_component(hetero_feature_binning_0,
data=Data(data=feature_scale_0.output.data))
train_line.append(hetero_feature_binning_0)
selection_param = {
"select_col_indexes": -1,
"filter_methods": ["manually", "iv_value_thres", "iv_percentile"],
"manually_param": {
"filter_out_indexes": None
},
"iv_value_param": {
"value_threshold": 1.0
},
"iv_percentile_param": {
"percentile_threshold": 0.9
},
"need_run": True
}
hetero_feature_selection_0 = HeteroFeatureSelection(
name='hetero_feature_selection_0', **selection_param)
pipeline.add_component(
hetero_feature_selection_0,
data=Data(data=hetero_feature_binning_0.output.data),
model=Model(isometric_model=[hetero_feature_binning_0.output.model]))
train_line.append(hetero_feature_selection_0)
onehot_param = {
"transform_col_indexes": -1,
"transform_col_names": None,
"need_run": True
}
one_hot_encoder_0 = OneHotEncoder(name='one_hot_encoder_0', **onehot_param)
pipeline.add_component(
one_hot_encoder_0,
data=Data(data=hetero_feature_selection_0.output.data))
train_line.append(one_hot_encoder_0)
last_cpn = None
if has_validate:
reader_1 = Reader(name="reader_1")
reader_1.get_party_instance(
role='guest',
party_id=guest).component_param(table=guest_eval_data)
reader_1.get_party_instance(
role='host', party_id=hosts).component_param(table=host_eval_data)
pipeline.add_component(reader_1)
last_cpn = reader_1
for cpn in train_line:
cpn_name = cpn.name
new_name = "_".join(cpn_name.split('_')[:-1] + ['1'])
validate_cpn = type(cpn)(name=new_name)
if hasattr(cpn.output, "model"):
pipeline.add_component(validate_cpn,
data=Data(data=last_cpn.output.data),
model=Model(cpn.output.model))
else:
pipeline.add_component(validate_cpn,
data=Data(data=last_cpn.output.data))
last_cpn = validate_cpn
hetero_lr_0 = HeteroLR(**lr_param)
if has_validate:
pipeline.add_component(hetero_lr_0,
data=Data(
train_data=one_hot_encoder_0.output.data,
validate_data=last_cpn.output.data))
else:
pipeline.add_component(
hetero_lr_0, data=Data(train_data=one_hot_encoder_0.output.data))
if is_cv:
pipeline.compile()
return pipeline
evaluation_data = [hetero_lr_0.output.data]
if has_validate:
hetero_lr_1 = HeteroLR(name='hetero_lr_1')
pipeline.add_component(hetero_lr_1,
data=Data(test_data=last_cpn.output.data),
model=Model(hetero_lr_0.output.model))
evaluation_data.append(hetero_lr_1.output.data)
evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary")
pipeline.add_component(evaluation_0, data=Data(data=evaluation_data))
pipeline.compile()
return pipeline
def main(config="../../config.yaml", namespace=""):
# obtain config
if isinstance(config, str):
config = load_job_config(config)
parties = config.parties
guest = parties.guest[0]
host = parties.host[0]
arbiter = parties.arbiter[0]
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))