def main(config="../../config.yaml", namespace=""): if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] guest_train_data = { "name": "breast_hetero_guest", "namespace": f"experiment{namespace}" } host_train_data = { "name": "breast_hetero_host", "namespace": f"experiment{namespace}" } pipeline = PipeLine().set_initiator(role='guest', party_id=guest).set_roles(guest=guest, host=host) reader_0 = Reader(name="reader_0") reader_0.get_party_instance( role='guest', party_id=guest).component_param(table=guest_train_data) reader_0.get_party_instance( role='host', party_id=host).component_param(table=host_train_data) data_transform_0 = DataTransform(name="data_transform_0") data_transform_0.get_party_instance( role='guest', party_id=guest).component_param(with_label=True) data_transform_0.get_party_instance( role='host', party_id=host).component_param(with_label=False) intersection_0 = Intersection(name="intersection_0") param = { "name": "hetero_feature_binning_0", "method": "quantile", "compress_thres": 10000, "head_size": 10000, "error": 0.001, "bin_num": 10, "bin_indexes": -1, "bin_names": None, "category_indexes": None, "category_names": None, "adjustment_factor": 0.5, "local_only": False, "transform_param": { "transform_cols": [0, 1, 2], "transform_names": None, "transform_type": "woe" } } hetero_feature_binning_0 = HeteroFeatureBinning(**param) hetero_feature_binning_0.get_party_instance( role="host", party_id=host).component_param( transform_param={"transform_type": None}) pipeline.add_component(reader_0) pipeline.add_component(data_transform_0, data=Data(data=reader_0.output.data)) pipeline.add_component(intersection_0, data=Data(data=data_transform_0.output.data)) pipeline.add_component(hetero_feature_binning_0, data=Data(data=intersection_0.output.data)) pipeline.compile() pipeline.fit()
def main(config="../../config.yaml", param="./lr_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 == "default_credit_hetero_guest.csv": guest_data_table = 'default_credit_hetero_guest' host_data_table = 'default_credit_hetero_host' elif data_set == 'breast_hetero_guest.csv': guest_data_table = 'breast_hetero_guest' host_data_table = 'breast_hetero_host' elif data_set == 'give_credit_hetero_guest.csv': guest_data_table = 'give_credit_hetero_guest' host_data_table = 'give_credit_hetero_host' elif data_set == 'epsilon_5k_hetero_guest.csv': guest_data_table = 'epsilon_5k_hetero_guest' host_data_table = 'epsilon_5k_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", "tol": 1e-5, "floating_point_precision": param.get("floating_point_precision"), "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="binary") # 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 job_parameters = JobParameters() pipeline.fit(job_parameters) 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 = extract_data(lr_0_data, "predict_result") lr_0_label = extract_data(lr_0_data, "label") lr_1_score = extract_data(lr_1_data, "predict_result") lr_1_label = extract_data(lr_1_data, "label") 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) result_summary = parse_summary_result( pipeline.get_component("evaluation_0").get_summary()) metric_lr = { "score_diversity_ratio": classification_metric.Distribution.compute(lr_0_score_label, lr_1_score_label), "ks_2samp": classification_metric.KSTest.compute(lr_0_score, lr_1_score), "mAP_D_value": classification_metric.AveragePrecisionScore().compute( lr_0_score, lr_1_score, lr_0_label, lr_1_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] 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") # 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") param = {"k": 3, "max_iter": 10} hetero_kmeans_0 = HeteroKmeans(name='hetero_kmeans_0', **param) evaluation_0 = Evaluation(name='evaluation_0', eval_type='clustering') # add components to pipeline, in order of task execution pipeline.add_component(reader_0) pipeline.add_component(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_kmeans_0, data=Data(train_data=intersection_0.output.data)) print(f"data: {hetero_kmeans_0.output.data.data[0]}") pipeline.add_component(evaluation_0, data=Data(data=hetero_kmeans_0.output.data.data[0])) # compile pipeline once finished adding modules, this step will form conf and dsl files for running job pipeline.compile() # fit model 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] # 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).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="regression", objective_param={"objective": "lse"}, encrypt_param={"method": "Paillier"}, 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(data_transform_0, data=Data(data=reader_0.output.data)) pipeline.add_component(data_transform_1, data=Data(data=reader_1.output.data), model=Model(data_transform_0.output.model)) pipeline.add_component(intersect_0, data=Data(data=data_transform_0.output.data)) pipeline.add_component(intersect_1, data=Data(data=data_transform_1.output.data)) pipeline.add_component(hetero_secure_boost_0, data=Data(train_data=intersect_0.output.data, validate_data=intersect_1.output.data)) pipeline.add_component(evaluation_0, data=Data(data=hetero_secure_boost_0.output.data)) pipeline.compile() pipeline.fit() print("fitting hetero secureboost done, result:") print(pipeline.get_component("hetero_secure_boost_0").get_summary())
def 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_homo_guest", "namespace": f"experiment{namespace}" } guest_validate_data = { "name": "breast_homo_test", "namespace": f"experiment{namespace}" } host_train_data = { "name": "breast_homo_host", "namespace": f"experiment{namespace}" } host_validate_data = { "name": "breast_homo_test", "namespace": f"experiment{namespace}" } pipeline = PipeLine().set_initiator( role='guest', party_id=guest).set_roles(guest=guest, host=host, arbiter=arbiter) 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=3, task_type='classification', objective_param={"objective": "cross_entropy"}, tree_param={"max_depth": 3}, 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) # predict # deploy required components pipeline.deploy_component([dataio_0, homo_secureboost_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.dataio_0.input.data: reader_1.output.data })) # run predict model 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_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_roles(guest=guest, host=host, arbiter=arbiter) # define Reader components to read in data reader_0 = Reader(name="reader_0") # configure Reader 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") # start component numbering at 0 data_transform_0_guest_party_instance = data_transform_0.get_party_instance(role="guest", party_id=guest) data_transform_0_guest_party_instance.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") intersection_0 = Intersection(name="intersection_0") label_transform_0 = LabelTransform(name="label_transform_0", label_encoder={"0": 1, "1": 0}, label_list=[0, 1]) label_transform_0.get_party_instance(role="host", party_id=host).component_param(need_run=False) hetero_lr_0 = HeteroLR(name="hetero_lr_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"}, floating_point_precision=23) label_transform_1 = LabelTransform(name="label_transform_1") # 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(label_transform_0, data=Data(data=intersection_0.output.data)) pipeline.add_component(hetero_lr_0, data=Data(train_data=label_transform_0.output.data)) pipeline.add_component(label_transform_1, data=Data(data=hetero_lr_0.output.data), model=Model(label_transform_0.output.model)) # compile pipeline once finished adding modules, this step will form conf and dsl files for running job pipeline.compile() # fit model pipeline.fit()
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] arbiter = parties.arbiter[0] backend = config.backend work_mode = config.work_mode 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).algorithm_param(table=guest_train_data) reader_0.get_party_instance( role='host', party_id=host).algorithm_param(table=host_train_data) dataio_0 = DataIO(name="dataio_0") dataio_0.get_party_instance(role='guest', party_id=guest).algorithm_param( with_label=True, output_format="dense", label_name="doctorco", label_type="float", ) dataio_0.get_party_instance( role='host', party_id=host).algorithm_param(with_label=False) intersection_0 = Intersection(name="intersection_0") hetero_poisson_0 = HeteroPoisson( name="hetero_poisson_0", early_stop="diff", max_iter=5, penalty="None", optimizer="sgd", tol=0.001, batch_size=-1, learning_rate=0.15, decay=0.0, decay_sqrt=False, alpha=0.01, init_param={"init_method": "zeros"}, encrypted_mode_calculator_param={"mode": "fast"}, stepwise_param={ "score_name": "AIC", "direction": "both", "need_stepwise": True, "max_step": 1, "nvmin": 2 }) 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_poisson_0, data=Data(train_data=intersection_0.output.data)) pipeline.compile() pipeline.fit(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] 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) reader_0 = Reader(name="reader_0") 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) dataio_0 = DataIO(name="dataio_0") dataio_0.get_party_instance( role='guest', party_id=guest).algorithm_param(with_label=True) dataio_0.get_party_instance( role='host', party_id=host).algorithm_param(with_label=False) intersection_0 = Intersection(name="intersection_0") hetero_nn_0 = HeteroNN(name="hetero_nn_0", epochs=100, interactive_layer_lr=0.15, batch_size=-1, early_stop="diff") hetero_nn_0.add_bottom_model( Dense(units=3, input_shape=(10, ), activation="relu", kernel_initializer=initializers.Constant(value=1))) hetero_nn_0.set_interactve_layer( Dense(units=2, input_shape=(2, ), kernel_initializer=initializers.Constant(value=1))) hetero_nn_0.add_top_model( Dense(units=1, input_shape=(2, ), activation="sigmoid", kernel_initializer=initializers.Constant(value=1))) hetero_nn_0.compile(optimizer=optimizers.SGD(lr=0.15), metrics=["AUC"], loss="binary_crossentropy") hetero_nn_1 = HeteroNN(name="hetero_nn_1") evaluation_0 = Evaluation(name="evaluation_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)) 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(model=hetero_nn_0.output.model)) pipeline.add_component(evaluation_0, data=Data(data=hetero_nn_0.output.data)) pipeline.compile() pipeline.fit(backend=backend, work_mode=work_mode) print(pipeline.get_component("hetero_nn_0").get_summary()) 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] hosts = parties.host 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=hosts, arbiter=arbiter) reader_0 = Reader(name="reader_0") reader_0.get_party_instance(role='guest', party_id=guest).component_param(table=guest_train_data) reader_0.get_party_instance(role='host', party_id=hosts).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=hosts).component_param(with_label=False) intersection_0 = Intersection(name="intersection_0") sample_weight_0 = SampleWeight(name="sample_weight_0") sample_weight_0.get_party_instance(role='guest', party_id=guest).component_param(need_run=True, class_weight="balanced") sample_weight_0.get_party_instance(role='host', party_id=hosts).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)
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 DataTransform components data_transform_0 = DataTransform( name="data_transform_0") # start component numbering at 0 # get DataTransform party instance of guest data_transform_0_guest_party_instance = data_transform_0.get_party_instance( role='guest', party_id=guest) # configure DataTransform for guest data_transform_0_guest_party_instance.component_param( with_label=True, output_format="dense") # get and configure DataTransform party instance of host data_transform_0.get_party_instance( role='host', party_id=hosts).component_param(with_label=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(data_transform_0, data=Data(data=reader_0.output.data)) pipeline.add_component(scale_0, data=Data(data=data_transform_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] 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") hetero_linr_0 = HeteroSSHELinR(name="hetero_linr_0", penalty="None", optimizer="sgd", tol=0.001, alpha=0.01, max_iter=20, early_stop="weight_diff", batch_size=-1, learning_rate=0.15, decay=0.0, decay_sqrt=False, init_param={"init_method": "zeros"}, cv_param={ "n_splits": 5, "shuffle": False, "random_seed": 42, "need_cv": True }) pipeline.add_component(reader_0) pipeline.add_component(data_transform_0, data=Data(data=reader_0.output.data)) pipeline.add_component(intersection_0, data=Data(data=data_transform_0.output.data)) pipeline.add_component(hetero_linr_0, data=Data(train_data=intersection_0.output.data)) pipeline.compile() pipeline.fit()
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] 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) 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_nn_0 = HeteroNN(name="hetero_nn_0", epochs=100, interactive_layer_lr=0.15, batch_size=-1, early_stop="diff") guest_nn_0 = hetero_nn_0.get_party_instance(role='guest', party_id=guest) guest_nn_0.add_bottom_model( Dense(units=3, input_shape=(9, ), activation="relu", kernel_initializer=initializers.Constant(value=1))) guest_nn_0.set_interactve_layer( Dense(units=2, input_shape=(2, ), kernel_initializer=initializers.Constant(value=1))) guest_nn_0.add_top_model( Dense(units=4, input_shape=(2, ), activation="softmax", kernel_initializer=initializers.Constant(value=1))) host_nn_0 = hetero_nn_0.get_party_instance(role='host', party_id=host) host_nn_0.add_bottom_model( Dense(units=3, input_shape=(9, ), activation="relu", kernel_initializer=initializers.Constant(value=1))) host_nn_0.set_interactve_layer( Dense(units=2, input_shape=(2, ), kernel_initializer=initializers.Constant(value=1))) hetero_nn_0.compile(optimizer=optimizers.Adam(lr=0.15), loss="categorical_crossentropy") hetero_nn_1 = HeteroNN(name="hetero_nn_1") evaluation_0 = Evaluation(name="evaluation_0", eval_type="multi") 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_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(model=hetero_nn_0.output.model)) pipeline.add_component(evaluation_0, data=Data(data=hetero_nn_0.output.data)) pipeline.compile() pipeline.fit() print(pipeline.get_component("hetero_nn_0").get_summary()) print(pipeline.get_component("evaluation_0").get_summary())
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) 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(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 = pipeline.get_component("evaluation_0").get_summary() 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="./breast_lr_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 == "default_credit_homo_guest.csv": guest_data_table = 'default_credit_guest' host_data_table = 'default_credit_host1' elif data_set == 'breast_homo_guest.csv': guest_data_table = 'breast_homo_guest' host_data_table = 'breast_homo_host' elif data_set == 'give_credit_homo_guest.csv': guest_data_table = 'give_credit_homo_guest' host_data_table = 'give_credit_homo_host' elif data_set == 'epsilon_5k_homo_guest.csv': guest_data_table = 'epsilon_5k_homo_guest' host_data_table = 'epsilon_5k_homo_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 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=True) lr_param = {} config_param = { "penalty": param["penalty"], "max_iter": param["max_iter"], "alpha": param["alpha"], "learning_rate": param["learning_rate"], "optimizer": param.get("optimizer", "sgd"), "batch_size": param.get("batch_size", -1), "init_param": { "init_method": param.get("init_method", 'random_uniform') }, "encrypt_param": { "method": None } } lr_param.update(config_param) print(f"lr_param: {lr_param}, data_set: {data_set}") homo_lr_0 = HomoLR(name='homo_lr_0', **lr_param) evaluation_0 = Evaluation(name='evaluation_0', eval_type="binary") evaluation_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)) pipeline.add_component(homo_lr_0, data=Data(train_data=dataio_0.output.data)) 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 data_summary = { "train": { "guest": guest_train_data["name"], "host": host_train_data["name"] }, "test": { "guest": guest_train_data["name"], "host": host_train_data["name"] } } result_summary = pipeline.get_component("evaluation_0").get_summary() 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": "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, arbiter=arbiter) reader_0 = Reader(name="reader_0") 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) dataio_0 = DataIO(name="dataio_0") dataio_0.get_party_instance(role='guest', party_id=guest).algorithm_param( with_label=True, label_name="motor_speed", label_type="float", output_format="dense") dataio_0.get_party_instance( role='host', party_id=host).algorithm_param(with_label=False) intersection_0 = Intersection(name="intersection_0") hetero_data_split_0 = HeteroDataSplit(name="hetero_data_split_0", stratified=True, test_size=0.3, validate_size=0.2, split_points=[0.0, 0.2]) hetero_linr_0 = HeteroLinR( name="hetero_linr_0", penalty="L2", optimizer="sgd", tol=0.001, alpha=0.01, max_iter=10, 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"}) hetero_linr_1 = HeteroLinR() 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_data_split_0, data=Data(data=intersection_0.output.data)) pipeline.add_component( hetero_linr_0, data=Data(train_data=hetero_data_split_0.output.data.train_data, validate_data=hetero_data_split_0.output.data.validate_data)) pipeline.add_component( hetero_linr_1, data=Data(test_data=hetero_data_split_0.output.data.test_data), model=Model(model=hetero_linr_0.output.model)) pipeline.compile() pipeline.fit(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] 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 DataTransform components data_transform_0 = DataTransform( name="data_transform_0") # start component numbering at 0 # get DataTransform party instance of guest data_transform_0_guest_party_instance = data_transform_0.get_party_instance( role="guest", party_id=guest) # configure DataTransform for guest data_transform_0_guest_party_instance.component_param( with_label=True, output_format="dense") # get and configure DataTransform party instance of host data_transform_0.get_party_instance( role="host", party_id=host).component_param(with_label=False) # define Intersection components intersection_0 = Intersection(name="intersection_0", 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(data_transform_0, data=Data(data=reader_0.output.data)) # set data input sources of intersection components pipeline.add_component(intersection_0, data=Data(data=data_transform_0.output.data)) 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 pipeline.fit()
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] # data sets guest_train_data = { "name": "breast_hetero_guest", "namespace": f"experiment{namespace}" } host_train_data = { "name": "breast_hetero_host", "namespace": f"experiment{namespace}" } # init pipeline pipeline = PipeLine().set_initiator(role="guest", party_id=guest).set_roles( guest=guest, host=host, ) # set data reader and data-io reader_0 = Reader(name="reader_0") reader_0.get_party_instance( role="guest", party_id=guest).component_param(table=guest_train_data) reader_0.get_party_instance( role="host", party_id=host).component_param(table=host_train_data) data_transform_0 = DataTransform(name="data_transform_0") data_transform_0.get_party_instance( role="guest", party_id=guest).component_param(with_label=True, output_format="dense") data_transform_0.get_party_instance( role="host", party_id=host).component_param(with_label=False) # data intersect component intersect_0 = Intersection(name="intersection_0") # secure boost component hetero_secure_boost_0 = HeteroSecureBoost( name="hetero_secure_boost_0", num_trees=3, task_type="classification", objective_param={"objective": "cross_entropy"}, encrypt_param={"method": "Paillier"}, tree_param={"max_depth": 3}, validation_freqs=1, cv_param={ "need_cv": True, "n_splits": 5, "shuffle": False, "random_seed": 103 }) pipeline.add_component(reader_0) pipeline.add_component(data_transform_0, data=Data(data=reader_0.output.data)) pipeline.add_component(intersect_0, data=Data(data=data_transform_0.output.data)) pipeline.add_component(hetero_secure_boost_0, data=Data(train_data=intersect_0.output.data)) pipeline.compile() pipeline.fit() print("fitting hetero secureboost done, result:") print(pipeline.get_component("hetero_secure_boost_0").get_summary())
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] guest_train_data = { "name": "breast_hetero_host", "namespace": f"experiment_sid{namespace}" } host_train_data = { "name": "breast_hetero_guest", "namespace": f"experiment_sid{namespace}" } # initialize pipeline pipeline = PipeLine() # set job initiator pipeline.set_initiator(role="guest", party_id=guest) # set participants information pipeline.set_roles(guest=guest, host=host) # 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) data_transform_0 = DataTransform(name="datatransform_0", with_match_id=True) 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=True) param = { "security_level": 0.5, "oblivious_transfer_protocol": "OT_Hauck", "commutative_encryption": "CommutativeEncryptionPohligHellman", "non_committing_encryption": "aes", "dh_params": { "key_length": 1024 }, "raw_retrieval": False, "target_cols": ["x0", "x3"] } secure_information_retrieval_0 = SecureInformationRetrieval( name="secure_information_retrieval_0", **param) # add components to pipeline, in order of task execution. pipeline.add_component(reader_0) pipeline.add_component(data_transform_0, data=Data(data=reader_0.output.data)) pipeline.add_component(secure_information_retrieval_0, data=Data(data=data_transform_0.output.data)) # compile pipeline once finished adding modules, this step will form conf and dsl files for running job pipeline.compile() # fit model pipeline.fit()
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] 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}" } 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).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="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_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 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()
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": "vehicle_scale_homo_guest", "namespace": f"experiment{namespace}" } guest_validate_data = { "name": "vehicle_scale_homo_test", "namespace": f"experiment{namespace}" } host_train_data = { "name": "vehicle_scale_homo_host", "namespace": f"experiment{namespace}" } host_validate_data = { "name": "vehicle_scale_homo_test", "namespace": f"experiment{namespace}" } pipeline = PipeLine().set_initiator( role='guest', party_id=guest).set_roles(guest=guest, host=host, arbiter=arbiter) data_transform_0, data_transform_1 = DataTransform( name="data_transform_0"), DataTransform(name='data_transform_1') reader_0, reader_1 = Reader(name="reader_0"), Reader(name='reader_1') reader_0.get_party_instance( role='guest', party_id=guest).component_param(table=guest_train_data) reader_0.get_party_instance( role='host', party_id=host).component_param(table=host_train_data) data_transform_0.get_party_instance( role='guest', party_id=guest).component_param(with_label=True, output_format="dense") data_transform_0.get_party_instance( role='host', party_id=host).component_param(with_label=True, output_format="dense") reader_1.get_party_instance( role='guest', party_id=guest).component_param(table=guest_validate_data) reader_1.get_party_instance( role='host', party_id=host).component_param(table=host_validate_data) data_transform_1.get_party_instance( role='guest', party_id=guest).component_param(with_label=True, output_format="dense") data_transform_1.get_party_instance( role='host', party_id=host).component_param(with_label=True, output_format="dense") homo_secureboost_0 = HomoSecureBoost( name="homo_secureboost_0", num_trees=3, task_type='classification', objective_param={"objective": "cross_entropy"}, tree_param={"max_depth": 3}, validation_freqs=1) evaluation_0 = Evaluation(name='evaluation_0', eval_type='multi') pipeline.add_component(reader_0) pipeline.add_component(data_transform_0, data=Data(data=reader_0.output.data)) pipeline.add_component(reader_1) pipeline.add_component(data_transform_1, data=Data(data=reader_1.output.data), model=Model(data_transform_0.output.model)) pipeline.add_component(homo_secureboost_0, data=Data( train_data=data_transform_0.output.data, validate_data=data_transform_1.output.data)) pipeline.add_component(evaluation_0, data=Data(homo_secureboost_0.output.data)) pipeline.compile() pipeline.fit()
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] 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", output_format="sparse") data_transform_0.get_party_instance( role='guest', party_id=guest).component_param(with_label=True, label_name="doctorco", label_type="float") 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=2, alpha=100.0, batch_size=-1, learning_rate=0.01, exposure_colname="exposure", optimizer="rmsprop", penalty="L2", decay_sqrt=False, tol=0.001, init_param={"init_method": "zeros"}, 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(evaluation_0, data=Data(data=hetero_poisson_0.output.data)) pipeline.compile() pipeline.fit()
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, 2], "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": "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", method="min_max_scale", mode="cap", feat_upper=1, feat_lower=0) hetero_feature_binning_0 = HeteroFeatureBinning( name="hetero_feature_binning_0") hetero_feature_selection_0 = HeteroFeatureSelection( name="hetero_feature_selection_0") one_hot_0 = OneHotEncoder(name="one_hot_0") hetero_lr_0 = HeteroLR(name="hetero_lr_0", penalty="L2", optimizer="rmsprop", tol=1e-5, init_param={"init_method": "random_uniform"}, alpha=0.01, max_iter=10, early_stop="diff", batch_size=320, learning_rate=0.15) evaluation_0 = Evaluation(name="evaluation_0") pipeline.add_component(reader_0) pipeline.add_component(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(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) print(pipeline.get_component("evaluation_0").get_summary())
def main(config="../../config.yaml", namespace=""): if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] 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=""): # 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_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 job_parameters = JobParameters(backend=backend, work_mode=work_mode) pipeline.fit(job_parameters) # 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": "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) data_transform_0 = DataTransform(name="data_transform_0") data_transform_0.get_party_instance( role='guest', party_id=guest).component_param( with_label=True, output_format="dense", label_type="int", label_name="y") data_transform_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(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(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() pipeline.fit() # predict pipeline.deploy_component([data_transform_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.data_transform_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()
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": "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).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": ["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(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 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 guest_train_data = { "name": "breast_hetero_guest", "namespace": "experiment" } guest_test_data = { "name": "breast_hetero_guest", "namespace": "experiment" } host_train_data = { "name": "mock_tag_hetero_host", "namespace": "experiment" } host_test_data = { "name": "mock_tag_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) # 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": False, "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": ["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') one_hot_encoder_0 = OneHotEncoder(name="one_hot_encoder_0") one_hot_encoder_1 = OneHotEncoder(name="one_hot_encoder_1") one_hot_encoder_0.get_party_instance( role='guest', party_id=guest).component_param(need_run=False) one_hot_encoder_0.get_party_instance(role='host', party_id=host) one_hot_encoder_1.get_party_instance( role='guest', party_id=guest).component_param(need_run=False) one_hot_encoder_1.get_party_instance(role='host', party_id=host) 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": "iterativeAffine" }, "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)) pipeline.add_component( one_hot_encoder_0, data=Data(data=hetero_feature_selection_0.output.data)) pipeline.add_component( one_hot_encoder_1, data=Data(data=hetero_feature_selection_1.output.data), model=Model(one_hot_encoder_0.output.model)) # set train & validate data of hetero_secureboost_0 component pipeline.add_component(hetero_secureboost_0, data=Data( train_data=one_hot_encoder_0.output.data, validate_data=one_hot_encoder_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 job_parameters = JobParameters(backend=backend, work_mode=work_mode) pipeline.fit(job_parameters) # 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] guest_train_data = { "name": "vehicle_scale_hetero_guest", "namespace": f"experiment{namespace}" } guest_validate_data = { "name": "vehicle_scale_hetero_guest", "namespace": f"experiment{namespace}" } host_train_data = { "name": "vehicle_scale_hetero_host", "namespace": f"experiment{namespace}" } host_validate_data = { "name": "vehicle_scale_hetero_host", "namespace": f"experiment{namespace}" } pipeline = PipeLine().set_initiator(role='guest', party_id=guest).set_roles(guest=guest, host=host) data_transform_0, data_transform_1 = DataTransform( name="data_transform_0"), DataTransform(name='data_transform_1') reader_0, reader_1 = Reader(name="reader_0"), Reader(name='reader_1') reader_0.get_party_instance( role='guest', party_id=guest).component_param(table=guest_train_data) reader_0.get_party_instance( role='host', party_id=host).component_param(table=host_train_data) data_transform_0.get_party_instance( role='guest', party_id=guest).component_param(with_label=True, output_format="dense") data_transform_0.get_party_instance( role='host', party_id=host).component_param(with_label=False, output_format="dense") reader_1.get_party_instance( role='guest', party_id=guest).component_param(table=guest_validate_data) reader_1.get_party_instance( role='host', party_id=host).component_param(table=host_validate_data) data_transform_1.get_party_instance( role='guest', party_id=guest).component_param(with_label=True, output_format="dense") data_transform_1.get_party_instance( role='host', party_id=host).component_param(with_label=True, output_format="dense") intersection_0 = Intersection(name="intersection_0") intersection_1 = Intersection(name="intersection_1") param = { "method": "quantile", "optimal_binning_param": { "metric_method": "gini", "min_bin_pct": 0.05, "max_bin_pct": 0.8, "init_bucket_method": "quantile", "init_bin_nums": 100, "mixture": True }, "compress_thres": 10000, "head_size": 10000, "error": 0.001, "bin_num": 10, "bin_indexes": -1, "bin_names": None, "category_indexes": [0, 1, 2], "category_names": None, "adjustment_factor": 0.5, "local_only": False, "transform_param": { "transform_cols": -1, "transform_names": None, "transform_type": "bin_num" } } hetero_feature_binning_0 = HeteroFeatureBinning( name="hetero_feature_binning_0", **param) hetero_feature_binning_1 = HeteroFeatureBinning( name='hetero_feature_binning_1') pipeline.add_component(reader_0) pipeline.add_component(data_transform_0, data=Data(data=reader_0.output.data)) pipeline.add_component(reader_1) pipeline.add_component(data_transform_1, data=Data(data=reader_1.output.data), model=Model(data_transform_0.output.model)) pipeline.add_component(intersection_0, data=Data(data=data_transform_0.output.data)) pipeline.add_component(intersection_1, data=Data(data=data_transform_1.output.data)) pipeline.add_component(hetero_feature_binning_0, data=Data(data=intersection_0.output.data)) pipeline.add_component(hetero_feature_binning_1, data=Data(data=intersection_1.output.data), model=Model(hetero_feature_binning_0.output.model)) pipeline.compile() pipeline.fit() # predict # deploy required components pipeline.deploy_component( [data_transform_0, intersection_0, hetero_feature_binning_0]) predict_pipeline = PipeLine() # add data reader onto predict pipeline predict_pipeline.add_component(reader_1) # add selected components from train pipeline onto predict pipeline # specify data source predict_pipeline.add_component( pipeline, data=Data(predict_input={ pipeline.data_transform_0.input.data: reader_1.output.data })) # run predict model predict_pipeline.predict()