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="normal") feature_scale_0.get_party_instance(role='guest', party_id=guest).component_param(feat_upper=[1, 2, 1, 1, 0.5, 1, 2, 2, 1, 1]) 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=""): # 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_sid{namespace}" } host_train_data = { "name": "breast_hetero_host", "namespace": f"experiment_sid{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", with_match_id=True) 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") feature_scale_0 = FeatureScale(name='feature_scale_0', method="standard_scale", need_run=True) binning_param = { "method": "quantile", "compress_thres": 10000, "head_size": 10000, "error": 0.001, "bin_num": 10, "bin_indexes": -1, "adjustment_factor": 0.5, "local_only": False, "need_run": True, "transform_param": { "transform_cols": -1, "transform_type": "bin_num" } } hetero_feature_binning_0 = HeteroFeatureBinning( name='hetero_feature_binning_0', **binning_param) statistic_0 = DataStatistics(name='statistic_0', statistics=["95%"]) pearson_0 = HeteroPearson(name='pearson_0', column_indexes=-1) onehot_0 = OneHotEncoder(name='onehot_0') selection_param = { "name": "hetero_feature_selection_0", "select_col_indexes": -1, "select_names": [], "filter_methods": [ "manually", "unique_value", "iv_filter", "coefficient_of_variation_value_thres", "outlier_cols" ], "manually_param": { "filter_out_indexes": [0, 1, 2], "filter_out_names": ["x3"] }, "unique_param": { "eps": 1e-06 }, "iv_param": { "metrics": ["iv", "iv", "iv"], "filter_type": ["threshold", "top_k", "top_percentile"], "threshold": [0.001, 100, 0.99] }, "variance_coe_param": { "value_threshold": 0.3 }, "outlier_param": { "percentile": 0.95, "upper_threshold": 2.0 } } hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param) lr_param = { "name": "hetero_lr_0", "penalty": "L2", "optimizer": "rmsprop", "tol": 0.0001, "alpha": 0.01, "max_iter": 30, "early_stop": "diff", "batch_size": 320, "learning_rate": 0.15, "init_param": { "init_method": "zeros" }, "sqn_param": { "update_interval_L": 3, "memory_M": 5, "sample_size": 5000, "random_seed": None }, "cv_param": { "n_splits": 5, "shuffle": False, "random_seed": 103, "need_cv": False } } hetero_lr_0 = HeteroLR(**lr_param) evaluation_0 = Evaluation(name='evaluation_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)) pipeline.add_component(feature_scale_0, data=Data(data=intersection_0.output.data)) pipeline.add_component(hetero_feature_binning_0, data=Data(data=feature_scale_0.output.data)) pipeline.add_component(statistic_0, data=Data(data=feature_scale_0.output.data)) pipeline.add_component(pearson_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), model=Model(isometric_model=[ hetero_feature_binning_0.output.model, statistic_0.output.model ])) pipeline.add_component( onehot_0, data=Data(data=hetero_feature_selection_0.output.data)) pipeline.add_component(hetero_lr_0, data=Data(train_data=onehot_0.output.data)) pipeline.add_component(evaluation_0, data=Data(data=hetero_lr_0.output.data)) pipeline.compile() pipeline.fit()
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") selection_param = { "select_col_indexes": -1, "filter_methods": ["manually"] } hetero_feature_selection_0 = HeteroFeatureSelection( name="hetero_feature_selection_0", **selection_param) hetero_feature_selection_0.get_party_instance( role='guest', party_id=guest).component_param( manually_param={"left_col_indexes": [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)) pipeline.add_component(hetero_feature_selection_0, data=Data(data=intersection_0.output.data)) lr_param = { "name": "hetero_sshe_lr_0", "penalty": None, "optimizer": "sgd", "tol": 0.0001, "alpha": 0.01, "max_iter": 30, "early_stop": "diff", "batch_size": -1, "learning_rate": 0.15, "init_param": { "init_method": "random_uniform" }, "reveal_strategy": "encrypted_reveal_in_host", "reveal_every_iter": False } hetero_sshe_lr_0 = HeteroSSHELR(**lr_param) pipeline.add_component( hetero_sshe_lr_0, data=Data(train_data=hetero_feature_selection_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()) return pipeline
def make_normal_dsl(config, namespace, selection_param, is_multi_host=False, host_dense_output=True, **kwargs): parties = config.parties guest = parties.guest[0] if is_multi_host: hosts = parties.host else: hosts = parties.host[0] guest_train_data = { "name": "breast_hetero_guest", "namespace": f"experiment{namespace}" } host_train_data = { "name": "breast_hetero_host", "namespace": f"experiment{namespace}" } guest_eval_data = { "name": "breast_hetero_guest", "namespace": f"experiment{namespace}" } host_eval_data = { "name": "breast_hetero_host", "namespace": f"experiment{namespace}" } # initialize pipeline pipeline = PipeLine() # set job initiator pipeline.set_initiator(role='guest', party_id=guest) # set participants information pipeline.set_roles(guest=guest, host=hosts) # define Reader components to read in data reader_0 = Reader(name="reader_0") # configure Reader for guest reader_0.get_party_instance( role='guest', party_id=guest).component_param(table=guest_train_data) # configure Reader for host reader_0.get_party_instance( role='host', party_id=hosts).component_param(table=host_train_data) # define 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=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)) last_cpn = intersection_0 selection_include_model = [] if 'binning_param' in kwargs: hetero_feature_binning_0 = HeteroFeatureBinning( **kwargs['binning_param']) pipeline.add_component(hetero_feature_binning_0, data=Data(data=last_cpn.output.data)) selection_include_model.append(hetero_feature_binning_0) # last_cpn = hetero_feature_binning_0 if 'statistic_param' in kwargs: # print(f"param: {kwargs['statistic_param']}, kwargs: {kwargs}") statistic_0 = DataStatistics(**kwargs['statistic_param']) pipeline.add_component(statistic_0, data=Data(data=last_cpn.output.data)) # last_cpn = statistic_0 selection_include_model.append(statistic_0) if 'psi_param' in kwargs: reader_1 = Reader(name="reader_1") reader_1.get_party_instance( role='guest', party_id=guest).component_param(table=guest_eval_data) reader_1.get_party_instance( role='host', party_id=hosts).component_param(table=host_eval_data) data_transform_1 = DataTransform(name="data_transform_1") intersection_1 = Intersection(name="intersection_1") 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_1, data=Data(data=data_transform_1.output.data)) psi_0 = PSI(**kwargs['psi_param']) pipeline.add_component(psi_0, data=Data( train_data=intersection_0.output.data, validate_data=intersection_1.output.data)) # last_cpn = statistic_0 selection_include_model.append(psi_0) if 'sbt_param' in kwargs: secureboost_0 = HeteroSecureBoost(**kwargs['sbt_param']) pipeline.add_component( secureboost_0, data=Data(train_data=intersection_0.output.data)) selection_include_model.append(secureboost_0) if "fast_sbt_param" in kwargs: fast_sbt_0 = HeteroFastSecureBoost(**kwargs['fast_sbt_param']) pipeline.add_component( fast_sbt_0, data=Data(train_data=intersection_0.output.data)) selection_include_model.append(fast_sbt_0) hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param) pipeline.add_component( hetero_feature_selection_0, data=Data(data=intersection_0.output.data), model=Model( isometric_model=[x.output.model for x in selection_include_model])) # compile pipeline once finished adding modules, this step will form conf and dsl files for running job pipeline.compile() return pipeline
def make_single_predict_pipeline(config, namespace, selection_param, is_multi_host=False, **kwargs): parties = config.parties guest = parties.guest[0] if is_multi_host: hosts = parties.host else: hosts = parties.host[0] guest_train_data = { "name": "breast_hetero_guest", "namespace": f"experiment{namespace}" } host_train_data = { "name": "breast_hetero_host", "namespace": f"experiment{namespace}" } guest_eval_data = { "name": "breast_hetero_guest", "namespace": f"experiment{namespace}" } host_eval_data = { "name": "breast_hetero_host", "namespace": f"experiment{namespace}" } # initialize pipeline pipeline = PipeLine() # set job initiator pipeline.set_initiator(role='guest', party_id=guest) # set participants information pipeline.set_roles(guest=guest, host=hosts) # define Reader components to read in data reader_0 = Reader(name="reader_0") # configure Reader for guest reader_0.get_party_instance( role='guest', party_id=guest).component_param(table=guest_train_data) # configure Reader for host reader_0.get_party_instance( role='host', party_id=hosts).component_param(table=host_train_data) # define 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=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)) reader_1 = Reader(name="reader_1") reader_1.get_party_instance( role='guest', party_id=guest).component_param(table=guest_eval_data) reader_1.get_party_instance( role='host', party_id=hosts).component_param(table=host_eval_data) data_transform_1 = DataTransform(name="data_transform_1") intersection_1 = Intersection(name="intersection_1") 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_1, data=Data(data=data_transform_1.output.data)) sample_0 = FederatedSample(name='sample_0', fractions=0.9) pipeline.add_component(sample_0, data=Data(data=intersection_0.output.data)) if "binning_param" not in kwargs: raise ValueError("Binning_param is needed") hetero_feature_binning_0 = HeteroFeatureBinning(**kwargs['binning_param']) pipeline.add_component(hetero_feature_binning_0, data=Data(data=sample_0.output.data)) hetero_feature_binning_1 = HeteroFeatureBinning( name='hetero_feature_binning_1') pipeline.add_component(hetero_feature_binning_1, data=Data(data=intersection_1.output.data), model=Model(hetero_feature_binning_0.output.model)) hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param) pipeline.add_component( hetero_feature_selection_0, data=Data(data=hetero_feature_binning_0.output.data), model=Model(isometric_model=[hetero_feature_binning_0.output.model])) hetero_feature_selection_1 = HeteroFeatureSelection( name='hetero_feature_selection_1') pipeline.add_component( hetero_feature_selection_1, data=Data(data=hetero_feature_binning_1.output.data), model=Model(hetero_feature_selection_0.output.model)) scale_0 = FeatureScale(name='scale_0') scale_1 = FeatureScale(name='scale_1') pipeline.add_component( scale_0, data=Data(data=hetero_feature_selection_0.output.data)) pipeline.add_component( scale_1, data=Data(data=hetero_feature_selection_1.output.data), model=Model(scale_0.output.model)) pipeline.compile() return pipeline
def make_feature_engineering_dsl(config, namespace, lr_param, is_multi_host=False, has_validate=False, is_cv=False, is_ovr=False): parties = config.parties guest = parties.guest[0] if is_multi_host: hosts = parties.host else: hosts = parties.host[0] arbiter = parties.arbiter[0] if is_ovr: guest_train_data = {"name": "vehicle_scale_hetero_guest", "namespace": f"experiment{namespace}"} host_train_data = {"name": "vehicle_scale_hetero_host", "namespace": f"experiment{namespace}"} guest_eval_data = {"name": "vehicle_scale_hetero_guest", "namespace": f"experiment{namespace}"} host_eval_data = {"name": "vehicle_scale_hetero_host", "namespace": f"experiment{namespace}"} else: guest_train_data = {"name": "breast_hetero_guest", "namespace": f"experiment{namespace}"} host_train_data = {"name": "breast_hetero_host", "namespace": f"experiment{namespace}"} guest_eval_data = {"name": "breast_hetero_guest", "namespace": f"experiment{namespace}"} host_eval_data = {"name": "breast_hetero_host", "namespace": f"experiment{namespace}"} train_line = [] # initialize pipeline pipeline = PipeLine() # set job initiator pipeline.set_initiator(role='guest', party_id=guest) # set participants information pipeline.set_roles(guest=guest, host=hosts, arbiter=arbiter) # define Reader components to read in data reader_0 = Reader(name="reader_0") # configure Reader for guest reader_0.get_party_instance(role='guest', party_id=guest).component_param(table=guest_train_data) # configure Reader for host reader_0.get_party_instance(role='host', party_id=hosts).component_param(table=host_train_data) # define 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=False) train_line.append(data_transform_0) # 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)) train_line.append(intersection_0) feature_scale_0 = FeatureScale(name='feature_scale_0', method="standard_scale", need_run=True) pipeline.add_component(feature_scale_0, data=Data(data=intersection_0.output.data)) train_line.append(feature_scale_0) binning_param = { "method": "quantile", "compress_thres": 10000, "head_size": 10000, "error": 0.001, "bin_num": 10, "bin_indexes": -1, "adjustment_factor": 0.5, "local_only": False, "need_run": True, "transform_param": { "transform_cols": -1, "transform_type": "bin_num" } } hetero_feature_binning_0 = HeteroFeatureBinning(name='hetero_feature_binning_0', **binning_param) pipeline.add_component(hetero_feature_binning_0, data=Data(data=feature_scale_0.output.data)) train_line.append(hetero_feature_binning_0) selection_param = { "select_col_indexes": -1, "filter_methods": [ "manually", "iv_value_thres", "iv_percentile" ], "manually_param": { "filter_out_indexes": None }, "iv_value_param": { "value_threshold": 1.0 }, "iv_percentile_param": { "percentile_threshold": 0.9 }, "need_run": True } hetero_feature_selection_0 = HeteroFeatureSelection(name='hetero_feature_selection_0', **selection_param) pipeline.add_component(hetero_feature_selection_0, data=Data(data=hetero_feature_binning_0.output.data), model=Model(isometric_model=[hetero_feature_binning_0.output.model])) train_line.append(hetero_feature_selection_0) onehot_param = { "transform_col_indexes": -1, "transform_col_names": None, "need_run": True } one_hot_encoder_0 = OneHotEncoder(name='one_hot_encoder_0', **onehot_param) pipeline.add_component(one_hot_encoder_0, data=Data(data=hetero_feature_selection_0.output.data)) train_line.append(one_hot_encoder_0) last_cpn = None if has_validate: reader_1 = Reader(name="reader_1") reader_1.get_party_instance(role='guest', party_id=guest).component_param(table=guest_eval_data) reader_1.get_party_instance(role='host', party_id=hosts).component_param(table=host_eval_data) pipeline.add_component(reader_1) last_cpn = reader_1 for cpn in train_line: cpn_name = cpn.name new_name = "_".join(cpn_name.split('_')[:-1] + ['1']) validate_cpn = type(cpn)(name=new_name) if hasattr(cpn.output, "model"): pipeline.add_component(validate_cpn, data=Data(data=last_cpn.output.data), model=Model(cpn.output.model)) else: pipeline.add_component(validate_cpn, data=Data(data=last_cpn.output.data)) last_cpn = validate_cpn hetero_lr_0 = HeteroLR(**lr_param) if has_validate: pipeline.add_component(hetero_lr_0, data=Data(train_data=one_hot_encoder_0.output.data, validate_data=last_cpn.output.data)) else: pipeline.add_component(hetero_lr_0, data=Data(train_data=one_hot_encoder_0.output.data)) if is_cv: pipeline.compile() return pipeline evaluation_data = [hetero_lr_0.output.data] if has_validate: hetero_lr_1 = HeteroLR(name='hetero_lr_1') pipeline.add_component(hetero_lr_1, data=Data(test_data=last_cpn.output.data), model=Model(hetero_lr_0.output.model)) evaluation_data.append(hetero_lr_1.output.data) evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary") pipeline.add_component(evaluation_0, data=Data(data=evaluation_data)) pipeline.compile() return pipeline
def 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": "breast_hetero_guest", "namespace": "experiment" } guest_test_data = { "name": "breast_hetero_guest", "namespace": "experiment" } host_train_data = { "name": "breast_hetero_host_tag_value", "namespace": "experiment" } host_test_data = { "name": "breast_hetero_host_tag_value", "namespace": "experiment" } # initialize pipeline pipeline = PipeLine() # set job initiator pipeline.set_initiator(role='guest', party_id=guest) # set participants information pipeline.set_roles(guest=guest, host=host) # define Reader components to read in data reader_0 = Reader(name="reader_0") reader_1 = Reader(name="reader_1") # configure Reader for guest reader_0.get_party_instance( role='guest', party_id=guest).component_param(table=guest_train_data) reader_1.get_party_instance( role='guest', party_id=guest).component_param(table=guest_test_data) # configure Reader for host reader_0.get_party_instance( role='host', party_id=host).component_param(table=host_train_data) reader_1.get_party_instance( role='host', party_id=host).component_param(table=host_test_data) # define DataIO components dataio_0 = DataIO(name="dataio_0") # start component numbering at 0 dataio_1 = DataIO(name="dataio_1") # start component numbering at 1 param = { "with_label": True, "label_name": "y", "label_type": "int", "output_format": "dense", "missing_fill": True, "missing_fill_method": "mean", "outlier_replace": False, "outlier_replace_method": "designated", "outlier_replace_value": 0.66, "outlier_impute": "-9999" } # get DataIO party instance of guest dataio_0_guest_party_instance = dataio_0.get_party_instance(role='guest', party_id=guest) # configure DataIO for guest dataio_0_guest_party_instance.component_param(**param) # get and configure DataIO party instance of host dataio_1.get_party_instance(role='guest', party_id=guest).component_param(**param) param = { "input_format": "tag", "with_label": False, "tag_with_value": True, "delimitor": ";", "output_format": "dense" } dataio_0.get_party_instance(role='host', party_id=host).component_param(**param) dataio_1.get_party_instance(role='host', party_id=host).component_param(**param) # define Intersection components intersection_0 = Intersection(name="intersection_0", intersect_method="raw") intersection_1 = Intersection(name="intersection_1", intersect_method="raw") param = { "name": 'hetero_feature_binning_0', "method": 'optimal', "optimal_binning_param": { "metric_method": "iv", "init_bucket_method": "quantile" }, "bin_indexes": -1 } hetero_feature_binning_0 = HeteroFeatureBinning(**param) statistic_0 = DataStatistics(name='statistic_0') param = { "name": 'hetero_feature_selection_0', "filter_methods": ["manually", "unique_value", "iv_filter", "statistic_filter"], "manually_param": { "filter_out_indexes": [1, 2], "filter_out_names": ["x2", "x3"] }, "unique_param": { "eps": 1e-6 }, "iv_param": { "metrics": ["iv", "iv"], "filter_type": ["top_k", "threshold"], "take_high": [True, True], "threshold": [10, 0.1] }, "statistic_param": { "metrics": ["coefficient_of_variance", "skewness"], "filter_type": ["threshold", "threshold"], "take_high": [True, False], "threshold": [0.001, -0.01] }, "select_col_indexes": -1 } hetero_feature_selection_0 = HeteroFeatureSelection(**param) hetero_feature_selection_1 = HeteroFeatureSelection( name='hetero_feature_selection_1') param = { "task_type": "classification", "learning_rate": 0.1, "num_trees": 10, "subsample_feature_rate": 0.5, "n_iter_no_change": False, "tol": 0.0002, "bin_num": 50, "objective_param": { "objective": "cross_entropy" }, "encrypt_param": { "method": "paillier" }, "predict_param": { "threshold": 0.5 }, "tree_param": { "max_depth": 2 }, "cv_param": { "n_splits": 5, "shuffle": False, "random_seed": 103, "need_cv": False }, "validation_freqs": 2, "early_stopping_rounds": 5, "metrics": ["auc", "ks"] } hetero_secureboost_0 = HeteroSecureBoost(name='hetero_secureboost_0', **param) evaluation_0 = Evaluation(name='evaluation_0') # add components to pipeline, in order of task execution pipeline.add_component(reader_0) pipeline.add_component(reader_1) pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data)) pipeline.add_component(dataio_1, data=Data(data=reader_1.output.data), model=Model(dataio_0.output.model)) # set data input sources of intersection components pipeline.add_component(intersection_0, data=Data(data=dataio_0.output.data)) pipeline.add_component(intersection_1, data=Data(data=dataio_1.output.data)) pipeline.add_component(hetero_feature_binning_0, data=Data(data=intersection_0.output.data)) pipeline.add_component(statistic_0, data=Data(data=intersection_0.output.data)) pipeline.add_component( hetero_feature_selection_0, data=Data(data=intersection_0.output.data), model=Model(isometric_model=[ hetero_feature_binning_0.output.model, statistic_0.output.model ])) pipeline.add_component(hetero_feature_selection_1, data=Data(data=intersection_1.output.data), model=Model( hetero_feature_selection_0.output.model)) # set train & validate data of hetero_secureboost_0 component pipeline.add_component( hetero_secureboost_0, data=Data(train_data=hetero_feature_selection_0.output.data, validate_data=hetero_feature_selection_1.output.data)) pipeline.add_component(evaluation_0, data=Data(data=hetero_secureboost_0.output.data)) # compile pipeline once finished adding modules, this step will form conf and dsl files for running job pipeline.compile() # fit model pipeline.fit() # query component summary print(pipeline.get_component("hetero_secureboost_0").get_summary())
def main(config="../../config.yaml", namespace=""): 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 = { "model_id": "guest-10000#host-9999#model", "model_version": "202108301602196678300", "component_name": "hetero_feature_binning_0", "step_index": None } model_loader_0 = ModelLoader(name="model_loader_0", **param) selection_param = { "name": "hetero_feature_selection_0", "select_col_indexes": -1, "select_names": [], "filter_methods": ["iv_filter"], "iv_param": { "metrics": ["iv", "iv", "iv"], "filter_type": ["threshold", "top_k", "top_percentile"], "take_high": True, "threshold": [0.03, 15, 0.7], "host_thresholds": [[0.15], None, None], "select_federated": True } } hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param) pipeline.add_component(reader_0) pipeline.add_component(data_transform_0, data=Data(data=reader_0.output.data)) pipeline.add_component(intersection_0, data=Data(data=data_transform_0.output.data)) pipeline.add_component(model_loader_0) pipeline.add_component( hetero_feature_selection_0, data=Data(data=intersection_0.output.data), model=Model(isometric_model=model_loader_0.output.model)) pipeline.compile() pipeline.fit()
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] guest_train_data = { "name": "breast_hetero_guest", "namespace": f"experiment{namespace}" } host_train_data = { "name": "breast_hetero_host", "namespace": f"experiment{namespace}" } pipeline = PipeLine().set_initiator(role='guest', party_id=guest).set_roles(guest=guest, host=host) reader_0 = Reader(name="reader_0") reader_0.get_party_instance( role='guest', party_id=guest).component_param(table=guest_train_data) reader_0.get_party_instance( role='host', party_id=host).component_param(table=host_train_data) data_transform_0 = DataTransform(name="data_transform_0") data_transform_0.get_party_instance( role='guest', party_id=guest).component_param(with_label=True) data_transform_0.get_party_instance( role='host', party_id=host).component_param(with_label=False) intersection_0 = Intersection(name="intersection_0") hetero_pearson_0 = HeteroPearson(name='hetero_pearson_0', column_indexes=-1) hetero_binning_0 = HeteroFeatureBinning(name='hetero_binning_0') selection_param = { "name": "hetero_feature_selection_0", "select_col_indexes": -1, "select_names": [], "filter_methods": ["vif_filter", "correlation_filter"], "vif_param": { "threshold": 5 }, "correlation_param": { "threshold": 0.5, "select_federated": False } } hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param) pipeline.add_component(reader_0) pipeline.add_component(data_transform_0, data=Data(data=reader_0.output.data)) pipeline.add_component(intersection_0, data=Data(data=data_transform_0.output.data)) pipeline.add_component(hetero_binning_0, data=Data(data=intersection_0.output.data)) pipeline.add_component(hetero_pearson_0, data=Data(data=intersection_0.output.data)) pipeline.add_component( hetero_feature_selection_0, data=Data(data=intersection_0.output.data), model=Model(isometric_model=[ hetero_pearson_0.output.model, hetero_binning_0.output.model ])) pipeline.compile() pipeline.fit()
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] arbiter = parties.arbiter[0] backend = config.backend work_mode = config.work_mode guest_train_data = { "name": "breast_hetero_guest", "namespace": f"experiment{namespace}" } host_train_data = { "name": "breast_hetero_host", "namespace": f"experiment{namespace}" } pipeline = PipeLine().set_initiator( role='guest', party_id=guest).set_roles(guest=guest, host=host, arbiter=arbiter) reader_0 = Reader(name="reader_0") reader_0.get_party_instance( role='guest', party_id=guest).component_param(table=guest_train_data) reader_0.get_party_instance( role='host', party_id=host).component_param(table=host_train_data) dataio_0 = DataIO(name="dataio_0") dataio_0.get_party_instance(role='guest', party_id=guest).component_param( with_label=True, label_name="y", label_type="int", output_format="dense") dataio_0.get_party_instance( role='host', party_id=host).component_param(with_label=False) intersection_0 = Intersection(name="intersection_0") binning_param = { "name": 'hetero_feature_binning_0', "method": "quantile", "compress_thres": 10000, "head_size": 10000, "error": 0.001, "bin_num": 10, "bin_indexes": -1, "bin_names": None, "category_indexes": None, "category_names": None, "adjustment_factor": 0.5, "local_only": False, "transform_param": { "transform_cols": -1, "transform_names": None, "transform_type": "bin_num" } } selection_param = { "name": "hetero_feature_selection_0", "select_col_indexes": -1, "select_names": [], "filter_methods": ["iv_value_thres"], "iv_value_param": { "value_threshold": 0.1 } } hetero_feature_binning_0 = HeteroFeatureBinning(**binning_param) hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param) sample_weight_0 = SampleWeight(name="sample_weight_0") sample_weight_0.get_party_instance( role='guest', party_id=guest).component_param(need_run=True, class_weight={ "0": 1, "1": 2 }) sample_weight_0.get_party_instance( role='host', party_id=host).component_param(need_run=False) feature_scale_0 = FeatureScale(name="feature_scale_0", method="standard_scale", need_run=True) hetero_lr_0 = HeteroLR(name="hetero_lr_0", optimizer="nesterov_momentum_sgd", tol=0.001, alpha=0.01, max_iter=20, early_stop="weight_diff", batch_size=-1, learning_rate=0.15, init_param={"init_method": "zeros"}) evaluation_0 = Evaluation(name="evaluation_0", eval_type="binary", pos_label=1) # evaluation_0.get_party_instance(role='host', party_id=host).component_param(need_run=False) pipeline.add_component(reader_0) pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data)) pipeline.add_component(intersection_0, data=Data(data=dataio_0.output.data)) pipeline.add_component(sample_weight_0, data=Data(data=intersection_0.output.data)) pipeline.add_component(hetero_feature_binning_0, data=Data(data=sample_weight_0.output.data)) pipeline.add_component( hetero_feature_selection_0, data=Data(data=hetero_feature_binning_0.output.data), model=Model(isometric_model=[hetero_feature_binning_0.output.model])) pipeline.add_component(feature_scale_0, data=Data(hetero_feature_selection_0.output.data)) pipeline.add_component(hetero_lr_0, data=Data(train_data=feature_scale_0.output.data)) pipeline.add_component(evaluation_0, data=Data(data=hetero_lr_0.output.data)) pipeline.compile() job_parameters = JobParameters(backend=backend, work_mode=work_mode) pipeline.fit(job_parameters)
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] guest_train_data = {"name": "vehicle_scale_hetero_guest", "namespace": f"experiment{namespace}"} guest_validate_data = {"name": "vehicle_scale_hetero_guest", "namespace": f"experiment{namespace}"} host_train_data = {"name": "vehicle_scale_hetero_host", "namespace": f"experiment{namespace}"} host_validate_data = {"name": "vehicle_scale_hetero_host", "namespace": f"experiment{namespace}"} pipeline = PipeLine().set_initiator(role='guest', party_id=guest).set_roles(guest=guest, host=host) data_transform_0, data_transform_1 = DataTransform(name="data_transform_0"), DataTransform(name='data_transform_1') reader_0, reader_1 = Reader(name="reader_0"), Reader(name='reader_1') reader_0.get_party_instance(role='guest', party_id=guest).component_param(table=guest_train_data) reader_0.get_party_instance(role='host', party_id=host).component_param(table=host_train_data) data_transform_0.get_party_instance( role='guest', party_id=guest).component_param( with_label=True, output_format="dense") data_transform_0.get_party_instance( role='host', party_id=host).component_param( with_label=False, output_format="dense") reader_1.get_party_instance(role='guest', party_id=guest).component_param(table=guest_validate_data) reader_1.get_party_instance(role='host', party_id=host).component_param(table=host_validate_data) data_transform_1.get_party_instance( role='guest', party_id=guest).component_param( with_label=True, output_format="dense") data_transform_1.get_party_instance( role='host', party_id=host).component_param( with_label=True, output_format="dense") intersection_0 = Intersection(name="intersection_0") intersection_1 = Intersection(name="intersection_1") param = { "method": "quantile", "optimal_binning_param": { "metric_method": "gini", "min_bin_pct": 0.05, "max_bin_pct": 0.8, "init_bucket_method": "quantile", "init_bin_nums": 100, "mixture": True }, "compress_thres": 10000, "head_size": 10000, "error": 0.001, "bin_num": 10, "bin_indexes": -1, "bin_names": None, "category_indexes": [0, 1, 2], "category_names": None, "adjustment_factor": 0.5, "local_only": False, "transform_param": { "transform_cols": -1, "transform_names": None, "transform_type": "bin_num" } } hetero_feature_binning_0 = HeteroFeatureBinning(name="hetero_feature_binning_0", **param) hetero_feature_binning_1 = HeteroFeatureBinning(name='hetero_feature_binning_1') selection_param = { "name": "hetero_feature_selection_0", "select_col_indexes": -1, "select_names": [], "filter_methods": ["iv_filter"], "iv_param": { "metrics": ["iv", "iv", "iv"], "filter_type": ["threshold", "top_k", "top_percentile"], "threshold": [2, 10, 0.9], "mul_class_merge_type": ["max", "min", "average"] }} hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param) hetero_feature_selection_1 = HeteroFeatureSelection(name="hetero_feature_selection_1") pipeline.add_component(reader_0) pipeline.add_component(data_transform_0, data=Data(data=reader_0.output.data)) pipeline.add_component(reader_1) pipeline.add_component( data_transform_1, data=Data( data=reader_1.output.data), model=Model( data_transform_0.output.model)) pipeline.add_component(intersection_0, data=Data(data=data_transform_0.output.data)) pipeline.add_component(intersection_1, data=Data(data=data_transform_1.output.data)) pipeline.add_component(hetero_feature_binning_0, data=Data(data=intersection_0.output.data)) pipeline.add_component(hetero_feature_binning_1, data=Data(data=intersection_1.output.data), model=Model(hetero_feature_binning_0.output.model)) pipeline.add_component(hetero_feature_selection_0, data=Data(data=hetero_feature_binning_0.output.data), model=Model(isometric_model=hetero_feature_binning_0.output.model)) pipeline.add_component(hetero_feature_selection_1, data=Data(data=hetero_feature_binning_1.output.data), model=Model(hetero_feature_selection_0.output.model)) pipeline.compile() pipeline.fit() # predict # deploy required components pipeline.deploy_component([data_transform_0, intersection_0, hetero_feature_selection_0]) predict_pipeline = PipeLine() # add data reader onto predict pipeline predict_pipeline.add_component(reader_1) # add selected components from train pipeline onto predict pipeline # specify data source predict_pipeline.add_component( pipeline, data=Data( predict_input={ pipeline.data_transform_0.input.data: reader_1.output.data})) # run predict model predict_pipeline.predict()
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] arbiter = parties.arbiter[0] guest_train_data = { "name": "breast_hetero_guest", "namespace": f"experiment{namespace}" } host_train_data = { "name": "breast_hetero_host", "namespace": f"experiment{namespace}" } pipeline = PipeLine().set_initiator( role='guest', party_id=guest).set_roles(guest=guest, host=host, arbiter=arbiter) reader_0 = Reader(name="reader_0") reader_0.get_party_instance( role='guest', party_id=guest).component_param(table=guest_train_data) reader_0.get_party_instance( role='host', party_id=host).component_param(table=host_train_data) reader_1 = Reader(name="reader_1") reader_1.get_party_instance( role='guest', party_id=guest).component_param(table=guest_train_data) reader_1.get_party_instance( role='host', party_id=host).component_param(table=host_train_data) reader_2 = Reader(name="reader_2") reader_2.get_party_instance( role='guest', party_id=guest).component_param(table=guest_train_data) reader_2.get_party_instance( role='host', party_id=host).component_param(table=host_train_data) data_transform_0 = DataTransform(name="data_transform_0") data_transform_0.get_party_instance( role='guest', party_id=guest).component_param(with_label=True, missing_fill=True, outlier_replace=True) data_transform_0.get_party_instance( role='host', party_id=host).component_param(with_label=False, missing_fill=True, outlier_replace=True) data_transform_1 = DataTransform(name="data_transform_1") data_transform_2 = DataTransform(name="data_transform_2") intersection_0 = Intersection(name="intersection_0") intersection_1 = Intersection(name="intersection_1") intersection_2 = Intersection(name="intersection_2") union_0 = Union(name="union_0") federated_sample_0 = FederatedSample(name="federated_sample_0", mode="stratified", method="downsample", fractions=[[0, 1.0], [1, 1.0]]) feature_scale_0 = FeatureScale(name="feature_scale_0") feature_scale_1 = FeatureScale(name="feature_scale_1") hetero_feature_binning_0 = HeteroFeatureBinning( name="hetero_feature_binning_0") hetero_feature_binning_1 = HeteroFeatureBinning( name="hetero_feature_binning_1") hetero_feature_selection_0 = HeteroFeatureSelection( name="hetero_feature_selection_0") hetero_feature_selection_1 = HeteroFeatureSelection( name="hetero_feature_selection_1") one_hot_0 = OneHotEncoder(name="one_hot_0") one_hot_1 = OneHotEncoder(name="one_hot_1") hetero_lr_0 = HeteroLR(name="hetero_lr_0", penalty="L2", optimizer="rmsprop", tol=1e-5, init_param={"init_method": "random_uniform"}, alpha=0.01, max_iter=3, early_stop="diff", batch_size=320, learning_rate=0.15) hetero_lr_1 = HeteroLR(name="hetero_lr_1") hetero_lr_2 = HeteroLR(name="hetero_lr_2", penalty="L2", optimizer="rmsprop", tol=1e-5, init_param={"init_method": "random_uniform"}, alpha=0.01, max_iter=3, early_stop="diff", batch_size=320, learning_rate=0.15, cv_param={ "n_splits": 5, "shuffle": True, "random_seed": 103, "need_cv": True }) hetero_sshe_lr_0 = HeteroSSHELR( name="hetero_sshe_lr_0", reveal_every_iter=True, reveal_strategy="respectively", penalty="L2", optimizer="rmsprop", tol=1e-5, batch_size=320, learning_rate=0.15, init_param={"init_method": "random_uniform"}, alpha=0.01, max_iter=3) hetero_sshe_lr_1 = HeteroSSHELR(name="hetero_sshe_lr_1") local_baseline_0 = LocalBaseline(name="local_baseline_0", model_name="LogisticRegression", model_opts={ "penalty": "l2", "tol": 0.0001, "C": 1.0, "fit_intercept": True, "solver": "lbfgs", "max_iter": 5, "multi_class": "ovr" }) local_baseline_0.get_party_instance( role='guest', party_id=guest).component_param(need_run=True) local_baseline_0.get_party_instance( role='host', party_id=host).component_param(need_run=False) local_baseline_1 = LocalBaseline(name="local_baseline_1") hetero_secureboost_0 = HeteroSecureBoost(name="hetero_secureboost_0", num_trees=3) hetero_secureboost_1 = HeteroSecureBoost(name="hetero_secureboost_1") hetero_secureboost_2 = HeteroSecureBoost(name="hetero_secureboost_2", num_trees=3, cv_param={ "shuffle": False, "need_cv": True }) hetero_linr_0 = HeteroLinR(name="hetero_linr_0", penalty="L2", optimizer="sgd", tol=0.001, alpha=0.01, max_iter=3, early_stop="weight_diff", batch_size=-1, learning_rate=0.15, decay=0.0, decay_sqrt=False, init_param={"init_method": "zeros"}, floating_point_precision=23) hetero_linr_1 = HeteroLinR(name="hetero_linr_1") hetero_sshe_linr_0 = HeteroSSHELinR(name="hetero_sshe_linr_0", max_iter=5, early_stop="weight_diff", batch_size=-1) hetero_sshe_linr_1 = HeteroSSHELinR(name="hetero_sshe_linr_1") hetero_poisson_0 = HeteroPoisson(name="hetero_poisson_0", early_stop="weight_diff", max_iter=10, alpha=100.0, batch_size=-1, learning_rate=0.01, optimizer="rmsprop", exposure_colname="exposure", decay_sqrt=False, tol=0.001, init_param={"init_method": "zeros"}, penalty="L2") hetero_poisson_1 = HeteroPoisson(name="hetero_poisson_1") hetero_sshe_poisson_0 = HeteroSSHEPoisson(name="hetero_sshe_poisson_0", max_iter=5) hetero_sshe_poisson_1 = HeteroSSHEPoisson(name="hetero_sshe_poisson_1") evaluation_0 = Evaluation(name="evaluation_0") evaluation_1 = Evaluation(name="evaluation_1") evaluation_2 = Evaluation(name="evaluation_2") pipeline.add_component(reader_0) pipeline.add_component(reader_1) pipeline.add_component(reader_2) pipeline.add_component(data_transform_0, data=Data(data=reader_0.output.data)) pipeline.add_component(data_transform_1, data=Data(data=reader_1.output.data), model=Model(model=data_transform_0.output.model)) pipeline.add_component(data_transform_2, data=Data(data=reader_2.output.data), model=Model(model=data_transform_0.output.model)) pipeline.add_component(intersection_0, data=Data(data=data_transform_0.output.data)) pipeline.add_component(intersection_1, data=Data(data=data_transform_1.output.data)) pipeline.add_component(intersection_2, data=Data(data=data_transform_2.output.data)) pipeline.add_component( union_0, data=Data( data=[intersection_0.output.data, intersection_2.output.data])) pipeline.add_component(federated_sample_0, data=Data(data=intersection_1.output.data)) pipeline.add_component(feature_scale_0, data=Data(data=union_0.output.data)) pipeline.add_component(feature_scale_1, data=Data(data=federated_sample_0.output.data), model=Model(model=feature_scale_0.output.model)) pipeline.add_component(hetero_feature_binning_0, data=Data(data=feature_scale_0.output.data)) pipeline.add_component( hetero_feature_binning_1, data=Data(data=feature_scale_1.output.data), model=Model(model=hetero_feature_binning_0.output.model)) pipeline.add_component( hetero_feature_selection_0, data=Data(data=hetero_feature_binning_0.output.data)) pipeline.add_component( hetero_feature_selection_1, data=Data(data=hetero_feature_binning_1.output.data), model=Model(model=hetero_feature_selection_0.output.model)) pipeline.add_component( one_hot_0, data=Data(data=hetero_feature_selection_0.output.data)) pipeline.add_component( one_hot_1, data=Data(data=hetero_feature_selection_1.output.data), model=Model(model=one_hot_0.output.model)) pipeline.add_component(hetero_lr_0, data=Data(train_data=one_hot_0.output.data)) pipeline.add_component(hetero_lr_1, data=Data(test_data=one_hot_1.output.data), model=Model(model=hetero_lr_0.output.model)) pipeline.add_component(hetero_lr_2, data=Data(train_data=one_hot_0.output.data)) pipeline.add_component(local_baseline_0, data=Data(train_data=one_hot_0.output.data)) pipeline.add_component(local_baseline_1, data=Data(test_data=one_hot_1.output.data), model=Model(model=local_baseline_0.output.model)) pipeline.add_component(hetero_sshe_lr_0, data=Data(train_data=one_hot_0.output.data)) pipeline.add_component(hetero_sshe_lr_1, data=Data(test_data=one_hot_1.output.data), model=Model(model=hetero_sshe_lr_0.output.model)) pipeline.add_component(hetero_secureboost_0, data=Data(train_data=one_hot_0.output.data)) pipeline.add_component( hetero_secureboost_1, data=Data(test_data=one_hot_1.output.data), model=Model(model=hetero_secureboost_0.output.model)) pipeline.add_component(hetero_secureboost_2, data=Data(train_data=one_hot_0.output.data)) pipeline.add_component(hetero_linr_0, data=Data(train_data=one_hot_0.output.data)) pipeline.add_component(hetero_linr_1, data=Data(test_data=one_hot_1.output.data), model=Model(model=hetero_linr_0.output.model)) pipeline.add_component(hetero_sshe_linr_0, data=Data(train_data=one_hot_0.output.data)) pipeline.add_component(hetero_sshe_linr_1, data=Data(test_data=one_hot_1.output.data), model=Model(model=hetero_sshe_linr_0.output.model)) pipeline.add_component(hetero_poisson_0, data=Data(train_data=one_hot_0.output.data)) pipeline.add_component(hetero_poisson_1, data=Data(test_data=one_hot_1.output.data), model=Model(model=hetero_poisson_0.output.model)) pipeline.add_component( evaluation_0, data=Data(data=[ hetero_lr_0.output.data, hetero_lr_1.output.data, hetero_sshe_lr_0.output.data, hetero_sshe_lr_1.output.data, local_baseline_0.output.data, local_baseline_1.output.data ])) pipeline.add_component(hetero_sshe_poisson_0, data=Data(train_data=one_hot_0.output.data)) pipeline.add_component( hetero_sshe_poisson_1, data=Data(test_data=one_hot_1.output.data), model=Model(model=hetero_sshe_poisson_0.output.model)) pipeline.add_component( evaluation_1, data=Data(data=[ hetero_linr_0.output.data, hetero_linr_1.output.data, hetero_sshe_linr_0.output.data, hetero_linr_1.output.data ])) pipeline.add_component( evaluation_2, data=Data(data=[ hetero_poisson_0.output.data, hetero_poisson_1.output.data, hetero_sshe_poisson_0.output.data, hetero_sshe_poisson_1.output.data ])) pipeline.compile() pipeline.fit() print(pipeline.get_component("evaluation_0").get_summary()) print(pipeline.get_component("evaluation_1").get_summary()) print(pipeline.get_component("evaluation_2").get_summary())
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] 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).component_param(table=guest_train_data) reader_0.get_party_instance( role='host', party_id=host).component_param(table=host_train_data) dataio_0 = DataIO(name="dataio_0") dataio_0.get_party_instance( role='guest', party_id=guest).component_param(with_label=True) dataio_0.get_party_instance( role='host', party_id=host).component_param(with_label=False) intersection_0 = Intersection(name="intersection_0") hetero_pearson_0 = HeteroPearson(name='hetero_pearson_0', column_indexes=-1) selection_param = { "name": "hetero_feature_selection_0", "select_col_indexes": -1, "select_names": [], "filter_methods": ["vif_filter"], "vif_param": { "threshold": 5 } } hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param) 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_pearson_0, data=Data(train_data=intersection_0.output.data)) pipeline.add_component( hetero_feature_selection_0, data=Data(data=intersection_0.output.data), model=Model(isometric_model=hetero_pearson_0.output.model)) pipeline.compile() job_parameters = JobParameters(backend=backend, work_mode=work_mode) pipeline.fit(job_parameters)
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] 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).component_param(table=guest_train_data) reader_0.get_party_instance( role='host', party_id=host).component_param(table=host_train_data) dataio_0 = DataIO(name="dataio_0") dataio_0.get_party_instance( role='guest', party_id=guest).component_param(with_label=True) dataio_0.get_party_instance( role='host', party_id=host).component_param(with_label=False) intersection_0 = Intersection(name="intersection_0") hetero_pearson_0 = HeteroPearson(name='hetero_pearson_0', column_indexes=-1) hetero_binning_0 = HeteroFeatureBinning(name='hetero_binning_0') selection_param = { "name": "hetero_feature_selection_0", "select_col_indexes": -1, "select_names": [], "filter_methods": ["vif_filter", "correlation_filter"], "vif_param": { "threshold": 5 }, "correlation_param": { "threshold": 0.5, "select_federated": False } } hetero_feature_selection_0 = HeteroFeatureSelection(**selection_param) pipeline.add_component(reader_0) pipeline.add_component(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_binning_0, data=Data(data=intersection_0.output.data)) pipeline.add_component(hetero_pearson_0, data=Data(data=intersection_0.output.data)) pipeline.add_component( hetero_feature_selection_0, data=Data(data=intersection_0.output.data), model=Model(isometric_model=[ hetero_pearson_0.output.model, hetero_binning_0.output.model ])) pipeline.compile() job_parameters = JobParameters(backend=backend, work_mode=work_mode) pipeline.fit(job_parameters) # predict # deploy required components pipeline.deploy_component([ dataio_0, intersection_0, hetero_binning_0, hetero_feature_selection_0 ]) predict_pipeline = PipeLine() # add data reader onto predict pipeline predict_pipeline.add_component(reader_0) # add selected components from train pipeline onto predict pipeline # specify data source predict_pipeline.add_component( pipeline, data=Data( predict_input={pipeline.dataio_0.input.data: reader_0.output.data })) # run predict model predict_pipeline.predict(job_parameters)
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] arbiter = parties.arbiter[0] guest_train_data_0 = {"name": "breast_hetero_guest", "namespace": "experiment"} guest_train_data_1 = {"name": "breast_hetero_guest", "namespace": "experiment"} guest_test_data_0 = {"name": "breast_hetero_guest", "namespace": "experiment"} guest_test_data_1 = {"name": "breast_hetero_guest", "namespace": "experiment"} host_train_data_0 = {"name": "breast_hetero_host_tag_value", "namespace": "experiment"} host_train_data_1 = {"name": "breast_hetero_host_tag_value", "namespace": "experiment"} host_test_data_0 = {"name": "breast_hetero_host_tag_value", "namespace": "experiment"} host_test_data_1 = {"name": "breast_hetero_host_tag_value", "namespace": "experiment"} # initialize pipeline pipeline = PipeLine() # set job initiator pipeline.set_initiator(role='guest', party_id=guest) # set participants information pipeline.set_roles(guest=guest, host=host, arbiter=arbiter) # define Reader components to read in data reader_0 = Reader(name="reader_0") reader_1 = Reader(name="reader_1") reader_2 = Reader(name="reader_2") reader_3 = Reader(name="reader_3") # configure Reader for guest reader_0.get_party_instance(role='guest', party_id=guest).component_param(table=guest_train_data_0) reader_1.get_party_instance(role='guest', party_id=guest).component_param(table=guest_train_data_1) reader_2.get_party_instance(role='guest', party_id=guest).component_param(table=guest_test_data_0) reader_3.get_party_instance(role='guest', party_id=guest).component_param(table=guest_test_data_1) # configure Reader for host reader_0.get_party_instance(role='host', party_id=host).component_param(table=host_train_data_0) reader_1.get_party_instance(role='host', party_id=host).component_param(table=host_train_data_1) reader_2.get_party_instance(role='host', party_id=host).component_param(table=host_test_data_0) reader_3.get_party_instance(role='host', party_id=host).component_param(table=host_test_data_1) param = { "name": "union_0", "keep_duplicate": True } union_0 = Union(**param) param = { "name": "union_1", "keep_duplicate": True } union_1 = Union(**param) param = { "input_format": "tag", "with_label": False, "tag_with_value": True, "delimitor": ";", "output_format": "dense" } # define DataIO components dataio_0 = DataIO(name="dataio_0") # start component numbering at 0 dataio_1 = DataIO(name="dataio_1") # start component numbering at 1 # get DataIO party instance of guest dataio_0_guest_party_instance = dataio_0.get_party_instance(role='guest', party_id=guest) # configure DataIO for guest dataio_0_guest_party_instance.component_param(with_label=True, output_format="dense") # get and configure DataIO party instance of host dataio_0.get_party_instance(role='host', party_id=host).component_param(**param) dataio_1.get_party_instance(role='guest', party_id=guest).component_param(with_label=True) dataio_1.get_party_instance(role='host', party_id=host).component_param(**param) # define Intersection components intersection_0 = Intersection(name="intersection_0") intersection_1 = Intersection(name="intersection_1") param = { "name": 'hetero_feature_binning_0', "method": 'optimal', "optimal_binning_param": { "metric_method": "iv" }, "bin_indexes": -1 } hetero_feature_binning_0 = HeteroFeatureBinning(**param) statistic_0 = DataStatistics(name='statistic_0') param = { "name": 'hetero_feature_selection_0', "filter_methods": ["manually", "iv_filter", "statistic_filter"], "manually_param": { "filter_out_indexes": [1, 2], "filter_out_names": ["x2", "x3"] }, "iv_param": { "metrics": ["iv", "iv"], "filter_type": ["top_k", "threshold"], "take_high": [True, True], "threshold": [10, 0.01] }, "statistic_param": { "metrics": ["coefficient_of_variance", "skewness"], "filter_type": ["threshold", "threshold"], "take_high": [True, True], "threshold": [0.001, -0.01] }, "select_col_indexes": -1 } hetero_feature_selection_0 = HeteroFeatureSelection(**param) hetero_feature_selection_1 = HeteroFeatureSelection(name='hetero_feature_selection_1') param = { "name": "hetero_scale_0", "method": "standard_scale" } hetero_scale_0 = FeatureScale(**param) hetero_scale_1 = FeatureScale(name='hetero_scale_1') param = { "penalty": "L2", "validation_freqs": None, "early_stopping_rounds": None, "max_iter": 5 } hetero_lr_0 = HeteroLR(name='hetero_lr_0', **param) evaluation_0 = Evaluation(name='evaluation_0') # add components to pipeline, in order of task execution pipeline.add_component(reader_0) pipeline.add_component(reader_1) pipeline.add_component(reader_2) pipeline.add_component(reader_3) pipeline.add_component(union_0, data=Data(data=[reader_0.output.data, reader_1.output.data])) pipeline.add_component(union_1, data=Data(data=[reader_2.output.data, reader_3.output.data])) pipeline.add_component(dataio_0, data=Data(data=union_0.output.data)) pipeline.add_component(dataio_1, data=Data(data=union_1.output.data), model=Model(dataio_0.output.model)) # set data input sources of intersection components pipeline.add_component(intersection_0, data=Data(data=dataio_0.output.data)) pipeline.add_component(intersection_1, data=Data(data=dataio_1.output.data)) # set train & validate data of hetero_lr_0 component pipeline.add_component(hetero_feature_binning_0, data=Data(data=intersection_0.output.data)) pipeline.add_component(statistic_0, data=Data(data=intersection_0.output.data)) pipeline.add_component(hetero_feature_selection_0, data=Data(data=intersection_0.output.data), model=Model(isometric_model=[hetero_feature_binning_0.output.model, statistic_0.output.model])) pipeline.add_component(hetero_feature_selection_1, data=Data(data=intersection_1.output.data), model=Model(hetero_feature_selection_0.output.model)) pipeline.add_component(hetero_scale_0, data=Data(data=hetero_feature_selection_0.output.data)) pipeline.add_component(hetero_scale_1, data=Data(data=hetero_feature_selection_1.output.data), model=Model(hetero_scale_0.output.model)) # set train & validate data of hetero_lr_0 component pipeline.add_component(hetero_lr_0, data=Data(train_data=hetero_scale_0.output.data, validate_data=hetero_scale_1.output.data)) pipeline.add_component(evaluation_0, data=Data(data=[hetero_lr_0.output.data])) # compile pipeline once finished adding modules, this step will form conf and dsl files for running job pipeline.compile() # fit model pipeline.fit() # query component summary print(pipeline.get_component("hetero_lr_0").get_summary())
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] arbiter = parties.arbiter[0] guest_train_data = { "name": "breast_hetero_guest", "namespace": f"experiment{namespace}" } host_train_data = { "name": "breast_hetero_host", "namespace": f"experiment{namespace}" } pipeline = PipeLine().set_initiator( role='guest', party_id=guest).set_roles(guest=guest, host=host, arbiter=arbiter) reader_0 = Reader(name="reader_0") reader_0.get_party_instance( role='guest', party_id=guest).component_param(table=guest_train_data) reader_0.get_party_instance( role='host', party_id=host).component_param(table=host_train_data) data_transform_0 = DataTransform(name="data_transform_0") data_transform_0.get_party_instance( role='guest', party_id=guest).component_param(with_label=True, missing_fill=True, outlier_replace=True) data_transform_0.get_party_instance( role='host', party_id=host).component_param(with_label=False, missing_fill=True, outlier_replace=True) intersection_0 = Intersection(name="intersection_0") federated_sample_0 = FederatedSample(name="federated_sample_0", mode="stratified", method="upsample", fractions=[[0, 1.5], [1, 2.0]]) feature_scale_0 = FeatureScale(name="feature_scale_0") hetero_feature_binning_0 = HeteroFeatureBinning( name="hetero_feature_binning_0") hetero_feature_selection_0 = HeteroFeatureSelection( name="hetero_feature_selection_0") one_hot_0 = OneHotEncoder(name="one_hot_0") hetero_lr_0 = HeteroLR(name="hetero_lr_0", penalty="L2", optimizer="rmsprop", tol=1e-5, init_param={"init_method": "random_uniform"}, alpha=0.01, max_iter=10, early_stop="diff", batch_size=320, learning_rate=0.15) hetero_lr_1 = HeteroLR(name="hetero_lr_1", penalty="L2", optimizer="rmsprop", tol=1e-5, init_param={"init_method": "random_uniform"}, alpha=0.01, max_iter=10, early_stop="diff", batch_size=320, learning_rate=0.15, cv_param={ "n_splits": 5, "shuffle": True, "random_seed": 103, "need_cv": True }) hetero_secureboost_0 = HeteroSecureBoost(name="hetero_secureboost_0", num_trees=5, cv_param={ "shuffle": False, "need_cv": True }) hetero_secureboost_1 = HeteroSecureBoost(name="hetero_secureboost_1", num_trees=5) evaluation_0 = Evaluation(name="evaluation_0") evaluation_1 = Evaluation(name="evaluation_1") pipeline.add_component(reader_0) pipeline.add_component(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(federated_sample_0, data=Data(data=intersection_0.output.data)) pipeline.add_component(feature_scale_0, data=Data(data=federated_sample_0.output.data)) pipeline.add_component(hetero_feature_binning_0, data=Data(data=feature_scale_0.output.data)) pipeline.add_component( hetero_feature_selection_0, data=Data(data=hetero_feature_binning_0.output.data)) pipeline.add_component( one_hot_0, data=Data(data=hetero_feature_selection_0.output.data)) pipeline.add_component(hetero_lr_0, data=Data(train_data=one_hot_0.output.data)) pipeline.add_component(hetero_lr_1, data=Data(train_data=one_hot_0.output.data)) pipeline.add_component(hetero_secureboost_0, data=Data(train_data=one_hot_0.output.data)) pipeline.add_component(hetero_secureboost_1, data=Data(train_data=one_hot_0.output.data)) pipeline.add_component(evaluation_0, data=Data(data=hetero_lr_0.output.data)) pipeline.add_component(evaluation_1, data=Data(data=hetero_secureboost_1.output.data)) pipeline.compile() pipeline.fit() print(pipeline.get_component("evaluation_0").get_summary())
def main(config="../../config.yaml", namespace=""): # obtain config if isinstance(config, str): config = load_job_config(config) parties = config.parties guest = parties.guest[0] host = parties.host[0] arbiter = parties.arbiter[0] backend = config.backend work_mode = config.work_mode guest_train_data = { "name": "breast_hetero_guest", "namespace": "experiment" } guest_test_data = { "name": "breast_hetero_guest", "namespace": "experiment" } host_train_data = { "name": "breast_hetero_host_tag_value", "namespace": "experiment" } host_test_data = { "name": "breast_hetero_host_tag_value", "namespace": "experiment" } # initialize pipeline pipeline = PipeLine() # set job initiator pipeline.set_initiator(role='guest', party_id=guest) # set participants information pipeline.set_roles(guest=guest, host=host, arbiter=arbiter) # define Reader components to read in data reader_0 = Reader(name="reader_0") reader_1 = Reader(name="reader_1") # configure Reader for guest reader_0.get_party_instance( role='guest', party_id=guest).algorithm_param(table=guest_train_data) reader_1.get_party_instance( role='guest', party_id=guest).algorithm_param(table=guest_test_data) # configure Reader for host reader_0.get_party_instance( role='host', party_id=host).algorithm_param(table=host_train_data) reader_1.get_party_instance( role='host', party_id=host).algorithm_param(table=host_test_data) # define DataIO components dataio_0 = DataIO(name="dataio_0") # start component numbering at 0 dataio_1 = DataIO(name="dataio_1") # start component numbering at 1 param = { "with_label": True, "label_name": "y", "label_type": "int", "output_format": "dense", "missing_fill": True, "missing_fill_method": "mean", "outlier_replace": False, "outlier_replace_method": "designated", "outlier_replace_value": 0.66, "outlier_impute": "-9999" } # get DataIO party instance of guest dataio_0_guest_party_instance = dataio_0.get_party_instance(role='guest', party_id=guest) # configure DataIO for guest dataio_0_guest_party_instance.algorithm_param(**param) # get and configure DataIO party instance of host dataio_1.get_party_instance(role='guest', party_id=guest).algorithm_param(**param) param = { "input_format": "tag", "with_label": False, "tag_with_value": True, "delimitor": ";", "output_format": "dense" } dataio_0.get_party_instance(role='host', party_id=host).algorithm_param(**param) dataio_1.get_party_instance(role='host', party_id=host).algorithm_param(**param) # define Intersection components intersection_0 = Intersection(name="intersection_0", intersect_method="raw") intersection_1 = Intersection(name="intersection_1", intersect_method="raw") param = { "name": 'hetero_feature_binning_0', "method": 'optimal', "optimal_binning_param": { "metric_method": "iv", "init_bucket_method": "quantile" }, "bin_indexes": -1 } hetero_feature_binning_0 = HeteroFeatureBinning(**param) statistic_0 = DataStatistics(name='statistic_0') param = { "name": 'hetero_feature_selection_0', "filter_methods": ["manually", "unique_value", "iv_filter", "statistic_filter"], "manually_param": { "filter_out_indexes": [1, 2], "filter_out_names": ["x3", "x4"] }, "unique_param": { "eps": 1e-6 }, "iv_param": { "metrics": ["iv", "iv"], "filter_type": ["top_k", "threshold"], "take_high": [True, True], "threshold": [10, 0.1] }, "statistic_param": { "metrics": ["coefficient_of_variance", "skewness"], "filter_type": ["threshold", "threshold"], "take_high": [True, False], "threshold": [0.001, -0.01] }, "select_col_indexes": -1 } hetero_feature_selection_0 = HeteroFeatureSelection(**param) hetero_feature_selection_1 = HeteroFeatureSelection( name='hetero_feature_selection_1') param = {"name": "hetero_scale_0", "method": "standard_scale"} hetero_scale_0 = FeatureScale(**param) hetero_scale_1 = FeatureScale(name='hetero_scale_1') param = { "penalty": "L2", "optimizer": "nesterov_momentum_sgd", "tol": 1e-4, "alpha": 0.01, "max_iter": 5, "early_stop": "diff", "batch_size": -1, "learning_rate": 0.15, "init_param": { "init_method": "zeros" }, "validation_freqs": None, "early_stopping_rounds": None } hetero_lr_0 = HeteroLR(name='hetero_lr_0', **param) evaluation_0 = Evaluation(name='evaluation_0') # add components to pipeline, in order of task execution pipeline.add_component(reader_0) pipeline.add_component(reader_1) pipeline.add_component(dataio_0, data=Data(data=reader_0.output.data)) pipeline.add_component(dataio_1, data=Data(data=reader_1.output.data), model=Model(dataio_0.output.model)) # set data input sources of intersection components pipeline.add_component(intersection_0, data=Data(data=dataio_0.output.data)) pipeline.add_component(intersection_1, data=Data(data=dataio_1.output.data)) # set train & validate data of hetero_lr_0 component pipeline.add_component(hetero_feature_binning_0, data=Data(data=intersection_0.output.data)) pipeline.add_component(statistic_0, data=Data(data=intersection_0.output.data)) pipeline.add_component( hetero_feature_selection_0, data=Data(data=intersection_0.output.data), model=Model(isometric_model=[ hetero_feature_binning_0.output.model, statistic_0.output.model ])) pipeline.add_component(hetero_feature_selection_1, data=Data(data=intersection_1.output.data), model=Model( hetero_feature_selection_0.output.model)) pipeline.add_component( hetero_scale_0, data=Data(data=hetero_feature_selection_0.output.data)) pipeline.add_component( hetero_scale_1, data=Data(data=hetero_feature_selection_1.output.data), model=Model(hetero_scale_0.output.model)) # set train & validate data of hetero_lr_0 component pipeline.add_component(hetero_lr_0, data=Data(train_data=hetero_scale_0.output.data, validate_data=hetero_scale_1.output.data)) pipeline.add_component(evaluation_0, data=Data(data=[hetero_lr_0.output.data])) # compile pipeline once finished adding modules, this step will form conf and dsl files for running job pipeline.compile() # fit model pipeline.fit(backend=backend, work_mode=work_mode) # query component summary print(pipeline.get_component("hetero_lr_0").get_summary())
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 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") param = { "name": 'hetero_feature_binning_0', "method": 'optimal', "optimal_binning_param": { "metric_method": "iv" }, "bin_indexes": -1 } hetero_feature_binning_0 = HeteroFeatureBinning(**param) param = { "name": 'hetero_feature_selection_0', "filter_methods": ["manually", "iv_filter"], "manually_param": { "filter_out_indexes": [1] }, "iv_param": { "metrics": ["iv", "iv"], "filter_type": ["top_k", "threshold"], "take_high": [True, True], "threshold": [10, 0.001] }, "select_col_indexes": -1 } hetero_feature_selection_0 = HeteroFeatureSelection(**param) 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(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)) # 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(hetero_feature_selection_0, data=Data(data=intersection_0.output.data), model=Model(isometric_model=hetero_feature_binning_0.output.model)) pipeline.add_component(hetero_kmeans_0, data=Data(train_data=hetero_feature_selection_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 pipeline.fit() # query component summary print(pipeline.get_component("hetero_kmeans_0").get_summary())